From 27ae69b230c1e04fb80bd374cb811a936a87f97b Mon Sep 17 00:00:00 2001 From: Carl Pearson Date: Tue, 10 Oct 2023 13:53:47 -0400 Subject: [PATCH] more results --- results/implicit_mapped_GPUWrHost.json | 1996 +++++++++++++- results/r1-1465528.out | 699 +++++ results/r10-1465527.out | 1690 ++++++++++++ results/r11-1465787.out | 162 ++ results/r12-1467862.out | 591 +++++ results/r2-1465529.out | 205 ++ results/r3-1465530.out | 3371 ++++++++++++++++++++++++ results/r4-1465531.out | 241 ++ results/r5-1465786.out | 205 ++ results/r6-1465533.out | 1546 +++++++++++ results/r7-1465534.out | 434 +++ results/r8-1465535.out | 31 + results/r9-1465536.out | 1402 ++++++++++ 13 files changed, 12572 insertions(+), 1 deletion(-) create mode 100644 results/r1-1465528.out create mode 100644 results/r10-1465527.out create mode 100644 results/r11-1465787.out create mode 100644 results/r12-1467862.out create mode 100644 results/r2-1465529.out create mode 100644 results/r3-1465530.out create mode 100644 results/r4-1465531.out create mode 100644 results/r5-1465786.out create mode 100644 results/r6-1465533.out create mode 100644 results/r7-1465534.out create mode 100644 results/r8-1465535.out create mode 100644 results/r9-1465536.out diff --git a/results/implicit_mapped_GPUWrHost.json b/results/implicit_mapped_GPUWrHost.json index 639133b..9d53d99 100644 --- a/results/implicit_mapped_GPUWrHost.json +++ b/results/implicit_mapped_GPUWrHost.json @@ -1197,4 +1197,1998 @@ "bytes_per_second": 9.9211867173143700e-05, "own_numa": NaN, "wr_gpu": NaN - } \ No newline at end of file + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "family_index": 0, + "per_family_instance_index": 7, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 21237, + "real_time": 3.2961222086962647e+04, + "cpu_time": 6.8156828977727593e+04, + "time_unit": "ns", + "bytes": 5.2428800000000000e+05, + "bytes_per_second": 1.5906206348076357e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "family_index": 0, + "per_family_instance_index": 7, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 21237, + "real_time": 3.2970548260706557e+04, + "cpu_time": 6.8216041531289651e+04, + "time_unit": "ns", + "bytes": 5.2428800000000000e+05, + "bytes_per_second": 1.5901707058503267e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "family_index": 0, + "per_family_instance_index": 7, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 21237, + "real_time": 3.2976801415748079e+04, + "cpu_time": 6.8193017281160210e+04, + "time_unit": "ns", + "bytes": 5.2428800000000000e+05, + "bytes_per_second": 1.5898691731503899e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "family_index": 0, + "per_family_instance_index": 7, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 21237, + "real_time": 3.2962047690767336e+04, + "cpu_time": 6.8210511560013256e+04, + "time_unit": "ns", + "bytes": 5.2428800000000000e+05, + "bytes_per_second": 1.5905807943687094e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "family_index": 0, + "per_family_instance_index": 7, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 21237, + "real_time": 3.2961580673439152e+04, + "cpu_time": 6.8164303055987184e+04, + "time_unit": "ns", + "bytes": 5.2428800000000000e+05, + "bytes_per_second": 1.5906033305692703e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 7, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 3.2966440025524753e+04, + "cpu_time": 6.8188140481235576e+04, + "time_unit": "ns", + "bytes": 5.2428800000000000e+05, + "bytes_per_second": 1.5903689277492664e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time_median", + "family_index": 0, + "per_family_instance_index": 7, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 3.2962047690767336e+04, + "cpu_time": 6.8193017281160210e+04, + "time_unit": "ns", + "bytes": 5.2428800000000000e+05, + "bytes_per_second": 1.5905807943687094e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 7, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 6.9708104316588475e+00, + "cpu_time": 2.6699016971253826e+01, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 3.3624216309558800e+06, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 7, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 2.1145171957486443e-04, + "cpu_time": 3.9154927503267262e-04, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 2.1142400183298796e-04, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "family_index": 0, + "per_family_instance_index": 8, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 13266, + "real_time": 5.2775078919960768e+04, + "cpu_time": 1.1250615535956579e+05, + "time_unit": "ns", + "bytes": 1.0485760000000000e+06, + "bytes_per_second": 1.9868771804022903e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "family_index": 0, + "per_family_instance_index": 8, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 13266, + "real_time": 5.2764586005406316e+04, + "cpu_time": 1.1262464458012964e+05, + "time_unit": "ns", + "bytes": 1.0485760000000000e+06, + "bytes_per_second": 1.9872722964083561e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "family_index": 0, + "per_family_instance_index": 8, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 13266, + "real_time": 5.2756615466702096e+04, + "cpu_time": 1.1279118181818175e+05, + "time_unit": "ns", + "bytes": 1.0485760000000000e+06, + "bytes_per_second": 1.9875725361150585e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "family_index": 0, + "per_family_instance_index": 8, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 13266, + "real_time": 5.2770204045635961e+04, + "cpu_time": 1.1296532948891872e+05, + "time_unit": "ns", + "bytes": 1.0485760000000000e+06, + "bytes_per_second": 1.9870607267184067e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "family_index": 0, + "per_family_instance_index": 8, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 13266, + "real_time": 5.2766645865699305e+04, + "cpu_time": 1.1294324981154836e+05, + "time_unit": "ns", + "bytes": 1.0485760000000000e+06, + "bytes_per_second": 1.9871947189306221e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 8, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 5.2766626060680908e+04, + "cpu_time": 1.1276611221166886e+05, + "time_unit": "ns", + "bytes": 1.0485760000000000e+06, + "bytes_per_second": 1.9871954917149471e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time_median", + "family_index": 0, + "per_family_instance_index": 8, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 5.2766645865699298e+04, + "cpu_time": 1.1279118181818177e+05, + "time_unit": "ns", + "bytes": 1.0485760000000000e+06, + "bytes_per_second": 1.9871947189306221e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 8, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 6.8670775134915960e+00, + "cpu_time": 1.9955224487373715e+02, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 2.5862411244738954e+06, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 8, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 1.3014054576077218e-04, + "cpu_time": 1.7696118183019864e-03, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 1.3014527937772104e-04, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "family_index": 0, + "per_family_instance_index": 9, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 7591, + "real_time": 9.2221364105251152e+04, + "cpu_time": 1.9643949598208437e+05, + "time_unit": "ns", + "bytes": 2.0971520000000000e+06, + "bytes_per_second": 2.2740414006526138e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "family_index": 0, + "per_family_instance_index": 9, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 7591, + "real_time": 9.2226256172176654e+04, + "cpu_time": 1.9653569661441131e+05, + "time_unit": "ns", + "bytes": 2.0971520000000000e+06, + "bytes_per_second": 2.2739207759716923e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "family_index": 0, + "per_family_instance_index": 9, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 7591, + "real_time": 9.2221411166539910e+04, + "cpu_time": 1.9642581860097559e+05, + "time_unit": "ns", + "bytes": 2.0971520000000000e+06, + "bytes_per_second": 2.2740402401919613e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "family_index": 0, + "per_family_instance_index": 9, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 7591, + "real_time": 9.2209142642536128e+04, + "cpu_time": 1.9642320129100201e+05, + "time_unit": "ns", + "bytes": 2.0971520000000000e+06, + "bytes_per_second": 2.2743428036522949e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "family_index": 0, + "per_family_instance_index": 9, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 7591, + "real_time": 9.2205963422872912e+04, + "cpu_time": 1.9643737755236329e+05, + "time_unit": "ns", + "bytes": 2.0971520000000000e+06, + "bytes_per_second": 2.2744212219572922e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 9, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 9.2216827501875363e+04, + "cpu_time": 1.9645231800816732e+05, + "time_unit": "ns", + "bytes": 2.0971520000000000e+06, + "bytes_per_second": 2.2741532884851711e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time_median", + "family_index": 0, + "per_family_instance_index": 9, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 9.2221364105251152e+04, + "cpu_time": 1.9643737755236329e+05, + "time_unit": "ns", + "bytes": 2.0971520000000000e+06, + "bytes_per_second": 2.2740414006526138e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 9, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 8.7689202473802528e+00, + "cpu_time": 4.7142378466514508e+01, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 2.1625518176820641e+06, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 9, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 9.5090239871914093e-05, + "cpu_time": 2.3996855290124198e-04, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 9.5092614408703931e-05, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "family_index": 0, + "per_family_instance_index": 10, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 4196, + "real_time": 1.6699423211059280e+05, + "cpu_time": 3.7165227216396388e+05, + "time_unit": "ns", + "bytes": 4.1943040000000000e+06, + "bytes_per_second": 2.5116460293205219e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "family_index": 0, + "per_family_instance_index": 10, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 4196, + "real_time": 1.6697093377642694e+05, + "cpu_time": 3.7121869470924750e+05, + "time_unit": "ns", + "bytes": 4.1943040000000000e+06, + "bytes_per_second": 2.5119964925249485e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "family_index": 0, + "per_family_instance_index": 10, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 4196, + "real_time": 1.6704639775804032e+05, + "cpu_time": 3.7205727859866450e+05, + "time_unit": "ns", + "bytes": 4.1943040000000000e+06, + "bytes_per_second": 2.5108616865089622e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "family_index": 0, + "per_family_instance_index": 10, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 4196, + "real_time": 1.6695709462413317e+05, + "cpu_time": 3.7206392612011568e+05, + "time_unit": "ns", + "bytes": 4.1943040000000000e+06, + "bytes_per_second": 2.5122047130986221e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "family_index": 0, + "per_family_instance_index": 10, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 4196, + "real_time": 1.6696925839181506e+05, + "cpu_time": 3.7263947426120221e+05, + "time_unit": "ns", + "bytes": 4.1943040000000000e+06, + "bytes_per_second": 2.5120216981245258e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 10, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 1.6698758333220167e+05, + "cpu_time": 3.7192632917063881e+05, + "time_unit": "ns", + "bytes": 4.1943040000000000e+06, + "bytes_per_second": 2.5117461239155163e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time_median", + "family_index": 0, + "per_family_instance_index": 10, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 1.6697093377642697e+05, + "cpu_time": 3.7205727859866444e+05, + "time_unit": "ns", + "bytes": 4.1943040000000000e+06, + "bytes_per_second": 2.5119964925249485e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 10, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 3.5517303507519230e+01, + "cpu_time": 5.2927081141717542e+02, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 5.3412968454337008e+06, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 10, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 2.1269427821385880e-04, + "cpu_time": 1.4230528196199506e-03, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 2.1265273566371622e-04, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "family_index": 0, + "per_family_instance_index": 11, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 2162, + "real_time": 3.2362471260920865e+05, + "cpu_time": 7.6086096808510472e+05, + "time_unit": "ns", + "bytes": 8.3886080000000000e+06, + "bytes_per_second": 2.5920789337647461e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "family_index": 0, + "per_family_instance_index": 11, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 2162, + "real_time": 3.2385360870306159e+05, + "cpu_time": 7.6403697548566130e+05, + "time_unit": "ns", + "bytes": 8.3886080000000000e+06, + "bytes_per_second": 2.5902468814826267e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "family_index": 0, + "per_family_instance_index": 11, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 2162, + "real_time": 3.2381787432810408e+05, + "cpu_time": 7.6293607631822373e+05, + "time_unit": "ns", + "bytes": 8.3886080000000000e+06, + "bytes_per_second": 2.5905327238052204e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "family_index": 0, + "per_family_instance_index": 11, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 2162, + "real_time": 3.2395479499464069e+05, + "cpu_time": 7.6423365356151876e+05, + "time_unit": "ns", + "bytes": 8.3886080000000000e+06, + "bytes_per_second": 2.5894378257740482e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "family_index": 0, + "per_family_instance_index": 11, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 2162, + "real_time": 3.2391327836703259e+05, + "cpu_time": 7.6305557446808484e+05, + "time_unit": "ns", + "bytes": 8.3886080000000000e+06, + "bytes_per_second": 2.5897697193181133e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 11, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 3.2383285380040959e+05, + "cpu_time": 7.6302464958371874e+05, + "time_unit": "ns", + "bytes": 8.3886080000000000e+06, + "bytes_per_second": 2.5904132168289509e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time_median", + "family_index": 0, + "per_family_instance_index": 11, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 3.2385360870306159e+05, + "cpu_time": 7.6305557446808484e+05, + "time_unit": "ns", + "bytes": 8.3886080000000000e+06, + "bytes_per_second": 2.5902468814826267e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 11, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 1.2778465458092390e+02, + "cpu_time": 1.3394787744381345e+03, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 1.0225017158792449e+07, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 11, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 3.9460064993801530e-04, + "cpu_time": 1.7554855864340821e-03, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 3.9472533155576560e-04, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "family_index": 0, + "per_family_instance_index": 12, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 1093, + "real_time": 6.4030860468475975e+05, + "cpu_time": 1.5422251427264416e+06, + "time_unit": "ns", + "bytes": 1.6777216000000000e+07, + "bytes_per_second": 2.6201765644333096e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "family_index": 0, + "per_family_instance_index": 12, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 1093, + "real_time": 6.4019633339690720e+05, + "cpu_time": 1.5421269990850834e+06, + "time_unit": "ns", + "bytes": 1.6777216000000000e+07, + "bytes_per_second": 2.6206360650301487e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "family_index": 0, + "per_family_instance_index": 12, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 1093, + "real_time": 6.4018975049921905e+05, + "cpu_time": 1.5421097200366000e+06, + "time_unit": "ns", + "bytes": 1.6777216000000000e+07, + "bytes_per_second": 2.6206630123205116e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "family_index": 0, + "per_family_instance_index": 12, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 1093, + "real_time": 6.4018037592376990e+05, + "cpu_time": 1.5392733851784063e+06, + "time_unit": "ns", + "bytes": 1.6777216000000000e+07, + "bytes_per_second": 2.6207013883846020e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "family_index": 0, + "per_family_instance_index": 12, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 1093, + "real_time": 6.4030084634380380e+05, + "cpu_time": 1.5422688755718253e+06, + "time_unit": "ns", + "bytes": 1.6777216000000000e+07, + "bytes_per_second": 2.6202083123581604e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 12, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 6.4023518216969189e+05, + "cpu_time": 1.5416008245196715e+06, + "time_unit": "ns", + "bytes": 1.6777216000000000e+07, + "bytes_per_second": 2.6204770685053467e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time_median", + "family_index": 0, + "per_family_instance_index": 12, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 6.4019633339690720e+05, + "cpu_time": 1.5421269990850834e+06, + "time_unit": "ns", + "bytes": 1.6777216000000000e+07, + "bytes_per_second": 2.6206360650301487e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 12, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 6.3795842125627587e+01, + "cpu_time": 1.3027733529701841e+03, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 2.6110676044867164e+06, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 12, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 9.9644386785227826e-05, + "cpu_time": 8.4507826685685592e-04, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 9.9640925534830296e-05, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "family_index": 0, + "per_family_instance_index": 13, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 552, + "real_time": 1.2669229008547585e+06, + "cpu_time": 3.0502753387681046e+06, + "time_unit": "ns", + "bytes": 3.3554432000000000e+07, + "bytes_per_second": 2.6484983401406460e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "family_index": 0, + "per_family_instance_index": 13, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 552, + "real_time": 1.2666994152823463e+06, + "cpu_time": 3.0563120235507386e+06, + "time_unit": "ns", + "bytes": 3.3554432000000000e+07, + "bytes_per_second": 2.6489656184550098e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "family_index": 0, + "per_family_instance_index": 13, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 552, + "real_time": 1.2664808560604826e+06, + "cpu_time": 3.0523025289855087e+06, + "time_unit": "ns", + "bytes": 3.3554432000000000e+07, + "bytes_per_second": 2.6494227559328831e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "family_index": 0, + "per_family_instance_index": 13, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 552, + "real_time": 1.2670275348194782e+06, + "cpu_time": 3.0611593931159587e+06, + "time_unit": "ns", + "bytes": 3.3554432000000000e+07, + "bytes_per_second": 2.6482796212302303e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "family_index": 0, + "per_family_instance_index": 13, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 552, + "real_time": 1.2647185358218849e+06, + "cpu_time": 3.0810984202898555e+06, + "time_unit": "ns", + "bytes": 3.3554432000000000e+07, + "bytes_per_second": 2.6531145902905941e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 13, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 1.2663698485677899e+06, + "cpu_time": 3.0602295409420333e+06, + "time_unit": "ns", + "bytes": 3.3554432000000000e+07, + "bytes_per_second": 2.6496561852098728e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time_median", + "family_index": 0, + "per_family_instance_index": 13, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 1.2666994152823463e+06, + "cpu_time": 3.0563120235507386e+06, + "time_unit": "ns", + "bytes": 3.3554432000000000e+07, + "bytes_per_second": 2.6489656184550098e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 13, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 9.4686175155303465e+02, + "cpu_time": 1.2385933072334949e+04, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 1.9828937794469979e+07, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 13, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 7.4769764348376960e-04, + "cpu_time": 4.0473869383412901e-03, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 7.4835889671849543e-04, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "family_index": 0, + "per_family_instance_index": 14, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 276, + "real_time": 2.5333063238286884e+06, + "cpu_time": 6.3108529601448970e+06, + "time_unit": "ns", + "bytes": 6.7108864000000000e+07, + "bytes_per_second": 2.6490623486296616e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "family_index": 0, + "per_family_instance_index": 14, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 276, + "real_time": 2.5300186513788132e+06, + "cpu_time": 6.3209407572463332e+06, + "time_unit": "ns", + "bytes": 6.7108864000000000e+07, + "bytes_per_second": 2.6525047142805412e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "family_index": 0, + "per_family_instance_index": 14, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 276, + "real_time": 2.5328795553819425e+06, + "cpu_time": 6.3274877862319350e+06, + "time_unit": "ns", + "bytes": 6.7108864000000000e+07, + "bytes_per_second": 2.6495086928790184e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "family_index": 0, + "per_family_instance_index": 14, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 276, + "real_time": 2.5344555792601211e+06, + "cpu_time": 6.2937752789855171e+06, + "time_unit": "ns", + "bytes": 6.7108864000000000e+07, + "bytes_per_second": 2.6478611244625153e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "family_index": 0, + "per_family_instance_index": 14, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 276, + "real_time": 2.5340672244952209e+06, + "cpu_time": 6.3178111231884155e+06, + "time_unit": "ns", + "bytes": 6.7108864000000000e+07, + "bytes_per_second": 2.6482669185450634e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 14, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 2.5329454668689580e+06, + "cpu_time": 6.3141735811594194e+06, + "time_unit": "ns", + "bytes": 6.7108864000000000e+07, + "bytes_per_second": 2.6494407597593601e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time_median", + "family_index": 0, + "per_family_instance_index": 14, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 2.5333063238286888e+06, + "cpu_time": 6.3178111231884155e+06, + "time_unit": "ns", + "bytes": 6.7108864000000000e+07, + "bytes_per_second": 2.6490623486296616e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 14, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 1.7492563122584434e+03, + "cpu_time": 1.2878389810379260e+04, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 1.8308999194232326e+07, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 14, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 6.9060164742541666e-04, + "cpu_time": 2.0396002176447147e-03, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 6.9105146536264776e-04, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "family_index": 0, + "per_family_instance_index": 15, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 138, + "real_time": 5.0558920450292639e+06, + "cpu_time": 1.2831195268115934e+07, + "time_unit": "ns", + "bytes": 1.3421772800000000e+08, + "bytes_per_second": 2.6546794671369045e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "family_index": 0, + "per_family_instance_index": 15, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 138, + "real_time": 5.0564067256029537e+06, + "cpu_time": 1.2827766746376827e+07, + "time_unit": "ns", + "bytes": 1.3421772800000000e+08, + "bytes_per_second": 2.6544092531242165e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "family_index": 0, + "per_family_instance_index": 15, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 138, + "real_time": 5.0571938686450757e+06, + "cpu_time": 1.2825944268115975e+07, + "time_unit": "ns", + "bytes": 1.3421772800000000e+08, + "bytes_per_second": 2.6539960991442009e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "family_index": 0, + "per_family_instance_index": 15, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 138, + "real_time": 5.0556807529073264e+06, + "cpu_time": 1.2818127210144922e+07, + "time_unit": "ns", + "bytes": 1.3421772800000000e+08, + "bytes_per_second": 2.6547904141854008e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "family_index": 0, + "per_family_instance_index": 15, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 138, + "real_time": 5.0558662480688179e+06, + "cpu_time": 1.2801847253623167e+07, + "time_unit": "ns", + "bytes": 1.3421772800000000e+08, + "bytes_per_second": 2.6546930123253746e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 15, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 5.0562079280506885e+06, + "cpu_time": 1.2820976149275366e+07, + "time_unit": "ns", + "bytes": 1.3421772800000000e+08, + "bytes_per_second": 2.6545136491832199e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time_median", + "family_index": 0, + "per_family_instance_index": 15, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 5.0558920450292639e+06, + "cpu_time": 1.2825944268115977e+07, + "time_unit": "ns", + "bytes": 1.3421772800000000e+08, + "bytes_per_second": 2.6546794671369045e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 15, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 6.1360414982758527e+02, + "cpu_time": 1.1718104654839601e+04, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 3.2211107045365577e+06, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 15, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 1.2135658947557307e-04, + "cpu_time": 9.1397913219750456e-04, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 1.2134466535998701e-04, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "family_index": 0, + "per_family_instance_index": 16, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 69, + "real_time": 1.0100161184327327e+07, + "cpu_time": 2.5814307347826120e+07, + "time_unit": "ns", + "bytes": 2.6843545600000000e+08, + "bytes_per_second": 2.6577343777101109e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "family_index": 0, + "per_family_instance_index": 16, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 69, + "real_time": 1.0097395277757576e+07, + "cpu_time": 2.5787414159420196e+07, + "time_unit": "ns", + "bytes": 2.6843545600000000e+08, + "bytes_per_second": 2.6584623916952770e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "family_index": 0, + "per_family_instance_index": 16, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 69, + "real_time": 1.0099725635803264e+07, + "cpu_time": 2.5806926695652127e+07, + "time_unit": "ns", + "bytes": 2.6843545600000000e+08, + "bytes_per_second": 2.6578489919409622e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "family_index": 0, + "per_family_instance_index": 16, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 69, + "real_time": 1.0099199182097463e+07, + "cpu_time": 2.5868804782608852e+07, + "time_unit": "ns", + "bytes": 2.6843545600000000e+08, + "bytes_per_second": 2.6579875409908463e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "family_index": 0, + "per_family_instance_index": 16, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 69, + "real_time": 1.0099013619448828e+07, + "cpu_time": 2.5855631666666530e+07, + "time_unit": "ns", + "bytes": 2.6843545600000000e+08, + "bytes_per_second": 2.6580363797415134e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 16, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 1.0099098979886893e+07, + "cpu_time": 2.5826616930434763e+07, + "time_unit": "ns", + "bytes": 2.6843545600000000e+08, + "bytes_per_second": 2.6580139364157421e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time_median", + "family_index": 0, + "per_family_instance_index": 16, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 1.0099199182097461e+07, + "cpu_time": 2.5814307347826120e+07, + "time_unit": "ns", + "bytes": 2.6843545600000000e+08, + "bytes_per_second": 2.6579875409908463e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 16, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 1.0536725890616965e+03, + "cpu_time": 3.4270097078257219e+04, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 2.7734108575831312e+06, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 16, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 1.0433332628585620e-04, + "cpu_time": 1.3269293911225527e-03, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 1.0434147163739099e-04, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "family_index": 0, + "per_family_instance_index": 17, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 35, + "real_time": 2.0186294828142438e+07, + "cpu_time": 5.1467226800000228e+07, + "time_unit": "ns", + "bytes": 5.3687091200000000e+08, + "bytes_per_second": 2.6595812484197395e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "family_index": 0, + "per_family_instance_index": 17, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 35, + "real_time": 2.0185914476002965e+07, + "cpu_time": 5.1488342057142846e+07, + "time_unit": "ns", + "bytes": 5.3687091200000000e+08, + "bytes_per_second": 2.6596313614537140e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "family_index": 0, + "per_family_instance_index": 17, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 35, + "real_time": 2.0195094176701136e+07, + "cpu_time": 5.1817182285714939e+07, + "time_unit": "ns", + "bytes": 5.3687091200000000e+08, + "bytes_per_second": 2.6584224233001209e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "family_index": 0, + "per_family_instance_index": 17, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 35, + "real_time": 2.0210578452263560e+07, + "cpu_time": 5.1889857685714394e+07, + "time_unit": "ns", + "bytes": 5.3687091200000000e+08, + "bytes_per_second": 2.6563856807367683e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "family_index": 0, + "per_family_instance_index": 17, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 35, + "real_time": 2.0202862098813057e+07, + "cpu_time": 5.1876610628571436e+07, + "time_unit": "ns", + "bytes": 5.3687091200000000e+08, + "bytes_per_second": 2.6574002701901421e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 17, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 2.0196148806384631e+07, + "cpu_time": 5.1707843891428776e+07, + "time_unit": "ns", + "bytes": 5.3687091200000000e+08, + "bytes_per_second": 2.6582841968200974e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time_median", + "family_index": 0, + "per_family_instance_index": 17, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 2.0195094176701136e+07, + "cpu_time": 5.1817182285714939e+07, + "time_unit": "ns", + "bytes": 5.3687091200000000e+08, + "bytes_per_second": 2.6584224233001209e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 17, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 1.0679859839636831e+04, + "cpu_time": 2.1192201235430557e+05, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 1.4055240624769112e+07, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 17, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 5.2880675132778757e-04, + "cpu_time": 4.0984499914419048e-03, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 5.2873355834497776e-04, + "own_numa": NaN, + "wr_gpu": NaN + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "family_index": 0, + "per_family_instance_index": 18, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 0, + "threads": 1, + "iterations": 17, + "real_time": 4.0506263866144069e+07, + "cpu_time": 1.0457281752941166e+08, + "time_unit": "ns", + "bytes": 1.0737418240000000e+09, + "bytes_per_second": 2.6508043979278339e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "family_index": 0, + "per_family_instance_index": 18, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 1, + "threads": 1, + "iterations": 17, + "real_time": 4.0494555936140172e+07, + "cpu_time": 1.0461779129411753e+08, + "time_unit": "ns", + "bytes": 1.0737418240000000e+09, + "bytes_per_second": 2.6515708079211647e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "family_index": 0, + "per_family_instance_index": 18, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 2, + "threads": 1, + "iterations": 17, + "real_time": 4.0568456711137995e+07, + "cpu_time": 1.0457464858823621e+08, + "time_unit": "ns", + "bytes": 1.0737418240000000e+09, + "bytes_per_second": 2.6467406232517742e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "family_index": 0, + "per_family_instance_index": 18, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 3, + "threads": 1, + "iterations": 17, + "real_time": 4.0443346561754450e+07, + "cpu_time": 1.0446937582353024e+08, + "time_unit": "ns", + "bytes": 1.0737418240000000e+09, + "bytes_per_second": 2.6549282274662006e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "family_index": 0, + "per_family_instance_index": 18, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "run_type": "iteration", + "repetitions": 5, + "repetition_index": 4, + "threads": 1, + "iterations": 17, + "real_time": 4.0510471910238266e+07, + "cpu_time": 1.0454226788235299e+08, + "time_unit": "ns", + "bytes": 1.0737418240000000e+09, + "bytes_per_second": 2.6505290443892159e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time_mean", + "family_index": 0, + "per_family_instance_index": 18, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "mean", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 4.0504618997082993e+07, + "cpu_time": 1.0455538022352973e+08, + "time_unit": "ns", + "bytes": 1.0737418240000000e+09, + "bytes_per_second": 2.6509146201912380e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time_median", + "family_index": 0, + "per_family_instance_index": 18, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "median", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 4.0506263866144076e+07, + "cpu_time": 1.0457281752941164e+08, + "time_unit": "ns", + "bytes": 1.0737418240000000e+09, + "bytes_per_second": 2.6508043979278339e+10, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time_stddev", + "family_index": 0, + "per_family_instance_index": 18, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "stddev", + "aggregate_unit": "time", + "iterations": 5, + "real_time": 4.4631245919956767e+04, + "cpu_time": 5.5088931637860565e+04, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 2.9207316630822491e+07, + "own_numa": 0.0000000000000000e+00, + "wr_gpu": 0.0000000000000000e+00 + }, + { + "name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time_cv", + "family_index": 0, + "per_family_instance_index": 18, + "run_name": "Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time", + "run_type": "aggregate", + "repetitions": 5, + "threads": 1, + "aggregate_name": "cv", + "aggregate_unit": "percentage", + "iterations": 5, + "real_time": 1.1018804033972264e-03, + "cpu_time": 5.2688758359527299e-04, + "time_unit": "ns", + "bytes": 0.0000000000000000e+00, + "bytes_per_second": 1.1017826228109703e-03, + "own_numa": NaN, + "wr_gpu": NaN + } + ] +} diff --git a/results/r1-1465528.out b/results/r1-1465528.out new file mode 100644 index 0000000..391617e --- /dev/null +++ b/results/r1-1465528.out @@ -0,0 +1,699 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 05:38:26 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:38:26.962] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:38:26.963] [scope] [info] recorded CPU goveror +[2023-10-09 17:38:26.963] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:38:26.963] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:38:29-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1870.01 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.31, 11.54, 26.80 +---------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +---------------------------------------------------------------------------------------------------------------------------- +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):8/manual_time 13094 ns 19976 ns 53295 bytes=256 bytes_per_second=18.6447M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):8/manual_time 13044 ns 19867 ns 53295 bytes=256 bytes_per_second=18.716M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):8/manual_time 13009 ns 19804 ns 53295 bytes=256 bytes_per_second=18.7676M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):8/manual_time 13033 ns 19849 ns 53295 bytes=256 bytes_per_second=18.7326M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):8/manual_time 13045 ns 19857 ns 53295 bytes=256 bytes_per_second=18.7158M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):8/manual_time_mean 13045 ns 19871 ns 5 bytes=256 bytes_per_second=18.7154M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):8/manual_time_median 13044 ns 19857 ns 5 bytes=256 bytes_per_second=18.716M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):8/manual_time_stddev 31.3 ns 63.4 ns 5 bytes=0 bytes_per_second=45.8469k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):8/manual_time_cv 0.24 % 0.32 % 5 bytes=0.00% bytes_per_second=0.24% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):9/manual_time 12986 ns 19807 ns 53884 bytes=512 bytes_per_second=37.6007M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):9/manual_time 13013 ns 19893 ns 53884 bytes=512 bytes_per_second=37.5216M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):9/manual_time 13060 ns 19917 ns 53884 bytes=512 bytes_per_second=37.3885M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):9/manual_time 13010 ns 19864 ns 53884 bytes=512 bytes_per_second=37.5324M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):9/manual_time 13073 ns 19900 ns 53884 bytes=512 bytes_per_second=37.3517M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):9/manual_time_mean 13028 ns 19876 ns 5 bytes=512 bytes_per_second=37.479M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):9/manual_time_median 13013 ns 19893 ns 5 bytes=512 bytes_per_second=37.5216M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):9/manual_time_stddev 36.4 ns 43.1 ns 5 bytes=0 bytes_per_second=107.231k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):9/manual_time_cv 0.28 % 0.22 % 5 bytes=0.00% bytes_per_second=0.28% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):10/manual_time 13116 ns 19937 ns 53587 bytes=1024 bytes_per_second=74.4559M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):10/manual_time 13093 ns 19929 ns 53587 bytes=1024 bytes_per_second=74.5861M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):10/manual_time 13170 ns 20019 ns 53587 bytes=1024 bytes_per_second=74.1531M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):10/manual_time 13078 ns 19926 ns 53587 bytes=1024 bytes_per_second=74.673M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):10/manual_time 13064 ns 19903 ns 53587 bytes=1024 bytes_per_second=74.7499M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):10/manual_time_mean 13104 ns 19943 ns 5 bytes=1024 bytes_per_second=74.5236M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):10/manual_time_median 13093 ns 19929 ns 5 bytes=1024 bytes_per_second=74.5861M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):10/manual_time_stddev 41.3 ns 44.5 ns 5 bytes=0 bytes_per_second=239.773k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):10/manual_time_cv 0.31 % 0.22 % 5 bytes=0.00% bytes_per_second=0.31% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):11/manual_time 13206 ns 20105 ns 52954 bytes=2.048k bytes_per_second=147.895M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):11/manual_time 13212 ns 20140 ns 52954 bytes=2.048k bytes_per_second=147.826M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):11/manual_time 13279 ns 20244 ns 52954 bytes=2.048k bytes_per_second=147.086M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):11/manual_time 13235 ns 20189 ns 52954 bytes=2.048k bytes_per_second=147.574M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):11/manual_time 13207 ns 20173 ns 52954 bytes=2.048k bytes_per_second=147.884M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):11/manual_time_mean 13228 ns 20170 ns 5 bytes=2.048k bytes_per_second=147.653M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):11/manual_time_median 13212 ns 20173 ns 5 bytes=2.048k bytes_per_second=147.826M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):11/manual_time_stddev 30.8 ns 52.5 ns 5 bytes=0 bytes_per_second=350.823k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):11/manual_time_cv 0.23 % 0.26 % 5 bytes=0.00% bytes_per_second=0.23% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):12/manual_time 13469 ns 20487 ns 52173 bytes=4.096k bytes_per_second=290.008M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):12/manual_time 13473 ns 20464 ns 52173 bytes=4.096k bytes_per_second=289.934M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):12/manual_time 13387 ns 20455 ns 52173 bytes=4.096k bytes_per_second=291.804M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):12/manual_time 13486 ns 20540 ns 52173 bytes=4.096k bytes_per_second=289.642M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):12/manual_time 13433 ns 20478 ns 52173 bytes=4.096k bytes_per_second=290.802M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):12/manual_time_mean 13450 ns 20485 ns 5 bytes=4.096k bytes_per_second=290.438M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):12/manual_time_median 13469 ns 20478 ns 5 bytes=4.096k bytes_per_second=290.008M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):12/manual_time_stddev 40.5 ns 33.3 ns 5 bytes=0 bytes_per_second=897.233k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):12/manual_time_cv 0.30 % 0.16 % 5 bytes=0.00% bytes_per_second=0.30% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):13/manual_time 13685 ns 21007 ns 51470 bytes=8.192k bytes_per_second=570.883M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):13/manual_time 13607 ns 20974 ns 51470 bytes=8.192k bytes_per_second=574.173M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):13/manual_time 13673 ns 21114 ns 51470 bytes=8.192k bytes_per_second=571.383M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):13/manual_time 13620 ns 20996 ns 51470 bytes=8.192k bytes_per_second=573.625M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):13/manual_time 13615 ns 20981 ns 51470 bytes=8.192k bytes_per_second=573.814M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):13/manual_time_mean 13640 ns 21014 ns 5 bytes=8.192k bytes_per_second=572.776M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):13/manual_time_median 13620 ns 20996 ns 5 bytes=8.192k bytes_per_second=573.625M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):13/manual_time_stddev 36.3 ns 57.3 ns 5 bytes=0 bytes_per_second=1.52257M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):13/manual_time_cv 0.27 % 0.27 % 5 bytes=0.00% bytes_per_second=0.27% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):14/manual_time 13922 ns 21786 ns 50185 bytes=16.384k bytes_per_second=1122.3M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):14/manual_time 13933 ns 21865 ns 50185 bytes=16.384k bytes_per_second=1121.44M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):14/manual_time 13950 ns 21886 ns 50185 bytes=16.384k bytes_per_second=1120.05M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):14/manual_time 13928 ns 21823 ns 50185 bytes=16.384k bytes_per_second=1121.86M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):14/manual_time 13937 ns 21890 ns 50185 bytes=16.384k bytes_per_second=1121.16M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):14/manual_time_mean 13934 ns 21850 ns 5 bytes=16.384k bytes_per_second=1121.36M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):14/manual_time_median 13933 ns 21865 ns 5 bytes=16.384k bytes_per_second=1121.44M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):14/manual_time_stddev 10.6 ns 44.5 ns 5 bytes=0 bytes_per_second=871.26k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):14/manual_time_cv 0.08 % 0.20 % 5 bytes=0.00% bytes_per_second=0.08% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):15/manual_time 14713 ns 23046 ns 47768 bytes=32.768k bytes_per_second=2.07415G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):15/manual_time 14674 ns 23000 ns 47768 bytes=32.768k bytes_per_second=2.07977G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):15/manual_time 14703 ns 23000 ns 47768 bytes=32.768k bytes_per_second=2.07565G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):15/manual_time 14712 ns 23075 ns 47768 bytes=32.768k bytes_per_second=2.07427G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):15/manual_time 14717 ns 23075 ns 47768 bytes=32.768k bytes_per_second=2.07358G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):15/manual_time_mean 14704 ns 23039 ns 5 bytes=32.768k bytes_per_second=2.07549G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):15/manual_time_median 14712 ns 23046 ns 5 bytes=32.768k bytes_per_second=2.07427G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):15/manual_time_stddev 17.8 ns 37.9 ns 5 bytes=0 bytes_per_second=2.57407M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):15/manual_time_cv 0.12 % 0.16 % 5 bytes=0.00% bytes_per_second=0.12% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):16/manual_time 16063 ns 26595 ns 43396 bytes=65.536k bytes_per_second=3.79973G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):16/manual_time 16137 ns 26739 ns 43396 bytes=65.536k bytes_per_second=3.78222G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):16/manual_time 16297 ns 26916 ns 43396 bytes=65.536k bytes_per_second=3.74508G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):16/manual_time 16249 ns 26767 ns 43396 bytes=65.536k bytes_per_second=3.75635G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):16/manual_time 16245 ns 26825 ns 43396 bytes=65.536k bytes_per_second=3.75706G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):16/manual_time_mean 16198 ns 26768 ns 5 bytes=65.536k bytes_per_second=3.76809G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):16/manual_time_median 16245 ns 26767 ns 5 bytes=65.536k bytes_per_second=3.75706G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):16/manual_time_stddev 95.6 ns 118 ns 5 bytes=0 bytes_per_second=22.8388M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):16/manual_time_cv 0.59 % 0.44 % 5 bytes=0.00% bytes_per_second=0.59% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):17/manual_time 19851 ns 33693 ns 35403 bytes=131.072k bytes_per_second=6.14938G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):17/manual_time 19820 ns 33694 ns 35403 bytes=131.072k bytes_per_second=6.15883G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):17/manual_time 19866 ns 33712 ns 35403 bytes=131.072k bytes_per_second=6.14483G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):17/manual_time 19854 ns 33787 ns 35403 bytes=131.072k bytes_per_second=6.14844G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):17/manual_time 19791 ns 33818 ns 35403 bytes=131.072k bytes_per_second=6.16785G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):17/manual_time_mean 19836 ns 33741 ns 5 bytes=131.072k bytes_per_second=6.15387G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):17/manual_time_median 19851 ns 33712 ns 5 bytes=131.072k bytes_per_second=6.14938G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):17/manual_time_stddev 30.2 ns 58.0 ns 5 bytes=0 bytes_per_second=9.59847M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):17/manual_time_cv 0.15 % 0.17 % 5 bytes=0.00% bytes_per_second=0.15% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):18/manual_time 23716 ns 49230 ns 29531 bytes=262.144k bytes_per_second=10.2944G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):18/manual_time 23682 ns 49083 ns 29531 bytes=262.144k bytes_per_second=10.3093G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):18/manual_time 23726 ns 49274 ns 29531 bytes=262.144k bytes_per_second=10.2898G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):18/manual_time 23684 ns 49069 ns 29531 bytes=262.144k bytes_per_second=10.3084G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):18/manual_time 23787 ns 49355 ns 29531 bytes=262.144k bytes_per_second=10.2637G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):18/manual_time_mean 23719 ns 49202 ns 5 bytes=262.144k bytes_per_second=10.2931G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):18/manual_time_median 23716 ns 49230 ns 5 bytes=262.144k bytes_per_second=10.2944G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):18/manual_time_stddev 42.7 ns 124 ns 5 bytes=0 bytes_per_second=18.9665M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):18/manual_time_cv 0.18 % 0.25 % 5 bytes=0.00% bytes_per_second=0.18% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):19/manual_time 34268 ns 74301 ns 20412 bytes=524.288k bytes_per_second=14.2491G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):19/manual_time 34279 ns 74268 ns 20412 bytes=524.288k bytes_per_second=14.2441G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):19/manual_time 34264 ns 74306 ns 20412 bytes=524.288k bytes_per_second=14.2505G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):19/manual_time 34245 ns 74113 ns 20412 bytes=524.288k bytes_per_second=14.2585G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):19/manual_time 34309 ns 74030 ns 20412 bytes=524.288k bytes_per_second=14.2321G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):19/manual_time_mean 34273 ns 74204 ns 5 bytes=524.288k bytes_per_second=14.2468G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):19/manual_time_median 34268 ns 74268 ns 5 bytes=524.288k bytes_per_second=14.2491G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):19/manual_time_stddev 23.4 ns 125 ns 5 bytes=0 bytes_per_second=9.96899M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):19/manual_time_cv 0.07 % 0.17 % 5 bytes=0.00% bytes_per_second=0.07% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):20/manual_time 55171 ns 124796 ns 12719 bytes=1048.58k bytes_per_second=17.7005G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):20/manual_time 55151 ns 125408 ns 12719 bytes=1048.58k bytes_per_second=17.7069G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):20/manual_time 55150 ns 124745 ns 12719 bytes=1048.58k bytes_per_second=17.7073G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):20/manual_time 55181 ns 124830 ns 12719 bytes=1048.58k bytes_per_second=17.6974G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):20/manual_time 55150 ns 124885 ns 12719 bytes=1048.58k bytes_per_second=17.7075G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):20/manual_time_mean 55161 ns 124933 ns 5 bytes=1048.58k bytes_per_second=17.7039G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):20/manual_time_median 55151 ns 124830 ns 5 bytes=1048.58k bytes_per_second=17.7069G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):20/manual_time_stddev 14.6 ns 270 ns 5 bytes=0 bytes_per_second=4.78152M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):20/manual_time_cv 0.03 % 0.22 % 5 bytes=0.00% bytes_per_second=0.03% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):21/manual_time 97566 ns 223926 ns 7181 bytes=2.09715M bytes_per_second=20.0186G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):21/manual_time 97576 ns 223477 ns 7181 bytes=2.09715M bytes_per_second=20.0165G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):21/manual_time 97522 ns 223558 ns 7181 bytes=2.09715M bytes_per_second=20.0274G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):21/manual_time 97560 ns 224240 ns 7181 bytes=2.09715M bytes_per_second=20.0197G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):21/manual_time 97555 ns 223578 ns 7181 bytes=2.09715M bytes_per_second=20.0207G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):21/manual_time_mean 97556 ns 223756 ns 5 bytes=2.09715M bytes_per_second=20.0206G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):21/manual_time_median 97560 ns 223578 ns 5 bytes=2.09715M bytes_per_second=20.0197G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):21/manual_time_stddev 20.2 ns 321 ns 5 bytes=0 bytes_per_second=4.24073M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):21/manual_time_cv 0.02 % 0.14 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):22/manual_time 183853 ns 424592 ns 3808 bytes=4.1943M bytes_per_second=21.2466G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):22/manual_time 183853 ns 416206 ns 3808 bytes=4.1943M bytes_per_second=21.2466G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):22/manual_time 183859 ns 424705 ns 3808 bytes=4.1943M bytes_per_second=21.246G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):22/manual_time 183826 ns 415632 ns 3808 bytes=4.1943M bytes_per_second=21.2497G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):22/manual_time 183822 ns 425789 ns 3808 bytes=4.1943M bytes_per_second=21.2502G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):22/manual_time_mean 183842 ns 421385 ns 5 bytes=4.1943M bytes_per_second=21.2478G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):22/manual_time_median 183853 ns 424592 ns 5 bytes=4.1943M bytes_per_second=21.2466G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):22/manual_time_stddev 17.0 ns 5015 ns 5 bytes=0 bytes_per_second=2.00892M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):22/manual_time_cv 0.01 % 1.19 % 5 bytes=0.00% bytes_per_second=0.01% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):23/manual_time 350899 ns 814807 ns 1994 bytes=8.38861M bytes_per_second=22.2642G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):23/manual_time 351026 ns 817287 ns 1994 bytes=8.38861M bytes_per_second=22.2562G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):23/manual_time 350895 ns 816732 ns 1994 bytes=8.38861M bytes_per_second=22.2645G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):23/manual_time 350995 ns 815937 ns 1994 bytes=8.38861M bytes_per_second=22.2582G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):23/manual_time 350886 ns 818923 ns 1994 bytes=8.38861M bytes_per_second=22.2651G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):23/manual_time_mean 350940 ns 816737 ns 5 bytes=8.38861M bytes_per_second=22.2616G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):23/manual_time_median 350899 ns 816732 ns 5 bytes=8.38861M bytes_per_second=22.2642G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):23/manual_time_stddev 65.2 ns 1537 ns 5 bytes=0 bytes_per_second=4.23738M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):23/manual_time_cv 0.02 % 0.19 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):24/manual_time 684281 ns 1758992 ns 1024 bytes=16.7772M bytes_per_second=22.8342G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):24/manual_time 684315 ns 1758863 ns 1024 bytes=16.7772M bytes_per_second=22.8331G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):24/manual_time 683682 ns 1755736 ns 1024 bytes=16.7772M bytes_per_second=22.8542G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):24/manual_time 683249 ns 1755853 ns 1024 bytes=16.7772M bytes_per_second=22.8687G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):24/manual_time 684243 ns 1758898 ns 1024 bytes=16.7772M bytes_per_second=22.8355G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):24/manual_time_mean 683954 ns 1757668 ns 5 bytes=16.7772M bytes_per_second=22.8451G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):24/manual_time_median 684243 ns 1758863 ns 5 bytes=16.7772M bytes_per_second=22.8355G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):24/manual_time_stddev 472 ns 1712 ns 5 bytes=0 bytes_per_second=16.1549M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):24/manual_time_cv 0.07 % 0.10 % 5 bytes=0.00% bytes_per_second=0.07% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):25/manual_time 1349319 ns 3142541 ns 519 bytes=33.5544M bytes_per_second=23.1598G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):25/manual_time 1348503 ns 3478213 ns 519 bytes=33.5544M bytes_per_second=23.1739G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):25/manual_time 1349006 ns 3126719 ns 519 bytes=33.5544M bytes_per_second=23.1652G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):25/manual_time 1349700 ns 3149121 ns 519 bytes=33.5544M bytes_per_second=23.1533G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):25/manual_time 1348667 ns 3145609 ns 519 bytes=33.5544M bytes_per_second=23.171G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):25/manual_time_mean 1349039 ns 3208440 ns 5 bytes=33.5544M bytes_per_second=23.1646G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):25/manual_time_median 1349006 ns 3145609 ns 5 bytes=33.5544M bytes_per_second=23.1652G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):25/manual_time_stddev 485 ns 151050 ns 5 bytes=0 bytes_per_second=8.53154M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):25/manual_time_cv 0.04 % 4.71 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):26/manual_time 2682878 ns 6955818 ns 261 bytes=67.1089M bytes_per_second=23.2959G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):26/manual_time 2682082 ns 6518743 ns 261 bytes=67.1089M bytes_per_second=23.3028G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):26/manual_time 2683255 ns 6936557 ns 261 bytes=67.1089M bytes_per_second=23.2926G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):26/manual_time 2681785 ns 6912890 ns 261 bytes=67.1089M bytes_per_second=23.3054G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):26/manual_time 2682430 ns 6507981 ns 261 bytes=67.1089M bytes_per_second=23.2998G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):26/manual_time_mean 2682486 ns 6766398 ns 5 bytes=67.1089M bytes_per_second=23.2993G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):26/manual_time_median 2682430 ns 6912890 ns 5 bytes=67.1089M bytes_per_second=23.2998G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):26/manual_time_stddev 592 ns 231520 ns 5 bytes=0 bytes_per_second=5.26721M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):26/manual_time_cv 0.02 % 3.42 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):27/manual_time 5347196 ns 13903035 ns 131 bytes=134.218M bytes_per_second=23.3767G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):27/manual_time 5347307 ns 13278818 ns 131 bytes=134.218M bytes_per_second=23.3763G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):27/manual_time 5347190 ns 13882453 ns 131 bytes=134.218M bytes_per_second=23.3768G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):27/manual_time 5347965 ns 13921217 ns 131 bytes=134.218M bytes_per_second=23.3734G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):27/manual_time 5347498 ns 13167056 ns 131 bytes=134.218M bytes_per_second=23.3754G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):27/manual_time_mean 5347431 ns 13630516 ns 5 bytes=134.218M bytes_per_second=23.3757G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):27/manual_time_median 5347307 ns 13882453 ns 5 bytes=134.218M bytes_per_second=23.3763G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):27/manual_time_stddev 324 ns 374410 ns 5 bytes=0 bytes_per_second=1.44803M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):27/manual_time_cv 0.01 % 2.75 % 5 bytes=0.00% bytes_per_second=0.01% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):28/manual_time 10677597 ns 27944244 ns 66 bytes=268.435M bytes_per_second=23.4135G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):28/manual_time 10677307 ns 27815454 ns 66 bytes=268.435M bytes_per_second=23.4141G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):28/manual_time 10677421 ns 27772872 ns 66 bytes=268.435M bytes_per_second=23.4139G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):28/manual_time 10677106 ns 27833697 ns 66 bytes=268.435M bytes_per_second=23.4146G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):28/manual_time 10677377 ns 26676423 ns 66 bytes=268.435M bytes_per_second=23.414G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):28/manual_time_mean 10677361 ns 27608538 ns 5 bytes=268.435M bytes_per_second=23.414G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):28/manual_time_median 10677377 ns 27815454 ns 5 bytes=268.435M bytes_per_second=23.414G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):28/manual_time_stddev 179 ns 524894 ns 5 bytes=0 bytes_per_second=411.165k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):28/manual_time_cv 0.00 % 1.90 % 5 bytes=0.00% bytes_per_second=0.00% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):29/manual_time 21336098 ns 54960439 ns 33 bytes=536.871M bytes_per_second=23.4345G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):29/manual_time 21336389 ns 55733433 ns 33 bytes=536.871M bytes_per_second=23.4341G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):29/manual_time 21337068 ns 55899188 ns 33 bytes=536.871M bytes_per_second=23.4334G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):29/manual_time 21337029 ns 55846746 ns 33 bytes=536.871M bytes_per_second=23.4334G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):29/manual_time 21336370 ns 56326899 ns 33 bytes=536.871M bytes_per_second=23.4342G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):29/manual_time_mean 21336591 ns 55753341 ns 5 bytes=536.871M bytes_per_second=23.4339G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):29/manual_time_median 21336389 ns 55846746 ns 5 bytes=536.871M bytes_per_second=23.4341G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):29/manual_time_stddev 434 ns 497004 ns 5 bytes=0 bytes_per_second=499.311k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):29/manual_time_cv 0.00 % 0.89 % 5 bytes=0.00% bytes_per_second=0.00% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):30/manual_time 42656070 ns 112111599 ns 16 bytes=1073.74M bytes_per_second=23.4433G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):30/manual_time 42656331 ns 112606852 ns 16 bytes=1073.74M bytes_per_second=23.4432G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):30/manual_time 42656330 ns 112561541 ns 16 bytes=1073.74M bytes_per_second=23.4432G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):30/manual_time 42655881 ns 112489074 ns 16 bytes=1073.74M bytes_per_second=23.4434G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):30/manual_time 42655841 ns 112337935 ns 16 bytes=1073.74M bytes_per_second=23.4434G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):30/manual_time_mean 42656090 ns 112421400 ns 5 bytes=1073.74M bytes_per_second=23.4433G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):30/manual_time_median 42656070 ns 112489074 ns 5 bytes=1073.74M bytes_per_second=23.4433G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):30/manual_time_stddev 236 ns 200970 ns 5 bytes=0 bytes_per_second=135.818k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPinned/0/0/log2(N):30/manual_time_cv 0.00 % 0.18 % 5 bytes=0.00% bytes_per_second=0.00% hip_id=-nan% numa_id=-nan% +[2023-10-09 17:41:26.732] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 17:41:26.732] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:41:26.865] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:41:26.866] [scope] [info] recorded CPU goveror +[2023-10-09 17:41:26.866] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:41:26.866] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:41:29-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1795.86 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 1.53, 7.18, 22.42 +---------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +---------------------------------------------------------------------------------------------------------------------------- +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):8/manual_time 12985 ns 545889676 ns 53841 bytes=256 bytes_per_second=18.8015M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):8/manual_time 12825 ns 540897992 ns 53841 bytes=256 bytes_per_second=19.0367M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):8/manual_time 12807 ns 540264717 ns 53841 bytes=256 bytes_per_second=19.0629M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):8/manual_time 12785 ns 539621377 ns 53841 bytes=256 bytes_per_second=19.0958M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):8/manual_time 12777 ns 539520836 ns 53841 bytes=256 bytes_per_second=19.1071M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):8/manual_time_mean 12836 ns 541238920 ns 5 bytes=256 bytes_per_second=19.0208M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):8/manual_time_median 12807 ns 540264717 ns 5 bytes=256 bytes_per_second=19.0629M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):8/manual_time_stddev 85.5 ns 2658152 ns 5 bytes=0 bytes_per_second=128.694k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):8/manual_time_cv 0.67 % 0.49 % 5 bytes=0.00% bytes_per_second=0.66% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):9/manual_time 12779 ns 545589341 ns 54750 bytes=512 bytes_per_second=38.2098M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):9/manual_time 12853 ns 550846379 ns 54750 bytes=512 bytes_per_second=37.9897M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):9/manual_time 12785 ns 547686358 ns 54750 bytes=512 bytes_per_second=38.191M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):9/manual_time 12833 ns 549130353 ns 54750 bytes=512 bytes_per_second=38.0475M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):9/manual_time 12848 ns 549773092 ns 54750 bytes=512 bytes_per_second=38.0041M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):9/manual_time_mean 12820 ns 548605104 ns 5 bytes=512 bytes_per_second=38.0884M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):9/manual_time_median 12833 ns 549130353 ns 5 bytes=512 bytes_per_second=38.0475M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):9/manual_time_stddev 35.2 ns 2037297 ns 5 bytes=0 bytes_per_second=107.117k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):9/manual_time_cv 0.27 % 0.37 % 5 bytes=0.00% bytes_per_second=0.27% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):10/manual_time 12893 ns 546588341 ns 54509 bytes=1024 bytes_per_second=75.7432M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):10/manual_time 12813 ns 539875394 ns 54509 bytes=1024 bytes_per_second=76.2184M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):10/manual_time 12812 ns 543569957 ns 54509 bytes=1024 bytes_per_second=76.2204M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):10/manual_time 12821 ns 544262445 ns 54509 bytes=1024 bytes_per_second=76.1662M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):10/manual_time 12849 ns 544787867 ns 54509 bytes=1024 bytes_per_second=76.0004M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):10/manual_time_mean 12838 ns 543816801 ns 5 bytes=1024 bytes_per_second=76.0697M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):10/manual_time_median 12821 ns 544262445 ns 5 bytes=1024 bytes_per_second=76.1662M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):10/manual_time_stddev 34.4 ns 2470760 ns 5 bytes=0 bytes_per_second=208.333k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):10/manual_time_cv 0.27 % 0.45 % 5 bytes=0.00% bytes_per_second=0.27% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):11/manual_time 12828 ns 545727740 ns 54620 bytes=2.048k bytes_per_second=152.259M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):11/manual_time 12841 ns 546423250 ns 54620 bytes=2.048k bytes_per_second=152.102M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):11/manual_time 12939 ns 551229068 ns 54620 bytes=2.048k bytes_per_second=150.948M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):11/manual_time 12907 ns 546008924 ns 54620 bytes=2.048k bytes_per_second=151.325M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):11/manual_time 12915 ns 546485442 ns 54620 bytes=2.048k bytes_per_second=151.233M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):11/manual_time_mean 12886 ns 547174885 ns 5 bytes=2.048k bytes_per_second=151.573M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):11/manual_time_median 12907 ns 546423250 ns 5 bytes=2.048k bytes_per_second=151.325M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):11/manual_time_stddev 48.8 ns 2287487 ns 5 bytes=0 bytes_per_second=587.788k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):11/manual_time_cv 0.38 % 0.42 % 5 bytes=0.00% bytes_per_second=0.38% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):12/manual_time 12926 ns 544189094 ns 53998 bytes=4.096k bytes_per_second=302.191M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):12/manual_time 12955 ns 544867435 ns 53998 bytes=4.096k bytes_per_second=301.527M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):12/manual_time 12948 ns 545611488 ns 53998 bytes=4.096k bytes_per_second=301.696M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):12/manual_time 12938 ns 544035703 ns 53998 bytes=4.096k bytes_per_second=301.926M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):12/manual_time 12927 ns 544282256 ns 53998 bytes=4.096k bytes_per_second=302.176M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):12/manual_time_mean 12939 ns 544597195 ns 5 bytes=4.096k bytes_per_second=301.903M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):12/manual_time_median 12938 ns 544282256 ns 5 bytes=4.096k bytes_per_second=301.926M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):12/manual_time_stddev 12.5 ns 648619 ns 5 bytes=0 bytes_per_second=299.727k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):12/manual_time_cv 0.10 % 0.12 % 5 bytes=0.00% bytes_per_second=0.10% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):13/manual_time 13086 ns 548141565 ns 53454 bytes=8.192k bytes_per_second=596.998M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):13/manual_time 13084 ns 547150345 ns 53454 bytes=8.192k bytes_per_second=597.106M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):13/manual_time 13082 ns 543214252 ns 53454 bytes=8.192k bytes_per_second=597.197M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):13/manual_time 13038 ns 545802693 ns 53454 bytes=8.192k bytes_per_second=599.214M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):13/manual_time 13111 ns 547435518 ns 53454 bytes=8.192k bytes_per_second=595.866M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):13/manual_time_mean 13080 ns 546348875 ns 5 bytes=8.192k bytes_per_second=597.276M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):13/manual_time_median 13084 ns 547150345 ns 5 bytes=8.192k bytes_per_second=597.106M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):13/manual_time_stddev 26.5 ns 1946861 ns 5 bytes=0 bytes_per_second=1.21019M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):13/manual_time_cv 0.20 % 0.36 % 5 bytes=0.00% bytes_per_second=0.20% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):14/manual_time 13429 ns 541291598 ns 52056 bytes=16.384k bytes_per_second=1.13624G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):14/manual_time 13449 ns 544402303 ns 52056 bytes=16.384k bytes_per_second=1.13454G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):14/manual_time 13505 ns 541428141 ns 52056 bytes=16.384k bytes_per_second=1.12982G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):14/manual_time 13444 ns 541774994 ns 52056 bytes=16.384k bytes_per_second=1.13502G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):14/manual_time 13433 ns 541507021 ns 52056 bytes=16.384k bytes_per_second=1.13596G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):14/manual_time_mean 13452 ns 542080811 ns 5 bytes=16.384k bytes_per_second=1.13432G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):14/manual_time_median 13444 ns 541507021 ns 5 bytes=16.384k bytes_per_second=1.13502G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):14/manual_time_stddev 31.0 ns 1309668 ns 5 bytes=0 bytes_per_second=2.66848M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):14/manual_time_cv 0.23 % 0.24 % 5 bytes=0.00% bytes_per_second=0.23% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):15/manual_time 14088 ns 535168158 ns 49753 bytes=32.768k bytes_per_second=2.1662G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):15/manual_time 14077 ns 537280524 ns 49753 bytes=32.768k bytes_per_second=2.16786G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):15/manual_time 14182 ns 537145649 ns 49753 bytes=32.768k bytes_per_second=2.15192G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):15/manual_time 14070 ns 535424721 ns 49753 bytes=32.768k bytes_per_second=2.16899G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):15/manual_time 14092 ns 534686914 ns 49753 bytes=32.768k bytes_per_second=2.16559G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):15/manual_time_mean 14102 ns 535941193 ns 5 bytes=32.768k bytes_per_second=2.16411G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):15/manual_time_median 14088 ns 535424721 ns 5 bytes=32.768k bytes_per_second=2.1662G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):15/manual_time_stddev 45.5 ns 1191854 ns 5 bytes=0 bytes_per_second=7.11647M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):15/manual_time_cv 0.32 % 0.22 % 5 bytes=0.00% bytes_per_second=0.32% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):16/manual_time 16604 ns 525011229 ns 43073 bytes=65.536k bytes_per_second=3.67591G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):16/manual_time 16408 ns 517299050 ns 43073 bytes=65.536k bytes_per_second=3.71975G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):16/manual_time 16472 ns 520311959 ns 43073 bytes=65.536k bytes_per_second=3.70528G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):16/manual_time 16297 ns 515492066 ns 43073 bytes=65.536k bytes_per_second=3.74509G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):16/manual_time 16456 ns 518010125 ns 43073 bytes=65.536k bytes_per_second=3.70888G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):16/manual_time_mean 16448 ns 519224886 ns 5 bytes=65.536k bytes_per_second=3.71098G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):16/manual_time_median 16456 ns 518010125 ns 5 bytes=65.536k bytes_per_second=3.70888G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):16/manual_time_stddev 111 ns 3666808 ns 5 bytes=0 bytes_per_second=25.636M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):16/manual_time_cv 0.67 % 0.71 % 5 bytes=0.00% bytes_per_second=0.67% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):17/manual_time 19963 ns 495744894 ns 35050 bytes=131.072k bytes_per_second=6.11495G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):17/manual_time 19974 ns 496546936 ns 35050 bytes=131.072k bytes_per_second=6.11157G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):17/manual_time 19959 ns 495529356 ns 35050 bytes=131.072k bytes_per_second=6.11601G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):17/manual_time 19976 ns 496188006 ns 35050 bytes=131.072k bytes_per_second=6.11082G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):17/manual_time 19979 ns 496622039 ns 35050 bytes=131.072k bytes_per_second=6.10978G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):17/manual_time_mean 19970 ns 496126246 ns 5 bytes=131.072k bytes_per_second=6.11263G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):17/manual_time_median 19974 ns 496188006 ns 5 bytes=131.072k bytes_per_second=6.11157G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):17/manual_time_stddev 8.84 ns 481745 ns 5 bytes=0 bytes_per_second=2.77256M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):17/manual_time_cv 0.04 % 0.10 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):18/manual_time 23051 ns 505399413 ns 30354 bytes=262.144k bytes_per_second=10.5915G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):18/manual_time 23073 ns 506113904 ns 30354 bytes=262.144k bytes_per_second=10.5814G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):18/manual_time 23077 ns 506863614 ns 30354 bytes=262.144k bytes_per_second=10.5792G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):18/manual_time 23068 ns 507592180 ns 30354 bytes=262.144k bytes_per_second=10.5836G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):18/manual_time 23066 ns 507622877 ns 30354 bytes=262.144k bytes_per_second=10.5845G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):18/manual_time_mean 23067 ns 506718398 ns 5 bytes=262.144k bytes_per_second=10.584G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):18/manual_time_median 23068 ns 506863614 ns 5 bytes=262.144k bytes_per_second=10.5836G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):18/manual_time_stddev 10.2 ns 962782 ns 5 bytes=0 bytes_per_second=4.78403M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):18/manual_time_cv 0.04 % 0.19 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):19/manual_time 33942 ns 510052060 ns 20558 bytes=524.288k bytes_per_second=14.3858G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):19/manual_time 34056 ns 509168109 ns 20558 bytes=524.288k bytes_per_second=14.3378G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):19/manual_time 34076 ns 510743686 ns 20558 bytes=524.288k bytes_per_second=14.3293G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):19/manual_time 34023 ns 510464610 ns 20558 bytes=524.288k bytes_per_second=14.3516G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):19/manual_time 34020 ns 510233609 ns 20558 bytes=524.288k bytes_per_second=14.3526G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):19/manual_time_mean 34023 ns 510132415 ns 5 bytes=524.288k bytes_per_second=14.3514G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):19/manual_time_median 34023 ns 510233609 ns 5 bytes=524.288k bytes_per_second=14.3516G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):19/manual_time_stddev 51.1 ns 598036 ns 5 bytes=0 bytes_per_second=22.088M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):19/manual_time_cv 0.15 % 0.12 % 5 bytes=0.00% bytes_per_second=0.15% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):20/manual_time 54873 ns 525119636 ns 12697 bytes=1048.58k bytes_per_second=17.7966G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):20/manual_time 54700 ns 524454800 ns 12697 bytes=1048.58k bytes_per_second=17.8532G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):20/manual_time 54970 ns 526177828 ns 12697 bytes=1048.58k bytes_per_second=17.7653G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):20/manual_time 54874 ns 525092378 ns 12697 bytes=1048.58k bytes_per_second=17.7964G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):20/manual_time 54879 ns 525181196 ns 12697 bytes=1048.58k bytes_per_second=17.7949G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):20/manual_time_mean 54859 ns 525205168 ns 5 bytes=1048.58k bytes_per_second=17.8013G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):20/manual_time_median 54874 ns 525119636 ns 5 bytes=1048.58k bytes_per_second=17.7964G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):20/manual_time_stddev 98.2 ns 618412 ns 5 bytes=0 bytes_per_second=32.6833M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):20/manual_time_cv 0.18 % 0.12 % 5 bytes=0.00% bytes_per_second=0.18% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):21/manual_time 96021 ns 502518711 ns 7256 bytes=2.09715M bytes_per_second=20.3406G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):21/manual_time 96101 ns 503040536 ns 7256 bytes=2.09715M bytes_per_second=20.3236G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):21/manual_time 96058 ns 502274878 ns 7256 bytes=2.09715M bytes_per_second=20.3328G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):21/manual_time 95859 ns 501648311 ns 7256 bytes=2.09715M bytes_per_second=20.375G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):21/manual_time 95841 ns 502003653 ns 7256 bytes=2.09715M bytes_per_second=20.3787G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):21/manual_time_mean 95976 ns 502297218 ns 5 bytes=2.09715M bytes_per_second=20.3502G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):21/manual_time_median 96021 ns 502274878 ns 5 bytes=2.09715M bytes_per_second=20.3406G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):21/manual_time_stddev 119 ns 526626 ns 5 bytes=0 bytes_per_second=25.7621M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):21/manual_time_cv 0.12 % 0.10 % 5 bytes=0.00% bytes_per_second=0.12% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):22/manual_time 181244 ns 487970791 ns 3852 bytes=4.1943M bytes_per_second=21.5524G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):22/manual_time 181815 ns 478957347 ns 3852 bytes=4.1943M bytes_per_second=21.4848G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):22/manual_time 181307 ns 488515856 ns 3852 bytes=4.1943M bytes_per_second=21.545G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):22/manual_time 181784 ns 479324361 ns 3852 bytes=4.1943M bytes_per_second=21.4884G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):22/manual_time 181330 ns 488078043 ns 3852 bytes=4.1943M bytes_per_second=21.5422G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):22/manual_time_mean 181496 ns 484569279 ns 5 bytes=4.1943M bytes_per_second=21.5225G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):22/manual_time_median 181330 ns 487970791 ns 5 bytes=4.1943M bytes_per_second=21.5422G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):22/manual_time_stddev 279 ns 4961353 ns 5 bytes=0 bytes_per_second=33.8574M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):22/manual_time_cv 0.15 % 1.02 % 5 bytes=0.00% bytes_per_second=0.15% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):23/manual_time 349182 ns 476862865 ns 2004 bytes=8.38861M bytes_per_second=22.3737G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):23/manual_time 349160 ns 475804956 ns 2004 bytes=8.38861M bytes_per_second=22.3751G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):23/manual_time 349264 ns 477081262 ns 2004 bytes=8.38861M bytes_per_second=22.3685G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):23/manual_time 349349 ns 476975411 ns 2004 bytes=8.38861M bytes_per_second=22.363G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):23/manual_time 349269 ns 477300840 ns 2004 bytes=8.38861M bytes_per_second=22.3682G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):23/manual_time_mean 349245 ns 476805067 ns 5 bytes=8.38861M bytes_per_second=22.3697G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):23/manual_time_median 349264 ns 476975411 ns 5 bytes=8.38861M bytes_per_second=22.3685G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):23/manual_time_stddev 75.6 ns 581948 ns 5 bytes=0 bytes_per_second=4.95836M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):23/manual_time_cv 0.02 % 0.12 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):24/manual_time 681828 ns 482101483 ns 1026 bytes=16.7772M bytes_per_second=22.9163G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):24/manual_time 681485 ns 481354780 ns 1026 bytes=16.7772M bytes_per_second=22.9279G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):24/manual_time 681808 ns 481496086 ns 1026 bytes=16.7772M bytes_per_second=22.917G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):24/manual_time 681748 ns 481717586 ns 1026 bytes=16.7772M bytes_per_second=22.919G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):24/manual_time 681863 ns 481539157 ns 1026 bytes=16.7772M bytes_per_second=22.9152G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):24/manual_time_mean 681746 ns 481641818 ns 5 bytes=16.7772M bytes_per_second=22.9191G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):24/manual_time_median 681808 ns 481539157 ns 5 bytes=16.7772M bytes_per_second=22.917G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):24/manual_time_stddev 152 ns 287750 ns 5 bytes=0 bytes_per_second=5.23256M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):24/manual_time_cv 0.02 % 0.06 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):25/manual_time 1280901 ns 613293266 ns 561 bytes=33.5544M bytes_per_second=24.3969G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):25/manual_time 1249369 ns 661086857 ns 561 bytes=33.5544M bytes_per_second=25.0126G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):25/manual_time 1269103 ns 628395692 ns 561 bytes=33.5544M bytes_per_second=24.6237G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):25/manual_time 1253856 ns 655096074 ns 561 bytes=33.5544M bytes_per_second=24.9231G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):25/manual_time 1275865 ns 615956502 ns 561 bytes=33.5544M bytes_per_second=24.4932G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):25/manual_time_mean 1265819 ns 634765678 ns 5 bytes=33.5544M bytes_per_second=24.6899G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):25/manual_time_median 1269103 ns 628395692 ns 5 bytes=33.5544M bytes_per_second=24.6237G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):25/manual_time_stddev 13719 ns 22144727 ns 5 bytes=0 bytes_per_second=274.52M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):25/manual_time_cv 1.08 % 3.49 % 5 bytes=0.00% bytes_per_second=1.09% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):26/manual_time 2401574 ns 827974291 ns 292 bytes=67.1089M bytes_per_second=26.0246G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):26/manual_time 2404026 ns 823356890 ns 292 bytes=67.1089M bytes_per_second=25.9981G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):26/manual_time 2401519 ns 824738929 ns 292 bytes=67.1089M bytes_per_second=26.0252G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):26/manual_time 2402018 ns 811476079 ns 292 bytes=67.1089M bytes_per_second=26.0198G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):26/manual_time 2400438 ns 811006494 ns 292 bytes=67.1089M bytes_per_second=26.0369G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):26/manual_time_mean 2401915 ns 819710537 ns 5 bytes=67.1089M bytes_per_second=26.0209G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):26/manual_time_median 2401574 ns 823356890 ns 5 bytes=67.1089M bytes_per_second=26.0246G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):26/manual_time_stddev 1316 ns 7912599 ns 5 bytes=0 bytes_per_second=14.5893M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):26/manual_time_cv 0.05 % 0.97 % 5 bytes=0.00% bytes_per_second=0.05% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):27/manual_time 4776640 ns 904705549 ns 147 bytes=134.218M bytes_per_second=26.169G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):27/manual_time 4777145 ns 909476214 ns 147 bytes=134.218M bytes_per_second=26.1663G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):27/manual_time 4776168 ns 903083930 ns 147 bytes=134.218M bytes_per_second=26.1716G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):27/manual_time 4777925 ns 905779115 ns 147 bytes=134.218M bytes_per_second=26.162G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):27/manual_time 4776812 ns 907840184 ns 147 bytes=134.218M bytes_per_second=26.1681G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):27/manual_time_mean 4776938 ns 906176998 ns 5 bytes=134.218M bytes_per_second=26.1674G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):27/manual_time_median 4776812 ns 905779115 ns 5 bytes=134.218M bytes_per_second=26.1681G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):27/manual_time_stddev 655 ns 2526933 ns 5 bytes=0 bytes_per_second=3.67375M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):27/manual_time_cv 0.01 % 0.28 % 5 bytes=0.00% bytes_per_second=0.01% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):28/manual_time 9528581 ns 974389377 ns 73 bytes=268.435M bytes_per_second=26.2369G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):28/manual_time 9528662 ns 958821927 ns 73 bytes=268.435M bytes_per_second=26.2366G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):28/manual_time 9527888 ns 960520072 ns 73 bytes=268.435M bytes_per_second=26.2388G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):28/manual_time 9527533 ns 960278943 ns 73 bytes=268.435M bytes_per_second=26.2397G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):28/manual_time 9527594 ns 967636722 ns 73 bytes=268.435M bytes_per_second=26.2396G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):28/manual_time_mean 9528051 ns 964329408 ns 5 bytes=268.435M bytes_per_second=26.2383G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):28/manual_time_median 9527888 ns 960520072 ns 5 bytes=268.435M bytes_per_second=26.2388G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):28/manual_time_stddev 538 ns 6583900 ns 5 bytes=0 bytes_per_second=1.51711M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):28/manual_time_cv 0.01 % 0.68 % 5 bytes=0.00% bytes_per_second=0.01% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):29/manual_time 19035296 ns 1033070361 ns 37 bytes=536.871M bytes_per_second=26.267G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):29/manual_time 19036645 ns 1033545764 ns 37 bytes=536.871M bytes_per_second=26.2651G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):29/manual_time 19032784 ns 1060158163 ns 37 bytes=536.871M bytes_per_second=26.2705G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):29/manual_time 19034527 ns 1059246902 ns 37 bytes=536.871M bytes_per_second=26.2681G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):29/manual_time 19034224 ns 1062930212 ns 37 bytes=536.871M bytes_per_second=26.2685G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):29/manual_time_mean 19034695 ns 1049790280 ns 5 bytes=536.871M bytes_per_second=26.2678G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):29/manual_time_median 19034527 ns 1059246902 ns 5 bytes=536.871M bytes_per_second=26.2681G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):29/manual_time_stddev 1420 ns 15108098 ns 5 bytes=0 bytes_per_second=2.00683M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):29/manual_time_cv 0.01 % 1.44 % 5 bytes=0.00% bytes_per_second=0.01% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):30/manual_time 37999730 ns 1130163201 ns 18 bytes=1073.74M bytes_per_second=26.316G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):30/manual_time 37999907 ns 1128575605 ns 18 bytes=1073.74M bytes_per_second=26.3159G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):30/manual_time 37986066 ns 1129896157 ns 18 bytes=1073.74M bytes_per_second=26.3254G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):30/manual_time 37989781 ns 1129767792 ns 18 bytes=1073.74M bytes_per_second=26.3229G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):30/manual_time 37990643 ns 1127958549 ns 18 bytes=1073.74M bytes_per_second=26.3223G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):30/manual_time_mean 37993225 ns 1129272261 ns 5 bytes=1073.74M bytes_per_second=26.3205G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):30/manual_time_median 37990643 ns 1129767792 ns 5 bytes=1073.74M bytes_per_second=26.3223G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):30/manual_time_stddev 6260 ns 953905 ns 5 bytes=0 bytes_per_second=4.44056M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PinnedToGPU/0/0/log2(N):30/manual_time_cv 0.02 % 0.08 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +[2023-10-09 17:44:02.970] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 17:44:02.970] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:44:03.141] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:44:03.142] [scope] [info] recorded CPU goveror +[2023-10-09 17:44:03.142] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:44:03.142] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:44:05-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1813.34 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 2.29, 5.25, 19.34 +------------------------------------------------------------------------------------------------------------------------------ +Benchmark Time CPU Iterations UserCounters... +------------------------------------------------------------------------------------------------------------------------------ +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):8/manual_time 7579 ns 14577 ns 92456 bytes=256 bytes_per_second=32.2124M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):8/manual_time 7582 ns 14620 ns 92456 bytes=256 bytes_per_second=32.2014M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):8/manual_time 7612 ns 14589 ns 92456 bytes=256 bytes_per_second=32.0747M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):8/manual_time 7565 ns 14601 ns 92456 bytes=256 bytes_per_second=32.2717M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):8/manual_time 7612 ns 14579 ns 92456 bytes=256 bytes_per_second=32.0713M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):8/manual_time_mean 7590 ns 14593 ns 5 bytes=256 bytes_per_second=32.1663M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):8/manual_time_median 7582 ns 14589 ns 5 bytes=256 bytes_per_second=32.2014M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):8/manual_time_stddev 21.1 ns 17.7 ns 5 bytes=0 bytes_per_second=91.4346k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):8/manual_time_cv 0.28 % 0.12 % 5 bytes=0.00% bytes_per_second=0.28% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):9/manual_time 8026 ns 14984 ns 86703 bytes=512 bytes_per_second=60.8401M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):9/manual_time 8062 ns 15055 ns 86703 bytes=512 bytes_per_second=60.5625M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):9/manual_time 8042 ns 14996 ns 86703 bytes=512 bytes_per_second=60.7192M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):9/manual_time 8051 ns 15062 ns 86703 bytes=512 bytes_per_second=60.6513M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):9/manual_time 8028 ns 14983 ns 86703 bytes=512 bytes_per_second=60.8211M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):9/manual_time_mean 8042 ns 15016 ns 5 bytes=512 bytes_per_second=60.7188M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):9/manual_time_median 8042 ns 14996 ns 5 bytes=512 bytes_per_second=60.7192M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):9/manual_time_stddev 15.4 ns 39.1 ns 5 bytes=0 bytes_per_second=119.173k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):9/manual_time_cv 0.19 % 0.26 % 5 bytes=0.00% bytes_per_second=0.19% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):10/manual_time 9012 ns 16001 ns 77804 bytes=1024 bytes_per_second=108.362M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):10/manual_time 9063 ns 16098 ns 77804 bytes=1024 bytes_per_second=107.755M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):10/manual_time 8852 ns 15874 ns 77804 bytes=1024 bytes_per_second=110.32M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):10/manual_time 9005 ns 16072 ns 77804 bytes=1024 bytes_per_second=108.443M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):10/manual_time 8864 ns 15858 ns 77804 bytes=1024 bytes_per_second=110.172M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):10/manual_time_mean 8959 ns 15980 ns 5 bytes=1024 bytes_per_second=109.01M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):10/manual_time_median 9005 ns 16001 ns 5 bytes=1024 bytes_per_second=108.443M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):10/manual_time_stddev 95.1 ns 111 ns 5 bytes=0 bytes_per_second=1.16005M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):10/manual_time_cv 1.06 % 0.69 % 5 bytes=0.00% bytes_per_second=1.06% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):11/manual_time 9612 ns 16555 ns 72804 bytes=2.048k bytes_per_second=203.205M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):11/manual_time 9617 ns 16590 ns 72804 bytes=2.048k bytes_per_second=203.087M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):11/manual_time 9608 ns 16573 ns 72804 bytes=2.048k bytes_per_second=203.277M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):11/manual_time 9613 ns 16592 ns 72804 bytes=2.048k bytes_per_second=203.166M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):11/manual_time 9607 ns 16534 ns 72804 bytes=2.048k bytes_per_second=203.306M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):11/manual_time_mean 9611 ns 16569 ns 5 bytes=2.048k bytes_per_second=203.208M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):11/manual_time_median 9612 ns 16573 ns 5 bytes=2.048k bytes_per_second=203.205M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):11/manual_time_stddev 4.14 ns 24.5 ns 5 bytes=0 bytes_per_second=89.598k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):11/manual_time_cv 0.04 % 0.15 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):12/manual_time 10153 ns 17211 ns 68983 bytes=4.096k bytes_per_second=384.727M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):12/manual_time 10149 ns 17228 ns 68983 bytes=4.096k bytes_per_second=384.88M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):12/manual_time 10152 ns 17249 ns 68983 bytes=4.096k bytes_per_second=384.787M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):12/manual_time 10150 ns 17233 ns 68983 bytes=4.096k bytes_per_second=384.847M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):12/manual_time 10151 ns 17195 ns 68983 bytes=4.096k bytes_per_second=384.805M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):12/manual_time_mean 10151 ns 17223 ns 5 bytes=4.096k bytes_per_second=384.809M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):12/manual_time_median 10151 ns 17228 ns 5 bytes=4.096k bytes_per_second=384.805M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):12/manual_time_stddev 1.54 ns 20.5 ns 5 bytes=0 bytes_per_second=59.9289k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):12/manual_time_cv 0.02 % 0.12 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):13/manual_time 11223 ns 18536 ns 62388 bytes=8.192k bytes_per_second=696.105M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):13/manual_time 11223 ns 18605 ns 62388 bytes=8.192k bytes_per_second=696.135M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):13/manual_time 11223 ns 18539 ns 62388 bytes=8.192k bytes_per_second=696.116M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):13/manual_time 11222 ns 18537 ns 62388 bytes=8.192k bytes_per_second=696.201M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):13/manual_time 11221 ns 18476 ns 62388 bytes=8.192k bytes_per_second=696.252M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):13/manual_time_mean 11222 ns 18539 ns 5 bytes=8.192k bytes_per_second=696.162M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):13/manual_time_median 11223 ns 18537 ns 5 bytes=8.192k bytes_per_second=696.135M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):13/manual_time_stddev 1.01 ns 45.4 ns 5 bytes=0 bytes_per_second=63.9499k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):13/manual_time_cv 0.01 % 0.25 % 5 bytes=0.00% bytes_per_second=0.01% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):14/manual_time 11229 ns 18931 ns 62366 bytes=16.384k bytes_per_second=1.35885G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):14/manual_time 11225 ns 19027 ns 62366 bytes=16.384k bytes_per_second=1.35939G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):14/manual_time 11230 ns 18938 ns 62366 bytes=16.384k bytes_per_second=1.35877G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):14/manual_time 11228 ns 19016 ns 62366 bytes=16.384k bytes_per_second=1.35896G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):14/manual_time 11226 ns 18887 ns 62366 bytes=16.384k bytes_per_second=1.35929G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):14/manual_time_mean 11228 ns 18960 ns 5 bytes=16.384k bytes_per_second=1.35905G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):14/manual_time_median 11228 ns 18938 ns 5 bytes=16.384k bytes_per_second=1.35896G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):14/manual_time_stddev 2.27 ns 59.7 ns 5 bytes=0 bytes_per_second=287.636k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):14/manual_time_cv 0.02 % 0.31 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):15/manual_time 11497 ns 19542 ns 60920 bytes=32.768k bytes_per_second=2.65432G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):15/manual_time 11489 ns 19561 ns 60920 bytes=32.768k bytes_per_second=2.65626G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):15/manual_time 11499 ns 19526 ns 60920 bytes=32.768k bytes_per_second=2.65401G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):15/manual_time 11491 ns 19555 ns 60920 bytes=32.768k bytes_per_second=2.65584G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):15/manual_time 11500 ns 19540 ns 60920 bytes=32.768k bytes_per_second=2.6537G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):15/manual_time_mean 11495 ns 19545 ns 5 bytes=32.768k bytes_per_second=2.65482G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):15/manual_time_median 11497 ns 19542 ns 5 bytes=32.768k bytes_per_second=2.65432G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):15/manual_time_stddev 4.96 ns 13.7 ns 5 bytes=0 bytes_per_second=1.17373M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):15/manual_time_cv 0.04 % 0.07 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):16/manual_time 12422 ns 22861 ns 56362 bytes=65.536k bytes_per_second=4.91332G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):16/manual_time 12421 ns 22947 ns 56362 bytes=65.536k bytes_per_second=4.91401G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):16/manual_time 12422 ns 22861 ns 56362 bytes=65.536k bytes_per_second=4.91355G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):16/manual_time 12409 ns 22932 ns 56362 bytes=65.536k bytes_per_second=4.91846G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):16/manual_time 12418 ns 22897 ns 56362 bytes=65.536k bytes_per_second=4.91518G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):16/manual_time_mean 12418 ns 22900 ns 5 bytes=65.536k bytes_per_second=4.91491G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):16/manual_time_median 12421 ns 22897 ns 5 bytes=65.536k bytes_per_second=4.91401G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):16/manual_time_stddev 5.34 ns 40.0 ns 5 bytes=0 bytes_per_second=2.16533M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):16/manual_time_cv 0.04 % 0.17 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):17/manual_time 14541 ns 28082 ns 48140 bytes=131.072k bytes_per_second=8.39503G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):17/manual_time 14538 ns 28189 ns 48140 bytes=131.072k bytes_per_second=8.39686G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):17/manual_time 14541 ns 28087 ns 48140 bytes=131.072k bytes_per_second=8.39467G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):17/manual_time 14541 ns 28208 ns 48140 bytes=131.072k bytes_per_second=8.39469G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):17/manual_time 14544 ns 28107 ns 48140 bytes=131.072k bytes_per_second=8.39311G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):17/manual_time_mean 14541 ns 28135 ns 5 bytes=131.072k bytes_per_second=8.39487G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):17/manual_time_median 14541 ns 28107 ns 5 bytes=131.072k bytes_per_second=8.39469G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):17/manual_time_stddev 2.31 ns 59.5 ns 5 bytes=0 bytes_per_second=1.36665M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):17/manual_time_cv 0.02 % 0.21 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):18/manual_time 19529 ns 41785 ns 35855 bytes=262.144k bytes_per_second=12.5012G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):18/manual_time 19521 ns 41845 ns 35855 bytes=262.144k bytes_per_second=12.5066G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):18/manual_time 19529 ns 41858 ns 35855 bytes=262.144k bytes_per_second=12.5014G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):18/manual_time 19519 ns 41849 ns 35855 bytes=262.144k bytes_per_second=12.5076G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):18/manual_time 19528 ns 41837 ns 35855 bytes=262.144k bytes_per_second=12.5019G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):18/manual_time_mean 19525 ns 41835 ns 5 bytes=262.144k bytes_per_second=12.5037G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):18/manual_time_median 19528 ns 41845 ns 5 bytes=262.144k bytes_per_second=12.5019G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):18/manual_time_stddev 4.84 ns 28.8 ns 5 bytes=0 bytes_per_second=3.17372M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):18/manual_time_cv 0.02 % 0.07 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):19/manual_time 33826 ns 70191 ns 20705 bytes=524.288k bytes_per_second=14.4353G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):19/manual_time 33809 ns 70174 ns 20705 bytes=524.288k bytes_per_second=14.4425G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):19/manual_time 33823 ns 70103 ns 20705 bytes=524.288k bytes_per_second=14.4362G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):19/manual_time 33810 ns 70249 ns 20705 bytes=524.288k bytes_per_second=14.4421G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):19/manual_time 33824 ns 70156 ns 20705 bytes=524.288k bytes_per_second=14.436G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):19/manual_time_mean 33818 ns 70175 ns 5 bytes=524.288k bytes_per_second=14.4384G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):19/manual_time_median 33823 ns 70174 ns 5 bytes=524.288k bytes_per_second=14.4362G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):19/manual_time_stddev 8.31 ns 52.9 ns 5 bytes=0 bytes_per_second=3.63342M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):19/manual_time_cv 0.02 % 0.08 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):20/manual_time 57389 ns 121381 ns 12172 bytes=1048.58k bytes_per_second=17.0165G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):20/manual_time 57378 ns 121333 ns 12172 bytes=1048.58k bytes_per_second=17.0198G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):20/manual_time 57365 ns 121312 ns 12172 bytes=1048.58k bytes_per_second=17.0237G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):20/manual_time 57362 ns 121279 ns 12172 bytes=1048.58k bytes_per_second=17.0244G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):20/manual_time 57332 ns 121280 ns 12172 bytes=1048.58k bytes_per_second=17.0336G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):20/manual_time_mean 57365 ns 121317 ns 5 bytes=1048.58k bytes_per_second=17.0236G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):20/manual_time_median 57365 ns 121312 ns 5 bytes=1048.58k bytes_per_second=17.0237G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):20/manual_time_stddev 21.6 ns 42.4 ns 5 bytes=0 bytes_per_second=6.5658M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):20/manual_time_cv 0.04 % 0.03 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):21/manual_time 121425 ns 229526 ns 5772 bytes=2.09715M bytes_per_second=16.085G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):21/manual_time 121594 ns 229842 ns 5772 bytes=2.09715M bytes_per_second=16.0627G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):21/manual_time 121437 ns 229453 ns 5772 bytes=2.09715M bytes_per_second=16.0834G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):21/manual_time 121403 ns 230117 ns 5772 bytes=2.09715M bytes_per_second=16.0879G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):21/manual_time 121583 ns 230116 ns 5772 bytes=2.09715M bytes_per_second=16.0641G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):21/manual_time_mean 121488 ns 229811 ns 5 bytes=2.09715M bytes_per_second=16.0766G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):21/manual_time_median 121437 ns 229842 ns 5 bytes=2.09715M bytes_per_second=16.0834G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):21/manual_time_stddev 92.2 ns 315 ns 5 bytes=0 bytes_per_second=12.4916M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):21/manual_time_cv 0.08 % 0.14 % 5 bytes=0.00% bytes_per_second=0.08% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):22/manual_time 230118 ns 437704 ns 3041 bytes=4.1943M bytes_per_second=16.975G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):22/manual_time 229975 ns 437211 ns 3041 bytes=4.1943M bytes_per_second=16.9856G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):22/manual_time 230023 ns 437265 ns 3041 bytes=4.1943M bytes_per_second=16.982G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):22/manual_time 230044 ns 437848 ns 3041 bytes=4.1943M bytes_per_second=16.9804G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):22/manual_time 230053 ns 437273 ns 3041 bytes=4.1943M bytes_per_second=16.9798G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):22/manual_time_mean 230043 ns 437460 ns 5 bytes=4.1943M bytes_per_second=16.9806G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):22/manual_time_median 230044 ns 437273 ns 5 bytes=4.1943M bytes_per_second=16.9804G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):22/manual_time_stddev 51.9 ns 294 ns 5 bytes=0 bytes_per_second=3.92017M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):22/manual_time_cv 0.02 % 0.07 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):23/manual_time 452472 ns 889985 ns 1547 bytes=8.38861M bytes_per_second=17.2663G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):23/manual_time 452325 ns 889898 ns 1547 bytes=8.38861M bytes_per_second=17.2719G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):23/manual_time 452650 ns 889992 ns 1547 bytes=8.38861M bytes_per_second=17.2595G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):23/manual_time 452427 ns 890074 ns 1547 bytes=8.38861M bytes_per_second=17.268G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):23/manual_time 452351 ns 889865 ns 1547 bytes=8.38861M bytes_per_second=17.2709G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):23/manual_time_mean 452445 ns 889963 ns 5 bytes=8.38861M bytes_per_second=17.2673G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):23/manual_time_median 452427 ns 889985 ns 5 bytes=8.38861M bytes_per_second=17.268G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):23/manual_time_stddev 129 ns 82.7 ns 5 bytes=0 bytes_per_second=5.0344M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):23/manual_time_cv 0.03 % 0.01 % 5 bytes=0.00% bytes_per_second=0.03% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):24/manual_time 889067 ns 1790009 ns 786 bytes=16.7772M bytes_per_second=17.5746G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):24/manual_time 888571 ns 1786728 ns 786 bytes=16.7772M bytes_per_second=17.5844G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):24/manual_time 888764 ns 1786225 ns 786 bytes=16.7772M bytes_per_second=17.5806G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):24/manual_time 888502 ns 1787164 ns 786 bytes=16.7772M bytes_per_second=17.5858G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):24/manual_time 888806 ns 1786989 ns 786 bytes=16.7772M bytes_per_second=17.5798G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):24/manual_time_mean 888742 ns 1787423 ns 5 bytes=16.7772M bytes_per_second=17.581G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):24/manual_time_median 888764 ns 1786989 ns 5 bytes=16.7772M bytes_per_second=17.5806G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):24/manual_time_stddev 222 ns 1488 ns 5 bytes=0 bytes_per_second=4.49603M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):24/manual_time_cv 0.02 % 0.08 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):25/manual_time 9659482 ns 18739817 ns 71 bytes=33.5544M bytes_per_second=3.23516G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):25/manual_time 9616969 ns 18676453 ns 71 bytes=33.5544M bytes_per_second=3.24946G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):25/manual_time 9635899 ns 18689815 ns 71 bytes=33.5544M bytes_per_second=3.24308G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):25/manual_time 9631547 ns 18714126 ns 71 bytes=33.5544M bytes_per_second=3.24455G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):25/manual_time 9664034 ns 18708799 ns 71 bytes=33.5544M bytes_per_second=3.23364G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):25/manual_time_mean 9641586 ns 18705802 ns 5 bytes=33.5544M bytes_per_second=3.24118G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):25/manual_time_median 9635899 ns 18708799 ns 5 bytes=33.5544M bytes_per_second=3.24308G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):25/manual_time_stddev 19769 ns 24250 ns 5 bytes=0 bytes_per_second=6.80484M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):25/manual_time_cv 0.21 % 0.13 % 5 bytes=0.00% bytes_per_second=0.21% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):26/manual_time 18686963 ns 36070115 ns 37 bytes=67.1089M bytes_per_second=3.34458G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):26/manual_time 18743002 ns 36117253 ns 37 bytes=67.1089M bytes_per_second=3.33458G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):26/manual_time 18683266 ns 36069823 ns 37 bytes=67.1089M bytes_per_second=3.34524G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):26/manual_time 18715439 ns 36105855 ns 37 bytes=67.1089M bytes_per_second=3.33949G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):26/manual_time 18644849 ns 36049191 ns 37 bytes=67.1089M bytes_per_second=3.35213G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):26/manual_time_mean 18694704 ns 36082447 ns 5 bytes=67.1089M bytes_per_second=3.3432G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):26/manual_time_median 18686963 ns 36070115 ns 5 bytes=67.1089M bytes_per_second=3.34458G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):26/manual_time_stddev 36875 ns 28182 ns 5 bytes=0 bytes_per_second=6.75291M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):26/manual_time_cv 0.20 % 0.08 % 5 bytes=0.00% bytes_per_second=0.20% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):27/manual_time 36870042 ns 70217141 ns 19 bytes=134.218M bytes_per_second=3.39029G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):27/manual_time 36919785 ns 70309112 ns 19 bytes=134.218M bytes_per_second=3.38572G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):27/manual_time 36856585 ns 70264864 ns 19 bytes=134.218M bytes_per_second=3.39152G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):27/manual_time 36834472 ns 70236869 ns 19 bytes=134.218M bytes_per_second=3.39356G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):27/manual_time 36890968 ns 70260313 ns 19 bytes=134.218M bytes_per_second=3.38836G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):27/manual_time_mean 36874370 ns 70257660 ns 5 bytes=134.218M bytes_per_second=3.38989G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):27/manual_time_median 36870042 ns 70260313 ns 5 bytes=134.218M bytes_per_second=3.39029G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):27/manual_time_stddev 32653 ns 34570 ns 5 bytes=0 bytes_per_second=3.07331M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):27/manual_time_cv 0.09 % 0.05 % 5 bytes=0.00% bytes_per_second=0.09% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):28/manual_time 73235760 ns 136685434 ns 10 bytes=268.435M bytes_per_second=3.41363G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):28/manual_time 73415408 ns 136872730 ns 10 bytes=268.435M bytes_per_second=3.40528G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):28/manual_time 73812287 ns 137255593 ns 10 bytes=268.435M bytes_per_second=3.38697G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):28/manual_time 73454287 ns 136824267 ns 10 bytes=268.435M bytes_per_second=3.40348G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):28/manual_time 73310847 ns 136690078 ns 10 bytes=268.435M bytes_per_second=3.41014G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):28/manual_time_mean 73445718 ns 136865621 ns 5 bytes=268.435M bytes_per_second=3.4039G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):28/manual_time_median 73415408 ns 136824267 ns 5 bytes=268.435M bytes_per_second=3.40528G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):28/manual_time_stddev 222282 ns 232981 ns 5 bytes=0 bytes_per_second=10.522M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):28/manual_time_cv 0.30 % 0.17 % 5 bytes=0.00% bytes_per_second=0.30% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):29/manual_time 145783100 ns 261301310 ns 5 bytes=536.871M bytes_per_second=3.42975G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):29/manual_time 145780414 ns 261344300 ns 5 bytes=536.871M bytes_per_second=3.42982G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):29/manual_time 145335454 ns 260726372 ns 5 bytes=536.871M bytes_per_second=3.44032G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):29/manual_time 145926875 ns 261412034 ns 5 bytes=536.871M bytes_per_second=3.42637G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):29/manual_time 145133340 ns 260491423 ns 5 bytes=536.871M bytes_per_second=3.44511G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):29/manual_time_mean 145591837 ns 261055088 ns 5 bytes=536.871M bytes_per_second=3.43427G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):29/manual_time_median 145780414 ns 261301310 ns 5 bytes=536.871M bytes_per_second=3.42982G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):29/manual_time_stddev 339244 ns 417568 ns 5 bytes=0 bytes_per_second=8.20185M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):29/manual_time_cv 0.23 % 0.16 % 5 bytes=0.00% bytes_per_second=0.23% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):30/manual_time 284267232 ns 450656363 ns 2 bytes=1073.74M bytes_per_second=3.51782G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):30/manual_time 284685001 ns 451559402 ns 2 bytes=1073.74M bytes_per_second=3.51265G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):30/manual_time 284388185 ns 450859513 ns 2 bytes=1073.74M bytes_per_second=3.51632G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):30/manual_time 285485148 ns 451974126 ns 2 bytes=1073.74M bytes_per_second=3.50281G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):30/manual_time 284181297 ns 450904146 ns 2 bytes=1073.74M bytes_per_second=3.51888G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):30/manual_time_mean 284601372 ns 451190710 ns 5 bytes=1073.74M bytes_per_second=3.5137G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):30/manual_time_median 284388185 ns 450904146 ns 5 bytes=1073.74M bytes_per_second=3.51632G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):30/manual_time_stddev 529532 ns 553853 ns 5 bytes=0 bytes_per_second=6.6826M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_GPUToPageable/0/0/log2(N):30/manual_time_cv 0.19 % 0.12 % 5 bytes=0.00% bytes_per_second=0.19% hip_id=-nan% numa_id=-nan% +[2023-10-09 17:46:49.565] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 17:46:49.565] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Mon 09 Oct 2023 05:46:49 PM EDT diff --git a/results/r10-1465527.out b/results/r10-1465527.out new file mode 100644 index 0000000..fb7c5c0 --- /dev/null +++ b/results/r10-1465527.out @@ -0,0 +1,1690 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 05:38:26 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:38:29.022] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:38:29.023] [scope] [info] recorded CPU goveror +[2023-10-09 17:38:29.023] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:38:29.023] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:38:31-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1960.75 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.68, 11.22, 26.93 +------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +------------------------------------------------------------------------------------------------------------------------- +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):8/manual_time 7012 ns 1718050297 ns 100306 bytes=256 bytes_per_second=34.8199M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):8/manual_time 7001 ns 1717467596 ns 100306 bytes=256 bytes_per_second=34.8705M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):8/manual_time 7034 ns 1718915612 ns 100306 bytes=256 bytes_per_second=34.7105M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):8/manual_time 7016 ns 1717095274 ns 100306 bytes=256 bytes_per_second=34.7977M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):8/manual_time 7027 ns 1718753374 ns 100306 bytes=256 bytes_per_second=34.7412M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):8/manual_time_mean 7018 ns 1718056431 ns 5 bytes=256 bytes_per_second=34.788M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):8/manual_time_median 7016 ns 1718050297 ns 5 bytes=256 bytes_per_second=34.7977M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):8/manual_time_stddev 12.8 ns 789701 ns 5 bytes=0 bytes_per_second=64.9808k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):8/manual_time_cv 0.18 % 0.05 % 5 bytes=0.00% bytes_per_second=0.18% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):9/manual_time 7085 ns 1698900110 ns 99014 bytes=512 bytes_per_second=68.9155M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):9/manual_time 7074 ns 1700437623 ns 99014 bytes=512 bytes_per_second=69.0248M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):9/manual_time 7078 ns 1700241486 ns 99014 bytes=512 bytes_per_second=68.9863M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):9/manual_time 7068 ns 1696304490 ns 99014 bytes=512 bytes_per_second=69.088M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):9/manual_time 7085 ns 1699981737 ns 99014 bytes=512 bytes_per_second=68.913M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):9/manual_time_mean 7078 ns 1699173089 ns 5 bytes=512 bytes_per_second=68.9855M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):9/manual_time_median 7078 ns 1699981737 ns 5 bytes=512 bytes_per_second=68.9863M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):9/manual_time_stddev 7.64 ns 1710103 ns 5 bytes=0 bytes_per_second=76.2884k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):9/manual_time_cv 0.11 % 0.10 % 5 bytes=0.00% bytes_per_second=0.11% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):10/manual_time 7250 ns 1675307955 ns 97132 bytes=1024 bytes_per_second=134.697M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):10/manual_time 7186 ns 1673120637 ns 97132 bytes=1024 bytes_per_second=135.896M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):10/manual_time 7285 ns 1679662046 ns 97132 bytes=1024 bytes_per_second=134.056M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):10/manual_time 7191 ns 1671868442 ns 97132 bytes=1024 bytes_per_second=135.812M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):10/manual_time 7242 ns 1674746647 ns 97132 bytes=1024 bytes_per_second=134.844M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):10/manual_time_mean 7231 ns 1674941145 ns 5 bytes=1024 bytes_per_second=135.061M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):10/manual_time_median 7242 ns 1674746647 ns 5 bytes=1024 bytes_per_second=134.844M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):10/manual_time_stddev 41.9 ns 2967113 ns 5 bytes=0 bytes_per_second=801.646k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):10/manual_time_cv 0.58 % 0.18 % 5 bytes=0.00% bytes_per_second=0.58% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):11/manual_time 8035 ns 1552467330 ns 87997 bytes=2.048k bytes_per_second=243.077M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):11/manual_time 7927 ns 1548951986 ns 87997 bytes=2.048k bytes_per_second=246.376M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):11/manual_time 8133 ns 1558864186 ns 87997 bytes=2.048k bytes_per_second=240.144M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):11/manual_time 7996 ns 1550014351 ns 87997 bytes=2.048k bytes_per_second=244.26M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):11/manual_time 8079 ns 1556805014 ns 87997 bytes=2.048k bytes_per_second=241.75M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):11/manual_time_mean 8034 ns 1553420573 ns 5 bytes=2.048k bytes_per_second=243.121M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):11/manual_time_median 8035 ns 1552467330 ns 5 bytes=2.048k bytes_per_second=243.077M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):11/manual_time_stddev 78.5 ns 4288550 ns 5 bytes=0 bytes_per_second=2.37878M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):11/manual_time_cv 0.98 % 0.28 % 5 bytes=0.00% bytes_per_second=0.98% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):12/manual_time 9606 ns 1349867366 ns 73193 bytes=4.096k bytes_per_second=406.637M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):12/manual_time 9533 ns 1347313016 ns 73193 bytes=4.096k bytes_per_second=409.772M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):12/manual_time 9723 ns 1355478986 ns 73193 bytes=4.096k bytes_per_second=401.756M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):12/manual_time 9551 ns 1346770304 ns 73193 bytes=4.096k bytes_per_second=408.997M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):12/manual_time 9626 ns 1351510121 ns 73193 bytes=4.096k bytes_per_second=405.795M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):12/manual_time_mean 9608 ns 1350187959 ns 5 bytes=4.096k bytes_per_second=406.591M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):12/manual_time_median 9606 ns 1349867366 ns 5 bytes=4.096k bytes_per_second=406.637M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):12/manual_time_stddev 75.0 ns 3528155 ns 5 bytes=0 bytes_per_second=3.15914M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):12/manual_time_cv 0.78 % 0.26 % 5 bytes=0.00% bytes_per_second=0.78% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):13/manual_time 10777 ns 1235718678 ns 65037 bytes=8.192k bytes_per_second=724.946M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):13/manual_time 10766 ns 1235514977 ns 65037 bytes=8.192k bytes_per_second=725.676M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):13/manual_time 10777 ns 1236443199 ns 65037 bytes=8.192k bytes_per_second=724.921M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):13/manual_time 10765 ns 1234107048 ns 65037 bytes=8.192k bytes_per_second=725.746M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):13/manual_time 10775 ns 1236219325 ns 65037 bytes=8.192k bytes_per_second=725.073M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):13/manual_time_mean 10772 ns 1235600645 ns 5 bytes=8.192k bytes_per_second=725.272M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):13/manual_time_median 10775 ns 1235718678 ns 5 bytes=8.192k bytes_per_second=725.073M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):13/manual_time_stddev 6.02 ns 914435 ns 5 bytes=0 bytes_per_second=415.222k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):13/manual_time_cv 0.06 % 0.07 % 5 bytes=0.00% bytes_per_second=0.06% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):14/manual_time 10816 ns 1249892793 ns 64812 bytes=16.384k bytes_per_second=1.4107G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):14/manual_time 10810 ns 1249308342 ns 64812 bytes=16.384k bytes_per_second=1.41152G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):14/manual_time 10822 ns 1250190323 ns 64812 bytes=16.384k bytes_per_second=1.40997G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):14/manual_time 10803 ns 1246910508 ns 64812 bytes=16.384k bytes_per_second=1.41243G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):14/manual_time 10815 ns 1248703961 ns 64812 bytes=16.384k bytes_per_second=1.41086G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):14/manual_time_mean 10813 ns 1249001185 ns 5 bytes=16.384k bytes_per_second=1.4111G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):14/manual_time_median 10815 ns 1249308342 ns 5 bytes=16.384k bytes_per_second=1.41086G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):14/manual_time_stddev 7.09 ns 1300253 ns 5 bytes=0 bytes_per_second=969.847k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):14/manual_time_cv 0.07 % 0.10 % 5 bytes=0.00% bytes_per_second=0.07% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):15/manual_time 10849 ns 1266768198 ns 64610 bytes=32.768k bytes_per_second=2.81291G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):15/manual_time 10831 ns 1267658945 ns 64610 bytes=32.768k bytes_per_second=2.81749G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):15/manual_time 10846 ns 1268122086 ns 64610 bytes=32.768k bytes_per_second=2.8138G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):15/manual_time 10832 ns 1267244188 ns 64610 bytes=32.768k bytes_per_second=2.81734G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):15/manual_time 10848 ns 1267811938 ns 64610 bytes=32.768k bytes_per_second=2.81325G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):15/manual_time_mean 10841 ns 1267521071 ns 5 bytes=32.768k bytes_per_second=2.81496G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):15/manual_time_median 10846 ns 1267658945 ns 5 bytes=32.768k bytes_per_second=2.8138G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):15/manual_time_stddev 8.72 ns 526383 ns 5 bytes=0 bytes_per_second=2.31984M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):15/manual_time_cv 0.08 % 0.04 % 5 bytes=0.00% bytes_per_second=0.08% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):16/manual_time 11383 ns 1262542874 ns 61539 bytes=65.536k bytes_per_second=5.36188G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):16/manual_time 11378 ns 1262326145 ns 61539 bytes=65.536k bytes_per_second=5.36451G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):16/manual_time 11386 ns 1262697894 ns 61539 bytes=65.536k bytes_per_second=5.3604G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):16/manual_time 11375 ns 1260189426 ns 61539 bytes=65.536k bytes_per_second=5.36568G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):16/manual_time 11386 ns 1262622397 ns 61539 bytes=65.536k bytes_per_second=5.3604G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):16/manual_time_mean 11382 ns 1262075747 ns 5 bytes=65.536k bytes_per_second=5.36257G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):16/manual_time_median 11383 ns 1262542874 ns 5 bytes=65.536k bytes_per_second=5.36188G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):16/manual_time_stddev 5.13 ns 1063603 ns 5 bytes=0 bytes_per_second=2.47533M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):16/manual_time_cv 0.05 % 0.08 % 5 bytes=0.00% bytes_per_second=0.05% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):17/manual_time 12893 ns 1226115149 ns 54375 bytes=131.072k bytes_per_second=9.46765G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):17/manual_time 12880 ns 1225949752 ns 54375 bytes=131.072k bytes_per_second=9.47735G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):17/manual_time 12882 ns 1226418762 ns 54375 bytes=131.072k bytes_per_second=9.47628G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):17/manual_time 12877 ns 1224416792 ns 54375 bytes=131.072k bytes_per_second=9.47977G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):17/manual_time 12883 ns 1225287893 ns 54375 bytes=131.072k bytes_per_second=9.47549G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):17/manual_time_mean 12883 ns 1225637669 ns 5 bytes=131.072k bytes_per_second=9.47531G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):17/manual_time_median 12882 ns 1225949752 ns 5 bytes=131.072k bytes_per_second=9.47628G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):17/manual_time_stddev 6.22 ns 798181 ns 5 bytes=0 bytes_per_second=4.68431M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):17/manual_time_cv 0.05 % 0.07 % 5 bytes=0.00% bytes_per_second=0.05% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):18/manual_time 13046 ns 1297932023 ns 53698 bytes=262.144k bytes_per_second=18.7134G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):18/manual_time 13038 ns 1297496590 ns 53698 bytes=262.144k bytes_per_second=18.7251G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):18/manual_time 13047 ns 1298679456 ns 53698 bytes=262.144k bytes_per_second=18.713G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):18/manual_time 13032 ns 1296164009 ns 53698 bytes=262.144k bytes_per_second=18.7345G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):18/manual_time 13045 ns 1297566207 ns 53698 bytes=262.144k bytes_per_second=18.7153G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):18/manual_time_mean 13042 ns 1297567657 ns 5 bytes=262.144k bytes_per_second=18.7202G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):18/manual_time_median 13045 ns 1297566207 ns 5 bytes=262.144k bytes_per_second=18.7153G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):18/manual_time_stddev 6.53 ns 914350 ns 5 bytes=0 bytes_per_second=9.59667M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):18/manual_time_cv 0.05 % 0.07 % 5 bytes=0.00% bytes_per_second=0.05% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):19/manual_time 13199 ns 1290188650 ns 53104 bytes=524.288k bytes_per_second=36.9946G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):19/manual_time 13185 ns 1289252747 ns 53104 bytes=524.288k bytes_per_second=37.0321G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):19/manual_time 13201 ns 1290475079 ns 53104 bytes=524.288k bytes_per_second=36.9886G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):19/manual_time 13193 ns 1289345224 ns 53104 bytes=524.288k bytes_per_second=37.0097G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):19/manual_time 13199 ns 1290111060 ns 53104 bytes=524.288k bytes_per_second=36.9942G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):19/manual_time_mean 13195 ns 1289874552 ns 5 bytes=524.288k bytes_per_second=37.0038G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):19/manual_time_median 13199 ns 1290111060 ns 5 bytes=524.288k bytes_per_second=36.9946G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):19/manual_time_stddev 6.29 ns 543612 ns 5 bytes=0 bytes_per_second=18.0782M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):19/manual_time_cv 0.05 % 0.04 % 5 bytes=0.00% bytes_per_second=0.05% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):20/manual_time 13632 ns 1266133344 ns 51414 bytes=1048.58k bytes_per_second=71.6388G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):20/manual_time 13618 ns 1264622531 ns 51414 bytes=1048.58k bytes_per_second=71.7112G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):20/manual_time 13632 ns 1265026050 ns 51414 bytes=1048.58k bytes_per_second=71.636G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):20/manual_time 13619 ns 1262608910 ns 51414 bytes=1048.58k bytes_per_second=71.7033G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):20/manual_time 13629 ns 1264768645 ns 51414 bytes=1048.58k bytes_per_second=71.6539G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):20/manual_time_mean 13626 ns 1264631896 ns 5 bytes=1048.58k bytes_per_second=71.6686G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):20/manual_time_median 13629 ns 1264768645 ns 5 bytes=1048.58k bytes_per_second=71.6539G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):20/manual_time_stddev 6.84 ns 1276809 ns 5 bytes=0 bytes_per_second=36.8447M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):20/manual_time_cv 0.05 % 0.10 % 5 bytes=0.00% bytes_per_second=0.05% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):21/manual_time 14651 ns 1208365605 ns 47790 bytes=2.09715M bytes_per_second=133.308G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):21/manual_time 14655 ns 1207718215 ns 47790 bytes=2.09715M bytes_per_second=133.271G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):21/manual_time 14674 ns 1208791462 ns 47790 bytes=2.09715M bytes_per_second=133.101G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):21/manual_time 14658 ns 1207636041 ns 47790 bytes=2.09715M bytes_per_second=133.248G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):21/manual_time 14681 ns 1209497841 ns 47790 bytes=2.09715M bytes_per_second=133.037G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):21/manual_time_mean 14664 ns 1208401833 ns 5 bytes=2.09715M bytes_per_second=133.193G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):21/manual_time_median 14658 ns 1208365605 ns 5 bytes=2.09715M bytes_per_second=133.248G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):21/manual_time_stddev 12.9 ns 775907 ns 5 bytes=0 bytes_per_second=120.361M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):21/manual_time_cv 0.09 % 0.06 % 5 bytes=0.00% bytes_per_second=0.09% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):22/manual_time 18424 ns 1056600163 ns 37997 bytes=4.1943M bytes_per_second=212.019G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):22/manual_time 18413 ns 1055688933 ns 37997 bytes=4.1943M bytes_per_second=212.148G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):22/manual_time 18419 ns 1055563360 ns 37997 bytes=4.1943M bytes_per_second=212.078G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):22/manual_time 18419 ns 1055312478 ns 37997 bytes=4.1943M bytes_per_second=212.078G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):22/manual_time 18420 ns 1056535889 ns 37997 bytes=4.1943M bytes_per_second=212.064G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):22/manual_time_mean 18419 ns 1055940165 ns 5 bytes=4.1943M bytes_per_second=212.077G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):22/manual_time_median 18419 ns 1055688933 ns 5 bytes=4.1943M bytes_per_second=212.078G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):22/manual_time_stddev 4.01 ns 589401 ns 5 bytes=0 bytes_per_second=47.3226M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):22/manual_time_cv 0.02 % 0.06 % 5 bytes=0.00% bytes_per_second=0.02% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):23/manual_time 25004 ns 926639179 ns 28043 bytes=8.38861M bytes_per_second=312.451G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):23/manual_time 24966 ns 925974984 ns 28043 bytes=8.38861M bytes_per_second=312.927G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):23/manual_time 24996 ns 926336297 ns 28043 bytes=8.38861M bytes_per_second=312.545G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):23/manual_time 24944 ns 925131168 ns 28043 bytes=8.38861M bytes_per_second=313.206G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):23/manual_time 25002 ns 926119416 ns 28043 bytes=8.38861M bytes_per_second=312.471G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):23/manual_time_mean 24982 ns 926040209 ns 5 bytes=8.38861M bytes_per_second=312.72G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):23/manual_time_median 24996 ns 926119416 ns 5 bytes=8.38861M bytes_per_second=312.545G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):23/manual_time_stddev 26.6 ns 566418 ns 5 bytes=0 bytes_per_second=341.1M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):23/manual_time_cv 0.11 % 0.06 % 5 bytes=0.00% bytes_per_second=0.11% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):24/manual_time 37389 ns 841444165 ns 18729 bytes=16.7772M bytes_per_second=417.902G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):24/manual_time 37382 ns 841417881 ns 18729 bytes=16.7772M bytes_per_second=417.985G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):24/manual_time 37397 ns 841656195 ns 18729 bytes=16.7772M bytes_per_second=417.809G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):24/manual_time 37371 ns 840957014 ns 18729 bytes=16.7772M bytes_per_second=418.108G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):24/manual_time 37391 ns 841525310 ns 18729 bytes=16.7772M bytes_per_second=417.886G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):24/manual_time_mean 37386 ns 841400113 ns 5 bytes=16.7772M bytes_per_second=417.938G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):24/manual_time_median 37389 ns 841444165 ns 5 bytes=16.7772M bytes_per_second=417.902G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):24/manual_time_stddev 10.2 ns 264502 ns 5 bytes=0 bytes_per_second=116.569M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):24/manual_time_cv 0.03 % 0.03 % 5 bytes=0.00% bytes_per_second=0.03% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):25/manual_time 65417 ns 756568350 ns 10683 bytes=33.5544M bytes_per_second=477.703G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):25/manual_time 65290 ns 756596708 ns 10683 bytes=33.5544M bytes_per_second=478.632G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):25/manual_time 65323 ns 756073751 ns 10683 bytes=33.5544M bytes_per_second=478.391G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):25/manual_time 65301 ns 756450098 ns 10683 bytes=33.5544M bytes_per_second=478.554G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):25/manual_time 65303 ns 756074926 ns 10683 bytes=33.5544M bytes_per_second=478.536G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):25/manual_time_mean 65327 ns 756352767 ns 5 bytes=33.5544M bytes_per_second=478.363G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):25/manual_time_median 65303 ns 756450098 ns 5 bytes=33.5544M bytes_per_second=478.536G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):25/manual_time_stddev 51.8 ns 260049 ns 5 bytes=0 bytes_per_second=388.213M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):25/manual_time_cv 0.08 % 0.03 % 5 bytes=0.00% bytes_per_second=0.08% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):26/manual_time 118858 ns 715893784 ns 5892 bytes=67.1089M bytes_per_second=525.84G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):26/manual_time 118766 ns 715487756 ns 5892 bytes=67.1089M bytes_per_second=526.245G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):26/manual_time 118835 ns 715782589 ns 5892 bytes=67.1089M bytes_per_second=525.94G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):26/manual_time 118761 ns 715331246 ns 5892 bytes=67.1089M bytes_per_second=526.269G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):26/manual_time 118825 ns 715972591 ns 5892 bytes=67.1089M bytes_per_second=525.984G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):26/manual_time_mean 118809 ns 715693593 ns 5 bytes=67.1089M bytes_per_second=526.056G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):26/manual_time_median 118825 ns 715782589 ns 5 bytes=67.1089M bytes_per_second=525.984G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):26/manual_time_stddev 43.2 ns 273633 ns 5 bytes=0 bytes_per_second=196.09M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):26/manual_time_cv 0.04 % 0.04 % 5 bytes=0.00% bytes_per_second=0.04% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):27/manual_time 225691 ns 690134567 ns 3101 bytes=134.218M bytes_per_second=553.853G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):27/manual_time 225674 ns 690470302 ns 3101 bytes=134.218M bytes_per_second=553.898G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):27/manual_time 225731 ns 690261570 ns 3101 bytes=134.218M bytes_per_second=553.756G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):27/manual_time 225651 ns 690299306 ns 3101 bytes=134.218M bytes_per_second=553.952G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):27/manual_time 225662 ns 690191657 ns 3101 bytes=134.218M bytes_per_second=553.925G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):27/manual_time_mean 225682 ns 690271481 ns 5 bytes=134.218M bytes_per_second=553.877G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):27/manual_time_median 225674 ns 690261570 ns 5 bytes=134.218M bytes_per_second=553.898G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):27/manual_time_stddev 31.2 ns 127984 ns 5 bytes=0 bytes_per_second=78.5188M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):27/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):28/manual_time 444933 ns 674282860 ns 1574 bytes=268.435M bytes_per_second=561.883G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):28/manual_time 444661 ns 673922327 ns 1574 bytes=268.435M bytes_per_second=562.226G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):28/manual_time 444881 ns 674219235 ns 1574 bytes=268.435M bytes_per_second=561.948G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):28/manual_time 444607 ns 673936690 ns 1574 bytes=268.435M bytes_per_second=562.294G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):28/manual_time 445028 ns 674350079 ns 1574 bytes=268.435M bytes_per_second=561.762G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):28/manual_time_mean 444822 ns 674142238 ns 5 bytes=268.435M bytes_per_second=562.023G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):28/manual_time_median 444881 ns 674219235 ns 5 bytes=268.435M bytes_per_second=561.948G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):28/manual_time_stddev 181 ns 199695 ns 5 bytes=0 bytes_per_second=233.744M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):28/manual_time_cv 0.04 % 0.03 % 5 bytes=0.00% bytes_per_second=0.04% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):29/manual_time 872716 ns 660874804 ns 792 bytes=536.871M bytes_per_second=572.924G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):29/manual_time 872714 ns 660805391 ns 792 bytes=536.871M bytes_per_second=572.926G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):29/manual_time 872685 ns 660831433 ns 792 bytes=536.871M bytes_per_second=572.944G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):29/manual_time 872662 ns 660798612 ns 792 bytes=536.871M bytes_per_second=572.96G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):29/manual_time 872826 ns 660898725 ns 792 bytes=536.871M bytes_per_second=572.852G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):29/manual_time_mean 872720 ns 660841793 ns 5 bytes=536.871M bytes_per_second=572.921G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):29/manual_time_median 872714 ns 660831433 ns 5 bytes=536.871M bytes_per_second=572.926G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):29/manual_time_stddev 63.2 ns 43669 ns 5 bytes=0 bytes_per_second=42.5096M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):29/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):30/manual_time 1746694 ns 659866595 ns 397 bytes=1073.74M bytes_per_second=572.51G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):30/manual_time 1743863 ns 659266423 ns 397 bytes=1073.74M bytes_per_second=573.439G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):30/manual_time 1746639 ns 659852084 ns 397 bytes=1073.74M bytes_per_second=572.528G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):30/manual_time 1743785 ns 659292955 ns 397 bytes=1073.74M bytes_per_second=573.465G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):30/manual_time 1746301 ns 659777782 ns 397 bytes=1073.74M bytes_per_second=572.639G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):30/manual_time_mean 1745457 ns 659611168 ns 5 bytes=1073.74M bytes_per_second=572.916G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):30/manual_time_median 1746301 ns 659777782 ns 5 bytes=1073.74M bytes_per_second=572.639G/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):30/manual_time_stddev 1498 ns 304611 ns 5 bytes=0 bytes_per_second=503.582M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/0/log2(N):30/manual_time_cv 0.09 % 0.05 % 5 bytes=0.00% bytes_per_second=0.09% dst_id=-nan% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):8/manual_time 12079 ns 1183451917 ns 56881 bytes=256 bytes_per_second=20.212M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):8/manual_time 12015 ns 1175743759 ns 56881 bytes=256 bytes_per_second=20.3193M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):8/manual_time 12158 ns 1177119879 ns 56881 bytes=256 bytes_per_second=20.0805M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):8/manual_time 12148 ns 1182126312 ns 56881 bytes=256 bytes_per_second=20.0965M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):8/manual_time 12029 ns 1180430365 ns 56881 bytes=256 bytes_per_second=20.2958M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):8/manual_time_mean 12086 ns 1179774446 ns 5 bytes=256 bytes_per_second=20.2008M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):8/manual_time_median 12079 ns 1180430365 ns 5 bytes=256 bytes_per_second=20.212M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):8/manual_time_stddev 65.9 ns 3270262 ns 5 bytes=0 bytes_per_second=112.813k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):8/manual_time_cv 0.55 % 0.28 % 5 bytes=0.00% bytes_per_second=0.55% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):9/manual_time 12211 ns 1200904997 ns 57942 bytes=512 bytes_per_second=39.9873M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):9/manual_time 12241 ns 1206211876 ns 57942 bytes=512 bytes_per_second=39.8885M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):9/manual_time 12089 ns 1204206062 ns 57942 bytes=512 bytes_per_second=40.3918M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):9/manual_time 12083 ns 1200171066 ns 57942 bytes=512 bytes_per_second=40.4107M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):9/manual_time 12200 ns 1200030713 ns 57942 bytes=512 bytes_per_second=40.0224M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):9/manual_time_mean 12165 ns 1202304943 ns 5 bytes=512 bytes_per_second=40.1402M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):9/manual_time_median 12200 ns 1200904997 ns 5 bytes=512 bytes_per_second=40.0224M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):9/manual_time_stddev 73.7 ns 2764226 ns 5 bytes=0 bytes_per_second=249.28k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):9/manual_time_cv 0.61 % 0.23 % 5 bytes=0.00% bytes_per_second=0.61% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):10/manual_time 12141 ns 1188937798 ns 56993 bytes=1024 bytes_per_second=80.4334M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):10/manual_time 12112 ns 1181818556 ns 56993 bytes=1024 bytes_per_second=80.6252M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):10/manual_time 12320 ns 1185368529 ns 56993 bytes=1024 bytes_per_second=79.2666M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):10/manual_time 12266 ns 1189898324 ns 56993 bytes=1024 bytes_per_second=79.6158M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):10/manual_time 12169 ns 1188075592 ns 56993 bytes=1024 bytes_per_second=80.2517M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):10/manual_time_mean 12202 ns 1186819760 ns 5 bytes=1024 bytes_per_second=80.0385M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):10/manual_time_median 12169 ns 1188075592 ns 5 bytes=1024 bytes_per_second=80.2517M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):10/manual_time_stddev 87.8 ns 3265688 ns 5 bytes=0 bytes_per_second=588.251k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):10/manual_time_cv 0.72 % 0.28 % 5 bytes=0.00% bytes_per_second=0.72% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):11/manual_time 12404 ns 1191451566 ns 57151 bytes=2.048k bytes_per_second=157.463M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):11/manual_time 12360 ns 1194973194 ns 57151 bytes=2.048k bytes_per_second=158.024M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):11/manual_time 12265 ns 1195313451 ns 57151 bytes=2.048k bytes_per_second=159.249M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):11/manual_time 12242 ns 1189757225 ns 57151 bytes=2.048k bytes_per_second=159.543M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):11/manual_time 12389 ns 1190632142 ns 57151 bytes=2.048k bytes_per_second=157.644M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):11/manual_time_mean 12332 ns 1192425516 ns 5 bytes=2.048k bytes_per_second=158.384M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):11/manual_time_median 12360 ns 1191451566 ns 5 bytes=2.048k bytes_per_second=158.024M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):11/manual_time_stddev 73.9 ns 2555160 ns 5 bytes=0 bytes_per_second=973.59k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):11/manual_time_cv 0.60 % 0.21 % 5 bytes=0.00% bytes_per_second=0.60% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):12/manual_time 12402 ns 1171829831 ns 55823 bytes=4.096k bytes_per_second=314.971M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):12/manual_time 12379 ns 1164831714 ns 55823 bytes=4.096k bytes_per_second=315.558M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):12/manual_time 12523 ns 1167615864 ns 55823 bytes=4.096k bytes_per_second=311.915M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):12/manual_time 12534 ns 1174211439 ns 55823 bytes=4.096k bytes_per_second=311.661M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):12/manual_time 12403 ns 1171693789 ns 55823 bytes=4.096k bytes_per_second=314.949M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):12/manual_time_mean 12448 ns 1170036527 ns 5 bytes=4.096k bytes_per_second=313.811M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):12/manual_time_median 12403 ns 1171693789 ns 5 bytes=4.096k bytes_per_second=314.949M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):12/manual_time_stddev 74.1 ns 3753067 ns 5 bytes=0 bytes_per_second=1.86455M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):12/manual_time_cv 0.60 % 0.32 % 5 bytes=0.00% bytes_per_second=0.59% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):13/manual_time 12662 ns 1174727234 ns 55946 bytes=8.192k bytes_per_second=617.009M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):13/manual_time 12673 ns 1179300007 ns 55946 bytes=8.192k bytes_per_second=616.446M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):13/manual_time 12564 ns 1177537023 ns 55946 bytes=8.192k bytes_per_second=621.816M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):13/manual_time 12555 ns 1172795454 ns 55946 bytes=8.192k bytes_per_second=622.27M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):13/manual_time 12676 ns 1174119969 ns 55946 bytes=8.192k bytes_per_second=616.304M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):13/manual_time_mean 12626 ns 1175695938 ns 5 bytes=8.192k bytes_per_second=618.769M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):13/manual_time_median 12662 ns 1174727234 ns 5 bytes=8.192k bytes_per_second=617.009M/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):13/manual_time_stddev 61.2 ns 2655832 ns 5 bytes=0 bytes_per_second=3.00459M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):13/manual_time_cv 0.48 % 0.23 % 5 bytes=0.00% bytes_per_second=0.49% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):14/manual_time 12809 ns 1159358168 ns 54128 bytes=16.384k bytes_per_second=1.19122G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):14/manual_time 12793 ns 1152921860 ns 54128 bytes=16.384k bytes_per_second=1.19275G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):14/manual_time 12915 ns 1156537366 ns 54128 bytes=16.384k bytes_per_second=1.18144G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):14/manual_time 12953 ns 1160642562 ns 54128 bytes=16.384k bytes_per_second=1.17802G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):14/manual_time 12829 ns 1159989224 ns 54128 bytes=16.384k bytes_per_second=1.18942G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):14/manual_time_mean 12860 ns 1157889836 ns 5 bytes=16.384k bytes_per_second=1.18657G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):14/manual_time_median 12829 ns 1159358168 ns 5 bytes=16.384k bytes_per_second=1.18942G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):14/manual_time_stddev 70.2 ns 3187903 ns 5 bytes=0 bytes_per_second=6.6225M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):14/manual_time_cv 0.55 % 0.28 % 5 bytes=0.00% bytes_per_second=0.55% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):15/manual_time 13200 ns 1160349352 ns 53428 bytes=32.768k bytes_per_second=2.31189G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):15/manual_time 13249 ns 1164908597 ns 53428 bytes=32.768k bytes_per_second=2.30335G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):15/manual_time 13104 ns 1165017837 ns 53428 bytes=32.768k bytes_per_second=2.32894G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):15/manual_time 13098 ns 1160795108 ns 53428 bytes=32.768k bytes_per_second=2.32999G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):15/manual_time 13215 ns 1161430148 ns 53428 bytes=32.768k bytes_per_second=2.30932G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):15/manual_time_mean 13173 ns 1162500208 ns 5 bytes=32.768k bytes_per_second=2.3167G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):15/manual_time_median 13200 ns 1161430148 ns 5 bytes=32.768k bytes_per_second=2.31189G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):15/manual_time_stddev 68.5 ns 2281303 ns 5 bytes=0 bytes_per_second=12.3539M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):15/manual_time_cv 0.52 % 0.20 % 5 bytes=0.00% bytes_per_second=0.52% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):16/manual_time 13693 ns 1151606086 ns 50608 bytes=65.536k bytes_per_second=4.45728G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):16/manual_time 13674 ns 1144486085 ns 50608 bytes=65.536k bytes_per_second=4.46364G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):16/manual_time 13821 ns 1147955300 ns 50608 bytes=65.536k bytes_per_second=4.41612G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):16/manual_time 13815 ns 1152885266 ns 50608 bytes=65.536k bytes_per_second=4.41793G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):16/manual_time 13690 ns 1152005148 ns 50608 bytes=65.536k bytes_per_second=4.45845G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):16/manual_time_mean 13739 ns 1149787577 ns 5 bytes=65.536k bytes_per_second=4.44268G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):16/manual_time_median 13693 ns 1151606086 ns 5 bytes=65.536k bytes_per_second=4.45728G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):16/manual_time_stddev 73.0 ns 3510104 ns 5 bytes=0 bytes_per_second=24.1176M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):16/manual_time_cv 0.53 % 0.31 % 5 bytes=0.00% bytes_per_second=0.53% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):17/manual_time 15237 ns 1146929346 ns 46400 bytes=131.072k bytes_per_second=8.01163G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):17/manual_time 15237 ns 1149404738 ns 46400 bytes=131.072k bytes_per_second=8.01169G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):17/manual_time 15086 ns 1150027679 ns 46400 bytes=131.072k bytes_per_second=8.09184G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):17/manual_time 15087 ns 1145266538 ns 46400 bytes=131.072k bytes_per_second=8.09114G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):17/manual_time 15226 ns 1147173957 ns 46400 bytes=131.072k bytes_per_second=8.0174G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):17/manual_time_mean 15174 ns 1147760452 ns 5 bytes=131.072k bytes_per_second=8.04474G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):17/manual_time_median 15226 ns 1147173957 ns 5 bytes=131.072k bytes_per_second=8.0174G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):17/manual_time_stddev 80.5 ns 1942827 ns 5 bytes=0 bytes_per_second=43.7674M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):17/manual_time_cv 0.53 % 0.17 % 5 bytes=0.00% bytes_per_second=0.53% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):18/manual_time 19170 ns 1025581500 ns 36141 bytes=262.144k bytes_per_second=12.7354G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):18/manual_time 19263 ns 1023407567 ns 36141 bytes=262.144k bytes_per_second=12.674G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):18/manual_time 19351 ns 1024651472 ns 36141 bytes=262.144k bytes_per_second=12.6163G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):18/manual_time 19374 ns 1028365774 ns 36141 bytes=262.144k bytes_per_second=12.6016G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):18/manual_time 19174 ns 1025203738 ns 36141 bytes=262.144k bytes_per_second=12.7326G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):18/manual_time_mean 19267 ns 1025442010 ns 5 bytes=262.144k bytes_per_second=12.672G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):18/manual_time_median 19263 ns 1025203738 ns 5 bytes=262.144k bytes_per_second=12.674G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):18/manual_time_stddev 95.5 ns 1829517 ns 5 bytes=0 bytes_per_second=64.2886M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):18/manual_time_cv 0.50 % 0.18 % 5 bytes=0.00% bytes_per_second=0.50% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):19/manual_time 21879 ns 946952772 ns 32222 bytes=524.288k bytes_per_second=22.3178G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):19/manual_time 21876 ns 947792115 ns 32222 bytes=524.288k bytes_per_second=22.32G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):19/manual_time 21773 ns 948972389 ns 32222 bytes=524.288k bytes_per_second=22.4257G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):19/manual_time 21754 ns 946036169 ns 32222 bytes=524.288k bytes_per_second=22.4452G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):19/manual_time 21877 ns 946802703 ns 32222 bytes=524.288k bytes_per_second=22.3192G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):19/manual_time_mean 21832 ns 947311230 ns 5 bytes=524.288k bytes_per_second=22.3656G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):19/manual_time_median 21876 ns 946952772 ns 5 bytes=524.288k bytes_per_second=22.32G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):19/manual_time_stddev 62.5 ns 1118433 ns 5 bytes=0 bytes_per_second=65.6854M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):19/manual_time_cv 0.29 % 0.12 % 5 bytes=0.00% bytes_per_second=0.29% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):20/manual_time 32052 ns 759089128 ns 21748 bytes=1048.58k bytes_per_second=30.4682G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):20/manual_time 32045 ns 756428615 ns 21748 bytes=1048.58k bytes_per_second=30.475G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):20/manual_time 32193 ns 758150319 ns 21748 bytes=1048.58k bytes_per_second=30.3351G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):20/manual_time 32199 ns 759739472 ns 21748 bytes=1048.58k bytes_per_second=30.329G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):20/manual_time 32058 ns 759362649 ns 21748 bytes=1048.58k bytes_per_second=30.4623G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):20/manual_time_mean 32109 ns 758554036 ns 5 bytes=1048.58k bytes_per_second=30.4139G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):20/manual_time_median 32058 ns 759089128 ns 5 bytes=1048.58k bytes_per_second=30.4623G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):20/manual_time_stddev 79.1 ns 1325315 ns 5 bytes=0 bytes_per_second=76.6745M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):20/manual_time_cv 0.25 % 0.17 % 5 bytes=0.00% bytes_per_second=0.25% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):21/manual_time 52729 ns 606593605 ns 13274 bytes=2.09715M bytes_per_second=37.0409G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):21/manual_time 52839 ns 607014518 ns 13274 bytes=2.09715M bytes_per_second=36.9636G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):21/manual_time 52840 ns 607959743 ns 13274 bytes=2.09715M bytes_per_second=36.9631G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):21/manual_time 52720 ns 607926786 ns 13274 bytes=2.09715M bytes_per_second=37.047G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):21/manual_time 52717 ns 606760196 ns 13274 bytes=2.09715M bytes_per_second=37.049G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):21/manual_time_mean 52769 ns 607250970 ns 5 bytes=2.09715M bytes_per_second=37.0127G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):21/manual_time_median 52729 ns 607014518 ns 5 bytes=2.09715M bytes_per_second=37.0409G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):21/manual_time_stddev 64.4 ns 649612 ns 5 bytes=0 bytes_per_second=46.2701M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):21/manual_time_cv 0.12 % 0.11 % 5 bytes=0.00% bytes_per_second=0.12% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):22/manual_time 93940 ns 501643552 ns 7458 bytes=4.1943M bytes_per_second=41.5824G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):22/manual_time 93963 ns 501974687 ns 7458 bytes=4.1943M bytes_per_second=41.5724G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):22/manual_time 93822 ns 502179675 ns 7458 bytes=4.1943M bytes_per_second=41.6345G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):22/manual_time 93826 ns 501344321 ns 7458 bytes=4.1943M bytes_per_second=41.6328G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):22/manual_time 93936 ns 501691161 ns 7458 bytes=4.1943M bytes_per_second=41.584G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):22/manual_time_mean 93897 ns 501766679 ns 5 bytes=4.1943M bytes_per_second=41.6012G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):22/manual_time_median 93936 ns 501691161 ns 5 bytes=4.1943M bytes_per_second=41.584G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):22/manual_time_stddev 67.6 ns 321357 ns 5 bytes=0 bytes_per_second=30.6651M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):22/manual_time_cv 0.07 % 0.06 % 5 bytes=0.00% bytes_per_second=0.07% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):23/manual_time 176733 ns 438516658 ns 3961 bytes=8.38861M bytes_per_second=44.205G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):23/manual_time 176634 ns 438547682 ns 3961 bytes=8.38861M bytes_per_second=44.23G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):23/manual_time 176612 ns 438185397 ns 3961 bytes=8.38861M bytes_per_second=44.2355G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):23/manual_time 176735 ns 438305182 ns 3961 bytes=8.38861M bytes_per_second=44.2045G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):23/manual_time 176741 ns 438517197 ns 3961 bytes=8.38861M bytes_per_second=44.2031G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):23/manual_time_mean 176691 ns 438414423 ns 5 bytes=8.38861M bytes_per_second=44.2156G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):23/manual_time_median 176733 ns 438516658 ns 5 bytes=8.38861M bytes_per_second=44.205G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):23/manual_time_stddev 63.0 ns 160592 ns 5 bytes=0 bytes_per_second=16.1388M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):23/manual_time_cv 0.04 % 0.04 % 5 bytes=0.00% bytes_per_second=0.04% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):24/manual_time 341231 ns 409245895 ns 2050 bytes=16.7772M bytes_per_second=45.7901G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):24/manual_time 341286 ns 409233985 ns 2050 bytes=16.7772M bytes_per_second=45.7828G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):24/manual_time 341427 ns 409210355 ns 2050 bytes=16.7772M bytes_per_second=45.7638G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):24/manual_time 341383 ns 409367062 ns 2050 bytes=16.7772M bytes_per_second=45.7697G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):24/manual_time 341248 ns 409278346 ns 2050 bytes=16.7772M bytes_per_second=45.7878G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):24/manual_time_mean 341315 ns 409267129 ns 5 bytes=16.7772M bytes_per_second=45.7788G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):24/manual_time_median 341286 ns 409245895 ns 5 bytes=16.7772M bytes_per_second=45.7828G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):24/manual_time_stddev 86.0 ns 61002 ns 5 bytes=0 bytes_per_second=11.8173M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):24/manual_time_cv 0.03 % 0.01 % 5 bytes=0.00% bytes_per_second=0.03% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):25/manual_time 671075 ns 393147136 ns 1042 bytes=33.5544M bytes_per_second=46.5671G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):25/manual_time 671088 ns 393148738 ns 1042 bytes=33.5544M bytes_per_second=46.5662G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):25/manual_time 671229 ns 393207471 ns 1042 bytes=33.5544M bytes_per_second=46.5564G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):25/manual_time 671166 ns 393296123 ns 1042 bytes=33.5544M bytes_per_second=46.5608G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):25/manual_time 671076 ns 393177987 ns 1042 bytes=33.5544M bytes_per_second=46.567G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):25/manual_time_mean 671127 ns 393195491 ns 5 bytes=33.5544M bytes_per_second=46.5635G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):25/manual_time_median 671088 ns 393177987 ns 5 bytes=33.5544M bytes_per_second=46.5662G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):25/manual_time_stddev 68.5 ns 61443 ns 5 bytes=0 bytes_per_second=4.86695M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):25/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):26/manual_time 1329927 ns 386171800 ns 526 bytes=67.1089M bytes_per_second=46.995G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):26/manual_time 1330420 ns 386166757 ns 526 bytes=67.1089M bytes_per_second=46.9776G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):26/manual_time 1330143 ns 386104371 ns 526 bytes=67.1089M bytes_per_second=46.9874G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):26/manual_time 1330075 ns 386125343 ns 526 bytes=67.1089M bytes_per_second=46.9898G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):26/manual_time 1330364 ns 386267237 ns 526 bytes=67.1089M bytes_per_second=46.9796G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):26/manual_time_mean 1330186 ns 386167102 ns 5 bytes=67.1089M bytes_per_second=46.9859G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):26/manual_time_median 1330143 ns 386166757 ns 5 bytes=67.1089M bytes_per_second=46.9874G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):26/manual_time_stddev 205 ns 62706 ns 5 bytes=0 bytes_per_second=7.4038M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):26/manual_time_cv 0.02 % 0.02 % 5 bytes=0.00% bytes_per_second=0.02% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):27/manual_time 2648036 ns 383509107 ns 264 bytes=134.218M bytes_per_second=47.2048G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):27/manual_time 2648637 ns 383578134 ns 264 bytes=134.218M bytes_per_second=47.1941G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):27/manual_time 2648240 ns 383515281 ns 264 bytes=134.218M bytes_per_second=47.2012G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):27/manual_time 2648157 ns 383507777 ns 264 bytes=134.218M bytes_per_second=47.2026G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):27/manual_time 2648598 ns 383573342 ns 264 bytes=134.218M bytes_per_second=47.1948G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):27/manual_time_mean 2648333 ns 383536728 ns 5 bytes=134.218M bytes_per_second=47.1995G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):27/manual_time_median 2648240 ns 383515281 ns 5 bytes=134.218M bytes_per_second=47.2012G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):27/manual_time_stddev 269 ns 35764 ns 5 bytes=0 bytes_per_second=4.91604M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):27/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):28/manual_time 5284457 ns 386120473 ns 132 bytes=268.435M bytes_per_second=47.3085G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):28/manual_time 5284004 ns 386049672 ns 132 bytes=268.435M bytes_per_second=47.3126G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):28/manual_time 5284562 ns 386101206 ns 132 bytes=268.435M bytes_per_second=47.3076G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):28/manual_time 5284537 ns 386123296 ns 132 bytes=268.435M bytes_per_second=47.3078G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):28/manual_time 5284172 ns 386079448 ns 132 bytes=268.435M bytes_per_second=47.3111G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):28/manual_time_mean 5284346 ns 386094819 ns 5 bytes=268.435M bytes_per_second=47.3095G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):28/manual_time_median 5284457 ns 386101206 ns 5 bytes=268.435M bytes_per_second=47.3085G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):28/manual_time_stddev 246 ns 30759 ns 5 bytes=0 bytes_per_second=2.25762M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):28/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):29/manual_time 10556463 ns 392309691 ns 66 bytes=536.871M bytes_per_second=47.3643G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):29/manual_time 10557021 ns 392377178 ns 66 bytes=536.871M bytes_per_second=47.3618G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):29/manual_time 10555957 ns 392310308 ns 66 bytes=536.871M bytes_per_second=47.3666G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):29/manual_time 10555353 ns 392278345 ns 66 bytes=536.871M bytes_per_second=47.3693G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):29/manual_time 10557060 ns 392377563 ns 66 bytes=536.871M bytes_per_second=47.3617G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):29/manual_time_mean 10556371 ns 392330617 ns 5 bytes=536.871M bytes_per_second=47.3648G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):29/manual_time_median 10556463 ns 392310308 ns 5 bytes=536.871M bytes_per_second=47.3643G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):29/manual_time_stddev 727 ns 44594 ns 5 bytes=0 bytes_per_second=3.33982M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):29/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):30/manual_time 21098644 ns 408131643 ns 33 bytes=1073.74M bytes_per_second=47.3964G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):30/manual_time 21098843 ns 408118336 ns 33 bytes=1073.74M bytes_per_second=47.396G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):30/manual_time 21104719 ns 408223654 ns 33 bytes=1073.74M bytes_per_second=47.3828G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):30/manual_time 21106921 ns 408277928 ns 33 bytes=1073.74M bytes_per_second=47.3778G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):30/manual_time 21106038 ns 408269369 ns 33 bytes=1073.74M bytes_per_second=47.3798G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):30/manual_time_mean 21103033 ns 408204186 ns 5 bytes=1073.74M bytes_per_second=47.3866G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):30/manual_time_median 21104719 ns 408223654 ns 5 bytes=1073.74M bytes_per_second=47.3828G/s dst_id=1 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):30/manual_time_stddev 3994 ns 75330 ns 5 bytes=0 bytes_per_second=9.1842M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/1/log2(N):30/manual_time_cv 0.02 % 0.02 % 5 bytes=0.00% bytes_per_second=0.02% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):8/manual_time 12763 ns 1190690867 ns 50468 bytes=256 bytes_per_second=19.1287M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):8/manual_time 12685 ns 1172271407 ns 50468 bytes=256 bytes_per_second=19.2463M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):8/manual_time 12692 ns 1173895622 ns 50468 bytes=256 bytes_per_second=19.2351M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):8/manual_time 12731 ns 1175659985 ns 50468 bytes=256 bytes_per_second=19.1762M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):8/manual_time 12643 ns 1170305269 ns 50468 bytes=256 bytes_per_second=19.3096M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):8/manual_time_mean 12703 ns 1176564630 ns 5 bytes=256 bytes_per_second=19.2192M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):8/manual_time_median 12692 ns 1173895622 ns 5 bytes=256 bytes_per_second=19.2351M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):8/manual_time_stddev 45.8 ns 8141006 ns 5 bytes=0 bytes_per_second=70.9673k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):8/manual_time_cv 0.36 % 0.69 % 5 bytes=0.00% bytes_per_second=0.36% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):9/manual_time 12755 ns 1282334530 ns 55019 bytes=512 bytes_per_second=38.2814M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):9/manual_time 12755 ns 1279181133 ns 55019 bytes=512 bytes_per_second=38.2808M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):9/manual_time 12714 ns 1276992180 ns 55019 bytes=512 bytes_per_second=38.4053M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):9/manual_time 12667 ns 1277786094 ns 55019 bytes=512 bytes_per_second=38.547M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):9/manual_time 12701 ns 1280127665 ns 55019 bytes=512 bytes_per_second=38.4448M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):9/manual_time_mean 12718 ns 1279284320 ns 5 bytes=512 bytes_per_second=38.3919M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):9/manual_time_median 12714 ns 1279181133 ns 5 bytes=512 bytes_per_second=38.4053M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):9/manual_time_stddev 37.6 ns 2093099 ns 5 bytes=0 bytes_per_second=116.306k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):9/manual_time_cv 0.30 % 0.16 % 5 bytes=0.00% bytes_per_second=0.30% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):10/manual_time 12755 ns 1268171429 ns 54552 bytes=1024 bytes_per_second=76.5605M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):10/manual_time 12772 ns 1269199734 ns 54552 bytes=1024 bytes_per_second=76.4641M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):10/manual_time 12767 ns 1271472587 ns 54552 bytes=1024 bytes_per_second=76.4902M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):10/manual_time 12831 ns 1271960820 ns 54552 bytes=1024 bytes_per_second=76.1109M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):10/manual_time 12823 ns 1268770906 ns 54552 bytes=1024 bytes_per_second=76.1601M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):10/manual_time_mean 12789 ns 1269915095 ns 5 bytes=1024 bytes_per_second=76.3572M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):10/manual_time_median 12772 ns 1269199734 ns 5 bytes=1024 bytes_per_second=76.4641M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):10/manual_time_stddev 34.6 ns 1693521 ns 5 bytes=0 bytes_per_second=211.101k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):10/manual_time_cv 0.27 % 0.13 % 5 bytes=0.00% bytes_per_second=0.27% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):11/manual_time 12930 ns 1266555593 ns 54153 bytes=2.048k bytes_per_second=151.054M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):11/manual_time 12983 ns 1264922627 ns 54153 bytes=2.048k bytes_per_second=150.436M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):11/manual_time 12934 ns 1264168824 ns 54153 bytes=2.048k bytes_per_second=151.008M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):11/manual_time 12899 ns 1264953421 ns 54153 bytes=2.048k bytes_per_second=151.422M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):11/manual_time 12894 ns 1265980803 ns 54153 bytes=2.048k bytes_per_second=151.475M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):11/manual_time_mean 12928 ns 1265316254 ns 5 bytes=2.048k bytes_per_second=151.079M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):11/manual_time_median 12930 ns 1264953421 ns 5 bytes=2.048k bytes_per_second=151.054M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):11/manual_time_stddev 35.7 ns 946146 ns 5 bytes=0 bytes_per_second=426.302k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):11/manual_time_cv 0.28 % 0.07 % 5 bytes=0.00% bytes_per_second=0.28% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):12/manual_time 13113 ns 1253196991 ns 53465 bytes=4.096k bytes_per_second=297.889M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):12/manual_time 13097 ns 1252869560 ns 53465 bytes=4.096k bytes_per_second=298.248M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):12/manual_time 13091 ns 1254161854 ns 53465 bytes=4.096k bytes_per_second=298.395M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):12/manual_time 13109 ns 1254067018 ns 53465 bytes=4.096k bytes_per_second=297.993M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):12/manual_time 13089 ns 1251812399 ns 53465 bytes=4.096k bytes_per_second=298.437M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):12/manual_time_mean 13100 ns 1253221564 ns 5 bytes=4.096k bytes_per_second=298.192M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):12/manual_time_median 13097 ns 1253196991 ns 5 bytes=4.096k bytes_per_second=298.248M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):12/manual_time_stddev 10.7 ns 962964 ns 5 bytes=0 bytes_per_second=248.651k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):12/manual_time_cv 0.08 % 0.08 % 5 bytes=0.00% bytes_per_second=0.08% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):13/manual_time 13229 ns 1248551150 ns 52986 bytes=8.192k bytes_per_second=590.546M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):13/manual_time 13244 ns 1245204930 ns 52986 bytes=8.192k bytes_per_second=589.869M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):13/manual_time 13231 ns 1243532754 ns 52986 bytes=8.192k bytes_per_second=590.492M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):13/manual_time 13207 ns 1246302959 ns 52986 bytes=8.192k bytes_per_second=591.534M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):13/manual_time 13196 ns 1246156777 ns 52986 bytes=8.192k bytes_per_second=592.043M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):13/manual_time_mean 13221 ns 1245949714 ns 5 bytes=8.192k bytes_per_second=590.897M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):13/manual_time_median 13229 ns 1246156777 ns 5 bytes=8.192k bytes_per_second=590.546M/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):13/manual_time_stddev 19.6 ns 1825618 ns 5 bytes=0 bytes_per_second=896.31k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):13/manual_time_cv 0.15 % 0.15 % 5 bytes=0.00% bytes_per_second=0.15% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):14/manual_time 13607 ns 1233907185 ns 51418 bytes=16.384k bytes_per_second=1.12138G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):14/manual_time 13563 ns 1232018755 ns 51418 bytes=16.384k bytes_per_second=1.12505G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):14/manual_time 13546 ns 1233720207 ns 51418 bytes=16.384k bytes_per_second=1.12647G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):14/manual_time 13607 ns 1232844819 ns 51418 bytes=16.384k bytes_per_second=1.12142G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):14/manual_time 13576 ns 1231112656 ns 51418 bytes=16.384k bytes_per_second=1.12399G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):14/manual_time_mean 13580 ns 1232720724 ns 5 bytes=16.384k bytes_per_second=1.12366G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):14/manual_time_median 13576 ns 1232844819 ns 5 bytes=16.384k bytes_per_second=1.12399G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):14/manual_time_stddev 27.1 ns 1172678 ns 5 bytes=0 bytes_per_second=2.29975M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):14/manual_time_cv 0.20 % 0.10 % 5 bytes=0.00% bytes_per_second=0.20% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):15/manual_time 13990 ns 1229406377 ns 50116 bytes=32.768k bytes_per_second=2.18145G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):15/manual_time 14043 ns 1225950023 ns 50116 bytes=32.768k bytes_per_second=2.1731G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):15/manual_time 13999 ns 1226749913 ns 50116 bytes=32.768k bytes_per_second=2.18001G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):15/manual_time 13977 ns 1231334518 ns 50116 bytes=32.768k bytes_per_second=2.18347G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):15/manual_time 13979 ns 1229633866 ns 50116 bytes=32.768k bytes_per_second=2.18303G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):15/manual_time_mean 13998 ns 1228614939 ns 5 bytes=32.768k bytes_per_second=2.18021G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):15/manual_time_median 13990 ns 1229406377 ns 5 bytes=32.768k bytes_per_second=2.18145G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):15/manual_time_stddev 27.0 ns 2215897 ns 5 bytes=0 bytes_per_second=4.30499M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):15/manual_time_cv 0.19 % 0.18 % 5 bytes=0.00% bytes_per_second=0.19% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):16/manual_time 14875 ns 1199395810 ns 46923 bytes=65.536k bytes_per_second=4.10313G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):16/manual_time 14880 ns 1199155953 ns 46923 bytes=65.536k bytes_per_second=4.1017G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):16/manual_time 14885 ns 1203714286 ns 46923 bytes=65.536k bytes_per_second=4.10057G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):16/manual_time 14929 ns 1203724810 ns 46923 bytes=65.536k bytes_per_second=4.08831G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):16/manual_time 14863 ns 1201007718 ns 46923 bytes=65.536k bytes_per_second=4.10663G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):16/manual_time_mean 14886 ns 1201399715 ns 5 bytes=65.536k bytes_per_second=4.10007G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):16/manual_time_median 14880 ns 1201007718 ns 5 bytes=65.536k bytes_per_second=4.1017G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):16/manual_time_stddev 25.3 ns 2234226 ns 5 bytes=0 bytes_per_second=7.12298M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):16/manual_time_cv 0.17 % 0.19 % 5 bytes=0.00% bytes_per_second=0.17% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):17/manual_time 20279 ns 1033858495 ns 34724 bytes=131.072k bytes_per_second=6.01946G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):17/manual_time 20318 ns 1032068601 ns 34724 bytes=131.072k bytes_per_second=6.00787G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):17/manual_time 20247 ns 1031346710 ns 34724 bytes=131.072k bytes_per_second=6.02897G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):17/manual_time 20172 ns 1031189294 ns 34724 bytes=131.072k bytes_per_second=6.05155G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):17/manual_time 20262 ns 1032861146 ns 34724 bytes=131.072k bytes_per_second=6.02469G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):17/manual_time_mean 20256 ns 1032264849 ns 5 bytes=131.072k bytes_per_second=6.02651G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):17/manual_time_median 20262 ns 1032068601 ns 5 bytes=131.072k bytes_per_second=6.02469G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):17/manual_time_stddev 53.9 ns 1110584 ns 5 bytes=0 bytes_per_second=16.4579M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):17/manual_time_cv 0.27 % 0.11 % 5 bytes=0.00% bytes_per_second=0.27% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):18/manual_time 21628 ns 1039967957 ns 32331 bytes=262.144k bytes_per_second=11.288G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):18/manual_time 21625 ns 1039343607 ns 32331 bytes=262.144k bytes_per_second=11.2897G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):18/manual_time 21673 ns 1041165285 ns 32331 bytes=262.144k bytes_per_second=11.2646G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):18/manual_time 21650 ns 1040321704 ns 32331 bytes=262.144k bytes_per_second=11.2767G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):18/manual_time 21640 ns 1040381940 ns 32331 bytes=262.144k bytes_per_second=11.2821G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):18/manual_time_mean 21643 ns 1040236098 ns 5 bytes=262.144k bytes_per_second=11.2802G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):18/manual_time_median 21640 ns 1040321704 ns 5 bytes=262.144k bytes_per_second=11.2821G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):18/manual_time_stddev 19.4 ns 663405 ns 5 bytes=0 bytes_per_second=10.3666M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):18/manual_time_cv 0.09 % 0.06 % 5 bytes=0.00% bytes_per_second=0.09% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):19/manual_time 27109 ns 903023053 ns 25789 bytes=524.288k bytes_per_second=18.0121G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):19/manual_time 27148 ns 901242713 ns 25789 bytes=524.288k bytes_per_second=17.986G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):19/manual_time 27143 ns 903134868 ns 25789 bytes=524.288k bytes_per_second=17.9891G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):19/manual_time 27140 ns 903503003 ns 25789 bytes=524.288k bytes_per_second=17.9914G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):19/manual_time 27130 ns 903029800 ns 25789 bytes=524.288k bytes_per_second=17.9976G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):19/manual_time_mean 27134 ns 902786688 ns 5 bytes=524.288k bytes_per_second=17.9952G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):19/manual_time_median 27140 ns 903029800 ns 5 bytes=524.288k bytes_per_second=17.9914G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):19/manual_time_stddev 15.6 ns 885038 ns 5 bytes=0 bytes_per_second=10.5884M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):19/manual_time_cv 0.06 % 0.10 % 5 bytes=0.00% bytes_per_second=0.06% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):20/manual_time 41318 ns 713153419 ns 16938 bytes=1048.58k bytes_per_second=23.6354G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):20/manual_time 41254 ns 713273828 ns 16938 bytes=1048.58k bytes_per_second=23.6719G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):20/manual_time 41310 ns 714353792 ns 16938 bytes=1048.58k bytes_per_second=23.64G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):20/manual_time 41317 ns 714815447 ns 16938 bytes=1048.58k bytes_per_second=23.6358G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):20/manual_time 41334 ns 714332919 ns 16938 bytes=1048.58k bytes_per_second=23.626G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):20/manual_time_mean 41307 ns 713985881 ns 5 bytes=1048.58k bytes_per_second=23.6418G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):20/manual_time_median 41317 ns 714332919 ns 5 bytes=1048.58k bytes_per_second=23.6358G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):20/manual_time_stddev 30.7 ns 732118 ns 5 bytes=0 bytes_per_second=17.9782M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):20/manual_time_cv 0.07 % 0.10 % 5 bytes=0.00% bytes_per_second=0.07% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):21/manual_time 69633 ns 568218139 ns 10053 bytes=2.09715M bytes_per_second=28.0489G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):21/manual_time 69624 ns 567986921 ns 10053 bytes=2.09715M bytes_per_second=28.0523G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):21/manual_time 69680 ns 568270569 ns 10053 bytes=2.09715M bytes_per_second=28.03G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):21/manual_time 69633 ns 567693099 ns 10053 bytes=2.09715M bytes_per_second=28.0487G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):21/manual_time 69627 ns 568221609 ns 10053 bytes=2.09715M bytes_per_second=28.0514G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):21/manual_time_mean 69639 ns 568078067 ns 5 bytes=2.09715M bytes_per_second=28.0463G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):21/manual_time_median 69633 ns 568218139 ns 5 bytes=2.09715M bytes_per_second=28.0489G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):21/manual_time_stddev 23.0 ns 241759 ns 5 bytes=0 bytes_per_second=9.46147M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):21/manual_time_cv 0.03 % 0.04 % 5 bytes=0.00% bytes_per_second=0.03% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):22/manual_time 126279 ns 479474868 ns 5545 bytes=4.1943M bytes_per_second=30.9336G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):22/manual_time 126298 ns 479165654 ns 5545 bytes=4.1943M bytes_per_second=30.9287G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):22/manual_time 126225 ns 479098351 ns 5545 bytes=4.1943M bytes_per_second=30.9468G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):22/manual_time 126249 ns 479489053 ns 5545 bytes=4.1943M bytes_per_second=30.9409G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):22/manual_time 126282 ns 479433257 ns 5545 bytes=4.1943M bytes_per_second=30.9328G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):22/manual_time_mean 126266 ns 479332237 ns 5 bytes=4.1943M bytes_per_second=30.9366G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):22/manual_time_median 126279 ns 479433257 ns 5 bytes=4.1943M bytes_per_second=30.9336G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):22/manual_time_stddev 29.5 ns 185467 ns 5 bytes=0 bytes_per_second=7.39898M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):22/manual_time_cv 0.02 % 0.04 % 5 bytes=0.00% bytes_per_second=0.02% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):23/manual_time 239962 ns 425525049 ns 2916 bytes=8.38861M bytes_per_second=32.5573G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):23/manual_time 239962 ns 425060862 ns 2916 bytes=8.38861M bytes_per_second=32.5572G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):23/manual_time 239926 ns 425205046 ns 2916 bytes=8.38861M bytes_per_second=32.5622G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):23/manual_time 239947 ns 424924232 ns 2916 bytes=8.38861M bytes_per_second=32.5592G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):23/manual_time 239877 ns 424947163 ns 2916 bytes=8.38861M bytes_per_second=32.5688G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):23/manual_time_mean 239935 ns 425132470 ns 5 bytes=8.38861M bytes_per_second=32.5609G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):23/manual_time_median 239947 ns 425060862 ns 5 bytes=8.38861M bytes_per_second=32.5592G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):23/manual_time_stddev 35.6 ns 246077 ns 5 bytes=0 bytes_per_second=4.94541M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):23/manual_time_cv 0.01 % 0.06 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):24/manual_time 467045 ns 397165399 ns 1499 bytes=16.7772M bytes_per_second=33.455G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):24/manual_time 467078 ns 397370162 ns 1499 bytes=16.7772M bytes_per_second=33.4527G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):24/manual_time 466878 ns 397233355 ns 1499 bytes=16.7772M bytes_per_second=33.467G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):24/manual_time 466987 ns 397309182 ns 1499 bytes=16.7772M bytes_per_second=33.4592G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):24/manual_time 466927 ns 397318141 ns 1499 bytes=16.7772M bytes_per_second=33.4634G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):24/manual_time_mean 466983 ns 397279248 ns 5 bytes=16.7772M bytes_per_second=33.4594G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):24/manual_time_median 466987 ns 397309182 ns 5 bytes=16.7772M bytes_per_second=33.4592G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):24/manual_time_stddev 82.1 ns 80221 ns 5 bytes=0 bytes_per_second=6.02117M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):24/manual_time_cv 0.02 % 0.02 % 5 bytes=0.00% bytes_per_second=0.02% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):25/manual_time 920821 ns 384016327 ns 760 bytes=33.5544M bytes_per_second=33.9371G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):25/manual_time 920785 ns 384031562 ns 760 bytes=33.5544M bytes_per_second=33.9384G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):25/manual_time 920892 ns 384074205 ns 760 bytes=33.5544M bytes_per_second=33.9345G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):25/manual_time 920738 ns 383996703 ns 760 bytes=33.5544M bytes_per_second=33.9402G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):25/manual_time 920688 ns 383972331 ns 760 bytes=33.5544M bytes_per_second=33.942G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):25/manual_time_mean 920785 ns 384018226 ns 5 bytes=33.5544M bytes_per_second=33.9384G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):25/manual_time_median 920785 ns 384016327 ns 5 bytes=33.5544M bytes_per_second=33.9384G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):25/manual_time_stddev 78.0 ns 38356 ns 5 bytes=0 bytes_per_second=2.94278M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):25/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):26/manual_time 1828698 ns 378821301 ns 383 bytes=67.1089M bytes_per_second=34.1773G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):26/manual_time 1828962 ns 378863075 ns 383 bytes=67.1089M bytes_per_second=34.1724G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):26/manual_time 1828372 ns 378763640 ns 383 bytes=67.1089M bytes_per_second=34.1834G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):26/manual_time 1828711 ns 378798092 ns 383 bytes=67.1089M bytes_per_second=34.1771G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):26/manual_time 1828606 ns 378784309 ns 383 bytes=67.1089M bytes_per_second=34.179G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):26/manual_time_mean 1828670 ns 378806083 ns 5 bytes=67.1089M bytes_per_second=34.1778G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):26/manual_time_median 1828698 ns 378798092 ns 5 bytes=67.1089M bytes_per_second=34.1773G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):26/manual_time_stddev 213 ns 38141 ns 5 bytes=0 bytes_per_second=4.0724M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):26/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):27/manual_time 3643826 ns 379195403 ns 192 bytes=134.218M bytes_per_second=34.3046G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):27/manual_time 3643935 ns 379166497 ns 192 bytes=134.218M bytes_per_second=34.3036G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):27/manual_time 3644046 ns 379245032 ns 192 bytes=134.218M bytes_per_second=34.3025G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):27/manual_time 3643898 ns 379259797 ns 192 bytes=134.218M bytes_per_second=34.3039G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):27/manual_time 3643740 ns 379129659 ns 192 bytes=134.218M bytes_per_second=34.3054G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):27/manual_time_mean 3643889 ns 379199277 ns 5 bytes=134.218M bytes_per_second=34.304G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):27/manual_time_median 3643898 ns 379195403 ns 5 bytes=134.218M bytes_per_second=34.3039G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):27/manual_time_stddev 115 ns 54066 ns 5 bytes=0 bytes_per_second=1.11245M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):27/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):28/manual_time 7273853 ns 381871620 ns 96 bytes=268.435M bytes_per_second=34.3697G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):28/manual_time 7274118 ns 381879857 ns 96 bytes=268.435M bytes_per_second=34.3684G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):28/manual_time 7274215 ns 381867377 ns 96 bytes=268.435M bytes_per_second=34.368G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):28/manual_time 7274286 ns 381902595 ns 96 bytes=268.435M bytes_per_second=34.3676G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):28/manual_time 7274471 ns 381950503 ns 96 bytes=268.435M bytes_per_second=34.3668G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):28/manual_time_mean 7274189 ns 381894390 ns 5 bytes=268.435M bytes_per_second=34.3681G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):28/manual_time_median 7274215 ns 381879857 ns 5 bytes=268.435M bytes_per_second=34.368G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):28/manual_time_stddev 228 ns 34188 ns 5 bytes=0 bytes_per_second=1.10262M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):28/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):29/manual_time 14533762 ns 391557614 ns 48 bytes=536.871M bytes_per_second=34.4027G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):29/manual_time 14533389 ns 391531569 ns 48 bytes=536.871M bytes_per_second=34.4035G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):29/manual_time 14535302 ns 391591562 ns 48 bytes=536.871M bytes_per_second=34.399G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):29/manual_time 14535079 ns 391602784 ns 48 bytes=536.871M bytes_per_second=34.3995G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):29/manual_time 14534296 ns 391546132 ns 48 bytes=536.871M bytes_per_second=34.4014G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):29/manual_time_mean 14534366 ns 391565932 ns 5 bytes=536.871M bytes_per_second=34.4012G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):29/manual_time_median 14534296 ns 391557614 ns 5 bytes=536.871M bytes_per_second=34.4014G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):29/manual_time_stddev 823 ns 30236 ns 5 bytes=0 bytes_per_second=1.99471M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):29/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):30/manual_time 29056458 ns 413705620 ns 24 bytes=1073.74M bytes_per_second=34.4158G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):30/manual_time 29057284 ns 413692765 ns 24 bytes=1073.74M bytes_per_second=34.4148G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):30/manual_time 29057751 ns 413714702 ns 24 bytes=1073.74M bytes_per_second=34.4142G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):30/manual_time 29060058 ns 413749748 ns 24 bytes=1073.74M bytes_per_second=34.4115G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):30/manual_time 29056891 ns 413685389 ns 24 bytes=1073.74M bytes_per_second=34.4152G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):30/manual_time_mean 29057688 ns 413709645 ns 5 bytes=1073.74M bytes_per_second=34.4143G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):30/manual_time_median 29057284 ns 413705620 ns 5 bytes=1073.74M bytes_per_second=34.4148G/s dst_id=2 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):30/manual_time_stddev 1408 ns 25116 ns 5 bytes=0 bytes_per_second=1.7076M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/2/log2(N):30/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):8/manual_time 12243 ns 1195088707 ns 57814 bytes=256 bytes_per_second=19.9417M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):8/manual_time 12234 ns 1200816993 ns 57814 bytes=256 bytes_per_second=19.9553M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):8/manual_time 12023 ns 1195051572 ns 57814 bytes=256 bytes_per_second=20.3057M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):8/manual_time 12053 ns 1196434895 ns 57814 bytes=256 bytes_per_second=20.2563M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):8/manual_time 12251 ns 1194604205 ns 57814 bytes=256 bytes_per_second=19.9284M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):8/manual_time_mean 12161 ns 1196399274 ns 5 bytes=256 bytes_per_second=20.0775M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):8/manual_time_median 12234 ns 1195088707 ns 5 bytes=256 bytes_per_second=19.9553M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):8/manual_time_stddev 113 ns 2562892 ns 5 bytes=0 bytes_per_second=191.342k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):8/manual_time_cv 0.93 % 0.21 % 5 bytes=0.00% bytes_per_second=0.93% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):9/manual_time 12073 ns 1179734136 ns 56988 bytes=512 bytes_per_second=40.4427M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):9/manual_time 12106 ns 1181820261 ns 56988 bytes=512 bytes_per_second=40.3337M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):9/manual_time 12301 ns 1180953261 ns 56988 bytes=512 bytes_per_second=39.6931M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):9/manual_time 12286 ns 1183761364 ns 56988 bytes=512 bytes_per_second=39.7429M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):9/manual_time 12075 ns 1181510807 ns 56988 bytes=512 bytes_per_second=40.4365M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):9/manual_time_mean 12168 ns 1181555966 ns 5 bytes=512 bytes_per_second=40.1298M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):9/manual_time_median 12106 ns 1181510807 ns 5 bytes=512 bytes_per_second=40.3337M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):9/manual_time_stddev 115 ns 1467821 ns 5 bytes=0 bytes_per_second=387.902k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):9/manual_time_cv 0.95 % 0.12 % 5 bytes=0.00% bytes_per_second=0.94% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):10/manual_time 12391 ns 1196103708 ns 57518 bytes=1024 bytes_per_second=78.8153M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):10/manual_time 12341 ns 1198735743 ns 57518 bytes=1024 bytes_per_second=79.1306M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):10/manual_time 12148 ns 1194595214 ns 57518 bytes=1024 bytes_per_second=80.3904M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):10/manual_time 12201 ns 1197144774 ns 57518 bytes=1024 bytes_per_second=80.038M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):10/manual_time 12363 ns 1193833168 ns 57518 bytes=1024 bytes_per_second=78.9878M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):10/manual_time_mean 12289 ns 1196082521 ns 5 bytes=1024 bytes_per_second=79.4724M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):10/manual_time_median 12341 ns 1196103708 ns 5 bytes=1024 bytes_per_second=79.1306M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):10/manual_time_stddev 107 ns 1964694 ns 5 bytes=0 bytes_per_second=714.239k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):10/manual_time_cv 0.87 % 0.16 % 5 bytes=0.00% bytes_per_second=0.88% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):11/manual_time 12343 ns 1177024957 ns 56238 bytes=2.048k bytes_per_second=158.233M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):11/manual_time 12279 ns 1173656526 ns 56238 bytes=2.048k bytes_per_second=159.057M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):11/manual_time 12489 ns 1172440930 ns 56238 bytes=2.048k bytes_per_second=156.387M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):11/manual_time 12449 ns 1173912411 ns 56238 bytes=2.048k bytes_per_second=156.895M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):11/manual_time 12275 ns 1172741230 ns 56238 bytes=2.048k bytes_per_second=159.109M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):11/manual_time_mean 12367 ns 1173955211 ns 5 bytes=2.048k bytes_per_second=157.936M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):11/manual_time_median 12343 ns 1173656526 ns 5 bytes=2.048k bytes_per_second=158.233M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):11/manual_time_stddev 97.7 ns 1822168 ns 5 bytes=0 bytes_per_second=1.24541M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):11/manual_time_cv 0.79 % 0.16 % 5 bytes=0.00% bytes_per_second=0.79% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):12/manual_time 12664 ns 1179518156 ns 56317 bytes=4.096k bytes_per_second=308.447M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):12/manual_time 12617 ns 1182419630 ns 56317 bytes=4.096k bytes_per_second=309.59M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):12/manual_time 12429 ns 1180688380 ns 56317 bytes=4.096k bytes_per_second=314.288M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):12/manual_time 12460 ns 1181696914 ns 56317 bytes=4.096k bytes_per_second=313.503M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):12/manual_time 12641 ns 1179338042 ns 56317 bytes=4.096k bytes_per_second=309.023M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):12/manual_time_mean 12562 ns 1180732224 ns 5 bytes=4.096k bytes_per_second=310.97M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):12/manual_time_median 12617 ns 1180688380 ns 5 bytes=4.096k bytes_per_second=309.59M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):12/manual_time_stddev 109 ns 1341416 ns 5 bytes=0 bytes_per_second=2.71509M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):12/manual_time_cv 0.87 % 0.11 % 5 bytes=0.00% bytes_per_second=0.87% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):13/manual_time 12602 ns 1156178853 ns 54808 bytes=8.192k bytes_per_second=619.941M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):13/manual_time 12593 ns 1155061889 ns 54808 bytes=8.192k bytes_per_second=620.406M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):13/manual_time 12840 ns 1153231014 ns 54808 bytes=8.192k bytes_per_second=608.472M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):13/manual_time 12803 ns 1154959795 ns 54808 bytes=8.192k bytes_per_second=610.215M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):13/manual_time 12601 ns 1153395479 ns 54808 bytes=8.192k bytes_per_second=619.97M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):13/manual_time_mean 12688 ns 1154565406 ns 5 bytes=8.192k bytes_per_second=615.801M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):13/manual_time_median 12602 ns 1154959795 ns 5 bytes=8.192k bytes_per_second=619.941M/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):13/manual_time_stddev 123 ns 1240421 ns 5 bytes=0 bytes_per_second=5.92967M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):13/manual_time_cv 0.97 % 0.11 % 5 bytes=0.00% bytes_per_second=0.96% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):14/manual_time 13167 ns 1158088204 ns 53969 bytes=16.384k bytes_per_second=1.1589G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):14/manual_time 13140 ns 1159117881 ns 53969 bytes=16.384k bytes_per_second=1.16129G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):14/manual_time 12923 ns 1158442106 ns 53969 bytes=16.384k bytes_per_second=1.18078G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):14/manual_time 12982 ns 1159159028 ns 53969 bytes=16.384k bytes_per_second=1.17534G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):14/manual_time 13172 ns 1159019261 ns 53969 bytes=16.384k bytes_per_second=1.1584G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):14/manual_time_mean 13077 ns 1158765296 ns 5 bytes=16.384k bytes_per_second=1.16694G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):14/manual_time_median 13140 ns 1159019261 ns 5 bytes=16.384k bytes_per_second=1.16129G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):14/manual_time_stddev 116 ns 476116 ns 5 bytes=0 bytes_per_second=10.6356M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):14/manual_time_cv 0.89 % 0.04 % 5 bytes=0.00% bytes_per_second=0.89% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):15/manual_time 13318 ns 1141152034 ns 51793 bytes=32.768k bytes_per_second=2.29153G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):15/manual_time 13341 ns 1141933549 ns 51793 bytes=32.768k bytes_per_second=2.2875G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):15/manual_time 13552 ns 1140407517 ns 51793 bytes=32.768k bytes_per_second=2.25194G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):15/manual_time 13525 ns 1142382281 ns 51793 bytes=32.768k bytes_per_second=2.25634G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):15/manual_time 13329 ns 1140280053 ns 51793 bytes=32.768k bytes_per_second=2.2895G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):15/manual_time_mean 13413 ns 1141231087 ns 5 bytes=32.768k bytes_per_second=2.27536G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):15/manual_time_median 13341 ns 1141152034 ns 5 bytes=32.768k bytes_per_second=2.2875G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):15/manual_time_stddev 115 ns 922996 ns 5 bytes=0 bytes_per_second=19.9542M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):15/manual_time_cv 0.86 % 0.08 % 5 bytes=0.00% bytes_per_second=0.86% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):16/manual_time 14405 ns 1144051421 ns 49350 bytes=65.536k bytes_per_second=4.23698G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):16/manual_time 14365 ns 1145551685 ns 49350 bytes=65.536k bytes_per_second=4.24896G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):16/manual_time 14155 ns 1142510241 ns 49350 bytes=65.536k bytes_per_second=4.31206G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):16/manual_time 14184 ns 1143797894 ns 49350 bytes=65.536k bytes_per_second=4.3031G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):16/manual_time 14411 ns 1143730432 ns 49350 bytes=65.536k bytes_per_second=4.23544G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):16/manual_time_mean 14304 ns 1143928335 ns 5 bytes=65.536k bytes_per_second=4.26731G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):16/manual_time_median 14365 ns 1143797894 ns 5 bytes=65.536k bytes_per_second=4.24896G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):16/manual_time_stddev 125 ns 1086000 ns 5 bytes=0 bytes_per_second=38.161M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):16/manual_time_cv 0.87 % 0.09 % 5 bytes=0.00% bytes_per_second=0.87% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):17/manual_time 16259 ns 1090390980 ns 42510 bytes=131.072k bytes_per_second=7.50803G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):17/manual_time 16345 ns 1092192323 ns 42510 bytes=131.072k bytes_per_second=7.46836G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):17/manual_time 16543 ns 1091541248 ns 42510 bytes=131.072k bytes_per_second=7.37914G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):17/manual_time 16502 ns 1091779404 ns 42510 bytes=131.072k bytes_per_second=7.39713G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):17/manual_time 16228 ns 1089350889 ns 42510 bytes=131.072k bytes_per_second=7.52238G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):17/manual_time_mean 16375 ns 1091050969 ns 5 bytes=131.072k bytes_per_second=7.45501G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):17/manual_time_median 16345 ns 1091541248 ns 5 bytes=131.072k bytes_per_second=7.46836G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):17/manual_time_stddev 142 ns 1161845 ns 5 bytes=0 bytes_per_second=66.0328M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):17/manual_time_cv 0.87 % 0.11 % 5 bytes=0.00% bytes_per_second=0.86% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):18/manual_time 19381 ns 1046207034 ns 36381 bytes=262.144k bytes_per_second=12.5967G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):18/manual_time 19358 ns 1046194600 ns 36381 bytes=262.144k bytes_per_second=12.612G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):18/manual_time 19127 ns 1044912244 ns 36381 bytes=262.144k bytes_per_second=12.764G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):18/manual_time 19241 ns 1045819735 ns 36381 bytes=262.144k bytes_per_second=12.6882G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):18/manual_time 19387 ns 1045759420 ns 36381 bytes=262.144k bytes_per_second=12.5932G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):18/manual_time_mean 19299 ns 1045778607 ns 5 bytes=262.144k bytes_per_second=12.6508G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):18/manual_time_median 19358 ns 1045819735 ns 5 bytes=262.144k bytes_per_second=12.612G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):18/manual_time_stddev 113 ns 526603 ns 5 bytes=0 bytes_per_second=75.892M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):18/manual_time_cv 0.58 % 0.05 % 5 bytes=0.00% bytes_per_second=0.59% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):19/manual_time 25060 ns 872652467 ns 27726 bytes=524.288k bytes_per_second=19.4842G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):19/manual_time 25112 ns 873427931 ns 27726 bytes=524.288k bytes_per_second=19.4442G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):19/manual_time 25305 ns 872927617 ns 27726 bytes=524.288k bytes_per_second=19.2961G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):19/manual_time 25242 ns 873040386 ns 27726 bytes=524.288k bytes_per_second=19.3441G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):19/manual_time 25064 ns 872400393 ns 27726 bytes=524.288k bytes_per_second=19.481G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):19/manual_time_mean 25157 ns 872889759 ns 5 bytes=524.288k bytes_per_second=19.4099G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):19/manual_time_median 25112 ns 872927617 ns 5 bytes=524.288k bytes_per_second=19.4442G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):19/manual_time_stddev 111 ns 390364 ns 5 bytes=0 bytes_per_second=87.269M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):19/manual_time_cv 0.44 % 0.04 % 5 bytes=0.00% bytes_per_second=0.44% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):20/manual_time 39250 ns 699733004 ns 17910 bytes=1048.58k bytes_per_second=24.8805G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):20/manual_time 39219 ns 699642336 ns 17910 bytes=1048.58k bytes_per_second=24.9004G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):20/manual_time 38985 ns 699689072 ns 17910 bytes=1048.58k bytes_per_second=25.0495G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):20/manual_time 39073 ns 699489668 ns 17910 bytes=1048.58k bytes_per_second=24.993G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):20/manual_time 39267 ns 699834082 ns 17910 bytes=1048.58k bytes_per_second=24.8696G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):20/manual_time_mean 39159 ns 699677633 ns 5 bytes=1048.58k bytes_per_second=24.9386G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):20/manual_time_median 39219 ns 699689072 ns 5 bytes=1048.58k bytes_per_second=24.9004G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):20/manual_time_stddev 124 ns 126738 ns 5 bytes=0 bytes_per_second=80.7202M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):20/manual_time_cv 0.32 % 0.02 % 5 bytes=0.00% bytes_per_second=0.32% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):21/manual_time 66917 ns 555045737 ns 10434 bytes=2.09715M bytes_per_second=29.1871G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):21/manual_time 66740 ns 555149932 ns 10434 bytes=2.09715M bytes_per_second=29.2645G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):21/manual_time 66879 ns 555228387 ns 10434 bytes=2.09715M bytes_per_second=29.2037G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):21/manual_time 66957 ns 554907165 ns 10434 bytes=2.09715M bytes_per_second=29.1696G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):21/manual_time 66948 ns 555268748 ns 10434 bytes=2.09715M bytes_per_second=29.1736G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):21/manual_time_mean 66889 ns 555119994 ns 5 bytes=2.09715M bytes_per_second=29.1997G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):21/manual_time_median 66917 ns 555149932 ns 5 bytes=2.09715M bytes_per_second=29.1871G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):21/manual_time_stddev 88.3 ns 146273 ns 5 bytes=0 bytes_per_second=39.5149M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):21/manual_time_cv 0.13 % 0.03 % 5 bytes=0.00% bytes_per_second=0.13% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):22/manual_time 122769 ns 467778364 ns 5692 bytes=4.1943M bytes_per_second=31.818G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):22/manual_time 122827 ns 467704684 ns 5692 bytes=4.1943M bytes_per_second=31.803G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):22/manual_time 123032 ns 467778685 ns 5692 bytes=4.1943M bytes_per_second=31.75G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):22/manual_time 122971 ns 467860510 ns 5692 bytes=4.1943M bytes_per_second=31.7656G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):22/manual_time 122781 ns 467840774 ns 5692 bytes=4.1943M bytes_per_second=31.8148G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):22/manual_time_mean 122876 ns 467792604 ns 5 bytes=4.1943M bytes_per_second=31.7903G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):22/manual_time_median 122827 ns 467778685 ns 5 bytes=4.1943M bytes_per_second=31.803G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):22/manual_time_stddev 119 ns 61356 ns 5 bytes=0 bytes_per_second=31.4009M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):22/manual_time_cv 0.10 % 0.01 % 5 bytes=0.00% bytes_per_second=0.10% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):23/manual_time 234539 ns 420156644 ns 2985 bytes=8.38861M bytes_per_second=33.31G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):23/manual_time 234675 ns 420458189 ns 2985 bytes=8.38861M bytes_per_second=33.2907G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):23/manual_time 234648 ns 420256319 ns 2985 bytes=8.38861M bytes_per_second=33.2945G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):23/manual_time 234457 ns 420547979 ns 2985 bytes=8.38861M bytes_per_second=33.3217G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):23/manual_time 234493 ns 420074977 ns 2985 bytes=8.38861M bytes_per_second=33.3165G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):23/manual_time_mean 234563 ns 420298822 ns 5 bytes=8.38861M bytes_per_second=33.3067G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):23/manual_time_median 234539 ns 420256319 ns 5 bytes=8.38861M bytes_per_second=33.31G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):23/manual_time_stddev 95.5 ns 199753 ns 5 bytes=0 bytes_per_second=13.8881M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):23/manual_time_cv 0.04 % 0.05 % 5 bytes=0.00% bytes_per_second=0.04% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):24/manual_time 458202 ns 395314974 ns 1528 bytes=16.7772M bytes_per_second=34.1007G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):24/manual_time 458105 ns 395341096 ns 1528 bytes=16.7772M bytes_per_second=34.1079G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):24/manual_time 457897 ns 395330918 ns 1528 bytes=16.7772M bytes_per_second=34.1234G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):24/manual_time 457915 ns 395205279 ns 1528 bytes=16.7772M bytes_per_second=34.1221G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):24/manual_time 458136 ns 395336799 ns 1528 bytes=16.7772M bytes_per_second=34.1056G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):24/manual_time_mean 458051 ns 395305813 ns 5 bytes=16.7772M bytes_per_second=34.1119G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):24/manual_time_median 458105 ns 395330918 ns 5 bytes=16.7772M bytes_per_second=34.1079G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):24/manual_time_stddev 137 ns 57066 ns 5 bytes=0 bytes_per_second=10.4688M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):24/manual_time_cv 0.03 % 0.01 % 5 bytes=0.00% bytes_per_second=0.03% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):25/manual_time 904757 ns 382790292 ns 773 bytes=33.5544M bytes_per_second=34.5397G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):25/manual_time 904707 ns 382837047 ns 773 bytes=33.5544M bytes_per_second=34.5416G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):25/manual_time 904522 ns 382777046 ns 773 bytes=33.5544M bytes_per_second=34.5486G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):25/manual_time 904572 ns 382770326 ns 773 bytes=33.5544M bytes_per_second=34.5467G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):25/manual_time 904772 ns 382800905 ns 773 bytes=33.5544M bytes_per_second=34.5391G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):25/manual_time_mean 904666 ns 382795123 ns 5 bytes=33.5544M bytes_per_second=34.5431G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):25/manual_time_median 904707 ns 382790292 ns 5 bytes=33.5544M bytes_per_second=34.5416G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):25/manual_time_stddev 113 ns 26249 ns 5 bytes=0 bytes_per_second=4.40517M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):25/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):26/manual_time 1797858 ns 377792438 ns 389 bytes=67.1089M bytes_per_second=34.7636G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):26/manual_time 1798285 ns 377886168 ns 389 bytes=67.1089M bytes_per_second=34.7553G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):26/manual_time 1797678 ns 377809078 ns 389 bytes=67.1089M bytes_per_second=34.7671G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):26/manual_time 1797686 ns 377800870 ns 389 bytes=67.1089M bytes_per_second=34.7669G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):26/manual_time 1798264 ns 377888001 ns 389 bytes=67.1089M bytes_per_second=34.7557G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):26/manual_time_mean 1797954 ns 377835311 ns 5 bytes=67.1089M bytes_per_second=34.7617G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):26/manual_time_median 1797858 ns 377809078 ns 5 bytes=67.1089M bytes_per_second=34.7636G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):26/manual_time_stddev 301 ns 47632 ns 5 bytes=0 bytes_per_second=5.96734M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):26/manual_time_cv 0.02 % 0.01 % 5 bytes=0.00% bytes_per_second=0.02% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):27/manual_time 3584191 ns 378556636 ns 195 bytes=134.218M bytes_per_second=34.8754G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):27/manual_time 3584743 ns 378610103 ns 195 bytes=134.218M bytes_per_second=34.87G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):27/manual_time 3583907 ns 378538480 ns 195 bytes=134.218M bytes_per_second=34.8781G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):27/manual_time 3583967 ns 378490865 ns 195 bytes=134.218M bytes_per_second=34.8776G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):27/manual_time 3584726 ns 378635186 ns 195 bytes=134.218M bytes_per_second=34.8702G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):27/manual_time_mean 3584307 ns 378566254 ns 5 bytes=134.218M bytes_per_second=34.8742G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):27/manual_time_median 3584191 ns 378556636 ns 5 bytes=134.218M bytes_per_second=34.8754G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):27/manual_time_stddev 405 ns 57493 ns 5 bytes=0 bytes_per_second=4.03089M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):27/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):28/manual_time 7156792 ns 383474747 ns 98 bytes=268.435M bytes_per_second=34.9319G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):28/manual_time 7156838 ns 383452673 ns 98 bytes=268.435M bytes_per_second=34.9316G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):28/manual_time 7157151 ns 383507090 ns 98 bytes=268.435M bytes_per_second=34.9301G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):28/manual_time 7156466 ns 383483891 ns 98 bytes=268.435M bytes_per_second=34.9334G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):28/manual_time 7156304 ns 383449909 ns 98 bytes=268.435M bytes_per_second=34.9342G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):28/manual_time_mean 7156710 ns 383473662 ns 5 bytes=268.435M bytes_per_second=34.9323G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):28/manual_time_median 7156792 ns 383474747 ns 5 bytes=268.435M bytes_per_second=34.9319G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):28/manual_time_stddev 333 ns 23601 ns 5 bytes=0 bytes_per_second=1.6622M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):28/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):29/manual_time 14301173 ns 393078714 ns 49 bytes=536.871M bytes_per_second=34.9622G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):29/manual_time 14302894 ns 393174880 ns 49 bytes=536.871M bytes_per_second=34.958G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):29/manual_time 14301098 ns 393085848 ns 49 bytes=536.871M bytes_per_second=34.9624G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):29/manual_time 14302130 ns 393111452 ns 49 bytes=536.871M bytes_per_second=34.9598G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):29/manual_time 14301441 ns 393128260 ns 49 bytes=536.871M bytes_per_second=34.9615G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):29/manual_time_mean 14301747 ns 393115831 ns 5 bytes=536.871M bytes_per_second=34.9608G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):29/manual_time_median 14301441 ns 393111452 ns 5 bytes=536.871M bytes_per_second=34.9615G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):29/manual_time_stddev 759 ns 38526 ns 5 bytes=0 bytes_per_second=1.90061M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):29/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):30/manual_time 28594980 ns 407404426 ns 24 bytes=1073.74M bytes_per_second=34.9712G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):30/manual_time 28593107 ns 407361824 ns 24 bytes=1073.74M bytes_per_second=34.9735G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):30/manual_time 28594554 ns 407418894 ns 24 bytes=1073.74M bytes_per_second=34.9717G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):30/manual_time 28592454 ns 407356699 ns 24 bytes=1073.74M bytes_per_second=34.9743G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):30/manual_time 28591147 ns 407326077 ns 24 bytes=1073.74M bytes_per_second=34.9759G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):30/manual_time_mean 28593248 ns 407373584 ns 5 bytes=1073.74M bytes_per_second=34.9733G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):30/manual_time_median 28593107 ns 407361824 ns 5 bytes=1073.74M bytes_per_second=34.9735G/s dst_id=3 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):30/manual_time_stddev 1563 ns 37698 ns 5 bytes=0 bytes_per_second=1.95762M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/3/log2(N):30/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):8/manual_time 12694 ns 1275790415 ns 55235 bytes=256 bytes_per_second=19.2321M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):8/manual_time 12708 ns 1277282223 ns 55235 bytes=256 bytes_per_second=19.2116M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):8/manual_time 12696 ns 1276398059 ns 55235 bytes=256 bytes_per_second=19.2299M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):8/manual_time 12700 ns 1276375039 ns 55235 bytes=256 bytes_per_second=19.2232M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):8/manual_time 12705 ns 1275194782 ns 55235 bytes=256 bytes_per_second=19.2163M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):8/manual_time_mean 12701 ns 1276208104 ns 5 bytes=256 bytes_per_second=19.2226M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):8/manual_time_median 12700 ns 1276375039 ns 5 bytes=256 bytes_per_second=19.2232M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):8/manual_time_stddev 5.75 ns 777652 ns 5 bytes=0 bytes_per_second=8.91286k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):8/manual_time_cv 0.05 % 0.06 % 5 bytes=0.00% bytes_per_second=0.05% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):9/manual_time 12729 ns 1269954185 ns 54869 bytes=512 bytes_per_second=38.3601M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):9/manual_time 12738 ns 1270884362 ns 54869 bytes=512 bytes_per_second=38.3341M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):9/manual_time 12732 ns 1269941790 ns 54869 bytes=512 bytes_per_second=38.3505M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):9/manual_time 12760 ns 1271519142 ns 54869 bytes=512 bytes_per_second=38.2673M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):9/manual_time 12714 ns 1269457332 ns 54869 bytes=512 bytes_per_second=38.4056M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):9/manual_time_mean 12734 ns 1270351362 ns 5 bytes=512 bytes_per_second=38.3435M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):9/manual_time_median 12732 ns 1269954185 ns 5 bytes=512 bytes_per_second=38.3505M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):9/manual_time_stddev 16.7 ns 832554 ns 5 bytes=0 bytes_per_second=51.3977k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):9/manual_time_cv 0.13 % 0.07 % 5 bytes=0.00% bytes_per_second=0.13% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):10/manual_time 12821 ns 1269749230 ns 54590 bytes=1024 bytes_per_second=76.1685M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):10/manual_time 12833 ns 1269716551 ns 54590 bytes=1024 bytes_per_second=76.1003M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):10/manual_time 12783 ns 1265446037 ns 54590 bytes=1024 bytes_per_second=76.3966M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):10/manual_time 12828 ns 1270146990 ns 54590 bytes=1024 bytes_per_second=76.1269M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):10/manual_time 12788 ns 1266364706 ns 54590 bytes=1024 bytes_per_second=76.3656M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):10/manual_time_mean 12811 ns 1268284703 ns 5 bytes=1024 bytes_per_second=76.2316M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):10/manual_time_median 12821 ns 1269716551 ns 5 bytes=1024 bytes_per_second=76.1685M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):10/manual_time_stddev 23.4 ns 2202700 ns 5 bytes=0 bytes_per_second=142.395k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):10/manual_time_cv 0.18 % 0.17 % 5 bytes=0.00% bytes_per_second=0.18% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):11/manual_time 12936 ns 1259633294 ns 54025 bytes=2.048k bytes_per_second=150.982M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):11/manual_time 12958 ns 1259855554 ns 54025 bytes=2.048k bytes_per_second=150.729M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):11/manual_time 12969 ns 1259212528 ns 54025 bytes=2.048k bytes_per_second=150.601M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):11/manual_time 12963 ns 1260014584 ns 54025 bytes=2.048k bytes_per_second=150.67M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):11/manual_time 12948 ns 1257404764 ns 54025 bytes=2.048k bytes_per_second=150.844M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):11/manual_time_mean 12955 ns 1259224145 ns 5 bytes=2.048k bytes_per_second=150.765M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):11/manual_time_median 12958 ns 1259633294 ns 5 bytes=2.048k bytes_per_second=150.729M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):11/manual_time_stddev 12.9 ns 1060796 ns 5 bytes=0 bytes_per_second=154.103k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):11/manual_time_cv 0.10 % 0.08 % 5 bytes=0.00% bytes_per_second=0.10% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):12/manual_time 13074 ns 1256025237 ns 53664 bytes=4.096k bytes_per_second=298.772M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):12/manual_time 13083 ns 1255891612 ns 53664 bytes=4.096k bytes_per_second=298.574M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):12/manual_time 13061 ns 1254068790 ns 53664 bytes=4.096k bytes_per_second=299.072M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):12/manual_time 13101 ns 1255252791 ns 53664 bytes=4.096k bytes_per_second=298.155M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):12/manual_time 13053 ns 1255522475 ns 53664 bytes=4.096k bytes_per_second=299.271M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):12/manual_time_mean 13075 ns 1255352181 ns 5 bytes=4.096k bytes_per_second=298.769M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):12/manual_time_median 13074 ns 1255522475 ns 5 bytes=4.096k bytes_per_second=298.772M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):12/manual_time_stddev 19.1 ns 779416 ns 5 bytes=0 bytes_per_second=445.967k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):12/manual_time_cv 0.15 % 0.06 % 5 bytes=0.00% bytes_per_second=0.15% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):13/manual_time 13274 ns 1234570512 ns 52641 bytes=8.192k bytes_per_second=588.544M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):13/manual_time 13295 ns 1234435103 ns 52641 bytes=8.192k bytes_per_second=587.633M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):13/manual_time 13282 ns 1234286187 ns 52641 bytes=8.192k bytes_per_second=588.22M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):13/manual_time 13277 ns 1233879940 ns 52641 bytes=8.192k bytes_per_second=588.444M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):13/manual_time 13264 ns 1233095192 ns 52641 bytes=8.192k bytes_per_second=589.009M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):13/manual_time_mean 13278 ns 1234053387 ns 5 bytes=8.192k bytes_per_second=588.37M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):13/manual_time_median 13277 ns 1234286187 ns 5 bytes=8.192k bytes_per_second=588.444M/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):13/manual_time_stddev 11.3 ns 594883 ns 5 bytes=0 bytes_per_second=514.505k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):13/manual_time_cv 0.09 % 0.05 % 5 bytes=0.00% bytes_per_second=0.09% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):14/manual_time 13600 ns 1230603627 ns 51505 bytes=16.384k bytes_per_second=1.12196G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):14/manual_time 13645 ns 1232570946 ns 51505 bytes=16.384k bytes_per_second=1.11826G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):14/manual_time 13544 ns 1227604320 ns 51505 bytes=16.384k bytes_per_second=1.12657G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):14/manual_time 13636 ns 1232567916 ns 51505 bytes=16.384k bytes_per_second=1.11905G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):14/manual_time 13552 ns 1230062944 ns 51505 bytes=16.384k bytes_per_second=1.12594G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):14/manual_time_mean 13595 ns 1230681951 ns 5 bytes=16.384k bytes_per_second=1.12236G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):14/manual_time_median 13600 ns 1230603627 ns 5 bytes=16.384k bytes_per_second=1.12196G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):14/manual_time_stddev 46.3 ns 2060721 ns 5 bytes=0 bytes_per_second=3.91656M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):14/manual_time_cv 0.34 % 0.17 % 5 bytes=0.00% bytes_per_second=0.34% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):15/manual_time 14003 ns 1213563960 ns 49826 bytes=32.768k bytes_per_second=2.17943G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):15/manual_time 14027 ns 1213497838 ns 49826 bytes=32.768k bytes_per_second=2.17564G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):15/manual_time 13980 ns 1215514569 ns 49826 bytes=32.768k bytes_per_second=2.18296G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):15/manual_time 14047 ns 1215208386 ns 49826 bytes=32.768k bytes_per_second=2.17253G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):15/manual_time 14001 ns 1213607067 ns 49826 bytes=32.768k bytes_per_second=2.17969G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):15/manual_time_mean 14011 ns 1214278364 ns 5 bytes=32.768k bytes_per_second=2.17805G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):15/manual_time_median 14003 ns 1213607067 ns 5 bytes=32.768k bytes_per_second=2.17943G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):15/manual_time_stddev 25.9 ns 995412 ns 5 bytes=0 bytes_per_second=4.12727M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):15/manual_time_cv 0.19 % 0.08 % 5 bytes=0.00% bytes_per_second=0.19% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):16/manual_time 14844 ns 1199775158 ns 47094 bytes=65.536k bytes_per_second=4.11168G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):16/manual_time 14887 ns 1200613563 ns 47094 bytes=65.536k bytes_per_second=4.0999G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):16/manual_time 14864 ns 1202794313 ns 47094 bytes=65.536k bytes_per_second=4.10623G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):16/manual_time 14852 ns 1199843805 ns 47094 bytes=65.536k bytes_per_second=4.10952G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):16/manual_time 14877 ns 1201686690 ns 47094 bytes=65.536k bytes_per_second=4.10266G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):16/manual_time_mean 14865 ns 1200942706 ns 5 bytes=65.536k bytes_per_second=4.106G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):16/manual_time_median 14864 ns 1200613563 ns 5 bytes=65.536k bytes_per_second=4.10623G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):16/manual_time_stddev 17.5 ns 1290450 ns 5 bytes=0 bytes_per_second=4.93943M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):16/manual_time_cv 0.12 % 0.11 % 5 bytes=0.00% bytes_per_second=0.12% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):17/manual_time 20367 ns 1021127863 ns 34324 bytes=131.072k bytes_per_second=5.99353G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):17/manual_time 20363 ns 1020850851 ns 34324 bytes=131.072k bytes_per_second=5.99472G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):17/manual_time 20386 ns 1021003725 ns 34324 bytes=131.072k bytes_per_second=5.98795G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):17/manual_time 20364 ns 1020198760 ns 34324 bytes=131.072k bytes_per_second=5.99428G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):17/manual_time 20399 ns 1020660000 ns 34324 bytes=131.072k bytes_per_second=5.98422G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):17/manual_time_mean 20376 ns 1020768240 ns 5 bytes=131.072k bytes_per_second=5.99094G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):17/manual_time_median 20367 ns 1020850851 ns 5 bytes=131.072k bytes_per_second=5.99353G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):17/manual_time_stddev 15.8 ns 363191 ns 5 bytes=0 bytes_per_second=4.75307M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):17/manual_time_cv 0.08 % 0.04 % 5 bytes=0.00% bytes_per_second=0.08% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):18/manual_time 21617 ns 1047973752 ns 32434 bytes=262.144k bytes_per_second=11.294G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):18/manual_time 21568 ns 1046904782 ns 32434 bytes=262.144k bytes_per_second=11.3194G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):18/manual_time 21612 ns 1044711808 ns 32434 bytes=262.144k bytes_per_second=11.2967G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):18/manual_time 21618 ns 1044443388 ns 32434 bytes=262.144k bytes_per_second=11.2932G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):18/manual_time 21599 ns 1045540200 ns 32434 bytes=262.144k bytes_per_second=11.3032G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):18/manual_time_mean 21603 ns 1045914786 ns 5 bytes=262.144k bytes_per_second=11.3013G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):18/manual_time_median 21612 ns 1045540200 ns 5 bytes=262.144k bytes_per_second=11.2967G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):18/manual_time_stddev 20.8 ns 1497658 ns 5 bytes=0 bytes_per_second=11.1339M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):18/manual_time_cv 0.10 % 0.14 % 5 bytes=0.00% bytes_per_second=0.10% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):19/manual_time 26898 ns 908759782 ns 25968 bytes=524.288k bytes_per_second=18.1529G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):19/manual_time 26921 ns 907586385 ns 25968 bytes=524.288k bytes_per_second=18.1378G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):19/manual_time 26895 ns 907859344 ns 25968 bytes=524.288k bytes_per_second=18.1548G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):19/manual_time 26942 ns 908333107 ns 25968 bytes=524.288k bytes_per_second=18.1235G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):19/manual_time 26895 ns 906594441 ns 25968 bytes=524.288k bytes_per_second=18.1551G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):19/manual_time_mean 26910 ns 907826612 ns 5 bytes=524.288k bytes_per_second=18.1448G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):19/manual_time_median 26898 ns 907859344 ns 5 bytes=524.288k bytes_per_second=18.1529G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):19/manual_time_stddev 20.7 ns 822248 ns 5 bytes=0 bytes_per_second=14.2627M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):19/manual_time_cv 0.08 % 0.09 % 5 bytes=0.00% bytes_per_second=0.08% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):20/manual_time 40870 ns 720017418 ns 17130 bytes=1048.58k bytes_per_second=23.8946G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):20/manual_time 40856 ns 720190901 ns 17130 bytes=1048.58k bytes_per_second=23.9023G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):20/manual_time 40842 ns 719227870 ns 17130 bytes=1048.58k bytes_per_second=23.9106G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):20/manual_time 40844 ns 719928910 ns 17130 bytes=1048.58k bytes_per_second=23.9094G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):20/manual_time 40857 ns 719230080 ns 17130 bytes=1048.58k bytes_per_second=23.9022G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):20/manual_time_mean 40854 ns 719719036 ns 5 bytes=1048.58k bytes_per_second=23.9038G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):20/manual_time_median 40856 ns 719928910 ns 5 bytes=1048.58k bytes_per_second=23.9023G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):20/manual_time_stddev 11.0 ns 457181 ns 5 bytes=0 bytes_per_second=6.5951M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):20/manual_time_cv 0.03 % 0.06 % 5 bytes=0.00% bytes_per_second=0.03% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):21/manual_time 68738 ns 571504074 ns 10180 bytes=2.09715M bytes_per_second=28.4138G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):21/manual_time 68711 ns 571240729 ns 10180 bytes=2.09715M bytes_per_second=28.4252G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):21/manual_time 68747 ns 571791664 ns 10180 bytes=2.09715M bytes_per_second=28.4102G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):21/manual_time 68706 ns 571943129 ns 10180 bytes=2.09715M bytes_per_second=28.4274G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):21/manual_time 68721 ns 572030011 ns 10180 bytes=2.09715M bytes_per_second=28.4209G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):21/manual_time_mean 68725 ns 571701921 ns 5 bytes=2.09715M bytes_per_second=28.4195G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):21/manual_time_median 68721 ns 571791664 ns 5 bytes=2.09715M bytes_per_second=28.4209G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):21/manual_time_stddev 17.8 ns 326236 ns 5 bytes=0 bytes_per_second=7.51788M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):21/manual_time_cv 0.03 % 0.06 % 5 bytes=0.00% bytes_per_second=0.03% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):22/manual_time 124635 ns 481085139 ns 5614 bytes=4.1943M bytes_per_second=31.3415G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):22/manual_time 124654 ns 481423097 ns 5614 bytes=4.1943M bytes_per_second=31.3368G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):22/manual_time 124621 ns 481157531 ns 5614 bytes=4.1943M bytes_per_second=31.3449G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):22/manual_time 124662 ns 481377010 ns 5614 bytes=4.1943M bytes_per_second=31.3347G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):22/manual_time 124629 ns 481070273 ns 5614 bytes=4.1943M bytes_per_second=31.343G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):22/manual_time_mean 124640 ns 481222610 ns 5 bytes=4.1943M bytes_per_second=31.3402G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):22/manual_time_median 124635 ns 481157531 ns 5 bytes=4.1943M bytes_per_second=31.3415G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):22/manual_time_stddev 17.2 ns 166113 ns 5 bytes=0 bytes_per_second=4.41571M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):22/manual_time_cv 0.01 % 0.03 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):23/manual_time 236291 ns 426740417 ns 2961 bytes=8.38861M bytes_per_second=33.063G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):23/manual_time 236256 ns 426691671 ns 2961 bytes=8.38861M bytes_per_second=33.068G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):23/manual_time 236284 ns 426731162 ns 2961 bytes=8.38861M bytes_per_second=33.064G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):23/manual_time 236255 ns 426529588 ns 2961 bytes=8.38861M bytes_per_second=33.0681G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):23/manual_time 236267 ns 426752816 ns 2961 bytes=8.38861M bytes_per_second=33.0664G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):23/manual_time_mean 236270 ns 426689131 ns 5 bytes=8.38861M bytes_per_second=33.0659G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):23/manual_time_median 236267 ns 426731162 ns 5 bytes=8.38861M bytes_per_second=33.0664G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):23/manual_time_stddev 16.6 ns 92078 ns 5 bytes=0 bytes_per_second=2.37772M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):23/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):24/manual_time 459809 ns 398110652 ns 1522 bytes=16.7772M bytes_per_second=33.9815G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):24/manual_time 459763 ns 398055355 ns 1522 bytes=16.7772M bytes_per_second=33.9849G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):24/manual_time 459803 ns 398025897 ns 1522 bytes=16.7772M bytes_per_second=33.9819G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):24/manual_time 459882 ns 398150249 ns 1522 bytes=16.7772M bytes_per_second=33.9761G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):24/manual_time 459730 ns 398001894 ns 1522 bytes=16.7772M bytes_per_second=33.9873G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):24/manual_time_mean 459797 ns 398068809 ns 5 bytes=16.7772M bytes_per_second=33.9824G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):24/manual_time_median 459803 ns 398055355 ns 5 bytes=16.7772M bytes_per_second=33.9819G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):24/manual_time_stddev 57.1 ns 60999 ns 5 bytes=0 bytes_per_second=4.32235M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):24/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):25/manual_time 906326 ns 384219226 ns 772 bytes=33.5544M bytes_per_second=34.4799G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):25/manual_time 906388 ns 384209412 ns 772 bytes=33.5544M bytes_per_second=34.4775G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):25/manual_time 906356 ns 384188147 ns 772 bytes=33.5544M bytes_per_second=34.4787G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):25/manual_time 906294 ns 384360634 ns 772 bytes=33.5544M bytes_per_second=34.4811G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):25/manual_time 906277 ns 384293704 ns 772 bytes=33.5544M bytes_per_second=34.4817G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):25/manual_time_mean 906328 ns 384254225 ns 5 bytes=33.5544M bytes_per_second=34.4798G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):25/manual_time_median 906326 ns 384219226 ns 5 bytes=33.5544M bytes_per_second=34.4799G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):25/manual_time_stddev 45.3 ns 71556 ns 5 bytes=0 bytes_per_second=1.76636M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):25/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):26/manual_time 1799421 ns 378888188 ns 389 bytes=67.1089M bytes_per_second=34.7334G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):26/manual_time 1799857 ns 378945642 ns 389 bytes=67.1089M bytes_per_second=34.725G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):26/manual_time 1799534 ns 378922080 ns 389 bytes=67.1089M bytes_per_second=34.7312G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):26/manual_time 1799363 ns 378870784 ns 389 bytes=67.1089M bytes_per_second=34.7345G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):26/manual_time 1799891 ns 378973920 ns 389 bytes=67.1089M bytes_per_second=34.7243G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):26/manual_time_mean 1799613 ns 378920123 ns 5 bytes=67.1089M bytes_per_second=34.7297G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):26/manual_time_median 1799534 ns 378922080 ns 5 bytes=67.1089M bytes_per_second=34.7312G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):26/manual_time_stddev 246 ns 41843 ns 5 bytes=0 bytes_per_second=4.86815M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):26/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):27/manual_time 3585697 ns 379071584 ns 195 bytes=134.218M bytes_per_second=34.8607G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):27/manual_time 3586146 ns 379153176 ns 195 bytes=134.218M bytes_per_second=34.8564G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):27/manual_time 3585510 ns 379051574 ns 195 bytes=134.218M bytes_per_second=34.8625G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):27/manual_time 3585717 ns 379127970 ns 195 bytes=134.218M bytes_per_second=34.8605G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):27/manual_time 3586176 ns 379166326 ns 195 bytes=134.218M bytes_per_second=34.8561G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):27/manual_time_mean 3585849 ns 379114126 ns 5 bytes=134.218M bytes_per_second=34.8592G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):27/manual_time_median 3585717 ns 379127970 ns 5 bytes=134.218M bytes_per_second=34.8605G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):27/manual_time_stddev 296 ns 50408 ns 5 bytes=0 bytes_per_second=2.94782M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):27/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):28/manual_time 7157984 ns 383843580 ns 98 bytes=268.435M bytes_per_second=34.926G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):28/manual_time 7158425 ns 383762289 ns 98 bytes=268.435M bytes_per_second=34.9239G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):28/manual_time 7157990 ns 383762558 ns 98 bytes=268.435M bytes_per_second=34.926G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):28/manual_time 7158164 ns 383752267 ns 98 bytes=268.435M bytes_per_second=34.9252G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):28/manual_time 7158619 ns 383777268 ns 98 bytes=268.435M bytes_per_second=34.9229G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):28/manual_time_mean 7158236 ns 383779593 ns 5 bytes=268.435M bytes_per_second=34.9248G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):28/manual_time_median 7158164 ns 383762558 ns 5 bytes=268.435M bytes_per_second=34.9252G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):28/manual_time_stddev 279 ns 36865 ns 5 bytes=0 bytes_per_second=1.39409M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):28/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):29/manual_time 14304209 ns 393268379 ns 49 bytes=536.871M bytes_per_second=34.9547G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):29/manual_time 14304043 ns 393282438 ns 49 bytes=536.871M bytes_per_second=34.9552G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):29/manual_time 14303174 ns 393264603 ns 49 bytes=536.871M bytes_per_second=34.9573G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):29/manual_time 14304150 ns 393294706 ns 49 bytes=536.871M bytes_per_second=34.9549G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):29/manual_time 14303318 ns 393256133 ns 49 bytes=536.871M bytes_per_second=34.9569G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):29/manual_time_mean 14303779 ns 393273252 ns 5 bytes=536.871M bytes_per_second=34.9558G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):29/manual_time_median 14304043 ns 393268379 ns 5 bytes=536.871M bytes_per_second=34.9552G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):29/manual_time_stddev 493 ns 15299 ns 5 bytes=0 bytes_per_second=1.23302M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):29/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):30/manual_time 28600150 ns 407503223 ns 24 bytes=1073.74M bytes_per_second=34.9649G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):30/manual_time 28596137 ns 407499215 ns 24 bytes=1073.74M bytes_per_second=34.9698G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):30/manual_time 28596604 ns 407502835 ns 24 bytes=1073.74M bytes_per_second=34.9692G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):30/manual_time 28596450 ns 407478293 ns 24 bytes=1073.74M bytes_per_second=34.9694G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):30/manual_time 28596264 ns 407478162 ns 24 bytes=1073.74M bytes_per_second=34.9696G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):30/manual_time_mean 28597121 ns 407492346 ns 5 bytes=1073.74M bytes_per_second=34.9686G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):30/manual_time_median 28596450 ns 407499215 ns 5 bytes=1073.74M bytes_per_second=34.9694G/s dst_id=4 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):30/manual_time_stddev 1703 ns 12983 ns 5 bytes=0 bytes_per_second=2.1319M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/4/log2(N):30/manual_time_cv 0.01 % 0.00 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):8/manual_time 12199 ns 1194999593 ns 57477 bytes=256 bytes_per_second=20.0132M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):8/manual_time 12226 ns 1197812481 ns 57477 bytes=256 bytes_per_second=19.9684M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):8/manual_time 12203 ns 1189843255 ns 57477 bytes=256 bytes_per_second=20.0061M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):8/manual_time 12174 ns 1193081975 ns 57477 bytes=256 bytes_per_second=20.054M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):8/manual_time 12182 ns 1195089640 ns 57477 bytes=256 bytes_per_second=20.0409M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):8/manual_time_mean 12197 ns 1194165389 ns 5 bytes=256 bytes_per_second=20.0165M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):8/manual_time_median 12199 ns 1194999593 ns 5 bytes=256 bytes_per_second=20.0132M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):8/manual_time_stddev 20.3 ns 2945592 ns 5 bytes=0 bytes_per_second=34.1019k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):8/manual_time_cv 0.17 % 0.25 % 5 bytes=0.00% bytes_per_second=0.17% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):9/manual_time 12306 ns 1178016872 ns 56729 bytes=512 bytes_per_second=39.6785M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):9/manual_time 12292 ns 1181303057 ns 56729 bytes=512 bytes_per_second=39.7243M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):9/manual_time 12332 ns 1183818048 ns 56729 bytes=512 bytes_per_second=39.5961M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):9/manual_time 12334 ns 1186383120 ns 56729 bytes=512 bytes_per_second=39.5868M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):9/manual_time 12291 ns 1178618821 ns 56729 bytes=512 bytes_per_second=39.7269M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):9/manual_time_mean 12311 ns 1181627984 ns 5 bytes=512 bytes_per_second=39.6625M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):9/manual_time_median 12306 ns 1181303057 ns 5 bytes=512 bytes_per_second=39.6785M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):9/manual_time_stddev 21.0 ns 3521664 ns 5 bytes=0 bytes_per_second=69.4129k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):9/manual_time_cv 0.17 % 0.30 % 5 bytes=0.00% bytes_per_second=0.17% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):10/manual_time 12407 ns 1185275319 ns 56595 bytes=1024 bytes_per_second=78.711M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):10/manual_time 12444 ns 1188354956 ns 56595 bytes=1024 bytes_per_second=78.4741M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):10/manual_time 12383 ns 1178132253 ns 56595 bytes=1024 bytes_per_second=78.8661M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):10/manual_time 12386 ns 1182206545 ns 56595 bytes=1024 bytes_per_second=78.844M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):10/manual_time 12395 ns 1185085003 ns 56595 bytes=1024 bytes_per_second=78.7857M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):10/manual_time_mean 12403 ns 1183810815 ns 5 bytes=1024 bytes_per_second=78.7362M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):10/manual_time_median 12395 ns 1185085003 ns 5 bytes=1024 bytes_per_second=78.7857M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):10/manual_time_stddev 25.0 ns 3848288 ns 5 bytes=0 bytes_per_second=162.149k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):10/manual_time_cv 0.20 % 0.33 % 5 bytes=0.00% bytes_per_second=0.20% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):11/manual_time 12489 ns 1167014475 ns 55869 bytes=2.048k bytes_per_second=156.385M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):11/manual_time 12469 ns 1170267869 ns 55869 bytes=2.048k bytes_per_second=156.643M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):11/manual_time 12481 ns 1172446148 ns 55869 bytes=2.048k bytes_per_second=156.484M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):11/manual_time 12519 ns 1174223302 ns 55869 bytes=2.048k bytes_per_second=156.013M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):11/manual_time 12481 ns 1165825675 ns 55869 bytes=2.048k bytes_per_second=156.486M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):11/manual_time_mean 12488 ns 1169955494 ns 5 bytes=2.048k bytes_per_second=156.402M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):11/manual_time_median 12481 ns 1170267869 ns 5 bytes=2.048k bytes_per_second=156.484M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):11/manual_time_stddev 18.9 ns 3543308 ns 5 bytes=0 bytes_per_second=241.787k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):11/manual_time_cv 0.15 % 0.30 % 5 bytes=0.00% bytes_per_second=0.15% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):12/manual_time 12639 ns 1168169108 ns 55399 bytes=4.096k bytes_per_second=309.071M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):12/manual_time 12711 ns 1170510915 ns 55399 bytes=4.096k bytes_per_second=307.321M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):12/manual_time 12622 ns 1162772426 ns 55399 bytes=4.096k bytes_per_second=309.484M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):12/manual_time 12638 ns 1165327946 ns 55399 bytes=4.096k bytes_per_second=309.098M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):12/manual_time 12641 ns 1167897444 ns 55399 bytes=4.096k bytes_per_second=309.024M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):12/manual_time_mean 12650 ns 1166935568 ns 5 bytes=4.096k bytes_per_second=308.799M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):12/manual_time_median 12639 ns 1167897444 ns 5 bytes=4.096k bytes_per_second=309.071M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):12/manual_time_stddev 34.8 ns 2964209 ns 5 bytes=0 bytes_per_second=866.811k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):12/manual_time_cv 0.28 % 0.25 % 5 bytes=0.00% bytes_per_second=0.27% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):13/manual_time 12781 ns 1150067783 ns 54618 bytes=8.192k bytes_per_second=611.236M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):13/manual_time 12773 ns 1152685198 ns 54618 bytes=8.192k bytes_per_second=611.635M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):13/manual_time 12750 ns 1155347428 ns 54618 bytes=8.192k bytes_per_second=612.768M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):13/manual_time 12819 ns 1155742436 ns 54618 bytes=8.192k bytes_per_second=609.465M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):13/manual_time 12746 ns 1149388568 ns 54618 bytes=8.192k bytes_per_second=612.931M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):13/manual_time_mean 12774 ns 1152646283 ns 5 bytes=8.192k bytes_per_second=611.607M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):13/manual_time_median 12773 ns 1152685198 ns 5 bytes=8.192k bytes_per_second=611.635M/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):13/manual_time_stddev 29.2 ns 2921696 ns 5 bytes=0 bytes_per_second=1.39873M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):13/manual_time_cv 0.23 % 0.25 % 5 bytes=0.00% bytes_per_second=0.23% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):14/manual_time 13098 ns 1151610206 ns 53422 bytes=16.384k bytes_per_second=1.165G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):14/manual_time 13142 ns 1153919874 ns 53422 bytes=16.384k bytes_per_second=1.16111G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):14/manual_time 13102 ns 1147028507 ns 53422 bytes=16.384k bytes_per_second=1.16465G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):14/manual_time 13103 ns 1149655971 ns 53422 bytes=16.384k bytes_per_second=1.16451G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):14/manual_time 13133 ns 1152459982 ns 53422 bytes=16.384k bytes_per_second=1.16191G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):14/manual_time_mean 13115 ns 1150934908 ns 5 bytes=16.384k bytes_per_second=1.16343G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):14/manual_time_median 13103 ns 1151610206 ns 5 bytes=16.384k bytes_per_second=1.16451G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):14/manual_time_stddev 20.2 ns 2673366 ns 5 bytes=0 bytes_per_second=1.83215M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):14/manual_time_cv 0.15 % 0.23 % 5 bytes=0.00% bytes_per_second=0.15% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):15/manual_time 13542 ns 1141649162 ns 51563 bytes=32.768k bytes_per_second=2.25358G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):15/manual_time 13531 ns 1143914590 ns 51563 bytes=32.768k bytes_per_second=2.25545G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):15/manual_time 13547 ns 1147384628 ns 51563 bytes=32.768k bytes_per_second=2.25267G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):15/manual_time 13561 ns 1147986878 ns 51563 bytes=32.768k bytes_per_second=2.25043G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):15/manual_time 13531 ns 1141881168 ns 51563 bytes=32.768k bytes_per_second=2.25532G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):15/manual_time_mean 13542 ns 1144563285 ns 5 bytes=32.768k bytes_per_second=2.25349G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):15/manual_time_median 13542 ns 1143914590 ns 5 bytes=32.768k bytes_per_second=2.25358G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):15/manual_time_stddev 12.5 ns 2991138 ns 5 bytes=0 bytes_per_second=2.12551M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):15/manual_time_cv 0.09 % 0.26 % 5 bytes=0.00% bytes_per_second=0.09% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):16/manual_time 14414 ns 1138083659 ns 48627 bytes=65.536k bytes_per_second=4.23458G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):16/manual_time 14451 ns 1139244840 ns 48627 bytes=65.536k bytes_per_second=4.2237G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):16/manual_time 14392 ns 1134519476 ns 48627 bytes=65.536k bytes_per_second=4.24082G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):16/manual_time 14391 ns 1136416846 ns 48627 bytes=65.536k bytes_per_second=4.24121G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):16/manual_time 14410 ns 1138647628 ns 48627 bytes=65.536k bytes_per_second=4.23555G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):16/manual_time_mean 14412 ns 1137382490 ns 5 bytes=65.536k bytes_per_second=4.23517G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):16/manual_time_median 14410 ns 1138083659 ns 5 bytes=65.536k bytes_per_second=4.23555G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):16/manual_time_stddev 24.1 ns 1916369 ns 5 bytes=0 bytes_per_second=7.25017M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):16/manual_time_cv 0.17 % 0.17 % 5 bytes=0.00% bytes_per_second=0.17% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):17/manual_time 17191 ns 1066898386 ns 40705 bytes=131.072k bytes_per_second=7.10075G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):17/manual_time 17111 ns 1066330062 ns 40705 bytes=131.072k bytes_per_second=7.13391G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):17/manual_time 17026 ns 1066078321 ns 40705 bytes=131.072k bytes_per_second=7.16946G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):17/manual_time 17176 ns 1068749720 ns 40705 bytes=131.072k bytes_per_second=7.10716G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):17/manual_time 17010 ns 1063163457 ns 40705 bytes=131.072k bytes_per_second=7.17659G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):17/manual_time_mean 17103 ns 1066243989 ns 5 bytes=131.072k bytes_per_second=7.13757G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):17/manual_time_median 17111 ns 1066330062 ns 5 bytes=131.072k bytes_per_second=7.13391G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):17/manual_time_stddev 83.3 ns 2014414 ns 5 bytes=0 bytes_per_second=35.5954M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):17/manual_time_cv 0.49 % 0.19 % 5 bytes=0.00% bytes_per_second=0.49% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):18/manual_time 19225 ns 1049903548 ns 36374 bytes=262.144k bytes_per_second=12.6992G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):18/manual_time 19277 ns 1052190890 ns 36374 bytes=262.144k bytes_per_second=12.6647G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):18/manual_time 19193 ns 1042316626 ns 36374 bytes=262.144k bytes_per_second=12.7205G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):18/manual_time 19238 ns 1047354977 ns 36374 bytes=262.144k bytes_per_second=12.6908G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):18/manual_time 19220 ns 1051413036 ns 36374 bytes=262.144k bytes_per_second=12.7022G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):18/manual_time_mean 19231 ns 1048635815 ns 5 bytes=262.144k bytes_per_second=12.6955G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):18/manual_time_median 19225 ns 1049903548 ns 5 bytes=262.144k bytes_per_second=12.6992G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):18/manual_time_stddev 30.8 ns 3985328 ns 5 bytes=0 bytes_per_second=20.8299M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):18/manual_time_cv 0.16 % 0.38 % 5 bytes=0.00% bytes_per_second=0.16% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):19/manual_time 25494 ns 871511907 ns 27402 bytes=524.288k bytes_per_second=19.1527G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):19/manual_time 25504 ns 872816808 ns 27402 bytes=524.288k bytes_per_second=19.1454G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):19/manual_time 25489 ns 875080974 ns 27402 bytes=524.288k bytes_per_second=19.1568G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):19/manual_time 25557 ns 875406140 ns 27402 bytes=524.288k bytes_per_second=19.1055G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):19/manual_time 25486 ns 871706598 ns 27402 bytes=524.288k bytes_per_second=19.1589G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):19/manual_time_mean 25506 ns 873304485 ns 5 bytes=524.288k bytes_per_second=19.1439G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):19/manual_time_median 25494 ns 872816808 ns 5 bytes=524.288k bytes_per_second=19.1527G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):19/manual_time_stddev 29.5 ns 1842368 ns 5 bytes=0 bytes_per_second=22.6046M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):19/manual_time_cv 0.12 % 0.21 % 5 bytes=0.00% bytes_per_second=0.12% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):20/manual_time 39784 ns 698636055 ns 17621 bytes=1048.58k bytes_per_second=24.5469G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):20/manual_time 39782 ns 698414787 ns 17621 bytes=1048.58k bytes_per_second=24.5478G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):20/manual_time 39733 ns 696085705 ns 17621 bytes=1048.58k bytes_per_second=24.5782G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):20/manual_time 39689 ns 695916502 ns 17621 bytes=1048.58k bytes_per_second=24.6052G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):20/manual_time 39775 ns 698288004 ns 17621 bytes=1048.58k bytes_per_second=24.5523G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):20/manual_time_mean 39752 ns 697468211 ns 5 bytes=1048.58k bytes_per_second=24.5661G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):20/manual_time_median 39775 ns 698288004 ns 5 bytes=1048.58k bytes_per_second=24.5523G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):20/manual_time_stddev 41.0 ns 1346389 ns 5 bytes=0 bytes_per_second=25.9396M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):20/manual_time_cv 0.10 % 0.19 % 5 bytes=0.00% bytes_per_second=0.10% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):21/manual_time 67978 ns 555088907 ns 10284 bytes=2.09715M bytes_per_second=28.7317G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):21/manual_time 67987 ns 554635874 ns 10284 bytes=2.09715M bytes_per_second=28.7278G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):21/manual_time 68034 ns 555080536 ns 10284 bytes=2.09715M bytes_per_second=28.7079G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):21/manual_time 67952 ns 555141071 ns 10284 bytes=2.09715M bytes_per_second=28.7426G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):21/manual_time 68048 ns 555272639 ns 10284 bytes=2.09715M bytes_per_second=28.7023G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):21/manual_time_mean 68000 ns 555043805 ns 5 bytes=2.09715M bytes_per_second=28.7224G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):21/manual_time_median 67987 ns 555088907 ns 5 bytes=2.09715M bytes_per_second=28.7278G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):21/manual_time_stddev 40.0 ns 240633 ns 5 bytes=0 bytes_per_second=17.2858M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):21/manual_time_cv 0.06 % 0.04 % 5 bytes=0.00% bytes_per_second=0.06% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):22/manual_time 124737 ns 466893161 ns 5609 bytes=4.1943M bytes_per_second=31.3159G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):22/manual_time 124709 ns 466804188 ns 5609 bytes=4.1943M bytes_per_second=31.323G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):22/manual_time 124777 ns 467509614 ns 5609 bytes=4.1943M bytes_per_second=31.3058G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):22/manual_time 124790 ns 467307863 ns 5609 bytes=4.1943M bytes_per_second=31.3027G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):22/manual_time 124712 ns 467058511 ns 5609 bytes=4.1943M bytes_per_second=31.3222G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):22/manual_time_mean 124745 ns 467114667 ns 5 bytes=4.1943M bytes_per_second=31.3139G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):22/manual_time_median 124737 ns 467058511 ns 5 bytes=4.1943M bytes_per_second=31.3159G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):22/manual_time_stddev 37.1 ns 292371 ns 5 bytes=0 bytes_per_second=9.53395M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):22/manual_time_cv 0.03 % 0.06 % 5 bytes=0.00% bytes_per_second=0.03% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):23/manual_time 238303 ns 416946052 ns 2935 bytes=8.38861M bytes_per_second=32.7839G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):23/manual_time 238319 ns 417274241 ns 2935 bytes=8.38861M bytes_per_second=32.7818G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):23/manual_time 238302 ns 417084923 ns 2935 bytes=8.38861M bytes_per_second=32.7841G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):23/manual_time 238266 ns 417201682 ns 2935 bytes=8.38861M bytes_per_second=32.789G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):23/manual_time 238336 ns 417173342 ns 2935 bytes=8.38861M bytes_per_second=32.7794G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):23/manual_time_mean 238305 ns 417136048 ns 5 bytes=8.38861M bytes_per_second=32.7836G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):23/manual_time_median 238303 ns 417173342 ns 5 bytes=8.38861M bytes_per_second=32.7839G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):23/manual_time_stddev 25.9 ns 126004 ns 5 bytes=0 bytes_per_second=3.64394M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):23/manual_time_cv 0.01 % 0.03 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):24/manual_time 465015 ns 394242557 ns 1505 bytes=16.7772M bytes_per_second=33.6011G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):24/manual_time 465115 ns 394288551 ns 1505 bytes=16.7772M bytes_per_second=33.5938G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):24/manual_time 464969 ns 394184026 ns 1505 bytes=16.7772M bytes_per_second=33.6044G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):24/manual_time 464926 ns 394100952 ns 1505 bytes=16.7772M bytes_per_second=33.6075G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):24/manual_time 465128 ns 394344283 ns 1505 bytes=16.7772M bytes_per_second=33.5929G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):24/manual_time_mean 465031 ns 394232074 ns 5 bytes=16.7772M bytes_per_second=33.5999G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):24/manual_time_median 465015 ns 394242557 ns 5 bytes=16.7772M bytes_per_second=33.6011G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):24/manual_time_stddev 88.8 ns 94064 ns 5 bytes=0 bytes_per_second=6.56702M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):24/manual_time_cv 0.02 % 0.02 % 5 bytes=0.00% bytes_per_second=0.02% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):25/manual_time 918711 ns 382040978 ns 761 bytes=33.5544M bytes_per_second=34.015G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):25/manual_time 918678 ns 382051253 ns 761 bytes=33.5544M bytes_per_second=34.0163G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):25/manual_time 918651 ns 381973126 ns 761 bytes=33.5544M bytes_per_second=34.0173G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):25/manual_time 918755 ns 382042622 ns 761 bytes=33.5544M bytes_per_second=34.0134G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):25/manual_time 918696 ns 382019993 ns 761 bytes=33.5544M bytes_per_second=34.0156G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):25/manual_time_mean 918698 ns 382025594 ns 5 bytes=33.5544M bytes_per_second=34.0155G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):25/manual_time_median 918696 ns 382040978 ns 5 bytes=33.5544M bytes_per_second=34.0156G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):25/manual_time_stddev 38.9 ns 31501 ns 5 bytes=0 bytes_per_second=1.4739M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):25/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):26/manual_time 1825514 ns 377301799 ns 383 bytes=67.1089M bytes_per_second=34.2369G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):26/manual_time 1826100 ns 377409477 ns 383 bytes=67.1089M bytes_per_second=34.2259G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):26/manual_time 1825718 ns 377326866 ns 383 bytes=67.1089M bytes_per_second=34.2331G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):26/manual_time 1825572 ns 377290844 ns 383 bytes=67.1089M bytes_per_second=34.2358G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):26/manual_time 1826057 ns 377415809 ns 383 bytes=67.1089M bytes_per_second=34.2268G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):26/manual_time_mean 1825792 ns 377348959 ns 5 bytes=67.1089M bytes_per_second=34.2317G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):26/manual_time_median 1825718 ns 377326866 ns 5 bytes=67.1089M bytes_per_second=34.2331G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):26/manual_time_stddev 272 ns 59626 ns 5 bytes=0 bytes_per_second=5.22184M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):26/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):27/manual_time 3639343 ns 378041117 ns 192 bytes=134.218M bytes_per_second=34.3469G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):27/manual_time 3640103 ns 378216818 ns 192 bytes=134.218M bytes_per_second=34.3397G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):27/manual_time 3639561 ns 378146951 ns 192 bytes=134.218M bytes_per_second=34.3448G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):27/manual_time 3639436 ns 378170594 ns 192 bytes=134.218M bytes_per_second=34.346G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):27/manual_time 3639445 ns 378109122 ns 192 bytes=134.218M bytes_per_second=34.3459G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):27/manual_time_mean 3639578 ns 378136920 ns 5 bytes=134.218M bytes_per_second=34.3446G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):27/manual_time_median 3639445 ns 378146951 ns 5 bytes=134.218M bytes_per_second=34.3459G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):27/manual_time_stddev 304 ns 66274 ns 5 bytes=0 bytes_per_second=2.93565M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):27/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):28/manual_time 7267606 ns 381340342 ns 96 bytes=268.435M bytes_per_second=34.3992G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):28/manual_time 7267613 ns 381338962 ns 96 bytes=268.435M bytes_per_second=34.3992G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):28/manual_time 7267319 ns 381288983 ns 96 bytes=268.435M bytes_per_second=34.4006G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):28/manual_time 7268011 ns 381377447 ns 96 bytes=268.435M bytes_per_second=34.3973G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):28/manual_time 7267748 ns 381369161 ns 96 bytes=268.435M bytes_per_second=34.3986G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):28/manual_time_mean 7267659 ns 381342979 ns 5 bytes=268.435M bytes_per_second=34.399G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):28/manual_time_median 7267613 ns 381340342 ns 5 bytes=268.435M bytes_per_second=34.3992G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):28/manual_time_stddev 251 ns 34685 ns 5 bytes=0 bytes_per_second=1.21698M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):28/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):29/manual_time 14522910 ns 391184506 ns 48 bytes=536.871M bytes_per_second=34.4284G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):29/manual_time 14523443 ns 391206060 ns 48 bytes=536.871M bytes_per_second=34.4271G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):29/manual_time 14523477 ns 391195414 ns 48 bytes=536.871M bytes_per_second=34.427G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):29/manual_time 14523150 ns 391190359 ns 48 bytes=536.871M bytes_per_second=34.4278G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):29/manual_time 14524183 ns 391236705 ns 48 bytes=536.871M bytes_per_second=34.4253G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):29/manual_time_mean 14523433 ns 391202609 ns 5 bytes=536.871M bytes_per_second=34.4271G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):29/manual_time_median 14523443 ns 391195414 ns 5 bytes=536.871M bytes_per_second=34.4271G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):29/manual_time_stddev 479 ns 20640 ns 5 bytes=0 bytes_per_second=1.16319M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):29/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):30/manual_time 29036594 ns 413359092 ns 24 bytes=1073.74M bytes_per_second=34.4393G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):30/manual_time 29032781 ns 413290363 ns 24 bytes=1073.74M bytes_per_second=34.4438G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):30/manual_time 29036468 ns 413378101 ns 24 bytes=1073.74M bytes_per_second=34.4395G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):30/manual_time 29034208 ns 413308723 ns 24 bytes=1073.74M bytes_per_second=34.4421G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):30/manual_time 29034348 ns 413300902 ns 24 bytes=1073.74M bytes_per_second=34.442G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):30/manual_time_mean 29034880 ns 413327436 ns 5 bytes=1073.74M bytes_per_second=34.4413G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):30/manual_time_median 29034348 ns 413308723 ns 5 bytes=1073.74M bytes_per_second=34.442G/s dst_id=5 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):30/manual_time_stddev 1628 ns 38722 ns 5 bytes=0 bytes_per_second=1.97745M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/5/log2(N):30/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):8/manual_time 12602 ns 1274535137 ns 55405 bytes=256 bytes_per_second=19.373M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):8/manual_time 12601 ns 1279053385 ns 55405 bytes=256 bytes_per_second=19.3742M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):8/manual_time 12656 ns 1280165671 ns 55405 bytes=256 bytes_per_second=19.2906M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):8/manual_time 12611 ns 1276093025 ns 55405 bytes=256 bytes_per_second=19.3591M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):8/manual_time 12606 ns 1274610055 ns 55405 bytes=256 bytes_per_second=19.3669M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):8/manual_time_mean 12615 ns 1276891455 ns 5 bytes=256 bytes_per_second=19.3528M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):8/manual_time_median 12606 ns 1276093025 ns 5 bytes=256 bytes_per_second=19.3669M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):8/manual_time_stddev 23.0 ns 2587902 ns 5 bytes=0 bytes_per_second=36.0921k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):8/manual_time_cv 0.18 % 0.20 % 5 bytes=0.00% bytes_per_second=0.18% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):9/manual_time 12699 ns 1286175532 ns 55516 bytes=512 bytes_per_second=38.4489M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):9/manual_time 12633 ns 1280647601 ns 55516 bytes=512 bytes_per_second=38.6506M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):9/manual_time 12613 ns 1282671745 ns 55516 bytes=512 bytes_per_second=38.7123M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):9/manual_time 12599 ns 1283036966 ns 55516 bytes=512 bytes_per_second=38.7558M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):9/manual_time 12696 ns 1287536349 ns 55516 bytes=512 bytes_per_second=38.4593M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):9/manual_time_mean 12648 ns 1284013639 ns 5 bytes=512 bytes_per_second=38.6054M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):9/manual_time_median 12633 ns 1283036966 ns 5 bytes=512 bytes_per_second=38.6506M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):9/manual_time_stddev 46.9 ns 2791418 ns 5 bytes=0 bytes_per_second=146.552k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):9/manual_time_cv 0.37 % 0.22 % 5 bytes=0.00% bytes_per_second=0.37% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):10/manual_time 12715 ns 1266739645 ns 54866 bytes=1024 bytes_per_second=76.8028M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):10/manual_time 12710 ns 1271082709 ns 54866 bytes=1024 bytes_per_second=76.8345M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):10/manual_time 12757 ns 1273200267 ns 54866 bytes=1024 bytes_per_second=76.5484M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):10/manual_time 12752 ns 1270758149 ns 54866 bytes=1024 bytes_per_second=76.5792M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):10/manual_time 12717 ns 1270015867 ns 54866 bytes=1024 bytes_per_second=76.7929M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):10/manual_time_mean 12730 ns 1270359328 ns 5 bytes=1024 bytes_per_second=76.7115M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):10/manual_time_median 12717 ns 1270758149 ns 5 bytes=1024 bytes_per_second=76.7929M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):10/manual_time_stddev 22.6 ns 2343787 ns 5 bytes=0 bytes_per_second=139.472k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):10/manual_time_cv 0.18 % 0.18 % 5 bytes=0.00% bytes_per_second=0.18% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):11/manual_time 12923 ns 1267846630 ns 54357 bytes=2.048k bytes_per_second=151.131M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):11/manual_time 12886 ns 1262220925 ns 54357 bytes=2.048k bytes_per_second=151.567M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):11/manual_time 12904 ns 1263464401 ns 54357 bytes=2.048k bytes_per_second=151.36M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):11/manual_time 12860 ns 1261654393 ns 54357 bytes=2.048k bytes_per_second=151.873M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):11/manual_time 12950 ns 1269975375 ns 54357 bytes=2.048k bytes_per_second=150.822M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):11/manual_time_mean 12905 ns 1265032345 ns 5 bytes=2.048k bytes_per_second=151.35M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):11/manual_time_median 12904 ns 1263464401 ns 5 bytes=2.048k bytes_per_second=151.36M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):11/manual_time_stddev 34.3 ns 3678547 ns 5 bytes=0 bytes_per_second=412.088k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):11/manual_time_cv 0.27 % 0.29 % 5 bytes=0.00% bytes_per_second=0.27% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):12/manual_time 13000 ns 1248651857 ns 53729 bytes=4.096k bytes_per_second=300.474M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):12/manual_time 12976 ns 1252422770 ns 53729 bytes=4.096k bytes_per_second=301.045M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):12/manual_time 13017 ns 1255732357 ns 53729 bytes=4.096k bytes_per_second=300.089M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):12/manual_time 13027 ns 1252862916 ns 53729 bytes=4.096k bytes_per_second=299.854M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):12/manual_time 13014 ns 1255391195 ns 53729 bytes=4.096k bytes_per_second=300.154M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):12/manual_time_mean 13007 ns 1253012219 ns 5 bytes=4.096k bytes_per_second=300.323M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):12/manual_time_median 13014 ns 1252862916 ns 5 bytes=4.096k bytes_per_second=300.154M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):12/manual_time_stddev 19.9 ns 2847858 ns 5 bytes=0 bytes_per_second=471.493k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):12/manual_time_cv 0.15 % 0.23 % 5 bytes=0.00% bytes_per_second=0.15% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):13/manual_time 13185 ns 1244982940 ns 53136 bytes=8.192k bytes_per_second=592.526M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):13/manual_time 13178 ns 1241565127 ns 53136 bytes=8.192k bytes_per_second=592.851M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):13/manual_time 13158 ns 1243027415 ns 53136 bytes=8.192k bytes_per_second=593.733M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):13/manual_time 13134 ns 1242944869 ns 53136 bytes=8.192k bytes_per_second=594.834M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):13/manual_time 13191 ns 1244676692 ns 53136 bytes=8.192k bytes_per_second=592.275M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):13/manual_time_mean 13169 ns 1243439409 ns 5 bytes=8.192k bytes_per_second=593.244M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):13/manual_time_median 13178 ns 1243027415 ns 5 bytes=8.192k bytes_per_second=592.851M/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):13/manual_time_stddev 23.2 ns 1400053 ns 5 bytes=0 bytes_per_second=1071.04k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):13/manual_time_cv 0.18 % 0.11 % 5 bytes=0.00% bytes_per_second=0.18% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):14/manual_time 13451 ns 1235581479 ns 52127 bytes=16.384k bytes_per_second=1.13444G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):14/manual_time 13419 ns 1238151195 ns 52127 bytes=16.384k bytes_per_second=1.1371G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):14/manual_time 13446 ns 1239812134 ns 52127 bytes=16.384k bytes_per_second=1.13479G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):14/manual_time 13410 ns 1235729032 ns 52127 bytes=16.384k bytes_per_second=1.13784G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):14/manual_time 13442 ns 1235166685 ns 52127 bytes=16.384k bytes_per_second=1.13518G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):14/manual_time_mean 13434 ns 1236888105 ns 5 bytes=16.384k bytes_per_second=1.13587G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):14/manual_time_median 13442 ns 1235729032 ns 5 bytes=16.384k bytes_per_second=1.13518G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):14/manual_time_stddev 17.8 ns 2009935 ns 5 bytes=0 bytes_per_second=1.54106M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):14/manual_time_cv 0.13 % 0.16 % 5 bytes=0.00% bytes_per_second=0.13% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):15/manual_time 13721 ns 1243641788 ns 51143 bytes=32.768k bytes_per_second=2.22419G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):15/manual_time 13698 ns 1239840758 ns 51143 bytes=32.768k bytes_per_second=2.22794G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):15/manual_time 13710 ns 1241293517 ns 51143 bytes=32.768k bytes_per_second=2.22592G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):15/manual_time 13672 ns 1241556405 ns 51143 bytes=32.768k bytes_per_second=2.23209G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):15/manual_time 13705 ns 1244291553 ns 51143 bytes=32.768k bytes_per_second=2.2267G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):15/manual_time_mean 13701 ns 1242124804 ns 5 bytes=32.768k bytes_per_second=2.22737G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):15/manual_time_median 13705 ns 1241556405 ns 5 bytes=32.768k bytes_per_second=2.2267G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):15/manual_time_stddev 18.3 ns 1818448 ns 5 bytes=0 bytes_per_second=3.04278M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):15/manual_time_cv 0.13 % 0.15 % 5 bytes=0.00% bytes_per_second=0.13% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):16/manual_time 14242 ns 1237919754 ns 49168 bytes=65.536k bytes_per_second=4.28543G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):16/manual_time 14236 ns 1241891256 ns 49168 bytes=65.536k bytes_per_second=4.28746G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):16/manual_time 14231 ns 1243904372 ns 49168 bytes=65.536k bytes_per_second=4.28889G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):16/manual_time 14253 ns 1243476291 ns 49168 bytes=65.536k bytes_per_second=4.28212G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):16/manual_time 14208 ns 1239665738 ns 49168 bytes=65.536k bytes_per_second=4.29596G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):16/manual_time_mean 14234 ns 1241371482 ns 5 bytes=65.536k bytes_per_second=4.28797G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):16/manual_time_median 14236 ns 1241891256 ns 5 bytes=65.536k bytes_per_second=4.28746G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):16/manual_time_stddev 17.0 ns 2546561 ns 5 bytes=0 bytes_per_second=5.26043M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):16/manual_time_cv 0.12 % 0.21 % 5 bytes=0.00% bytes_per_second=0.12% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):17/manual_time 15710 ns 1218808873 ns 44616 bytes=131.072k bytes_per_second=7.77016G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):17/manual_time 15712 ns 1216466421 ns 44616 bytes=131.072k bytes_per_second=7.76947G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):17/manual_time 15721 ns 1217455826 ns 44616 bytes=131.072k bytes_per_second=7.7647G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):17/manual_time 15671 ns 1219297338 ns 44616 bytes=131.072k bytes_per_second=7.78979G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):17/manual_time 15703 ns 1221365566 ns 44616 bytes=131.072k bytes_per_second=7.77354G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):17/manual_time_mean 15703 ns 1218678805 ns 5 bytes=131.072k bytes_per_second=7.77353G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):17/manual_time_median 15710 ns 1218808873 ns 5 bytes=131.072k bytes_per_second=7.77016G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):17/manual_time_stddev 19.4 ns 1871397 ns 5 bytes=0 bytes_per_second=9.85354M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):17/manual_time_cv 0.12 % 0.15 % 5 bytes=0.00% bytes_per_second=0.12% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):18/manual_time 21603 ns 1029840569 ns 32445 bytes=262.144k bytes_per_second=11.301G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):18/manual_time 21528 ns 1029131779 ns 32445 bytes=262.144k bytes_per_second=11.3409G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):18/manual_time 21684 ns 1036438766 ns 32445 bytes=262.144k bytes_per_second=11.2592G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):18/manual_time 21551 ns 1029819638 ns 32445 bytes=262.144k bytes_per_second=11.3287G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):18/manual_time 21635 ns 1031305537 ns 32445 bytes=262.144k bytes_per_second=11.2845G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):18/manual_time_mean 21600 ns 1031307258 ns 5 bytes=262.144k bytes_per_second=11.3029G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):18/manual_time_median 21603 ns 1029840569 ns 5 bytes=262.144k bytes_per_second=11.301G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):18/manual_time_stddev 63.1 ns 2976125 ns 5 bytes=0 bytes_per_second=33.8193M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):18/manual_time_cv 0.29 % 0.29 % 5 bytes=0.00% bytes_per_second=0.29% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):19/manual_time 23463 ns 978703369 ns 29854 bytes=524.288k bytes_per_second=20.811G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):19/manual_time 23490 ns 976736691 ns 29854 bytes=524.288k bytes_per_second=20.7865G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):19/manual_time 23453 ns 977301762 ns 29854 bytes=524.288k bytes_per_second=20.8198G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):19/manual_time 23429 ns 977774656 ns 29854 bytes=524.288k bytes_per_second=20.8406G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):19/manual_time 23449 ns 978656070 ns 29854 bytes=524.288k bytes_per_second=20.823G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):19/manual_time_mean 23457 ns 977834510 ns 5 bytes=524.288k bytes_per_second=20.8162G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):19/manual_time_median 23453 ns 977774656 ns 5 bytes=524.288k bytes_per_second=20.8198G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):19/manual_time_stddev 22.3 ns 854764 ns 5 bytes=0 bytes_per_second=20.2259M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):19/manual_time_cv 0.09 % 0.09 % 5 bytes=0.00% bytes_per_second=0.09% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):20/manual_time 33710 ns 788974724 ns 20797 bytes=1048.58k bytes_per_second=28.9693G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):20/manual_time 33627 ns 789161875 ns 20797 bytes=1048.58k bytes_per_second=29.041G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):20/manual_time 33710 ns 792489935 ns 20797 bytes=1048.58k bytes_per_second=28.9693G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):20/manual_time 33687 ns 789504389 ns 20797 bytes=1048.58k bytes_per_second=28.9891G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):20/manual_time 33689 ns 790054775 ns 20797 bytes=1048.58k bytes_per_second=28.9873G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):20/manual_time_mean 33685 ns 790037140 ns 5 bytes=1048.58k bytes_per_second=28.9912G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):20/manual_time_median 33689 ns 789504389 ns 5 bytes=1048.58k bytes_per_second=28.9873G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):20/manual_time_stddev 34.1 ns 1431359 ns 5 bytes=0 bytes_per_second=30.108M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):20/manual_time_cv 0.10 % 0.18 % 5 bytes=0.00% bytes_per_second=0.10% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):21/manual_time 54304 ns 624589626 ns 12882 bytes=2.09715M bytes_per_second=35.9662G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):21/manual_time 54307 ns 624716295 ns 12882 bytes=2.09715M bytes_per_second=35.9646G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):21/manual_time 54343 ns 624571175 ns 12882 bytes=2.09715M bytes_per_second=35.9405G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):21/manual_time 54331 ns 624148835 ns 12882 bytes=2.09715M bytes_per_second=35.9485G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):21/manual_time 54315 ns 624965457 ns 12882 bytes=2.09715M bytes_per_second=35.9591G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):21/manual_time_mean 54320 ns 624598278 ns 5 bytes=2.09715M bytes_per_second=35.9558G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):21/manual_time_median 54315 ns 624589626 ns 5 bytes=2.09715M bytes_per_second=35.9591G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):21/manual_time_stddev 16.6 ns 296461 ns 5 bytes=0 bytes_per_second=11.2739M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):21/manual_time_cv 0.03 % 0.05 % 5 bytes=0.00% bytes_per_second=0.03% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):22/manual_time 95563 ns 518080560 ns 7321 bytes=4.1943M bytes_per_second=40.876G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):22/manual_time 95590 ns 517812226 ns 7321 bytes=4.1943M bytes_per_second=40.8648G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):22/manual_time 95544 ns 517416663 ns 7321 bytes=4.1943M bytes_per_second=40.8844G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):22/manual_time 95581 ns 517889519 ns 7321 bytes=4.1943M bytes_per_second=40.8684G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):22/manual_time 95576 ns 517978621 ns 7321 bytes=4.1943M bytes_per_second=40.8706G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):22/manual_time_mean 95571 ns 517835518 ns 5 bytes=4.1943M bytes_per_second=40.8728G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):22/manual_time_median 95576 ns 517889519 ns 5 bytes=4.1943M bytes_per_second=40.8706G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):22/manual_time_stddev 17.8 ns 254667 ns 5 bytes=0 bytes_per_second=7.79787M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):22/manual_time_cv 0.02 % 0.05 % 5 bytes=0.00% bytes_per_second=0.02% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):23/manual_time 177927 ns 447531431 ns 3932 bytes=8.38861M bytes_per_second=43.9084G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):23/manual_time 177999 ns 447407841 ns 3932 bytes=8.38861M bytes_per_second=43.8908G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):23/manual_time 177956 ns 447624428 ns 3932 bytes=8.38861M bytes_per_second=43.9014G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):23/manual_time 177991 ns 447787465 ns 3932 bytes=8.38861M bytes_per_second=43.8928G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):23/manual_time 177960 ns 447682168 ns 3932 bytes=8.38861M bytes_per_second=43.9002G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):23/manual_time_mean 177967 ns 447606667 ns 5 bytes=8.38861M bytes_per_second=43.8987G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):23/manual_time_median 177960 ns 447624428 ns 5 bytes=8.38861M bytes_per_second=43.9002G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):23/manual_time_stddev 28.7 ns 144824 ns 5 bytes=0 bytes_per_second=7.25528M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):23/manual_time_cv 0.02 % 0.03 % 5 bytes=0.00% bytes_per_second=0.02% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):24/manual_time 342755 ns 413670395 ns 2042 bytes=16.7772M bytes_per_second=45.5865G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):24/manual_time 342690 ns 413648457 ns 2042 bytes=16.7772M bytes_per_second=45.5952G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):24/manual_time 342712 ns 413596503 ns 2042 bytes=16.7772M bytes_per_second=45.5922G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):24/manual_time 342628 ns 413584501 ns 2042 bytes=16.7772M bytes_per_second=45.6034G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):24/manual_time 342655 ns 413477349 ns 2042 bytes=16.7772M bytes_per_second=45.5998G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):24/manual_time_mean 342688 ns 413595441 ns 5 bytes=16.7772M bytes_per_second=45.5954G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):24/manual_time_median 342690 ns 413596503 ns 5 bytes=16.7772M bytes_per_second=45.5952G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):24/manual_time_stddev 49.4 ns 74992 ns 5 bytes=0 bytes_per_second=6.72426M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):24/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):25/manual_time 671747 ns 394984289 ns 1041 bytes=33.5544M bytes_per_second=46.5205G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):25/manual_time 671711 ns 394966433 ns 1041 bytes=33.5544M bytes_per_second=46.523G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):25/manual_time 671727 ns 395036772 ns 1041 bytes=33.5544M bytes_per_second=46.5219G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):25/manual_time 671774 ns 395118506 ns 1041 bytes=33.5544M bytes_per_second=46.5186G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):25/manual_time 671744 ns 395011534 ns 1041 bytes=33.5544M bytes_per_second=46.5207G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):25/manual_time_mean 671741 ns 395023507 ns 5 bytes=33.5544M bytes_per_second=46.5209G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):25/manual_time_median 671744 ns 395011534 ns 5 bytes=33.5544M bytes_per_second=46.5207G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):25/manual_time_stddev 23.8 ns 59455 ns 5 bytes=0 bytes_per_second=1.68447M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):25/manual_time_cv 0.00 % 0.02 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):26/manual_time 1330050 ns 387070045 ns 526 bytes=67.1089M bytes_per_second=46.9907G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):26/manual_time 1330434 ns 387179807 ns 526 bytes=67.1089M bytes_per_second=46.9772G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):26/manual_time 1330084 ns 387149251 ns 526 bytes=67.1089M bytes_per_second=46.9895G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):26/manual_time 1330057 ns 387043951 ns 526 bytes=67.1089M bytes_per_second=46.9905G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):26/manual_time 1330538 ns 387234233 ns 526 bytes=67.1089M bytes_per_second=46.9735G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):26/manual_time_mean 1330233 ns 387135458 ns 5 bytes=67.1089M bytes_per_second=46.9843G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):26/manual_time_median 1330084 ns 387149251 ns 5 bytes=67.1089M bytes_per_second=46.9895G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):26/manual_time_stddev 235 ns 78368 ns 5 bytes=0 bytes_per_second=8.48396M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):26/manual_time_cv 0.02 % 0.02 % 5 bytes=0.00% bytes_per_second=0.02% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):27/manual_time 2647334 ns 383845246 ns 264 bytes=134.218M bytes_per_second=47.2173G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):27/manual_time 2646872 ns 383775525 ns 264 bytes=134.218M bytes_per_second=47.2255G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):27/manual_time 2646952 ns 383805158 ns 264 bytes=134.218M bytes_per_second=47.2241G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):27/manual_time 2647357 ns 383842118 ns 264 bytes=134.218M bytes_per_second=47.2169G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):27/manual_time 2646788 ns 383743092 ns 264 bytes=134.218M bytes_per_second=47.2271G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):27/manual_time_mean 2647061 ns 383802228 ns 5 bytes=134.218M bytes_per_second=47.2222G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):27/manual_time_median 2646952 ns 383805158 ns 5 bytes=134.218M bytes_per_second=47.2241G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):27/manual_time_stddev 267 ns 43762 ns 5 bytes=0 bytes_per_second=4.86929M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):27/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):28/manual_time 5280251 ns 386054944 ns 132 bytes=268.435M bytes_per_second=47.3462G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):28/manual_time 5280172 ns 386047441 ns 132 bytes=268.435M bytes_per_second=47.3469G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):28/manual_time 5280615 ns 386098905 ns 132 bytes=268.435M bytes_per_second=47.343G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):28/manual_time 5280306 ns 386080064 ns 132 bytes=268.435M bytes_per_second=47.3457G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):28/manual_time 5280335 ns 386061715 ns 132 bytes=268.435M bytes_per_second=47.3455G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):28/manual_time_mean 5280336 ns 386068614 ns 5 bytes=268.435M bytes_per_second=47.3455G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):28/manual_time_median 5280306 ns 386061715 ns 5 bytes=268.435M bytes_per_second=47.3457G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):28/manual_time_stddev 168 ns 20805 ns 5 bytes=0 bytes_per_second=1.54042M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):28/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):29/manual_time 10546762 ns 392130225 ns 66 bytes=536.871M bytes_per_second=47.4079G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):29/manual_time 10546994 ns 392128553 ns 66 bytes=536.871M bytes_per_second=47.4069G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):29/manual_time 10545814 ns 392105019 ns 66 bytes=536.871M bytes_per_second=47.4122G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):29/manual_time 10546536 ns 392095310 ns 66 bytes=536.871M bytes_per_second=47.4089G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):29/manual_time 10546463 ns 392123925 ns 66 bytes=536.871M bytes_per_second=47.4093G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):29/manual_time_mean 10546514 ns 392116606 ns 5 bytes=536.871M bytes_per_second=47.409G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):29/manual_time_median 10546536 ns 392123925 ns 5 bytes=536.871M bytes_per_second=47.4089G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):29/manual_time_stddev 443 ns 15569 ns 5 bytes=0 bytes_per_second=2.0401M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):29/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):30/manual_time 21078032 ns 407824602 ns 33 bytes=1073.74M bytes_per_second=47.4428G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):30/manual_time 21077737 ns 407849767 ns 33 bytes=1073.74M bytes_per_second=47.4434G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):30/manual_time 21077843 ns 407880962 ns 33 bytes=1073.74M bytes_per_second=47.4432G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):30/manual_time 21078188 ns 407871491 ns 33 bytes=1073.74M bytes_per_second=47.4424G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):30/manual_time 21076670 ns 407823970 ns 33 bytes=1073.74M bytes_per_second=47.4458G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):30/manual_time_mean 21077694 ns 407850158 ns 5 bytes=1073.74M bytes_per_second=47.4435G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):30/manual_time_median 21077843 ns 407849767 ns 5 bytes=1073.74M bytes_per_second=47.4432G/s dst_id=6 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):30/manual_time_stddev 598 ns 26187 ns 5 bytes=0 bytes_per_second=1.37857M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/6/log2(N):30/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):8/manual_time 12261 ns 1199510436 ns 57864 bytes=256 bytes_per_second=19.9114M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):8/manual_time 12215 ns 1203779015 ns 57864 bytes=256 bytes_per_second=19.9869M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):8/manual_time 12057 ns 1204350248 ns 57864 bytes=256 bytes_per_second=20.2495M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):8/manual_time 12066 ns 1202547448 ns 57864 bytes=256 bytes_per_second=20.2338M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):8/manual_time 12271 ns 1200838165 ns 57864 bytes=256 bytes_per_second=19.8963M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):8/manual_time_mean 12174 ns 1202205062 ns 5 bytes=256 bytes_per_second=20.0556M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):8/manual_time_median 12215 ns 1202547448 ns 5 bytes=256 bytes_per_second=19.9869M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):8/manual_time_stddev 105 ns 2020260 ns 5 bytes=0 bytes_per_second=177.533k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):8/manual_time_cv 0.86 % 0.17 % 5 bytes=0.00% bytes_per_second=0.86% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):9/manual_time 12062 ns 1190937763 ns 57260 bytes=512 bytes_per_second=40.4801M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):9/manual_time 12090 ns 1190994137 ns 57260 bytes=512 bytes_per_second=40.3864M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):9/manual_time 12265 ns 1185990949 ns 57260 bytes=512 bytes_per_second=39.8106M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):9/manual_time 12226 ns 1191848758 ns 57260 bytes=512 bytes_per_second=39.9376M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):9/manual_time 12052 ns 1190507504 ns 57260 bytes=512 bytes_per_second=40.5132M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):9/manual_time_mean 12139 ns 1190055822 ns 5 bytes=512 bytes_per_second=40.2256M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):9/manual_time_median 12090 ns 1190937763 ns 5 bytes=512 bytes_per_second=40.3864M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):9/manual_time_stddev 99.1 ns 2323794 ns 5 bytes=0 bytes_per_second=335.146k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):9/manual_time_cv 0.82 % 0.20 % 5 bytes=0.00% bytes_per_second=0.81% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):10/manual_time 12363 ns 1196340834 ns 57542 bytes=1024 bytes_per_second=78.9907M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):10/manual_time 12319 ns 1201649742 ns 57542 bytes=1024 bytes_per_second=79.2703M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):10/manual_time 12125 ns 1200559071 ns 57542 bytes=1024 bytes_per_second=80.5415M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):10/manual_time 12174 ns 1197703164 ns 57542 bytes=1024 bytes_per_second=80.2154M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):10/manual_time 12303 ns 1194964550 ns 57542 bytes=1024 bytes_per_second=79.3772M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):10/manual_time_mean 12257 ns 1198243472 ns 5 bytes=1024 bytes_per_second=79.679M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):10/manual_time_median 12303 ns 1197703164 ns 5 bytes=1024 bytes_per_second=79.3772M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):10/manual_time_stddev 102 ns 2811937 ns 5 bytes=0 bytes_per_second=679.904k/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):10/manual_time_cv 0.83 % 0.23 % 5 bytes=0.00% bytes_per_second=0.83% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):11/manual_time 12211 ns 1180572537 ns 56407 bytes=2.048k bytes_per_second=159.947M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):11/manual_time 12265 ns 1179396220 ns 56407 bytes=2.048k bytes_per_second=159.242M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):11/manual_time 12437 ns 1175746811 ns 56407 bytes=2.048k bytes_per_second=157.041M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):11/manual_time 12415 ns 1179313011 ns 56407 bytes=2.048k bytes_per_second=157.319M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):11/manual_time 12188 ns 1178392523 ns 56407 bytes=2.048k bytes_per_second=160.25M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):11/manual_time_mean 12303 ns 1178684221 ns 5 bytes=2.048k bytes_per_second=158.76M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):11/manual_time_median 12265 ns 1179313011 ns 5 bytes=2.048k bytes_per_second=159.242M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):11/manual_time_stddev 116 ns 1815318 ns 5 bytes=0 bytes_per_second=1.49091M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):11/manual_time_cv 0.94 % 0.15 % 5 bytes=0.00% bytes_per_second=0.94% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):12/manual_time 12608 ns 1181963241 ns 56390 bytes=4.096k bytes_per_second=309.818M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):12/manual_time 12588 ns 1189770423 ns 56390 bytes=4.096k bytes_per_second=310.307M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):12/manual_time 12387 ns 1184828809 ns 56390 bytes=4.096k bytes_per_second=315.358M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):12/manual_time 12424 ns 1181451425 ns 56390 bytes=4.096k bytes_per_second=314.416M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):12/manual_time 12584 ns 1182267410 ns 56390 bytes=4.096k bytes_per_second=310.414M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):12/manual_time_mean 12518 ns 1184056262 ns 5 bytes=4.096k bytes_per_second=312.063M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):12/manual_time_median 12584 ns 1182267410 ns 5 bytes=4.096k bytes_per_second=310.414M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):12/manual_time_stddev 104 ns 3450158 ns 5 bytes=0 bytes_per_second=2.60961M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):12/manual_time_cv 0.83 % 0.29 % 5 bytes=0.00% bytes_per_second=0.84% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):13/manual_time 12527 ns 1161600505 ns 55106 bytes=8.192k bytes_per_second=623.637M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):13/manual_time 12535 ns 1159757421 ns 55106 bytes=8.192k bytes_per_second=623.237M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):13/manual_time 12745 ns 1161179930 ns 55106 bytes=8.192k bytes_per_second=612.995M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):13/manual_time 12686 ns 1159908271 ns 55106 bytes=8.192k bytes_per_second=615.815M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):13/manual_time 12539 ns 1161099519 ns 55106 bytes=8.192k bytes_per_second=623.039M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):13/manual_time_mean 12607 ns 1160709129 ns 5 bytes=8.192k bytes_per_second=619.745M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):13/manual_time_median 12539 ns 1161099519 ns 5 bytes=8.192k bytes_per_second=623.039M/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):13/manual_time_stddev 102 ns 823973 ns 5 bytes=0 bytes_per_second=4.97987M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):13/manual_time_cv 0.81 % 0.07 % 5 bytes=0.00% bytes_per_second=0.80% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):14/manual_time 13010 ns 1170971497 ns 54671 bytes=16.384k bytes_per_second=1.17284G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):14/manual_time 12968 ns 1175406467 ns 54671 bytes=16.384k bytes_per_second=1.17663G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):14/manual_time 12783 ns 1172712825 ns 54671 bytes=16.384k bytes_per_second=1.19366G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):14/manual_time 12828 ns 1170245385 ns 54671 bytes=16.384k bytes_per_second=1.18949G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):14/manual_time 12979 ns 1168461781 ns 54671 bytes=16.384k bytes_per_second=1.17567G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):14/manual_time_mean 12914 ns 1171559591 ns 5 bytes=16.384k bytes_per_second=1.18166G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):14/manual_time_median 12968 ns 1170971497 ns 5 bytes=16.384k bytes_per_second=1.17663G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):14/manual_time_stddev 101 ns 2636182 ns 5 bytes=0 bytes_per_second=9.498M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):14/manual_time_cv 0.78 % 0.23 % 5 bytes=0.00% bytes_per_second=0.78% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):15/manual_time 13053 ns 1160415686 ns 52822 bytes=32.768k bytes_per_second=2.33803G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):15/manual_time 13116 ns 1159612879 ns 52822 bytes=32.768k bytes_per_second=2.32668G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):15/manual_time 13265 ns 1156020197 ns 52822 bytes=32.768k bytes_per_second=2.30063G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):15/manual_time 13265 ns 1159800201 ns 52822 bytes=32.768k bytes_per_second=2.30069G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):15/manual_time 13056 ns 1159679121 ns 52822 bytes=32.768k bytes_per_second=2.33737G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):15/manual_time_mean 13151 ns 1159105617 ns 5 bytes=32.768k bytes_per_second=2.32068G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):15/manual_time_median 13116 ns 1159679121 ns 5 bytes=32.768k bytes_per_second=2.32668G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):15/manual_time_stddev 107 ns 1753907 ns 5 bytes=0 bytes_per_second=19.2736M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):15/manual_time_cv 0.81 % 0.15 % 5 bytes=0.00% bytes_per_second=0.81% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):16/manual_time 13850 ns 1172991387 ns 51275 bytes=65.536k bytes_per_second=4.40679G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):16/manual_time 13828 ns 1178328935 ns 51275 bytes=65.536k bytes_per_second=4.41379G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):16/manual_time 13633 ns 1175380440 ns 51275 bytes=65.536k bytes_per_second=4.47705G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):16/manual_time 13647 ns 1172164025 ns 51275 bytes=65.536k bytes_per_second=4.47244G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):16/manual_time 13844 ns 1174455604 ns 51275 bytes=65.536k bytes_per_second=4.40866G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):16/manual_time_mean 13761 ns 1174664078 ns 5 bytes=65.536k bytes_per_second=4.43574G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):16/manual_time_median 13828 ns 1174455604 ns 5 bytes=65.536k bytes_per_second=4.41379G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):16/manual_time_stddev 111 ns 2399791 ns 5 bytes=0 bytes_per_second=36.5877M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):16/manual_time_cv 0.80 % 0.20 % 5 bytes=0.00% bytes_per_second=0.81% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):17/manual_time 15036 ns 1148471363 ns 45967 bytes=131.072k bytes_per_second=8.1184G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):17/manual_time 15094 ns 1148394486 ns 45967 bytes=131.072k bytes_per_second=8.08715G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):17/manual_time 15254 ns 1145996338 ns 45967 bytes=131.072k bytes_per_second=8.00243G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):17/manual_time 15261 ns 1152271606 ns 45967 bytes=131.072k bytes_per_second=7.99869G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):17/manual_time 15045 ns 1149758634 ns 45967 bytes=131.072k bytes_per_second=8.11381G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):17/manual_time_mean 15138 ns 1148978485 ns 5 bytes=131.072k bytes_per_second=8.0641G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):17/manual_time_median 15094 ns 1148471363 ns 5 bytes=131.072k bytes_per_second=8.08715G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):17/manual_time_stddev 111 ns 2288269 ns 5 bytes=0 bytes_per_second=60.652M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):17/manual_time_cv 0.74 % 0.20 % 5 bytes=0.00% bytes_per_second=0.73% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):18/manual_time 19416 ns 1033799617 ns 36242 bytes=262.144k bytes_per_second=12.5742G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):18/manual_time 19390 ns 1037715254 ns 36242 bytes=262.144k bytes_per_second=12.5911G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):18/manual_time 19171 ns 1036098523 ns 36242 bytes=262.144k bytes_per_second=12.735G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):18/manual_time 19305 ns 1036772898 ns 36242 bytes=262.144k bytes_per_second=12.6467G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):18/manual_time 19414 ns 1034430814 ns 36242 bytes=262.144k bytes_per_second=12.5754G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):18/manual_time_mean 19339 ns 1035763421 ns 5 bytes=262.144k bytes_per_second=12.6245G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):18/manual_time_median 19390 ns 1036098523 ns 5 bytes=262.144k bytes_per_second=12.5911G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):18/manual_time_stddev 104 ns 1625835 ns 5 bytes=0 bytes_per_second=70.1158M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):18/manual_time_cv 0.54 % 0.16 % 5 bytes=0.00% bytes_per_second=0.54% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):19/manual_time 21678 ns 946376480 ns 31947 bytes=524.288k bytes_per_second=22.5238G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):19/manual_time 21780 ns 946317647 ns 31947 bytes=524.288k bytes_per_second=22.4185G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):19/manual_time 21937 ns 944489779 ns 31947 bytes=524.288k bytes_per_second=22.2587G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):19/manual_time 21910 ns 946078682 ns 31947 bytes=524.288k bytes_per_second=22.2857G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):19/manual_time 21692 ns 945679237 ns 31947 bytes=524.288k bytes_per_second=22.5101G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):19/manual_time_mean 21799 ns 945788365 ns 5 bytes=524.288k bytes_per_second=22.3993G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):19/manual_time_median 21780 ns 946078682 ns 5 bytes=524.288k bytes_per_second=22.4185G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):19/manual_time_stddev 120 ns 775973 ns 5 bytes=0 bytes_per_second=126.241M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):19/manual_time_cv 0.55 % 0.08 % 5 bytes=0.00% bytes_per_second=0.55% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):20/manual_time 32196 ns 766341637 ns 21884 bytes=1048.58k bytes_per_second=30.3317G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):20/manual_time 32122 ns 767040653 ns 21884 bytes=1048.58k bytes_per_second=30.4019G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):20/manual_time 31955 ns 766374895 ns 21884 bytes=1048.58k bytes_per_second=30.5605G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):20/manual_time 31966 ns 764939166 ns 21884 bytes=1048.58k bytes_per_second=30.55G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):20/manual_time 32222 ns 765782914 ns 21884 bytes=1048.58k bytes_per_second=30.3072G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):20/manual_time_mean 32092 ns 766095853 ns 5 bytes=1048.58k bytes_per_second=30.4303G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):20/manual_time_median 32122 ns 766341637 ns 5 bytes=1048.58k bytes_per_second=30.4019G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):20/manual_time_stddev 126 ns 785299 ns 5 bytes=0 bytes_per_second=122.204M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):20/manual_time_cv 0.39 % 0.10 % 5 bytes=0.00% bytes_per_second=0.39% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):21/manual_time 52835 ns 607917667 ns 13225 bytes=2.09715M bytes_per_second=36.9662G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):21/manual_time 52617 ns 608405360 ns 13225 bytes=2.09715M bytes_per_second=37.1193G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):21/manual_time 52720 ns 607180396 ns 13225 bytes=2.09715M bytes_per_second=37.0472G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):21/manual_time 52855 ns 607525700 ns 13225 bytes=2.09715M bytes_per_second=36.9526G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):21/manual_time 52820 ns 607765286 ns 13225 bytes=2.09715M bytes_per_second=36.9773G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):21/manual_time_mean 52769 ns 607758882 ns 5 bytes=2.09715M bytes_per_second=37.0125G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):21/manual_time_median 52820 ns 607765286 ns 5 bytes=2.09715M bytes_per_second=36.9773G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):21/manual_time_stddev 99.6 ns 456127 ns 5 bytes=0 bytes_per_second=71.6592M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):21/manual_time_cv 0.19 % 0.08 % 5 bytes=0.00% bytes_per_second=0.19% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):22/manual_time 93757 ns 503022974 ns 7450 bytes=4.1943M bytes_per_second=41.6637G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):22/manual_time 93773 ns 502490227 ns 7450 bytes=4.1943M bytes_per_second=41.6566G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):22/manual_time 94009 ns 502472991 ns 7450 bytes=4.1943M bytes_per_second=41.552G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):22/manual_time 93914 ns 502693606 ns 7450 bytes=4.1943M bytes_per_second=41.594G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):22/manual_time 93730 ns 503127044 ns 7450 bytes=4.1943M bytes_per_second=41.6755G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):22/manual_time_mean 93836 ns 502761368 ns 5 bytes=4.1943M bytes_per_second=41.6283G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):22/manual_time_median 93773 ns 502693606 ns 5 bytes=4.1943M bytes_per_second=41.6566G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):22/manual_time_stddev 120 ns 301424 ns 5 bytes=0 bytes_per_second=54.3632M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):22/manual_time_cv 0.13 % 0.06 % 5 bytes=0.00% bytes_per_second=0.13% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):23/manual_time 176542 ns 438880987 ns 3965 bytes=8.38861M bytes_per_second=44.253G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):23/manual_time 176753 ns 439192348 ns 3965 bytes=8.38861M bytes_per_second=44.2G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):23/manual_time 176671 ns 439124698 ns 3965 bytes=8.38861M bytes_per_second=44.2206G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):23/manual_time 176504 ns 439268651 ns 3965 bytes=8.38861M bytes_per_second=44.2625G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):23/manual_time 176527 ns 438871660 ns 3965 bytes=8.38861M bytes_per_second=44.2566G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):23/manual_time_mean 176599 ns 439067669 ns 5 bytes=8.38861M bytes_per_second=44.2385G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):23/manual_time_median 176542 ns 439124698 ns 5 bytes=8.38861M bytes_per_second=44.253G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):23/manual_time_stddev 108 ns 181976 ns 5 bytes=0 bytes_per_second=27.6561M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):23/manual_time_cv 0.06 % 0.04 % 5 bytes=0.00% bytes_per_second=0.06% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):24/manual_time 341325 ns 408900297 ns 2051 bytes=16.7772M bytes_per_second=45.7775G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):24/manual_time 341342 ns 409080262 ns 2051 bytes=16.7772M bytes_per_second=45.7751G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):24/manual_time 341091 ns 409031928 ns 2051 bytes=16.7772M bytes_per_second=45.8089G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):24/manual_time 341126 ns 408814361 ns 2051 bytes=16.7772M bytes_per_second=45.8043G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):24/manual_time 341343 ns 408903470 ns 2051 bytes=16.7772M bytes_per_second=45.775G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):24/manual_time_mean 341245 ns 408946064 ns 5 bytes=16.7772M bytes_per_second=45.7882G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):24/manual_time_median 341325 ns 408903470 ns 5 bytes=16.7772M bytes_per_second=45.7775G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):24/manual_time_stddev 126 ns 107977 ns 5 bytes=0 bytes_per_second=17.3257M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):24/manual_time_cv 0.04 % 0.03 % 5 bytes=0.00% bytes_per_second=0.04% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):25/manual_time 671080 ns 392864339 ns 1042 bytes=33.5544M bytes_per_second=46.5667G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):25/manual_time 671026 ns 392930813 ns 1042 bytes=33.5544M bytes_per_second=46.5705G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):25/manual_time 670899 ns 393005796 ns 1042 bytes=33.5544M bytes_per_second=46.5793G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):25/manual_time 670880 ns 392877744 ns 1042 bytes=33.5544M bytes_per_second=46.5806G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):25/manual_time 671086 ns 392896687 ns 1042 bytes=33.5544M bytes_per_second=46.5663G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):25/manual_time_mean 670994 ns 392915076 ns 5 bytes=33.5544M bytes_per_second=46.5727G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):25/manual_time_median 671026 ns 392896687 ns 5 bytes=33.5544M bytes_per_second=46.5705G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):25/manual_time_stddev 98.7 ns 56533 ns 5 bytes=0 bytes_per_second=7.01281M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):25/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):26/manual_time 1330383 ns 386149016 ns 526 bytes=67.1089M bytes_per_second=46.979G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):26/manual_time 1330769 ns 386261204 ns 526 bytes=67.1089M bytes_per_second=46.9653G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):26/manual_time 1330097 ns 386146871 ns 526 bytes=67.1089M bytes_per_second=46.989G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):26/manual_time 1330184 ns 386123603 ns 526 bytes=67.1089M bytes_per_second=46.986G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):26/manual_time 1330855 ns 386258568 ns 526 bytes=67.1089M bytes_per_second=46.9623G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):26/manual_time_mean 1330458 ns 386187852 ns 5 bytes=67.1089M bytes_per_second=46.9763G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):26/manual_time_median 1330383 ns 386149016 ns 5 bytes=67.1089M bytes_per_second=46.979G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):26/manual_time_stddev 341 ns 66515 ns 5 bytes=0 bytes_per_second=12.3313M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):26/manual_time_cv 0.03 % 0.02 % 5 bytes=0.00% bytes_per_second=0.03% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):27/manual_time 2648988 ns 383572986 ns 264 bytes=134.218M bytes_per_second=47.1878G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):27/manual_time 2648682 ns 383559021 ns 264 bytes=134.218M bytes_per_second=47.1933G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):27/manual_time 2648504 ns 383581857 ns 264 bytes=134.218M bytes_per_second=47.1965G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):27/manual_time 2648836 ns 383598887 ns 264 bytes=134.218M bytes_per_second=47.1905G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):27/manual_time 2648822 ns 383570960 ns 264 bytes=134.218M bytes_per_second=47.1908G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):27/manual_time_mean 2648767 ns 383576742 ns 5 bytes=134.218M bytes_per_second=47.1918G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):27/manual_time_median 2648822 ns 383572986 ns 5 bytes=134.218M bytes_per_second=47.1908G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):27/manual_time_stddev 182 ns 14817 ns 5 bytes=0 bytes_per_second=3.32632M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):27/manual_time_cv 0.01 % 0.00 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):28/manual_time 5285244 ns 386191027 ns 132 bytes=268.435M bytes_per_second=47.3015G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):28/manual_time 5285575 ns 386219797 ns 132 bytes=268.435M bytes_per_second=47.2985G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):28/manual_time 5285774 ns 386222295 ns 132 bytes=268.435M bytes_per_second=47.2968G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):28/manual_time 5285320 ns 386172217 ns 132 bytes=268.435M bytes_per_second=47.3008G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):28/manual_time 5285685 ns 386211049 ns 132 bytes=268.435M bytes_per_second=47.2976G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):28/manual_time_mean 5285520 ns 386203277 ns 5 bytes=268.435M bytes_per_second=47.299G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):28/manual_time_median 5285575 ns 386211049 ns 5 bytes=268.435M bytes_per_second=47.2985G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):28/manual_time_stddev 230 ns 21271 ns 5 bytes=0 bytes_per_second=2.10466M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):28/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):29/manual_time 10557830 ns 392395185 ns 66 bytes=536.871M bytes_per_second=47.3582G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):29/manual_time 10558502 ns 392440227 ns 66 bytes=536.871M bytes_per_second=47.3552G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):29/manual_time 10558858 ns 392444720 ns 66 bytes=536.871M bytes_per_second=47.3536G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):29/manual_time 10559416 ns 392448047 ns 66 bytes=536.871M bytes_per_second=47.3511G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):29/manual_time 10558499 ns 392448925 ns 66 bytes=536.871M bytes_per_second=47.3552G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):29/manual_time_mean 10558621 ns 392435421 ns 5 bytes=536.871M bytes_per_second=47.3547G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):29/manual_time_median 10558502 ns 392444720 ns 5 bytes=536.871M bytes_per_second=47.3552G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):29/manual_time_stddev 579 ns 22750 ns 5 bytes=0 bytes_per_second=2.66038M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):29/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):30/manual_time 21103297 ns 408207248 ns 33 bytes=1073.74M bytes_per_second=47.386G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):30/manual_time 21099462 ns 408109975 ns 33 bytes=1073.74M bytes_per_second=47.3946G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):30/manual_time 21103118 ns 408220067 ns 33 bytes=1073.74M bytes_per_second=47.3864G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):30/manual_time 21102395 ns 408214742 ns 33 bytes=1073.74M bytes_per_second=47.388G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):30/manual_time 21101765 ns 408205268 ns 33 bytes=1073.74M bytes_per_second=47.3894G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):30/manual_time_mean 21102007 ns 408191460 ns 5 bytes=1073.74M bytes_per_second=47.3889G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):30/manual_time_median 21102395 ns 408207248 ns 5 bytes=1073.74M bytes_per_second=47.388G/s dst_id=7 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):30/manual_time_stddev 1548 ns 45935 ns 5 bytes=0 bytes_per_second=3.56M/s dst_id=0 src_id=0 +Comm_hipMemcpyAsync_GPUToGPU/0/7/log2(N):30/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% dst_id=0.00% src_id=-nan% +[2023-10-09 18:06:11.219] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 18:06:11.219] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Mon 09 Oct 2023 06:06:11 PM EDT diff --git a/results/r11-1465787.out b/results/r11-1465787.out new file mode 100644 index 0000000..97fa5d3 --- /dev/null +++ b/results/r11-1465787.out @@ -0,0 +1,162 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 08:21:14 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 20:21:15.373] [scope] [info] recorded system CPU turbo state +[2023-10-09 20:21:15.373] [scope] [info] recorded CPU goveror +[2023-10-09 20:21:15.373] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 20:21:15.373] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T20:21:17-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1796.12 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.45, 0.25, 0.20 +----------------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +----------------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):12/manual_time 3260 ns 282479 ns 214287 bytes=4.096k bytes_per_second=1.17016G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):12/manual_time 3267 ns 283941 ns 214287 bytes=4.096k bytes_per_second=1.16773G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):12/manual_time 3288 ns 284167 ns 214287 bytes=4.096k bytes_per_second=1.16006G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):12/manual_time 3290 ns 284445 ns 214287 bytes=4.096k bytes_per_second=1.15954G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):12/manual_time 3281 ns 283840 ns 214287 bytes=4.096k bytes_per_second=1.16283G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):12/manual_time_mean 3277 ns 283775 ns 5 bytes=4.096k bytes_per_second=1.16406G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):12/manual_time_median 3281 ns 283941 ns 5 bytes=4.096k bytes_per_second=1.16283G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):12/manual_time_stddev 13.2 ns 760 ns 5 bytes=0 bytes_per_second=4.81904M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):12/manual_time_cv 0.40 % 0.27 % 5 bytes=0.00% bytes_per_second=0.40% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):13/manual_time 3340 ns 301994 ns 207615 bytes=8.192k bytes_per_second=2.28409G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):13/manual_time 3339 ns 301095 ns 207615 bytes=8.192k bytes_per_second=2.28527G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):13/manual_time 3322 ns 302489 ns 207615 bytes=8.192k bytes_per_second=2.29666G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):13/manual_time 3314 ns 301530 ns 207615 bytes=8.192k bytes_per_second=2.30205G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):13/manual_time 3329 ns 303923 ns 207615 bytes=8.192k bytes_per_second=2.29175G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):13/manual_time_mean 3329 ns 302206 ns 5 bytes=8.192k bytes_per_second=2.29196G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):13/manual_time_median 3329 ns 301994 ns 5 bytes=8.192k bytes_per_second=2.29175G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):13/manual_time_stddev 11.0 ns 1091 ns 5 bytes=0 bytes_per_second=7.77451M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):13/manual_time_cv 0.33 % 0.36 % 5 bytes=0.00% bytes_per_second=0.33% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):14/manual_time 3533 ns 339335 ns 196248 bytes=16.384k bytes_per_second=4.3195G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):14/manual_time 3521 ns 338896 ns 196248 bytes=16.384k bytes_per_second=4.33341G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):14/manual_time 3549 ns 339123 ns 196248 bytes=16.384k bytes_per_second=4.2996G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):14/manual_time 3550 ns 339158 ns 196248 bytes=16.384k bytes_per_second=4.29885G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):14/manual_time 3519 ns 339049 ns 196248 bytes=16.384k bytes_per_second=4.33606G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):14/manual_time_mean 3534 ns 339112 ns 5 bytes=16.384k bytes_per_second=4.31748G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):14/manual_time_median 3533 ns 339123 ns 5 bytes=16.384k bytes_per_second=4.3195G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):14/manual_time_stddev 14.6 ns 160 ns 5 bytes=0 bytes_per_second=18.2484M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):14/manual_time_cv 0.41 % 0.05 % 5 bytes=0.00% bytes_per_second=0.41% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):15/manual_time 4189 ns 414996 ns 167373 bytes=32.768k bytes_per_second=7.28488G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):15/manual_time 4162 ns 411905 ns 167373 bytes=32.768k bytes_per_second=7.33192G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):15/manual_time 4168 ns 411558 ns 167373 bytes=32.768k bytes_per_second=7.32234G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):15/manual_time 4163 ns 407515 ns 167373 bytes=32.768k bytes_per_second=7.33049G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):15/manual_time 4172 ns 416086 ns 167373 bytes=32.768k bytes_per_second=7.31495G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):15/manual_time_mean 4171 ns 412412 ns 5 bytes=32.768k bytes_per_second=7.31692G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):15/manual_time_median 4168 ns 411905 ns 5 bytes=32.768k bytes_per_second=7.32234G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):15/manual_time_stddev 11.0 ns 3359 ns 5 bytes=0 bytes_per_second=19.6254M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):15/manual_time_cv 0.26 % 0.81 % 5 bytes=0.00% bytes_per_second=0.26% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):16/manual_time 5245 ns 564918 ns 133552 bytes=65.536k bytes_per_second=11.6376G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):16/manual_time 5230 ns 564787 ns 133552 bytes=65.536k bytes_per_second=11.6703G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):16/manual_time 5256 ns 556498 ns 133552 bytes=65.536k bytes_per_second=11.6122G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):16/manual_time 5211 ns 543584 ns 133552 bytes=65.536k bytes_per_second=11.7136G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):16/manual_time 5169 ns 565790 ns 133552 bytes=65.536k bytes_per_second=11.8082G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):16/manual_time_mean 5222 ns 559115 ns 5 bytes=65.536k bytes_per_second=11.6884G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):16/manual_time_median 5230 ns 564787 ns 5 bytes=65.536k bytes_per_second=11.6703G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):16/manual_time_stddev 34.3 ns 9466 ns 5 bytes=0 bytes_per_second=78.8469M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):16/manual_time_cv 0.66 % 1.69 % 5 bytes=0.00% bytes_per_second=0.66% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):17/manual_time 7310 ns 859930 ns 96624 bytes=131.072k bytes_per_second=16.7G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):17/manual_time 7276 ns 859409 ns 96624 bytes=131.072k bytes_per_second=16.778G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):17/manual_time 7239 ns 858225 ns 96624 bytes=131.072k bytes_per_second=16.8629G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):17/manual_time 7271 ns 859658 ns 96624 bytes=131.072k bytes_per_second=16.7879G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):17/manual_time 7293 ns 860399 ns 96624 bytes=131.072k bytes_per_second=16.7369G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):17/manual_time_mean 7278 ns 859524 ns 5 bytes=131.072k bytes_per_second=16.7731G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):17/manual_time_median 7276 ns 859658 ns 5 bytes=131.072k bytes_per_second=16.778G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):17/manual_time_stddev 26.5 ns 814 ns 5 bytes=0 bytes_per_second=62.6408M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):17/manual_time_cv 0.36 % 0.09 % 5 bytes=0.00% bytes_per_second=0.36% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):18/manual_time 11486 ns 1446969 ns 60973 bytes=262.144k bytes_per_second=21.2553G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):18/manual_time 11484 ns 1446779 ns 60973 bytes=262.144k bytes_per_second=21.2584G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):18/manual_time 11490 ns 1449109 ns 60973 bytes=262.144k bytes_per_second=21.2486G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):18/manual_time 11548 ns 1445269 ns 60973 bytes=262.144k bytes_per_second=21.1412G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):18/manual_time 11563 ns 1444931 ns 60973 bytes=262.144k bytes_per_second=21.1137G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):18/manual_time_mean 11514 ns 1446612 ns 5 bytes=262.144k bytes_per_second=21.2034G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):18/manual_time_median 11490 ns 1446779 ns 5 bytes=262.144k bytes_per_second=21.2486G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):18/manual_time_stddev 38.1 ns 1660 ns 5 bytes=0 bytes_per_second=71.8239M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):18/manual_time_cv 0.33 % 0.11 % 5 bytes=0.00% bytes_per_second=0.33% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):19/manual_time 19045 ns 2622700 ns 36722 bytes=524.288k bytes_per_second=25.6383G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):19/manual_time 19056 ns 2621065 ns 36722 bytes=524.288k bytes_per_second=25.624G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):19/manual_time 19000 ns 2622783 ns 36722 bytes=524.288k bytes_per_second=25.6984G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):19/manual_time 19060 ns 2622744 ns 36722 bytes=524.288k bytes_per_second=25.6183G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):19/manual_time 19063 ns 2623048 ns 36722 bytes=524.288k bytes_per_second=25.6142G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):19/manual_time_mean 19045 ns 2622468 ns 5 bytes=524.288k bytes_per_second=25.6387G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):19/manual_time_median 19056 ns 2622744 ns 5 bytes=524.288k bytes_per_second=25.624G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):19/manual_time_stddev 25.7 ns 796 ns 5 bytes=0 bytes_per_second=35.4623M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):19/manual_time_cv 0.13 % 0.03 % 5 bytes=0.00% bytes_per_second=0.14% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):20/manual_time 33800 ns 4967549 ns 20751 bytes=1048.58k bytes_per_second=28.8927G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):20/manual_time 33681 ns 4970475 ns 20751 bytes=1048.58k bytes_per_second=28.994G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):20/manual_time 33712 ns 4967940 ns 20751 bytes=1048.58k bytes_per_second=28.9681G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):20/manual_time 33821 ns 4972069 ns 20751 bytes=1048.58k bytes_per_second=28.8742G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):20/manual_time 33841 ns 4968986 ns 20751 bytes=1048.58k bytes_per_second=28.8571G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):20/manual_time_mean 33771 ns 4969404 ns 5 bytes=1048.58k bytes_per_second=28.9172G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):20/manual_time_median 33800 ns 4968986 ns 5 bytes=1048.58k bytes_per_second=28.8927G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):20/manual_time_stddev 70.4 ns 1871 ns 5 bytes=0 bytes_per_second=61.758M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):20/manual_time_cv 0.21 % 0.04 % 5 bytes=0.00% bytes_per_second=0.21% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):21/manual_time 63539 ns 9895292 ns 11000 bytes=2.09715M bytes_per_second=30.7391G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):21/manual_time 63433 ns 9896801 ns 11000 bytes=2.09715M bytes_per_second=30.7902G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):21/manual_time 63345 ns 9620552 ns 11000 bytes=2.09715M bytes_per_second=30.8329G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):21/manual_time 63294 ns 9608109 ns 11000 bytes=2.09715M bytes_per_second=30.8581G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):21/manual_time 63323 ns 9592106 ns 11000 bytes=2.09715M bytes_per_second=30.844G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):21/manual_time_mean 63387 ns 9722572 ns 5 bytes=2.09715M bytes_per_second=30.8129G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):21/manual_time_median 63345 ns 9620552 ns 5 bytes=2.09715M bytes_per_second=30.8329G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):21/manual_time_stddev 99.7 ns 158681 ns 5 bytes=0 bytes_per_second=49.5835M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):21/manual_time_cv 0.16 % 1.63 % 5 bytes=0.00% bytes_per_second=0.16% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):22/manual_time 122862 ns 19558165 ns 5699 bytes=4.1943M bytes_per_second=31.7937G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):22/manual_time 123017 ns 19562464 ns 5699 bytes=4.1943M bytes_per_second=31.7538G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):22/manual_time 123198 ns 19567680 ns 5699 bytes=4.1943M bytes_per_second=31.7071G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):22/manual_time 123179 ns 17564758 ns 5699 bytes=4.1943M bytes_per_second=31.7121G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):22/manual_time 122946 ns 17900312 ns 5699 bytes=4.1943M bytes_per_second=31.772G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):22/manual_time_mean 123040 ns 18830676 ns 5 bytes=4.1943M bytes_per_second=31.7477G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):22/manual_time_median 123017 ns 19558165 ns 5 bytes=4.1943M bytes_per_second=31.7538G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):22/manual_time_stddev 146 ns 1009462 ns 5 bytes=0 bytes_per_second=38.513M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):22/manual_time_cv 0.12 % 5.36 % 5 bytes=0.00% bytes_per_second=0.12% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):23/manual_time 241222 ns 38492434 ns 2904 bytes=8.38861M bytes_per_second=32.3872G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):23/manual_time 242200 ns 38487878 ns 2904 bytes=8.38861M bytes_per_second=32.2565G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):23/manual_time 242371 ns 38493388 ns 2904 bytes=8.38861M bytes_per_second=32.2337G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):23/manual_time 241792 ns 38481145 ns 2904 bytes=8.38861M bytes_per_second=32.3109G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):23/manual_time 241282 ns 38484196 ns 2904 bytes=8.38861M bytes_per_second=32.3791G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):23/manual_time_mean 241773 ns 38487808 ns 5 bytes=8.38861M bytes_per_second=32.3135G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):23/manual_time_median 241792 ns 38487878 ns 5 bytes=8.38861M bytes_per_second=32.3109G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):23/manual_time_stddev 521 ns 5244 ns 5 bytes=0 bytes_per_second=71.2447M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):23/manual_time_cv 0.22 % 0.01 % 5 bytes=0.00% bytes_per_second=0.22% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):24/manual_time 604773 ns 76611305 ns 1454 bytes=16.7772M bytes_per_second=25.8361G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):24/manual_time 806434 ns 76834109 ns 1454 bytes=16.7772M bytes_per_second=19.3754G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):24/manual_time 528676 ns 76538584 ns 1454 bytes=16.7772M bytes_per_second=29.5549G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):24/manual_time 480632 ns 76311426 ns 1454 bytes=16.7772M bytes_per_second=32.5093G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):24/manual_time 477457 ns 76356301 ns 1454 bytes=16.7772M bytes_per_second=32.7255G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):24/manual_time_mean 579594 ns 76530345 ns 5 bytes=16.7772M bytes_per_second=28.0003G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):24/manual_time_median 528676 ns 76538584 ns 5 bytes=16.7772M bytes_per_second=29.5549G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):24/manual_time_stddev 136847 ns 210423 ns 5 bytes=0 bytes_per_second=5.57106G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):24/manual_time_cv 23.61 % 0.27 % 5 bytes=0.00% bytes_per_second=19.90% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):25/manual_time 1141583 ns 152064394 ns 596 bytes=33.5544M bytes_per_second=27.3743G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):25/manual_time 1199043 ns 152112298 ns 596 bytes=33.5544M bytes_per_second=26.0625G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):25/manual_time 1871776 ns 136884090 ns 596 bytes=33.5544M bytes_per_second=16.6954G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):25/manual_time 1895197 ns 152873079 ns 596 bytes=33.5544M bytes_per_second=16.489G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):25/manual_time 1875426 ns 152859016 ns 596 bytes=33.5544M bytes_per_second=16.6629G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):25/manual_time_mean 1596605 ns 149358575 ns 5 bytes=33.5544M bytes_per_second=20.6568G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):25/manual_time_median 1871776 ns 152112298 ns 5 bytes=33.5544M bytes_per_second=16.6954G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):25/manual_time_stddev 389782 ns 6984305 ns 5 bytes=0 bytes_per_second=5.55338G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_coarse/0/0/log2(N):25/manual_time_cv 24.41 % 4.68 % 5 bytes=0.00% bytes_per_second=26.88% dst_numa=-nan% src_gpu=-nan% +srun: Job step aborted: Waiting up to 32 seconds for job step to finish. +slurmstepd: error: *** STEP 1465787.0 ON frontier07630 CANCELLED AT 2023-10-09T22:21:30 DUE TO TIME LIMIT *** +slurmstepd: error: *** JOB 1465787 ON frontier07630 CANCELLED AT 2023-10-09T22:21:30 DUE TO TIME LIMIT *** +srun: error: frontier07630: task 0: Terminated +srun: Terminating StepId=1465787.0 diff --git a/results/r12-1467862.out b/results/r12-1467862.out new file mode 100644 index 0000000..92ae0ab --- /dev/null +++ b/results/r12-1467862.out @@ -0,0 +1,591 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Tue 10 Oct 2023 01:13:07 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-10 13:13:10.303] [scope] [info] recorded system CPU turbo state +[2023-10-10 13:13:10.304] [scope] [info] recorded CPU goveror +[2023-10-10 13:13:10.304] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-10 13:13:10.304] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-10T13:13:12-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1795.96 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 1.55, 6.82, 8.79 +--------------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +--------------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):12/manual_time 1864211 ns 2063759 ns 381 bytes=4.096k bytes_per_second=2.09539M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):12/manual_time 1868578 ns 2068120 ns 381 bytes=4.096k bytes_per_second=2.09049M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):12/manual_time 1864502 ns 2063887 ns 381 bytes=4.096k bytes_per_second=2.09506M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):12/manual_time 1869043 ns 2068099 ns 381 bytes=4.096k bytes_per_second=2.08997M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):12/manual_time 1864586 ns 2063856 ns 381 bytes=4.096k bytes_per_second=2.09497M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):12/manual_time_mean 1866184 ns 2065544 ns 5 bytes=4.096k bytes_per_second=2.09318M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):12/manual_time_median 1864586 ns 2063887 ns 5 bytes=4.096k bytes_per_second=2.09497M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):12/manual_time_stddev 2407 ns 2342 ns 5 bytes=0 bytes_per_second=2.76363k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):12/manual_time_cv 0.13 % 0.11 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):13/manual_time 1864042 ns 2064285 ns 382 bytes=8.192k bytes_per_second=4.19116M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):13/manual_time 1867970 ns 2068637 ns 382 bytes=8.192k bytes_per_second=4.18235M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):13/manual_time 1864034 ns 2064611 ns 382 bytes=8.192k bytes_per_second=4.19118M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):13/manual_time 1869683 ns 2070254 ns 382 bytes=8.192k bytes_per_second=4.17852M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):13/manual_time 1863700 ns 2064325 ns 382 bytes=8.192k bytes_per_second=4.19193M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):13/manual_time_mean 1865886 ns 2066423 ns 5 bytes=8.192k bytes_per_second=4.18703M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):13/manual_time_median 1864042 ns 2064611 ns 5 bytes=8.192k bytes_per_second=4.19116M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):13/manual_time_stddev 2755 ns 2821 ns 5 bytes=0 bytes_per_second=6.32653k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):13/manual_time_cv 0.15 % 0.14 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):14/manual_time 1869772 ns 2071375 ns 378 bytes=16.384k bytes_per_second=8.35664M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):14/manual_time 1870609 ns 2072332 ns 378 bytes=16.384k bytes_per_second=8.35289M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):14/manual_time 1864961 ns 2067210 ns 378 bytes=16.384k bytes_per_second=8.37819M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):14/manual_time 1869081 ns 2070577 ns 378 bytes=16.384k bytes_per_second=8.35972M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):14/manual_time 1865687 ns 2067756 ns 378 bytes=16.384k bytes_per_second=8.37493M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):14/manual_time_mean 1868022 ns 2069850 ns 5 bytes=16.384k bytes_per_second=8.36448M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):14/manual_time_median 1869081 ns 2070577 ns 5 bytes=16.384k bytes_per_second=8.35972M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):14/manual_time_stddev 2535 ns 2257 ns 5 bytes=0 bytes_per_second=11.6268k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):14/manual_time_cv 0.14 % 0.11 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):15/manual_time 1871750 ns 2074823 ns 378 bytes=32.768k bytes_per_second=16.6956M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):15/manual_time 1867778 ns 2070496 ns 378 bytes=32.768k bytes_per_second=16.7311M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):15/manual_time 1863320 ns 2070990 ns 378 bytes=32.768k bytes_per_second=16.7711M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):15/manual_time 1872126 ns 2075141 ns 378 bytes=32.768k bytes_per_second=16.6923M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):15/manual_time 1867283 ns 2070394 ns 378 bytes=32.768k bytes_per_second=16.7355M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):15/manual_time_mean 1868451 ns 2072369 ns 5 bytes=32.768k bytes_per_second=16.7251M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):15/manual_time_median 1867778 ns 2070990 ns 5 bytes=32.768k bytes_per_second=16.7311M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):15/manual_time_stddev 3624 ns 2399 ns 5 bytes=0 bytes_per_second=33.2357k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):15/manual_time_cv 0.19 % 0.12 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):16/manual_time 1874348 ns 2082390 ns 377 bytes=65.536k bytes_per_second=33.3449M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):16/manual_time 1868692 ns 2077016 ns 377 bytes=65.536k bytes_per_second=33.4458M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):16/manual_time 1864275 ns 2076784 ns 377 bytes=65.536k bytes_per_second=33.5251M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):16/manual_time 1875097 ns 2082829 ns 377 bytes=65.536k bytes_per_second=33.3316M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):16/manual_time 1868839 ns 2076780 ns 377 bytes=65.536k bytes_per_second=33.4432M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):16/manual_time_mean 1870250 ns 2079160 ns 5 bytes=65.536k bytes_per_second=33.4181M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):16/manual_time_median 1868839 ns 2077016 ns 5 bytes=65.536k bytes_per_second=33.4432M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):16/manual_time_stddev 4484 ns 3154 ns 5 bytes=0 bytes_per_second=82.0559k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):16/manual_time_cv 0.24 % 0.15 % 5 bytes=0.00% bytes_per_second=0.24% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):17/manual_time 1866860 ns 2088116 ns 377 bytes=131.072k bytes_per_second=66.9573M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):17/manual_time 1875399 ns 2092057 ns 377 bytes=131.072k bytes_per_second=66.6525M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):17/manual_time 1870123 ns 2086858 ns 377 bytes=131.072k bytes_per_second=66.8405M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):17/manual_time 1874678 ns 2091649 ns 377 bytes=131.072k bytes_per_second=66.6781M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):17/manual_time 1866798 ns 2087503 ns 377 bytes=131.072k bytes_per_second=66.9596M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):17/manual_time_mean 1870772 ns 2089236 ns 5 bytes=131.072k bytes_per_second=66.8176M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):17/manual_time_median 1870123 ns 2088116 ns 5 bytes=131.072k bytes_per_second=66.8405M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):17/manual_time_stddev 4128 ns 2434 ns 5 bytes=0 bytes_per_second=150.947k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):17/manual_time_cv 0.22 % 0.12 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):18/manual_time 1878801 ns 2111504 ns 376 bytes=262.144k bytes_per_second=133.064M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):18/manual_time 1877415 ns 2110063 ns 376 bytes=262.144k bytes_per_second=133.162M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):18/manual_time 1877843 ns 2110269 ns 376 bytes=262.144k bytes_per_second=133.131M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):18/manual_time 1876872 ns 2109692 ns 376 bytes=262.144k bytes_per_second=133.2M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):18/manual_time 1876901 ns 2109515 ns 376 bytes=262.144k bytes_per_second=133.198M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):18/manual_time_mean 1877566 ns 2110209 ns 5 bytes=262.144k bytes_per_second=133.151M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):18/manual_time_median 1877415 ns 2110063 ns 5 bytes=262.144k bytes_per_second=133.162M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):18/manual_time_stddev 798 ns 783 ns 5 bytes=0 bytes_per_second=57.9538k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):18/manual_time_cv 0.04 % 0.04 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):19/manual_time 1892338 ns 2155829 ns 374 bytes=524.288k bytes_per_second=264.223M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):19/manual_time 1890006 ns 2155282 ns 374 bytes=524.288k bytes_per_second=264.549M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):19/manual_time 1887157 ns 2152653 ns 374 bytes=524.288k bytes_per_second=264.949M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):19/manual_time 1887343 ns 2152532 ns 374 bytes=524.288k bytes_per_second=264.923M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):19/manual_time 1888413 ns 2153858 ns 374 bytes=524.288k bytes_per_second=264.773M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):19/manual_time_mean 1889051 ns 2154031 ns 5 bytes=524.288k bytes_per_second=264.683M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):19/manual_time_median 1888413 ns 2153858 ns 5 bytes=524.288k bytes_per_second=264.773M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):19/manual_time_stddev 2158 ns 1498 ns 5 bytes=0 bytes_per_second=309.384k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):19/manual_time_cv 0.11 % 0.07 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):20/manual_time 1896289 ns 2225017 ns 369 bytes=1048.58k bytes_per_second=527.346M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):20/manual_time 1901596 ns 2227754 ns 369 bytes=1048.58k bytes_per_second=525.874M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):20/manual_time 1896966 ns 2224423 ns 369 bytes=1048.58k bytes_per_second=527.158M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):20/manual_time 1902829 ns 2228621 ns 369 bytes=1048.58k bytes_per_second=525.533M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):20/manual_time 1892593 ns 2225382 ns 369 bytes=1048.58k bytes_per_second=528.376M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):20/manual_time_mean 1898055 ns 2226240 ns 5 bytes=1048.58k bytes_per_second=526.857M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):20/manual_time_median 1896966 ns 2225382 ns 5 bytes=1048.58k bytes_per_second=527.158M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):20/manual_time_stddev 4168 ns 1837 ns 5 bytes=0 bytes_per_second=1.15696M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):20/manual_time_cv 0.22 % 0.08 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):21/manual_time 1954326 ns 2409710 ns 360 bytes=2.09715M bytes_per_second=1023.37M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):21/manual_time 1945569 ns 2403334 ns 360 bytes=2.09715M bytes_per_second=1027.98M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):21/manual_time 1947164 ns 2404286 ns 360 bytes=2.09715M bytes_per_second=1027.13M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):21/manual_time 1946076 ns 2402840 ns 360 bytes=2.09715M bytes_per_second=1027.71M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):21/manual_time 1945346 ns 2400527 ns 360 bytes=2.09715M bytes_per_second=1028.09M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):21/manual_time_mean 1947696 ns 2404140 ns 5 bytes=2.09715M bytes_per_second=1026.86M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):21/manual_time_median 1946076 ns 2403334 ns 5 bytes=2.09715M bytes_per_second=1027.71M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):21/manual_time_stddev 3772 ns 3407 ns 5 bytes=0 bytes_per_second=1.98394M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):21/manual_time_cv 0.19 % 0.14 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):22/manual_time 2070409 ns 2772275 ns 340 bytes=4.1943M bytes_per_second=1.8867G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):22/manual_time 2071647 ns 2773190 ns 340 bytes=4.1943M bytes_per_second=1.88558G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):22/manual_time 2074460 ns 2776677 ns 340 bytes=4.1943M bytes_per_second=1.88302G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):22/manual_time 2071245 ns 2774681 ns 340 bytes=4.1943M bytes_per_second=1.88594G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):22/manual_time 2069534 ns 2771968 ns 340 bytes=4.1943M bytes_per_second=1.8875G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):22/manual_time_mean 2071459 ns 2773758 ns 5 bytes=4.1943M bytes_per_second=1.88575G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):22/manual_time_median 2071245 ns 2773190 ns 5 bytes=4.1943M bytes_per_second=1.88594G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):22/manual_time_stddev 1864 ns 1943 ns 5 bytes=0 bytes_per_second=1.73641M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):22/manual_time_cv 0.09 % 0.07 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):23/manual_time 2181146 ns 3409387 ns 320 bytes=8.38861M bytes_per_second=3.58183G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):23/manual_time 2187243 ns 3412303 ns 320 bytes=8.38861M bytes_per_second=3.57185G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):23/manual_time 2181752 ns 3410320 ns 320 bytes=8.38861M bytes_per_second=3.58084G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):23/manual_time 2186494 ns 3411045 ns 320 bytes=8.38861M bytes_per_second=3.57307G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):23/manual_time 2181764 ns 3410199 ns 320 bytes=8.38861M bytes_per_second=3.58082G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):23/manual_time_mean 2183680 ns 3410651 ns 5 bytes=8.38861M bytes_per_second=3.57768G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):23/manual_time_median 2181764 ns 3410320 ns 5 bytes=8.38861M bytes_per_second=3.58082G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):23/manual_time_stddev 2933 ns 1095 ns 5 bytes=0 bytes_per_second=4.91908M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):23/manual_time_cv 0.13 % 0.03 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):24/manual_time 3236109 ns 5513445 ns 216 bytes=16.7772M bytes_per_second=4.82833G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):24/manual_time 3237189 ns 5516247 ns 216 bytes=16.7772M bytes_per_second=4.82672G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):24/manual_time 3235566 ns 5512795 ns 216 bytes=16.7772M bytes_per_second=4.82914G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):24/manual_time 3237089 ns 5518113 ns 216 bytes=16.7772M bytes_per_second=4.82687G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):24/manual_time 3236283 ns 5519344 ns 216 bytes=16.7772M bytes_per_second=4.82807G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):24/manual_time_mean 3236447 ns 5515989 ns 5 bytes=16.7772M bytes_per_second=4.82782G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):24/manual_time_median 3236283 ns 5516247 ns 5 bytes=16.7772M bytes_per_second=4.82807G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):24/manual_time_stddev 686 ns 2851 ns 5 bytes=0 bytes_per_second=1072.44k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):24/manual_time_cv 0.02 % 0.05 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):25/manual_time 6473268 ns 10804239 ns 109 bytes=33.5544M bytes_per_second=4.82755G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):25/manual_time 6475162 ns 10809530 ns 109 bytes=33.5544M bytes_per_second=4.82613G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):25/manual_time 6474070 ns 10807462 ns 109 bytes=33.5544M bytes_per_second=4.82695G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):25/manual_time 6465160 ns 10796707 ns 109 bytes=33.5544M bytes_per_second=4.8336G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):25/manual_time 6454133 ns 10782171 ns 109 bytes=33.5544M bytes_per_second=4.84186G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):25/manual_time_mean 6468359 ns 10800022 ns 5 bytes=33.5544M bytes_per_second=4.83122G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):25/manual_time_median 6473268 ns 10804239 ns 5 bytes=33.5544M bytes_per_second=4.82755G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):25/manual_time_stddev 8883 ns 11104 ns 5 bytes=0 bytes_per_second=6.80125M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):25/manual_time_cv 0.14 % 0.10 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):26/manual_time 13220714 ns 21857016 ns 53 bytes=67.1089M bytes_per_second=4.72743G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):26/manual_time 12844021 ns 20934150 ns 53 bytes=67.1089M bytes_per_second=4.86608G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):26/manual_time 13203477 ns 21853234 ns 53 bytes=67.1089M bytes_per_second=4.7336G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):26/manual_time 13212890 ns 21853147 ns 53 bytes=67.1089M bytes_per_second=4.73023G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):26/manual_time 13221434 ns 21859390 ns 53 bytes=67.1089M bytes_per_second=4.72717G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):26/manual_time_mean 13140507 ns 21671387 ns 5 bytes=67.1089M bytes_per_second=4.7569G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):26/manual_time_median 13212890 ns 21853234 ns 5 bytes=67.1089M bytes_per_second=4.73023G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):26/manual_time_stddev 165900 ns 412137 ns 5 bytes=0 bytes_per_second=62.5521M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):26/manual_time_cv 1.26 % 1.90 % 5 bytes=0.00% bytes_per_second=1.28% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):27/manual_time 25614135 ns 41924226 ns 28 bytes=134.218M bytes_per_second=4.88012G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):27/manual_time 25637142 ns 41937790 ns 28 bytes=134.218M bytes_per_second=4.87574G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):27/manual_time 25607857 ns 41915580 ns 28 bytes=134.218M bytes_per_second=4.88131G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):27/manual_time 25590417 ns 41881220 ns 28 bytes=134.218M bytes_per_second=4.88464G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):27/manual_time 25390291 ns 40955218 ns 28 bytes=134.218M bytes_per_second=4.92314G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):27/manual_time_mean 25567968 ns 41722807 ns 5 bytes=134.218M bytes_per_second=4.88899G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):27/manual_time_median 25607857 ns 41915580 ns 5 bytes=134.218M bytes_per_second=4.88131G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):27/manual_time_stddev 100723 ns 429604 ns 5 bytes=0 bytes_per_second=19.8196M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):27/manual_time_cv 0.39 % 1.03 % 5 bytes=0.00% bytes_per_second=0.40% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):28/manual_time 50144832 ns 80899168 ns 14 bytes=268.435M bytes_per_second=4.98556G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):28/manual_time 46333932 ns 79248397 ns 14 bytes=268.435M bytes_per_second=5.39561G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):28/manual_time 50158627 ns 80861249 ns 14 bytes=268.435M bytes_per_second=4.98419G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):28/manual_time 50128799 ns 80903294 ns 14 bytes=268.435M bytes_per_second=4.98715G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):28/manual_time 50147612 ns 80863024 ns 14 bytes=268.435M bytes_per_second=4.98528G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):28/manual_time_mean 49382760 ns 80555026 ns 5 bytes=268.435M bytes_per_second=5.06756G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):28/manual_time_median 50144832 ns 80863024 ns 5 bytes=268.435M bytes_per_second=4.98556G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):28/manual_time_stddev 1704380 ns 730691 ns 5 bytes=0 bytes_per_second=187.793M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):28/manual_time_cv 3.45 % 0.91 % 5 bytes=0.00% bytes_per_second=3.62% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):29/manual_time 98970509 ns 156854489 ns 8 bytes=536.871M bytes_per_second=5.05201G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):29/manual_time 95839703 ns 152854147 ns 8 bytes=536.871M bytes_per_second=5.21704G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):29/manual_time 98968538 ns 156823213 ns 8 bytes=536.871M bytes_per_second=5.05211G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):29/manual_time 95778676 ns 152804851 ns 8 bytes=536.871M bytes_per_second=5.22037G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):29/manual_time 99263352 ns 156941942 ns 8 bytes=536.871M bytes_per_second=5.03711G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):29/manual_time_mean 97764156 ns 155255728 ns 5 bytes=536.871M bytes_per_second=5.11573G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):29/manual_time_median 98968538 ns 156823213 ns 5 bytes=536.871M bytes_per_second=5.05211G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):29/manual_time_stddev 1788789 ns 2215331 ns 5 bytes=0 bytes_per_second=96.4727M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):29/manual_time_cv 1.83 % 1.43 % 5 bytes=0.00% bytes_per_second=1.84% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):30/manual_time 190296192 ns 289132225 ns 4 bytes=1073.74M bytes_per_second=5.25497G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):30/manual_time 190316543 ns 287287120 ns 4 bytes=1073.74M bytes_per_second=5.2544G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):30/manual_time 190412253 ns 287068154 ns 4 bytes=1073.74M bytes_per_second=5.25176G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):30/manual_time 190101098 ns 286420572 ns 4 bytes=1073.74M bytes_per_second=5.26036G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):30/manual_time 190388910 ns 287059673 ns 4 bytes=1073.74M bytes_per_second=5.25241G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):30/manual_time_mean 190302999 ns 287393549 ns 5 bytes=1073.74M bytes_per_second=5.25478G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):30/manual_time_median 190316543 ns 287068154 ns 5 bytes=1073.74M bytes_per_second=5.2544G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):30/manual_time_stddev 122791 ns 1024495 ns 5 bytes=0 bytes_per_second=3.47388M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_fine/0/0/log2(N):30/manual_time_cv 0.06 % 0.36 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=-nan% src_numa=-nan% +[2023-10-10 13:15:23.084] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-10 13:15:23.084] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-10 13:15:25.053] [scope] [info] recorded system CPU turbo state +[2023-10-10 13:15:25.053] [scope] [info] recorded CPU goveror +[2023-10-10 13:15:25.053] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-10 13:15:25.053] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-10T13:15:27-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1796.26 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 2.33, 5.29, 7.95 +----------------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +----------------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):12/manual_time 1864839 ns 2064453 ns 378 bytes=4.096k bytes_per_second=2.09468M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):12/manual_time 1868405 ns 2067969 ns 378 bytes=4.096k bytes_per_second=2.09069M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):12/manual_time 1860276 ns 2063986 ns 378 bytes=4.096k bytes_per_second=2.09982M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):12/manual_time 1865140 ns 2064357 ns 378 bytes=4.096k bytes_per_second=2.09435M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):12/manual_time 1869962 ns 2069432 ns 378 bytes=4.096k bytes_per_second=2.08895M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):12/manual_time_mean 1865724 ns 2066039 ns 5 bytes=4.096k bytes_per_second=2.0937M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):12/manual_time_median 1865140 ns 2064453 ns 5 bytes=4.096k bytes_per_second=2.09435M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):12/manual_time_stddev 3740 ns 2490 ns 5 bytes=0 bytes_per_second=4.30022k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):12/manual_time_cv 0.20 % 0.12 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):13/manual_time 1865680 ns 2066380 ns 378 bytes=8.192k bytes_per_second=4.18748M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):13/manual_time 1870644 ns 2071123 ns 378 bytes=8.192k bytes_per_second=4.17637M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):13/manual_time 1866706 ns 2066694 ns 378 bytes=8.192k bytes_per_second=4.18518M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):13/manual_time 1872326 ns 2072219 ns 378 bytes=8.192k bytes_per_second=4.17262M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):13/manual_time 1870718 ns 2071240 ns 378 bytes=8.192k bytes_per_second=4.1762M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):13/manual_time_mean 1869215 ns 2069531 ns 5 bytes=8.192k bytes_per_second=4.17957M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):13/manual_time_median 1870644 ns 2071123 ns 5 bytes=8.192k bytes_per_second=4.17637M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):13/manual_time_stddev 2862 ns 2768 ns 5 bytes=0 bytes_per_second=6.55629k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):13/manual_time_cv 0.15 % 0.13 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):14/manual_time 1866980 ns 2068745 ns 378 bytes=16.384k bytes_per_second=8.36913M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):14/manual_time 1871686 ns 2072823 ns 378 bytes=16.384k bytes_per_second=8.34809M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):14/manual_time 1867048 ns 2068405 ns 378 bytes=16.384k bytes_per_second=8.36883M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):14/manual_time 1871184 ns 2072610 ns 378 bytes=16.384k bytes_per_second=8.35033M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):14/manual_time 1872893 ns 2074688 ns 378 bytes=16.384k bytes_per_second=8.34271M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):14/manual_time_mean 1869958 ns 2071454 ns 5 bytes=16.384k bytes_per_second=8.35582M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):14/manual_time_median 1871184 ns 2072610 ns 5 bytes=16.384k bytes_per_second=8.35033M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):14/manual_time_stddev 2759 ns 2752 ns 5 bytes=0 bytes_per_second=12.627k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):14/manual_time_cv 0.15 % 0.13 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):15/manual_time 1869878 ns 2072538 ns 377 bytes=32.768k bytes_per_second=16.7123M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):15/manual_time 1873653 ns 2077010 ns 377 bytes=32.768k bytes_per_second=16.6787M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):15/manual_time 1867473 ns 2070729 ns 377 bytes=32.768k bytes_per_second=16.7338M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):15/manual_time 1872127 ns 2075258 ns 377 bytes=32.768k bytes_per_second=16.6922M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):15/manual_time 1866895 ns 2070280 ns 377 bytes=32.768k bytes_per_second=16.739M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):15/manual_time_mean 1870005 ns 2073163 ns 5 bytes=32.768k bytes_per_second=16.7112M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):15/manual_time_median 1869878 ns 2072538 ns 5 bytes=32.768k bytes_per_second=16.7123M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):15/manual_time_stddev 2912 ns 2908 ns 5 bytes=0 bytes_per_second=26.6397k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):15/manual_time_cv 0.16 % 0.14 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):16/manual_time 1869841 ns 2077934 ns 381 bytes=65.536k bytes_per_second=33.4253M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):16/manual_time 1873335 ns 2081482 ns 381 bytes=65.536k bytes_per_second=33.363M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):16/manual_time 1868817 ns 2076647 ns 381 bytes=65.536k bytes_per_second=33.4436M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):16/manual_time 1874151 ns 2082473 ns 381 bytes=65.536k bytes_per_second=33.3484M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):16/manual_time 1868829 ns 2076976 ns 381 bytes=65.536k bytes_per_second=33.4434M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):16/manual_time_mean 1870995 ns 2079103 ns 5 bytes=65.536k bytes_per_second=33.4047M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):16/manual_time_median 1869841 ns 2077934 ns 5 bytes=65.536k bytes_per_second=33.4253M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):16/manual_time_stddev 2560 ns 2690 ns 5 bytes=0 bytes_per_second=46.7751k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):16/manual_time_cv 0.14 % 0.13 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):17/manual_time 1870792 ns 2087539 ns 380 bytes=131.072k bytes_per_second=66.8166M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):17/manual_time 1867953 ns 2088319 ns 380 bytes=131.072k bytes_per_second=66.9182M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):17/manual_time 1876809 ns 2093385 ns 380 bytes=131.072k bytes_per_second=66.6024M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):17/manual_time 1869481 ns 2089650 ns 380 bytes=131.072k bytes_per_second=66.8635M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):17/manual_time 1871313 ns 2088317 ns 380 bytes=131.072k bytes_per_second=66.798M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):17/manual_time_mean 1871270 ns 2089442 ns 5 bytes=131.072k bytes_per_second=66.7997M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):17/manual_time_median 1870792 ns 2088319 ns 5 bytes=131.072k bytes_per_second=66.8166M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):17/manual_time_stddev 3358 ns 2331 ns 5 bytes=0 bytes_per_second=122.579k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):17/manual_time_cv 0.18 % 0.11 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):18/manual_time 1874452 ns 2107238 ns 379 bytes=262.144k bytes_per_second=133.372M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):18/manual_time 1877220 ns 2110328 ns 379 bytes=262.144k bytes_per_second=133.176M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):18/manual_time 1871809 ns 2107631 ns 379 bytes=262.144k bytes_per_second=133.561M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):18/manual_time 1872190 ns 2115198 ns 379 bytes=262.144k bytes_per_second=133.533M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):18/manual_time 1871299 ns 2120218 ns 379 bytes=262.144k bytes_per_second=133.597M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):18/manual_time_mean 1873394 ns 2112123 ns 5 bytes=262.144k bytes_per_second=133.448M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):18/manual_time_median 1872190 ns 2110328 ns 5 bytes=262.144k bytes_per_second=133.533M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):18/manual_time_stddev 2455 ns 5528 ns 5 bytes=0 bytes_per_second=178.88k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):18/manual_time_cv 0.13 % 0.26 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):19/manual_time 1895679 ns 2177481 ns 370 bytes=524.288k bytes_per_second=263.758M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):19/manual_time 1895358 ns 2177326 ns 370 bytes=524.288k bytes_per_second=263.802M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):19/manual_time 1894730 ns 2176771 ns 370 bytes=524.288k bytes_per_second=263.89M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):19/manual_time 1893258 ns 2177048 ns 370 bytes=524.288k bytes_per_second=264.095M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):19/manual_time 1891285 ns 2175414 ns 370 bytes=524.288k bytes_per_second=264.371M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):19/manual_time_mean 1894062 ns 2176808 ns 5 bytes=524.288k bytes_per_second=263.983M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):19/manual_time_median 1894730 ns 2177048 ns 5 bytes=524.288k bytes_per_second=263.89M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):19/manual_time_stddev 1810 ns 825 ns 5 bytes=0 bytes_per_second=258.43k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):19/manual_time_cv 0.10 % 0.04 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):20/manual_time 1894455 ns 2257930 ns 369 bytes=1048.58k bytes_per_second=527.856M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):20/manual_time 1900257 ns 2261491 ns 369 bytes=1048.58k bytes_per_second=526.245M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):20/manual_time 1893084 ns 2257430 ns 369 bytes=1048.58k bytes_per_second=528.239M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):20/manual_time 1900050 ns 2261077 ns 369 bytes=1048.58k bytes_per_second=526.302M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):20/manual_time 1891775 ns 2255970 ns 369 bytes=1048.58k bytes_per_second=528.604M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):20/manual_time_mean 1895924 ns 2258780 ns 5 bytes=1048.58k bytes_per_second=527.449M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):20/manual_time_median 1894455 ns 2257930 ns 5 bytes=1048.58k bytes_per_second=527.856M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):20/manual_time_stddev 3976 ns 2401 ns 5 bytes=0 bytes_per_second=1.10562M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):20/manual_time_cv 0.21 % 0.11 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):21/manual_time 1941025 ns 2456217 ns 363 bytes=2.09715M bytes_per_second=1030.38M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):21/manual_time 1941729 ns 2456836 ns 363 bytes=2.09715M bytes_per_second=1030.01M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):21/manual_time 1936886 ns 2459622 ns 363 bytes=2.09715M bytes_per_second=1032.59M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):21/manual_time 1940630 ns 2456053 ns 363 bytes=2.09715M bytes_per_second=1030.59M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):21/manual_time 1947159 ns 2456202 ns 363 bytes=2.09715M bytes_per_second=1027.14M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):21/manual_time_mean 1941486 ns 2456986 ns 5 bytes=2.09715M bytes_per_second=1030.14M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):21/manual_time_median 1941025 ns 2456217 ns 5 bytes=2.09715M bytes_per_second=1030.38M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):21/manual_time_stddev 3686 ns 1504 ns 5 bytes=0 bytes_per_second=1.95407M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):21/manual_time_cv 0.19 % 0.06 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):22/manual_time 2041422 ns 2861637 ns 344 bytes=4.1943M bytes_per_second=1.91349G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):22/manual_time 2043839 ns 2861048 ns 344 bytes=4.1943M bytes_per_second=1.91123G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):22/manual_time 2045734 ns 2861518 ns 344 bytes=4.1943M bytes_per_second=1.90946G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):22/manual_time 2042460 ns 2859908 ns 344 bytes=4.1943M bytes_per_second=1.91252G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):22/manual_time 2043570 ns 2861013 ns 344 bytes=4.1943M bytes_per_second=1.91148G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):22/manual_time_mean 2043405 ns 2861025 ns 5 bytes=4.1943M bytes_per_second=1.91164G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):22/manual_time_median 2043570 ns 2861048 ns 5 bytes=4.1943M bytes_per_second=1.91148G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):22/manual_time_stddev 1617 ns 683 ns 5 bytes=0 bytes_per_second=1.54921M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):22/manual_time_cv 0.08 % 0.02 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):23/manual_time 2083672 ns 3570808 ns 335 bytes=8.38861M bytes_per_second=3.74939G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):23/manual_time 2088075 ns 3572891 ns 335 bytes=8.38861M bytes_per_second=3.74148G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):23/manual_time 2080843 ns 3571030 ns 335 bytes=8.38861M bytes_per_second=3.75449G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):23/manual_time 2090196 ns 3574295 ns 335 bytes=8.38861M bytes_per_second=3.73769G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):23/manual_time 2085150 ns 3568993 ns 335 bytes=8.38861M bytes_per_second=3.74673G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):23/manual_time_mean 2085587 ns 3571603 ns 5 bytes=8.38861M bytes_per_second=3.74596G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):23/manual_time_median 2085150 ns 3571030 ns 5 bytes=8.38861M bytes_per_second=3.74673G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):23/manual_time_stddev 3667 ns 2042 ns 5 bytes=0 bytes_per_second=6.74528M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):23/manual_time_cv 0.18 % 0.06 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):24/manual_time 3505007 ns 6363932 ns 199 bytes=16.7772M bytes_per_second=4.45791G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):24/manual_time 3508507 ns 6373458 ns 199 bytes=16.7772M bytes_per_second=4.45346G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):24/manual_time 3509993 ns 6373538 ns 199 bytes=16.7772M bytes_per_second=4.45158G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):24/manual_time 3504629 ns 6369718 ns 199 bytes=16.7772M bytes_per_second=4.45839G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):24/manual_time 3503117 ns 6359001 ns 199 bytes=16.7772M bytes_per_second=4.46031G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):24/manual_time_mean 3506250 ns 6367930 ns 5 bytes=16.7772M bytes_per_second=4.45633G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):24/manual_time_median 3505007 ns 6369718 ns 5 bytes=16.7772M bytes_per_second=4.45791G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):24/manual_time_stddev 2876 ns 6343 ns 5 bytes=0 bytes_per_second=3.74254M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):24/manual_time_cv 0.08 % 0.10 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):25/manual_time 7063862 ns 12958764 ns 101 bytes=33.5544M bytes_per_second=4.42393G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):25/manual_time 7067895 ns 12954682 ns 101 bytes=33.5544M bytes_per_second=4.4214G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):25/manual_time 7061672 ns 12955119 ns 101 bytes=33.5544M bytes_per_second=4.4253G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):25/manual_time 7076708 ns 12964943 ns 101 bytes=33.5544M bytes_per_second=4.4159G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):25/manual_time 7072630 ns 12952759 ns 101 bytes=33.5544M bytes_per_second=4.41844G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):25/manual_time_mean 7068553 ns 12957253 ns 5 bytes=33.5544M bytes_per_second=4.42099G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):25/manual_time_median 7067895 ns 12955119 ns 5 bytes=33.5544M bytes_per_second=4.4214G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):25/manual_time_stddev 6183 ns 4816 ns 5 bytes=0 bytes_per_second=3.95912M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):25/manual_time_cv 0.09 % 0.04 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):26/manual_time 14118497 ns 25710183 ns 50 bytes=67.1089M bytes_per_second=4.42682G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):26/manual_time 13772371 ns 24737117 ns 50 bytes=67.1089M bytes_per_second=4.53807G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):26/manual_time 14122546 ns 25712054 ns 50 bytes=67.1089M bytes_per_second=4.42555G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):26/manual_time 14108271 ns 25685967 ns 50 bytes=67.1089M bytes_per_second=4.43003G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):26/manual_time 14127106 ns 25707315 ns 50 bytes=67.1089M bytes_per_second=4.42412G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):26/manual_time_mean 14049758 ns 25510527 ns 5 bytes=67.1089M bytes_per_second=4.44892G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):26/manual_time_median 14118497 ns 25707315 ns 5 bytes=67.1089M bytes_per_second=4.42682G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):26/manual_time_stddev 155220 ns 432476 ns 5 bytes=0 bytes_per_second=51.0843M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):26/manual_time_cv 1.10 % 1.70 % 5 bytes=0.00% bytes_per_second=1.12% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):27/manual_time 27222325 ns 48701151 ns 26 bytes=134.218M bytes_per_second=4.59182G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):27/manual_time 27165950 ns 48674630 ns 26 bytes=134.218M bytes_per_second=4.60135G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):27/manual_time 27202560 ns 48684332 ns 26 bytes=134.218M bytes_per_second=4.59516G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):27/manual_time 27197267 ns 48694791 ns 26 bytes=134.218M bytes_per_second=4.59605G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):27/manual_time 26773949 ns 47087593 ns 26 bytes=134.218M bytes_per_second=4.66872G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):27/manual_time_mean 27112410 ns 48368499 ns 5 bytes=134.218M bytes_per_second=4.61062G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):27/manual_time_median 27197267 ns 48684332 ns 5 bytes=134.218M bytes_per_second=4.59605G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):27/manual_time_stddev 190284 ns 716120 ns 5 bytes=0 bytes_per_second=33.4417M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):27/manual_time_cv 0.70 % 1.48 % 5 bytes=0.00% bytes_per_second=0.71% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):28/manual_time 52709759 ns 90856503 ns 10 bytes=268.435M bytes_per_second=4.74295G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):28/manual_time 52530158 ns 90797320 ns 10 bytes=268.435M bytes_per_second=4.75917G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):28/manual_time 49138173 ns 87876538 ns 10 bytes=268.435M bytes_per_second=5.08769G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):28/manual_time 52662639 ns 90868765 ns 10 bytes=268.435M bytes_per_second=4.7472G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):28/manual_time 52701374 ns 91383154 ns 10 bytes=268.435M bytes_per_second=4.74371G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):28/manual_time_mean 51948421 ns 90356456 ns 5 bytes=268.435M bytes_per_second=4.81615G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):28/manual_time_median 52662639 ns 90856503 ns 5 bytes=268.435M bytes_per_second=4.7472G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):28/manual_time_stddev 1572625 ns 1406323 ns 5 bytes=0 bytes_per_second=155.586M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):28/manual_time_cv 3.03 % 1.56 % 5 bytes=0.00% bytes_per_second=3.15% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):29/manual_time 103376929 ns 176645419 ns 8 bytes=536.871M bytes_per_second=4.83667G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):29/manual_time 92233662 ns 171367641 ns 8 bytes=536.871M bytes_per_second=5.42101G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):29/manual_time 103419549 ns 176696455 ns 8 bytes=536.871M bytes_per_second=4.83468G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):29/manual_time 92157389 ns 171406353 ns 8 bytes=536.871M bytes_per_second=5.4255G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):29/manual_time 103564523 ns 176815768 ns 8 bytes=536.871M bytes_per_second=4.82791G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):29/manual_time_mean 98950410 ns 174586327 ns 5 bytes=536.871M bytes_per_second=5.06915G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):29/manual_time_median 103376929 ns 176645419 ns 5 bytes=536.871M bytes_per_second=4.83667G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):29/manual_time_stddev 6166789 ns 2921262 ns 5 bytes=0 bytes_per_second=331.03M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):29/manual_time_cv 6.23 % 1.67 % 5 bytes=0.00% bytes_per_second=6.38% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):30/manual_time 186505951 ns 302328019 ns 4 bytes=1073.74M bytes_per_second=5.36176G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):30/manual_time 186741266 ns 301590022 ns 4 bytes=1073.74M bytes_per_second=5.355G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):30/manual_time 186651953 ns 301568705 ns 4 bytes=1073.74M bytes_per_second=5.35757G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):30/manual_time 187214356 ns 301930907 ns 4 bytes=1073.74M bytes_per_second=5.34147G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):30/manual_time 186694797 ns 301441421 ns 4 bytes=1073.74M bytes_per_second=5.35634G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):30/manual_time_mean 186761665 ns 301771815 ns 5 bytes=1073.74M bytes_per_second=5.35443G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):30/manual_time_median 186694797 ns 301590022 ns 5 bytes=1073.74M bytes_per_second=5.35634G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):30/manual_time_stddev 267975 ns 359908 ns 5 bytes=0 bytes_per_second=7.85631M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPUWrHost_coarse/0/0/log2(N):30/manual_time_cv 0.14 % 0.12 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=-nan% src_numa=-nan% +[2023-10-10 13:17:39.342] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-10 13:17:39.342] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-10 13:17:39.729] [scope] [info] recorded system CPU turbo state +[2023-10-10 13:17:39.729] [scope] [info] recorded CPU goveror +[2023-10-10 13:17:39.729] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-10 13:17:39.729] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-10T13:17:42-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1795.34 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 2.33, 4.27, 7.21 +--------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +--------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):12/manual_time 13306 ns 20417 ns 52613 bytes=4.096k bytes_per_second=293.566M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):12/manual_time 13301 ns 20429 ns 52613 bytes=4.096k bytes_per_second=293.683M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):12/manual_time 13302 ns 20442 ns 52613 bytes=4.096k bytes_per_second=293.653M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):12/manual_time 13305 ns 20434 ns 52613 bytes=4.096k bytes_per_second=293.602M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):12/manual_time 13293 ns 20402 ns 52613 bytes=4.096k bytes_per_second=293.847M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):12/manual_time_mean 13301 ns 20425 ns 5 bytes=4.096k bytes_per_second=293.67M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):12/manual_time_median 13302 ns 20429 ns 5 bytes=4.096k bytes_per_second=293.653M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):12/manual_time_stddev 4.93 ns 15.5 ns 5 bytes=0 bytes_per_second=111.434k/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):12/manual_time_cv 0.04 % 0.08 % 5 bytes=0.00% bytes_per_second=0.04% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):13/manual_time 13302 ns 20656 ns 52606 bytes=8.192k bytes_per_second=587.338M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):13/manual_time 13306 ns 20656 ns 52606 bytes=8.192k bytes_per_second=587.146M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):13/manual_time 13303 ns 20633 ns 52606 bytes=8.192k bytes_per_second=587.293M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):13/manual_time 13294 ns 20611 ns 52606 bytes=8.192k bytes_per_second=587.67M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):13/manual_time 13306 ns 20671 ns 52606 bytes=8.192k bytes_per_second=587.147M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):13/manual_time_mean 13302 ns 20645 ns 5 bytes=8.192k bytes_per_second=587.319M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):13/manual_time_median 13303 ns 20656 ns 5 bytes=8.192k bytes_per_second=587.293M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):13/manual_time_stddev 4.85 ns 23.5 ns 5 bytes=0 bytes_per_second=219.329k/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):13/manual_time_cv 0.04 % 0.11 % 5 bytes=0.00% bytes_per_second=0.04% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):14/manual_time 13304 ns 20818 ns 52631 bytes=16.384k bytes_per_second=1.14691G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):14/manual_time 13298 ns 20802 ns 52631 bytes=16.384k bytes_per_second=1.14748G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):14/manual_time 13295 ns 20806 ns 52631 bytes=16.384k bytes_per_second=1.14773G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):14/manual_time 13297 ns 20788 ns 52631 bytes=16.384k bytes_per_second=1.14751G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):14/manual_time 13298 ns 20794 ns 52631 bytes=16.384k bytes_per_second=1.14746G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):14/manual_time_mean 13298 ns 20802 ns 5 bytes=16.384k bytes_per_second=1.14742G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):14/manual_time_median 13298 ns 20802 ns 5 bytes=16.384k bytes_per_second=1.14748G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):14/manual_time_stddev 3.49 ns 11.5 ns 5 bytes=0 bytes_per_second=315.889k/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):14/manual_time_cv 0.03 % 0.06 % 5 bytes=0.00% bytes_per_second=0.03% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):15/manual_time 13303 ns 21281 ns 52641 bytes=32.768k bytes_per_second=2.294G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):15/manual_time 13298 ns 21285 ns 52641 bytes=32.768k bytes_per_second=2.29482G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):15/manual_time 13299 ns 21259 ns 52641 bytes=32.768k bytes_per_second=2.2947G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):15/manual_time 13301 ns 21302 ns 52641 bytes=32.768k bytes_per_second=2.29438G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):15/manual_time 13300 ns 21309 ns 52641 bytes=32.768k bytes_per_second=2.2946G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):15/manual_time_mean 13300 ns 21287 ns 5 bytes=32.768k bytes_per_second=2.2945G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):15/manual_time_median 13300 ns 21285 ns 5 bytes=32.768k bytes_per_second=2.2946G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):15/manual_time_stddev 1.87 ns 19.5 ns 5 bytes=0 bytes_per_second=338.054k/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):15/manual_time_cv 0.01 % 0.09 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):16/manual_time 13720 ns 23504 ns 51034 bytes=65.536k bytes_per_second=4.44851G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):16/manual_time 13720 ns 23506 ns 51034 bytes=65.536k bytes_per_second=4.44854G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):16/manual_time 13734 ns 23491 ns 51034 bytes=65.536k bytes_per_second=4.44398G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):16/manual_time 13723 ns 23482 ns 51034 bytes=65.536k bytes_per_second=4.44764G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):16/manual_time 13716 ns 23495 ns 51034 bytes=65.536k bytes_per_second=4.45002G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):16/manual_time_mean 13723 ns 23496 ns 5 bytes=65.536k bytes_per_second=4.44774G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):16/manual_time_median 13720 ns 23495 ns 5 bytes=65.536k bytes_per_second=4.44851G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):16/manual_time_stddev 7.00 ns 9.66 ns 5 bytes=0 bytes_per_second=2.32359M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):16/manual_time_cv 0.05 % 0.04 % 5 bytes=0.00% bytes_per_second=0.05% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):17/manual_time 17968 ns 31749 ns 38978 bytes=131.072k bytes_per_second=6.79358G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):17/manual_time 17958 ns 31734 ns 38978 bytes=131.072k bytes_per_second=6.79738G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):17/manual_time 17973 ns 31713 ns 38978 bytes=131.072k bytes_per_second=6.79169G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):17/manual_time 17970 ns 31766 ns 38978 bytes=131.072k bytes_per_second=6.79295G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):17/manual_time 17961 ns 31759 ns 38978 bytes=131.072k bytes_per_second=6.79648G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):17/manual_time_mean 17966 ns 31744 ns 5 bytes=131.072k bytes_per_second=6.79442G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):17/manual_time_median 17968 ns 31749 ns 5 bytes=131.072k bytes_per_second=6.79358G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):17/manual_time_stddev 6.38 ns 21.2 ns 5 bytes=0 bytes_per_second=2.47114M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):17/manual_time_cv 0.04 % 0.07 % 5 bytes=0.00% bytes_per_second=0.04% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):18/manual_time 23097 ns 45072 ns 30312 bytes=262.144k bytes_per_second=10.5701G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):18/manual_time 23098 ns 45093 ns 30312 bytes=262.144k bytes_per_second=10.5698G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):18/manual_time 23092 ns 45194 ns 30312 bytes=262.144k bytes_per_second=10.5724G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):18/manual_time 23095 ns 45199 ns 30312 bytes=262.144k bytes_per_second=10.5712G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):18/manual_time 23095 ns 45219 ns 30312 bytes=262.144k bytes_per_second=10.5709G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):18/manual_time_mean 23096 ns 45155 ns 5 bytes=262.144k bytes_per_second=10.5709G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):18/manual_time_median 23095 ns 45194 ns 5 bytes=262.144k bytes_per_second=10.5709G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):18/manual_time_stddev 2.29 ns 67.8 ns 5 bytes=0 bytes_per_second=1099.7k/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):18/manual_time_cv 0.01 % 0.15 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time 32961 ns 68157 ns 21237 bytes=524.288k bytes_per_second=14.8138G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time 32971 ns 68216 ns 21237 bytes=524.288k bytes_per_second=14.8096G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time 32977 ns 68193 ns 21237 bytes=524.288k bytes_per_second=14.8068G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time 32962 ns 68211 ns 21237 bytes=524.288k bytes_per_second=14.8134G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time 32962 ns 68164 ns 21237 bytes=524.288k bytes_per_second=14.8136G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time_mean 32966 ns 68188 ns 5 bytes=524.288k bytes_per_second=14.8115G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time_median 32962 ns 68193 ns 5 bytes=524.288k bytes_per_second=14.8134G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time_stddev 6.97 ns 26.7 ns 5 bytes=0 bytes_per_second=3.20666M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):19/manual_time_cv 0.02 % 0.04 % 5 bytes=0.00% bytes_per_second=0.02% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time 52775 ns 112506 ns 13266 bytes=1048.58k bytes_per_second=18.5042G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time 52765 ns 112625 ns 13266 bytes=1048.58k bytes_per_second=18.5079G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time 52757 ns 112791 ns 13266 bytes=1048.58k bytes_per_second=18.5107G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time 52770 ns 112965 ns 13266 bytes=1048.58k bytes_per_second=18.5059G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time 52767 ns 112943 ns 13266 bytes=1048.58k bytes_per_second=18.5072G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time_mean 52767 ns 112766 ns 5 bytes=1048.58k bytes_per_second=18.5072G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time_median 52767 ns 112791 ns 5 bytes=1048.58k bytes_per_second=18.5072G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time_stddev 6.87 ns 200 ns 5 bytes=0 bytes_per_second=2.46643M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):20/manual_time_cv 0.01 % 0.18 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time 92221 ns 196439 ns 7591 bytes=2.09715M bytes_per_second=21.1787G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time 92226 ns 196536 ns 7591 bytes=2.09715M bytes_per_second=21.1775G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time 92221 ns 196426 ns 7591 bytes=2.09715M bytes_per_second=21.1787G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time 92209 ns 196423 ns 7591 bytes=2.09715M bytes_per_second=21.1815G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time 92206 ns 196437 ns 7591 bytes=2.09715M bytes_per_second=21.1822G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time_mean 92217 ns 196452 ns 5 bytes=2.09715M bytes_per_second=21.1797G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time_median 92221 ns 196437 ns 5 bytes=2.09715M bytes_per_second=21.1787G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time_stddev 8.77 ns 47.1 ns 5 bytes=0 bytes_per_second=2.06237M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):21/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time 166994 ns 371652 ns 4196 bytes=4.1943M bytes_per_second=23.3915G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time 166971 ns 371219 ns 4196 bytes=4.1943M bytes_per_second=23.3948G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time 167046 ns 372057 ns 4196 bytes=4.1943M bytes_per_second=23.3842G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time 166957 ns 372064 ns 4196 bytes=4.1943M bytes_per_second=23.3967G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time 166969 ns 372639 ns 4196 bytes=4.1943M bytes_per_second=23.395G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time_mean 166988 ns 371926 ns 5 bytes=4.1943M bytes_per_second=23.3925G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time_median 166971 ns 372057 ns 5 bytes=4.1943M bytes_per_second=23.3948G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time_stddev 35.5 ns 529 ns 5 bytes=0 bytes_per_second=5.09386M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):22/manual_time_cv 0.02 % 0.14 % 5 bytes=0.00% bytes_per_second=0.02% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time 323625 ns 760861 ns 2162 bytes=8.38861M bytes_per_second=24.1406G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time 323854 ns 764037 ns 2162 bytes=8.38861M bytes_per_second=24.1236G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time 323818 ns 762936 ns 2162 bytes=8.38861M bytes_per_second=24.1262G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time 323955 ns 764234 ns 2162 bytes=8.38861M bytes_per_second=24.116G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time 323913 ns 763056 ns 2162 bytes=8.38861M bytes_per_second=24.1191G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time_mean 323833 ns 763025 ns 5 bytes=8.38861M bytes_per_second=24.1251G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time_median 323854 ns 763056 ns 5 bytes=8.38861M bytes_per_second=24.1236G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time_stddev 128 ns 1339 ns 5 bytes=0 bytes_per_second=9.75134M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):23/manual_time_cv 0.04 % 0.18 % 5 bytes=0.00% bytes_per_second=0.04% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time 640309 ns 1542225 ns 1093 bytes=16.7772M bytes_per_second=24.4023G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time 640196 ns 1542127 ns 1093 bytes=16.7772M bytes_per_second=24.4066G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time 640190 ns 1542110 ns 1093 bytes=16.7772M bytes_per_second=24.4068G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time 640180 ns 1539273 ns 1093 bytes=16.7772M bytes_per_second=24.4072G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time 640301 ns 1542269 ns 1093 bytes=16.7772M bytes_per_second=24.4026G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time_mean 640235 ns 1541601 ns 5 bytes=16.7772M bytes_per_second=24.4051G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time_median 640196 ns 1542127 ns 5 bytes=16.7772M bytes_per_second=24.4066G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time_stddev 63.8 ns 1303 ns 5 bytes=0 bytes_per_second=2.49011M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):24/manual_time_cv 0.01 % 0.08 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time 1266923 ns 3050275 ns 552 bytes=33.5544M bytes_per_second=24.6661G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time 1266699 ns 3056312 ns 552 bytes=33.5544M bytes_per_second=24.6704G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time 1266481 ns 3052303 ns 552 bytes=33.5544M bytes_per_second=24.6747G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time 1267028 ns 3061159 ns 552 bytes=33.5544M bytes_per_second=24.664G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time 1264719 ns 3081098 ns 552 bytes=33.5544M bytes_per_second=24.7091G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time_mean 1266370 ns 3060230 ns 5 bytes=33.5544M bytes_per_second=24.6768G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time_median 1266699 ns 3056312 ns 5 bytes=33.5544M bytes_per_second=24.6704G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time_stddev 947 ns 12386 ns 5 bytes=0 bytes_per_second=18.9103M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):25/manual_time_cv 0.07 % 0.40 % 5 bytes=0.00% bytes_per_second=0.07% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time 2533306 ns 6310853 ns 276 bytes=67.1089M bytes_per_second=24.6713G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time 2530019 ns 6320941 ns 276 bytes=67.1089M bytes_per_second=24.7034G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time 2532880 ns 6327488 ns 276 bytes=67.1089M bytes_per_second=24.6755G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time 2534456 ns 6293775 ns 276 bytes=67.1089M bytes_per_second=24.6601G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time 2534067 ns 6317811 ns 276 bytes=67.1089M bytes_per_second=24.6639G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time_mean 2532945 ns 6314174 ns 5 bytes=67.1089M bytes_per_second=24.6748G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time_median 2533306 ns 6317811 ns 5 bytes=67.1089M bytes_per_second=24.6713G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time_stddev 1749 ns 12878 ns 5 bytes=0 bytes_per_second=17.4608M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):26/manual_time_cv 0.07 % 0.20 % 5 bytes=0.00% bytes_per_second=0.07% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time 5055892 ns 12831195 ns 138 bytes=134.218M bytes_per_second=24.7236G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time 5056407 ns 12827767 ns 138 bytes=134.218M bytes_per_second=24.7211G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time 5057194 ns 12825944 ns 138 bytes=134.218M bytes_per_second=24.7173G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time 5055681 ns 12818127 ns 138 bytes=134.218M bytes_per_second=24.7247G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time 5055866 ns 12801847 ns 138 bytes=134.218M bytes_per_second=24.7238G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time_mean 5056208 ns 12820976 ns 5 bytes=134.218M bytes_per_second=24.7221G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time_median 5055892 ns 12825944 ns 5 bytes=134.218M bytes_per_second=24.7236G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time_stddev 614 ns 11718 ns 5 bytes=0 bytes_per_second=3.07189M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):27/manual_time_cv 0.01 % 0.09 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time 10100161 ns 25814307 ns 69 bytes=268.435M bytes_per_second=24.7521G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time 10097395 ns 25787414 ns 69 bytes=268.435M bytes_per_second=24.7589G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time 10099726 ns 25806927 ns 69 bytes=268.435M bytes_per_second=24.7531G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time 10099199 ns 25868805 ns 69 bytes=268.435M bytes_per_second=24.7544G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time 10099014 ns 25855632 ns 69 bytes=268.435M bytes_per_second=24.7549G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time_mean 10099099 ns 25826617 ns 5 bytes=268.435M bytes_per_second=24.7547G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time_median 10099199 ns 25814307 ns 5 bytes=268.435M bytes_per_second=24.7544G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time_stddev 1054 ns 34270 ns 5 bytes=0 bytes_per_second=2.64493M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):28/manual_time_cv 0.01 % 0.13 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time 20186295 ns 51467227 ns 35 bytes=536.871M bytes_per_second=24.7693G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time 20185914 ns 51488342 ns 35 bytes=536.871M bytes_per_second=24.7697G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time 20195094 ns 51817182 ns 35 bytes=536.871M bytes_per_second=24.7585G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time 20210578 ns 51889858 ns 35 bytes=536.871M bytes_per_second=24.7395G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time 20202862 ns 51876611 ns 35 bytes=536.871M bytes_per_second=24.749G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time_mean 20196149 ns 51707844 ns 5 bytes=536.871M bytes_per_second=24.7572G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time_median 20195094 ns 51817182 ns 5 bytes=536.871M bytes_per_second=24.7585G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time_stddev 10680 ns 211922 ns 5 bytes=0 bytes_per_second=13.4041M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):29/manual_time_cv 0.05 % 0.41 % 5 bytes=0.00% bytes_per_second=0.05% own_numa=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time 40506264 ns 104572818 ns 17 bytes=1073.74M bytes_per_second=24.6875G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time 40494556 ns 104617791 ns 17 bytes=1073.74M bytes_per_second=24.6947G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time 40568457 ns 104574649 ns 17 bytes=1073.74M bytes_per_second=24.6497G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time 40443347 ns 104469376 ns 17 bytes=1073.74M bytes_per_second=24.7259G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time 40510472 ns 104542268 ns 17 bytes=1073.74M bytes_per_second=24.685G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time_mean 40504619 ns 104555380 ns 5 bytes=1073.74M bytes_per_second=24.6886G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time_median 40506264 ns 104572818 ns 5 bytes=1073.74M bytes_per_second=24.6875G/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time_stddev 44631 ns 55089 ns 5 bytes=0 bytes_per_second=27.8543M/s own_numa=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrHost/0/0/log2(N):30/manual_time_cv 0.11 % 0.05 % 5 bytes=0.00% bytes_per_second=0.11% own_numa=-nan% wr_gpu=-nan% +[2023-10-10 13:20:13.674] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-10 13:20:13.674] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Tue 10 Oct 2023 01:20:13 PM EDT diff --git a/results/r2-1465529.out b/results/r2-1465529.out new file mode 100644 index 0000000..9303c9f --- /dev/null +++ b/results/r2-1465529.out @@ -0,0 +1,205 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 05:38:26 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:38:29.025] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:38:29.025] [scope] [info] recorded CPU goveror +[2023-10-09 17:38:29.025] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:38:29.025] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:38:31-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1790.37 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.63, 11.72, 27.46 +--------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +--------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time 13343 ns 20307 ns 52486 bytes=4.096k bytes_per_second=292.754M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time 13339 ns 20320 ns 52486 bytes=4.096k bytes_per_second=292.839M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time 13346 ns 20286 ns 52486 bytes=4.096k bytes_per_second=292.686M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time 13340 ns 20322 ns 52486 bytes=4.096k bytes_per_second=292.828M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time 13337 ns 20307 ns 52486 bytes=4.096k bytes_per_second=292.881M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time_mean 13341 ns 20308 ns 5 bytes=4.096k bytes_per_second=292.798M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time_median 13340 ns 20307 ns 5 bytes=4.096k bytes_per_second=292.828M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time_stddev 3.52 ns 14.4 ns 5 bytes=0 bytes_per_second=79.1263k/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time_cv 0.03 % 0.07 % 5 bytes=0.00% bytes_per_second=0.03% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time 13364 ns 20549 ns 52394 bytes=8.192k bytes_per_second=584.599M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time 13364 ns 20583 ns 52394 bytes=8.192k bytes_per_second=584.594M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time 13360 ns 20438 ns 52394 bytes=8.192k bytes_per_second=584.781M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time 13375 ns 20561 ns 52394 bytes=8.192k bytes_per_second=584.116M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time 13376 ns 20551 ns 52394 bytes=8.192k bytes_per_second=584.081M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time_mean 13368 ns 20536 ns 5 bytes=8.192k bytes_per_second=584.434M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time_median 13364 ns 20551 ns 5 bytes=8.192k bytes_per_second=584.594M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time_stddev 7.23 ns 56.9 ns 5 bytes=0 bytes_per_second=323.424k/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time_cv 0.05 % 0.28 % 5 bytes=0.00% bytes_per_second=0.05% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time 13414 ns 20582 ns 52192 bytes=16.384k bytes_per_second=1.13755G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time 13414 ns 20608 ns 52192 bytes=16.384k bytes_per_second=1.13753G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time 13415 ns 20661 ns 52192 bytes=16.384k bytes_per_second=1.13743G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time 13418 ns 20646 ns 52192 bytes=16.384k bytes_per_second=1.13715G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time 13417 ns 20611 ns 52192 bytes=16.384k bytes_per_second=1.13728G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time_mean 13416 ns 20621 ns 5 bytes=16.384k bytes_per_second=1.13739G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time_median 13415 ns 20611 ns 5 bytes=16.384k bytes_per_second=1.13743G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time_stddev 2.00 ns 31.6 ns 5 bytes=0 bytes_per_second=177.698k/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time_cv 0.01 % 0.15 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time 13712 ns 20765 ns 51044 bytes=32.768k bytes_per_second=2.22561G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time 13713 ns 20747 ns 51044 bytes=32.768k bytes_per_second=2.22553G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time 13711 ns 20774 ns 51044 bytes=32.768k bytes_per_second=2.22576G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time 13712 ns 20766 ns 51044 bytes=32.768k bytes_per_second=2.22565G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time 13719 ns 20776 ns 51044 bytes=32.768k bytes_per_second=2.22447G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time_mean 13713 ns 20765 ns 5 bytes=32.768k bytes_per_second=2.2254G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time_median 13712 ns 20766 ns 5 bytes=32.768k bytes_per_second=2.22561G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time_stddev 3.26 ns 11.4 ns 5 bytes=0 bytes_per_second=555.175k/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time_cv 0.02 % 0.05 % 5 bytes=0.00% bytes_per_second=0.02% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time 14221 ns 21575 ns 49230 bytes=65.536k bytes_per_second=4.29194G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time 14220 ns 21585 ns 49230 bytes=65.536k bytes_per_second=4.29207G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time 14221 ns 21592 ns 49230 bytes=65.536k bytes_per_second=4.29202G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time 14217 ns 21575 ns 49230 bytes=65.536k bytes_per_second=4.29306G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time 14219 ns 21583 ns 49230 bytes=65.536k bytes_per_second=4.29264G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time_mean 14220 ns 21582 ns 5 bytes=65.536k bytes_per_second=4.29235G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time_median 14220 ns 21583 ns 5 bytes=65.536k bytes_per_second=4.29207G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time_stddev 1.61 ns 7.31 ns 5 bytes=0 bytes_per_second=509.071k/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time_cv 0.01 % 0.03 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time 15265 ns 23268 ns 45881 bytes=131.072k bytes_per_second=7.99658G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time 15262 ns 23286 ns 45881 bytes=131.072k bytes_per_second=7.99819G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time 15260 ns 23283 ns 45881 bytes=131.072k bytes_per_second=7.99936G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time 15259 ns 23263 ns 45881 bytes=131.072k bytes_per_second=7.99971G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time 15262 ns 23259 ns 45881 bytes=131.072k bytes_per_second=7.99813G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time_mean 15262 ns 23272 ns 5 bytes=131.072k bytes_per_second=7.99839G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time_median 15262 ns 23268 ns 5 bytes=131.072k bytes_per_second=7.99819G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time_stddev 2.35 ns 12.0 ns 5 bytes=0 bytes_per_second=1.26005M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time_cv 0.02 % 0.05 % 5 bytes=0.00% bytes_per_second=0.02% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time 18885 ns 29051 ns 37054 bytes=262.144k bytes_per_second=12.9277G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time 18891 ns 29037 ns 37054 bytes=262.144k bytes_per_second=12.9236G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time 18892 ns 29067 ns 37054 bytes=262.144k bytes_per_second=12.9229G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time 18897 ns 29070 ns 37054 bytes=262.144k bytes_per_second=12.9193G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time 18892 ns 29060 ns 37054 bytes=262.144k bytes_per_second=12.923G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time_mean 18892 ns 29057 ns 5 bytes=262.144k bytes_per_second=12.9233G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time_median 18892 ns 29060 ns 5 bytes=262.144k bytes_per_second=12.923G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time_stddev 4.36 ns 13.4 ns 5 bytes=0 bytes_per_second=3.05332M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time_cv 0.02 % 0.05 % 5 bytes=0.00% bytes_per_second=0.02% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time 29304 ns 44704 ns 23894 bytes=524.288k bytes_per_second=16.6628G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time 29307 ns 44656 ns 23894 bytes=524.288k bytes_per_second=16.6606G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time 29308 ns 44666 ns 23894 bytes=524.288k bytes_per_second=16.6601G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time 29335 ns 44700 ns 23894 bytes=524.288k bytes_per_second=16.6453G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time 29327 ns 44659 ns 23894 bytes=524.288k bytes_per_second=16.6497G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time_mean 29316 ns 44677 ns 5 bytes=524.288k bytes_per_second=16.6557G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time_median 29308 ns 44666 ns 5 bytes=524.288k bytes_per_second=16.6601G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time_stddev 13.6 ns 23.1 ns 5 bytes=0 bytes_per_second=7.91632M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time_cv 0.05 % 0.05 % 5 bytes=0.00% bytes_per_second=0.05% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time 49890 ns 76844 ns 14029 bytes=1048.58k bytes_per_second=19.5744G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time 49892 ns 76832 ns 14029 bytes=1048.58k bytes_per_second=19.5733G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time 49905 ns 76819 ns 14029 bytes=1048.58k bytes_per_second=19.5686G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time 49901 ns 76789 ns 14029 bytes=1048.58k bytes_per_second=19.5702G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time 49887 ns 76854 ns 14029 bytes=1048.58k bytes_per_second=19.5754G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time_mean 49895 ns 76828 ns 5 bytes=1048.58k bytes_per_second=19.5724G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time_median 49892 ns 76832 ns 5 bytes=1048.58k bytes_per_second=19.5733G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time_stddev 7.41 ns 25.2 ns 5 bytes=0 bytes_per_second=2.97605M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time_cv 0.01 % 0.03 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time 91041 ns 132126 ns 7690 bytes=2.09715M bytes_per_second=21.4532G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time 91049 ns 132052 ns 7690 bytes=2.09715M bytes_per_second=21.4514G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time 91058 ns 132108 ns 7690 bytes=2.09715M bytes_per_second=21.4492G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time 91019 ns 132119 ns 7690 bytes=2.09715M bytes_per_second=21.4584G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time 91012 ns 132106 ns 7690 bytes=2.09715M bytes_per_second=21.4601G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time_mean 91036 ns 132102 ns 5 bytes=2.09715M bytes_per_second=21.4545G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time_median 91041 ns 132108 ns 5 bytes=2.09715M bytes_per_second=21.4532G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time_stddev 19.7 ns 29.3 ns 5 bytes=0 bytes_per_second=4.74509M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time_cv 0.02 % 0.02 % 5 bytes=0.00% bytes_per_second=0.02% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):22/manual_time 173187 ns 240365 ns 4041 bytes=4.1943M bytes_per_second=22.5552G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):22/manual_time 173202 ns 244088 ns 4041 bytes=4.1943M bytes_per_second=22.5532G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):22/manual_time 173198 ns 240340 ns 4041 bytes=4.1943M bytes_per_second=22.5537G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):22/manual_time 173189 ns 244174 ns 4041 bytes=4.1943M bytes_per_second=22.5548G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):22/manual_time 173191 ns 240632 ns 4041 bytes=4.1943M bytes_per_second=22.5546G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):22/manual_time_mean 173193 ns 241920 ns 5 bytes=4.1943M bytes_per_second=22.5543G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):22/manual_time_median 173191 ns 240632 ns 5 bytes=4.1943M bytes_per_second=22.5546G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):22/manual_time_stddev 6.23 ns 2022 ns 5 bytes=0 bytes_per_second=850.259k/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):22/manual_time_cv 0.00 % 0.84 % 5 bytes=0.00% bytes_per_second=0.00% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):23/manual_time 337221 ns 457941 ns 2076 bytes=8.38861M bytes_per_second=23.1673G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):23/manual_time 337320 ns 466865 ns 2076 bytes=8.38861M bytes_per_second=23.1605G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):23/manual_time 337234 ns 458136 ns 2076 bytes=8.38861M bytes_per_second=23.1664G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):23/manual_time 337195 ns 466960 ns 2076 bytes=8.38861M bytes_per_second=23.1691G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):23/manual_time 337215 ns 457882 ns 2076 bytes=8.38861M bytes_per_second=23.1677G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):23/manual_time_mean 337237 ns 461557 ns 5 bytes=8.38861M bytes_per_second=23.1662G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):23/manual_time_median 337221 ns 458136 ns 5 bytes=8.38861M bytes_per_second=23.1673G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):23/manual_time_stddev 48.5 ns 4890 ns 5 bytes=0 bytes_per_second=3.41177M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):23/manual_time_cv 0.01 % 1.06 % 5 bytes=0.00% bytes_per_second=0.01% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):24/manual_time 667902 ns 920301 ns 1048 bytes=16.7772M bytes_per_second=23.3941G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):24/manual_time 668092 ns 921196 ns 1048 bytes=16.7772M bytes_per_second=23.3875G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):24/manual_time 668197 ns 890874 ns 1048 bytes=16.7772M bytes_per_second=23.3838G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):24/manual_time 668325 ns 892868 ns 1048 bytes=16.7772M bytes_per_second=23.3794G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):24/manual_time 668204 ns 892911 ns 1048 bytes=16.7772M bytes_per_second=23.3836G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):24/manual_time_mean 668144 ns 903630 ns 5 bytes=16.7772M bytes_per_second=23.3857G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):24/manual_time_median 668197 ns 892911 ns 5 bytes=16.7772M bytes_per_second=23.3838G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):24/manual_time_stddev 158 ns 15652 ns 5 bytes=0 bytes_per_second=5.67175M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):24/manual_time_cv 0.02 % 1.73 % 5 bytes=0.00% bytes_per_second=0.02% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):25/manual_time 1332701 ns 2176061 ns 526 bytes=33.5544M bytes_per_second=23.4486G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):25/manual_time 1333410 ns 2178501 ns 526 bytes=33.5544M bytes_per_second=23.4362G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):25/manual_time 1334276 ns 2184553 ns 526 bytes=33.5544M bytes_per_second=23.4209G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):25/manual_time 1335126 ns 2186197 ns 526 bytes=33.5544M bytes_per_second=23.406G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):25/manual_time 1331949 ns 2184276 ns 526 bytes=33.5544M bytes_per_second=23.4619G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):25/manual_time_mean 1333492 ns 2181918 ns 5 bytes=33.5544M bytes_per_second=23.4347G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):25/manual_time_median 1333410 ns 2184276 ns 5 bytes=33.5544M bytes_per_second=23.4362G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):25/manual_time_stddev 1255 ns 4381 ns 5 bytes=0 bytes_per_second=22.5761M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):25/manual_time_cv 0.09 % 0.20 % 5 bytes=0.00% bytes_per_second=0.09% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):26/manual_time 2645934 ns 5587461 ns 264 bytes=67.1089M bytes_per_second=23.6212G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):26/manual_time 2650663 ns 5582103 ns 264 bytes=67.1089M bytes_per_second=23.579G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):26/manual_time 2650071 ns 5580277 ns 264 bytes=67.1089M bytes_per_second=23.5843G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):26/manual_time 2650805 ns 5566541 ns 264 bytes=67.1089M bytes_per_second=23.5777G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):26/manual_time 2651329 ns 5596130 ns 264 bytes=67.1089M bytes_per_second=23.5731G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):26/manual_time_mean 2649760 ns 5582502 ns 5 bytes=67.1089M bytes_per_second=23.5871G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):26/manual_time_median 2650663 ns 5582103 ns 5 bytes=67.1089M bytes_per_second=23.579G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):26/manual_time_stddev 2185 ns 10842 ns 5 bytes=0 bytes_per_second=19.9408M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):26/manual_time_cv 0.08 % 0.19 % 5 bytes=0.00% bytes_per_second=0.08% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):27/manual_time 5285898 ns 12190735 ns 132 bytes=134.218M bytes_per_second=23.6478G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):27/manual_time 5288189 ns 12202866 ns 132 bytes=134.218M bytes_per_second=23.6376G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):27/manual_time 5287321 ns 12205878 ns 132 bytes=134.218M bytes_per_second=23.6415G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):27/manual_time 5288423 ns 12222264 ns 132 bytes=134.218M bytes_per_second=23.6365G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):27/manual_time 5289445 ns 12195299 ns 132 bytes=134.218M bytes_per_second=23.632G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):27/manual_time_mean 5287855 ns 12203408 ns 5 bytes=134.218M bytes_per_second=23.6391G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):27/manual_time_median 5288189 ns 12202866 ns 5 bytes=134.218M bytes_per_second=23.6376G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):27/manual_time_stddev 1330 ns 12128 ns 5 bytes=0 bytes_per_second=6.08926M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):27/manual_time_cv 0.03 % 0.10 % 5 bytes=0.00% bytes_per_second=0.03% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):28/manual_time 10555864 ns 25612818 ns 66 bytes=268.435M bytes_per_second=23.6835G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):28/manual_time 10564164 ns 25615036 ns 66 bytes=268.435M bytes_per_second=23.6649G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):28/manual_time 10558644 ns 25611541 ns 66 bytes=268.435M bytes_per_second=23.6773G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):28/manual_time 10555842 ns 25569549 ns 66 bytes=268.435M bytes_per_second=23.6836G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):28/manual_time 10553476 ns 25571406 ns 66 bytes=268.435M bytes_per_second=23.6889G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):28/manual_time_mean 10557598 ns 25596070 ns 5 bytes=268.435M bytes_per_second=23.6796G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):28/manual_time_median 10555864 ns 25611541 ns 5 bytes=268.435M bytes_per_second=23.6835G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):28/manual_time_stddev 4102 ns 23405 ns 5 bytes=0 bytes_per_second=9.41773M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):28/manual_time_cv 0.04 % 0.09 % 5 bytes=0.00% bytes_per_second=0.04% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):29/manual_time 21266342 ns 52715657 ns 33 bytes=536.871M bytes_per_second=23.5113G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):29/manual_time 21188150 ns 52617560 ns 33 bytes=536.871M bytes_per_second=23.5981G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):29/manual_time 21201552 ns 52618082 ns 33 bytes=536.871M bytes_per_second=23.5832G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):29/manual_time 21234032 ns 52736683 ns 33 bytes=536.871M bytes_per_second=23.5471G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):29/manual_time 21229285 ns 52784332 ns 33 bytes=536.871M bytes_per_second=23.5524G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):29/manual_time_mean 21223872 ns 52694463 ns 5 bytes=536.871M bytes_per_second=23.5584G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):29/manual_time_median 21229285 ns 52715657 ns 5 bytes=536.871M bytes_per_second=23.5524G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):29/manual_time_stddev 30457 ns 74257 ns 5 bytes=0 bytes_per_second=34.6092M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):29/manual_time_cv 0.14 % 0.14 % 5 bytes=0.00% bytes_per_second=0.14% own_numa=-nan% rd_gpu=-nan% +Comm_implicit_mapped_GPURdHost/0/0/log2(N):30/manual_time 42643473 ns 106807451 ns 16 bytes=1073.74M bytes_per_second=23.4502G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):30/manual_time 42610013 ns 106744743 ns 16 bytes=1073.74M bytes_per_second=23.4687G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):30/manual_time 42571332 ns 105885869 ns 16 bytes=1073.74M bytes_per_second=23.49G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):30/manual_time 42586072 ns 105916378 ns 16 bytes=1073.74M bytes_per_second=23.4819G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):30/manual_time 42525032 ns 105853849 ns 16 bytes=1073.74M bytes_per_second=23.5156G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):30/manual_time_mean 42587185 ns 106241658 ns 5 bytes=1073.74M bytes_per_second=23.4813G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):30/manual_time_median 42586072 ns 105916378 ns 5 bytes=1073.74M bytes_per_second=23.4819G/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):30/manual_time_stddev 44173 ns 488878 ns 5 bytes=0 bytes_per_second=24.9443M/s own_numa=0 rd_gpu=0 +Comm_implicit_mapped_GPURdHost/0/0/log2(N):30/manual_time_cv 0.10 % 0.46 % 5 bytes=0.00% bytes_per_second=0.10% own_numa=-nan% rd_gpu=-nan% +[2023-10-09 17:40:37.256] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 17:40:37.256] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Mon 09 Oct 2023 05:40:37 PM EDT diff --git a/results/r3-1465530.out b/results/r3-1465530.out new file mode 100644 index 0000000..3ac778b --- /dev/null +++ b/results/r3-1465530.out @@ -0,0 +1,3371 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 05:38:26 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:38:26.952] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:38:26.953] [scope] [info] recorded CPU goveror +[2023-10-09 17:38:26.953] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:38:26.953] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:38:29-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1804.42 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.71, 11.70, 26.82 +-------------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +-------------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time 13400 ns 25680 ns 52237 bytes=4.096k bytes_per_second=291.505M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time 13399 ns 25717 ns 52237 bytes=4.096k bytes_per_second=291.528M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time 13398 ns 25488 ns 52237 bytes=4.096k bytes_per_second=291.563M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time 13400 ns 26014 ns 52237 bytes=4.096k bytes_per_second=291.502M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time 13398 ns 25690 ns 52237 bytes=4.096k bytes_per_second=291.545M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time_mean 13399 ns 25718 ns 5 bytes=4.096k bytes_per_second=291.528M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time_median 13399 ns 25690 ns 5 bytes=4.096k bytes_per_second=291.528M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time_stddev 1.20 ns 189 ns 5 bytes=0 bytes_per_second=26.6412k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time_cv 0.01 % 0.73 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time 13397 ns 25618 ns 52260 bytes=8.192k bytes_per_second=583.135M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time 13395 ns 25655 ns 52260 bytes=8.192k bytes_per_second=583.223M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time 13396 ns 25541 ns 52260 bytes=8.192k bytes_per_second=583.2M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time 13400 ns 25387 ns 52260 bytes=8.192k bytes_per_second=583.031M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time 13396 ns 25885 ns 52260 bytes=8.192k bytes_per_second=583.185M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time_mean 13397 ns 25617 ns 5 bytes=8.192k bytes_per_second=583.155M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time_median 13396 ns 25618 ns 5 bytes=8.192k bytes_per_second=583.185M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time_stddev 1.76 ns 182 ns 5 bytes=0 bytes_per_second=78.3979k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time_cv 0.01 % 0.71 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time 13394 ns 25673 ns 52260 bytes=16.384k bytes_per_second=1.13923G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time 13394 ns 25588 ns 52260 bytes=16.384k bytes_per_second=1.13924G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time 13398 ns 25601 ns 52260 bytes=16.384k bytes_per_second=1.13888G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time 13400 ns 25930 ns 52260 bytes=16.384k bytes_per_second=1.13873G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time 13399 ns 25854 ns 52260 bytes=16.384k bytes_per_second=1.13884G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time_mean 13397 ns 25729 ns 5 bytes=16.384k bytes_per_second=1.13898G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time_median 13398 ns 25673 ns 5 bytes=16.384k bytes_per_second=1.13888G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time_stddev 2.75 ns 154 ns 5 bytes=0 bytes_per_second=245.22k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time_cv 0.02 % 0.60 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time 13397 ns 25994 ns 52257 bytes=32.768k bytes_per_second=2.27802G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time 13396 ns 25723 ns 52257 bytes=32.768k bytes_per_second=2.27803G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time 13397 ns 25623 ns 52257 bytes=32.768k bytes_per_second=2.27799G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time 13395 ns 25829 ns 52257 bytes=32.768k bytes_per_second=2.27826G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time 13398 ns 26022 ns 52257 bytes=32.768k bytes_per_second=2.27784G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time_mean 13396 ns 25838 ns 5 bytes=32.768k bytes_per_second=2.27803G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time_median 13397 ns 25829 ns 5 bytes=32.768k bytes_per_second=2.27802G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time_stddev 0.892 ns 172 ns 5 bytes=0 bytes_per_second=159.058k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time_cv 0.01 % 0.66 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time 13396 ns 25979 ns 52254 bytes=65.536k bytes_per_second=4.55623G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time 13393 ns 26228 ns 52254 bytes=65.536k bytes_per_second=4.55722G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time 13395 ns 26269 ns 52254 bytes=65.536k bytes_per_second=4.55653G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time 13397 ns 25979 ns 52254 bytes=65.536k bytes_per_second=4.55605G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time 13396 ns 26183 ns 52254 bytes=65.536k bytes_per_second=4.55627G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time_mean 13395 ns 26128 ns 5 bytes=65.536k bytes_per_second=4.55646G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time_median 13396 ns 26183 ns 5 bytes=65.536k bytes_per_second=4.55627G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time_stddev 1.35 ns 139 ns 5 bytes=0 bytes_per_second=479.79k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time_cv 0.01 % 0.53 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time 13402 ns 26188 ns 52237 bytes=131.072k bytes_per_second=9.10821G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time 13401 ns 25993 ns 52237 bytes=131.072k bytes_per_second=9.10896G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time 13403 ns 26057 ns 52237 bytes=131.072k bytes_per_second=9.10801G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time 13402 ns 26069 ns 52237 bytes=131.072k bytes_per_second=9.10829G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time 13405 ns 26380 ns 52237 bytes=131.072k bytes_per_second=9.10638G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time_mean 13403 ns 26138 ns 5 bytes=131.072k bytes_per_second=9.10797G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time_median 13402 ns 26069 ns 5 bytes=131.072k bytes_per_second=9.10821G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time_stddev 1.41 ns 153 ns 5 bytes=0 bytes_per_second=1005.46k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time_cv 0.01 % 0.59 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time 13711 ns 26662 ns 51062 bytes=262.144k bytes_per_second=17.8066G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time 13710 ns 26623 ns 51062 bytes=262.144k bytes_per_second=17.8077G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time 13708 ns 26444 ns 51062 bytes=262.144k bytes_per_second=17.8104G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time 13707 ns 26339 ns 51062 bytes=262.144k bytes_per_second=17.8109G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time 13712 ns 26800 ns 51062 bytes=262.144k bytes_per_second=17.8045G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time_mean 13710 ns 26573 ns 5 bytes=262.144k bytes_per_second=17.808G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time_median 13710 ns 26623 ns 5 bytes=262.144k bytes_per_second=17.8077G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time_stddev 2.05 ns 182 ns 5 bytes=0 bytes_per_second=2.72654M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time_cv 0.01 % 0.69 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time 13758 ns 26994 ns 50898 bytes=524.288k bytes_per_second=35.4913G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time 13753 ns 26833 ns 50898 bytes=524.288k bytes_per_second=35.5028G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time 13757 ns 26644 ns 50898 bytes=524.288k bytes_per_second=35.4932G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time 13755 ns 26517 ns 50898 bytes=524.288k bytes_per_second=35.4973G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time 13758 ns 26889 ns 50898 bytes=524.288k bytes_per_second=35.49G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time_mean 13756 ns 26775 ns 5 bytes=524.288k bytes_per_second=35.4949G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time_median 13757 ns 26833 ns 5 bytes=524.288k bytes_per_second=35.4932G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time_stddev 2.00 ns 193 ns 5 bytes=0 bytes_per_second=5.29454M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time_cv 0.01 % 0.72 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time 13829 ns 26978 ns 50622 bytes=1048.58k bytes_per_second=70.6165G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time 13831 ns 26953 ns 50622 bytes=1048.58k bytes_per_second=70.6086G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time 13836 ns 26787 ns 50622 bytes=1048.58k bytes_per_second=70.5834G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time 13832 ns 27059 ns 50622 bytes=1048.58k bytes_per_second=70.601G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time 13835 ns 26816 ns 50622 bytes=1048.58k bytes_per_second=70.5863G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time_mean 13832 ns 26918 ns 5 bytes=1048.58k bytes_per_second=70.5992G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time_median 13832 ns 26953 ns 5 bytes=1048.58k bytes_per_second=70.601G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time_stddev 2.78 ns 114 ns 5 bytes=0 bytes_per_second=14.5377M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time_cv 0.02 % 0.43 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time 13985 ns 27057 ns 50043 bytes=2.09715M bytes_per_second=139.657G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time 13985 ns 27377 ns 50043 bytes=2.09715M bytes_per_second=139.655G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time 13989 ns 27544 ns 50043 bytes=2.09715M bytes_per_second=139.619G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time 13986 ns 27185 ns 50043 bytes=2.09715M bytes_per_second=139.653G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time 13990 ns 27349 ns 50043 bytes=2.09715M bytes_per_second=139.606G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time_mean 13987 ns 27302 ns 5 bytes=2.09715M bytes_per_second=139.638G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time_median 13986 ns 27349 ns 5 bytes=2.09715M bytes_per_second=139.653G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time_stddev 2.38 ns 187 ns 5 bytes=0 bytes_per_second=24.3374M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time_cv 0.02 % 0.69 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time 14037 ns 27440 ns 49877 bytes=4.1943M bytes_per_second=278.277G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time 14032 ns 27488 ns 49877 bytes=4.1943M bytes_per_second=278.39G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time 14039 ns 27423 ns 49877 bytes=4.1943M bytes_per_second=278.248G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time 14035 ns 27335 ns 49877 bytes=4.1943M bytes_per_second=278.325G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time 14033 ns 27481 ns 49877 bytes=4.1943M bytes_per_second=278.352G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time_mean 14035 ns 27434 ns 5 bytes=4.1943M bytes_per_second=278.318G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time_median 14035 ns 27440 ns 5 bytes=4.1943M bytes_per_second=278.325G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time_stddev 2.86 ns 61.5 ns 5 bytes=0 bytes_per_second=58.0562M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time_cv 0.02 % 0.22 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time 17553 ns 31276 ns 39809 bytes=8.38861M bytes_per_second=445.084G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time 17571 ns 31177 ns 39809 bytes=8.38861M bytes_per_second=444.625G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time 17617 ns 30848 ns 39809 bytes=8.38861M bytes_per_second=443.467G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time 17625 ns 30804 ns 39809 bytes=8.38861M bytes_per_second=443.258G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time 17567 ns 31204 ns 39809 bytes=8.38861M bytes_per_second=444.729G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time_mean 17587 ns 31062 ns 5 bytes=8.38861M bytes_per_second=444.233G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time_median 17571 ns 31177 ns 5 bytes=8.38861M bytes_per_second=444.625G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time_stddev 32.3 ns 219 ns 5 bytes=0 bytes_per_second=835.03M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time_cv 0.18 % 0.70 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time 25253 ns 39161 ns 27719 bytes=16.7772M bytes_per_second=618.726G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time 25249 ns 38985 ns 27719 bytes=16.7772M bytes_per_second=618.84G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time 25252 ns 38946 ns 27719 bytes=16.7772M bytes_per_second=618.756G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time 25251 ns 39112 ns 27719 bytes=16.7772M bytes_per_second=618.783G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time 25250 ns 39339 ns 27719 bytes=16.7772M bytes_per_second=618.821G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time_mean 25251 ns 39109 ns 5 bytes=16.7772M bytes_per_second=618.785G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time_median 25251 ns 39112 ns 5 bytes=16.7772M bytes_per_second=618.783G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time_stddev 1.90 ns 156 ns 5 bytes=0 bytes_per_second=47.6561M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time_cv 0.01 % 0.40 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time 44023 ns 58012 ns 15889 bytes=33.5544M bytes_per_second=709.863G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time 44032 ns 58388 ns 15889 bytes=33.5544M bytes_per_second=709.712G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time 44023 ns 58184 ns 15889 bytes=33.5544M bytes_per_second=709.849G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time 44038 ns 58001 ns 15889 bytes=33.5544M bytes_per_second=709.609G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time 44061 ns 58610 ns 15889 bytes=33.5544M bytes_per_second=709.238G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time_mean 44036 ns 58239 ns 5 bytes=33.5544M bytes_per_second=709.654G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time_median 44032 ns 58184 ns 5 bytes=33.5544M bytes_per_second=709.712G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time_stddev 15.8 ns 260 ns 5 bytes=0 bytes_per_second=261.209M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time_cv 0.04 % 0.45 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time 82637 ns 98081 ns 8470 bytes=67.1089M bytes_per_second=756.32G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time 82625 ns 97938 ns 8470 bytes=67.1089M bytes_per_second=756.425G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time 82650 ns 97902 ns 8470 bytes=67.1089M bytes_per_second=756.198G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time 82662 ns 97897 ns 8470 bytes=67.1089M bytes_per_second=756.088G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time 82630 ns 98184 ns 8470 bytes=67.1089M bytes_per_second=756.384G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time_mean 82641 ns 98000 ns 5 bytes=67.1089M bytes_per_second=756.283G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time_median 82637 ns 97938 ns 5 bytes=67.1089M bytes_per_second=756.32G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time_stddev 15.2 ns 127 ns 5 bytes=0 bytes_per_second=142.228M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time_cv 0.02 % 0.13 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time 158956 ns 177991 ns 4397 bytes=134.218M bytes_per_second=786.379G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time 158985 ns 178221 ns 4397 bytes=134.218M bytes_per_second=786.238G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time 159002 ns 178133 ns 4397 bytes=134.218M bytes_per_second=786.156G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time 158979 ns 178124 ns 4397 bytes=134.218M bytes_per_second=786.266G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time 158995 ns 178218 ns 4397 bytes=134.218M bytes_per_second=786.188G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time_mean 158983 ns 178137 ns 5 bytes=134.218M bytes_per_second=786.245G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time_median 158985 ns 178133 ns 5 bytes=134.218M bytes_per_second=786.238G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time_stddev 17.4 ns 93.7 ns 5 bytes=0 bytes_per_second=88.248M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time_cv 0.01 % 0.05 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time 316541 ns 353519 ns 2212 bytes=268.435M bytes_per_second=789.786G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time 315903 ns 353721 ns 2212 bytes=268.435M bytes_per_second=791.383G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time 316305 ns 353232 ns 2212 bytes=268.435M bytes_per_second=790.376G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time 316374 ns 353420 ns 2212 bytes=268.435M bytes_per_second=790.204G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time 316368 ns 353514 ns 2212 bytes=268.435M bytes_per_second=790.218G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time_mean 316298 ns 353481 ns 5 bytes=268.435M bytes_per_second=790.394G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time_median 316368 ns 353514 ns 5 bytes=268.435M bytes_per_second=790.218G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time_stddev 238 ns 177 ns 5 bytes=0 bytes_per_second=608.989M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time_cv 0.08 % 0.05 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time 628675 ns 720029 ns 1106 bytes=536.871M bytes_per_second=795.323G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time 633358 ns 725741 ns 1106 bytes=536.871M bytes_per_second=789.443G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time 629150 ns 720494 ns 1106 bytes=536.871M bytes_per_second=794.723G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time 632064 ns 723340 ns 1106 bytes=536.871M bytes_per_second=791.06G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time 629073 ns 719964 ns 1106 bytes=536.871M bytes_per_second=794.82G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time_mean 630464 ns 721913 ns 5 bytes=536.871M bytes_per_second=793.074G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time_median 629150 ns 720494 ns 5 bytes=536.871M bytes_per_second=794.723G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time_stddev 2109 ns 2552 ns 5 bytes=0 bytes_per_second=2.64912G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time_cv 0.33 % 0.35 % 5 bytes=0.00% bytes_per_second=0.33% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time 1309037 ns 1640040 ns 532 bytes=1073.74M bytes_per_second=763.92G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time 1311722 ns 1642855 ns 532 bytes=1073.74M bytes_per_second=762.357G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time 1312093 ns 1642599 ns 532 bytes=1073.74M bytes_per_second=762.141G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time 1310714 ns 1641882 ns 532 bytes=1073.74M bytes_per_second=762.943G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time 1312106 ns 1642940 ns 532 bytes=1073.74M bytes_per_second=762.134G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time_mean 1311134 ns 1642063 ns 5 bytes=1073.74M bytes_per_second=762.699G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time_median 1311722 ns 1642599 ns 5 bytes=1073.74M bytes_per_second=762.357G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time_stddev 1302 ns 1205 ns 5 bytes=0 bytes_per_second=776.334M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time_cv 0.10 % 0.07 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time 2284531 ns 2602421 ns 303 bytes=4.096k bytes_per_second=1.70987M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time 2272978 ns 2572171 ns 303 bytes=4.096k bytes_per_second=1.71856M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time 2267834 ns 2567509 ns 303 bytes=4.096k bytes_per_second=1.72246M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time 2274542 ns 2579910 ns 303 bytes=4.096k bytes_per_second=1.71738M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time 2268021 ns 2567761 ns 303 bytes=4.096k bytes_per_second=1.72232M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time_mean 2273581 ns 2577955 ns 5 bytes=4.096k bytes_per_second=1.71812M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time_median 2272978 ns 2572171 ns 5 bytes=4.096k bytes_per_second=1.71856M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time_stddev 6803 ns 14568 ns 5 bytes=0 bytes_per_second=5.25283k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time_cv 0.30 % 0.57 % 5 bytes=0.00% bytes_per_second=0.30% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time 2269404 ns 2582285 ns 308 bytes=8.192k bytes_per_second=3.44253M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time 2269138 ns 2571572 ns 308 bytes=8.192k bytes_per_second=3.44294M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time 2283397 ns 2585404 ns 308 bytes=8.192k bytes_per_second=3.42144M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time 2269379 ns 2571383 ns 308 bytes=8.192k bytes_per_second=3.44257M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time 2276535 ns 2578529 ns 308 bytes=8.192k bytes_per_second=3.43175M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time_mean 2273571 ns 2577835 ns 5 bytes=8.192k bytes_per_second=3.43625M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time_median 2269404 ns 2578529 ns 5 bytes=8.192k bytes_per_second=3.44253M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time_stddev 6323 ns 6293 ns 5 bytes=0 bytes_per_second=9.76627k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time_cv 0.28 % 0.24 % 5 bytes=0.00% bytes_per_second=0.28% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time 2275150 ns 2579695 ns 305 bytes=16.384k bytes_per_second=6.86768M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time 2283501 ns 2594473 ns 305 bytes=16.384k bytes_per_second=6.84256M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time 2274956 ns 2579472 ns 305 bytes=16.384k bytes_per_second=6.86826M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time 2276287 ns 2588749 ns 305 bytes=16.384k bytes_per_second=6.86425M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time 2281349 ns 2588035 ns 305 bytes=16.384k bytes_per_second=6.84902M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time_mean 2278249 ns 2586085 ns 5 bytes=16.384k bytes_per_second=6.85835M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time_median 2276287 ns 2588035 ns 5 bytes=16.384k bytes_per_second=6.86425M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time_stddev 3921 ns 6439 ns 5 bytes=0 bytes_per_second=12.0776k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time_cv 0.17 % 0.25 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time 2295304 ns 2603670 ns 306 bytes=32.768k bytes_per_second=13.6148M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time 2297588 ns 2606581 ns 306 bytes=32.768k bytes_per_second=13.6012M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time 2289724 ns 2604148 ns 306 bytes=32.768k bytes_per_second=13.6479M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time 2290140 ns 2603676 ns 306 bytes=32.768k bytes_per_second=13.6455M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time 2296482 ns 2605228 ns 306 bytes=32.768k bytes_per_second=13.6078M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time_mean 2293848 ns 2604661 ns 5 bytes=32.768k bytes_per_second=13.6234M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time_median 2295304 ns 2604148 ns 5 bytes=32.768k bytes_per_second=13.6148M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time_stddev 3667 ns 1247 ns 5 bytes=0 bytes_per_second=22.3118k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time_cv 0.16 % 0.05 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time 2326973 ns 2644625 ns 301 bytes=65.536k bytes_per_second=26.8589M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time 2320743 ns 2644843 ns 301 bytes=65.536k bytes_per_second=26.931M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time 2328795 ns 2646740 ns 301 bytes=65.536k bytes_per_second=26.8379M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time 2320238 ns 2637967 ns 301 bytes=65.536k bytes_per_second=26.9369M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time 2320695 ns 2649808 ns 301 bytes=65.536k bytes_per_second=26.9316M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time_mean 2323489 ns 2644796 ns 5 bytes=65.536k bytes_per_second=26.8993M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time_median 2320743 ns 2644843 ns 5 bytes=65.536k bytes_per_second=26.931M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time_stddev 4069 ns 4347 ns 5 bytes=0 bytes_per_second=48.1974k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time_cv 0.18 % 0.16 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time 2385886 ns 2724033 ns 294 bytes=131.072k bytes_per_second=52.3914M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time 2390554 ns 2728323 ns 294 bytes=131.072k bytes_per_second=52.2891M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time 2392318 ns 2729302 ns 294 bytes=131.072k bytes_per_second=52.2506M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time 2379944 ns 2717577 ns 294 bytes=131.072k bytes_per_second=52.5222M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time 2391110 ns 2729155 ns 294 bytes=131.072k bytes_per_second=52.277M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time_mean 2387962 ns 2725678 ns 5 bytes=131.072k bytes_per_second=52.3461M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time_median 2390554 ns 2728323 ns 5 bytes=131.072k bytes_per_second=52.2891M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time_stddev 5104 ns 5014 ns 5 bytes=0 bytes_per_second=114.749k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time_cv 0.21 % 0.18 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time 2498517 ns 2870203 ns 281 bytes=262.144k bytes_per_second=100.059M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time 2500823 ns 2868781 ns 281 bytes=262.144k bytes_per_second=99.9671M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time 2500937 ns 2867931 ns 281 bytes=262.144k bytes_per_second=99.9625M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time 2496497 ns 2870648 ns 281 bytes=262.144k bytes_per_second=100.14M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time 2495924 ns 2867709 ns 281 bytes=262.144k bytes_per_second=100.163M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time_mean 2498540 ns 2869054 ns 5 bytes=262.144k bytes_per_second=100.059M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time_median 2498517 ns 2868781 ns 5 bytes=262.144k bytes_per_second=100.059M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time_stddev 2344 ns 1323 ns 5 bytes=0 bytes_per_second=96.128k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time_cv 0.09 % 0.05 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time 2594169 ns 3029738 ns 269 bytes=524.288k bytes_per_second=192.74M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time 2598224 ns 3029981 ns 269 bytes=524.288k bytes_per_second=192.439M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time 2592473 ns 3027402 ns 269 bytes=524.288k bytes_per_second=192.866M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time 2593021 ns 3025747 ns 269 bytes=524.288k bytes_per_second=192.825M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time 2599286 ns 3031009 ns 269 bytes=524.288k bytes_per_second=192.361M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time_mean 2595435 ns 3028775 ns 5 bytes=524.288k bytes_per_second=192.646M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time_median 2594169 ns 3029738 ns 5 bytes=524.288k bytes_per_second=192.74M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time_stddev 3115 ns 2146 ns 5 bytes=0 bytes_per_second=236.66k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time_cv 0.12 % 0.07 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time 2758165 ns 3330966 ns 253 bytes=1048.58k bytes_per_second=362.56M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time 2753429 ns 3323645 ns 253 bytes=1048.58k bytes_per_second=363.183M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time 2749103 ns 3317934 ns 253 bytes=1048.58k bytes_per_second=363.755M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time 2752290 ns 3324641 ns 253 bytes=1048.58k bytes_per_second=363.334M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time 2754734 ns 3322930 ns 253 bytes=1048.58k bytes_per_second=363.011M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time_mean 2753544 ns 3324023 ns 5 bytes=1048.58k bytes_per_second=363.169M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time_median 2753429 ns 3323645 ns 5 bytes=1048.58k bytes_per_second=363.183M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time_stddev 3320 ns 4664 ns 5 bytes=0 bytes_per_second=448.296k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time_cv 0.12 % 0.14 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time 3076643 ns 3968108 ns 227 bytes=2.09715M bytes_per_second=650.059M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time 3077262 ns 3967129 ns 227 bytes=2.09715M bytes_per_second=649.928M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time 3078175 ns 3966573 ns 227 bytes=2.09715M bytes_per_second=649.736M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time 3078514 ns 3970379 ns 227 bytes=2.09715M bytes_per_second=649.664M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time 3072097 ns 3959459 ns 227 bytes=2.09715M bytes_per_second=651.021M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time_mean 3076538 ns 3966330 ns 5 bytes=2.09715M bytes_per_second=650.082M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time_median 3077262 ns 3967129 ns 5 bytes=2.09715M bytes_per_second=649.928M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time_stddev 2590 ns 4107 ns 5 bytes=0 bytes_per_second=561.011k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time_cv 0.08 % 0.10 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time 3607135 ns 5020979 ns 194 bytes=4.1943M bytes_per_second=1108.91M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time 3607989 ns 5021797 ns 194 bytes=4.1943M bytes_per_second=1108.65M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time 3608017 ns 5023325 ns 194 bytes=4.1943M bytes_per_second=1108.64M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time 3620641 ns 5032546 ns 194 bytes=4.1943M bytes_per_second=1104.78M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time 3601531 ns 5014547 ns 194 bytes=4.1943M bytes_per_second=1110.64M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time_mean 3609063 ns 5022639 ns 5 bytes=4.1943M bytes_per_second=1108.32M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time_median 3607989 ns 5021797 ns 5 bytes=4.1943M bytes_per_second=1108.65M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time_stddev 7013 ns 6472 ns 5 bytes=0 bytes_per_second=2.15033M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time_cv 0.19 % 0.13 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time 4897316 ns 7569045 ns 138 bytes=8.38861M bytes_per_second=1.59526G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time 4873739 ns 7530240 ns 138 bytes=8.38861M bytes_per_second=1.60298G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time 4930007 ns 7591243 ns 138 bytes=8.38861M bytes_per_second=1.58468G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time 4926117 ns 7588656 ns 138 bytes=8.38861M bytes_per_second=1.58593G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time 4925414 ns 7586260 ns 138 bytes=8.38861M bytes_per_second=1.58616G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time_mean 4910519 ns 7573089 ns 5 bytes=8.38861M bytes_per_second=1.591G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time_median 4925414 ns 7586260 ns 5 bytes=8.38861M bytes_per_second=1.58616G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time_stddev 24351 ns 25484 ns 5 bytes=0 bytes_per_second=8.10541M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time_cv 0.50 % 0.34 % 5 bytes=0.00% bytes_per_second=0.50% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time 7941534 ns 13688445 ns 88 bytes=16.7772M bytes_per_second=1.9675G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time 7944300 ns 13687479 ns 88 bytes=16.7772M bytes_per_second=1.96682G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time 7947611 ns 13689998 ns 88 bytes=16.7772M bytes_per_second=1.966G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time 7937929 ns 13695520 ns 88 bytes=16.7772M bytes_per_second=1.9684G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time 7954156 ns 13702766 ns 88 bytes=16.7772M bytes_per_second=1.96438G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time_mean 7945106 ns 13692842 ns 5 bytes=16.7772M bytes_per_second=1.96662G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time_median 7944300 ns 13689998 ns 5 bytes=16.7772M bytes_per_second=1.96682G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time_stddev 6187 ns 6361 ns 5 bytes=0 bytes_per_second=1.56768M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time_cv 0.08 % 0.05 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time 13573709 ns 25007327 ns 52 bytes=33.5544M bytes_per_second=2.30224G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time 13562875 ns 24994526 ns 52 bytes=33.5544M bytes_per_second=2.30408G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time 13582967 ns 25031431 ns 52 bytes=33.5544M bytes_per_second=2.30068G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time 13542524 ns 24968074 ns 52 bytes=33.5544M bytes_per_second=2.30755G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time 13551416 ns 24973335 ns 52 bytes=33.5544M bytes_per_second=2.30603G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time_mean 13562698 ns 24994938 ns 5 bytes=33.5544M bytes_per_second=2.30412G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time_median 13562875 ns 24994526 ns 5 bytes=33.5544M bytes_per_second=2.30408G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time_stddev 16328 ns 25854 ns 5 bytes=0 bytes_per_second=2.84045M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time_cv 0.12 % 0.10 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time 24621350 ns 47668974 ns 28 bytes=67.1089M bytes_per_second=2.53845G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time 24531674 ns 47665281 ns 28 bytes=67.1089M bytes_per_second=2.54773G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time 24622676 ns 47666441 ns 28 bytes=67.1089M bytes_per_second=2.53831G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time 24540257 ns 47663884 ns 28 bytes=67.1089M bytes_per_second=2.54684G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time 24669779 ns 47676848 ns 28 bytes=67.1089M bytes_per_second=2.53346G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time_mean 24597147 ns 47668285 ns 5 bytes=67.1089M bytes_per_second=2.54096G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time_median 24621350 ns 47666441 ns 5 bytes=67.1089M bytes_per_second=2.53845G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time_stddev 59237 ns 5138 ns 5 bytes=0 bytes_per_second=6.26716M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time_cv 0.24 % 0.01 % 5 bytes=0.00% bytes_per_second=0.24% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time 44960851 ns 87076806 ns 16 bytes=134.218M bytes_per_second=2.7802G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time 44936059 ns 86973259 ns 16 bytes=134.218M bytes_per_second=2.78173G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time 44920269 ns 86941317 ns 16 bytes=134.218M bytes_per_second=2.78271G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time 44870279 ns 86925118 ns 16 bytes=134.218M bytes_per_second=2.78581G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time 44915590 ns 86930256 ns 16 bytes=134.218M bytes_per_second=2.783G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time_mean 44920609 ns 86969351 ns 5 bytes=134.218M bytes_per_second=2.78269G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time_median 44920269 ns 86941317 ns 5 bytes=134.218M bytes_per_second=2.78271G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time_stddev 33228 ns 62914 ns 5 bytes=0 bytes_per_second=2.10842M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time_cv 0.07 % 0.07 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time 85369773 ns 164395389 ns 8 bytes=268.435M bytes_per_second=2.92844G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time 85412476 ns 164414446 ns 8 bytes=268.435M bytes_per_second=2.92697G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time 85332995 ns 164393016 ns 8 bytes=268.435M bytes_per_second=2.9297G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time 83763760 ns 160527454 ns 8 bytes=268.435M bytes_per_second=2.98458G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time 86012801 ns 164895070 ns 8 bytes=268.435M bytes_per_second=2.90654G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time_mean 85178361 ns 163725075 ns 5 bytes=268.435M bytes_per_second=2.93525G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time_median 85369773 ns 164395389 ns 5 bytes=268.435M bytes_per_second=2.92844G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time_stddev 838562 ns 1800303 ns 5 bytes=0 bytes_per_second=29.8705M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time_cv 0.98 % 1.10 % 5 bytes=0.00% bytes_per_second=0.99% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time 164054330 ns 307345730 ns 4 bytes=536.871M bytes_per_second=3.04777G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time 166857589 ns 311587251 ns 4 bytes=536.871M bytes_per_second=2.99657G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time 164082367 ns 307330973 ns 4 bytes=536.871M bytes_per_second=3.04725G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time 166881833 ns 311619056 ns 4 bytes=536.871M bytes_per_second=2.99613G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time 163721122 ns 306779760 ns 4 bytes=536.871M bytes_per_second=3.05397G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time_mean 165119448 ns 308932554 ns 5 bytes=536.871M bytes_per_second=3.02834G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time_median 164082367 ns 307345730 ns 5 bytes=536.871M bytes_per_second=3.04725G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time_stddev 1604094 ns 2448586 ns 5 bytes=0 bytes_per_second=30.0256M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time_cv 0.97 % 0.79 % 5 bytes=0.00% bytes_per_second=0.97% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time 319469914 ns 561971947 ns 2 bytes=1073.74M bytes_per_second=3.13019G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time 318752781 ns 561479664 ns 2 bytes=1073.74M bytes_per_second=3.13723G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time 318013579 ns 560534703 ns 2 bytes=1073.74M bytes_per_second=3.14452G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time 318740621 ns 560253275 ns 2 bytes=1073.74M bytes_per_second=3.13735G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time 319003046 ns 561240250 ns 2 bytes=1073.74M bytes_per_second=3.13477G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time_mean 318795988 ns 561095968 ns 5 bytes=1073.74M bytes_per_second=3.13681G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time_median 318752781 ns 561240250 ns 5 bytes=1073.74M bytes_per_second=3.13723G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time_stddev 527765 ns 700095 ns 5 bytes=0 bytes_per_second=5.32009M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time_cv 0.17 % 0.12 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time 2274040 ns 2580201 ns 308 bytes=4.096k bytes_per_second=1.71776M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time 2266479 ns 2572871 ns 308 bytes=4.096k bytes_per_second=1.72349M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time 2272294 ns 2585376 ns 308 bytes=4.096k bytes_per_second=1.71908M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time 2267049 ns 2573462 ns 308 bytes=4.096k bytes_per_second=1.72306M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time 2266642 ns 2579669 ns 308 bytes=4.096k bytes_per_second=1.72336M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time_mean 2269301 ns 2578316 ns 5 bytes=4.096k bytes_per_second=1.72135M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time_median 2267049 ns 2579669 ns 5 bytes=4.096k bytes_per_second=1.72306M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time_stddev 3589 ns 5207 ns 5 bytes=0 bytes_per_second=2.78577k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time_cv 0.16 % 0.20 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time 2268047 ns 2576712 ns 306 bytes=8.192k bytes_per_second=3.44459M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time 2268046 ns 2583807 ns 306 bytes=8.192k bytes_per_second=3.4446M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time 2275934 ns 2584483 ns 306 bytes=8.192k bytes_per_second=3.43266M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time 2267877 ns 2582659 ns 306 bytes=8.192k bytes_per_second=3.44485M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time 2267691 ns 2582691 ns 306 bytes=8.192k bytes_per_second=3.44513M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time_mean 2269519 ns 2582070 ns 5 bytes=8.192k bytes_per_second=3.44237M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time_median 2268046 ns 2582691 ns 5 bytes=8.192k bytes_per_second=3.4446M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time_stddev 3589 ns 3094 ns 5 bytes=0 bytes_per_second=5.56258k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time_cv 0.16 % 0.12 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time 2275563 ns 2595898 ns 308 bytes=16.384k bytes_per_second=6.86643M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time 2282218 ns 2593751 ns 308 bytes=16.384k bytes_per_second=6.84641M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time 2280558 ns 2592354 ns 308 bytes=16.384k bytes_per_second=6.85139M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time 2281448 ns 2593401 ns 308 bytes=16.384k bytes_per_second=6.84872M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time 2275085 ns 2587629 ns 308 bytes=16.384k bytes_per_second=6.86788M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time_mean 2278974 ns 2592607 ns 5 bytes=16.384k bytes_per_second=6.85617M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time_median 2280558 ns 2593401 ns 5 bytes=16.384k bytes_per_second=6.85139M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time_stddev 3388 ns 3067 ns 5 bytes=0 bytes_per_second=10.4415k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time_cv 0.15 % 0.12 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time 2288313 ns 2610191 ns 306 bytes=32.768k bytes_per_second=13.6563M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time 2288830 ns 2605549 ns 306 bytes=32.768k bytes_per_second=13.6533M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time 2294049 ns 2616789 ns 306 bytes=32.768k bytes_per_second=13.6222M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time 2289598 ns 2606134 ns 306 bytes=32.768k bytes_per_second=13.6487M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time 2302167 ns 2618392 ns 306 bytes=32.768k bytes_per_second=13.5742M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time_mean 2292591 ns 2611411 ns 5 bytes=32.768k bytes_per_second=13.6309M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time_median 2289598 ns 2610191 ns 5 bytes=32.768k bytes_per_second=13.6487M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time_stddev 5815 ns 5945 ns 5 bytes=0 bytes_per_second=35.319k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time_cv 0.25 % 0.23 % 5 bytes=0.00% bytes_per_second=0.25% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time 2324702 ns 2649460 ns 301 bytes=65.536k bytes_per_second=26.8852M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time 2326098 ns 2664488 ns 301 bytes=65.536k bytes_per_second=26.869M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time 2325110 ns 2649882 ns 301 bytes=65.536k bytes_per_second=26.8805M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time 2336336 ns 2661803 ns 301 bytes=65.536k bytes_per_second=26.7513M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time 2323838 ns 2648986 ns 301 bytes=65.536k bytes_per_second=26.8952M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time_mean 2327217 ns 2654924 ns 5 bytes=65.536k bytes_per_second=26.8562M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time_median 2325110 ns 2649882 ns 5 bytes=65.536k bytes_per_second=26.8805M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time_stddev 5162 ns 7572 ns 5 bytes=0 bytes_per_second=60.833k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time_cv 0.22 % 0.29 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time 2380208 ns 2738273 ns 294 bytes=131.072k bytes_per_second=52.5164M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time 2384662 ns 2730657 ns 294 bytes=131.072k bytes_per_second=52.4183M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time 2379563 ns 2731221 ns 294 bytes=131.072k bytes_per_second=52.5307M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time 2379414 ns 2729234 ns 294 bytes=131.072k bytes_per_second=52.534M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time 2372019 ns 2716287 ns 294 bytes=131.072k bytes_per_second=52.6977M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time_mean 2379173 ns 2729134 ns 5 bytes=131.072k bytes_per_second=52.5394M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time_median 2379563 ns 2730657 ns 5 bytes=131.072k bytes_per_second=52.5307M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time_stddev 4544 ns 7988 ns 5 bytes=0 bytes_per_second=102.861k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time_cv 0.19 % 0.29 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time 2499912 ns 2871799 ns 278 bytes=262.144k bytes_per_second=100.004M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time 2488708 ns 2869279 ns 278 bytes=262.144k bytes_per_second=100.454M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time 2488045 ns 2863428 ns 278 bytes=262.144k bytes_per_second=100.48M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time 2494890 ns 2866310 ns 278 bytes=262.144k bytes_per_second=100.205M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time 2495415 ns 2870562 ns 278 bytes=262.144k bytes_per_second=100.184M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time_mean 2493394 ns 2868275 ns 5 bytes=262.144k bytes_per_second=100.265M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time_median 2494890 ns 2869279 ns 5 bytes=262.144k bytes_per_second=100.205M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time_stddev 4984 ns 3392 ns 5 bytes=0 bytes_per_second=205.212k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time_cv 0.20 % 0.12 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time 2593168 ns 3037228 ns 270 bytes=524.288k bytes_per_second=192.814M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time 2594242 ns 3036746 ns 270 bytes=524.288k bytes_per_second=192.735M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time 2598374 ns 3042283 ns 270 bytes=524.288k bytes_per_second=192.428M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time 2591665 ns 3035634 ns 270 bytes=524.288k bytes_per_second=192.926M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time 2597954 ns 3037708 ns 270 bytes=524.288k bytes_per_second=192.459M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time_mean 2595081 ns 3037920 ns 5 bytes=524.288k bytes_per_second=192.672M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time_median 2594242 ns 3037228 ns 5 bytes=524.288k bytes_per_second=192.735M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time_stddev 2963 ns 2558 ns 5 bytes=0 bytes_per_second=225.273k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time_cv 0.11 % 0.08 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time 2759043 ns 3336589 ns 254 bytes=1048.58k bytes_per_second=362.445M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time 2752395 ns 3335781 ns 254 bytes=1048.58k bytes_per_second=363.32M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time 2755943 ns 3332587 ns 254 bytes=1048.58k bytes_per_second=362.852M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time 2755734 ns 3337096 ns 254 bytes=1048.58k bytes_per_second=362.88M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time 2753494 ns 3330582 ns 254 bytes=1048.58k bytes_per_second=363.175M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time_mean 2755322 ns 3334527 ns 5 bytes=1048.58k bytes_per_second=362.934M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time_median 2755734 ns 3335781 ns 5 bytes=1048.58k bytes_per_second=362.88M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time_stddev 2565 ns 2817 ns 5 bytes=0 bytes_per_second=345.81k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time_cv 0.09 % 0.08 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time 3087657 ns 3991850 ns 226 bytes=2.09715M bytes_per_second=647.74M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time 3093155 ns 4004935 ns 226 bytes=2.09715M bytes_per_second=646.589M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time 3093612 ns 4009856 ns 226 bytes=2.09715M bytes_per_second=646.493M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time 3089188 ns 3995028 ns 226 bytes=2.09715M bytes_per_second=647.419M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time 3082328 ns 3991520 ns 226 bytes=2.09715M bytes_per_second=648.86M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time_mean 3089188 ns 3998638 ns 5 bytes=2.09715M bytes_per_second=647.42M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time_median 3089188 ns 3995028 ns 5 bytes=2.09715M bytes_per_second=647.419M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time_stddev 4602 ns 8296 ns 5 bytes=0 bytes_per_second=988.3k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time_cv 0.15 % 0.21 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time 3615829 ns 5064337 ns 193 bytes=4.1943M bytes_per_second=1106.25M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time 3616670 ns 5066656 ns 193 bytes=4.1943M bytes_per_second=1105.99M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time 3621663 ns 5071656 ns 193 bytes=4.1943M bytes_per_second=1104.46M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time 3618404 ns 5069419 ns 193 bytes=4.1943M bytes_per_second=1105.46M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time 3616458 ns 5068056 ns 193 bytes=4.1943M bytes_per_second=1106.05M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time_mean 3617805 ns 5068025 ns 5 bytes=4.1943M bytes_per_second=1105.64M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time_median 3616670 ns 5068056 ns 5 bytes=4.1943M bytes_per_second=1105.99M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time_stddev 2359 ns 2766 ns 5 bytes=0 bytes_per_second=737.725k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time_cv 0.07 % 0.05 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time 5002696 ns 7724392 ns 142 bytes=8.38861M bytes_per_second=1.56166G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time 4991553 ns 7708992 ns 142 bytes=8.38861M bytes_per_second=1.56514G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time 4984268 ns 7709802 ns 142 bytes=8.38861M bytes_per_second=1.56743G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time 4986782 ns 7709694 ns 142 bytes=8.38861M bytes_per_second=1.56664G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time 4980660 ns 7708679 ns 142 bytes=8.38861M bytes_per_second=1.56857G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time_mean 4989192 ns 7712312 ns 5 bytes=8.38861M bytes_per_second=1.56589G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time_median 4986782 ns 7709694 ns 5 bytes=8.38861M bytes_per_second=1.56664G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time_stddev 8526 ns 6770 ns 5 bytes=0 bytes_per_second=2.73699M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time_cv 0.17 % 0.09 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time 7831014 ns 13328289 ns 87 bytes=16.7772M bytes_per_second=1.99527G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time 7914831 ns 13469970 ns 87 bytes=16.7772M bytes_per_second=1.97414G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time 7841171 ns 13342888 ns 87 bytes=16.7772M bytes_per_second=1.99269G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time 7950487 ns 13521041 ns 87 bytes=16.7772M bytes_per_second=1.96529G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time 7932011 ns 13509693 ns 87 bytes=16.7772M bytes_per_second=1.96987G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time_mean 7893903 ns 13434377 ns 5 bytes=16.7772M bytes_per_second=1.97945G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time_median 7914831 ns 13469970 ns 5 bytes=16.7772M bytes_per_second=1.97414G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time_stddev 54377 ns 92297 ns 5 bytes=0 bytes_per_second=13.9854M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time_cv 0.69 % 0.69 % 5 bytes=0.00% bytes_per_second=0.69% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time 13716290 ns 25098388 ns 51 bytes=33.5544M bytes_per_second=2.27831G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time 13791783 ns 25200691 ns 51 bytes=33.5544M bytes_per_second=2.26584G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time 13774895 ns 25180097 ns 51 bytes=33.5544M bytes_per_second=2.26862G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time 13759720 ns 25136026 ns 51 bytes=33.5544M bytes_per_second=2.27112G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time 13808495 ns 25239101 ns 51 bytes=33.5544M bytes_per_second=2.2631G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time_mean 13770237 ns 25170861 ns 5 bytes=33.5544M bytes_per_second=2.2694G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time_median 13774895 ns 25180097 ns 5 bytes=33.5544M bytes_per_second=2.26862G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time_stddev 35251 ns 54995 ns 5 bytes=0 bytes_per_second=5.95696M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time_cv 0.26 % 0.22 % 5 bytes=0.00% bytes_per_second=0.26% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time 24365937 ns 46527073 ns 28 bytes=67.1089M bytes_per_second=2.56506G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time 25414041 ns 48346264 ns 28 bytes=67.1089M bytes_per_second=2.45927G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time 25414927 ns 48319044 ns 28 bytes=67.1089M bytes_per_second=2.45918G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time 25380578 ns 48316446 ns 28 bytes=67.1089M bytes_per_second=2.46251G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time 25391928 ns 48314614 ns 28 bytes=67.1089M bytes_per_second=2.46141G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time_mean 25193482 ns 47964688 ns 5 bytes=67.1089M bytes_per_second=2.48149G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time_median 25391928 ns 48316446 ns 5 bytes=67.1089M bytes_per_second=2.46141G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time_stddev 462845 ns 803755 ns 5 bytes=0 bytes_per_second=47.8598M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time_cv 1.84 % 1.68 % 5 bytes=0.00% bytes_per_second=1.88% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time 45995108 ns 88087952 ns 15 bytes=134.218M bytes_per_second=2.71768G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time 45896399 ns 87993801 ns 15 bytes=134.218M bytes_per_second=2.72353G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time 46128624 ns 88201295 ns 15 bytes=134.218M bytes_per_second=2.70981G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time 46641982 ns 89244664 ns 15 bytes=134.218M bytes_per_second=2.67999G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time 46054172 ns 88226636 ns 15 bytes=134.218M bytes_per_second=2.71419G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time_mean 46143257 ns 88350869 ns 5 bytes=134.218M bytes_per_second=2.70904G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time_median 46054172 ns 88201295 ns 5 bytes=134.218M bytes_per_second=2.71419G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time_stddev 291446 ns 508257 ns 5 bytes=0 bytes_per_second=17.4051M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time_cv 0.63 % 0.58 % 5 bytes=0.00% bytes_per_second=0.63% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time 87171018 ns 166662013 ns 8 bytes=268.435M bytes_per_second=2.86793G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time 87379562 ns 166795975 ns 8 bytes=268.435M bytes_per_second=2.86108G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time 87991043 ns 168196632 ns 8 bytes=268.435M bytes_per_second=2.8412G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time 87203378 ns 166717861 ns 8 bytes=268.435M bytes_per_second=2.86686G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time 87428119 ns 166818616 ns 8 bytes=268.435M bytes_per_second=2.85949G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time_mean 87434624 ns 167038219 ns 5 bytes=268.435M bytes_per_second=2.85931G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time_median 87379562 ns 166795975 ns 5 bytes=268.435M bytes_per_second=2.86108G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time_stddev 330015 ns 650575 ns 5 bytes=0 bytes_per_second=11.0105M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time_cv 0.38 % 0.39 % 5 bytes=0.00% bytes_per_second=0.38% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time 169995282 ns 316367557 ns 4 bytes=536.871M bytes_per_second=2.94126G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time 169169199 ns 314052989 ns 4 bytes=536.871M bytes_per_second=2.95562G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time 169662800 ns 315761398 ns 4 bytes=536.871M bytes_per_second=2.94702G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time 169356197 ns 314383605 ns 4 bytes=536.871M bytes_per_second=2.95236G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time 169794075 ns 316181117 ns 4 bytes=536.871M bytes_per_second=2.94474G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time_mean 169595511 ns 315349333 ns 5 bytes=536.871M bytes_per_second=2.9482G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time_median 169662800 ns 315761398 ns 5 bytes=536.871M bytes_per_second=2.94702G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time_stddev 332711 ns 1062024 ns 5 bytes=0 bytes_per_second=5.92409M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time_cv 0.20 % 0.34 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time 323198453 ns 565369518 ns 2 bytes=1073.74M bytes_per_second=3.09407G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time 323012605 ns 564638978 ns 2 bytes=1073.74M bytes_per_second=3.09585G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time 322899982 ns 562709401 ns 2 bytes=1073.74M bytes_per_second=3.09693G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time 323243216 ns 564983268 ns 2 bytes=1073.74M bytes_per_second=3.09365G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time 323896155 ns 566227723 ns 2 bytes=1073.74M bytes_per_second=3.08741G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time_mean 323250082 ns 564785777 ns 5 bytes=1073.74M bytes_per_second=3.09358G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time_median 323198453 ns 564983268 ns 5 bytes=1073.74M bytes_per_second=3.09407G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time_stddev 387004 ns 1303059 ns 5 bytes=0 bytes_per_second=3.78844M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time_cv 0.12 % 0.23 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time 2261768 ns 2570605 ns 309 bytes=4.096k bytes_per_second=1.72708M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time 2261467 ns 2581637 ns 309 bytes=4.096k bytes_per_second=1.72731M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time 2261925 ns 2570976 ns 309 bytes=4.096k bytes_per_second=1.72696M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time 2261581 ns 2577281 ns 309 bytes=4.096k bytes_per_second=1.72722M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time 2262170 ns 2576697 ns 309 bytes=4.096k bytes_per_second=1.72677M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time_mean 2261782 ns 2575439 ns 5 bytes=4.096k bytes_per_second=1.72707M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time_median 2261768 ns 2576697 ns 5 bytes=4.096k bytes_per_second=1.72708M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time_stddev 279 ns 4655 ns 5 bytes=0 bytes_per_second=223.394/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time_cv 0.01 % 0.18 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time 2270691 ns 2582469 ns 309 bytes=8.192k bytes_per_second=3.44058M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time 2263514 ns 2582447 ns 309 bytes=8.192k bytes_per_second=3.45149M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time 2263116 ns 2581086 ns 309 bytes=8.192k bytes_per_second=3.4521M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time 2263630 ns 2581739 ns 309 bytes=8.192k bytes_per_second=3.45131M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time 2263296 ns 2581459 ns 309 bytes=8.192k bytes_per_second=3.45182M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time_mean 2264849 ns 2581840 ns 5 bytes=8.192k bytes_per_second=3.44946M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time_median 2263514 ns 2581739 ns 5 bytes=8.192k bytes_per_second=3.45149M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time_stddev 3272 ns 610 ns 5 bytes=0 bytes_per_second=5.09264k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time_cv 0.14 % 0.02 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time 2269840 ns 2589973 ns 308 bytes=16.384k bytes_per_second=6.88375M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time 2277644 ns 2592603 ns 308 bytes=16.384k bytes_per_second=6.86016M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time 2275511 ns 2589374 ns 308 bytes=16.384k bytes_per_second=6.86659M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time 2269890 ns 2589939 ns 308 bytes=16.384k bytes_per_second=6.88359M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time 2290342 ns 2604640 ns 308 bytes=16.384k bytes_per_second=6.82212M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time_mean 2276645 ns 2593306 ns 5 bytes=16.384k bytes_per_second=6.86324M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time_median 2275511 ns 2589973 ns 5 bytes=16.384k bytes_per_second=6.86659M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time_stddev 8394 ns 6459 ns 5 bytes=0 bytes_per_second=25.8341k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time_cv 0.37 % 0.25 % 5 bytes=0.00% bytes_per_second=0.37% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time 2289083 ns 2613346 ns 306 bytes=32.768k bytes_per_second=13.6518M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time 2296593 ns 2615402 ns 306 bytes=32.768k bytes_per_second=13.6071M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time 2294292 ns 2611950 ns 306 bytes=32.768k bytes_per_second=13.6208M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time 2287727 ns 2611546 ns 306 bytes=32.768k bytes_per_second=13.6598M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time 2288005 ns 2606142 ns 306 bytes=32.768k bytes_per_second=13.6582M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time_mean 2291140 ns 2611677 ns 5 bytes=32.768k bytes_per_second=13.6395M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time_median 2289083 ns 2611950 ns 5 bytes=32.768k bytes_per_second=13.6518M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time_stddev 4043 ns 3442 ns 5 bytes=0 bytes_per_second=24.6269k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time_cv 0.18 % 0.13 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time 2325195 ns 2651596 ns 302 bytes=65.536k bytes_per_second=26.8795M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time 2319457 ns 2654316 ns 302 bytes=65.536k bytes_per_second=26.946M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time 2319550 ns 2653472 ns 302 bytes=65.536k bytes_per_second=26.9449M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time 2318679 ns 2646521 ns 302 bytes=65.536k bytes_per_second=26.955M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time 2324264 ns 2651684 ns 302 bytes=65.536k bytes_per_second=26.8902M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time_mean 2321429 ns 2651518 ns 5 bytes=65.536k bytes_per_second=26.9231M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time_median 2319550 ns 2651684 ns 5 bytes=65.536k bytes_per_second=26.9449M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time_stddev 3050 ns 3027 ns 5 bytes=0 bytes_per_second=36.1995k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time_cv 0.13 % 0.11 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time 2391414 ns 2746199 ns 293 bytes=131.072k bytes_per_second=52.2703M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time 2399212 ns 2750811 ns 293 bytes=131.072k bytes_per_second=52.1004M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time 2389767 ns 2744808 ns 293 bytes=131.072k bytes_per_second=52.3063M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time 2392585 ns 2738755 ns 293 bytes=131.072k bytes_per_second=52.2448M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time 2387830 ns 2742982 ns 293 bytes=131.072k bytes_per_second=52.3488M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time_mean 2392162 ns 2744711 ns 5 bytes=131.072k bytes_per_second=52.2541M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time_median 2391414 ns 2744808 ns 5 bytes=131.072k bytes_per_second=52.2703M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time_stddev 4328 ns 4413 ns 5 bytes=0 bytes_per_second=96.6767k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time_cv 0.18 % 0.16 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time 2513043 ns 2888726 ns 280 bytes=262.144k bytes_per_second=99.481M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time 2509353 ns 2885469 ns 280 bytes=262.144k bytes_per_second=99.6273M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time 2504101 ns 2883038 ns 280 bytes=262.144k bytes_per_second=99.8362M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time 2503229 ns 2886717 ns 280 bytes=262.144k bytes_per_second=99.871M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time 2509024 ns 2884151 ns 280 bytes=262.144k bytes_per_second=99.6403M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time_mean 2507750 ns 2885620 ns 5 bytes=262.144k bytes_per_second=99.6912M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time_median 2509024 ns 2885469 ns 5 bytes=262.144k bytes_per_second=99.6403M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time_stddev 4061 ns 2219 ns 5 bytes=0 bytes_per_second=165.291k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time_cv 0.16 % 0.08 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time 2599885 ns 3054660 ns 269 bytes=524.288k bytes_per_second=192.316M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time 2592967 ns 3041232 ns 269 bytes=524.288k bytes_per_second=192.829M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time 2589438 ns 3042580 ns 269 bytes=524.288k bytes_per_second=193.092M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time 2594376 ns 3043262 ns 269 bytes=524.288k bytes_per_second=192.725M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time 2592879 ns 3048668 ns 269 bytes=524.288k bytes_per_second=192.836M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time_mean 2593909 ns 3046080 ns 5 bytes=524.288k bytes_per_second=192.76M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time_median 2592967 ns 3043262 ns 5 bytes=524.288k bytes_per_second=192.829M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time_stddev 3804 ns 5568 ns 5 bytes=0 bytes_per_second=289.206k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time_cv 0.15 % 0.18 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time 2754533 ns 3337176 ns 255 bytes=1048.58k bytes_per_second=363.038M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time 2746987 ns 3331738 ns 255 bytes=1048.58k bytes_per_second=364.035M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time 2750247 ns 3331691 ns 255 bytes=1048.58k bytes_per_second=363.604M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time 2749676 ns 3331283 ns 255 bytes=1048.58k bytes_per_second=363.679M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time 2758953 ns 3344405 ns 255 bytes=1048.58k bytes_per_second=362.456M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time_mean 2752079 ns 3335258 ns 5 bytes=1048.58k bytes_per_second=363.362M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time_median 2750247 ns 3331738 ns 5 bytes=1048.58k bytes_per_second=363.604M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time_stddev 4699 ns 5663 ns 5 bytes=0 bytes_per_second=634.856k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time_cv 0.17 % 0.17 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time 3088050 ns 3996010 ns 227 bytes=2.09715M bytes_per_second=647.658M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time 3087041 ns 3995248 ns 227 bytes=2.09715M bytes_per_second=647.87M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time 3081119 ns 3992209 ns 227 bytes=2.09715M bytes_per_second=649.115M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time 3084983 ns 3994238 ns 227 bytes=2.09715M bytes_per_second=648.302M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time 3088604 ns 3993610 ns 227 bytes=2.09715M bytes_per_second=647.542M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time_mean 3085959 ns 3994263 ns 5 bytes=2.09715M bytes_per_second=648.097M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time_median 3087041 ns 3994238 ns 5 bytes=2.09715M bytes_per_second=647.87M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time_stddev 3038 ns 1472 ns 5 bytes=0 bytes_per_second=653.754k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time_cv 0.10 % 0.04 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time 3613318 ns 5069486 ns 194 bytes=4.1943M bytes_per_second=1107.02M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time 3610548 ns 5068216 ns 194 bytes=4.1943M bytes_per_second=1107.87M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time 3611656 ns 5071001 ns 194 bytes=4.1943M bytes_per_second=1107.53M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time 3608568 ns 5067512 ns 194 bytes=4.1943M bytes_per_second=1108.47M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time 3613525 ns 5069360 ns 194 bytes=4.1943M bytes_per_second=1106.95M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time_mean 3611523 ns 5069115 ns 5 bytes=4.1943M bytes_per_second=1107.57M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time_median 3611656 ns 5069360 ns 5 bytes=4.1943M bytes_per_second=1107.53M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time_stddev 2058 ns 1336 ns 5 bytes=0 bytes_per_second=646.284k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time_cv 0.06 % 0.03 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time 4877599 ns 7592615 ns 143 bytes=8.38861M bytes_per_second=1.60171G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time 4922560 ns 7651189 ns 143 bytes=8.38861M bytes_per_second=1.58708G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time 4915686 ns 7643280 ns 143 bytes=8.38861M bytes_per_second=1.5893G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time 4901249 ns 7631627 ns 143 bytes=8.38861M bytes_per_second=1.59398G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time 4975879 ns 7728142 ns 143 bytes=8.38861M bytes_per_second=1.57007G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time_mean 4918595 ns 7649370 ns 5 bytes=8.38861M bytes_per_second=1.58843G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time_median 4915686 ns 7643280 ns 5 bytes=8.38861M bytes_per_second=1.5893G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time_stddev 36357 ns 49451 ns 5 bytes=0 bytes_per_second=11.9713M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time_cv 0.74 % 0.65 % 5 bytes=0.00% bytes_per_second=0.74% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time 7813982 ns 13315635 ns 87 bytes=16.7772M bytes_per_second=1.99962G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time 7881850 ns 13431383 ns 87 bytes=16.7772M bytes_per_second=1.9824G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time 7842080 ns 13356930 ns 87 bytes=16.7772M bytes_per_second=1.99246G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time 7055044 ns 12511515 ns 87 bytes=16.7772M bytes_per_second=2.21473G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time 7830825 ns 13351080 ns 87 bytes=16.7772M bytes_per_second=1.99532G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time_mean 7684756 ns 13193309 ns 5 bytes=16.7772M bytes_per_second=2.03691G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time_median 7830825 ns 13351080 ns 5 bytes=16.7772M bytes_per_second=1.99532G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time_stddev 352906 ns 383454 ns 5 bytes=0 bytes_per_second=101.998M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time_cv 4.59 % 2.91 % 5 bytes=0.00% bytes_per_second=4.89% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time 13754747 ns 25071100 ns 51 bytes=33.5544M bytes_per_second=2.27194G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time 13699989 ns 25015458 ns 51 bytes=33.5544M bytes_per_second=2.28102G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time 13709756 ns 25001318 ns 51 bytes=33.5544M bytes_per_second=2.2794G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time 13728401 ns 25014852 ns 51 bytes=33.5544M bytes_per_second=2.2763G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time 13730358 ns 25001229 ns 51 bytes=33.5544M bytes_per_second=2.27598G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time_mean 13724650 ns 25020791 ns 5 bytes=33.5544M bytes_per_second=2.27693G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time_median 13728401 ns 25014852 ns 5 bytes=33.5544M bytes_per_second=2.2763G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time_stddev 21110 ns 28968 ns 5 bytes=0 bytes_per_second=3.58484M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time_cv 0.15 % 0.12 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time 25303560 ns 48225034 ns 28 bytes=67.1089M bytes_per_second=2.47001G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time 25361098 ns 48305348 ns 28 bytes=67.1089M bytes_per_second=2.4644G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time 25523688 ns 48492951 ns 28 bytes=67.1089M bytes_per_second=2.44871G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time 25338338 ns 48275923 ns 28 bytes=67.1089M bytes_per_second=2.46662G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time 25271040 ns 48171337 ns 28 bytes=67.1089M bytes_per_second=2.47319G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time_mean 25359545 ns 48294119 ns 5 bytes=67.1089M bytes_per_second=2.46458G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time_median 25338338 ns 48275923 ns 5 bytes=67.1089M bytes_per_second=2.46662G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time_stddev 97932 ns 122311 ns 5 bytes=0 bytes_per_second=9.71069M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time_cv 0.39 % 0.25 % 5 bytes=0.00% bytes_per_second=0.38% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time 47390253 ns 90851349 ns 15 bytes=134.218M bytes_per_second=2.63767G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time 45897176 ns 88001413 ns 15 bytes=134.218M bytes_per_second=2.72348G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time 45885218 ns 88048881 ns 15 bytes=134.218M bytes_per_second=2.72419G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time 45887224 ns 87960076 ns 15 bytes=134.218M bytes_per_second=2.72407G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time 45881143 ns 88029466 ns 15 bytes=134.218M bytes_per_second=2.72443G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time_mean 46188203 ns 88578237 ns 5 bytes=134.218M bytes_per_second=2.70677G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time_median 45887224 ns 88029466 ns 5 bytes=134.218M bytes_per_second=2.72407G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time_stddev 671992 ns 1271147 ns 5 bytes=0 bytes_per_second=39.554M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time_cv 1.45 % 1.44 % 5 bytes=0.00% bytes_per_second=1.43% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time 87700657 ns 167083828 ns 8 bytes=268.435M bytes_per_second=2.85061G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time 87124892 ns 166629261 ns 8 bytes=268.435M bytes_per_second=2.86944G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time 87260894 ns 166612839 ns 8 bytes=268.435M bytes_per_second=2.86497G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time 87061014 ns 166631664 ns 8 bytes=268.435M bytes_per_second=2.87155G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time 87402154 ns 166992412 ns 8 bytes=268.435M bytes_per_second=2.86034G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time_mean 87309922 ns 166790001 ns 5 bytes=268.435M bytes_per_second=2.86338G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time_median 87260894 ns 166631664 ns 5 bytes=268.435M bytes_per_second=2.86497G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time_stddev 254841 ns 228910 ns 5 bytes=0 bytes_per_second=8.54378M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time_cv 0.29 % 0.14 % 5 bytes=0.00% bytes_per_second=0.29% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time 167871390 ns 311636356 ns 4 bytes=536.871M bytes_per_second=2.97847G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time 169642515 ns 316158740 ns 4 bytes=536.871M bytes_per_second=2.94737G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time 167382658 ns 310690124 ns 4 bytes=536.871M bytes_per_second=2.98717G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time 169636071 ns 316109243 ns 4 bytes=536.871M bytes_per_second=2.94749G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time 167487454 ns 311250457 ns 4 bytes=536.871M bytes_per_second=2.9853G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time_mean 168404017 ns 313168984 ns 5 bytes=536.871M bytes_per_second=2.96916G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time_median 167871390 ns 311636356 ns 5 bytes=536.871M bytes_per_second=2.97847G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time_stddev 1142234 ns 2727554 ns 5 bytes=0 bytes_per_second=20.5806M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time_cv 0.68 % 0.87 % 5 bytes=0.00% bytes_per_second=0.68% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time 321174592 ns 561116463 ns 2 bytes=1073.74M bytes_per_second=3.11357G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time 331717491 ns 573483711 ns 2 bytes=1073.74M bytes_per_second=3.01461G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time 321434110 ns 562517070 ns 2 bytes=1073.74M bytes_per_second=3.11106G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time 322596282 ns 564335945 ns 2 bytes=1073.74M bytes_per_second=3.09985G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time 324889094 ns 567411797 ns 2 bytes=1073.74M bytes_per_second=3.07797G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time_mean 324362314 ns 565772997 ns 5 bytes=1073.74M bytes_per_second=3.08341G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time_median 322596282 ns 564335945 ns 5 bytes=1073.74M bytes_per_second=3.09985G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time_stddev 4365517 ns 4911473 ns 5 bytes=0 bytes_per_second=41.9305M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time_cv 1.35 % 0.87 % 5 bytes=0.00% bytes_per_second=1.33% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time 2254206 ns 2566219 ns 310 bytes=4.096k bytes_per_second=1.73287M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time 2252404 ns 2565174 ns 310 bytes=4.096k bytes_per_second=1.73426M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time 2257900 ns 2577236 ns 310 bytes=4.096k bytes_per_second=1.73004M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time 2258129 ns 2572062 ns 310 bytes=4.096k bytes_per_second=1.72986M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time 2255663 ns 2575448 ns 310 bytes=4.096k bytes_per_second=1.73175M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time_mean 2255661 ns 2571228 ns 5 bytes=4.096k bytes_per_second=1.73176M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time_median 2255663 ns 2572062 ns 5 bytes=4.096k bytes_per_second=1.73175M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time_stddev 2441 ns 5393 ns 5 bytes=0 bytes_per_second=1.91922k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time_cv 0.11 % 0.21 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time 2255596 ns 2569797 ns 310 bytes=8.192k bytes_per_second=3.46361M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time 2258081 ns 2574005 ns 310 bytes=8.192k bytes_per_second=3.4598M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time 2258323 ns 2573596 ns 310 bytes=8.192k bytes_per_second=3.45942M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time 2257375 ns 2579061 ns 310 bytes=8.192k bytes_per_second=3.46088M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time 2262441 ns 2582647 ns 310 bytes=8.192k bytes_per_second=3.45313M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time_mean 2258363 ns 2575821 ns 5 bytes=8.192k bytes_per_second=3.45937M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time_median 2258081 ns 2574005 ns 5 bytes=8.192k bytes_per_second=3.4598M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time_stddev 2517 ns 5041 ns 5 bytes=0 bytes_per_second=3.94531k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time_cv 0.11 % 0.20 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time 2265075 ns 2589731 ns 309 bytes=16.384k bytes_per_second=6.89823M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time 2270035 ns 2595108 ns 309 bytes=16.384k bytes_per_second=6.88315M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time 2270275 ns 2589132 ns 309 bytes=16.384k bytes_per_second=6.88243M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time 2265186 ns 2589491 ns 309 bytes=16.384k bytes_per_second=6.89789M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time 2270879 ns 2595613 ns 309 bytes=16.384k bytes_per_second=6.88059M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time_mean 2268290 ns 2591815 ns 5 bytes=16.384k bytes_per_second=6.88846M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time_median 2270035 ns 2589731 ns 5 bytes=16.384k bytes_per_second=6.88315M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time_stddev 2901 ns 3248 ns 5 bytes=0 bytes_per_second=9.02558k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time_cv 0.13 % 0.13 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time 2284367 ns 2615079 ns 307 bytes=32.768k bytes_per_second=13.6799M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time 2289869 ns 2623144 ns 307 bytes=32.768k bytes_per_second=13.6471M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time 2288994 ns 2614184 ns 307 bytes=32.768k bytes_per_second=13.6523M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time 2287309 ns 2613696 ns 307 bytes=32.768k bytes_per_second=13.6623M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time 2285649 ns 2611194 ns 307 bytes=32.768k bytes_per_second=13.6723M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time_mean 2287238 ns 2615459 ns 5 bytes=32.768k bytes_per_second=13.6628M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time_median 2287309 ns 2614184 ns 5 bytes=32.768k bytes_per_second=13.6623M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time_stddev 2279 ns 4531 ns 5 bytes=0 bytes_per_second=13.9428k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time_cv 0.10 % 0.17 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time 2328633 ns 2669077 ns 302 bytes=65.536k bytes_per_second=26.8398M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time 2334854 ns 2671054 ns 302 bytes=65.536k bytes_per_second=26.7683M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time 2328515 ns 2669989 ns 302 bytes=65.536k bytes_per_second=26.8411M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time 2327317 ns 2667770 ns 302 bytes=65.536k bytes_per_second=26.855M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time 2320398 ns 2654819 ns 302 bytes=65.536k bytes_per_second=26.935M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time_mean 2327944 ns 2666542 ns 5 bytes=65.536k bytes_per_second=26.8478M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time_median 2328515 ns 2669077 ns 5 bytes=65.536k bytes_per_second=26.8411M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time_stddev 5145 ns 6663 ns 5 bytes=0 bytes_per_second=60.7864k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time_cv 0.22 % 0.25 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time 2390335 ns 2745405 ns 291 bytes=131.072k bytes_per_second=52.2939M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time 2391053 ns 2747029 ns 291 bytes=131.072k bytes_per_second=52.2782M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time 2390240 ns 2744795 ns 291 bytes=131.072k bytes_per_second=52.296M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time 2388221 ns 2743462 ns 291 bytes=131.072k bytes_per_second=52.3402M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time 2389444 ns 2744182 ns 291 bytes=131.072k bytes_per_second=52.3134M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time_mean 2389859 ns 2744974 ns 5 bytes=131.072k bytes_per_second=52.3044M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time_median 2390240 ns 2744795 ns 5 bytes=131.072k bytes_per_second=52.296M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time_stddev 1078 ns 1356 ns 5 bytes=0 bytes_per_second=24.1739k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time_cv 0.05 % 0.05 % 5 bytes=0.00% bytes_per_second=0.05% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time 2503336 ns 2884986 ns 279 bytes=262.144k bytes_per_second=99.8668M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time 2504104 ns 2893107 ns 279 bytes=262.144k bytes_per_second=99.8361M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time 2508528 ns 2889537 ns 279 bytes=262.144k bytes_per_second=99.66M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time 2503789 ns 2885234 ns 279 bytes=262.144k bytes_per_second=99.8487M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time 2509003 ns 2894582 ns 279 bytes=262.144k bytes_per_second=99.6412M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time_mean 2505752 ns 2889489 ns 5 bytes=262.144k bytes_per_second=99.7705M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time_median 2504104 ns 2889537 ns 5 bytes=262.144k bytes_per_second=99.8361M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time_stddev 2770 ns 4399 ns 5 bytes=0 bytes_per_second=112.882k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time_cv 0.11 % 0.15 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time 2599645 ns 3053370 ns 269 bytes=524.288k bytes_per_second=192.334M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time 2604726 ns 3062089 ns 269 bytes=524.288k bytes_per_second=191.959M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time 2601303 ns 3058076 ns 269 bytes=524.288k bytes_per_second=192.211M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time 2598644 ns 3052904 ns 269 bytes=524.288k bytes_per_second=192.408M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time 2604981 ns 3062070 ns 269 bytes=524.288k bytes_per_second=191.94M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time_mean 2601860 ns 3057702 ns 5 bytes=524.288k bytes_per_second=192.17M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time_median 2601303 ns 3058076 ns 5 bytes=524.288k bytes_per_second=192.211M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time_stddev 2894 ns 4479 ns 5 bytes=0 bytes_per_second=218.888k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time_cv 0.11 % 0.15 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time 2777686 ns 3364050 ns 252 bytes=1048.58k bytes_per_second=360.012M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time 2779466 ns 3369849 ns 252 bytes=1048.58k bytes_per_second=359.781M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time 2775243 ns 3360292 ns 252 bytes=1048.58k bytes_per_second=360.329M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time 2781929 ns 3373985 ns 252 bytes=1048.58k bytes_per_second=359.463M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time 2778525 ns 3364305 ns 252 bytes=1048.58k bytes_per_second=359.903M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time_mean 2778570 ns 3366496 ns 5 bytes=1048.58k bytes_per_second=359.898M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time_median 2778525 ns 3364305 ns 5 bytes=1048.58k bytes_per_second=359.903M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time_stddev 2446 ns 5399 ns 5 bytes=0 bytes_per_second=324.474k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time_cv 0.09 % 0.16 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time 3093070 ns 3961005 ns 226 bytes=2.09715M bytes_per_second=646.607M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time 3094284 ns 3964592 ns 226 bytes=2.09715M bytes_per_second=646.353M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time 3092936 ns 3961114 ns 226 bytes=2.09715M bytes_per_second=646.635M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time 3093819 ns 3962190 ns 226 bytes=2.09715M bytes_per_second=646.45M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time 3098419 ns 3967634 ns 226 bytes=2.09715M bytes_per_second=645.491M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time_mean 3094506 ns 3963307 ns 5 bytes=2.09715M bytes_per_second=646.307M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time_median 3093819 ns 3962190 ns 5 bytes=2.09715M bytes_per_second=646.45M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time_stddev 2256 ns 2817 ns 5 bytes=0 bytes_per_second=482.094k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time_cv 0.07 % 0.07 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time 3738047 ns 5203967 ns 187 bytes=4.1943M bytes_per_second=1070.08M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time 3749585 ns 5214239 ns 187 bytes=4.1943M bytes_per_second=1066.78M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time 3744368 ns 5205691 ns 187 bytes=4.1943M bytes_per_second=1068.27M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time 3747804 ns 5210548 ns 187 bytes=4.1943M bytes_per_second=1067.29M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time 3752807 ns 5221414 ns 187 bytes=4.1943M bytes_per_second=1065.87M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time_mean 3746522 ns 5211172 ns 5 bytes=4.1943M bytes_per_second=1067.66M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time_median 3747804 ns 5210548 ns 5 bytes=4.1943M bytes_per_second=1067.29M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time_stddev 5634 ns 7011 ns 5 bytes=0 bytes_per_second=1.60678M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time_cv 0.15 % 0.13 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time 5163327 ns 7941120 ns 135 bytes=8.38861M bytes_per_second=1.51307G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time 5197792 ns 7977532 ns 135 bytes=8.38861M bytes_per_second=1.50304G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time 5242067 ns 8037693 ns 135 bytes=8.38861M bytes_per_second=1.49035G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time 5231860 ns 8022536 ns 135 bytes=8.38861M bytes_per_second=1.49325G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time 5222954 ns 8015765 ns 135 bytes=8.38861M bytes_per_second=1.4958G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time_mean 5211600 ns 7998929 ns 5 bytes=8.38861M bytes_per_second=1.4991G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time_median 5222954 ns 8015765 ns 5 bytes=8.38861M bytes_per_second=1.4958G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time_stddev 31577 ns 39189 ns 5 bytes=0 bytes_per_second=9.33598M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time_cv 0.61 % 0.49 % 5 bytes=0.00% bytes_per_second=0.61% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time 8396388 ns 13894815 ns 83 bytes=16.7772M bytes_per_second=1.86092G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time 8388226 ns 13897942 ns 83 bytes=16.7772M bytes_per_second=1.86273G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time 8384257 ns 13892158 ns 83 bytes=16.7772M bytes_per_second=1.86361G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time 8386746 ns 13891750 ns 83 bytes=16.7772M bytes_per_second=1.86306G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time 8385227 ns 13884808 ns 83 bytes=16.7772M bytes_per_second=1.8634G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time_mean 8388169 ns 13892294 ns 5 bytes=16.7772M bytes_per_second=1.86274G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time_median 8386746 ns 13892158 ns 5 bytes=16.7772M bytes_per_second=1.86306G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time_stddev 4836 ns 4863 ns 5 bytes=0 bytes_per_second=1125.41k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time_cv 0.06 % 0.04 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time 14495957 ns 25256759 ns 49 bytes=33.5544M bytes_per_second=2.15577G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time 14498311 ns 25366690 ns 49 bytes=33.5544M bytes_per_second=2.15542G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time 14465939 ns 25235227 ns 49 bytes=33.5544M bytes_per_second=2.16025G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time 14560329 ns 25339594 ns 49 bytes=33.5544M bytes_per_second=2.14624G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time 14462256 ns 25264583 ns 49 bytes=33.5544M bytes_per_second=2.1608G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time_mean 14496558 ns 25292571 ns 5 bytes=33.5544M bytes_per_second=2.1557G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time_median 14495957 ns 25264583 ns 5 bytes=33.5544M bytes_per_second=2.15577G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time_stddev 39321 ns 57138 ns 5 bytes=0 bytes_per_second=5.97481M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time_cv 0.27 % 0.23 % 5 bytes=0.00% bytes_per_second=0.27% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time 26530710 ns 48406277 ns 26 bytes=67.1089M bytes_per_second=2.35576G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time 26494082 ns 48389187 ns 26 bytes=67.1089M bytes_per_second=2.35902G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time 26550679 ns 48444927 ns 26 bytes=67.1089M bytes_per_second=2.35399G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time 26658691 ns 47656928 ns 26 bytes=67.1089M bytes_per_second=2.34445G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time 26465848 ns 48301826 ns 26 bytes=67.1089M bytes_per_second=2.36153G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time_mean 26540002 ns 48239829 ns 5 bytes=67.1089M bytes_per_second=2.35495G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time_median 26530710 ns 48389187 ns 5 bytes=67.1089M bytes_per_second=2.35576G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time_stddev 73985 ns 330036 ns 5 bytes=0 bytes_per_second=6.70894M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time_cv 0.28 % 0.68 % 5 bytes=0.00% bytes_per_second=0.28% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time 49641674 ns 90888550 ns 14 bytes=134.218M bytes_per_second=2.51805G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time 49753001 ns 90975493 ns 14 bytes=134.218M bytes_per_second=2.51241G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time 49677435 ns 90872035 ns 14 bytes=134.218M bytes_per_second=2.51623G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time 49670429 ns 90821018 ns 14 bytes=134.218M bytes_per_second=2.51659G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time 49700406 ns 90955455 ns 14 bytes=134.218M bytes_per_second=2.51507G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time_mean 49688589 ns 90902510 ns 5 bytes=134.218M bytes_per_second=2.51567G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time_median 49677435 ns 90888550 ns 5 bytes=134.218M bytes_per_second=2.51623G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time_stddev 41664 ns 63036 ns 5 bytes=0 bytes_per_second=2.15905M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time_cv 0.08 % 0.07 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time 95877393 ns 174135664 ns 7 bytes=268.435M bytes_per_second=2.6075G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time 95755476 ns 173771575 ns 7 bytes=268.435M bytes_per_second=2.61082G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time 95719883 ns 173741882 ns 7 bytes=268.435M bytes_per_second=2.61179G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time 96875709 ns 174619895 ns 7 bytes=268.435M bytes_per_second=2.58063G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time 95787453 ns 173931036 ns 7 bytes=268.435M bytes_per_second=2.60995G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time_mean 96003183 ns 174040010 ns 5 bytes=268.435M bytes_per_second=2.60413G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time_median 95787453 ns 173931036 ns 5 bytes=268.435M bytes_per_second=2.60995G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time_stddev 491244 ns 359941 ns 5 bytes=0 bytes_per_second=13.5552M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time_cv 0.51 % 0.21 % 5 bytes=0.00% bytes_per_second=0.51% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time 186343390 ns 329948624 ns 4 bytes=536.871M bytes_per_second=2.68322G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time 187819880 ns 333740296 ns 4 bytes=536.871M bytes_per_second=2.66213G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time 185864951 ns 330722645 ns 4 bytes=536.871M bytes_per_second=2.69013G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time 187808804 ns 333836464 ns 4 bytes=536.871M bytes_per_second=2.66228G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time 186303355 ns 330645483 ns 4 bytes=536.871M bytes_per_second=2.68379G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time_mean 186828076 ns 331778702 ns 5 bytes=536.871M bytes_per_second=2.67631G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time_median 186343390 ns 330722645 ns 5 bytes=536.871M bytes_per_second=2.68322G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time_stddev 919696 ns 1859493 ns 5 bytes=0 bytes_per_second=13.4745M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time_cv 0.49 % 0.56 % 5 bytes=0.00% bytes_per_second=0.49% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time 359908193 ns 602648722 ns 2 bytes=1073.74M bytes_per_second=2.77849G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time 361906424 ns 605538395 ns 2 bytes=1073.74M bytes_per_second=2.76315G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time 361000583 ns 603736441 ns 2 bytes=1073.74M bytes_per_second=2.77008G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time 360768914 ns 603574287 ns 2 bytes=1073.74M bytes_per_second=2.77186G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time 360041499 ns 603587802 ns 2 bytes=1073.74M bytes_per_second=2.77746G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time_mean 360725123 ns 603817129 ns 5 bytes=1073.74M bytes_per_second=2.77221G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time_median 360768914 ns 603587802 ns 5 bytes=1073.74M bytes_per_second=2.77186G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time_stddev 807463 ns 1054278 ns 5 bytes=0 bytes_per_second=6.34895M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time_cv 0.22 % 0.17 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time 2253929 ns 2576678 ns 310 bytes=4.096k bytes_per_second=1.73308M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time 2253785 ns 2577316 ns 310 bytes=4.096k bytes_per_second=1.7332M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time 2253830 ns 2578916 ns 310 bytes=4.096k bytes_per_second=1.73316M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time 2259719 ns 2578920 ns 310 bytes=4.096k bytes_per_second=1.72864M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time 2260338 ns 2579735 ns 310 bytes=4.096k bytes_per_second=1.72817M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time_mean 2256320 ns 2578313 ns 5 bytes=4.096k bytes_per_second=1.73125M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time_median 2253929 ns 2578916 ns 5 bytes=4.096k bytes_per_second=1.73308M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time_stddev 3393 ns 1267 ns 5 bytes=0 bytes_per_second=2.6641k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time_cv 0.15 % 0.05 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time 2259736 ns 2579762 ns 311 bytes=8.192k bytes_per_second=3.45726M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time 2254359 ns 2580964 ns 311 bytes=8.192k bytes_per_second=3.46551M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time 2259583 ns 2581788 ns 311 bytes=8.192k bytes_per_second=3.4575M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time 2254950 ns 2580589 ns 311 bytes=8.192k bytes_per_second=3.4646M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time 2253673 ns 2579730 ns 311 bytes=8.192k bytes_per_second=3.46656M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time_mean 2256460 ns 2580567 ns 5 bytes=8.192k bytes_per_second=3.46229M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time_median 2254950 ns 2580589 ns 5 bytes=8.192k bytes_per_second=3.4646M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time_stddev 2956 ns 866 ns 5 bytes=0 bytes_per_second=4.64234k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time_cv 0.13 % 0.03 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time 2269860 ns 2593784 ns 309 bytes=16.384k bytes_per_second=6.88368M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time 2265956 ns 2597094 ns 309 bytes=16.384k bytes_per_second=6.89554M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time 2263733 ns 2587333 ns 309 bytes=16.384k bytes_per_second=6.90232M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time 2265877 ns 2602342 ns 309 bytes=16.384k bytes_per_second=6.89579M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time 2263726 ns 2588222 ns 309 bytes=16.384k bytes_per_second=6.90234M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time_mean 2265830 ns 2593755 ns 5 bytes=16.384k bytes_per_second=6.89593M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time_median 2265877 ns 2593784 ns 5 bytes=16.384k bytes_per_second=6.89579M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time_stddev 2504 ns 6260 ns 5 bytes=0 bytes_per_second=7.7981k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time_cv 0.11 % 0.24 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time 2276045 ns 2608637 ns 308 bytes=32.768k bytes_per_second=13.73M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time 2275977 ns 2603103 ns 308 bytes=32.768k bytes_per_second=13.7304M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time 2287005 ns 2614009 ns 308 bytes=32.768k bytes_per_second=13.6642M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time 2275613 ns 2602271 ns 308 bytes=32.768k bytes_per_second=13.7326M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time 2281461 ns 2614745 ns 308 bytes=32.768k bytes_per_second=13.6974M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time_mean 2279220 ns 2608553 ns 5 bytes=32.768k bytes_per_second=13.7109M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time_median 2276045 ns 2608637 ns 5 bytes=32.768k bytes_per_second=13.73M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time_stddev 4981 ns 5858 ns 5 bytes=0 bytes_per_second=30.6309k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time_cv 0.22 % 0.22 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time 2308536 ns 2644846 ns 303 bytes=65.536k bytes_per_second=27.0734M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time 2314445 ns 2657251 ns 303 bytes=65.536k bytes_per_second=27.0043M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time 2307740 ns 2643829 ns 303 bytes=65.536k bytes_per_second=27.0828M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time 2315592 ns 2651607 ns 303 bytes=65.536k bytes_per_second=26.9909M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time 2316345 ns 2652468 ns 303 bytes=65.536k bytes_per_second=26.9822M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time_mean 2312532 ns 2650000 ns 5 bytes=65.536k bytes_per_second=27.0267M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time_median 2314445 ns 2651607 ns 5 bytes=65.536k bytes_per_second=27.0043M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time_stddev 4077 ns 5610 ns 5 bytes=0 bytes_per_second=48.8231k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time_cv 0.18 % 0.21 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time 2380970 ns 2735089 ns 296 bytes=131.072k bytes_per_second=52.4996M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time 2371062 ns 2726073 ns 296 bytes=131.072k bytes_per_second=52.719M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time 2371502 ns 2726087 ns 296 bytes=131.072k bytes_per_second=52.7092M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time 2370401 ns 2724820 ns 296 bytes=131.072k bytes_per_second=52.7337M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time 2369979 ns 2724233 ns 296 bytes=131.072k bytes_per_second=52.7431M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time_mean 2372783 ns 2727260 ns 5 bytes=131.072k bytes_per_second=52.6809M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time_median 2371062 ns 2726073 ns 5 bytes=131.072k bytes_per_second=52.719M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time_stddev 4614 ns 4449 ns 5 bytes=0 bytes_per_second=104.647k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time_cv 0.19 % 0.16 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time 2498285 ns 2891512 ns 278 bytes=262.144k bytes_per_second=100.069M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time 2497348 ns 2894231 ns 278 bytes=262.144k bytes_per_second=100.106M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time 2497323 ns 2890425 ns 278 bytes=262.144k bytes_per_second=100.107M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time 2502921 ns 2892296 ns 278 bytes=262.144k bytes_per_second=99.8833M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time 2505704 ns 2895216 ns 278 bytes=262.144k bytes_per_second=99.7724M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time_mean 2500316 ns 2892736 ns 5 bytes=262.144k bytes_per_second=99.9875M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time_median 2498285 ns 2892296 ns 5 bytes=262.144k bytes_per_second=100.069M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time_stddev 3798 ns 1963 ns 5 bytes=0 bytes_per_second=155.42k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time_cv 0.15 % 0.07 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time 2586750 ns 3047219 ns 271 bytes=524.288k bytes_per_second=193.293M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time 2594689 ns 3053842 ns 271 bytes=524.288k bytes_per_second=192.701M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time 2588440 ns 3046706 ns 271 bytes=524.288k bytes_per_second=193.167M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time 2590980 ns 3048527 ns 271 bytes=524.288k bytes_per_second=192.977M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time 2587261 ns 3047948 ns 271 bytes=524.288k bytes_per_second=193.255M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time_mean 2589624 ns 3048848 ns 5 bytes=524.288k bytes_per_second=193.078M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time_median 2588440 ns 3047948 ns 5 bytes=524.288k bytes_per_second=193.167M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time_stddev 3269 ns 2877 ns 5 bytes=0 bytes_per_second=249.341k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time_cv 0.13 % 0.09 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time 2748437 ns 3337993 ns 254 bytes=1048.58k bytes_per_second=363.843M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time 2747678 ns 3341615 ns 254 bytes=1048.58k bytes_per_second=363.944M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time 2747733 ns 3351459 ns 254 bytes=1048.58k bytes_per_second=363.936M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time 2745098 ns 3340402 ns 254 bytes=1048.58k bytes_per_second=364.286M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time 2745598 ns 3336337 ns 254 bytes=1048.58k bytes_per_second=364.219M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time_mean 2746909 ns 3341561 ns 5 bytes=1048.58k bytes_per_second=364.046M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time_median 2747678 ns 3340402 ns 5 bytes=1048.58k bytes_per_second=363.944M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time_stddev 1467 ns 5902 ns 5 bytes=0 bytes_per_second=199.055k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time_cv 0.05 % 0.18 % 5 bytes=0.00% bytes_per_second=0.05% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time 3079455 ns 3996119 ns 227 bytes=2.09715M bytes_per_second=649.466M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time 3087282 ns 4014223 ns 227 bytes=2.09715M bytes_per_second=647.819M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time 3088597 ns 4001468 ns 227 bytes=2.09715M bytes_per_second=647.543M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time 3079694 ns 4003444 ns 227 bytes=2.09715M bytes_per_second=649.415M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time 3071278 ns 3981113 ns 227 bytes=2.09715M bytes_per_second=651.195M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time_mean 3081261 ns 3999274 ns 5 bytes=2.09715M bytes_per_second=649.088M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time_median 3079694 ns 4001468 ns 5 bytes=2.09715M bytes_per_second=649.415M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time_stddev 6990 ns 12098 ns 5 bytes=0 bytes_per_second=1.47345M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time_cv 0.23 % 0.30 % 5 bytes=0.00% bytes_per_second=0.23% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time 3610114 ns 5082629 ns 194 bytes=4.1943M bytes_per_second=1108M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time 3602507 ns 5076266 ns 194 bytes=4.1943M bytes_per_second=1110.34M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time 3597935 ns 5062697 ns 194 bytes=4.1943M bytes_per_second=1111.75M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time 3592571 ns 5056894 ns 194 bytes=4.1943M bytes_per_second=1113.41M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time 3590982 ns 5053999 ns 194 bytes=4.1943M bytes_per_second=1113.9M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time_mean 3598822 ns 5066497 ns 5 bytes=4.1943M bytes_per_second=1111.48M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time_median 3597935 ns 5062697 ns 5 bytes=4.1943M bytes_per_second=1111.75M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time_stddev 7785 ns 12435 ns 5 bytes=0 bytes_per_second=2.40221M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time_cv 0.22 % 0.25 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time 4849675 ns 7525941 ns 144 bytes=8.38861M bytes_per_second=1.61093G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time 4898330 ns 7584530 ns 144 bytes=8.38861M bytes_per_second=1.59493G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time 4898848 ns 7588343 ns 144 bytes=8.38861M bytes_per_second=1.59476G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time 4883862 ns 7573556 ns 144 bytes=8.38861M bytes_per_second=1.59966G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time 4953204 ns 7671835 ns 144 bytes=8.38861M bytes_per_second=1.57726G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time_mean 4896784 ns 7588841 ns 5 bytes=8.38861M bytes_per_second=1.59551G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time_median 4898330 ns 7584530 ns 5 bytes=8.38861M bytes_per_second=1.59493G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time_stddev 37337 ns 52671 ns 5 bytes=0 bytes_per_second=12.4252M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time_cv 0.76 % 0.69 % 5 bytes=0.00% bytes_per_second=0.76% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time 7812245 ns 13323578 ns 88 bytes=16.7772M bytes_per_second=2.00007G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time 7853111 ns 13388211 ns 88 bytes=16.7772M bytes_per_second=1.98966G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time 7848842 ns 13386185 ns 88 bytes=16.7772M bytes_per_second=1.99074G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time 7831858 ns 13347926 ns 88 bytes=16.7772M bytes_per_second=1.99506G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time 7828471 ns 13346577 ns 88 bytes=16.7772M bytes_per_second=1.99592G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time_mean 7834905 ns 13358496 ns 5 bytes=16.7772M bytes_per_second=1.99429G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time_median 7831858 ns 13347926 ns 5 bytes=16.7772M bytes_per_second=1.99506G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time_stddev 16506 ns 27941 ns 5 bytes=0 bytes_per_second=4.30396M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time_cv 0.21 % 0.21 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time 13725475 ns 25012464 ns 51 bytes=33.5544M bytes_per_second=2.27679G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time 13694338 ns 25028847 ns 51 bytes=33.5544M bytes_per_second=2.28197G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time 13714953 ns 25021164 ns 51 bytes=33.5544M bytes_per_second=2.27854G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time 13715245 ns 25066578 ns 51 bytes=33.5544M bytes_per_second=2.27849G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time 13740431 ns 25062391 ns 51 bytes=33.5544M bytes_per_second=2.27431G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time_mean 13718088 ns 25038289 ns 5 bytes=33.5544M bytes_per_second=2.27802G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time_median 13715245 ns 25028847 ns 5 bytes=33.5544M bytes_per_second=2.27849G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time_stddev 16850 ns 24650 ns 5 bytes=0 bytes_per_second=2.86567M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time_cv 0.12 % 0.10 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time 25511407 ns 48405947 ns 27 bytes=67.1089M bytes_per_second=2.44988G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time 25325498 ns 48206646 ns 27 bytes=67.1089M bytes_per_second=2.46787G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time 25446310 ns 48338934 ns 27 bytes=67.1089M bytes_per_second=2.45615G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time 25477718 ns 48418816 ns 27 bytes=67.1089M bytes_per_second=2.45312G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time 25425149 ns 48284418 ns 27 bytes=67.1089M bytes_per_second=2.4582G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time_mean 25437216 ns 48330952 ns 5 bytes=67.1089M bytes_per_second=2.45704G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time_median 25446310 ns 48338934 ns 5 bytes=67.1089M bytes_per_second=2.45615G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time_stddev 70452 ns 88070 ns 5 bytes=0 bytes_per_second=6.98122M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time_cv 0.28 % 0.18 % 5 bytes=0.00% bytes_per_second=0.28% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time 46138092 ns 88417745 ns 15 bytes=134.218M bytes_per_second=2.70926G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time 46338262 ns 88564537 ns 15 bytes=134.218M bytes_per_second=2.69755G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time 46274092 ns 88422009 ns 15 bytes=134.218M bytes_per_second=2.7013G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time 46637550 ns 89007679 ns 15 bytes=134.218M bytes_per_second=2.68024G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time 46032821 ns 88151941 ns 15 bytes=134.218M bytes_per_second=2.71545G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time_mean 46284164 ns 88512782 ns 5 bytes=134.218M bytes_per_second=2.70076G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time_median 46274092 ns 88422009 ns 5 bytes=134.218M bytes_per_second=2.7013G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time_stddev 230445 ns 314277 ns 5 bytes=0 bytes_per_second=13.7346M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time_cv 0.50 % 0.36 % 5 bytes=0.00% bytes_per_second=0.50% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time 87771807 ns 167336634 ns 8 bytes=268.435M bytes_per_second=2.8483G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time 88093709 ns 167692701 ns 8 bytes=268.435M bytes_per_second=2.83789G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time 87507283 ns 165468584 ns 8 bytes=268.435M bytes_per_second=2.85691G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time 87659886 ns 167133857 ns 8 bytes=268.435M bytes_per_second=2.85193G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time 87684210 ns 167284627 ns 8 bytes=268.435M bytes_per_second=2.85114G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time_mean 87743379 ns 166983281 ns 5 bytes=268.435M bytes_per_second=2.84923G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time_median 87684210 ns 167284627 ns 5 bytes=268.435M bytes_per_second=2.85114G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time_stddev 217803 ns 871195 ns 5 bytes=0 bytes_per_second=7.22974M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time_cv 0.25 % 0.52 % 5 bytes=0.00% bytes_per_second=0.25% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time 169981681 ns 316648311 ns 4 bytes=536.871M bytes_per_second=2.94149G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time 169955436 ns 313758081 ns 4 bytes=536.871M bytes_per_second=2.94195G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time 170292556 ns 316649432 ns 4 bytes=536.871M bytes_per_second=2.93612G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time 170598794 ns 315131862 ns 4 bytes=536.871M bytes_per_second=2.93085G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time 170284756 ns 316815677 ns 4 bytes=536.871M bytes_per_second=2.93626G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time_mean 170222645 ns 315800673 ns 5 bytes=536.871M bytes_per_second=2.93734G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time_median 170284756 ns 316648311 ns 5 bytes=536.871M bytes_per_second=2.93626G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time_stddev 264432 ns 1331222 ns 5 bytes=0 bytes_per_second=4.67049M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time_cv 0.16 % 0.42 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time 326397136 ns 568385738 ns 2 bytes=1073.74M bytes_per_second=3.06375G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time 327041209 ns 568753843 ns 2 bytes=1073.74M bytes_per_second=3.05772G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time 326438814 ns 568115882 ns 2 bytes=1073.74M bytes_per_second=3.06336G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time 326169297 ns 567869986 ns 2 bytes=1073.74M bytes_per_second=3.06589G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time 326599136 ns 566683101 ns 2 bytes=1073.74M bytes_per_second=3.06186G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time_mean 326529118 ns 567961710 ns 5 bytes=1073.74M bytes_per_second=3.06252G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time_median 326438814 ns 568115882 ns 5 bytes=1073.74M bytes_per_second=3.06336G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time_stddev 324879 ns 786495 ns 5 bytes=0 bytes_per_second=3.11825M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time_cv 0.10 % 0.14 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time 2246731 ns 2579856 ns 313 bytes=4.096k bytes_per_second=1.73864M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time 2243502 ns 2577941 ns 313 bytes=4.096k bytes_per_second=1.74114M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time 2251481 ns 2592055 ns 313 bytes=4.096k bytes_per_second=1.73497M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time 2243080 ns 2577048 ns 313 bytes=4.096k bytes_per_second=1.74147M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time 2243198 ns 2588757 ns 313 bytes=4.096k bytes_per_second=1.74138M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time_mean 2245598 ns 2583132 ns 5 bytes=4.096k bytes_per_second=1.73952M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time_median 2243502 ns 2579856 ns 5 bytes=4.096k bytes_per_second=1.74114M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time_stddev 3619 ns 6818 ns 5 bytes=0 bytes_per_second=2.86643k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time_cv 0.16 % 0.26 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time 2254397 ns 2590175 ns 312 bytes=8.192k bytes_per_second=3.46545M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time 2243598 ns 2591600 ns 312 bytes=8.192k bytes_per_second=3.48213M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time 2243654 ns 2579357 ns 312 bytes=8.192k bytes_per_second=3.48204M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time 2256097 ns 2591642 ns 312 bytes=8.192k bytes_per_second=3.46284M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time 2243419 ns 2579304 ns 312 bytes=8.192k bytes_per_second=3.48241M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time_mean 2248233 ns 2586415 ns 5 bytes=8.192k bytes_per_second=3.47497M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time_median 2243654 ns 2590175 ns 5 bytes=8.192k bytes_per_second=3.48204M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time_stddev 6432 ns 6495 ns 5 bytes=0 bytes_per_second=10.1688k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time_cv 0.29 % 0.25 % 5 bytes=0.00% bytes_per_second=0.29% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time 2251283 ns 2600906 ns 311 bytes=16.384k bytes_per_second=6.94049M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time 2251927 ns 2592321 ns 311 bytes=16.384k bytes_per_second=6.9385M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time 2258587 ns 2602487 ns 311 bytes=16.384k bytes_per_second=6.91804M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time 2251468 ns 2589564 ns 311 bytes=16.384k bytes_per_second=6.93992M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time 2257640 ns 2595896 ns 311 bytes=16.384k bytes_per_second=6.92095M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time_mean 2254181 ns 2596235 ns 5 bytes=16.384k bytes_per_second=6.93158M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time_median 2251927 ns 2595896 ns 5 bytes=16.384k bytes_per_second=6.9385M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time_stddev 3613 ns 5496 ns 5 bytes=0 bytes_per_second=11.3694k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time_cv 0.16 % 0.21 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time 2262456 ns 2604561 ns 307 bytes=32.768k bytes_per_second=13.8124M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time 2268427 ns 2616744 ns 307 bytes=32.768k bytes_per_second=13.7761M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time 2262828 ns 2604775 ns 307 bytes=32.768k bytes_per_second=13.8102M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time 2262464 ns 2610710 ns 307 bytes=32.768k bytes_per_second=13.8124M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time 2268184 ns 2610506 ns 307 bytes=32.768k bytes_per_second=13.7775M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time_mean 2264872 ns 2609459 ns 5 bytes=32.768k bytes_per_second=13.7977M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time_median 2262828 ns 2610506 ns 5 bytes=32.768k bytes_per_second=13.8102M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time_stddev 3139 ns 5041 ns 5 bytes=0 bytes_per_second=19.5732k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time_cv 0.14 % 0.19 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time 2310743 ns 2661592 ns 304 bytes=65.536k bytes_per_second=27.0476M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time 2320447 ns 2671459 ns 304 bytes=65.536k bytes_per_second=26.9345M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time 2302725 ns 2660429 ns 304 bytes=65.536k bytes_per_second=27.1418M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time 2311116 ns 2662438 ns 304 bytes=65.536k bytes_per_second=27.0432M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time 2303243 ns 2660953 ns 304 bytes=65.536k bytes_per_second=27.1357M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time_mean 2309655 ns 2663374 ns 5 bytes=65.536k bytes_per_second=27.0605M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time_median 2310743 ns 2661592 ns 5 bytes=65.536k bytes_per_second=27.0476M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time_stddev 7227 ns 4581 ns 5 bytes=0 bytes_per_second=86.5909k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time_cv 0.31 % 0.17 % 5 bytes=0.00% bytes_per_second=0.31% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time 2358393 ns 2733923 ns 296 bytes=131.072k bytes_per_second=53.0022M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time 2367199 ns 2742173 ns 296 bytes=131.072k bytes_per_second=52.805M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time 2360823 ns 2729971 ns 296 bytes=131.072k bytes_per_second=52.9476M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time 2364151 ns 2738876 ns 296 bytes=131.072k bytes_per_second=52.8731M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time 2357047 ns 2731943 ns 296 bytes=131.072k bytes_per_second=53.0325M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time_mean 2361523 ns 2735377 ns 5 bytes=131.072k bytes_per_second=52.9321M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time_median 2360823 ns 2733923 ns 5 bytes=131.072k bytes_per_second=52.9476M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time_stddev 4167 ns 5039 ns 5 bytes=0 bytes_per_second=95.5897k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time_cv 0.18 % 0.18 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time 2489727 ns 2892889 ns 280 bytes=262.144k bytes_per_second=100.413M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time 2495966 ns 2895505 ns 280 bytes=262.144k bytes_per_second=100.162M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time 2500913 ns 2900526 ns 280 bytes=262.144k bytes_per_second=99.9635M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time 2490283 ns 2893678 ns 280 bytes=262.144k bytes_per_second=100.39M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time 2495255 ns 2898286 ns 280 bytes=262.144k bytes_per_second=100.19M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time_mean 2494429 ns 2896177 ns 5 bytes=262.144k bytes_per_second=100.224M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time_median 2495255 ns 2895505 ns 5 bytes=262.144k bytes_per_second=100.19M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time_stddev 4593 ns 3196 ns 5 bytes=0 bytes_per_second=188.881k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time_cv 0.18 % 0.11 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time 2578497 ns 3050424 ns 270 bytes=524.288k bytes_per_second=193.911M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time 2584392 ns 3056671 ns 270 bytes=524.288k bytes_per_second=193.469M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time 2576651 ns 3044891 ns 270 bytes=524.288k bytes_per_second=194.05M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time 2576076 ns 3048080 ns 270 bytes=524.288k bytes_per_second=194.094M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time 2581336 ns 3049528 ns 270 bytes=524.288k bytes_per_second=193.698M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time_mean 2579390 ns 3049919 ns 5 bytes=524.288k bytes_per_second=193.845M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time_median 2578497 ns 3049528 ns 5 bytes=524.288k bytes_per_second=193.911M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time_stddev 3467 ns 4320 ns 5 bytes=0 bytes_per_second=266.665k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time_cv 0.13 % 0.14 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time 2734353 ns 3339706 ns 254 bytes=1048.58k bytes_per_second=365.717M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time 2738640 ns 3346000 ns 254 bytes=1048.58k bytes_per_second=365.145M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time 2732927 ns 3338184 ns 254 bytes=1048.58k bytes_per_second=365.908M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time 2736300 ns 3340271 ns 254 bytes=1048.58k bytes_per_second=365.457M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time 2738703 ns 3344505 ns 254 bytes=1048.58k bytes_per_second=365.136M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time_mean 2736184 ns 3341733 ns 5 bytes=1048.58k bytes_per_second=365.473M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time_median 2736300 ns 3340271 ns 5 bytes=1048.58k bytes_per_second=365.457M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time_stddev 2567 ns 3344 ns 5 bytes=0 bytes_per_second=351.126k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time_cv 0.09 % 0.10 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time 3080158 ns 4008848 ns 228 bytes=2.09715M bytes_per_second=649.317M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time 3083354 ns 4009456 ns 228 bytes=2.09715M bytes_per_second=648.644M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time 3081030 ns 4006543 ns 228 bytes=2.09715M bytes_per_second=649.134M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time 3068795 ns 4005799 ns 228 bytes=2.09715M bytes_per_second=651.722M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time 3067702 ns 3993323 ns 228 bytes=2.09715M bytes_per_second=651.954M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time_mean 3076208 ns 4004794 ns 5 bytes=2.09715M bytes_per_second=650.154M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time_median 3080158 ns 4006543 ns 5 bytes=2.09715M bytes_per_second=649.317M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time_stddev 7369 ns 6592 ns 5 bytes=0 bytes_per_second=1.55864M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time_cv 0.24 % 0.16 % 5 bytes=0.00% bytes_per_second=0.24% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time 3592363 ns 5073697 ns 195 bytes=4.1943M bytes_per_second=1113.47M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time 3591598 ns 5068402 ns 195 bytes=4.1943M bytes_per_second=1113.71M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time 3592703 ns 5071035 ns 195 bytes=4.1943M bytes_per_second=1113.37M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time 3589976 ns 5067863 ns 195 bytes=4.1943M bytes_per_second=1114.21M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time 3585548 ns 5064370 ns 195 bytes=4.1943M bytes_per_second=1115.59M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time_mean 3590437 ns 5069073 ns 5 bytes=4.1943M bytes_per_second=1114.07M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time_median 3591598 ns 5068402 ns 5 bytes=4.1943M bytes_per_second=1113.71M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time_stddev 2928 ns 3509 ns 5 bytes=0 bytes_per_second=931.207k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time_cv 0.08 % 0.07 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time 4924177 ns 7680820 ns 142 bytes=8.38861M bytes_per_second=1.58656G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time 4925540 ns 7671940 ns 142 bytes=8.38861M bytes_per_second=1.58612G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time 4917106 ns 7671411 ns 142 bytes=8.38861M bytes_per_second=1.58884G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time 4953219 ns 7705103 ns 142 bytes=8.38861M bytes_per_second=1.57726G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time 4925529 ns 7683883 ns 142 bytes=8.38861M bytes_per_second=1.58612G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time_mean 4929114 ns 7682631 ns 5 bytes=8.38861M bytes_per_second=1.58498G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time_median 4925529 ns 7680820 ns 5 bytes=8.38861M bytes_per_second=1.58612G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time_stddev 13922 ns 13693 ns 5 bytes=0 bytes_per_second=4.56959M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time_cv 0.28 % 0.18 % 5 bytes=0.00% bytes_per_second=0.28% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time 7759842 ns 13273240 ns 82 bytes=16.7772M bytes_per_second=2.01357G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time 7792033 ns 13321903 ns 82 bytes=16.7772M bytes_per_second=2.00525G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time 7743994 ns 13247520 ns 82 bytes=16.7772M bytes_per_second=2.01769G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time 7793169 ns 13331182 ns 82 bytes=16.7772M bytes_per_second=2.00496G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time 7737262 ns 13235540 ns 82 bytes=16.7772M bytes_per_second=2.01945G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time_mean 7765260 ns 13281877 ns 5 bytes=16.7772M bytes_per_second=2.01219G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time_median 7759842 ns 13273240 ns 5 bytes=16.7772M bytes_per_second=2.01357G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time_stddev 26273 ns 43114 ns 5 bytes=0 bytes_per_second=6.96858M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time_cv 0.34 % 0.32 % 5 bytes=0.00% bytes_per_second=0.34% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time 13679108 ns 24964502 ns 53 bytes=33.5544M bytes_per_second=2.28451G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time 13750236 ns 25022043 ns 53 bytes=33.5544M bytes_per_second=2.27269G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time 13700772 ns 25005635 ns 53 bytes=33.5544M bytes_per_second=2.28089G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time 13731368 ns 24998768 ns 53 bytes=33.5544M bytes_per_second=2.27581G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time 13718976 ns 24960782 ns 53 bytes=33.5544M bytes_per_second=2.27787G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time_mean 13716092 ns 24990346 ns 5 bytes=33.5544M bytes_per_second=2.27835G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time_median 13718976 ns 24998768 ns 5 bytes=33.5544M bytes_per_second=2.27787G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time_stddev 27432 ns 26699 ns 5 bytes=0 bytes_per_second=4.66723M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time_cv 0.20 % 0.11 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time 25307104 ns 48164615 ns 28 bytes=67.1089M bytes_per_second=2.46966G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time 25342476 ns 48164641 ns 28 bytes=67.1089M bytes_per_second=2.46622G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time 25283841 ns 48163331 ns 28 bytes=67.1089M bytes_per_second=2.47193G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time 25401933 ns 48248416 ns 28 bytes=67.1089M bytes_per_second=2.46044G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time 25421201 ns 48304819 ns 28 bytes=67.1089M bytes_per_second=2.45858G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time_mean 25351311 ns 48209164 ns 5 bytes=67.1089M bytes_per_second=2.46537G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time_median 25342476 ns 48164641 ns 5 bytes=67.1089M bytes_per_second=2.46622G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time_stddev 59228 ns 64727 ns 5 bytes=0 bytes_per_second=5.89678M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time_cv 0.23 % 0.13 % 5 bytes=0.00% bytes_per_second=0.23% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time 45261677 ns 86318899 ns 15 bytes=134.218M bytes_per_second=2.76172G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time 45544216 ns 87257309 ns 15 bytes=134.218M bytes_per_second=2.74459G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time 45757796 ns 87694693 ns 15 bytes=134.218M bytes_per_second=2.73177G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time 45727898 ns 87646091 ns 15 bytes=134.218M bytes_per_second=2.73356G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time 45735599 ns 87725882 ns 15 bytes=134.218M bytes_per_second=2.7331G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time_mean 45605437 ns 87328575 ns 5 bytes=134.218M bytes_per_second=2.74095G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time_median 45727898 ns 87646091 ns 5 bytes=134.218M bytes_per_second=2.73356G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time_stddev 210399 ns 595239 ns 5 bytes=0 bytes_per_second=13.0025M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time_cv 0.46 % 0.68 % 5 bytes=0.00% bytes_per_second=0.46% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time 87242316 ns 167356606 ns 8 bytes=268.435M bytes_per_second=2.86558G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time 86270650 ns 165120926 ns 8 bytes=268.435M bytes_per_second=2.89786G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time 86642671 ns 165717760 ns 8 bytes=268.435M bytes_per_second=2.88541G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time 86534994 ns 165427192 ns 8 bytes=268.435M bytes_per_second=2.889G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time 87502876 ns 167430919 ns 8 bytes=268.435M bytes_per_second=2.85705G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time_mean 86838701 ns 166210681 ns 5 bytes=268.435M bytes_per_second=2.87898G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time_median 86642671 ns 165717760 ns 5 bytes=268.435M bytes_per_second=2.88541G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time_stddev 514145 ns 1100741 ns 5 bytes=0 bytes_per_second=17.4284M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time_cv 0.59 % 0.66 % 5 bytes=0.00% bytes_per_second=0.59% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time 168371201 ns 312334104 ns 4 bytes=536.871M bytes_per_second=2.96963G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time 168121763 ns 313346523 ns 4 bytes=536.871M bytes_per_second=2.97403G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time 168306276 ns 312376606 ns 4 bytes=536.871M bytes_per_second=2.97077G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time 168518085 ns 314246487 ns 4 bytes=536.871M bytes_per_second=2.96704G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time 168523397 ns 313108150 ns 4 bytes=536.871M bytes_per_second=2.96695G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time_mean 168368144 ns 313082374 ns 5 bytes=536.871M bytes_per_second=2.96969G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time_median 168371201 ns 313108150 ns 5 bytes=536.871M bytes_per_second=2.96963G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time_stddev 166678 ns 787974 ns 5 bytes=0 bytes_per_second=3.01174M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time_cv 0.10 % 0.25 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time 318372369 ns 563238668 ns 2 bytes=1073.74M bytes_per_second=3.14098G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time 324102417 ns 566311198 ns 2 bytes=1073.74M bytes_per_second=3.08544G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time 322568089 ns 567698350 ns 2 bytes=1073.74M bytes_per_second=3.10012G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time 318466231 ns 561850224 ns 2 bytes=1073.74M bytes_per_second=3.14005G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time 327437073 ns 571016426 ns 2 bytes=1073.74M bytes_per_second=3.05402G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time_mean 322189236 ns 566022973 ns 5 bytes=1073.74M bytes_per_second=3.10412G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time_median 322568089 ns 566311198 ns 5 bytes=1073.74M bytes_per_second=3.10012G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time_stddev 3865644 ns 3639668 ns 5 bytes=0 bytes_per_second=38.0535M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time_cv 1.20 % 0.64 % 5 bytes=0.00% bytes_per_second=1.20% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time 2241721 ns 2571587 ns 312 bytes=4.096k bytes_per_second=1.74252M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time 2247486 ns 2583310 ns 312 bytes=4.096k bytes_per_second=1.73805M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time 2241087 ns 2571175 ns 312 bytes=4.096k bytes_per_second=1.74302M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time 2240946 ns 2577211 ns 312 bytes=4.096k bytes_per_second=1.74313M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time 2241422 ns 2577043 ns 312 bytes=4.096k bytes_per_second=1.74275M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time_mean 2242532 ns 2576065 ns 5 bytes=4.096k bytes_per_second=1.74189M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time_median 2241422 ns 2577043 ns 5 bytes=4.096k bytes_per_second=1.74275M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time_stddev 2786 ns 4968 ns 5 bytes=0 bytes_per_second=2.21204k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time_cv 0.12 % 0.19 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time 2248817 ns 2585949 ns 312 bytes=8.192k bytes_per_second=3.47405M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time 2241634 ns 2573744 ns 312 bytes=8.192k bytes_per_second=3.48518M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time 2247089 ns 2578361 ns 312 bytes=8.192k bytes_per_second=3.47672M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time 2248201 ns 2580328 ns 312 bytes=8.192k bytes_per_second=3.475M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time 2248380 ns 2580088 ns 312 bytes=8.192k bytes_per_second=3.47472M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time_mean 2246824 ns 2579694 ns 5 bytes=8.192k bytes_per_second=3.47713M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time_median 2248201 ns 2580088 ns 5 bytes=8.192k bytes_per_second=3.475M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time_stddev 2971 ns 4384 ns 5 bytes=0 bytes_per_second=4.7149k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time_cv 0.13 % 0.17 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time 2249755 ns 2584031 ns 311 bytes=16.384k bytes_per_second=6.9452M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time 2257320 ns 2592224 ns 311 bytes=16.384k bytes_per_second=6.92193M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time 2256218 ns 2590161 ns 311 bytes=16.384k bytes_per_second=6.9253M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time 2250838 ns 2591130 ns 311 bytes=16.384k bytes_per_second=6.94186M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time 2257281 ns 2591215 ns 311 bytes=16.384k bytes_per_second=6.92205M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time_mean 2254282 ns 2589752 ns 5 bytes=16.384k bytes_per_second=6.93127M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time_median 2256218 ns 2591130 ns 5 bytes=16.384k bytes_per_second=6.9253M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time_stddev 3685 ns 3280 ns 5 bytes=0 bytes_per_second=11.6105k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time_cv 0.16 % 0.13 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time 2273388 ns 2610426 ns 309 bytes=32.768k bytes_per_second=13.746M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time 2265388 ns 2610211 ns 309 bytes=32.768k bytes_per_second=13.7945M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time 2265955 ns 2610216 ns 309 bytes=32.768k bytes_per_second=13.7911M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time 2271430 ns 2609737 ns 309 bytes=32.768k bytes_per_second=13.7579M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time 2265768 ns 2604404 ns 309 bytes=32.768k bytes_per_second=13.7922M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time_mean 2268386 ns 2608999 ns 5 bytes=32.768k bytes_per_second=13.7763M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time_median 2265955 ns 2610211 ns 5 bytes=32.768k bytes_per_second=13.7911M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time_stddev 3743 ns 2581 ns 5 bytes=0 bytes_per_second=23.2607k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time_cv 0.17 % 0.10 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time 2303867 ns 2651052 ns 305 bytes=65.536k bytes_per_second=27.1283M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time 2295071 ns 2649375 ns 305 bytes=65.536k bytes_per_second=27.2323M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time 2295558 ns 2648699 ns 305 bytes=65.536k bytes_per_second=27.2265M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time 2295269 ns 2642674 ns 305 bytes=65.536k bytes_per_second=27.2299M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time 2304066 ns 2657327 ns 305 bytes=65.536k bytes_per_second=27.126M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time_mean 2298766 ns 2649825 ns 5 bytes=65.536k bytes_per_second=27.1886M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time_median 2295558 ns 2649375 ns 5 bytes=65.536k bytes_per_second=27.2265M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time_stddev 4751 ns 5253 ns 5 bytes=0 bytes_per_second=57.4962k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time_cv 0.21 % 0.20 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time 2381687 ns 2748325 ns 295 bytes=131.072k bytes_per_second=52.4838M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time 2380708 ns 2747843 ns 295 bytes=131.072k bytes_per_second=52.5054M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time 2389905 ns 2756597 ns 295 bytes=131.072k bytes_per_second=52.3033M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time 2373726 ns 2740385 ns 295 bytes=131.072k bytes_per_second=52.6598M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time 2387153 ns 2752736 ns 295 bytes=131.072k bytes_per_second=52.3636M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time_mean 2382636 ns 2749177 ns 5 bytes=131.072k bytes_per_second=52.4632M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time_median 2381687 ns 2748325 ns 5 bytes=131.072k bytes_per_second=52.4838M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time_stddev 6270 ns 6073 ns 5 bytes=0 bytes_per_second=141.467k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time_cv 0.26 % 0.22 % 5 bytes=0.00% bytes_per_second=0.26% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time 2493525 ns 2890306 ns 282 bytes=262.144k bytes_per_second=100.26M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time 2482719 ns 2883425 ns 282 bytes=262.144k bytes_per_second=100.696M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time 2483056 ns 2882410 ns 282 bytes=262.144k bytes_per_second=100.682M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time 2494214 ns 2890895 ns 282 bytes=262.144k bytes_per_second=100.232M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time 2488495 ns 2884889 ns 282 bytes=262.144k bytes_per_second=100.462M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time_mean 2488402 ns 2886385 ns 5 bytes=262.144k bytes_per_second=100.466M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time_median 2488495 ns 2884889 ns 5 bytes=262.144k bytes_per_second=100.462M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time_stddev 5498 ns 3953 ns 5 bytes=0 bytes_per_second=227.308k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time_cv 0.22 % 0.14 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time 2579782 ns 3049726 ns 271 bytes=524.288k bytes_per_second=193.815M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time 2581682 ns 3049232 ns 271 bytes=524.288k bytes_per_second=193.672M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time 2581007 ns 3058221 ns 271 bytes=524.288k bytes_per_second=193.723M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time 2581357 ns 3052024 ns 271 bytes=524.288k bytes_per_second=193.697M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time 2577832 ns 3047242 ns 271 bytes=524.288k bytes_per_second=193.961M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time_mean 2580332 ns 3051289 ns 5 bytes=524.288k bytes_per_second=193.774M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time_median 2581007 ns 3049726 ns 5 bytes=524.288k bytes_per_second=193.723M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time_stddev 1572 ns 4232 ns 5 bytes=0 bytes_per_second=120.911k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time_cv 0.06 % 0.14 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time 2744027 ns 3343994 ns 256 bytes=1048.58k bytes_per_second=364.428M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time 2741250 ns 3346374 ns 256 bytes=1048.58k bytes_per_second=364.797M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time 2738717 ns 3340070 ns 256 bytes=1048.58k bytes_per_second=365.135M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time 2742466 ns 3350394 ns 256 bytes=1048.58k bytes_per_second=364.635M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time 2742941 ns 3343769 ns 256 bytes=1048.58k bytes_per_second=364.572M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time_mean 2741880 ns 3344920 ns 5 bytes=1048.58k bytes_per_second=364.713M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time_median 2742466 ns 3343994 ns 5 bytes=1048.58k bytes_per_second=364.635M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time_stddev 2030 ns 3801 ns 5 bytes=0 bytes_per_second=276.609k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time_cv 0.07 % 0.11 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time 3065348 ns 3990324 ns 229 bytes=2.09715M bytes_per_second=652.455M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time 3062076 ns 3991836 ns 229 bytes=2.09715M bytes_per_second=653.152M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time 3060994 ns 3992718 ns 229 bytes=2.09715M bytes_per_second=653.383M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time 3070652 ns 4003197 ns 229 bytes=2.09715M bytes_per_second=651.327M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time 3065130 ns 3994539 ns 229 bytes=2.09715M bytes_per_second=652.501M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time_mean 3064840 ns 3994523 ns 5 bytes=2.09715M bytes_per_second=652.563M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time_median 3065130 ns 3992718 ns 5 bytes=2.09715M bytes_per_second=652.501M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time_stddev 3760 ns 5083 ns 5 bytes=0 bytes_per_second=819.268k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time_cv 0.12 % 0.13 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time 3579926 ns 5060051 ns 195 bytes=4.1943M bytes_per_second=1117.34M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time 3584649 ns 5065506 ns 195 bytes=4.1943M bytes_per_second=1115.87M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time 3583954 ns 5061139 ns 195 bytes=4.1943M bytes_per_second=1116.09M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time 3600961 ns 5084479 ns 195 bytes=4.1943M bytes_per_second=1110.81M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time 3586255 ns 5065029 ns 195 bytes=4.1943M bytes_per_second=1115.37M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time_mean 3587149 ns 5067241 ns 5 bytes=4.1943M bytes_per_second=1115.1M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time_median 3584649 ns 5065029 ns 5 bytes=4.1943M bytes_per_second=1115.87M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time_stddev 8066 ns 9924 ns 5 bytes=0 bytes_per_second=2.50135M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time_cv 0.22 % 0.20 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time 4834801 ns 7528903 ns 145 bytes=8.38861M bytes_per_second=1.61589G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time 4869732 ns 7574449 ns 145 bytes=8.38861M bytes_per_second=1.6043G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time 4867421 ns 7545272 ns 145 bytes=8.38861M bytes_per_second=1.60506G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time 4870488 ns 7574100 ns 145 bytes=8.38861M bytes_per_second=1.60405G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time 4936069 ns 7665520 ns 145 bytes=8.38861M bytes_per_second=1.58274G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time_mean 4875702 ns 7577649 ns 5 bytes=8.38861M bytes_per_second=1.60241G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time_median 4869732 ns 7574100 ns 5 bytes=8.38861M bytes_per_second=1.6043G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time_stddev 36907 ns 52841 ns 5 bytes=0 bytes_per_second=12.3513M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time_cv 0.76 % 0.70 % 5 bytes=0.00% bytes_per_second=0.75% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time 7689358 ns 13137897 ns 88 bytes=16.7772M bytes_per_second=2.03203G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time 7745447 ns 13270336 ns 88 bytes=16.7772M bytes_per_second=2.01731G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time 7716102 ns 13176712 ns 88 bytes=16.7772M bytes_per_second=2.02499G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time 7702649 ns 13159993 ns 88 bytes=16.7772M bytes_per_second=2.02852G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time 7721349 ns 13194362 ns 88 bytes=16.7772M bytes_per_second=2.02361G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time_mean 7714981 ns 13187860 ns 5 bytes=16.7772M bytes_per_second=2.02529G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time_median 7716102 ns 13176712 ns 5 bytes=16.7772M bytes_per_second=2.02499G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time_stddev 21087 ns 50601 ns 5 bytes=0 bytes_per_second=5.66446M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time_cv 0.27 % 0.38 % 5 bytes=0.00% bytes_per_second=0.27% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time 13753458 ns 24960115 ns 51 bytes=33.5544M bytes_per_second=2.27216G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time 13761392 ns 24983173 ns 51 bytes=33.5544M bytes_per_second=2.27085G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time 13771312 ns 24973215 ns 51 bytes=33.5544M bytes_per_second=2.26921G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time 13789374 ns 25012162 ns 51 bytes=33.5544M bytes_per_second=2.26624G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time 13766293 ns 25018883 ns 51 bytes=33.5544M bytes_per_second=2.27004G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time_mean 13768366 ns 24989510 ns 5 bytes=33.5544M bytes_per_second=2.2697G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time_median 13766293 ns 24983173 ns 5 bytes=33.5544M bytes_per_second=2.27004G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time_stddev 13465 ns 25227 ns 5 bytes=0 bytes_per_second=2.27161M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time_cv 0.10 % 0.10 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time 25148833 ns 48011087 ns 28 bytes=67.1089M bytes_per_second=2.4852G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time 25328645 ns 48147259 ns 28 bytes=67.1089M bytes_per_second=2.46756G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time 23902113 ns 45728522 ns 28 bytes=67.1089M bytes_per_second=2.61483G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time 25153198 ns 47953268 ns 28 bytes=67.1089M bytes_per_second=2.48477G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time 25312074 ns 48101873 ns 28 bytes=67.1089M bytes_per_second=2.46918G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time_mean 24968973 ns 47588402 ns 5 bytes=67.1089M bytes_per_second=2.50431G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time_median 25153198 ns 48011087 ns 5 bytes=67.1089M bytes_per_second=2.48477G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time_stddev 602404 ns 1042463 ns 5 bytes=0 bytes_per_second=63.8389M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time_cv 2.41 % 2.19 % 5 bytes=0.00% bytes_per_second=2.49% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time 45620814 ns 87420578 ns 15 bytes=134.218M bytes_per_second=2.73998G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time 45616772 ns 87524696 ns 15 bytes=134.218M bytes_per_second=2.74022G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time 45621955 ns 87431550 ns 15 bytes=134.218M bytes_per_second=2.73991G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time 45761742 ns 87623396 ns 15 bytes=134.218M bytes_per_second=2.73154G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time 44686493 ns 85619995 ns 15 bytes=134.218M bytes_per_second=2.79727G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time_mean 45461555 ns 87124043 ns 5 bytes=134.218M bytes_per_second=2.74978G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time_median 45620814 ns 87431550 ns 5 bytes=134.218M bytes_per_second=2.73998G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time_stddev 437612 ns 844768 ns 5 bytes=0 bytes_per_second=27.4412M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time_cv 0.96 % 0.97 % 5 bytes=0.00% bytes_per_second=0.97% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time 86463508 ns 165413746 ns 8 bytes=268.435M bytes_per_second=2.89139G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time 86581670 ns 165499164 ns 8 bytes=268.435M bytes_per_second=2.88745G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time 85272543 ns 162183517 ns 8 bytes=268.435M bytes_per_second=2.93178G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time 86576090 ns 165478202 ns 8 bytes=268.435M bytes_per_second=2.88763G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time 86364589 ns 165241892 ns 8 bytes=268.435M bytes_per_second=2.8947G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time_mean 86251680 ns 164763304 ns 5 bytes=268.435M bytes_per_second=2.89859G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time_median 86463508 ns 165413746 ns 5 bytes=268.435M bytes_per_second=2.89139G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time_stddev 554631 ns 1445683 ns 5 bytes=0 bytes_per_second=19.242M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time_cv 0.64 % 0.88 % 5 bytes=0.00% bytes_per_second=0.65% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time 167939272 ns 313334525 ns 4 bytes=536.871M bytes_per_second=2.97727G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time 166515552 ns 307953478 ns 4 bytes=536.871M bytes_per_second=3.00272G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time 168011073 ns 313390588 ns 4 bytes=536.871M bytes_per_second=2.97599G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time 166263267 ns 307839572 ns 4 bytes=536.871M bytes_per_second=3.00728G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time 167814702 ns 313146833 ns 4 bytes=536.871M bytes_per_second=2.97948G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time_mean 167308773 ns 311132999 ns 5 bytes=536.871M bytes_per_second=2.98855G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time_median 167814702 ns 313146833 ns 5 bytes=536.871M bytes_per_second=2.97948G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time_stddev 846906 ns 2956136 ns 5 bytes=0 bytes_per_second=15.5205M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time_cv 0.51 % 0.95 % 5 bytes=0.00% bytes_per_second=0.51% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time 321046054 ns 561169463 ns 2 bytes=1073.74M bytes_per_second=3.11482G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time 319658145 ns 559270357 ns 2 bytes=1073.74M bytes_per_second=3.12834G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time 320576862 ns 560146309 ns 2 bytes=1073.74M bytes_per_second=3.11938G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time 320200786 ns 559817924 ns 2 bytes=1073.74M bytes_per_second=3.12304G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time 320046321 ns 560329719 ns 2 bytes=1073.74M bytes_per_second=3.12455G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time_mean 320305634 ns 560146754 ns 5 bytes=1073.74M bytes_per_second=3.12202G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time_median 320200786 ns 560146309 ns 5 bytes=1073.74M bytes_per_second=3.12304G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time_stddev 528977 ns 699216 ns 5 bytes=0 bytes_per_second=5.2777M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time_cv 0.17 % 0.12 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +[2023-10-09 17:57:23.864] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 17:57:23.864] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:57:26.063] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:57:26.063] [scope] [info] recorded CPU goveror +[2023-10-09 17:57:26.063] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:57:26.063] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:57:28-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1795.95 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 2.09, 2.66, 9.64 +---------------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +---------------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time 13319 ns 25218 ns 52604 bytes=4.096k bytes_per_second=293.28M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time 13306 ns 25183 ns 52604 bytes=4.096k bytes_per_second=293.578M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time 13306 ns 25293 ns 52604 bytes=4.096k bytes_per_second=293.565M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time 13314 ns 25473 ns 52604 bytes=4.096k bytes_per_second=293.399M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time 13307 ns 25362 ns 52604 bytes=4.096k bytes_per_second=293.55M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time_mean 13310 ns 25306 ns 5 bytes=4.096k bytes_per_second=293.474M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time_median 13307 ns 25293 ns 5 bytes=4.096k bytes_per_second=293.55M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time_stddev 5.91 ns 116 ns 5 bytes=0 bytes_per_second=133.492k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time_cv 0.04 % 0.46 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time 13303 ns 25686 ns 52591 bytes=8.192k bytes_per_second=587.259M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time 13309 ns 25694 ns 52591 bytes=8.192k bytes_per_second=587.024M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time 13308 ns 25766 ns 52591 bytes=8.192k bytes_per_second=587.07M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time 13304 ns 25610 ns 52591 bytes=8.192k bytes_per_second=587.218M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time 13302 ns 25635 ns 52591 bytes=8.192k bytes_per_second=587.303M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time_mean 13305 ns 25678 ns 5 bytes=8.192k bytes_per_second=587.175M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time_median 13304 ns 25686 ns 5 bytes=8.192k bytes_per_second=587.218M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time_stddev 2.75 ns 60.3 ns 5 bytes=0 bytes_per_second=124.446k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time_cv 0.02 % 0.24 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time 13311 ns 26004 ns 52610 bytes=16.384k bytes_per_second=1.14632G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time 13307 ns 25821 ns 52610 bytes=16.384k bytes_per_second=1.1467G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time 13309 ns 26029 ns 52610 bytes=16.384k bytes_per_second=1.14646G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time 13302 ns 25502 ns 52610 bytes=16.384k bytes_per_second=1.14713G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time 13304 ns 25789 ns 52610 bytes=16.384k bytes_per_second=1.14692G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time_mean 13307 ns 25829 ns 5 bytes=16.384k bytes_per_second=1.14671G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time_median 13307 ns 25821 ns 5 bytes=16.384k bytes_per_second=1.1467G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time_stddev 3.83 ns 212 ns 5 bytes=0 bytes_per_second=345.926k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time_cv 0.03 % 0.82 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time 13305 ns 26095 ns 52590 bytes=32.768k bytes_per_second=2.29367G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time 13306 ns 26090 ns 52590 bytes=32.768k bytes_per_second=2.29358G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time 13310 ns 26205 ns 52590 bytes=32.768k bytes_per_second=2.29285G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time 13302 ns 25678 ns 52590 bytes=32.768k bytes_per_second=2.29421G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time 13312 ns 26198 ns 52590 bytes=32.768k bytes_per_second=2.29254G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time_mean 13307 ns 26053 ns 5 bytes=32.768k bytes_per_second=2.29337G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time_median 13306 ns 26095 ns 5 bytes=32.768k bytes_per_second=2.29358G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time_stddev 3.89 ns 217 ns 5 bytes=0 bytes_per_second=703.713k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time_cv 0.03 % 0.83 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time 13312 ns 26369 ns 52589 bytes=65.536k bytes_per_second=4.58506G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time 13308 ns 25942 ns 52589 bytes=65.536k bytes_per_second=4.58622G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time 13305 ns 25970 ns 52589 bytes=65.536k bytes_per_second=4.58726G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time 13310 ns 26247 ns 52589 bytes=65.536k bytes_per_second=4.58563G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time 13306 ns 26042 ns 52589 bytes=65.536k bytes_per_second=4.5869G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time_mean 13308 ns 26114 ns 5 bytes=65.536k bytes_per_second=4.58622G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time_median 13308 ns 26042 ns 5 bytes=65.536k bytes_per_second=4.58622G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time_stddev 2.60 ns 186 ns 5 bytes=0 bytes_per_second=941.185k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time_cv 0.02 % 0.71 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time 13313 ns 26253 ns 52594 bytes=131.072k bytes_per_second=9.16922G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time 13309 ns 26291 ns 52594 bytes=131.072k bytes_per_second=9.17176G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time 13308 ns 26073 ns 52594 bytes=131.072k bytes_per_second=9.17272G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time 13309 ns 26259 ns 52594 bytes=131.072k bytes_per_second=9.17175G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time 13306 ns 26091 ns 52594 bytes=131.072k bytes_per_second=9.17384G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time_mean 13309 ns 26194 ns 5 bytes=131.072k bytes_per_second=9.17186G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time_median 13309 ns 26253 ns 5 bytes=131.072k bytes_per_second=9.17176G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time_stddev 2.48 ns 103 ns 5 bytes=0 bytes_per_second=1.74808M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time_cv 0.02 % 0.39 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time 13552 ns 26843 ns 51681 bytes=262.144k bytes_per_second=18.0157G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time 13550 ns 26723 ns 51681 bytes=262.144k bytes_per_second=18.0179G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time 13543 ns 26214 ns 51681 bytes=262.144k bytes_per_second=18.0266G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time 13545 ns 26355 ns 51681 bytes=262.144k bytes_per_second=18.0243G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time 13550 ns 26721 ns 51681 bytes=262.144k bytes_per_second=18.018G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time_mean 13548 ns 26571 ns 5 bytes=262.144k bytes_per_second=18.0205G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time_median 13550 ns 26721 ns 5 bytes=262.144k bytes_per_second=18.018G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time_stddev 3.51 ns 271 ns 5 bytes=0 bytes_per_second=4.78569M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time_cv 0.03 % 1.02 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time 13597 ns 26881 ns 51504 bytes=524.288k bytes_per_second=35.911G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time 13594 ns 26535 ns 51504 bytes=524.288k bytes_per_second=35.9179G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time 13594 ns 26774 ns 51504 bytes=524.288k bytes_per_second=35.9188G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time 13595 ns 26919 ns 51504 bytes=524.288k bytes_per_second=35.916G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time 13590 ns 26676 ns 51504 bytes=524.288k bytes_per_second=35.9289G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time_mean 13594 ns 26757 ns 5 bytes=524.288k bytes_per_second=35.9185G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time_median 13594 ns 26774 ns 5 bytes=524.288k bytes_per_second=35.9179G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time_stddev 2.47 ns 156 ns 5 bytes=0 bytes_per_second=6.68936M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time_cv 0.02 % 0.58 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time 13664 ns 26949 ns 51227 bytes=1048.58k bytes_per_second=71.4676G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time 13665 ns 27261 ns 51227 bytes=1048.58k bytes_per_second=71.4651G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time 13665 ns 26794 ns 51227 bytes=1048.58k bytes_per_second=71.4626G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time 13663 ns 26703 ns 51227 bytes=1048.58k bytes_per_second=71.4735G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time 13666 ns 26894 ns 51227 bytes=1048.58k bytes_per_second=71.4585G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time_mean 13665 ns 26920 ns 5 bytes=1048.58k bytes_per_second=71.4655G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time_median 13665 ns 26894 ns 5 bytes=1048.58k bytes_per_second=71.4651G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time_stddev 1.07 ns 213 ns 5 bytes=0 bytes_per_second=5.74198M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time_cv 0.01 % 0.79 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time 13843 ns 27521 ns 50517 bytes=2.09715M bytes_per_second=141.087G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time 13815 ns 27252 ns 50517 bytes=2.09715M bytes_per_second=141.375G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time 13852 ns 27215 ns 50517 bytes=2.09715M bytes_per_second=141.003G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time 13841 ns 27079 ns 50517 bytes=2.09715M bytes_per_second=141.116G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time 13869 ns 27423 ns 50517 bytes=2.09715M bytes_per_second=140.827G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time_mean 13844 ns 27298 ns 5 bytes=2.09715M bytes_per_second=141.082G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time_median 13843 ns 27252 ns 5 bytes=2.09715M bytes_per_second=141.087G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time_stddev 19.5 ns 175 ns 5 bytes=0 bytes_per_second=203.828M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time_cv 0.14 % 0.64 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time 16360 ns 30158 ns 42863 bytes=4.1943M bytes_per_second=238.764G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time 16344 ns 29877 ns 42863 bytes=4.1943M bytes_per_second=239.003G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time 16352 ns 29849 ns 42863 bytes=4.1943M bytes_per_second=238.881G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time 16361 ns 29902 ns 42863 bytes=4.1943M bytes_per_second=238.756G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time 16358 ns 30124 ns 42863 bytes=4.1943M bytes_per_second=238.798G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time_mean 16355 ns 29982 ns 5 bytes=4.1943M bytes_per_second=238.84G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time_median 16358 ns 29902 ns 5 bytes=4.1943M bytes_per_second=238.798G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time_stddev 7.08 ns 147 ns 5 bytes=0 bytes_per_second=105.955M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time_cv 0.04 % 0.49 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time 17715 ns 31706 ns 39482 bytes=8.38861M bytes_per_second=441.012G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time 17721 ns 31496 ns 39482 bytes=8.38861M bytes_per_second=440.867G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time 17708 ns 31494 ns 39482 bytes=8.38861M bytes_per_second=441.197G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time 17730 ns 31266 ns 39482 bytes=8.38861M bytes_per_second=440.633G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time 17741 ns 31926 ns 39482 bytes=8.38861M bytes_per_second=440.374G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time_mean 17723 ns 31578 ns 5 bytes=8.38861M bytes_per_second=440.817G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time_median 17721 ns 31496 ns 5 bytes=8.38861M bytes_per_second=440.867G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time_stddev 13.0 ns 249 ns 5 bytes=0 bytes_per_second=329.804M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time_cv 0.07 % 0.79 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time 23830 ns 38199 ns 29369 bytes=16.7772M bytes_per_second=655.677G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time 23814 ns 37793 ns 29369 bytes=16.7772M bytes_per_second=656.123G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time 23841 ns 37698 ns 29369 bytes=16.7772M bytes_per_second=655.397G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time 23855 ns 37880 ns 29369 bytes=16.7772M bytes_per_second=654.995G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time 23826 ns 37891 ns 29369 bytes=16.7772M bytes_per_second=655.787G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time_mean 23833 ns 37892 ns 5 bytes=16.7772M bytes_per_second=655.596G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time_median 23830 ns 37880 ns 5 bytes=16.7772M bytes_per_second=655.677G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time_stddev 15.4 ns 188 ns 5 bytes=0 bytes_per_second=435.085M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time_cv 0.06 % 0.50 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time 36402 ns 50827 ns 19202 bytes=33.5544M bytes_per_second=858.458G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time 36416 ns 50937 ns 19202 bytes=33.5544M bytes_per_second=858.135G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time 36416 ns 50892 ns 19202 bytes=33.5544M bytes_per_second=858.134G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time 36426 ns 50754 ns 19202 bytes=33.5544M bytes_per_second=857.909G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time 36429 ns 51182 ns 19202 bytes=33.5544M bytes_per_second=857.834G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time_mean 36418 ns 50918 ns 5 bytes=33.5544M bytes_per_second=858.094G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time_median 36416 ns 50892 ns 5 bytes=33.5544M bytes_per_second=858.134G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time_stddev 10.3 ns 163 ns 5 bytes=0 bytes_per_second=249.668M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time_cv 0.03 % 0.32 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time 61766 ns 77303 ns 11336 bytes=67.1089M bytes_per_second=1011.89G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time 61788 ns 77190 ns 11336 bytes=67.1089M bytes_per_second=1011.53G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time 61778 ns 77077 ns 11336 bytes=67.1089M bytes_per_second=1011.69G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time 61828 ns 77020 ns 11336 bytes=67.1089M bytes_per_second=1010.86G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time 61796 ns 77108 ns 11336 bytes=67.1089M bytes_per_second=1011.39G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time_mean 61791 ns 77140 ns 5 bytes=67.1089M bytes_per_second=1011.47G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time_median 61788 ns 77108 ns 5 bytes=67.1089M bytes_per_second=1011.53G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time_stddev 23.7 ns 110 ns 5 bytes=0 bytes_per_second=397.434M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time_cv 0.04 % 0.14 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time 111957 ns 129917 ns 6253 bytes=134.218M bytes_per_second=1116.5G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time 111987 ns 130124 ns 6253 bytes=134.218M bytes_per_second=1116.2G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time 112043 ns 129983 ns 6253 bytes=134.218M bytes_per_second=1115.65G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time 112052 ns 129958 ns 6253 bytes=134.218M bytes_per_second=1115.56G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time 112020 ns 129919 ns 6253 bytes=134.218M bytes_per_second=1115.87G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time_mean 112012 ns 129980 ns 5 bytes=134.218M bytes_per_second=1115.95G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time_median 112020 ns 129958 ns 5 bytes=134.218M bytes_per_second=1115.87G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time_stddev 39.5 ns 85.1 ns 5 bytes=0 bytes_per_second=402.636M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time_cv 0.04 % 0.07 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time 214940 ns 246144 ns 3257 bytes=268.435M bytes_per_second=1.13585T/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time 215058 ns 246710 ns 3257 bytes=268.435M bytes_per_second=1.13523T/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time 214836 ns 245426 ns 3257 bytes=268.435M bytes_per_second=1.13641T/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time 214853 ns 245574 ns 3257 bytes=268.435M bytes_per_second=1.13631T/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time 214886 ns 245909 ns 3257 bytes=268.435M bytes_per_second=1.13614T/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time_mean 214915 ns 245953 ns 5 bytes=268.435M bytes_per_second=1.13599T/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time_median 214886 ns 245909 ns 5 bytes=268.435M bytes_per_second=1.13614T/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time_stddev 89.3 ns 508 ns 5 bytes=0 bytes_per_second=494.952M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time_cv 0.04 % 0.21 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time 453232 ns 524905 ns 1588 bytes=536.871M bytes_per_second=1103.19G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time 440695 ns 512182 ns 1588 bytes=536.871M bytes_per_second=1.10798T/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time 453500 ns 525353 ns 1588 bytes=536.871M bytes_per_second=1102.54G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time 440889 ns 512359 ns 1588 bytes=536.871M bytes_per_second=1.10749T/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time 453921 ns 525651 ns 1588 bytes=536.871M bytes_per_second=1101.51G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time_mean 448447 ns 520090 ns 5 bytes=536.871M bytes_per_second=1115.18G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time_median 453232 ns 524905 ns 5 bytes=536.871M bytes_per_second=1103.19G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time_stddev 6993 ns 7143 ns 5 bytes=0 bytes_per_second=17.4886G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time_cv 1.56 % 1.37 % 5 bytes=0.00% bytes_per_second=1.57% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time 972824 ns 1223729 ns 717 bytes=1073.74M bytes_per_second=1027.94G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time 974089 ns 1224821 ns 717 bytes=1073.74M bytes_per_second=1026.6G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time 972402 ns 1222121 ns 717 bytes=1073.74M bytes_per_second=1028.38G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time 973439 ns 1223438 ns 717 bytes=1073.74M bytes_per_second=1027.29G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time 972168 ns 1222284 ns 717 bytes=1073.74M bytes_per_second=1028.63G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time_mean 972984 ns 1223279 ns 5 bytes=1073.74M bytes_per_second=1027.77G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time_median 972824 ns 1223438 ns 5 bytes=1073.74M bytes_per_second=1027.94G/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time_stddev 784 ns 1111 ns 5 bytes=0 bytes_per_second=847.917M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time_cv 0.08 % 0.09 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=-nan% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time 2265506 ns 2568235 ns 309 bytes=4.096k bytes_per_second=1.72423M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time 2272421 ns 2571938 ns 309 bytes=4.096k bytes_per_second=1.71898M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time 2273986 ns 2574609 ns 309 bytes=4.096k bytes_per_second=1.7178M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time 2267964 ns 2575473 ns 309 bytes=4.096k bytes_per_second=1.72236M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time 2267151 ns 2568997 ns 309 bytes=4.096k bytes_per_second=1.72298M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time_mean 2269406 ns 2571850 ns 5 bytes=4.096k bytes_per_second=1.72127M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time_median 2267964 ns 2571938 ns 5 bytes=4.096k bytes_per_second=1.72236M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time_stddev 3621 ns 3239 ns 5 bytes=0 bytes_per_second=2.8112k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time_cv 0.16 % 0.13 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time 2267224 ns 2574714 ns 309 bytes=8.192k bytes_per_second=3.44584M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time 2268232 ns 2570994 ns 309 bytes=8.192k bytes_per_second=3.44431M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time 2268663 ns 2582476 ns 309 bytes=8.192k bytes_per_second=3.44366M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time 2269102 ns 2571575 ns 309 bytes=8.192k bytes_per_second=3.44299M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time 2281240 ns 2584037 ns 309 bytes=8.192k bytes_per_second=3.42467M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time_mean 2270892 ns 2576759 ns 5 bytes=8.192k bytes_per_second=3.4403M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time_median 2268663 ns 2574714 ns 5 bytes=8.192k bytes_per_second=3.44366M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time_stddev 5826 ns 6123 ns 5 bytes=0 bytes_per_second=9.00865k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time_cv 0.26 % 0.24 % 5 bytes=0.00% bytes_per_second=0.26% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time 2275800 ns 2580011 ns 308 bytes=16.384k bytes_per_second=6.86572M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time 2281263 ns 2592676 ns 308 bytes=16.384k bytes_per_second=6.84928M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time 2275032 ns 2580110 ns 308 bytes=16.384k bytes_per_second=6.86803M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time 2274848 ns 2585220 ns 308 bytes=16.384k bytes_per_second=6.86859M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time 2275294 ns 2585997 ns 308 bytes=16.384k bytes_per_second=6.86724M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time_mean 2276448 ns 2584803 ns 5 bytes=16.384k bytes_per_second=6.86377M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time_median 2275294 ns 2585220 ns 5 bytes=16.384k bytes_per_second=6.86724M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time_stddev 2716 ns 5210 ns 5 bytes=0 bytes_per_second=8.37224k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time_cv 0.12 % 0.20 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time 2302359 ns 2610805 ns 306 bytes=32.768k bytes_per_second=13.573M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time 2289413 ns 2597791 ns 306 bytes=32.768k bytes_per_second=13.6498M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time 2289205 ns 2604025 ns 306 bytes=32.768k bytes_per_second=13.651M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time 2295670 ns 2604390 ns 306 bytes=32.768k bytes_per_second=13.6126M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time 2289917 ns 2605026 ns 306 bytes=32.768k bytes_per_second=13.6468M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time_mean 2293313 ns 2604408 ns 5 bytes=32.768k bytes_per_second=13.6266M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time_median 2289917 ns 2604390 ns 5 bytes=32.768k bytes_per_second=13.6468M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time_stddev 5723 ns 4616 ns 5 bytes=0 bytes_per_second=34.7521k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time_cv 0.25 % 0.18 % 5 bytes=0.00% bytes_per_second=0.25% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time 2322492 ns 2641698 ns 299 bytes=65.536k bytes_per_second=26.9107M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time 2329052 ns 2649004 ns 299 bytes=65.536k bytes_per_second=26.8349M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time 2328821 ns 2648170 ns 299 bytes=65.536k bytes_per_second=26.8376M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time 2327571 ns 2653615 ns 299 bytes=65.536k bytes_per_second=26.852M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time 2321720 ns 2647168 ns 299 bytes=65.536k bytes_per_second=26.9197M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time_mean 2325931 ns 2647931 ns 5 bytes=65.536k bytes_per_second=26.871M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time_median 2327571 ns 2648170 ns 5 bytes=65.536k bytes_per_second=26.852M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time_stddev 3548 ns 4270 ns 5 bytes=0 bytes_per_second=41.9896k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time_cv 0.15 % 0.16 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time 2383827 ns 2728789 ns 294 bytes=131.072k bytes_per_second=52.4367M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time 2383604 ns 2729527 ns 294 bytes=131.072k bytes_per_second=52.4416M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time 2389301 ns 2734680 ns 294 bytes=131.072k bytes_per_second=52.3166M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time 2382676 ns 2728524 ns 294 bytes=131.072k bytes_per_second=52.462M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time 2389460 ns 2730424 ns 294 bytes=131.072k bytes_per_second=52.3131M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time_mean 2385774 ns 2730389 ns 5 bytes=131.072k bytes_per_second=52.394M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time_median 2383827 ns 2729527 ns 5 bytes=131.072k bytes_per_second=52.4367M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time_stddev 3321 ns 2510 ns 5 bytes=0 bytes_per_second=74.6581k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time_cv 0.14 % 0.09 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time 2504979 ns 2880242 ns 280 bytes=262.144k bytes_per_second=99.8012M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time 2508195 ns 2880082 ns 280 bytes=262.144k bytes_per_second=99.6733M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time 2500289 ns 2870054 ns 280 bytes=262.144k bytes_per_second=99.9885M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time 2500853 ns 2876145 ns 280 bytes=262.144k bytes_per_second=99.9659M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time 2499519 ns 2874211 ns 280 bytes=262.144k bytes_per_second=100.019M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time_mean 2502767 ns 2876147 ns 5 bytes=262.144k bytes_per_second=99.8896M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time_median 2500853 ns 2876145 ns 5 bytes=262.144k bytes_per_second=99.9659M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time_stddev 3699 ns 4275 ns 5 bytes=0 bytes_per_second=151.032k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time_cv 0.15 % 0.15 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time 2587756 ns 3025108 ns 271 bytes=524.288k bytes_per_second=193.218M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time 2592051 ns 3029026 ns 271 bytes=524.288k bytes_per_second=192.897M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time 2588511 ns 3027313 ns 271 bytes=524.288k bytes_per_second=193.161M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time 2591188 ns 3024914 ns 271 bytes=524.288k bytes_per_second=192.962M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time 2586750 ns 3020682 ns 271 bytes=524.288k bytes_per_second=193.293M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time_mean 2589251 ns 3025409 ns 5 bytes=524.288k bytes_per_second=193.106M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time_median 2588511 ns 3025108 ns 5 bytes=524.288k bytes_per_second=193.161M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time_stddev 2271 ns 3138 ns 5 bytes=0 bytes_per_second=173.417k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time_cv 0.09 % 0.10 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time 2753440 ns 3327062 ns 255 bytes=1048.58k bytes_per_second=363.182M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time 2749324 ns 3321815 ns 255 bytes=1048.58k bytes_per_second=363.726M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time 2750920 ns 3321111 ns 255 bytes=1048.58k bytes_per_second=363.515M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time 2749008 ns 3320628 ns 255 bytes=1048.58k bytes_per_second=363.768M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time 2750689 ns 3319336 ns 255 bytes=1048.58k bytes_per_second=363.545M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time_mean 2750676 ns 3321990 ns 5 bytes=1048.58k bytes_per_second=363.547M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time_median 2750689 ns 3321111 ns 5 bytes=1048.58k bytes_per_second=363.545M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time_stddev 1754 ns 2976 ns 5 bytes=0 bytes_per_second=237.312k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time_cv 0.06 % 0.09 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time 3082004 ns 3969756 ns 226 bytes=2.09715M bytes_per_second=648.928M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time 3082627 ns 3976644 ns 226 bytes=2.09715M bytes_per_second=648.797M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time 3082757 ns 3977475 ns 226 bytes=2.09715M bytes_per_second=648.77M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time 3077627 ns 3964406 ns 226 bytes=2.09715M bytes_per_second=649.851M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time 3080808 ns 3973457 ns 226 bytes=2.09715M bytes_per_second=649.18M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time_mean 3081165 ns 3972347 ns 5 bytes=2.09715M bytes_per_second=649.105M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time_median 3082004 ns 3973457 ns 5 bytes=2.09715M bytes_per_second=648.928M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time_stddev 2122 ns 5380 ns 5 bytes=0 bytes_per_second=458.143k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time_cv 0.07 % 0.14 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time 3618581 ns 5032819 ns 193 bytes=4.1943M bytes_per_second=1105.41M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time 3617695 ns 5027162 ns 193 bytes=4.1943M bytes_per_second=1105.68M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time 3613692 ns 5023105 ns 193 bytes=4.1943M bytes_per_second=1106.9M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time 3620287 ns 5053151 ns 193 bytes=4.1943M bytes_per_second=1104.88M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time 3611683 ns 5020931 ns 193 bytes=4.1943M bytes_per_second=1107.52M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time_mean 3616388 ns 5031434 ns 5 bytes=4.1943M bytes_per_second=1106.08M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time_median 3617695 ns 5027162 ns 5 bytes=4.1943M bytes_per_second=1105.68M/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time_stddev 3575 ns 12956 ns 5 bytes=0 bytes_per_second=1120.01k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time_cv 0.10 % 0.26 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time 4930275 ns 7637082 ns 143 bytes=8.38861M bytes_per_second=1.5846G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time 4952542 ns 7656179 ns 143 bytes=8.38861M bytes_per_second=1.57747G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time 4944466 ns 7664083 ns 143 bytes=8.38861M bytes_per_second=1.58005G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time 4961774 ns 7677723 ns 143 bytes=8.38861M bytes_per_second=1.57454G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time 4941128 ns 7662014 ns 143 bytes=8.38861M bytes_per_second=1.58112G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time_mean 4946037 ns 7659416 ns 5 bytes=8.38861M bytes_per_second=1.57955G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time_median 4944466 ns 7662014 ns 5 bytes=8.38861M bytes_per_second=1.58005G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time_stddev 11885 ns 14773 ns 5 bytes=0 bytes_per_second=3.88637M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time_cv 0.24 % 0.19 % 5 bytes=0.00% bytes_per_second=0.24% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time 7995048 ns 13781672 ns 88 bytes=16.7772M bytes_per_second=1.95433G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time 7990682 ns 13790180 ns 88 bytes=16.7772M bytes_per_second=1.9554G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time 7987826 ns 13783975 ns 88 bytes=16.7772M bytes_per_second=1.9561G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time 8001477 ns 13793579 ns 88 bytes=16.7772M bytes_per_second=1.95276G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time 7999162 ns 13789241 ns 88 bytes=16.7772M bytes_per_second=1.95333G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time_mean 7994839 ns 13787729 ns 5 bytes=16.7772M bytes_per_second=1.95439G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time_median 7995048 ns 13789241 ns 5 bytes=16.7772M bytes_per_second=1.95433G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time_stddev 5685 ns 4830 ns 5 bytes=0 bytes_per_second=1.42304M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time_cv 0.07 % 0.04 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time 13578146 ns 25060329 ns 52 bytes=33.5544M bytes_per_second=2.30149G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time 13572595 ns 24997964 ns 52 bytes=33.5544M bytes_per_second=2.30243G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time 13595579 ns 25079058 ns 52 bytes=33.5544M bytes_per_second=2.29854G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time 13560730 ns 24959872 ns 52 bytes=33.5544M bytes_per_second=2.30445G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time 13564868 ns 25004917 ns 52 bytes=33.5544M bytes_per_second=2.30375G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time_mean 13574384 ns 25020428 ns 5 bytes=33.5544M bytes_per_second=2.30213G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time_median 13572595 ns 25004917 ns 5 bytes=33.5544M bytes_per_second=2.30243G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time_stddev 13634 ns 48584 ns 5 bytes=0 bytes_per_second=2.36636M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time_cv 0.10 % 0.19 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time 24551195 ns 47682737 ns 28 bytes=67.1089M bytes_per_second=2.5457G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time 24667676 ns 47669701 ns 28 bytes=67.1089M bytes_per_second=2.53368G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time 24626093 ns 47664403 ns 28 bytes=67.1089M bytes_per_second=2.53796G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time 24654710 ns 47663175 ns 28 bytes=67.1089M bytes_per_second=2.53501G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time 24592132 ns 47679811 ns 28 bytes=67.1089M bytes_per_second=2.54146G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time_mean 24618361 ns 47671965 ns 5 bytes=67.1089M bytes_per_second=2.53876G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time_median 24626093 ns 47669701 ns 5 bytes=67.1089M bytes_per_second=2.53796G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time_stddev 47466 ns 8905 ns 5 bytes=0 bytes_per_second=5.0159M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time_cv 0.19 % 0.02 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time 44878441 ns 86938621 ns 16 bytes=134.218M bytes_per_second=2.7853G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time 44930731 ns 86998784 ns 16 bytes=134.218M bytes_per_second=2.78206G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time 45045533 ns 86797669 ns 16 bytes=134.218M bytes_per_second=2.77497G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time 44967671 ns 87004492 ns 16 bytes=134.218M bytes_per_second=2.77977G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time 44860868 ns 86980766 ns 16 bytes=134.218M bytes_per_second=2.78639G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time_mean 44936649 ns 86944067 ns 5 bytes=134.218M bytes_per_second=2.7817G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time_median 44930731 ns 86980766 ns 5 bytes=134.218M bytes_per_second=2.78206G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time_stddev 74135 ns 85811 ns 5 bytes=0 bytes_per_second=4.69603M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time_cv 0.16 % 0.10 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time 85508892 ns 164378655 ns 8 bytes=268.435M bytes_per_second=2.92367G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time 84170997 ns 161371532 ns 8 bytes=268.435M bytes_per_second=2.97014G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time 85521609 ns 164376163 ns 8 bytes=268.435M bytes_per_second=2.92324G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time 85558866 ns 164563776 ns 8 bytes=268.435M bytes_per_second=2.92196G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time 85441146 ns 164508758 ns 8 bytes=268.435M bytes_per_second=2.92599G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time_mean 85240302 ns 163839777 ns 5 bytes=268.435M bytes_per_second=2.933G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time_median 85508892 ns 164378655 ns 5 bytes=268.435M bytes_per_second=2.92367G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time_stddev 599272 ns 1382212 ns 5 bytes=0 bytes_per_second=21.3136M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time_cv 0.70 % 0.84 % 5 bytes=0.00% bytes_per_second=0.71% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time 166648518 ns 311345297 ns 4 bytes=536.871M bytes_per_second=3.00033G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time 163435485 ns 306504040 ns 4 bytes=536.871M bytes_per_second=3.05931G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time 166662153 ns 311330703 ns 4 bytes=536.871M bytes_per_second=3.00008G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time 163851034 ns 307093831 ns 4 bytes=536.871M bytes_per_second=3.05155G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time 166600700 ns 311354980 ns 4 bytes=536.871M bytes_per_second=3.00119G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time_mean 165439578 ns 309525770 ns 5 bytes=536.871M bytes_per_second=3.02249G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time_median 166600700 ns 311330703 ns 5 bytes=536.871M bytes_per_second=3.00119G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time_stddev 1646534 ns 2497982 ns 5 bytes=0 bytes_per_second=30.9222M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time_cv 1.00 % 0.81 % 5 bytes=0.00% bytes_per_second=1.00% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time 318338364 ns 558395677 ns 2 bytes=1073.74M bytes_per_second=3.14131G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time 318841651 ns 557233087 ns 2 bytes=1073.74M bytes_per_second=3.13635G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time 318647563 ns 558022712 ns 2 bytes=1073.74M bytes_per_second=3.13826G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time 318757638 ns 558239243 ns 2 bytes=1073.74M bytes_per_second=3.13718G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time 319398612 ns 559735585 ns 2 bytes=1073.74M bytes_per_second=3.13088G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time_mean 318796766 ns 558325261 ns 5 bytes=1073.74M bytes_per_second=3.1368G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time_median 318757638 ns 558239243 ns 5 bytes=1073.74M bytes_per_second=3.13718G/s dst_gpu=1 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time_stddev 386703 ns 906332 ns 5 bytes=0 bytes_per_second=3.89387M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time_cv 0.12 % 0.16 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time 2267109 ns 2577265 ns 308 bytes=4.096k bytes_per_second=1.72301M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time 2266777 ns 2582286 ns 308 bytes=4.096k bytes_per_second=1.72326M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time 2274421 ns 2585289 ns 308 bytes=4.096k bytes_per_second=1.71747M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time 2266242 ns 2582638 ns 308 bytes=4.096k bytes_per_second=1.72367M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time 2266883 ns 2583129 ns 308 bytes=4.096k bytes_per_second=1.72318M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time_mean 2268287 ns 2582121 ns 5 bytes=4.096k bytes_per_second=1.72212M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time_median 2266883 ns 2582638 ns 5 bytes=4.096k bytes_per_second=1.72318M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time_stddev 3444 ns 2955 ns 5 bytes=0 bytes_per_second=2.67232k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time_cv 0.15 % 0.11 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time 2274173 ns 2587291 ns 309 bytes=8.192k bytes_per_second=3.43532M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time 2275076 ns 2589432 ns 309 bytes=8.192k bytes_per_second=3.43395M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time 2268231 ns 2586805 ns 309 bytes=8.192k bytes_per_second=3.44431M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time 2267587 ns 2586160 ns 309 bytes=8.192k bytes_per_second=3.44529M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time 2268353 ns 2586022 ns 309 bytes=8.192k bytes_per_second=3.44413M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time_mean 2270684 ns 2587142 ns 5 bytes=8.192k bytes_per_second=3.4406M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time_median 2268353 ns 2586805 ns 5 bytes=8.192k bytes_per_second=3.44413M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time_stddev 3623 ns 1378 ns 5 bytes=0 bytes_per_second=5.61819k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time_cv 0.16 % 0.05 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time 2276336 ns 2598540 ns 308 bytes=16.384k bytes_per_second=6.8641M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time 2281543 ns 2598616 ns 308 bytes=16.384k bytes_per_second=6.84843M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time 2275808 ns 2597193 ns 308 bytes=16.384k bytes_per_second=6.86569M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time 2275550 ns 2597895 ns 308 bytes=16.384k bytes_per_second=6.86647M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time 2283613 ns 2599973 ns 308 bytes=16.384k bytes_per_second=6.84223M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time_mean 2278570 ns 2598444 ns 5 bytes=16.384k bytes_per_second=6.85739M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time_median 2276336 ns 2598540 ns 5 bytes=16.384k bytes_per_second=6.8641M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time_stddev 3742 ns 1030 ns 5 bytes=0 bytes_per_second=11.5236k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time_cv 0.16 % 0.04 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time 2289422 ns 2615712 ns 306 bytes=32.768k bytes_per_second=13.6497M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time 2298210 ns 2619622 ns 306 bytes=32.768k bytes_per_second=13.5975M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time 2294842 ns 2614707 ns 306 bytes=32.768k bytes_per_second=13.6175M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time 2295171 ns 2615991 ns 306 bytes=32.768k bytes_per_second=13.6155M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time 2289223 ns 2615764 ns 306 bytes=32.768k bytes_per_second=13.6509M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time_mean 2293374 ns 2616359 ns 5 bytes=32.768k bytes_per_second=13.6262M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time_median 2294842 ns 2615764 ns 5 bytes=32.768k bytes_per_second=13.6175M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time_stddev 3925 ns 1890 ns 5 bytes=0 bytes_per_second=23.8822k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time_cv 0.17 % 0.07 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time 2333362 ns 2664028 ns 301 bytes=65.536k bytes_per_second=26.7854M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time 2323780 ns 2661647 ns 301 bytes=65.536k bytes_per_second=26.8958M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time 2324302 ns 2655250 ns 301 bytes=65.536k bytes_per_second=26.8898M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time 2331787 ns 2663829 ns 301 bytes=65.536k bytes_per_second=26.8035M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time 2332266 ns 2663912 ns 301 bytes=65.536k bytes_per_second=26.798M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time_mean 2329099 ns 2661733 ns 5 bytes=65.536k bytes_per_second=26.8345M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time_median 2331787 ns 2663829 ns 5 bytes=65.536k bytes_per_second=26.8035M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time_stddev 4656 ns 3757 ns 5 bytes=0 bytes_per_second=54.9718k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time_cv 0.20 % 0.14 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time 2391621 ns 2745982 ns 294 bytes=131.072k bytes_per_second=52.2658M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time 2383214 ns 2741977 ns 294 bytes=131.072k bytes_per_second=52.4502M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time 2388842 ns 2743356 ns 294 bytes=131.072k bytes_per_second=52.3266M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time 2370487 ns 2725111 ns 294 bytes=131.072k bytes_per_second=52.7318M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time 2377181 ns 2729244 ns 294 bytes=131.072k bytes_per_second=52.5833M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time_mean 2382269 ns 2737134 ns 5 bytes=131.072k bytes_per_second=52.4715M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time_median 2383214 ns 2741977 ns 5 bytes=131.072k bytes_per_second=52.4502M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time_stddev 8606 ns 9317 ns 5 bytes=0 bytes_per_second=194.291k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time_cv 0.36 % 0.34 % 5 bytes=0.00% bytes_per_second=0.36% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time 2489932 ns 2872020 ns 280 bytes=262.144k bytes_per_second=100.404M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time 2504167 ns 2882406 ns 280 bytes=262.144k bytes_per_second=99.8336M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time 2490031 ns 2871297 ns 280 bytes=262.144k bytes_per_second=100.4M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time 2489923 ns 2870651 ns 280 bytes=262.144k bytes_per_second=100.405M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time 2506074 ns 2882146 ns 280 bytes=262.144k bytes_per_second=99.7576M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time_mean 2496025 ns 2875704 ns 5 bytes=262.144k bytes_per_second=100.16M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time_median 2490031 ns 2872020 ns 5 bytes=262.144k bytes_per_second=100.4M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time_stddev 8330 ns 6020 ns 5 bytes=0 bytes_per_second=341.851k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time_cv 0.33 % 0.21 % 5 bytes=0.00% bytes_per_second=0.33% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time 2600794 ns 3045386 ns 270 bytes=524.288k bytes_per_second=192.249M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time 2598713 ns 3043765 ns 270 bytes=524.288k bytes_per_second=192.403M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time 2598070 ns 3047606 ns 270 bytes=524.288k bytes_per_second=192.451M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time 2599252 ns 3043946 ns 270 bytes=524.288k bytes_per_second=192.363M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time 2594850 ns 3043085 ns 270 bytes=524.288k bytes_per_second=192.689M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time_mean 2598336 ns 3044758 ns 5 bytes=524.288k bytes_per_second=192.431M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time_median 2598713 ns 3043946 ns 5 bytes=524.288k bytes_per_second=192.403M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time_stddev 2193 ns 1799 ns 5 bytes=0 bytes_per_second=166.433k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time_cv 0.08 % 0.06 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time 2754212 ns 3339222 ns 253 bytes=1048.58k bytes_per_second=363.08M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time 2756270 ns 3340896 ns 253 bytes=1048.58k bytes_per_second=362.809M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time 2755558 ns 3341227 ns 253 bytes=1048.58k bytes_per_second=362.903M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time 2758633 ns 3342184 ns 253 bytes=1048.58k bytes_per_second=362.498M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time 2757194 ns 3340346 ns 253 bytes=1048.58k bytes_per_second=362.688M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time_mean 2756374 ns 3340775 ns 5 bytes=1048.58k bytes_per_second=362.796M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time_median 2756270 ns 3340896 ns 5 bytes=1048.58k bytes_per_second=362.809M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time_stddev 1668 ns 1095 ns 5 bytes=0 bytes_per_second=224.811k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time_cv 0.06 % 0.03 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time 3104734 ns 4017232 ns 226 bytes=2.09715M bytes_per_second=644.178M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time 3098664 ns 4005653 ns 226 bytes=2.09715M bytes_per_second=645.44M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time 3097112 ns 4006026 ns 226 bytes=2.09715M bytes_per_second=645.763M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time 3096089 ns 4014080 ns 226 bytes=2.09715M bytes_per_second=645.976M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time 3098336 ns 4008377 ns 226 bytes=2.09715M bytes_per_second=645.508M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time_mean 3098987 ns 4010273 ns 5 bytes=2.09715M bytes_per_second=645.373M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time_median 3098336 ns 4008377 ns 5 bytes=2.09715M bytes_per_second=645.508M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time_stddev 3372 ns 5146 ns 5 bytes=0 bytes_per_second=718.183k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time_cv 0.11 % 0.13 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time 3620732 ns 5088592 ns 192 bytes=4.1943M bytes_per_second=1104.75M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time 3621080 ns 5083016 ns 192 bytes=4.1943M bytes_per_second=1104.64M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time 3615392 ns 5077391 ns 192 bytes=4.1943M bytes_per_second=1106.38M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time 3614682 ns 5078419 ns 192 bytes=4.1943M bytes_per_second=1106.6M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time 3616863 ns 5077186 ns 192 bytes=4.1943M bytes_per_second=1105.93M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time_mean 3617750 ns 5080921 ns 5 bytes=4.1943M bytes_per_second=1105.66M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time_median 3616863 ns 5078419 ns 5 bytes=4.1943M bytes_per_second=1105.93M/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time_stddev 2989 ns 4896 ns 5 bytes=0 bytes_per_second=935.348k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time_cv 0.08 % 0.10 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time 4990756 ns 7787999 ns 142 bytes=8.38861M bytes_per_second=1.56539G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time 5482726 ns 8474841 ns 142 bytes=8.38861M bytes_per_second=1.42493G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time 4933885 ns 7709488 ns 142 bytes=8.38861M bytes_per_second=1.58344G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time 4933310 ns 7702077 ns 142 bytes=8.38861M bytes_per_second=1.58362G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time 4987782 ns 7789324 ns 142 bytes=8.38861M bytes_per_second=1.56633G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time_mean 5065692 ns 7892746 ns 5 bytes=8.38861M bytes_per_second=1.54474G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time_median 4987782 ns 7787999 ns 5 bytes=8.38861M bytes_per_second=1.56633G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time_stddev 234787 ns 328040 ns 5 bytes=0 bytes_per_second=69.1795M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time_cv 4.63 % 4.16 % 5 bytes=0.00% bytes_per_second=4.37% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time 7824164 ns 13358113 ns 87 bytes=16.7772M bytes_per_second=1.99702G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time 7800569 ns 13328028 ns 87 bytes=16.7772M bytes_per_second=2.00306G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time 7915431 ns 13513201 ns 87 bytes=16.7772M bytes_per_second=1.97399G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time 7794364 ns 13308866 ns 87 bytes=16.7772M bytes_per_second=2.00465G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time 7857693 ns 13417982 ns 87 bytes=16.7772M bytes_per_second=1.9885G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time_mean 7838444 ns 13385238 ns 5 bytes=16.7772M bytes_per_second=1.99344G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time_median 7824164 ns 13358113 ns 5 bytes=16.7772M bytes_per_second=1.99702G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time_stddev 49697 ns 82595 ns 5 bytes=0 bytes_per_second=12.889M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time_cv 0.63 % 0.62 % 5 bytes=0.00% bytes_per_second=0.63% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time 13676612 ns 25044001 ns 51 bytes=33.5544M bytes_per_second=2.28492G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time 13645245 ns 25002784 ns 51 bytes=33.5544M bytes_per_second=2.29018G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time 13616006 ns 24942149 ns 51 bytes=33.5544M bytes_per_second=2.29509G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time 13663645 ns 25083935 ns 51 bytes=33.5544M bytes_per_second=2.28709G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time 13613424 ns 24942750 ns 51 bytes=33.5544M bytes_per_second=2.29553G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time_mean 13642986 ns 25003124 ns 5 bytes=33.5544M bytes_per_second=2.29056G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time_median 13645245 ns 25002784 ns 5 bytes=33.5544M bytes_per_second=2.29018G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time_stddev 28127 ns 62379 ns 5 bytes=0 bytes_per_second=4.83547M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time_cv 0.21 % 0.25 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time 25437473 ns 48407711 ns 27 bytes=67.1089M bytes_per_second=2.45701G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time 25253418 ns 48171635 ns 27 bytes=67.1089M bytes_per_second=2.47491G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time 25287617 ns 48209219 ns 27 bytes=67.1089M bytes_per_second=2.47157G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time 25397805 ns 48330570 ns 27 bytes=67.1089M bytes_per_second=2.46084G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time 25444495 ns 48431633 ns 27 bytes=67.1089M bytes_per_second=2.45633G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time_mean 25364161 ns 48310153 ns 5 bytes=67.1089M bytes_per_second=2.46413G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time_median 25397805 ns 48330570 ns 5 bytes=67.1089M bytes_per_second=2.46084G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time_stddev 88152 ns 116261 ns 5 bytes=0 bytes_per_second=8.77904M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time_cv 0.35 % 0.24 % 5 bytes=0.00% bytes_per_second=0.35% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time 46092402 ns 88279593 ns 15 bytes=134.218M bytes_per_second=2.71194G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time 46236744 ns 88365770 ns 15 bytes=134.218M bytes_per_second=2.70348G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time 46033927 ns 88142472 ns 15 bytes=134.218M bytes_per_second=2.71539G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time 45941819 ns 88011631 ns 15 bytes=134.218M bytes_per_second=2.72083G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time 45961532 ns 88250390 ns 15 bytes=134.218M bytes_per_second=2.71967G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time_mean 46053285 ns 88209971 ns 5 bytes=134.218M bytes_per_second=2.71426G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time_median 46033927 ns 88250390 ns 5 bytes=134.218M bytes_per_second=2.71539G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time_stddev 118749 ns 136610 ns 5 bytes=0 bytes_per_second=7.15556M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time_cv 0.26 % 0.15 % 5 bytes=0.00% bytes_per_second=0.26% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time 88145244 ns 168299750 ns 8 bytes=268.435M bytes_per_second=2.83623G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time 87316601 ns 166904242 ns 8 bytes=268.435M bytes_per_second=2.86314G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time 87381477 ns 167053900 ns 8 bytes=268.435M bytes_per_second=2.86102G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time 87145379 ns 166797766 ns 8 bytes=268.435M bytes_per_second=2.86877G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time 88227984 ns 168809744 ns 8 bytes=268.435M bytes_per_second=2.83357G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time_mean 87643337 ns 167573080 ns 5 bytes=268.435M bytes_per_second=2.85255G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time_median 87381477 ns 167053900 ns 5 bytes=268.435M bytes_per_second=2.86102G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time_stddev 504235 ns 918612 ns 5 bytes=0 bytes_per_second=16.7772M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time_cv 0.58 % 0.55 % 5 bytes=0.00% bytes_per_second=0.57% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time 167924918 ns 312321152 ns 4 bytes=536.871M bytes_per_second=2.97752G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time 169558737 ns 316243647 ns 4 bytes=536.871M bytes_per_second=2.94883G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time 168952644 ns 313711709 ns 4 bytes=536.871M bytes_per_second=2.95941G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time 169789772 ns 316468666 ns 4 bytes=536.871M bytes_per_second=2.94482G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time 169580199 ns 314939682 ns 4 bytes=536.871M bytes_per_second=2.94846G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time_mean 169161254 ns 314736971 ns 5 bytes=536.871M bytes_per_second=2.95581G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time_median 169558737 ns 314939682 ns 5 bytes=536.871M bytes_per_second=2.94883G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time_stddev 758384 ns 1746230 ns 5 bytes=0 bytes_per_second=13.6227M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time_cv 0.45 % 0.55 % 5 bytes=0.00% bytes_per_second=0.45% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time 329608291 ns 574571736 ns 2 bytes=1073.74M bytes_per_second=3.0339G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time 328888834 ns 574699702 ns 2 bytes=1073.74M bytes_per_second=3.04054G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time 330220759 ns 577935094 ns 2 bytes=1073.74M bytes_per_second=3.02828G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time 328314990 ns 573911880 ns 2 bytes=1073.74M bytes_per_second=3.04586G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time 329150751 ns 572786345 ns 2 bytes=1073.74M bytes_per_second=3.03812G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time_mean 329236725 ns 574780951 ns 5 bytes=1073.74M bytes_per_second=3.03734G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time_median 329150751 ns 574571736 ns 5 bytes=1073.74M bytes_per_second=3.03812G/s dst_gpu=2 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time_stddev 721873 ns 1919162 ns 5 bytes=0 bytes_per_second=6.81766M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time_cv 0.22 % 0.33 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time 2256473 ns 2567115 ns 309 bytes=4.096k bytes_per_second=1.73113M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time 2263096 ns 2581929 ns 309 bytes=4.096k bytes_per_second=1.72606M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time 2257136 ns 2569034 ns 309 bytes=4.096k bytes_per_second=1.73062M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time 2262698 ns 2574587 ns 309 bytes=4.096k bytes_per_second=1.72637M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time 2264208 ns 2576745 ns 309 bytes=4.096k bytes_per_second=1.72522M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time_mean 2260722 ns 2573882 ns 5 bytes=4.096k bytes_per_second=1.72788M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time_median 2262698 ns 2574587 ns 5 bytes=4.096k bytes_per_second=1.72637M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time_stddev 3627 ns 5974 ns 5 bytes=0 bytes_per_second=2.83991k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time_cv 0.16 % 0.23 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time 2261918 ns 2583533 ns 310 bytes=8.192k bytes_per_second=3.45393M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time 2267972 ns 2584051 ns 310 bytes=8.192k bytes_per_second=3.44471M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time 2268827 ns 2584146 ns 310 bytes=8.192k bytes_per_second=3.44341M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time 2260606 ns 2581919 ns 310 bytes=8.192k bytes_per_second=3.45593M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time 2267151 ns 2582693 ns 310 bytes=8.192k bytes_per_second=3.44596M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time_mean 2265295 ns 2583268 ns 5 bytes=8.192k bytes_per_second=3.44879M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time_median 2267151 ns 2583533 ns 5 bytes=8.192k bytes_per_second=3.44596M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time_stddev 3757 ns 949 ns 5 bytes=0 bytes_per_second=5.86114k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time_cv 0.17 % 0.04 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time 2277734 ns 2596218 ns 308 bytes=16.384k bytes_per_second=6.85989M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time 2269385 ns 2594616 ns 308 bytes=16.384k bytes_per_second=6.88512M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time 2269517 ns 2593189 ns 308 bytes=16.384k bytes_per_second=6.88472M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time 2276364 ns 2594824 ns 308 bytes=16.384k bytes_per_second=6.86402M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time 2277429 ns 2595465 ns 308 bytes=16.384k bytes_per_second=6.86081M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time_mean 2274086 ns 2594862 ns 5 bytes=16.384k bytes_per_second=6.87091M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time_median 2276364 ns 2594824 ns 5 bytes=16.384k bytes_per_second=6.86402M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time_stddev 4261 ns 1125 ns 5 bytes=0 bytes_per_second=13.192k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time_cv 0.19 % 0.04 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time 2290351 ns 2612905 ns 306 bytes=32.768k bytes_per_second=13.6442M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time 2283343 ns 2612850 ns 306 bytes=32.768k bytes_per_second=13.6861M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time 2283059 ns 2611784 ns 306 bytes=32.768k bytes_per_second=13.6878M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time 2288992 ns 2611297 ns 306 bytes=32.768k bytes_per_second=13.6523M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time 2282601 ns 2605390 ns 306 bytes=32.768k bytes_per_second=13.6905M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time_mean 2285669 ns 2610845 ns 5 bytes=32.768k bytes_per_second=13.6722M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time_median 2283343 ns 2611784 ns 5 bytes=32.768k bytes_per_second=13.6861M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time_stddev 3694 ns 3127 ns 5 bytes=0 bytes_per_second=22.6149k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time_cv 0.16 % 0.12 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time 2322503 ns 2652522 ns 299 bytes=65.536k bytes_per_second=26.9106M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time 2322210 ns 2655450 ns 299 bytes=65.536k bytes_per_second=26.914M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time 2326204 ns 2658945 ns 299 bytes=65.536k bytes_per_second=26.8678M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time 2316714 ns 2649812 ns 299 bytes=65.536k bytes_per_second=26.9779M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time 2316583 ns 2655597 ns 299 bytes=65.536k bytes_per_second=26.9794M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time_mean 2320843 ns 2654465 ns 5 bytes=65.536k bytes_per_second=26.9299M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time_median 2322210 ns 2655450 ns 5 bytes=65.536k bytes_per_second=26.914M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time_stddev 4140 ns 3455 ns 5 bytes=0 bytes_per_second=49.1892k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time_cv 0.18 % 0.13 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time 2390258 ns 2751552 ns 293 bytes=131.072k bytes_per_second=52.2956M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time 2387673 ns 2748423 ns 293 bytes=131.072k bytes_per_second=52.3522M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time 2389086 ns 2749838 ns 293 bytes=131.072k bytes_per_second=52.3213M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time 2383639 ns 2737985 ns 293 bytes=131.072k bytes_per_second=52.4408M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time 2387022 ns 2741629 ns 293 bytes=131.072k bytes_per_second=52.3665M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time_mean 2387535 ns 2745885 ns 5 bytes=131.072k bytes_per_second=52.3553M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time_median 2387673 ns 2748423 ns 5 bytes=131.072k bytes_per_second=52.3522M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time_stddev 2514 ns 5803 ns 5 bytes=0 bytes_per_second=56.4894k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time_cv 0.11 % 0.21 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time 2498201 ns 2878847 ns 281 bytes=262.144k bytes_per_second=100.072M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time 2494879 ns 2880254 ns 281 bytes=262.144k bytes_per_second=100.205M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time 2495317 ns 2875127 ns 281 bytes=262.144k bytes_per_second=100.188M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time 2501731 ns 2882132 ns 281 bytes=262.144k bytes_per_second=99.9308M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time 2499107 ns 2884185 ns 281 bytes=262.144k bytes_per_second=100.036M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time_mean 2497847 ns 2880109 ns 5 bytes=262.144k bytes_per_second=100.086M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time_median 2498201 ns 2880254 ns 5 bytes=262.144k bytes_per_second=100.072M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time_stddev 2829 ns 3433 ns 5 bytes=0 bytes_per_second=116.031k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time_cv 0.11 % 0.12 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time 2594277 ns 3048925 ns 270 bytes=524.288k bytes_per_second=192.732M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time 2592335 ns 3040826 ns 270 bytes=524.288k bytes_per_second=192.876M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time 2588518 ns 3042525 ns 270 bytes=524.288k bytes_per_second=193.161M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time 2592948 ns 3043730 ns 270 bytes=524.288k bytes_per_second=192.831M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time 2591919 ns 3049049 ns 270 bytes=524.288k bytes_per_second=192.907M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time_mean 2592000 ns 3045011 ns 5 bytes=524.288k bytes_per_second=192.901M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time_median 2592335 ns 3043730 ns 5 bytes=524.288k bytes_per_second=192.876M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time_stddev 2141 ns 3774 ns 5 bytes=0 bytes_per_second=163.232k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time_cv 0.08 % 0.12 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time 2750742 ns 3342957 ns 255 bytes=1048.58k bytes_per_second=363.538M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time 2745000 ns 3336459 ns 255 bytes=1048.58k bytes_per_second=364.299M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time 2752856 ns 3343587 ns 255 bytes=1048.58k bytes_per_second=363.259M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time 2744397 ns 3335074 ns 255 bytes=1048.58k bytes_per_second=364.379M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time 2751016 ns 3340488 ns 255 bytes=1048.58k bytes_per_second=363.502M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time_mean 2748802 ns 3339713 ns 5 bytes=1048.58k bytes_per_second=363.795M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time_median 2750742 ns 3340488 ns 5 bytes=1048.58k bytes_per_second=363.538M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time_stddev 3839 ns 3816 ns 5 bytes=0 bytes_per_second=520.499k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time_cv 0.14 % 0.11 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time 3089884 ns 4004551 ns 227 bytes=2.09715M bytes_per_second=647.274M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time 3087176 ns 3995670 ns 227 bytes=2.09715M bytes_per_second=647.841M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time 3086930 ns 4007294 ns 227 bytes=2.09715M bytes_per_second=647.893M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time 3073193 ns 3993304 ns 227 bytes=2.09715M bytes_per_second=650.789M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time 3090395 ns 4005373 ns 227 bytes=2.09715M bytes_per_second=647.166M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time_mean 3085516 ns 4001238 ns 5 bytes=2.09715M bytes_per_second=648.193M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time_median 3087176 ns 4004551 ns 5 bytes=2.09715M bytes_per_second=647.841M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time_stddev 7062 ns 6299 ns 5 bytes=0 bytes_per_second=1.48757M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time_cv 0.23 % 0.16 % 5 bytes=0.00% bytes_per_second=0.23% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time 3614123 ns 5080425 ns 194 bytes=4.1943M bytes_per_second=1106.77M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time 3610886 ns 5073591 ns 194 bytes=4.1943M bytes_per_second=1107.76M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time 3608067 ns 5064061 ns 194 bytes=4.1943M bytes_per_second=1108.63M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time 3608085 ns 5066164 ns 194 bytes=4.1943M bytes_per_second=1108.62M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time 3620230 ns 5081833 ns 194 bytes=4.1943M bytes_per_second=1104.9M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time_mean 3612278 ns 5073215 ns 5 bytes=4.1943M bytes_per_second=1107.34M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time_median 3610886 ns 5073591 ns 5 bytes=4.1943M bytes_per_second=1107.76M/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time_stddev 5096 ns 8061 ns 5 bytes=0 bytes_per_second=1.56081M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time_cv 0.14 % 0.16 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time 4880291 ns 7537339 ns 144 bytes=8.38861M bytes_per_second=1.60083G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time 4917750 ns 7585898 ns 144 bytes=8.38861M bytes_per_second=1.58863G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time 4909341 ns 7579111 ns 144 bytes=8.38861M bytes_per_second=1.59135G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time 4901292 ns 7575289 ns 144 bytes=8.38861M bytes_per_second=1.59397G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time 4970742 ns 7668167 ns 144 bytes=8.38861M bytes_per_second=1.5717G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time_mean 4915883 ns 7589161 ns 5 bytes=8.38861M bytes_per_second=1.5893G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time_median 4909341 ns 7579111 ns 5 bytes=8.38861M bytes_per_second=1.59135G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time_stddev 33673 ns 48041 ns 5 bytes=0 bytes_per_second=11.0903M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time_cv 0.68 % 0.63 % 5 bytes=0.00% bytes_per_second=0.68% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time 7825991 ns 13335226 ns 87 bytes=16.7772M bytes_per_second=1.99655G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time 7980839 ns 13629689 ns 87 bytes=16.7772M bytes_per_second=1.95781G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time 7810594 ns 13303862 ns 87 bytes=16.7772M bytes_per_second=2.00049G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time 7840700 ns 13351153 ns 87 bytes=16.7772M bytes_per_second=1.99281G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time 7834260 ns 13329062 ns 87 bytes=16.7772M bytes_per_second=1.99444G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time_mean 7858477 ns 13389798 ns 5 bytes=16.7772M bytes_per_second=1.98842G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time_median 7834260 ns 13335226 ns 5 bytes=16.7772M bytes_per_second=1.99444G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time_stddev 69324 ns 135179 ns 5 bytes=0 bytes_per_second=17.7659M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time_cv 0.88 % 1.01 % 5 bytes=0.00% bytes_per_second=0.87% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time 13672613 ns 24968078 ns 51 bytes=33.5544M bytes_per_second=2.28559G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time 13693165 ns 25002987 ns 51 bytes=33.5544M bytes_per_second=2.28216G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time 13715001 ns 25056507 ns 51 bytes=33.5544M bytes_per_second=2.27853G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time 13691515 ns 24982934 ns 51 bytes=33.5544M bytes_per_second=2.28244G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time 13652632 ns 24959068 ns 51 bytes=33.5544M bytes_per_second=2.28894G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time_mean 13684985 ns 24993915 ns 5 bytes=33.5544M bytes_per_second=2.28353G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time_median 13691515 ns 24982934 ns 5 bytes=33.5544M bytes_per_second=2.28244G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time_stddev 23507 ns 38738 ns 5 bytes=0 bytes_per_second=4.01766M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time_cv 0.17 % 0.15 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time 25427313 ns 48171502 ns 27 bytes=67.1089M bytes_per_second=2.45799G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time 24921568 ns 46943311 ns 27 bytes=67.1089M bytes_per_second=2.50787G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time 25441998 ns 48323660 ns 27 bytes=67.1089M bytes_per_second=2.45657G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time 25248314 ns 48132400 ns 27 bytes=67.1089M bytes_per_second=2.47541G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time 25356415 ns 48299337 ns 27 bytes=67.1089M bytes_per_second=2.46486G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time_mean 25279122 ns 47974042 ns 5 bytes=67.1089M bytes_per_second=2.47254G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time_median 25356415 ns 48171502 ns 5 bytes=67.1089M bytes_per_second=2.46486G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time_stddev 214043 ns 581920 ns 5 bytes=0 bytes_per_second=21.6147M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time_cv 0.85 % 1.21 % 5 bytes=0.00% bytes_per_second=0.85% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time 45987235 ns 88157721 ns 15 bytes=134.218M bytes_per_second=2.71815G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time 45855277 ns 88001038 ns 15 bytes=134.218M bytes_per_second=2.72597G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time 45749730 ns 87897971 ns 15 bytes=134.218M bytes_per_second=2.73226G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time 45909113 ns 88082366 ns 15 bytes=134.218M bytes_per_second=2.72277G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time 47342443 ns 90707495 ns 15 bytes=134.218M bytes_per_second=2.64034G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time_mean 46168760 ns 88569318 ns 5 bytes=134.218M bytes_per_second=2.7079G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time_median 45909113 ns 88082366 ns 5 bytes=134.218M bytes_per_second=2.72277G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time_stddev 661770 ns 1199165 ns 5 bytes=0 bytes_per_second=39.0283M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time_cv 1.43 % 1.35 % 5 bytes=0.00% bytes_per_second=1.41% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time 87171311 ns 166876899 ns 8 bytes=268.435M bytes_per_second=2.86792G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time 87371035 ns 166982982 ns 8 bytes=268.435M bytes_per_second=2.86136G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time 87616495 ns 168227841 ns 8 bytes=268.435M bytes_per_second=2.85334G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time 86928852 ns 166393818 ns 8 bytes=268.435M bytes_per_second=2.87592G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time 87251216 ns 166903782 ns 8 bytes=268.435M bytes_per_second=2.86529G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time_mean 87267782 ns 167077065 ns 5 bytes=268.435M bytes_per_second=2.86476G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time_median 87251216 ns 166903782 ns 5 bytes=268.435M bytes_per_second=2.86529G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time_stddev 253336 ns 683750 ns 5 bytes=0 bytes_per_second=8.51463M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time_cv 0.29 % 0.41 % 5 bytes=0.00% bytes_per_second=0.29% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time 169687886 ns 315706254 ns 4 bytes=536.871M bytes_per_second=2.94659G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time 168658596 ns 313163885 ns 4 bytes=536.871M bytes_per_second=2.96457G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time 169796485 ns 316325916 ns 4 bytes=536.871M bytes_per_second=2.9447G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time 168490160 ns 313157971 ns 4 bytes=536.871M bytes_per_second=2.96753G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time 169254530 ns 315526465 ns 4 bytes=536.871M bytes_per_second=2.95413G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time_mean 169177531 ns 314776098 ns 5 bytes=536.871M bytes_per_second=2.9555G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time_median 169254530 ns 315526465 ns 5 bytes=536.871M bytes_per_second=2.95413G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time_stddev 589760 ns 1503973 ns 5 bytes=0 bytes_per_second=10.5545M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time_cv 0.35 % 0.48 % 5 bytes=0.00% bytes_per_second=0.35% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time 386856958 ns 627763633 ns 2 bytes=1073.74M bytes_per_second=2.58493G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time 319344625 ns 559117074 ns 2 bytes=1073.74M bytes_per_second=3.13141G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time 319744542 ns 560244785 ns 2 bytes=1073.74M bytes_per_second=3.1275G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time 320950866 ns 561417378 ns 2 bytes=1073.74M bytes_per_second=3.11574G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time 320258692 ns 560558972 ns 2 bytes=1073.74M bytes_per_second=3.12248G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time_mean 333431137 ns 573820368 ns 5 bytes=1073.74M bytes_per_second=3.01641G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time_median 320258692 ns 560558972 ns 5 bytes=1073.74M bytes_per_second=3.12248G/s dst_gpu=3 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time_stddev 29871983 ns 30166446 ns 5 bytes=0 bytes_per_second=247.065M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time_cv 8.96 % 5.26 % 5 bytes=0.00% bytes_per_second=8.00% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time 2255736 ns 2573717 ns 310 bytes=4.096k bytes_per_second=1.7317M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time 2259498 ns 2580886 ns 310 bytes=4.096k bytes_per_second=1.72881M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time 2258696 ns 2576459 ns 310 bytes=4.096k bytes_per_second=1.72943M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time 2261351 ns 2578826 ns 310 bytes=4.096k bytes_per_second=1.7274M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time 2256809 ns 2578153 ns 310 bytes=4.096k bytes_per_second=1.73087M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time_mean 2258418 ns 2577608 ns 5 bytes=4.096k bytes_per_second=1.72964M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time_median 2258696 ns 2578153 ns 5 bytes=4.096k bytes_per_second=1.72943M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time_stddev 2215 ns 2692 ns 5 bytes=0 bytes_per_second=1.7371k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time_cv 0.10 % 0.10 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time 2261053 ns 2577695 ns 310 bytes=8.192k bytes_per_second=3.45525M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time 2264184 ns 2586161 ns 310 bytes=8.192k bytes_per_second=3.45047M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time 2257468 ns 2579972 ns 310 bytes=8.192k bytes_per_second=3.46074M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time 2258524 ns 2579696 ns 310 bytes=8.192k bytes_per_second=3.45912M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time 2261962 ns 2578731 ns 310 bytes=8.192k bytes_per_second=3.45386M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time_mean 2260638 ns 2580451 ns 5 bytes=8.192k bytes_per_second=3.45589M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time_median 2261053 ns 2579696 ns 5 bytes=8.192k bytes_per_second=3.45525M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time_stddev 2693 ns 3315 ns 5 bytes=0 bytes_per_second=4.21578k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time_cv 0.12 % 0.13 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time 2268806 ns 2593257 ns 309 bytes=16.384k bytes_per_second=6.88688M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time 2270481 ns 2590787 ns 309 bytes=16.384k bytes_per_second=6.8818M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time 2269520 ns 2589069 ns 309 bytes=16.384k bytes_per_second=6.88472M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time 2265416 ns 2590781 ns 309 bytes=16.384k bytes_per_second=6.89719M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time 2268648 ns 2588289 ns 309 bytes=16.384k bytes_per_second=6.88736M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time_mean 2268575 ns 2590437 ns 5 bytes=16.384k bytes_per_second=6.88759M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time_median 2268806 ns 2590781 ns 5 bytes=16.384k bytes_per_second=6.88688M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time_stddev 1908 ns 1916 ns 5 bytes=0 bytes_per_second=5.93647k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time_cv 0.08 % 0.07 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time 2287921 ns 2614125 ns 307 bytes=32.768k bytes_per_second=13.6587M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time 2289947 ns 2616850 ns 307 bytes=32.768k bytes_per_second=13.6466M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time 2283702 ns 2610129 ns 307 bytes=32.768k bytes_per_second=13.6839M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time 2289391 ns 2620751 ns 307 bytes=32.768k bytes_per_second=13.6499M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time 2282402 ns 2608525 ns 307 bytes=32.768k bytes_per_second=13.6917M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time_mean 2286673 ns 2614076 ns 5 bytes=32.768k bytes_per_second=13.6662M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time_median 2287921 ns 2614125 ns 5 bytes=32.768k bytes_per_second=13.6587M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time_stddev 3418 ns 4966 ns 5 bytes=0 bytes_per_second=20.9274k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time_cv 0.15 % 0.19 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time 2330893 ns 2665785 ns 299 bytes=65.536k bytes_per_second=26.8138M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time 2322989 ns 2658936 ns 299 bytes=65.536k bytes_per_second=26.905M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time 2328321 ns 2669046 ns 299 bytes=65.536k bytes_per_second=26.8434M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time 2323275 ns 2658788 ns 299 bytes=65.536k bytes_per_second=26.9017M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time 2328289 ns 2663164 ns 299 bytes=65.536k bytes_per_second=26.8437M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time_mean 2326753 ns 2663144 ns 5 bytes=65.536k bytes_per_second=26.8615M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time_median 2328289 ns 2663164 ns 5 bytes=65.536k bytes_per_second=26.8437M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time_stddev 3472 ns 4430 ns 5 bytes=0 bytes_per_second=41.0509k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time_cv 0.15 % 0.17 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time 2388097 ns 2749310 ns 291 bytes=131.072k bytes_per_second=52.3429M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time 2398033 ns 2755150 ns 291 bytes=131.072k bytes_per_second=52.1261M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time 2392948 ns 2753862 ns 291 bytes=131.072k bytes_per_second=52.2368M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time 2391268 ns 2749361 ns 291 bytes=131.072k bytes_per_second=52.2735M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time 2392472 ns 2753979 ns 291 bytes=131.072k bytes_per_second=52.2472M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time_mean 2392564 ns 2752333 ns 5 bytes=131.072k bytes_per_second=52.2453M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time_median 2392472 ns 2753862 ns 5 bytes=131.072k bytes_per_second=52.2472M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time_stddev 3595 ns 2782 ns 5 bytes=0 bytes_per_second=80.3424k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time_cv 0.15 % 0.10 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time 2509404 ns 2892509 ns 278 bytes=262.144k bytes_per_second=99.6253M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time 2512629 ns 2899729 ns 278 bytes=262.144k bytes_per_second=99.4974M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time 2511754 ns 2902162 ns 278 bytes=262.144k bytes_per_second=99.532M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time 2507719 ns 2890281 ns 278 bytes=262.144k bytes_per_second=99.6922M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time 2512811 ns 2896208 ns 278 bytes=262.144k bytes_per_second=99.4902M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time_mean 2510863 ns 2896178 ns 5 bytes=262.144k bytes_per_second=99.5674M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time_median 2511754 ns 2896208 ns 5 bytes=262.144k bytes_per_second=99.532M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time_stddev 2220 ns 4915 ns 5 bytes=0 bytes_per_second=90.2018k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time_cv 0.09 % 0.17 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time 2607677 ns 3064588 ns 268 bytes=524.288k bytes_per_second=191.742M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time 2610368 ns 3067026 ns 268 bytes=524.288k bytes_per_second=191.544M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time 2605348 ns 3061684 ns 268 bytes=524.288k bytes_per_second=191.913M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time 2605834 ns 3059076 ns 268 bytes=524.288k bytes_per_second=191.877M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time 2606910 ns 3060506 ns 268 bytes=524.288k bytes_per_second=191.798M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time_mean 2607227 ns 3062576 ns 5 bytes=524.288k bytes_per_second=191.775M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time_median 2606910 ns 3061684 ns 5 bytes=524.288k bytes_per_second=191.798M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time_stddev 1977 ns 3208 ns 5 bytes=0 bytes_per_second=148.867k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time_cv 0.08 % 0.10 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time 2783314 ns 3372446 ns 250 bytes=1048.58k bytes_per_second=359.284M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time 2791602 ns 3387131 ns 250 bytes=1048.58k bytes_per_second=358.217M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time 2784889 ns 3372955 ns 250 bytes=1048.58k bytes_per_second=359.081M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time 2786468 ns 3378432 ns 250 bytes=1048.58k bytes_per_second=358.877M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time 2784531 ns 3374085 ns 250 bytes=1048.58k bytes_per_second=359.127M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time_mean 2786161 ns 3377010 ns 5 bytes=1048.58k bytes_per_second=358.917M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time_median 2784889 ns 3374085 ns 5 bytes=1048.58k bytes_per_second=359.081M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time_stddev 3244 ns 6130 ns 5 bytes=0 bytes_per_second=427.382k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time_cv 0.12 % 0.18 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time 3101318 ns 3972228 ns 226 bytes=2.09715M bytes_per_second=644.887M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time 3101993 ns 3974794 ns 226 bytes=2.09715M bytes_per_second=644.747M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time 3106074 ns 3979569 ns 226 bytes=2.09715M bytes_per_second=643.9M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time 3099813 ns 3971269 ns 226 bytes=2.09715M bytes_per_second=645.2M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time 3101729 ns 3972960 ns 226 bytes=2.09715M bytes_per_second=644.802M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time_mean 3102185 ns 3974164 ns 5 bytes=2.09715M bytes_per_second=644.707M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time_median 3101729 ns 3972960 ns 5 bytes=2.09715M bytes_per_second=644.802M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time_stddev 2332 ns 3286 ns 5 bytes=0 bytes_per_second=495.9k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time_cv 0.08 % 0.08 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time 3774254 ns 5266224 ns 185 bytes=4.1943M bytes_per_second=1059.81M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time 3775622 ns 5274123 ns 185 bytes=4.1943M bytes_per_second=1059.43M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time 3775032 ns 5275985 ns 185 bytes=4.1943M bytes_per_second=1059.59M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time 3768067 ns 5276179 ns 185 bytes=4.1943M bytes_per_second=1061.55M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time 3767648 ns 5281625 ns 185 bytes=4.1943M bytes_per_second=1061.67M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time_mean 3772125 ns 5274827 ns 5 bytes=4.1943M bytes_per_second=1060.41M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time_median 3774254 ns 5275985 ns 5 bytes=4.1943M bytes_per_second=1059.81M/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time_stddev 3928 ns 5566 ns 5 bytes=0 bytes_per_second=1.10461M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time_cv 0.10 % 0.11 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time 5188674 ns 8006618 ns 134 bytes=8.38861M bytes_per_second=1.50568G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time 5233799 ns 8066081 ns 134 bytes=8.38861M bytes_per_second=1.4927G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time 5288190 ns 8143311 ns 134 bytes=8.38861M bytes_per_second=1.47735G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time 5359328 ns 8207163 ns 134 bytes=8.38861M bytes_per_second=1.45774G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time 5272598 ns 8127936 ns 134 bytes=8.38861M bytes_per_second=1.48172G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time_mean 5268518 ns 8110222 ns 5 bytes=8.38861M bytes_per_second=1.48304G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time_median 5272598 ns 8127936 ns 5 bytes=8.38861M bytes_per_second=1.48172G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time_stddev 63700 ns 76630 ns 5 bytes=0 bytes_per_second=18.3205M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time_cv 1.21 % 0.94 % 5 bytes=0.00% bytes_per_second=1.21% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time 8404317 ns 13911874 ns 83 bytes=16.7772M bytes_per_second=1.85916G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time 8414391 ns 13920589 ns 83 bytes=16.7772M bytes_per_second=1.85694G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time 8396564 ns 13907235 ns 83 bytes=16.7772M bytes_per_second=1.86088G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time 8412489 ns 13913774 ns 83 bytes=16.7772M bytes_per_second=1.85736G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time 8435602 ns 13941384 ns 83 bytes=16.7772M bytes_per_second=1.85227G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time_mean 8412673 ns 13918972 ns 5 bytes=16.7772M bytes_per_second=1.85732G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time_median 8412489 ns 13913774 ns 5 bytes=16.7772M bytes_per_second=1.85736G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time_stddev 14646 ns 13417 ns 5 bytes=0 bytes_per_second=3.30783M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time_cv 0.17 % 0.10 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time 14164700 ns 25213455 ns 48 bytes=33.5544M bytes_per_second=2.20619G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time 14471515 ns 25283794 ns 48 bytes=33.5544M bytes_per_second=2.15941G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time 14460542 ns 25265396 ns 48 bytes=33.5544M bytes_per_second=2.16105G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time 14504025 ns 25246893 ns 48 bytes=33.5544M bytes_per_second=2.15457G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time 14425538 ns 25257810 ns 48 bytes=33.5544M bytes_per_second=2.1663G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time_mean 14405264 ns 25253470 ns 5 bytes=33.5544M bytes_per_second=2.16951G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time_median 14460542 ns 25257810 ns 5 bytes=33.5544M bytes_per_second=2.16105G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time_stddev 137368 ns 26101 ns 5 bytes=0 bytes_per_second=21.4316M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time_cv 0.95 % 0.10 % 5 bytes=0.00% bytes_per_second=0.96% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time 26563442 ns 48400260 ns 26 bytes=67.1089M bytes_per_second=2.35286G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time 26636883 ns 48559410 ns 26 bytes=67.1089M bytes_per_second=2.34637G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time 26616077 ns 48566217 ns 26 bytes=67.1089M bytes_per_second=2.3482G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time 26523621 ns 48404630 ns 26 bytes=67.1089M bytes_per_second=2.35639G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time 26596519 ns 48481061 ns 26 bytes=67.1089M bytes_per_second=2.34993G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time_mean 26587308 ns 48482316 ns 5 bytes=67.1089M bytes_per_second=2.35075G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time_median 26596519 ns 48481061 ns 5 bytes=67.1089M bytes_per_second=2.34993G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time_stddev 44709 ns 80238 ns 5 bytes=0 bytes_per_second=4.05031M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time_cv 0.17 % 0.17 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time 49688668 ns 90970974 ns 14 bytes=134.218M bytes_per_second=2.51566G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time 49784063 ns 91046774 ns 14 bytes=134.218M bytes_per_second=2.51084G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time 50541587 ns 91928049 ns 14 bytes=134.218M bytes_per_second=2.47321G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time 49743800 ns 91067134 ns 14 bytes=134.218M bytes_per_second=2.51288G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time 49871435 ns 91090057 ns 14 bytes=134.218M bytes_per_second=2.50644G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time_mean 49925911 ns 91220598 ns 5 bytes=134.218M bytes_per_second=2.50381G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time_median 49784063 ns 91067134 ns 5 bytes=134.218M bytes_per_second=2.51084G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time_stddev 350569 ns 397997 ns 5 bytes=0 bytes_per_second=17.8499M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time_cv 0.70 % 0.44 % 5 bytes=0.00% bytes_per_second=0.70% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time 95718240 ns 173696909 ns 7 bytes=268.435M bytes_per_second=2.61183G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time 96884803 ns 174769888 ns 7 bytes=268.435M bytes_per_second=2.58038G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time 96195613 ns 174400973 ns 7 bytes=268.435M bytes_per_second=2.59887G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time 95918790 ns 174012236 ns 7 bytes=268.435M bytes_per_second=2.60637G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time 95920643 ns 173922098 ns 7 bytes=268.435M bytes_per_second=2.60632G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time_mean 96127618 ns 174160421 ns 5 bytes=268.435M bytes_per_second=2.60076G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time_median 95920643 ns 174012236 ns 5 bytes=268.435M bytes_per_second=2.60632G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time_stddev 456068 ns 425122 ns 5 bytes=0 bytes_per_second=12.5806M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time_cv 0.47 % 0.24 % 5 bytes=0.00% bytes_per_second=0.47% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time 187974196 ns 333997921 ns 4 bytes=536.871M bytes_per_second=2.65994G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time 186094079 ns 330695890 ns 4 bytes=536.871M bytes_per_second=2.68681G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time 188051391 ns 334477448 ns 4 bytes=536.871M bytes_per_second=2.65885G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time 186144438 ns 331214695 ns 4 bytes=536.871M bytes_per_second=2.68609G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time 187895995 ns 334030394 ns 4 bytes=536.871M bytes_per_second=2.66105G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time_mean 187232020 ns 332883270 ns 5 bytes=536.871M bytes_per_second=2.67055G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time_median 187895995 ns 333997921 ns 5 bytes=536.871M bytes_per_second=2.66105G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time_stddev 1017448 ns 1779643 ns 5 bytes=0 bytes_per_second=14.8894M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time_cv 0.54 % 0.53 % 5 bytes=0.00% bytes_per_second=0.54% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time 372246251 ns 615855694 ns 2 bytes=1073.74M bytes_per_second=2.68639G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time 371608242 ns 616403267 ns 2 bytes=1073.74M bytes_per_second=2.69101G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time 371081024 ns 616374493 ns 2 bytes=1073.74M bytes_per_second=2.69483G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time 367499009 ns 613086402 ns 2 bytes=1073.74M bytes_per_second=2.7211G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time 370753825 ns 616067366 ns 2 bytes=1073.74M bytes_per_second=2.69721G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time_mean 370637670 ns 615557444 ns 5 bytes=1073.74M bytes_per_second=2.69811G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time_median 371081024 ns 616067366 ns 5 bytes=1073.74M bytes_per_second=2.69483G/s dst_gpu=4 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time_stddev 1843285 ns 1399822 ns 5 bytes=0 bytes_per_second=13.8113M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time_cv 0.50 % 0.23 % 5 bytes=0.00% bytes_per_second=0.50% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time 2251654 ns 2573951 ns 311 bytes=4.096k bytes_per_second=1.73484M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time 2259475 ns 2586929 ns 311 bytes=4.096k bytes_per_second=1.72883M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time 2250842 ns 2572842 ns 311 bytes=4.096k bytes_per_second=1.73546M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time 2250761 ns 2579203 ns 311 bytes=4.096k bytes_per_second=1.73552M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time 2259061 ns 2581026 ns 311 bytes=4.096k bytes_per_second=1.72915M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time_mean 2254359 ns 2578790 ns 5 bytes=4.096k bytes_per_second=1.73276M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time_median 2251654 ns 2579203 ns 5 bytes=4.096k bytes_per_second=1.73484M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time_stddev 4498 ns 5705 ns 5 bytes=0 bytes_per_second=3.53752k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time_cv 0.20 % 0.22 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time 2265169 ns 2588452 ns 311 bytes=8.192k bytes_per_second=3.44897M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time 2251729 ns 2575916 ns 311 bytes=8.192k bytes_per_second=3.46956M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time 2251358 ns 2581522 ns 311 bytes=8.192k bytes_per_second=3.47013M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time 2257316 ns 2581699 ns 311 bytes=8.192k bytes_per_second=3.46097M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time 2251235 ns 2581388 ns 311 bytes=8.192k bytes_per_second=3.47032M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time_mean 2255362 ns 2581795 ns 5 bytes=8.192k bytes_per_second=3.46399M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time_median 2251729 ns 2581522 ns 5 bytes=8.192k bytes_per_second=3.46956M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time_stddev 6047 ns 4448 ns 5 bytes=0 bytes_per_second=9.48821k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time_cv 0.27 % 0.17 % 5 bytes=0.00% bytes_per_second=0.27% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time 2260789 ns 2587945 ns 309 bytes=16.384k bytes_per_second=6.9113M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time 2270538 ns 2600593 ns 309 bytes=16.384k bytes_per_second=6.88163M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time 2266334 ns 2594251 ns 309 bytes=16.384k bytes_per_second=6.89439M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time 2262771 ns 2598284 ns 309 bytes=16.384k bytes_per_second=6.90525M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time 2260850 ns 2596964 ns 309 bytes=16.384k bytes_per_second=6.91112M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time_mean 2264256 ns 2595607 ns 5 bytes=16.384k bytes_per_second=6.90074M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time_median 2262771 ns 2596964 ns 5 bytes=16.384k bytes_per_second=6.90525M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time_stddev 4172 ns 4858 ns 5 bytes=0 bytes_per_second=13.0044k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time_cv 0.18 % 0.19 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time 2276898 ns 2614578 ns 307 bytes=32.768k bytes_per_second=13.7248M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time 2276230 ns 2614034 ns 307 bytes=32.768k bytes_per_second=13.7288M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time 2276680 ns 2608163 ns 307 bytes=32.768k bytes_per_second=13.7261M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time 2281959 ns 2620108 ns 307 bytes=32.768k bytes_per_second=13.6944M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time 2276846 ns 2609184 ns 307 bytes=32.768k bytes_per_second=13.7251M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time_mean 2277723 ns 2613213 ns 5 bytes=32.768k bytes_per_second=13.7199M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time_median 2276846 ns 2614034 ns 5 bytes=32.768k bytes_per_second=13.7251M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time_stddev 2383 ns 4791 ns 5 bytes=0 bytes_per_second=14.6758k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time_cv 0.10 % 0.18 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time 2302998 ns 2650873 ns 304 bytes=65.536k bytes_per_second=27.1385M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time 2303398 ns 2647063 ns 304 bytes=65.536k bytes_per_second=27.1338M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time 2308981 ns 2657432 ns 304 bytes=65.536k bytes_per_second=27.0682M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time 2302902 ns 2646123 ns 304 bytes=65.536k bytes_per_second=27.1397M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time 2318258 ns 2661312 ns 304 bytes=65.536k bytes_per_second=26.9599M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time_mean 2307308 ns 2652561 ns 5 bytes=65.536k bytes_per_second=27.088M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time_median 2303398 ns 2650873 ns 5 bytes=65.536k bytes_per_second=27.1338M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time_stddev 6633 ns 6611 ns 5 bytes=0 bytes_per_second=79.527k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time_cv 0.29 % 0.25 % 5 bytes=0.00% bytes_per_second=0.29% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time 2362117 ns 2729204 ns 296 bytes=131.072k bytes_per_second=52.9186M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time 2368696 ns 2730971 ns 296 bytes=131.072k bytes_per_second=52.7716M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time 2362621 ns 2733725 ns 296 bytes=131.072k bytes_per_second=52.9073M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time 2362049 ns 2724227 ns 296 bytes=131.072k bytes_per_second=52.9202M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time 2362336 ns 2733738 ns 296 bytes=131.072k bytes_per_second=52.9137M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time_mean 2363564 ns 2730373 ns 5 bytes=131.072k bytes_per_second=52.8863M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time_median 2362336 ns 2730971 ns 5 bytes=131.072k bytes_per_second=52.9137M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time_stddev 2878 ns 3939 ns 5 bytes=0 bytes_per_second=65.8306k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time_cv 0.12 % 0.14 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time 2490816 ns 2891027 ns 281 bytes=262.144k bytes_per_second=100.369M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time 2492542 ns 2889244 ns 281 bytes=262.144k bytes_per_second=100.299M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time 2497011 ns 2888912 ns 281 bytes=262.144k bytes_per_second=100.12M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time 2498352 ns 2890641 ns 281 bytes=262.144k bytes_per_second=100.066M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time 2494447 ns 2889835 ns 281 bytes=262.144k bytes_per_second=100.223M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time_mean 2494634 ns 2889932 ns 5 bytes=262.144k bytes_per_second=100.215M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time_median 2494447 ns 2889835 ns 5 bytes=262.144k bytes_per_second=100.223M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time_stddev 3101 ns 898 ns 5 bytes=0 bytes_per_second=127.557k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time_cv 0.12 % 0.03 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time 2582336 ns 3048206 ns 271 bytes=524.288k bytes_per_second=193.623M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time 2588192 ns 3055185 ns 271 bytes=524.288k bytes_per_second=193.185M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time 2581138 ns 3047662 ns 271 bytes=524.288k bytes_per_second=193.713M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time 2585056 ns 3046650 ns 271 bytes=524.288k bytes_per_second=193.419M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time 2585893 ns 3048304 ns 271 bytes=524.288k bytes_per_second=193.357M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time_mean 2584523 ns 3049201 ns 5 bytes=524.288k bytes_per_second=193.459M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time_median 2585056 ns 3048206 ns 5 bytes=524.288k bytes_per_second=193.419M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time_stddev 2822 ns 3409 ns 5 bytes=0 bytes_per_second=216.326k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time_cv 0.11 % 0.11 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time 2740322 ns 3340321 ns 254 bytes=1048.58k bytes_per_second=364.921M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time 2747745 ns 3345757 ns 254 bytes=1048.58k bytes_per_second=363.935M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time 2739511 ns 3336487 ns 254 bytes=1048.58k bytes_per_second=365.029M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time 2740196 ns 3338266 ns 254 bytes=1048.58k bytes_per_second=364.937M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time 2733652 ns 3330502 ns 254 bytes=1048.58k bytes_per_second=365.811M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time_mean 2740285 ns 3338266 ns 5 bytes=1048.58k bytes_per_second=364.926M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time_median 2740196 ns 3338266 ns 5 bytes=1048.58k bytes_per_second=364.937M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time_stddev 5006 ns 5563 ns 5 bytes=0 bytes_per_second=682.419k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time_cv 0.18 % 0.17 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time 3077286 ns 4000079 ns 228 bytes=2.09715M bytes_per_second=649.923M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time 3078720 ns 4000842 ns 228 bytes=2.09715M bytes_per_second=649.621M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time 3077275 ns 3990178 ns 228 bytes=2.09715M bytes_per_second=649.926M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time 3089607 ns 4008501 ns 228 bytes=2.09715M bytes_per_second=647.332M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time 3089229 ns 4008177 ns 228 bytes=2.09715M bytes_per_second=647.411M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time_mean 3082423 ns 4001555 ns 5 bytes=2.09715M bytes_per_second=648.842M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time_median 3078720 ns 4000842 ns 5 bytes=2.09715M bytes_per_second=649.621M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time_stddev 6414 ns 7487 ns 5 bytes=0 bytes_per_second=1.34907M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time_cv 0.21 % 0.19 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time 3623196 ns 5107784 ns 164 bytes=4.1943M bytes_per_second=1104M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time 3602479 ns 5072645 ns 164 bytes=4.1943M bytes_per_second=1110.35M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time 3603408 ns 5074122 ns 164 bytes=4.1943M bytes_per_second=1110.06M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time 3605891 ns 5076634 ns 164 bytes=4.1943M bytes_per_second=1109.3M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time 3603337 ns 5071382 ns 164 bytes=4.1943M bytes_per_second=1110.08M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time_mean 3607662 ns 5080513 ns 5 bytes=4.1943M bytes_per_second=1108.76M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time_median 3603408 ns 5074122 ns 5 bytes=4.1943M bytes_per_second=1110.06M/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time_stddev 8776 ns 15370 ns 5 bytes=0 bytes_per_second=2.68894M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time_cv 0.24 % 0.30 % 5 bytes=0.00% bytes_per_second=0.24% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time 4954982 ns 7692732 ns 142 bytes=8.38861M bytes_per_second=1.5767G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time 4947527 ns 7681093 ns 142 bytes=8.38861M bytes_per_second=1.57907G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time 4951302 ns 7716342 ns 142 bytes=8.38861M bytes_per_second=1.57787G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time 4951424 ns 7720587 ns 142 bytes=8.38861M bytes_per_second=1.57783G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time 4950760 ns 7719870 ns 142 bytes=8.38861M bytes_per_second=1.57804G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time_mean 4951199 ns 7706125 ns 5 bytes=8.38861M bytes_per_second=1.5779G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time_median 4951302 ns 7716342 ns 5 bytes=8.38861M bytes_per_second=1.57787G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time_stddev 2648 ns 18086 ns 5 bytes=0 bytes_per_second=884.838k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time_cv 0.05 % 0.23 % 5 bytes=0.00% bytes_per_second=0.05% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time 7841460 ns 13370763 ns 87 bytes=16.7772M bytes_per_second=1.99261G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time 7931705 ns 13523533 ns 87 bytes=16.7772M bytes_per_second=1.96994G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time 7848764 ns 13390581 ns 87 bytes=16.7772M bytes_per_second=1.99076G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time 7869991 ns 13425132 ns 87 bytes=16.7772M bytes_per_second=1.98539G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time 7832409 ns 13347184 ns 87 bytes=16.7772M bytes_per_second=1.99492G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time_mean 7864866 ns 13411438 ns 5 bytes=16.7772M bytes_per_second=1.98672G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time_median 7848764 ns 13390581 ns 5 bytes=16.7772M bytes_per_second=1.99076G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time_stddev 39857 ns 68867 ns 5 bytes=0 bytes_per_second=10.2591M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time_cv 0.51 % 0.51 % 5 bytes=0.00% bytes_per_second=0.50% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time 13717450 ns 25018465 ns 51 bytes=33.5544M bytes_per_second=2.27812G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time 13743159 ns 25017633 ns 51 bytes=33.5544M bytes_per_second=2.27386G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time 13714381 ns 24977930 ns 51 bytes=33.5544M bytes_per_second=2.27863G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time 13750871 ns 25098814 ns 51 bytes=33.5544M bytes_per_second=2.27258G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time 13686877 ns 24980001 ns 51 bytes=33.5544M bytes_per_second=2.28321G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time_mean 13722548 ns 25018569 ns 5 bytes=33.5544M bytes_per_second=2.27728G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time_median 13717450 ns 25017633 ns 5 bytes=33.5544M bytes_per_second=2.27812G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time_stddev 25456 ns 48937 ns 5 bytes=0 bytes_per_second=4.32772M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time_cv 0.19 % 0.20 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time 25280005 ns 48152698 ns 27 bytes=67.1089M bytes_per_second=2.47231G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time 25533131 ns 48430864 ns 27 bytes=67.1089M bytes_per_second=2.4478G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time 25476657 ns 48394073 ns 27 bytes=67.1089M bytes_per_second=2.45323G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time 25338642 ns 48274760 ns 27 bytes=67.1089M bytes_per_second=2.46659G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time 25381640 ns 48290730 ns 27 bytes=67.1089M bytes_per_second=2.46241G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time_mean 25402015 ns 48308625 ns 5 bytes=67.1089M bytes_per_second=2.46047G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time_median 25381640 ns 48290730 ns 5 bytes=67.1089M bytes_per_second=2.46241G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time_stddev 102568 ns 109572 ns 5 bytes=0 bytes_per_second=10.1678M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time_cv 0.40 % 0.23 % 5 bytes=0.00% bytes_per_second=0.40% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time 45976659 ns 88069821 ns 15 bytes=134.218M bytes_per_second=2.71877G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time 46133630 ns 88285411 ns 15 bytes=134.218M bytes_per_second=2.70952G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time 46003699 ns 88122344 ns 15 bytes=134.218M bytes_per_second=2.71717G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time 46192106 ns 88325463 ns 15 bytes=134.218M bytes_per_second=2.70609G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time 45994377 ns 88225378 ns 15 bytes=134.218M bytes_per_second=2.71772G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time_mean 46060094 ns 88205683 ns 5 bytes=134.218M bytes_per_second=2.71386G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time_median 46003699 ns 88225378 ns 5 bytes=134.218M bytes_per_second=2.71717G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time_stddev 96560 ns 107814 ns 5 bytes=0 bytes_per_second=5.82024M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time_cv 0.21 % 0.12 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time 86735498 ns 164762659 ns 8 bytes=268.435M bytes_per_second=2.88233G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time 87685842 ns 167127017 ns 8 bytes=268.435M bytes_per_second=2.85109G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time 87514042 ns 167157329 ns 8 bytes=268.435M bytes_per_second=2.85668G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time 87573601 ns 167183495 ns 8 bytes=268.435M bytes_per_second=2.85474G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time 86679160 ns 165149848 ns 8 bytes=268.435M bytes_per_second=2.8842G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time_mean 87237629 ns 166276070 ns 5 bytes=268.435M bytes_per_second=2.86581G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time_median 87514042 ns 167127017 ns 5 bytes=268.435M bytes_per_second=2.85668G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time_stddev 488416 ns 1212738 ns 5 bytes=0 bytes_per_second=16.4599M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time_cv 0.56 % 0.73 % 5 bytes=0.00% bytes_per_second=0.56% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time 167127743 ns 311554592 ns 4 bytes=536.871M bytes_per_second=2.99172G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time 170041353 ns 316343296 ns 4 bytes=536.871M bytes_per_second=2.94046G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time 168532033 ns 312716646 ns 4 bytes=536.871M bytes_per_second=2.9668G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time 170177348 ns 316420784 ns 4 bytes=536.871M bytes_per_second=2.93811G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time 168150913 ns 312727795 ns 4 bytes=536.871M bytes_per_second=2.97352G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time_mean 168805878 ns 313952623 ns 5 bytes=536.871M bytes_per_second=2.96212G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time_median 168532033 ns 312727795 ns 5 bytes=536.871M bytes_per_second=2.9668G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time_stddev 1296865 ns 2268564 ns 5 bytes=0 bytes_per_second=23.3153M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time_cv 0.77 % 0.72 % 5 bytes=0.00% bytes_per_second=0.77% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time 329433456 ns 573804364 ns 2 bytes=1073.74M bytes_per_second=3.03551G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time 328199714 ns 574197841 ns 2 bytes=1073.74M bytes_per_second=3.04693G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time 328596979 ns 572589180 ns 2 bytes=1073.74M bytes_per_second=3.04324G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time 330911294 ns 577199484 ns 2 bytes=1073.74M bytes_per_second=3.02196G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time 328359202 ns 573615690 ns 2 bytes=1073.74M bytes_per_second=3.04545G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time_mean 329100129 ns 574281312 ns 5 bytes=1073.74M bytes_per_second=3.03862G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time_median 328596979 ns 573804364 ns 5 bytes=1073.74M bytes_per_second=3.04324G/s dst_gpu=5 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time_stddev 1118515 ns 1736127 ns 5 bytes=0 bytes_per_second=10.5451M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time_cv 0.34 % 0.30 % 5 bytes=0.00% bytes_per_second=0.34% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time 2255750 ns 2581192 ns 311 bytes=4.096k bytes_per_second=1.73169M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time 2250564 ns 2583216 ns 311 bytes=4.096k bytes_per_second=1.73568M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time 2256815 ns 2582229 ns 311 bytes=4.096k bytes_per_second=1.73087M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time 2254523 ns 2579717 ns 311 bytes=4.096k bytes_per_second=1.73263M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time 2251250 ns 2582867 ns 311 bytes=4.096k bytes_per_second=1.73515M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time_mean 2253781 ns 2581844 ns 5 bytes=4.096k bytes_per_second=1.7332M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time_median 2254523 ns 2582229 ns 5 bytes=4.096k bytes_per_second=1.73263M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time_stddev 2756 ns 1417 ns 5 bytes=0 bytes_per_second=2.17079k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time_cv 0.12 % 0.05 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time 2257334 ns 2585029 ns 311 bytes=8.192k bytes_per_second=3.46094M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time 2250054 ns 2578797 ns 311 bytes=8.192k bytes_per_second=3.47214M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time 2256838 ns 2584883 ns 311 bytes=8.192k bytes_per_second=3.4617M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time 2250355 ns 2584654 ns 311 bytes=8.192k bytes_per_second=3.47168M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time 2256977 ns 2585014 ns 311 bytes=8.192k bytes_per_second=3.46149M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time_mean 2254311 ns 2583676 ns 5 bytes=8.192k bytes_per_second=3.46559M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time_median 2256838 ns 2584883 ns 5 bytes=8.192k bytes_per_second=3.4617M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time_stddev 3755 ns 2731 ns 5 bytes=0 bytes_per_second=5.91534k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time_cv 0.17 % 0.11 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time 2257628 ns 2588270 ns 308 bytes=16.384k bytes_per_second=6.92098M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time 2257538 ns 2595488 ns 308 bytes=16.384k bytes_per_second=6.92126M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time 2263298 ns 2593213 ns 308 bytes=16.384k bytes_per_second=6.90364M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time 2264204 ns 2595226 ns 308 bytes=16.384k bytes_per_second=6.90088M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time 2264262 ns 2594698 ns 308 bytes=16.384k bytes_per_second=6.9007M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time_mean 2261386 ns 2593379 ns 5 bytes=16.384k bytes_per_second=6.90949M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time_median 2263298 ns 2594698 ns 5 bytes=16.384k bytes_per_second=6.90364M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time_stddev 3493 ns 2989 ns 5 bytes=0 bytes_per_second=10.9339k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time_cv 0.15 % 0.12 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time 2282519 ns 2618372 ns 308 bytes=32.768k bytes_per_second=13.691M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time 2279443 ns 2615676 ns 308 bytes=32.768k bytes_per_second=13.7095M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time 2272261 ns 2613571 ns 308 bytes=32.768k bytes_per_second=13.7528M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time 2272447 ns 2614691 ns 308 bytes=32.768k bytes_per_second=13.7517M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time 2278720 ns 2615009 ns 308 bytes=32.768k bytes_per_second=13.7138M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time_mean 2277078 ns 2615464 ns 5 bytes=32.768k bytes_per_second=13.7238M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time_median 2278720 ns 2615009 ns 5 bytes=32.768k bytes_per_second=13.7138M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time_stddev 4543 ns 1795 ns 5 bytes=0 bytes_per_second=28.0403k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time_cv 0.20 % 0.07 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time 2318145 ns 2662877 ns 303 bytes=65.536k bytes_per_second=26.9612M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time 2319814 ns 2665909 ns 303 bytes=65.536k bytes_per_second=26.9418M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time 2309457 ns 2660965 ns 303 bytes=65.536k bytes_per_second=27.0626M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time 2313158 ns 2664743 ns 303 bytes=65.536k bytes_per_second=27.0193M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time 2317974 ns 2663433 ns 303 bytes=65.536k bytes_per_second=26.9632M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time_mean 2315709 ns 2663585 ns 5 bytes=65.536k bytes_per_second=26.9896M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time_median 2317974 ns 2663433 ns 5 bytes=65.536k bytes_per_second=26.9632M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time_stddev 4287 ns 1879 ns 5 bytes=0 bytes_per_second=51.2101k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time_cv 0.19 % 0.07 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time 2376190 ns 2745102 ns 295 bytes=131.072k bytes_per_second=52.6052M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time 2382159 ns 2746200 ns 295 bytes=131.072k bytes_per_second=52.4734M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time 2376122 ns 2749428 ns 295 bytes=131.072k bytes_per_second=52.6067M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time 2376011 ns 2743496 ns 295 bytes=131.072k bytes_per_second=52.6092M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time 2384708 ns 2752160 ns 295 bytes=131.072k bytes_per_second=52.4173M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time_mean 2379038 ns 2747277 ns 5 bytes=131.072k bytes_per_second=52.5424M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time_median 2376190 ns 2746200 ns 5 bytes=131.072k bytes_per_second=52.6052M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time_stddev 4113 ns 3488 ns 5 bytes=0 bytes_per_second=92.9369k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time_cv 0.17 % 0.13 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time 2499918 ns 2898114 ns 280 bytes=262.144k bytes_per_second=100.003M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time 2501987 ns 2895927 ns 280 bytes=262.144k bytes_per_second=99.9206M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time 2494819 ns 2892069 ns 280 bytes=262.144k bytes_per_second=100.208M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time 2494812 ns 2896238 ns 280 bytes=262.144k bytes_per_second=100.208M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time 2501328 ns 2894822 ns 280 bytes=262.144k bytes_per_second=99.9469M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time_mean 2498573 ns 2895434 ns 5 bytes=262.144k bytes_per_second=100.057M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time_median 2499918 ns 2895927 ns 5 bytes=262.144k bytes_per_second=100.003M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time_stddev 3510 ns 2223 ns 5 bytes=0 bytes_per_second=144k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time_cv 0.14 % 0.08 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time 2585148 ns 3052793 ns 271 bytes=524.288k bytes_per_second=193.413M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time 2589034 ns 3056895 ns 271 bytes=524.288k bytes_per_second=193.122M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time 2583137 ns 3050644 ns 271 bytes=524.288k bytes_per_second=193.563M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time 2588165 ns 3049537 ns 271 bytes=524.288k bytes_per_second=193.187M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time 2585923 ns 3049919 ns 271 bytes=524.288k bytes_per_second=193.355M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time_mean 2586281 ns 3051957 ns 5 bytes=524.288k bytes_per_second=193.328M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time_median 2585923 ns 3050644 ns 5 bytes=524.288k bytes_per_second=193.355M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time_stddev 2368 ns 3034 ns 5 bytes=0 bytes_per_second=181.249k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time_cv 0.09 % 0.10 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time 2760384 ns 3358891 ns 254 bytes=1048.58k bytes_per_second=362.268M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time 2750411 ns 3350226 ns 254 bytes=1048.58k bytes_per_second=363.582M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time 2747212 ns 3345158 ns 254 bytes=1048.58k bytes_per_second=364.005M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time 2749238 ns 3348184 ns 254 bytes=1048.58k bytes_per_second=363.737M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time 2744183 ns 3344357 ns 254 bytes=1048.58k bytes_per_second=364.407M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time_mean 2750286 ns 3349363 ns 5 bytes=1048.58k bytes_per_second=363.6M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time_median 2749238 ns 3348184 ns 5 bytes=1048.58k bytes_per_second=363.737M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time_stddev 6119 ns 5824 ns 5 bytes=0 bytes_per_second=826.857k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time_cv 0.22 % 0.17 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time 3077890 ns 3995962 ns 228 bytes=2.09715M bytes_per_second=649.796M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time 3078980 ns 4006036 ns 228 bytes=2.09715M bytes_per_second=649.566M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time 3074680 ns 3996036 ns 228 bytes=2.09715M bytes_per_second=650.474M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time 3073086 ns 3998970 ns 228 bytes=2.09715M bytes_per_second=650.812M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time 3073779 ns 3996510 ns 228 bytes=2.09715M bytes_per_second=650.665M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time_mean 3075683 ns 3998703 ns 5 bytes=2.09715M bytes_per_second=650.262M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time_median 3074680 ns 3996510 ns 5 bytes=2.09715M bytes_per_second=650.474M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time_stddev 2604 ns 4280 ns 5 bytes=0 bytes_per_second=563.535k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time_cv 0.08 % 0.11 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time 3601722 ns 5072944 ns 194 bytes=4.1943M bytes_per_second=1110.58M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time 3601879 ns 5072040 ns 194 bytes=4.1943M bytes_per_second=1110.53M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time 3600294 ns 5072529 ns 194 bytes=4.1943M bytes_per_second=1111.02M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time 3594975 ns 5062635 ns 194 bytes=4.1943M bytes_per_second=1112.66M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time 3596587 ns 5064362 ns 194 bytes=4.1943M bytes_per_second=1112.17M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time_mean 3599091 ns 5068902 ns 5 bytes=4.1943M bytes_per_second=1111.39M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time_median 3600294 ns 5072040 ns 5 bytes=4.1943M bytes_per_second=1111.02M/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time_stddev 3137 ns 4981 ns 5 bytes=0 bytes_per_second=992.198k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time_cv 0.09 % 0.10 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time 4956585 ns 7700167 ns 141 bytes=8.38861M bytes_per_second=1.57619G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time 4946343 ns 7698408 ns 141 bytes=8.38861M bytes_per_second=1.57945G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time 4950207 ns 7705316 ns 141 bytes=8.38861M bytes_per_second=1.57822G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time 4950991 ns 7709916 ns 141 bytes=8.38861M bytes_per_second=1.57797G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time 4947597 ns 7697861 ns 141 bytes=8.38861M bytes_per_second=1.57905G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time_mean 4950344 ns 7702334 ns 5 bytes=8.38861M bytes_per_second=1.57817G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time_median 4950207 ns 7700167 ns 5 bytes=8.38861M bytes_per_second=1.57822G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time_stddev 3967 ns 5160 ns 5 bytes=0 bytes_per_second=1.29437M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time_cv 0.08 % 0.07 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time 7755758 ns 13219462 ns 88 bytes=16.7772M bytes_per_second=2.01463G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time 7771106 ns 13247394 ns 88 bytes=16.7772M bytes_per_second=2.01065G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time 7776062 ns 13286787 ns 88 bytes=16.7772M bytes_per_second=2.00937G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time 7761398 ns 13232480 ns 88 bytes=16.7772M bytes_per_second=2.01317G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time 7733120 ns 13206481 ns 88 bytes=16.7772M bytes_per_second=2.02053G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time_mean 7759489 ns 13238521 ns 5 bytes=16.7772M bytes_per_second=2.01367G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time_median 7761398 ns 13232480 ns 5 bytes=16.7772M bytes_per_second=2.01317G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time_stddev 16752 ns 30962 ns 5 bytes=0 bytes_per_second=4.45792M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time_cv 0.22 % 0.23 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time 13780360 ns 25024515 ns 51 bytes=33.5544M bytes_per_second=2.26772G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time 13757310 ns 24977293 ns 51 bytes=33.5544M bytes_per_second=2.27152G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time 13793574 ns 25020050 ns 51 bytes=33.5544M bytes_per_second=2.26555G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time 13747328 ns 24977883 ns 51 bytes=33.5544M bytes_per_second=2.27317G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time 13775067 ns 24998169 ns 51 bytes=33.5544M bytes_per_second=2.26859G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time_mean 13770728 ns 24999582 ns 5 bytes=33.5544M bytes_per_second=2.26931G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time_median 13775067 ns 24998169 ns 5 bytes=33.5544M bytes_per_second=2.26859G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time_stddev 18447 ns 22418 ns 5 bytes=0 bytes_per_second=3.11326M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time_cv 0.13 % 0.09 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time 25235588 ns 48012730 ns 28 bytes=67.1089M bytes_per_second=2.47666G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time 23803769 ns 45595197 ns 28 bytes=67.1089M bytes_per_second=2.62563G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time 25249840 ns 48062099 ns 28 bytes=67.1089M bytes_per_second=2.47526G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time 25309577 ns 48078814 ns 28 bytes=67.1089M bytes_per_second=2.46942G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time 25395057 ns 48240135 ns 28 bytes=67.1089M bytes_per_second=2.46111G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time_mean 24998766 ns 47597795 ns 5 bytes=67.1089M bytes_per_second=2.50162G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time_median 25249840 ns 48062099 ns 5 bytes=67.1089M bytes_per_second=2.47526G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time_stddev 670968 ns 1122734 ns 5 bytes=0 bytes_per_second=71.2677M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time_cv 2.68 % 2.36 % 5 bytes=0.00% bytes_per_second=2.78% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time 45510763 ns 87397548 ns 15 bytes=134.218M bytes_per_second=2.7466G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time 45511542 ns 87394567 ns 15 bytes=134.218M bytes_per_second=2.74656G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time 45583765 ns 87567032 ns 15 bytes=134.218M bytes_per_second=2.7422G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time 45560118 ns 87394593 ns 15 bytes=134.218M bytes_per_second=2.74363G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time 44457372 ns 85305698 ns 15 bytes=134.218M bytes_per_second=2.81168G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time_mean 45324712 ns 87011888 ns 5 bytes=134.218M bytes_per_second=2.75813G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time_median 45511542 ns 87394593 ns 5 bytes=134.218M bytes_per_second=2.74656G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time_stddev 485882 ns 956675 ns 5 bytes=0 bytes_per_second=30.7141M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time_cv 1.07 % 1.10 % 5 bytes=0.00% bytes_per_second=1.09% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time 86213307 ns 165197232 ns 8 bytes=268.435M bytes_per_second=2.89978G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time 86643931 ns 165774955 ns 8 bytes=268.435M bytes_per_second=2.88537G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time 87588933 ns 167450254 ns 8 bytes=268.435M bytes_per_second=2.85424G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time 86383188 ns 165437920 ns 8 bytes=268.435M bytes_per_second=2.89408G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time 86429128 ns 165473969 ns 8 bytes=268.435M bytes_per_second=2.89254G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time_mean 86651698 ns 165866866 ns 5 bytes=268.435M bytes_per_second=2.8852G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time_median 86429128 ns 165473969 ns 5 bytes=268.435M bytes_per_second=2.89254G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time_stddev 545961 ns 908617 ns 5 bytes=0 bytes_per_second=18.4884M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time_cv 0.63 % 0.55 % 5 bytes=0.00% bytes_per_second=0.63% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time 168371640 ns 313886119 ns 4 bytes=536.871M bytes_per_second=2.96962G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time 167130746 ns 311664105 ns 4 bytes=536.871M bytes_per_second=2.99167G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time 168489307 ns 313565347 ns 4 bytes=536.871M bytes_per_second=2.96755G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time 166867867 ns 311227972 ns 4 bytes=536.871M bytes_per_second=2.99638G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time 168143999 ns 313116631 ns 4 bytes=536.871M bytes_per_second=2.97364G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time_mean 167800712 ns 312692035 ns 5 bytes=536.871M bytes_per_second=2.97977G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time_median 168143999 ns 313116631 ns 5 bytes=536.871M bytes_per_second=2.97364G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time_stddev 747834 ns 1179927 ns 5 bytes=0 bytes_per_second=13.619M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time_cv 0.45 % 0.38 % 5 bytes=0.00% bytes_per_second=0.45% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time 320758060 ns 561477821 ns 2 bytes=1073.74M bytes_per_second=3.11761G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time 320145264 ns 561459207 ns 2 bytes=1073.74M bytes_per_second=3.12358G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time 320146367 ns 561386255 ns 2 bytes=1073.74M bytes_per_second=3.12357G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time 320071414 ns 560668674 ns 2 bytes=1073.74M bytes_per_second=3.1243G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time 321103424 ns 562507246 ns 2 bytes=1073.74M bytes_per_second=3.11426G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time_mean 320444906 ns 561499840 ns 5 bytes=1073.74M bytes_per_second=3.12067G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time_median 320146367 ns 561459207 ns 5 bytes=1073.74M bytes_per_second=3.12357G/s dst_gpu=6 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time_stddev 461009 ns 655885 ns 5 bytes=0 bytes_per_second=4.59376M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time_cv 0.14 % 0.12 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time 2241125 ns 2571442 ns 312 bytes=4.096k bytes_per_second=1.74299M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time 2252103 ns 2582715 ns 312 bytes=4.096k bytes_per_second=1.73449M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time 2240609 ns 2573015 ns 312 bytes=4.096k bytes_per_second=1.74339M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time 2240521 ns 2577609 ns 312 bytes=4.096k bytes_per_second=1.74346M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time 2240650 ns 2576795 ns 312 bytes=4.096k bytes_per_second=1.74336M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time_mean 2243002 ns 2576315 ns 5 bytes=4.096k bytes_per_second=1.74154M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time_median 2240650 ns 2576795 ns 5 bytes=4.096k bytes_per_second=1.74336M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time_stddev 5093 ns 4402 ns 5 bytes=0 bytes_per_second=4.03722k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time_cv 0.23 % 0.17 % 5 bytes=0.00% bytes_per_second=0.23% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time 2247480 ns 2585146 ns 312 bytes=8.192k bytes_per_second=3.47612M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time 2253511 ns 2585942 ns 312 bytes=8.192k bytes_per_second=3.46681M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time 2248534 ns 2580594 ns 312 bytes=8.192k bytes_per_second=3.47449M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time 2246680 ns 2578623 ns 312 bytes=8.192k bytes_per_second=3.47735M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time 2240835 ns 2579015 ns 312 bytes=8.192k bytes_per_second=3.48642M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time_mean 2247408 ns 2581864 ns 5 bytes=8.192k bytes_per_second=3.47624M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time_median 2247480 ns 2580594 ns 5 bytes=8.192k bytes_per_second=3.47612M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time_stddev 4535 ns 3451 ns 5 bytes=0 bytes_per_second=7.18473k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time_cv 0.20 % 0.13 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time 2250465 ns 2591165 ns 311 bytes=16.384k bytes_per_second=6.94301M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time 2251214 ns 2595111 ns 311 bytes=16.384k bytes_per_second=6.9407M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time 2256226 ns 2593730 ns 311 bytes=16.384k bytes_per_second=6.92528M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time 2253672 ns 2588115 ns 311 bytes=16.384k bytes_per_second=6.93313M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time 2248152 ns 2589111 ns 311 bytes=16.384k bytes_per_second=6.95015M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time_mean 2251946 ns 2591446 ns 5 bytes=16.384k bytes_per_second=6.93845M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time_median 2251214 ns 2591165 ns 5 bytes=16.384k bytes_per_second=6.9407M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time_stddev 3099 ns 2969 ns 5 bytes=0 bytes_per_second=9.77552k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time_cv 0.14 % 0.11 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time 2265512 ns 2610362 ns 309 bytes=32.768k bytes_per_second=13.7938M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time 2272499 ns 2612156 ns 309 bytes=32.768k bytes_per_second=13.7514M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time 2264965 ns 2604866 ns 309 bytes=32.768k bytes_per_second=13.7971M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time 2265343 ns 2616259 ns 309 bytes=32.768k bytes_per_second=13.7948M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time 2265097 ns 2604784 ns 309 bytes=32.768k bytes_per_second=13.7963M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time_mean 2266683 ns 2609685 ns 5 bytes=32.768k bytes_per_second=13.7867M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time_median 2265343 ns 2610362 ns 5 bytes=32.768k bytes_per_second=13.7948M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time_stddev 3258 ns 4925 ns 5 bytes=0 bytes_per_second=20.2537k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time_cv 0.14 % 0.19 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time 2294927 ns 2648856 ns 302 bytes=65.536k bytes_per_second=27.234M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time 2295327 ns 2643583 ns 302 bytes=65.536k bytes_per_second=27.2292M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time 2295023 ns 2654723 ns 302 bytes=65.536k bytes_per_second=27.2328M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time 2295080 ns 2642893 ns 302 bytes=65.536k bytes_per_second=27.2322M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time 2303465 ns 2657754 ns 302 bytes=65.536k bytes_per_second=27.133M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time_mean 2296764 ns 2649562 ns 5 bytes=65.536k bytes_per_second=27.2123M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time_median 2295080 ns 2648856 ns 5 bytes=65.536k bytes_per_second=27.2322M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time_stddev 3749 ns 6604 ns 5 bytes=0 bytes_per_second=45.3831k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time_cv 0.16 % 0.25 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time 2380951 ns 2747028 ns 295 bytes=131.072k bytes_per_second=52.5M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time 2374994 ns 2746564 ns 295 bytes=131.072k bytes_per_second=52.6317M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time 2380305 ns 2746242 ns 295 bytes=131.072k bytes_per_second=52.5143M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time 2373243 ns 2744116 ns 295 bytes=131.072k bytes_per_second=52.6705M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time 2386333 ns 2752493 ns 295 bytes=131.072k bytes_per_second=52.3816M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time_mean 2379165 ns 2747289 ns 5 bytes=131.072k bytes_per_second=52.5396M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time_median 2380305 ns 2746564 ns 5 bytes=131.072k bytes_per_second=52.5143M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time_stddev 5204 ns 3116 ns 5 bytes=0 bytes_per_second=117.644k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time_cv 0.22 % 0.11 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time 2492100 ns 2888498 ns 282 bytes=262.144k bytes_per_second=100.317M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time 2482476 ns 2883213 ns 282 bytes=262.144k bytes_per_second=100.706M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time 2489264 ns 2884827 ns 282 bytes=262.144k bytes_per_second=100.431M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time 2495772 ns 2891458 ns 282 bytes=262.144k bytes_per_second=100.169M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time 2482741 ns 2882598 ns 282 bytes=262.144k bytes_per_second=100.695M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time_mean 2488471 ns 2886119 ns 5 bytes=262.144k bytes_per_second=100.464M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time_median 2489264 ns 2884827 ns 5 bytes=262.144k bytes_per_second=100.431M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time_stddev 5828 ns 3764 ns 5 bytes=0 bytes_per_second=240.913k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time_cv 0.23 % 0.13 % 5 bytes=0.00% bytes_per_second=0.23% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time 2582111 ns 3048508 ns 271 bytes=524.288k bytes_per_second=193.64M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time 2577824 ns 3047611 ns 271 bytes=524.288k bytes_per_second=193.962M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time 2583121 ns 3048563 ns 271 bytes=524.288k bytes_per_second=193.564M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time 2581675 ns 3048102 ns 271 bytes=524.288k bytes_per_second=193.673M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time 2584891 ns 3047729 ns 271 bytes=524.288k bytes_per_second=193.432M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time_mean 2581924 ns 3048102 ns 5 bytes=524.288k bytes_per_second=193.654M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time_median 2582111 ns 3048102 ns 5 bytes=524.288k bytes_per_second=193.64M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time_stddev 2605 ns 435 ns 5 bytes=0 bytes_per_second=200.192k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time_cv 0.10 % 0.01 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time 2736191 ns 3338703 ns 256 bytes=1048.58k bytes_per_second=365.472M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time 2743488 ns 3351933 ns 256 bytes=1048.58k bytes_per_second=364.5M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time 2736040 ns 3335547 ns 256 bytes=1048.58k bytes_per_second=365.492M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time 2733678 ns 3340996 ns 256 bytes=1048.58k bytes_per_second=365.808M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time 2737065 ns 3336558 ns 256 bytes=1048.58k bytes_per_second=365.355M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time_mean 2737292 ns 3340748 ns 5 bytes=1048.58k bytes_per_second=365.325M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time_median 2736191 ns 3338703 ns 5 bytes=1048.58k bytes_per_second=365.472M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time_stddev 3684 ns 6594 ns 5 bytes=0 bytes_per_second=502.82k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time_cv 0.13 % 0.20 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time 3072044 ns 3999913 ns 227 bytes=2.09715M bytes_per_second=651.032M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time 3072370 ns 3998132 ns 227 bytes=2.09715M bytes_per_second=650.963M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time 3067119 ns 3990637 ns 227 bytes=2.09715M bytes_per_second=652.078M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time 3066335 ns 4003284 ns 227 bytes=2.09715M bytes_per_second=652.244M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time 3068071 ns 3998449 ns 227 bytes=2.09715M bytes_per_second=651.875M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time_mean 3069188 ns 3998083 ns 5 bytes=2.09715M bytes_per_second=651.639M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time_median 3068071 ns 3998449 ns 5 bytes=2.09715M bytes_per_second=651.875M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time_stddev 2827 ns 4636 ns 5 bytes=0 bytes_per_second=614.378k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time_cv 0.09 % 0.12 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time 3588903 ns 5065215 ns 195 bytes=4.1943M bytes_per_second=1114.55M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time 3589167 ns 5064709 ns 195 bytes=4.1943M bytes_per_second=1114.46M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time 3589838 ns 5068756 ns 195 bytes=4.1943M bytes_per_second=1114.26M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time 3595424 ns 5079950 ns 195 bytes=4.1943M bytes_per_second=1112.53M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time 3589871 ns 5071462 ns 195 bytes=4.1943M bytes_per_second=1114.25M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time_mean 3590641 ns 5070018 ns 5 bytes=4.1943M bytes_per_second=1114.01M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time_median 3589838 ns 5068756 ns 5 bytes=4.1943M bytes_per_second=1114.26M/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time_stddev 2707 ns 6196 ns 5 bytes=0 bytes_per_second=859.081k/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time_cv 0.08 % 0.12 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time 4835587 ns 7535363 ns 145 bytes=8.38861M bytes_per_second=1.61563G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time 4869084 ns 7578812 ns 145 bytes=8.38861M bytes_per_second=1.60451G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time 4873732 ns 7583993 ns 145 bytes=8.38861M bytes_per_second=1.60298G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time 4873152 ns 7594684 ns 145 bytes=8.38861M bytes_per_second=1.60317G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time 4945573 ns 7686190 ns 145 bytes=8.38861M bytes_per_second=1.5797G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time_mean 4879426 ns 7595808 ns 5 bytes=8.38861M bytes_per_second=1.6012G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time_median 4873152 ns 7583993 ns 5 bytes=8.38861M bytes_per_second=1.60317G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time_stddev 40237 ns 55345 ns 5 bytes=0 bytes_per_second=13.4352M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time_cv 0.82 % 0.73 % 5 bytes=0.00% bytes_per_second=0.82% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time 7747940 ns 13257061 ns 88 bytes=16.7772M bytes_per_second=2.01667G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time 7731862 ns 13195418 ns 88 bytes=16.7772M bytes_per_second=2.02086G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time 7721553 ns 13191665 ns 88 bytes=16.7772M bytes_per_second=2.02356G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time 7731535 ns 13202483 ns 88 bytes=16.7772M bytes_per_second=2.02094G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time 7753166 ns 13243109 ns 88 bytes=16.7772M bytes_per_second=2.01531G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time_mean 7737211 ns 13217947 ns 5 bytes=16.7772M bytes_per_second=2.01947G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time_median 7731862 ns 13202483 ns 5 bytes=16.7772M bytes_per_second=2.02086G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time_stddev 12997 ns 30002 ns 5 bytes=0 bytes_per_second=3.47296M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time_cv 0.17 % 0.23 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time 13737269 ns 24958427 ns 51 bytes=33.5544M bytes_per_second=2.27483G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time 13709225 ns 24910495 ns 51 bytes=33.5544M bytes_per_second=2.27949G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time 13778170 ns 25027809 ns 51 bytes=33.5544M bytes_per_second=2.26808G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time 13758757 ns 24957123 ns 51 bytes=33.5544M bytes_per_second=2.27128G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time 13745706 ns 24977176 ns 51 bytes=33.5544M bytes_per_second=2.27344G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time_mean 13745825 ns 24966206 ns 5 bytes=33.5544M bytes_per_second=2.27342G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time_median 13745706 ns 24958427 ns 5 bytes=33.5544M bytes_per_second=2.27344G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time_stddev 25623 ns 42314 ns 5 bytes=0 bytes_per_second=4.34117M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time_cv 0.19 % 0.17 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time 25315406 ns 48155785 ns 28 bytes=67.1089M bytes_per_second=2.46885G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time 25268279 ns 48100264 ns 28 bytes=67.1089M bytes_per_second=2.47346G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time 25361971 ns 48156133 ns 28 bytes=67.1089M bytes_per_second=2.46432G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time 25338600 ns 48158008 ns 28 bytes=67.1089M bytes_per_second=2.46659G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time 25359771 ns 48149507 ns 28 bytes=67.1089M bytes_per_second=2.46453G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time_mean 25328805 ns 48143939 ns 5 bytes=67.1089M bytes_per_second=2.46755G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time_median 25338600 ns 48155785 ns 5 bytes=67.1089M bytes_per_second=2.46659G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time_stddev 38722 ns 24625 ns 5 bytes=0 bytes_per_second=3.8669M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time_cv 0.15 % 0.05 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time 45137900 ns 86562829 ns 15 bytes=134.218M bytes_per_second=2.76929G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time 45698658 ns 87483093 ns 15 bytes=134.218M bytes_per_second=2.73531G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time 45572427 ns 87347058 ns 15 bytes=134.218M bytes_per_second=2.74289G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time 45548406 ns 87433825 ns 15 bytes=134.218M bytes_per_second=2.74433G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time 45594540 ns 87356616 ns 15 bytes=134.218M bytes_per_second=2.74156G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time_mean 45510386 ns 87236684 ns 5 bytes=134.218M bytes_per_second=2.74668G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time_median 45572427 ns 87356616 ns 5 bytes=134.218M bytes_per_second=2.74289G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time_stddev 215968 ns 380864 ns 5 bytes=0 bytes_per_second=13.417M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time_cv 0.47 % 0.44 % 5 bytes=0.00% bytes_per_second=0.48% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time 84820339 ns 162293517 ns 8 bytes=268.435M bytes_per_second=2.94741G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time 86297066 ns 165185001 ns 8 bytes=268.435M bytes_per_second=2.89697G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time 86418905 ns 165221679 ns 8 bytes=268.435M bytes_per_second=2.89289G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time 86384427 ns 165256783 ns 8 bytes=268.435M bytes_per_second=2.89404G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time 84718360 ns 162070063 ns 8 bytes=268.435M bytes_per_second=2.95095G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time_mean 85727819 ns 164005408 ns 5 bytes=268.435M bytes_per_second=2.91645G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time_median 86297066 ns 165185001 ns 5 bytes=268.435M bytes_per_second=2.89697G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time_stddev 876827 ns 1666795 ns 5 bytes=0 bytes_per_second=30.6593M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time_cv 1.02 % 1.02 % 5 bytes=0.00% bytes_per_second=1.03% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time 164116807 ns 305926552 ns 4 bytes=536.871M bytes_per_second=3.04661G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time 167607840 ns 312805653 ns 4 bytes=536.871M bytes_per_second=2.98315G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time 164013322 ns 305132301 ns 4 bytes=536.871M bytes_per_second=3.04853G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time 167605273 ns 313014963 ns 4 bytes=536.871M bytes_per_second=2.9832G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time 163974013 ns 305464716 ns 4 bytes=536.871M bytes_per_second=3.04926G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time_mean 165463451 ns 308468837 ns 5 bytes=536.871M bytes_per_second=3.02215G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time_median 164116807 ns 305926552 ns 5 bytes=536.871M bytes_per_second=3.04661G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time_stddev 1957074 ns 4064962 ns 5 bytes=0 bytes_per_second=36.4468M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time_cv 1.18 % 1.32 % 5 bytes=0.00% bytes_per_second=1.18% dst_gpu=0.00% src_gpu=-nan% +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time 317798287 ns 558979927 ns 2 bytes=1073.74M bytes_per_second=3.14665G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time 317685917 ns 557066069 ns 2 bytes=1073.74M bytes_per_second=3.14776G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time 319240957 ns 557919509 ns 2 bytes=1073.74M bytes_per_second=3.13243G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time 317770600 ns 556777157 ns 2 bytes=1073.74M bytes_per_second=3.14692G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time 317191184 ns 556754394 ns 2 bytes=1073.74M bytes_per_second=3.15267G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time_mean 317937389 ns 557499411 ns 5 bytes=1073.74M bytes_per_second=3.14529G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time_median 317770600 ns 557066069 ns 5 bytes=1073.74M bytes_per_second=3.14692G/s dst_gpu=7 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time_stddev 769175 ns 953008 ns 5 bytes=0 bytes_per_second=7.77359M/s dst_gpu=0 src_gpu=0 +Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time_cv 0.24 % 0.17 % 5 bytes=0.00% bytes_per_second=0.24% dst_gpu=0.00% src_gpu=-nan% +[2023-10-09 18:16:23.944] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 18:16:23.944] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 18:16:26.126] [scope] [info] recorded system CPU turbo state +[2023-10-09 18:16:26.126] [scope] [info] recorded CPU goveror +[2023-10-09 18:16:26.126] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 18:16:26.126] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T18:16:28-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1883.33 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 2.10, 2.56, 4.64 +--------------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +--------------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):12/manual_time 1863933 ns 2066156 ns 378 bytes=4.096k bytes_per_second=2.0957M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):12/manual_time 1866355 ns 2066231 ns 378 bytes=4.096k bytes_per_second=2.09298M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):12/manual_time 1862123 ns 2066124 ns 378 bytes=4.096k bytes_per_second=2.09774M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):12/manual_time 1862263 ns 2066139 ns 378 bytes=4.096k bytes_per_second=2.09758M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):12/manual_time 1865771 ns 2065175 ns 378 bytes=4.096k bytes_per_second=2.09364M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):12/manual_time_mean 1864089 ns 2065965 ns 5 bytes=4.096k bytes_per_second=2.09553M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):12/manual_time_median 1863933 ns 2066139 ns 5 bytes=4.096k bytes_per_second=2.0957M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):12/manual_time_stddev 1949 ns 444 ns 5 bytes=0 bytes_per_second=2.24287k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):12/manual_time_cv 0.10 % 0.02 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):13/manual_time 1859542 ns 2065013 ns 378 bytes=8.192k bytes_per_second=4.2013M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):13/manual_time 1864268 ns 2066159 ns 378 bytes=8.192k bytes_per_second=4.19065M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):13/manual_time 1859069 ns 2064835 ns 378 bytes=8.192k bytes_per_second=4.20237M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):13/manual_time 1863901 ns 2064854 ns 378 bytes=8.192k bytes_per_second=4.19148M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):13/manual_time 1868052 ns 2068961 ns 378 bytes=8.192k bytes_per_second=4.18216M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):13/manual_time_mean 1862966 ns 2065964 ns 5 bytes=8.192k bytes_per_second=4.19359M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):13/manual_time_median 1863901 ns 2065013 ns 5 bytes=8.192k bytes_per_second=4.19148M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):13/manual_time_stddev 3720 ns 1763 ns 5 bytes=0 bytes_per_second=8.57194k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):13/manual_time_cv 0.20 % 0.09 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):14/manual_time 1860625 ns 2067824 ns 378 bytes=16.384k bytes_per_second=8.39772M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):14/manual_time 1866847 ns 2069016 ns 378 bytes=16.384k bytes_per_second=8.36973M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):14/manual_time 1862397 ns 2069221 ns 378 bytes=16.384k bytes_per_second=8.38973M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):14/manual_time 1864329 ns 2067238 ns 378 bytes=16.384k bytes_per_second=8.38103M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):14/manual_time 1870672 ns 2072398 ns 378 bytes=16.384k bytes_per_second=8.35261M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):14/manual_time_mean 1864974 ns 2069139 ns 5 bytes=16.384k bytes_per_second=8.37816M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):14/manual_time_median 1864329 ns 2069016 ns 5 bytes=16.384k bytes_per_second=8.38103M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):14/manual_time_stddev 3936 ns 1999 ns 5 bytes=0 bytes_per_second=18.09k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):14/manual_time_cv 0.21 % 0.10 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):15/manual_time 1862744 ns 2071272 ns 377 bytes=32.768k bytes_per_second=16.7763M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):15/manual_time 1866972 ns 2070842 ns 377 bytes=32.768k bytes_per_second=16.7383M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):15/manual_time 1863193 ns 2071333 ns 377 bytes=32.768k bytes_per_second=16.7723M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):15/manual_time 1868545 ns 2072602 ns 377 bytes=32.768k bytes_per_second=16.7242M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):15/manual_time 1872173 ns 2077047 ns 377 bytes=32.768k bytes_per_second=16.6918M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):15/manual_time_mean 1866725 ns 2072619 ns 5 bytes=32.768k bytes_per_second=16.7406M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):15/manual_time_median 1866972 ns 2071333 ns 5 bytes=32.768k bytes_per_second=16.7383M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):15/manual_time_stddev 3917 ns 2561 ns 5 bytes=0 bytes_per_second=35.9528k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):15/manual_time_cv 0.21 % 0.12 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):16/manual_time 1864052 ns 2077810 ns 377 bytes=65.536k bytes_per_second=33.5291M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):16/manual_time 1868652 ns 2077533 ns 377 bytes=65.536k bytes_per_second=33.4466M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):16/manual_time 1866614 ns 2079861 ns 377 bytes=65.536k bytes_per_second=33.4831M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):16/manual_time 1868117 ns 2077084 ns 377 bytes=65.536k bytes_per_second=33.4562M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):16/manual_time 1874520 ns 2083070 ns 377 bytes=65.536k bytes_per_second=33.3419M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):16/manual_time_mean 1868391 ns 2079072 ns 5 bytes=65.536k bytes_per_second=33.4514M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):16/manual_time_median 1868117 ns 2077810 ns 5 bytes=65.536k bytes_per_second=33.4562M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):16/manual_time_stddev 3863 ns 2476 ns 5 bytes=0 bytes_per_second=70.7352k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):16/manual_time_cv 0.21 % 0.12 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):17/manual_time 1876106 ns 2093157 ns 377 bytes=131.072k bytes_per_second=66.6274M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):17/manual_time 1872045 ns 2088356 ns 377 bytes=131.072k bytes_per_second=66.7719M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):17/manual_time 1875330 ns 2092839 ns 377 bytes=131.072k bytes_per_second=66.6549M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):17/manual_time 1868906 ns 2089795 ns 377 bytes=131.072k bytes_per_second=66.884M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):17/manual_time 1878148 ns 2095512 ns 377 bytes=131.072k bytes_per_second=66.5549M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):17/manual_time_mean 1874107 ns 2091932 ns 5 bytes=131.072k bytes_per_second=66.6986M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):17/manual_time_median 1875330 ns 2092839 ns 5 bytes=131.072k bytes_per_second=66.6549M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):17/manual_time_stddev 3644 ns 2850 ns 5 bytes=0 bytes_per_second=132.912k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):17/manual_time_cv 0.19 % 0.14 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):18/manual_time 1880936 ns 2114076 ns 376 bytes=262.144k bytes_per_second=132.913M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):18/manual_time 1881366 ns 2114523 ns 376 bytes=262.144k bytes_per_second=132.882M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):18/manual_time 1880012 ns 2113906 ns 376 bytes=262.144k bytes_per_second=132.978M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):18/manual_time 1881199 ns 2113809 ns 376 bytes=262.144k bytes_per_second=132.894M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):18/manual_time 1879783 ns 2112737 ns 376 bytes=262.144k bytes_per_second=132.994M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):18/manual_time_mean 1880659 ns 2113810 ns 5 bytes=262.144k bytes_per_second=132.932M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):18/manual_time_median 1880936 ns 2113906 ns 5 bytes=262.144k bytes_per_second=132.913M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):18/manual_time_stddev 717 ns 660 ns 5 bytes=0 bytes_per_second=51.8937k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):18/manual_time_cv 0.04 % 0.03 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):19/manual_time 1893486 ns 2159321 ns 372 bytes=524.288k bytes_per_second=264.063M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):19/manual_time 1899114 ns 2165883 ns 372 bytes=524.288k bytes_per_second=263.281M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):19/manual_time 1894771 ns 2161845 ns 372 bytes=524.288k bytes_per_second=263.884M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):19/manual_time 1898428 ns 2162201 ns 372 bytes=524.288k bytes_per_second=263.376M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):19/manual_time 1897424 ns 2162127 ns 372 bytes=524.288k bytes_per_second=263.515M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):19/manual_time_mean 1896645 ns 2162275 ns 5 bytes=524.288k bytes_per_second=263.624M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):19/manual_time_median 1897424 ns 2162127 ns 5 bytes=524.288k bytes_per_second=263.515M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):19/manual_time_stddev 2417 ns 2343 ns 5 bytes=0 bytes_per_second=344.186k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):19/manual_time_cv 0.13 % 0.11 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):20/manual_time 1915665 ns 2239173 ns 370 bytes=1048.58k bytes_per_second=522.012M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):20/manual_time 1907863 ns 2235029 ns 370 bytes=1048.58k bytes_per_second=524.147M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):20/manual_time 1914351 ns 2238947 ns 370 bytes=1048.58k bytes_per_second=522.37M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):20/manual_time 1908389 ns 2235133 ns 370 bytes=1048.58k bytes_per_second=524.002M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):20/manual_time 1913051 ns 2236794 ns 370 bytes=1048.58k bytes_per_second=522.725M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):20/manual_time_mean 1911864 ns 2237015 ns 5 bytes=1048.58k bytes_per_second=523.051M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):20/manual_time_median 1913051 ns 2236794 ns 5 bytes=1048.58k bytes_per_second=522.725M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):20/manual_time_stddev 3540 ns 1995 ns 5 bytes=0 bytes_per_second=992.083k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):20/manual_time_cv 0.19 % 0.09 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):21/manual_time 1957061 ns 2416092 ns 360 bytes=2.09715M bytes_per_second=1021.94M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):21/manual_time 1957053 ns 2415992 ns 360 bytes=2.09715M bytes_per_second=1021.94M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):21/manual_time 1957606 ns 2416013 ns 360 bytes=2.09715M bytes_per_second=1021.66M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):21/manual_time 1958854 ns 2416522 ns 360 bytes=2.09715M bytes_per_second=1021.01M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):21/manual_time 1955762 ns 2411477 ns 360 bytes=2.09715M bytes_per_second=1022.62M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):21/manual_time_mean 1957267 ns 2415219 ns 5 bytes=2.09715M bytes_per_second=1021.83M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):21/manual_time_median 1957061 ns 2416013 ns 5 bytes=2.09715M bytes_per_second=1021.94M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):21/manual_time_stddev 1116 ns 2103 ns 5 bytes=0 bytes_per_second=596.787k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):21/manual_time_cv 0.06 % 0.09 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):22/manual_time 2090258 ns 2795255 ns 336 bytes=4.1943M bytes_per_second=1.86879G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):22/manual_time 2095707 ns 2799848 ns 336 bytes=4.1943M bytes_per_second=1.86393G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):22/manual_time 2090354 ns 2794487 ns 336 bytes=4.1943M bytes_per_second=1.8687G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):22/manual_time 2091161 ns 2795460 ns 336 bytes=4.1943M bytes_per_second=1.86798G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):22/manual_time 2088806 ns 2793986 ns 336 bytes=4.1943M bytes_per_second=1.87009G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):22/manual_time_mean 2091257 ns 2795807 ns 5 bytes=4.1943M bytes_per_second=1.8679G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):22/manual_time_median 2090354 ns 2795255 ns 5 bytes=4.1943M bytes_per_second=1.8687G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):22/manual_time_stddev 2628 ns 2335 ns 5 bytes=0 bytes_per_second=2.40084M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):22/manual_time_cv 0.13 % 0.08 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):23/manual_time 2225753 ns 3454213 ns 314 bytes=8.38861M bytes_per_second=3.51005G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):23/manual_time 2232882 ns 3458231 ns 314 bytes=8.38861M bytes_per_second=3.49884G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):23/manual_time 2226745 ns 3455294 ns 314 bytes=8.38861M bytes_per_second=3.50848G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):23/manual_time 2231238 ns 3456799 ns 314 bytes=8.38861M bytes_per_second=3.50142G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):23/manual_time 2225500 ns 3454400 ns 314 bytes=8.38861M bytes_per_second=3.51045G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):23/manual_time_mean 2228424 ns 3455787 ns 5 bytes=8.38861M bytes_per_second=3.50585G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):23/manual_time_median 2226745 ns 3455294 ns 5 bytes=8.38861M bytes_per_second=3.50848G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):23/manual_time_stddev 3402 ns 1706 ns 5 bytes=0 bytes_per_second=5.47702M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):23/manual_time_cv 0.15 % 0.05 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):24/manual_time 3331133 ns 5608658 ns 210 bytes=16.7772M bytes_per_second=4.6906G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):24/manual_time 3353696 ns 5631242 ns 210 bytes=16.7772M bytes_per_second=4.65904G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):24/manual_time 3328240 ns 5603456 ns 210 bytes=16.7772M bytes_per_second=4.69467G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):24/manual_time 3331164 ns 5607769 ns 210 bytes=16.7772M bytes_per_second=4.69055G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):24/manual_time 3329091 ns 5604207 ns 210 bytes=16.7772M bytes_per_second=4.69347G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):24/manual_time_mean 3334665 ns 5611067 ns 5 bytes=16.7772M bytes_per_second=4.68567G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):24/manual_time_median 3331133 ns 5607769 ns 5 bytes=16.7772M bytes_per_second=4.6906G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):24/manual_time_stddev 10715 ns 11497 ns 5 bytes=0 bytes_per_second=15.3537M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):24/manual_time_cv 0.32 % 0.20 % 5 bytes=0.00% bytes_per_second=0.32% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):25/manual_time 6675505 ns 10974599 ns 104 bytes=33.5544M bytes_per_second=4.68129G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):25/manual_time 6647619 ns 10940433 ns 104 bytes=33.5544M bytes_per_second=4.70093G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):25/manual_time 6655420 ns 10963515 ns 104 bytes=33.5544M bytes_per_second=4.69542G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):25/manual_time 6644094 ns 10944229 ns 104 bytes=33.5544M bytes_per_second=4.70343G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):25/manual_time 6634380 ns 10912446 ns 104 bytes=33.5544M bytes_per_second=4.71031G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):25/manual_time_mean 6651403 ns 10947044 ns 5 bytes=33.5544M bytes_per_second=4.69828G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):25/manual_time_median 6647619 ns 10944229 ns 5 bytes=33.5544M bytes_per_second=4.70093G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):25/manual_time_stddev 15448 ns 23871 ns 5 bytes=0 bytes_per_second=11.1585M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):25/manual_time_cv 0.23 % 0.22 % 5 bytes=0.00% bytes_per_second=0.23% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):26/manual_time 13561138 ns 22249437 ns 52 bytes=67.1089M bytes_per_second=4.60876G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):26/manual_time 13205759 ns 21306825 ns 52 bytes=67.1089M bytes_per_second=4.73278G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):26/manual_time 13570154 ns 22263162 ns 52 bytes=67.1089M bytes_per_second=4.6057G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):26/manual_time 13581969 ns 22273357 ns 52 bytes=67.1089M bytes_per_second=4.60169G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):26/manual_time 13564655 ns 22246173 ns 52 bytes=67.1089M bytes_per_second=4.60756G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):26/manual_time_mean 13496735 ns 22067791 ns 5 bytes=67.1089M bytes_per_second=4.6313G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):26/manual_time_median 13564655 ns 22249437 ns 5 bytes=67.1089M bytes_per_second=4.60756G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):26/manual_time_stddev 162852 ns 425533 ns 5 bytes=0 bytes_per_second=58.1586M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):26/manual_time_cv 1.21 % 1.93 % 5 bytes=0.00% bytes_per_second=1.23% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):27/manual_time 26271017 ns 42577795 ns 27 bytes=134.218M bytes_per_second=4.7581G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):27/manual_time 26279574 ns 42616521 ns 27 bytes=134.218M bytes_per_second=4.75655G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):27/manual_time 26268801 ns 42588407 ns 27 bytes=134.218M bytes_per_second=4.7585G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):27/manual_time 26288161 ns 42659886 ns 27 bytes=134.218M bytes_per_second=4.75499G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):27/manual_time 26116420 ns 41649207 ns 27 bytes=134.218M bytes_per_second=4.78626G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):27/manual_time_mean 26244795 ns 42418363 ns 5 bytes=134.218M bytes_per_second=4.76288G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):27/manual_time_median 26271017 ns 42588407 ns 5 bytes=134.218M bytes_per_second=4.7581G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):27/manual_time_stddev 72170 ns 431142 ns 5 bytes=0 bytes_per_second=13.46M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):27/manual_time_cv 0.27 % 1.02 % 5 bytes=0.00% bytes_per_second=0.28% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):28/manual_time 51197370 ns 81089192 ns 10 bytes=268.435M bytes_per_second=4.88306G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):28/manual_time 51283114 ns 81127683 ns 10 bytes=268.435M bytes_per_second=4.8749G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):28/manual_time 47494085 ns 79441692 ns 10 bytes=268.435M bytes_per_second=5.26381G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):28/manual_time 51250938 ns 81082568 ns 10 bytes=268.435M bytes_per_second=4.87796G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):28/manual_time 51259353 ns 81083335 ns 10 bytes=268.435M bytes_per_second=4.87716G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):28/manual_time_mean 50496972 ns 80764894 ns 5 bytes=268.435M bytes_per_second=4.95538G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):28/manual_time_median 51250938 ns 81083335 ns 5 bytes=268.435M bytes_per_second=4.87796G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):28/manual_time_stddev 1678958 ns 739927 ns 5 bytes=0 bytes_per_second=176.585M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):28/manual_time_cv 3.32 % 0.92 % 5 bytes=0.00% bytes_per_second=3.48% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):29/manual_time 101311033 ns 159572453 ns 8 bytes=536.871M bytes_per_second=4.9353G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):29/manual_time 89731237 ns 155701272 ns 8 bytes=536.871M bytes_per_second=5.5722G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):29/manual_time 101458775 ns 159332219 ns 8 bytes=536.871M bytes_per_second=4.92811G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):29/manual_time 89740275 ns 156500597 ns 8 bytes=536.871M bytes_per_second=5.57163G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):29/manual_time 101404735 ns 159306592 ns 8 bytes=536.871M bytes_per_second=4.93074G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):29/manual_time_mean 96729211 ns 158082627 ns 5 bytes=536.871M bytes_per_second=5.18759G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):29/manual_time_median 101311033 ns 159306592 ns 5 bytes=536.871M bytes_per_second=4.9353G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):29/manual_time_stddev 6384341 ns 1833904 ns 5 bytes=0 bytes_per_second=359.265M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):29/manual_time_cv 6.60 % 1.16 % 5 bytes=0.00% bytes_per_second=6.76% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):30/manual_time 187225550 ns 284932503 ns 4 bytes=1073.74M bytes_per_second=5.34115G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):30/manual_time 187323395 ns 285486249 ns 4 bytes=1073.74M bytes_per_second=5.33836G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):30/manual_time 187320907 ns 285414104 ns 4 bytes=1073.74M bytes_per_second=5.33843G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):30/manual_time 187252868 ns 285446675 ns 4 bytes=1073.74M bytes_per_second=5.34037G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):30/manual_time 187444191 ns 285764015 ns 4 bytes=1073.74M bytes_per_second=5.33492G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):30/manual_time_mean 187313382 ns 285408709 ns 5 bytes=1073.74M bytes_per_second=5.33865G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):30/manual_time_median 187320907 ns 285446675 ns 5 bytes=1073.74M bytes_per_second=5.33843G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):30/manual_time_stddev 84623 ns 300207 ns 5 bytes=0 bytes_per_second=2.46913M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_fine/0/0/log2(N):30/manual_time_cv 0.05 % 0.11 % 5 bytes=0.00% bytes_per_second=0.05% dst_gpu=-nan% src_numa=-nan% +[2023-10-09 18:18:38.872] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 18:18:38.872] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 18:18:39.285] [scope] [info] recorded system CPU turbo state +[2023-10-09 18:18:39.285] [scope] [info] recorded CPU goveror +[2023-10-09 18:18:39.285] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 18:18:39.285] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T18:18:41-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1796.27 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 2.44, 2.61, 4.37 +----------------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +----------------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time 1864807 ns 2064841 ns 378 bytes=4.096k bytes_per_second=2.09472M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time 1861071 ns 2064907 ns 378 bytes=4.096k bytes_per_second=2.09893M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time 1869373 ns 2069160 ns 378 bytes=4.096k bytes_per_second=2.0896M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time 1864995 ns 2064682 ns 378 bytes=4.096k bytes_per_second=2.09451M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time 1860636 ns 2064727 ns 378 bytes=4.096k bytes_per_second=2.09942M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time_mean 1864176 ns 2065663 ns 5 bytes=4.096k bytes_per_second=2.09544M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time_median 1864807 ns 2064841 ns 5 bytes=4.096k bytes_per_second=2.09472M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time_stddev 3545 ns 1957 ns 5 bytes=0 bytes_per_second=4.07698k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time_cv 0.19 % 0.09 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time 1864430 ns 2065223 ns 378 bytes=8.192k bytes_per_second=4.19029M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time 1859697 ns 2065490 ns 378 bytes=8.192k bytes_per_second=4.20095M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time 1863776 ns 2065156 ns 378 bytes=8.192k bytes_per_second=4.19176M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time 1860118 ns 2065504 ns 378 bytes=8.192k bytes_per_second=4.2M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time 1859788 ns 2065352 ns 378 bytes=8.192k bytes_per_second=4.20075M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time_mean 1861562 ns 2065345 ns 5 bytes=8.192k bytes_per_second=4.19675M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time_median 1860118 ns 2065352 ns 5 bytes=8.192k bytes_per_second=4.2M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time_stddev 2336 ns 156 ns 5 bytes=0 bytes_per_second=5.39112k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time_cv 0.13 % 0.01 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time 1866126 ns 2068244 ns 378 bytes=16.384k bytes_per_second=8.37296M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time 1860701 ns 2067551 ns 378 bytes=16.384k bytes_per_second=8.39737M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time 1864418 ns 2067444 ns 378 bytes=16.384k bytes_per_second=8.38063M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time 1860237 ns 2067670 ns 378 bytes=16.384k bytes_per_second=8.39947M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time 1864919 ns 2067328 ns 378 bytes=16.384k bytes_per_second=8.37838M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time_mean 1863280 ns 2067647 ns 5 bytes=16.384k bytes_per_second=8.38576M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time_median 1864418 ns 2067551 ns 5 bytes=16.384k bytes_per_second=8.38063M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time_stddev 2645 ns 357 ns 5 bytes=0 bytes_per_second=12.1949k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time_cv 0.14 % 0.02 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time 1867397 ns 2071025 ns 373 bytes=32.768k bytes_per_second=16.7345M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time 1862999 ns 2071442 ns 373 bytes=32.768k bytes_per_second=16.774M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time 1866870 ns 2071272 ns 373 bytes=32.768k bytes_per_second=16.7392M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time 1862967 ns 2071330 ns 373 bytes=32.768k bytes_per_second=16.7743M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time 1866984 ns 2071262 ns 373 bytes=32.768k bytes_per_second=16.7382M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time_mean 1865443 ns 2071266 ns 5 bytes=32.768k bytes_per_second=16.7521M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time_median 1866870 ns 2071272 ns 5 bytes=32.768k bytes_per_second=16.7392M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time_stddev 2255 ns 152 ns 5 bytes=0 bytes_per_second=20.7421k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time_cv 0.12 % 0.01 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time 1869601 ns 2077364 ns 374 bytes=65.536k bytes_per_second=33.4296M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time 1865143 ns 2077887 ns 374 bytes=65.536k bytes_per_second=33.5095M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time 1869811 ns 2077634 ns 374 bytes=65.536k bytes_per_second=33.4258M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time 1865596 ns 2078155 ns 374 bytes=65.536k bytes_per_second=33.5014M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time 1870052 ns 2077955 ns 374 bytes=65.536k bytes_per_second=33.4215M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time_mean 1868040 ns 2077799 ns 5 bytes=65.536k bytes_per_second=33.4576M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time_median 1869601 ns 2077887 ns 5 bytes=65.536k bytes_per_second=33.4296M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time_stddev 2449 ns 306 ns 5 bytes=0 bytes_per_second=44.9352k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time_cv 0.13 % 0.01 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time 1879033 ns 2095160 ns 377 bytes=131.072k bytes_per_second=66.5236M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time 1870066 ns 2090538 ns 377 bytes=131.072k bytes_per_second=66.8426M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time 1876274 ns 2093544 ns 377 bytes=131.072k bytes_per_second=66.6214M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time 1871139 ns 2088178 ns 377 bytes=131.072k bytes_per_second=66.8042M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time 1875918 ns 2092939 ns 377 bytes=131.072k bytes_per_second=66.634M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time_mean 1874486 ns 2092072 ns 5 bytes=131.072k bytes_per_second=66.6852M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time_median 1875918 ns 2092939 ns 5 bytes=131.072k bytes_per_second=66.634M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time_stddev 3764 ns 2737 ns 5 bytes=0 bytes_per_second=137.131k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time_cv 0.20 % 0.13 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time 1870736 ns 2107948 ns 376 bytes=262.144k bytes_per_second=133.637M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time 1877520 ns 2111334 ns 376 bytes=262.144k bytes_per_second=133.154M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time 1876780 ns 2110985 ns 376 bytes=262.144k bytes_per_second=133.207M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time 1877948 ns 2111327 ns 376 bytes=262.144k bytes_per_second=133.124M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time 1880212 ns 2113398 ns 376 bytes=262.144k bytes_per_second=132.964M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time_mean 1876639 ns 2110998 ns 5 bytes=262.144k bytes_per_second=133.217M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time_median 1877520 ns 2111327 ns 5 bytes=262.144k bytes_per_second=133.154M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time_stddev 3540 ns 1955 ns 5 bytes=0 bytes_per_second=257.733k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time_cv 0.19 % 0.09 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time 1896599 ns 2162878 ns 372 bytes=524.288k bytes_per_second=263.63M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time 1890800 ns 2157501 ns 372 bytes=524.288k bytes_per_second=264.438M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time 1890474 ns 2157422 ns 372 bytes=524.288k bytes_per_second=264.484M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time 1892936 ns 2160272 ns 372 bytes=524.288k bytes_per_second=264.14M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time 1895610 ns 2162124 ns 372 bytes=524.288k bytes_per_second=263.767M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time_mean 1893284 ns 2160039 ns 5 bytes=524.288k bytes_per_second=264.092M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time_median 1892936 ns 2160272 ns 5 bytes=524.288k bytes_per_second=264.14M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time_stddev 2765 ns 2537 ns 5 bytes=0 bytes_per_second=394.895k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time_cv 0.15 % 0.12 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time 1912945 ns 2238121 ns 368 bytes=1048.58k bytes_per_second=522.754M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time 1908089 ns 2235075 ns 368 bytes=1048.58k bytes_per_second=524.084M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time 1913366 ns 2237974 ns 368 bytes=1048.58k bytes_per_second=522.639M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time 1906862 ns 2234247 ns 368 bytes=1048.58k bytes_per_second=524.422M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time 1914455 ns 2238877 ns 368 bytes=1048.58k bytes_per_second=522.342M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time_mean 1911144 ns 2236859 ns 5 bytes=1048.58k bytes_per_second=523.248M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time_median 1912945 ns 2237974 ns 5 bytes=1048.58k bytes_per_second=522.754M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time_stddev 3421 ns 2056 ns 5 bytes=0 bytes_per_second=959.657k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time_cv 0.18 % 0.09 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time 1959554 ns 2417861 ns 358 bytes=2.09715M bytes_per_second=1020.64M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time 1958648 ns 2418012 ns 358 bytes=2.09715M bytes_per_second=1021.11M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time 1958192 ns 2416970 ns 358 bytes=2.09715M bytes_per_second=1021.35M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time 1959759 ns 2418459 ns 358 bytes=2.09715M bytes_per_second=1020.53M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time 1956051 ns 2413392 ns 358 bytes=2.09715M bytes_per_second=1022.47M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time_mean 1958441 ns 2416939 ns 5 bytes=2.09715M bytes_per_second=1021.22M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time_median 1958648 ns 2417861 ns 5 bytes=2.09715M bytes_per_second=1021.11M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time_stddev 1483 ns 2055 ns 5 bytes=0 bytes_per_second=792.059k/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time_cv 0.08 % 0.09 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time 2088627 ns 2794028 ns 336 bytes=4.1943M bytes_per_second=1.87025G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time 2095617 ns 2800380 ns 336 bytes=4.1943M bytes_per_second=1.86401G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time 2089318 ns 2794398 ns 336 bytes=4.1943M bytes_per_second=1.86963G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time 2089058 ns 2793256 ns 336 bytes=4.1943M bytes_per_second=1.86986G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time 2089237 ns 2794556 ns 336 bytes=4.1943M bytes_per_second=1.8697G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time_mean 2090371 ns 2795324 ns 5 bytes=4.1943M bytes_per_second=1.86869G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time_median 2089237 ns 2794398 ns 5 bytes=4.1943M bytes_per_second=1.8697G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time_stddev 2944 ns 2871 ns 5 bytes=0 bytes_per_second=2.69038M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time_cv 0.14 % 0.10 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time 2226295 ns 3454833 ns 314 bytes=8.38861M bytes_per_second=3.50919G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time 2231511 ns 3457667 ns 314 bytes=8.38861M bytes_per_second=3.50099G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time 2223345 ns 3452665 ns 314 bytes=8.38861M bytes_per_second=3.51385G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time 2230137 ns 3456741 ns 314 bytes=8.38861M bytes_per_second=3.50315G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time 2224832 ns 3454705 ns 314 bytes=8.38861M bytes_per_second=3.5115G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time_mean 2227224 ns 3455322 ns 5 bytes=8.38861M bytes_per_second=3.50774G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time_median 2226295 ns 3454833 ns 5 bytes=8.38861M bytes_per_second=3.50919G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time_stddev 3482 ns 1949 ns 5 bytes=0 bytes_per_second=5.61353M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time_cv 0.16 % 0.06 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time 3329543 ns 5608918 ns 210 bytes=16.7772M bytes_per_second=4.69284G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time 3330135 ns 5610486 ns 210 bytes=16.7772M bytes_per_second=4.692G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time 3338884 ns 5617436 ns 210 bytes=16.7772M bytes_per_second=4.67971G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time 3330411 ns 5608712 ns 210 bytes=16.7772M bytes_per_second=4.69161G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time 3331408 ns 5608592 ns 210 bytes=16.7772M bytes_per_second=4.69021G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time_mean 3332076 ns 5610829 ns 5 bytes=16.7772M bytes_per_second=4.68927G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time_median 3330411 ns 5608918 ns 5 bytes=16.7772M bytes_per_second=4.69161G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time_stddev 3865 ns 3772 ns 5 bytes=0 bytes_per_second=5.56145M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time_cv 0.12 % 0.07 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time 6652671 ns 10952665 ns 104 bytes=33.5544M bytes_per_second=4.69736G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time 6672230 ns 10970077 ns 104 bytes=33.5544M bytes_per_second=4.68359G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time 6657633 ns 10960439 ns 104 bytes=33.5544M bytes_per_second=4.69386G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time 6669484 ns 10967631 ns 104 bytes=33.5544M bytes_per_second=4.68552G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time 6671593 ns 10977877 ns 104 bytes=33.5544M bytes_per_second=4.68404G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time_mean 6664722 ns 10965738 ns 5 bytes=33.5544M bytes_per_second=4.68887G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time_median 6669484 ns 10967631 ns 5 bytes=33.5544M bytes_per_second=4.68552G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time_stddev 8968 ns 9601 ns 5 bytes=0 bytes_per_second=6.4648M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time_cv 0.13 % 0.09 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time 13572545 ns 22267988 ns 52 bytes=67.1089M bytes_per_second=4.60488G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time 13253714 ns 21369407 ns 52 bytes=67.1089M bytes_per_second=4.71566G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time 13583028 ns 22290338 ns 52 bytes=67.1089M bytes_per_second=4.60133G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time 13578680 ns 22278849 ns 52 bytes=67.1089M bytes_per_second=4.6028G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time 13542058 ns 22242661 ns 52 bytes=67.1089M bytes_per_second=4.61525G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time_mean 13506005 ns 22089849 ns 5 bytes=67.1089M bytes_per_second=4.62799G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time_median 13572545 ns 22267988 ns 5 bytes=67.1089M bytes_per_second=4.60488G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time_stddev 141944 ns 403125 ns 5 bytes=0 bytes_per_second=50.4966M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time_cv 1.05 % 1.82 % 5 bytes=0.00% bytes_per_second=1.07% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time 26283960 ns 42580222 ns 27 bytes=134.218M bytes_per_second=4.75575G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time 26292766 ns 42623692 ns 27 bytes=134.218M bytes_per_second=4.75416G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time 26265470 ns 42567152 ns 27 bytes=134.218M bytes_per_second=4.7591G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time 26286947 ns 42653315 ns 27 bytes=134.218M bytes_per_second=4.75521G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time 26110613 ns 41675103 ns 27 bytes=134.218M bytes_per_second=4.78733G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time_mean 26247951 ns 42419897 ns 5 bytes=134.218M bytes_per_second=4.76231G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time_median 26283960 ns 42580222 ns 5 bytes=134.218M bytes_per_second=4.75575G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time_stddev 77450 ns 417769 ns 5 bytes=0 bytes_per_second=14.4443M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time_cv 0.30 % 0.98 % 5 bytes=0.00% bytes_per_second=0.30% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time 51235354 ns 81178326 ns 10 bytes=268.435M bytes_per_second=4.87944G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time 51293835 ns 81084652 ns 10 bytes=268.435M bytes_per_second=4.87388G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time 47543637 ns 79450427 ns 10 bytes=268.435M bytes_per_second=5.25833G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time 51264523 ns 81066111 ns 10 bytes=268.435M bytes_per_second=4.87667G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time 51219387 ns 81066656 ns 10 bytes=268.435M bytes_per_second=4.88096G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time_mean 50511347 ns 80769234 ns 5 bytes=268.435M bytes_per_second=4.95386G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time_median 51235354 ns 81066656 ns 5 bytes=268.435M bytes_per_second=4.87944G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time_stddev 1659245 ns 738697 ns 5 bytes=0 bytes_per_second=174.311M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time_cv 3.28 % 0.91 % 5 bytes=0.00% bytes_per_second=3.44% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time 101269672 ns 159252118 ns 8 bytes=536.871M bytes_per_second=4.93731G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time 89620835 ns 155676061 ns 8 bytes=536.871M bytes_per_second=5.57906G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time 101539577 ns 159481430 ns 8 bytes=536.871M bytes_per_second=4.92419G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time 89733739 ns 156535253 ns 8 bytes=536.871M bytes_per_second=5.57204G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time 101505379 ns 159314813 ns 8 bytes=536.871M bytes_per_second=4.92585G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time_mean 96733841 ns 158051935 ns 5 bytes=536.871M bytes_per_second=5.18769G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time_median 101269672 ns 159252118 ns 5 bytes=536.871M bytes_per_second=4.93731G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time_stddev 6442684 ns 1804429 ns 5 bytes=0 bytes_per_second=362.61M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time_cv 6.66 % 1.14 % 5 bytes=0.00% bytes_per_second=6.83% dst_gpu=-nan% src_numa=-nan% +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time 187675167 ns 285314577 ns 4 bytes=1073.74M bytes_per_second=5.32836G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time 187657204 ns 285638442 ns 4 bytes=1073.74M bytes_per_second=5.32887G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time 187730957 ns 285829954 ns 4 bytes=1073.74M bytes_per_second=5.32677G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time 187512763 ns 285455171 ns 4 bytes=1073.74M bytes_per_second=5.33297G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time 187260680 ns 285101423 ns 4 bytes=1073.74M bytes_per_second=5.34015G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time_mean 187567354 ns 285467913 ns 5 bytes=1073.74M bytes_per_second=5.33142G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time_median 187657204 ns 285455171 ns 5 bytes=1073.74M bytes_per_second=5.32887G/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time_stddev 189401 ns 282021 ns 5 bytes=0 bytes_per_second=5.51741M/s dst_gpu=0 src_numa=0 +Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time_cv 0.10 % 0.10 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=-nan% src_numa=-nan% +[2023-10-09 18:20:51.808] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 18:20:51.808] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 18:20:52.203] [scope] [info] recorded system CPU turbo state +[2023-10-09 18:20:52.203] [scope] [info] recorded CPU goveror +[2023-10-09 18:20:52.203] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 18:20:52.203] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T18:20:54-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1816.72 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 2.57, 2.64, 4.15 +------------------------------------------------------------------------------------------------------------------------------ +Benchmark Time CPU Iterations UserCounters... +------------------------------------------------------------------------------------------------------------------------------ +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):12/manual_time 1862956 ns 2065618 ns 378 bytes=4.096k bytes_per_second=2.0968M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):12/manual_time 1866563 ns 2066370 ns 378 bytes=4.096k bytes_per_second=2.09275M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):12/manual_time 1871343 ns 2070664 ns 378 bytes=4.096k bytes_per_second=2.08741M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):12/manual_time 1866362 ns 2065414 ns 378 bytes=4.096k bytes_per_second=2.09298M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):12/manual_time 1870945 ns 2070015 ns 378 bytes=4.096k bytes_per_second=2.08785M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):12/manual_time_mean 1867634 ns 2067616 ns 5 bytes=4.096k bytes_per_second=2.09156M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):12/manual_time_median 1866563 ns 2066370 ns 5 bytes=4.096k bytes_per_second=2.09275M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):12/manual_time_stddev 3513 ns 2522 ns 5 bytes=0 bytes_per_second=4.0295k/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):12/manual_time_cv 0.19 % 0.12 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):13/manual_time 1869157 ns 2070316 ns 378 bytes=8.192k bytes_per_second=4.17969M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):13/manual_time 1865292 ns 2066292 ns 378 bytes=8.192k bytes_per_second=4.18835M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):13/manual_time 1860948 ns 2066598 ns 378 bytes=8.192k bytes_per_second=4.19813M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):13/manual_time 1865715 ns 2066765 ns 378 bytes=8.192k bytes_per_second=4.1874M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):13/manual_time 1872484 ns 2073726 ns 378 bytes=8.192k bytes_per_second=4.17226M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):13/manual_time_mean 1866719 ns 2068739 ns 5 bytes=8.192k bytes_per_second=4.18517M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):13/manual_time_median 1865715 ns 2066765 ns 5 bytes=8.192k bytes_per_second=4.1874M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):13/manual_time_stddev 4345 ns 3233 ns 5 bytes=0 bytes_per_second=9.97548k/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):13/manual_time_cv 0.23 % 0.16 % 5 bytes=0.00% bytes_per_second=0.23% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):14/manual_time 1872874 ns 2075023 ns 378 bytes=16.384k bytes_per_second=8.34279M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):14/manual_time 1868077 ns 2070100 ns 378 bytes=16.384k bytes_per_second=8.36422M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):14/manual_time 1873134 ns 2075398 ns 378 bytes=16.384k bytes_per_second=8.34163M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):14/manual_time 1867652 ns 2069929 ns 378 bytes=16.384k bytes_per_second=8.36612M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):14/manual_time 1867321 ns 2074437 ns 378 bytes=16.384k bytes_per_second=8.3676M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):14/manual_time_mean 1869812 ns 2072977 ns 5 bytes=16.384k bytes_per_second=8.35647M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):14/manual_time_median 1868077 ns 2074437 ns 5 bytes=16.384k bytes_per_second=8.36422M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):14/manual_time_stddev 2928 ns 2727 ns 5 bytes=0 bytes_per_second=13.3935k/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):14/manual_time_cv 0.16 % 0.13 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):15/manual_time 1864172 ns 2072599 ns 377 bytes=32.768k bytes_per_second=16.7635M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):15/manual_time 1868607 ns 2072438 ns 377 bytes=32.768k bytes_per_second=16.7237M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):15/manual_time 1873381 ns 2077092 ns 377 bytes=32.768k bytes_per_second=16.6811M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):15/manual_time 1868530 ns 2072673 ns 377 bytes=32.768k bytes_per_second=16.7244M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):15/manual_time 1873784 ns 2077747 ns 377 bytes=32.768k bytes_per_second=16.6775M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):15/manual_time_mean 1869695 ns 2074510 ns 5 bytes=32.768k bytes_per_second=16.714M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):15/manual_time_median 1868607 ns 2072673 ns 5 bytes=32.768k bytes_per_second=16.7237M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):15/manual_time_stddev 3980 ns 2668 ns 5 bytes=0 bytes_per_second=36.4462k/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):15/manual_time_cv 0.21 % 0.13 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):16/manual_time 1870774 ns 2078700 ns 377 bytes=65.536k bytes_per_second=33.4086M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):16/manual_time 1865841 ns 2078903 ns 377 bytes=65.536k bytes_per_second=33.497M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):16/manual_time 1867170 ns 2080429 ns 377 bytes=65.536k bytes_per_second=33.4731M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):16/manual_time 1871236 ns 2080167 ns 377 bytes=65.536k bytes_per_second=33.4004M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):16/manual_time 1878079 ns 2086733 ns 377 bytes=65.536k bytes_per_second=33.2787M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):16/manual_time_mean 1870620 ns 2080987 ns 5 bytes=65.536k bytes_per_second=33.4116M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):16/manual_time_median 1870774 ns 2080167 ns 5 bytes=65.536k bytes_per_second=33.4086M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):16/manual_time_stddev 4764 ns 3300 ns 5 bytes=0 bytes_per_second=86.9956k/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):16/manual_time_cv 0.25 % 0.16 % 5 bytes=0.00% bytes_per_second=0.25% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):17/manual_time 1871061 ns 2091476 ns 376 bytes=131.072k bytes_per_second=66.807M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):17/manual_time 1874442 ns 2090878 ns 376 bytes=131.072k bytes_per_second=66.6865M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):17/manual_time 1879235 ns 2095300 ns 376 bytes=131.072k bytes_per_second=66.5164M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):17/manual_time 1870822 ns 2091319 ns 376 bytes=131.072k bytes_per_second=66.8156M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):17/manual_time 1870625 ns 2090997 ns 376 bytes=131.072k bytes_per_second=66.8226M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):17/manual_time_mean 1873237 ns 2091994 ns 5 bytes=131.072k bytes_per_second=66.7296M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):17/manual_time_median 1871061 ns 2091319 ns 5 bytes=131.072k bytes_per_second=66.807M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):17/manual_time_stddev 3702 ns 1864 ns 5 bytes=0 bytes_per_second=134.806k/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):17/manual_time_cv 0.20 % 0.09 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):18/manual_time 1881934 ns 2113842 ns 375 bytes=262.144k bytes_per_second=132.842M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):18/manual_time 1881512 ns 2113223 ns 375 bytes=262.144k bytes_per_second=132.872M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):18/manual_time 1884081 ns 2116035 ns 375 bytes=262.144k bytes_per_second=132.691M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):18/manual_time 1878784 ns 2110409 ns 375 bytes=262.144k bytes_per_second=133.065M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):18/manual_time 1875618 ns 2110124 ns 375 bytes=262.144k bytes_per_second=133.289M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):18/manual_time_mean 1880386 ns 2112727 ns 5 bytes=262.144k bytes_per_second=132.952M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):18/manual_time_median 1881512 ns 2113223 ns 5 bytes=262.144k bytes_per_second=132.872M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):18/manual_time_stddev 3264 ns 2479 ns 5 bytes=0 bytes_per_second=236.497k/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):18/manual_time_cv 0.17 % 0.12 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):19/manual_time 1894615 ns 2157831 ns 374 bytes=524.288k bytes_per_second=263.906M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):19/manual_time 1894444 ns 2157652 ns 374 bytes=524.288k bytes_per_second=263.93M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):19/manual_time 1897577 ns 2160716 ns 374 bytes=524.288k bytes_per_second=263.494M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):19/manual_time 1899459 ns 2160633 ns 374 bytes=524.288k bytes_per_second=263.233M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):19/manual_time 1901336 ns 2162432 ns 374 bytes=524.288k bytes_per_second=262.973M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):19/manual_time_mean 1897486 ns 2159853 ns 5 bytes=524.288k bytes_per_second=263.507M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):19/manual_time_median 1897577 ns 2160633 ns 5 bytes=524.288k bytes_per_second=263.494M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):19/manual_time_stddev 3009 ns 2058 ns 5 bytes=0 bytes_per_second=427.848k/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):19/manual_time_cv 0.16 % 0.10 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):20/manual_time 1908755 ns 2235575 ns 371 bytes=1048.58k bytes_per_second=523.902M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):20/manual_time 1900361 ns 2231065 ns 371 bytes=1048.58k bytes_per_second=526.216M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):20/manual_time 1908841 ns 2235690 ns 371 bytes=1048.58k bytes_per_second=523.878M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):20/manual_time 1904993 ns 2233579 ns 371 bytes=1048.58k bytes_per_second=524.936M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):20/manual_time 1919184 ns 2243934 ns 371 bytes=1048.58k bytes_per_second=521.055M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):20/manual_time_mean 1908427 ns 2235968 ns 5 bytes=1048.58k bytes_per_second=523.997M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):20/manual_time_median 1908755 ns 2235575 ns 5 bytes=1048.58k bytes_per_second=523.902M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):20/manual_time_stddev 6943 ns 4833 ns 5 bytes=0 bytes_per_second=1.90297M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):20/manual_time_cv 0.36 % 0.22 % 5 bytes=0.00% bytes_per_second=0.36% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):21/manual_time 1944147 ns 2452382 ns 362 bytes=2.09715M bytes_per_second=1028.73M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):21/manual_time 1945540 ns 2452863 ns 362 bytes=2.09715M bytes_per_second=1027.99M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):21/manual_time 1943102 ns 2451416 ns 362 bytes=2.09715M bytes_per_second=1029.28M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):21/manual_time 1944544 ns 2453093 ns 362 bytes=2.09715M bytes_per_second=1028.52M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):21/manual_time 1943076 ns 2452054 ns 362 bytes=2.09715M bytes_per_second=1029.3M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):21/manual_time_mean 1944081 ns 2452362 ns 5 bytes=2.09715M bytes_per_second=1028.76M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):21/manual_time_median 1944147 ns 2452382 ns 5 bytes=2.09715M bytes_per_second=1028.73M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):21/manual_time_stddev 1039 ns 666 ns 5 bytes=0 bytes_per_second=562.79k/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):21/manual_time_cv 0.05 % 0.03 % 5 bytes=0.00% bytes_per_second=0.05% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):22/manual_time 1978296 ns 2792024 ns 355 bytes=4.1943M bytes_per_second=1.97455G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):22/manual_time 1979655 ns 2792168 ns 355 bytes=4.1943M bytes_per_second=1.9732G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):22/manual_time 1978118 ns 2792427 ns 355 bytes=4.1943M bytes_per_second=1.97473G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):22/manual_time 1985971 ns 2795837 ns 355 bytes=4.1943M bytes_per_second=1.96692G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):22/manual_time 1982827 ns 2793030 ns 355 bytes=4.1943M bytes_per_second=1.97004G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):22/manual_time_mean 1980973 ns 2793097 ns 5 bytes=4.1943M bytes_per_second=1.97189G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):22/manual_time_median 1979655 ns 2792427 ns 5 bytes=4.1943M bytes_per_second=1.9732G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):22/manual_time_stddev 3372 ns 1579 ns 5 bytes=0 bytes_per_second=3.43371M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):22/manual_time_cv 0.17 % 0.06 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):23/manual_time 2031144 ns 3523772 ns 343 bytes=8.38861M bytes_per_second=3.84636G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):23/manual_time 2038103 ns 3527109 ns 343 bytes=8.38861M bytes_per_second=3.83322G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):23/manual_time 2035678 ns 3524335 ns 343 bytes=8.38861M bytes_per_second=3.83779G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):23/manual_time 2040967 ns 3533121 ns 343 bytes=8.38861M bytes_per_second=3.82784G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):23/manual_time 2033890 ns 3524665 ns 343 bytes=8.38861M bytes_per_second=3.84116G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):23/manual_time_mean 2035956 ns 3526601 ns 5 bytes=8.38861M bytes_per_second=3.83727G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):23/manual_time_median 2035678 ns 3524665 ns 5 bytes=8.38861M bytes_per_second=3.83779G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):23/manual_time_stddev 3782 ns 3862 ns 5 bytes=0 bytes_per_second=7.29875M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):23/manual_time_cv 0.19 % 0.11 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):24/manual_time 3584544 ns 6514645 ns 194 bytes=16.7772M bytes_per_second=4.35899G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):24/manual_time 3587943 ns 6520065 ns 194 bytes=16.7772M bytes_per_second=4.35486G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):24/manual_time 3598859 ns 6532758 ns 194 bytes=16.7772M bytes_per_second=4.34165G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):24/manual_time 3582062 ns 6506189 ns 194 bytes=16.7772M bytes_per_second=4.36201G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):24/manual_time 3582432 ns 6505517 ns 194 bytes=16.7772M bytes_per_second=4.36156G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):24/manual_time_mean 3587168 ns 6515835 ns 5 bytes=16.7772M bytes_per_second=4.35582G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):24/manual_time_median 3584544 ns 6514645 ns 5 bytes=16.7772M bytes_per_second=4.35899G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):24/manual_time_stddev 6940 ns 11238 ns 5 bytes=0 bytes_per_second=8.61275M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):24/manual_time_cv 0.19 % 0.17 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):25/manual_time 7248218 ns 13398361 ns 98 bytes=33.5544M bytes_per_second=4.3114G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):25/manual_time 7253219 ns 13390923 ns 98 bytes=33.5544M bytes_per_second=4.30843G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):25/manual_time 7248055 ns 13394522 ns 98 bytes=33.5544M bytes_per_second=4.3115G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):25/manual_time 7253565 ns 13363636 ns 98 bytes=33.5544M bytes_per_second=4.30823G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):25/manual_time 7253803 ns 13405745 ns 98 bytes=33.5544M bytes_per_second=4.30808G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):25/manual_time_mean 7251372 ns 13390637 ns 5 bytes=33.5544M bytes_per_second=4.30953G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):25/manual_time_median 7253219 ns 13394522 ns 5 bytes=33.5544M bytes_per_second=4.30843G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):25/manual_time_stddev 2961 ns 16063 ns 5 bytes=0 bytes_per_second=1.80253M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):25/manual_time_cv 0.04 % 0.12 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):26/manual_time 14162119 ns 25764457 ns 50 bytes=67.1089M bytes_per_second=4.41318G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):26/manual_time 14169204 ns 25764054 ns 50 bytes=67.1089M bytes_per_second=4.41097G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):26/manual_time 14161895 ns 25747192 ns 50 bytes=67.1089M bytes_per_second=4.41325G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):26/manual_time 14160922 ns 25743086 ns 50 bytes=67.1089M bytes_per_second=4.41355G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):26/manual_time 14158445 ns 25726608 ns 50 bytes=67.1089M bytes_per_second=4.41433G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):26/manual_time_mean 14162517 ns 25749080 ns 5 bytes=67.1089M bytes_per_second=4.41306G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):26/manual_time_median 14161895 ns 25747192 ns 5 bytes=67.1089M bytes_per_second=4.41325G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):26/manual_time_stddev 4012 ns 15852 ns 5 bytes=0 bytes_per_second=1.27984M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):26/manual_time_cv 0.03 % 0.06 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):27/manual_time 27426021 ns 48683464 ns 26 bytes=134.218M bytes_per_second=4.55772G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):27/manual_time 27459080 ns 48771552 ns 26 bytes=134.218M bytes_per_second=4.55223G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):27/manual_time 27422914 ns 48779079 ns 26 bytes=134.218M bytes_per_second=4.55823G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):27/manual_time 27457086 ns 48794694 ns 26 bytes=134.218M bytes_per_second=4.55256G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):27/manual_time 27354599 ns 48598063 ns 26 bytes=134.218M bytes_per_second=4.56962G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):27/manual_time_mean 27423940 ns 48725370 ns 5 bytes=134.218M bytes_per_second=4.55807G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):27/manual_time_median 27426021 ns 48771552 ns 5 bytes=134.218M bytes_per_second=4.55772G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):27/manual_time_stddev 42270 ns 83346 ns 5 bytes=0 bytes_per_second=7.20358M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):27/manual_time_cv 0.15 % 0.17 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):28/manual_time 53539996 ns 91677905 ns 10 bytes=268.435M bytes_per_second=4.66941G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):28/manual_time 53630397 ns 91670752 ns 10 bytes=268.435M bytes_per_second=4.66154G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):28/manual_time 53598203 ns 91685682 ns 10 bytes=268.435M bytes_per_second=4.66434G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):28/manual_time 53412138 ns 91585910 ns 10 bytes=268.435M bytes_per_second=4.68058G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):28/manual_time 53483483 ns 91713879 ns 10 bytes=268.435M bytes_per_second=4.67434G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):28/manual_time_mean 53532844 ns 91666825 ns 5 bytes=268.435M bytes_per_second=4.67004G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):28/manual_time_median 53539996 ns 91677905 ns 5 bytes=268.435M bytes_per_second=4.66941G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):28/manual_time_stddev 87815 ns 48102 ns 5 bytes=0 bytes_per_second=7.84778M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):28/manual_time_cv 0.16 % 0.05 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):29/manual_time 104932920 ns 177001985 ns 8 bytes=536.871M bytes_per_second=4.76495G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):29/manual_time 105057440 ns 176912656 ns 8 bytes=536.871M bytes_per_second=4.7593G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):29/manual_time 105143603 ns 177056918 ns 8 bytes=536.871M bytes_per_second=4.7554G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):29/manual_time 105017362 ns 177251728 ns 8 bytes=536.871M bytes_per_second=4.76112G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):29/manual_time 105244405 ns 177289415 ns 8 bytes=536.871M bytes_per_second=4.75085G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):29/manual_time_mean 105079146 ns 177102540 ns 5 bytes=536.871M bytes_per_second=4.75832G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):29/manual_time_median 105057440 ns 177056918 ns 5 bytes=536.871M bytes_per_second=4.7593G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):29/manual_time_stddev 119515 ns 162348 ns 5 bytes=0 bytes_per_second=5.54063M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):29/manual_time_cv 0.11 % 0.09 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=-nan% src_numa=-nan% +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):30/manual_time 184767980 ns 306319604 ns 4 bytes=1073.74M bytes_per_second=5.41219G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):30/manual_time 184387613 ns 305918397 ns 4 bytes=1073.74M bytes_per_second=5.42336G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):30/manual_time 183694039 ns 305472714 ns 4 bytes=1073.74M bytes_per_second=5.44383G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):30/manual_time 184376244 ns 306192488 ns 4 bytes=1073.74M bytes_per_second=5.42369G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):30/manual_time 183433428 ns 305065292 ns 4 bytes=1073.74M bytes_per_second=5.45157G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):30/manual_time_mean 184131861 ns 305793699 ns 5 bytes=1073.74M bytes_per_second=5.43093G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):30/manual_time_median 184376244 ns 305918397 ns 5 bytes=1073.74M bytes_per_second=5.42369G/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):30/manual_time_stddev 549835 ns 520761 ns 5 bytes=0 bytes_per_second=16.6167M/s dst_gpu=0 src_numa=0 +Comm_hipManaged_HostToGPUWriteDst/0/0/log2(N):30/manual_time_cv 0.30 % 0.17 % 5 bytes=0.00% bytes_per_second=0.30% dst_gpu=-nan% src_numa=-nan% +[2023-10-09 18:23:09.257] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 18:23:09.257] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Mon 09 Oct 2023 06:23:09 PM EDT diff --git a/results/r4-1465531.out b/results/r4-1465531.out new file mode 100644 index 0000000..72c9188 --- /dev/null +++ b/results/r4-1465531.out @@ -0,0 +1,241 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 05:44:29 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:44:32.047] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:44:32.048] [scope] [info] recorded CPU goveror +[2023-10-09 17:44:32.048] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:44:32.048] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:44:34-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1795.72 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.02, 0.44, 3.92 +------------------------------------------------------------------------------------------------------------------------------ +Benchmark Time CPU Iterations UserCounters... +------------------------------------------------------------------------------------------------------------------------------ +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):8/manual_time 6909 ns 716860622 ns 101169 bytes=256 bytes_per_second=35.338M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):8/manual_time 6918 ns 720743245 ns 101169 bytes=256 bytes_per_second=35.291M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):8/manual_time 6911 ns 718172915 ns 101169 bytes=256 bytes_per_second=35.3254M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):8/manual_time 6917 ns 721226792 ns 101169 bytes=256 bytes_per_second=35.2944M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):8/manual_time 6908 ns 717969308 ns 101169 bytes=256 bytes_per_second=35.3393M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):8/manual_time_mean 6913 ns 718994576 ns 5 bytes=256 bytes_per_second=35.3176M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):8/manual_time_median 6911 ns 718172915 ns 5 bytes=256 bytes_per_second=35.3254M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):8/manual_time_stddev 4.59 ns 1892135 ns 5 bytes=0 bytes_per_second=23.9927k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):8/manual_time_cv 0.07 % 0.26 % 5 bytes=0.00% bytes_per_second=0.07% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):9/manual_time 6885 ns 718548672 ns 101579 bytes=512 bytes_per_second=70.9174M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):9/manual_time 6891 ns 722046395 ns 101579 bytes=512 bytes_per_second=70.8584M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):9/manual_time 6874 ns 718727919 ns 101579 bytes=512 bytes_per_second=71.0369M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):9/manual_time 6878 ns 721844970 ns 101579 bytes=512 bytes_per_second=70.9914M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):9/manual_time 6888 ns 718989207 ns 101579 bytes=512 bytes_per_second=70.8836M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):9/manual_time_mean 6883 ns 720031432 ns 5 bytes=512 bytes_per_second=70.9375M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):9/manual_time_median 6885 ns 718989207 ns 5 bytes=512 bytes_per_second=70.9174M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):9/manual_time_stddev 7.25 ns 1755915 ns 5 bytes=0 bytes_per_second=76.5091k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):9/manual_time_cv 0.11 % 0.24 % 5 bytes=0.00% bytes_per_second=0.11% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):10/manual_time 6945 ns 718198610 ns 100939 bytes=1024 bytes_per_second=140.609M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):10/manual_time 6932 ns 720218198 ns 100939 bytes=1024 bytes_per_second=140.877M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):10/manual_time 6946 ns 717528283 ns 100939 bytes=1024 bytes_per_second=140.589M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):10/manual_time 6932 ns 721352372 ns 100939 bytes=1024 bytes_per_second=140.875M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):10/manual_time 6942 ns 718197112 ns 100939 bytes=1024 bytes_per_second=140.678M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):10/manual_time_mean 6939 ns 719098915 ns 5 bytes=1024 bytes_per_second=140.725M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):10/manual_time_median 6942 ns 718198610 ns 5 bytes=1024 bytes_per_second=140.678M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):10/manual_time_stddev 6.96 ns 1614121 ns 5 bytes=0 bytes_per_second=144.499k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):10/manual_time_cv 0.10 % 0.22 % 5 bytes=0.00% bytes_per_second=0.10% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):11/manual_time 7004 ns 713807434 ns 99950 bytes=2.048k bytes_per_second=278.87M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):11/manual_time 7007 ns 717137212 ns 99950 bytes=2.048k bytes_per_second=278.745M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):11/manual_time 7008 ns 712686222 ns 99950 bytes=2.048k bytes_per_second=278.716M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):11/manual_time 7008 ns 717144431 ns 99950 bytes=2.048k bytes_per_second=278.707M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):11/manual_time 7005 ns 713618991 ns 99950 bytes=2.048k bytes_per_second=278.833M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):11/manual_time_mean 7006 ns 714878858 ns 5 bytes=2.048k bytes_per_second=278.774M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):11/manual_time_median 7007 ns 713807434 ns 5 bytes=2.048k bytes_per_second=278.745M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):11/manual_time_stddev 1.84 ns 2108071 ns 5 bytes=0 bytes_per_second=74.7856k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):11/manual_time_cv 0.03 % 0.29 % 5 bytes=0.00% bytes_per_second=0.03% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):12/manual_time 7266 ns 701496019 ns 96223 bytes=4.096k bytes_per_second=537.637M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):12/manual_time 7270 ns 705793242 ns 96223 bytes=4.096k bytes_per_second=537.294M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):12/manual_time 7267 ns 701326688 ns 96223 bytes=4.096k bytes_per_second=537.537M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):12/manual_time 7272 ns 705593815 ns 96223 bytes=4.096k bytes_per_second=537.145M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):12/manual_time 7267 ns 701616934 ns 96223 bytes=4.096k bytes_per_second=537.535M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):12/manual_time_mean 7268 ns 703165340 ns 5 bytes=4.096k bytes_per_second=537.43M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):12/manual_time_median 7267 ns 701616934 ns 5 bytes=4.096k bytes_per_second=537.535M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):12/manual_time_stddev 2.75 ns 2311287 ns 5 bytes=0 bytes_per_second=207.965k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):12/manual_time_cv 0.04 % 0.33 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):13/manual_time 9119 ns 631221559 ns 76701 bytes=8.192k bytes_per_second=856.72M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):13/manual_time 9090 ns 632607760 ns 76701 bytes=8.192k bytes_per_second=859.459M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):13/manual_time 9128 ns 630949007 ns 76701 bytes=8.192k bytes_per_second=855.923M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):13/manual_time 9112 ns 634791760 ns 76701 bytes=8.192k bytes_per_second=857.387M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):13/manual_time 9116 ns 631001023 ns 76701 bytes=8.192k bytes_per_second=857.05M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):13/manual_time_mean 9113 ns 632114222 ns 5 bytes=8.192k bytes_per_second=857.308M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):13/manual_time_median 9116 ns 631221559 ns 5 bytes=8.192k bytes_per_second=857.05M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):13/manual_time_stddev 14.0 ns 1643668 ns 5 bytes=0 bytes_per_second=1.31947M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):13/manual_time_cv 0.15 % 0.26 % 5 bytes=0.00% bytes_per_second=0.15% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):14/manual_time 9803 ns 612320057 ns 71438 bytes=16.384k bytes_per_second=1.55648G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):14/manual_time 9804 ns 618673026 ns 71438 bytes=16.384k bytes_per_second=1.55638G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):14/manual_time 9800 ns 612332019 ns 71438 bytes=16.384k bytes_per_second=1.55704G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):14/manual_time 9804 ns 619920082 ns 71438 bytes=16.384k bytes_per_second=1.55631G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):14/manual_time 9802 ns 610981165 ns 71438 bytes=16.384k bytes_per_second=1.55667G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):14/manual_time_mean 9803 ns 614845270 ns 5 bytes=16.384k bytes_per_second=1.55657G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):14/manual_time_median 9803 ns 612332019 ns 5 bytes=16.384k bytes_per_second=1.55648G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):14/manual_time_stddev 1.86 ns 4124011 ns 5 bytes=0 bytes_per_second=309.254k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):14/manual_time_cv 0.02 % 0.67 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):15/manual_time 10701 ns 597349412 ns 65430 bytes=32.768k bytes_per_second=2.85192G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):15/manual_time 10702 ns 600649373 ns 65430 bytes=32.768k bytes_per_second=2.85154G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):15/manual_time 10702 ns 597117213 ns 65430 bytes=32.768k bytes_per_second=2.8517G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):15/manual_time 10697 ns 600286081 ns 65430 bytes=32.768k bytes_per_second=2.85282G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):15/manual_time 10697 ns 596525607 ns 65430 bytes=32.768k bytes_per_second=2.85289G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):15/manual_time_mean 10700 ns 598385537 ns 5 bytes=32.768k bytes_per_second=2.85217G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):15/manual_time_median 10701 ns 597349412 ns 5 bytes=32.768k bytes_per_second=2.85192G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):15/manual_time_stddev 2.39 ns 1928637 ns 5 bytes=0 bytes_per_second=667.142k/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):15/manual_time_cv 0.02 % 0.32 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):16/manual_time 12421 ns 571922336 ns 56332 bytes=65.536k bytes_per_second=4.91374G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):16/manual_time 12446 ns 574956691 ns 56332 bytes=65.536k bytes_per_second=4.90409G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):16/manual_time 12419 ns 570509189 ns 56332 bytes=65.536k bytes_per_second=4.91469G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):16/manual_time 12413 ns 573827991 ns 56332 bytes=65.536k bytes_per_second=4.9169G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):16/manual_time 12423 ns 572060572 ns 56332 bytes=65.536k bytes_per_second=4.91327G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):16/manual_time_mean 12424 ns 572655356 ns 5 bytes=65.536k bytes_per_second=4.91254G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):16/manual_time_median 12421 ns 572060572 ns 5 bytes=65.536k bytes_per_second=4.91374G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):16/manual_time_stddev 12.5 ns 1744157 ns 5 bytes=0 bytes_per_second=5.04596M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):16/manual_time_cv 0.10 % 0.30 % 5 bytes=0.00% bytes_per_second=0.10% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):17/manual_time 15462 ns 543254830 ns 45316 bytes=131.072k bytes_per_second=7.8951G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):17/manual_time 15467 ns 546790507 ns 45316 bytes=131.072k bytes_per_second=7.89225G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):17/manual_time 15462 ns 543528021 ns 45316 bytes=131.072k bytes_per_second=7.89473G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):17/manual_time 15453 ns 546192048 ns 45316 bytes=131.072k bytes_per_second=7.89948G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):17/manual_time 15468 ns 543202491 ns 45316 bytes=131.072k bytes_per_second=7.89165G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):17/manual_time_mean 15462 ns 544593580 ns 5 bytes=131.072k bytes_per_second=7.89464G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):17/manual_time_median 15462 ns 543528021 ns 5 bytes=131.072k bytes_per_second=7.89473G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):17/manual_time_stddev 6.06 ns 1749599 ns 5 bytes=0 bytes_per_second=3.16959M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):17/manual_time_cv 0.04 % 0.32 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):18/manual_time 19099 ns 545911375 ns 36669 bytes=262.144k bytes_per_second=12.7829G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):18/manual_time 19092 ns 547605792 ns 36669 bytes=262.144k bytes_per_second=12.7879G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):18/manual_time 19097 ns 545757553 ns 36669 bytes=262.144k bytes_per_second=12.7843G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):18/manual_time 19094 ns 547709075 ns 36669 bytes=262.144k bytes_per_second=12.7864G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):18/manual_time 19099 ns 545867250 ns 36669 bytes=262.144k bytes_per_second=12.7827G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):18/manual_time_mean 19096 ns 546570209 ns 5 bytes=262.144k bytes_per_second=12.7848G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):18/manual_time_median 19097 ns 545911375 ns 5 bytes=262.144k bytes_per_second=12.7843G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):18/manual_time_stddev 3.37 ns 994745 ns 5 bytes=0 bytes_per_second=2.31204M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):18/manual_time_cv 0.02 % 0.18 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):19/manual_time 30771 ns 535031873 ns 22742 bytes=524.288k bytes_per_second=15.868G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):19/manual_time 30776 ns 537718392 ns 22742 bytes=524.288k bytes_per_second=15.8655G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):19/manual_time 30774 ns 542112033 ns 22742 bytes=524.288k bytes_per_second=15.8665G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):19/manual_time 30779 ns 538447429 ns 22742 bytes=524.288k bytes_per_second=15.8643G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):19/manual_time 30774 ns 537175164 ns 22742 bytes=524.288k bytes_per_second=15.8668G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):19/manual_time_mean 30775 ns 538096978 ns 5 bytes=524.288k bytes_per_second=15.8662G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):19/manual_time_median 30774 ns 537718392 ns 5 bytes=524.288k bytes_per_second=15.8665G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):19/manual_time_stddev 2.71 ns 2580282 ns 5 bytes=0 bytes_per_second=1.42843M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):19/manual_time_cv 0.01 % 0.48 % 5 bytes=0.00% bytes_per_second=0.01% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):20/manual_time 52816 ns 526425947 ns 13274 bytes=1048.58k bytes_per_second=18.4899G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):20/manual_time 52841 ns 527012328 ns 13274 bytes=1048.58k bytes_per_second=18.4811G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):20/manual_time 52815 ns 526439439 ns 13274 bytes=1048.58k bytes_per_second=18.4901G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):20/manual_time 52849 ns 527305996 ns 13274 bytes=1048.58k bytes_per_second=18.4784G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):20/manual_time 52825 ns 527607124 ns 13274 bytes=1048.58k bytes_per_second=18.4868G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):20/manual_time_mean 52829 ns 526958167 ns 5 bytes=1048.58k bytes_per_second=18.4853G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):20/manual_time_median 52825 ns 527012328 ns 5 bytes=1048.58k bytes_per_second=18.4868G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):20/manual_time_stddev 15.0 ns 523784 ns 5 bytes=0 bytes_per_second=5.38953M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):20/manual_time_cv 0.03 % 0.10 % 5 bytes=0.00% bytes_per_second=0.03% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):21/manual_time 97084 ns 499878418 ns 7213 bytes=2.09715M bytes_per_second=20.1179G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):21/manual_time 97512 ns 501104988 ns 7213 bytes=2.09715M bytes_per_second=20.0296G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):21/manual_time 96897 ns 498242558 ns 7213 bytes=2.09715M bytes_per_second=20.1566G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):21/manual_time 96970 ns 499086723 ns 7213 bytes=2.09715M bytes_per_second=20.1416G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):21/manual_time 97557 ns 500674161 ns 7213 bytes=2.09715M bytes_per_second=20.0204G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):21/manual_time_mean 97204 ns 499797370 ns 5 bytes=2.09715M bytes_per_second=20.0932G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):21/manual_time_median 97084 ns 499878418 ns 5 bytes=2.09715M bytes_per_second=20.1179G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):21/manual_time_stddev 309 ns 1162718 ns 5 bytes=0 bytes_per_second=65.3857M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):21/manual_time_cv 0.32 % 0.23 % 5 bytes=0.00% bytes_per_second=0.32% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):22/manual_time 185018 ns 483210961 ns 3779 bytes=4.1943M bytes_per_second=21.1128G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):22/manual_time 185001 ns 483046701 ns 3779 bytes=4.1943M bytes_per_second=21.1148G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):22/manual_time 185065 ns 483398164 ns 3779 bytes=4.1943M bytes_per_second=21.1075G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):22/manual_time 185075 ns 483018782 ns 3779 bytes=4.1943M bytes_per_second=21.1063G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):22/manual_time 184990 ns 482945517 ns 3779 bytes=4.1943M bytes_per_second=21.116G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):22/manual_time_mean 185030 ns 483124025 ns 5 bytes=4.1943M bytes_per_second=21.1115G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):22/manual_time_median 185018 ns 483046701 ns 5 bytes=4.1943M bytes_per_second=21.1128G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):22/manual_time_stddev 38.2 ns 181404 ns 5 bytes=0 bytes_per_second=4.46075M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):22/manual_time_cv 0.02 % 0.04 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):23/manual_time 361983 ns 477298597 ns 1932 bytes=8.38861M bytes_per_second=21.5825G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):23/manual_time 361761 ns 476894662 ns 1932 bytes=8.38861M bytes_per_second=21.5958G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):23/manual_time 361726 ns 476660141 ns 1932 bytes=8.38861M bytes_per_second=21.5978G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):23/manual_time 362141 ns 477300886 ns 1932 bytes=8.38861M bytes_per_second=21.5731G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):23/manual_time 361465 ns 476611460 ns 1932 bytes=8.38861M bytes_per_second=21.6134G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):23/manual_time_mean 361815 ns 476953149 ns 5 bytes=8.38861M bytes_per_second=21.5925G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):23/manual_time_median 361761 ns 476894662 ns 5 bytes=8.38861M bytes_per_second=21.5958G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):23/manual_time_stddev 259 ns 334021 ns 5 bytes=0 bytes_per_second=15.8081M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):23/manual_time_cv 0.07 % 0.07 % 5 bytes=0.00% bytes_per_second=0.07% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):24/manual_time 714894 ns 474349966 ns 980 bytes=16.7772M bytes_per_second=21.8564G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):24/manual_time 714467 ns 474287790 ns 980 bytes=16.7772M bytes_per_second=21.8694G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):24/manual_time 714664 ns 474150313 ns 980 bytes=16.7772M bytes_per_second=21.8634G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):24/manual_time 714036 ns 474130787 ns 980 bytes=16.7772M bytes_per_second=21.8827G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):24/manual_time 714617 ns 474428569 ns 980 bytes=16.7772M bytes_per_second=21.8649G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):24/manual_time_mean 714535 ns 474269485 ns 5 bytes=16.7772M bytes_per_second=21.8674G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):24/manual_time_median 714617 ns 474287790 ns 5 bytes=16.7772M bytes_per_second=21.8649G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):24/manual_time_stddev 319 ns 128022 ns 5 bytes=0 bytes_per_second=9.98446M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):24/manual_time_cv 0.04 % 0.03 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):25/manual_time 9780085 ns 704379274 ns 71 bytes=33.5544M bytes_per_second=3.19527G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):25/manual_time 9779819 ns 702938122 ns 71 bytes=33.5544M bytes_per_second=3.19536G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):25/manual_time 9757784 ns 702163113 ns 71 bytes=33.5544M bytes_per_second=3.20257G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):25/manual_time 9765442 ns 702818549 ns 71 bytes=33.5544M bytes_per_second=3.20006G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):25/manual_time 9773776 ns 702059014 ns 71 bytes=33.5544M bytes_per_second=3.19733G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):25/manual_time_mean 9771381 ns 702871615 ns 5 bytes=33.5544M bytes_per_second=3.19812G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):25/manual_time_median 9773776 ns 702818549 ns 5 bytes=33.5544M bytes_per_second=3.19733G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):25/manual_time_stddev 9655 ns 927708 ns 5 bytes=0 bytes_per_second=3.237M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):25/manual_time_cv 0.10 % 0.13 % 5 bytes=0.00% bytes_per_second=0.10% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):26/manual_time 18907664 ns 733185136 ns 37 bytes=67.1089M bytes_per_second=3.30554G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):26/manual_time 18874163 ns 731478822 ns 37 bytes=67.1089M bytes_per_second=3.31141G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):26/manual_time 18921307 ns 733093254 ns 37 bytes=67.1089M bytes_per_second=3.30315G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):26/manual_time 18945960 ns 733338956 ns 37 bytes=67.1089M bytes_per_second=3.29886G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):26/manual_time 18880088 ns 732404068 ns 37 bytes=67.1089M bytes_per_second=3.31037G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):26/manual_time_mean 18905836 ns 732700047 ns 5 bytes=67.1089M bytes_per_second=3.30586G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):26/manual_time_median 18907664 ns 733093254 ns 5 bytes=67.1089M bytes_per_second=3.30554G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):26/manual_time_stddev 29660 ns 770896 ns 5 bytes=0 bytes_per_second=5.30919M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):26/manual_time_cv 0.16 % 0.11 % 5 bytes=0.00% bytes_per_second=0.16% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):27/manual_time 37375964 ns 788487798 ns 19 bytes=134.218M bytes_per_second=3.3444G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):27/manual_time 37407627 ns 788916101 ns 19 bytes=134.218M bytes_per_second=3.34156G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):27/manual_time 37297792 ns 787280073 ns 19 bytes=134.218M bytes_per_second=3.3514G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):27/manual_time 37320941 ns 787618845 ns 19 bytes=134.218M bytes_per_second=3.34933G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):27/manual_time 37243822 ns 787530969 ns 19 bytes=134.218M bytes_per_second=3.35626G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):27/manual_time_mean 37329229 ns 787966757 ns 5 bytes=134.218M bytes_per_second=3.34859G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):27/manual_time_median 37320941 ns 787618845 ns 5 bytes=134.218M bytes_per_second=3.34933G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):27/manual_time_stddev 64579 ns 699147 ns 5 bytes=0 bytes_per_second=5.93275M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):27/manual_time_cv 0.17 % 0.09 % 5 bytes=0.00% bytes_per_second=0.17% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):28/manual_time 74604366 ns 917854684 ns 10 bytes=268.435M bytes_per_second=3.35101G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):28/manual_time 74093629 ns 914926745 ns 10 bytes=268.435M bytes_per_second=3.37411G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):28/manual_time 74396271 ns 917309728 ns 10 bytes=268.435M bytes_per_second=3.36038G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):28/manual_time 74398461 ns 917597162 ns 10 bytes=268.435M bytes_per_second=3.36028G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):28/manual_time 74280925 ns 916492196 ns 10 bytes=268.435M bytes_per_second=3.3656G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):28/manual_time_mean 74354730 ns 916836103 ns 5 bytes=268.435M bytes_per_second=3.36228G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):28/manual_time_median 74396271 ns 917309728 ns 5 bytes=268.435M bytes_per_second=3.36038G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):28/manual_time_stddev 186800 ns 1183740 ns 5 bytes=0 bytes_per_second=8.65186M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):28/manual_time_cv 0.25 % 0.13 % 5 bytes=0.00% bytes_per_second=0.25% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):29/manual_time 146456972 ns 1101984542 ns 5 bytes=536.871M bytes_per_second=3.41397G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):29/manual_time 145151621 ns 1095701312 ns 5 bytes=536.871M bytes_per_second=3.44467G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):29/manual_time 146130952 ns 1099454899 ns 5 bytes=536.871M bytes_per_second=3.42159G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):29/manual_time 144530532 ns 1093614831 ns 5 bytes=536.871M bytes_per_second=3.45948G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):29/manual_time 145863047 ns 1095810796 ns 5 bytes=536.871M bytes_per_second=3.42787G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):29/manual_time_mean 145626625 ns 1097313276 ns 5 bytes=536.871M bytes_per_second=3.43352G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):29/manual_time_median 145863047 ns 1095810796 ns 5 bytes=536.871M bytes_per_second=3.42787G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):29/manual_time_stddev 778904 ns 3351927 ns 5 bytes=0 bytes_per_second=18.8436M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):29/manual_time_cv 0.53 % 0.31 % 5 bytes=0.00% bytes_per_second=0.54% hip_id=-nan% numa_id=-nan% +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):30/manual_time 285576195 ns 1317092522 ns 2 bytes=1073.74M bytes_per_second=3.50169G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):30/manual_time 284204200 ns 1314313590 ns 2 bytes=1073.74M bytes_per_second=3.5186G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):30/manual_time 285069689 ns 1316311725 ns 2 bytes=1073.74M bytes_per_second=3.50791G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):30/manual_time 283708513 ns 1313950037 ns 2 bytes=1073.74M bytes_per_second=3.52474G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):30/manual_time 286436200 ns 1320094576 ns 2 bytes=1073.74M bytes_per_second=3.49118G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):30/manual_time_mean 284998959 ns 1316352490 ns 5 bytes=1073.74M bytes_per_second=3.50883G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):30/manual_time_median 285069689 ns 1316311725 ns 5 bytes=1073.74M bytes_per_second=3.50791G/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):30/manual_time_stddev 1084062 ns 2473935 ns 5 bytes=0 bytes_per_second=13.6619M/s hip_id=0 numa_id=0 +Comm_hipMemcpyAsync_PageableToGPU/0/0/log2(N):30/manual_time_cv 0.38 % 0.19 % 5 bytes=0.00% bytes_per_second=0.38% hip_id=-nan% numa_id=-nan% +[2023-10-09 17:47:06.150] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 17:47:06.150] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Mon 09 Oct 2023 05:47:06 PM EDT diff --git a/results/r5-1465786.out b/results/r5-1465786.out new file mode 100644 index 0000000..f2267a1 --- /dev/null +++ b/results/r5-1465786.out @@ -0,0 +1,205 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 08:12:06 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 20:12:09.020] [scope] [info] recorded system CPU turbo state +[2023-10-09 20:12:09.021] [scope] [info] recorded CPU goveror +[2023-10-09 20:12:09.021] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 20:12:09.021] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T20:12:11-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1795.68 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.91, 7.45, 10.79 +--------------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +--------------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):12/manual_time 3016 ns 269728 ns 233544 bytes=4.096k bytes_per_second=1.26499G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):12/manual_time 2966 ns 270883 ns 233544 bytes=4.096k bytes_per_second=1.28596G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):12/manual_time 2981 ns 269693 ns 233544 bytes=4.096k bytes_per_second=1.27974G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):12/manual_time 2987 ns 270624 ns 233544 bytes=4.096k bytes_per_second=1.27727G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):12/manual_time 2983 ns 268939 ns 233544 bytes=4.096k bytes_per_second=1.27885G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):12/manual_time_mean 2986 ns 269973 ns 5 bytes=4.096k bytes_per_second=1.27736G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):12/manual_time_median 2983 ns 269728 ns 5 bytes=4.096k bytes_per_second=1.27885G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):12/manual_time_stddev 18.0 ns 784 ns 5 bytes=0 bytes_per_second=7.84637M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):12/manual_time_cv 0.60 % 0.29 % 5 bytes=0.00% bytes_per_second=0.60% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):13/manual_time 3067 ns 280318 ns 227769 bytes=8.192k bytes_per_second=2.48746G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):13/manual_time 3081 ns 280905 ns 227769 bytes=8.192k bytes_per_second=2.47597G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):13/manual_time 3040 ns 281396 ns 227769 bytes=8.192k bytes_per_second=2.50994G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):13/manual_time 3063 ns 282364 ns 227769 bytes=8.192k bytes_per_second=2.49123G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):13/manual_time 3058 ns 280979 ns 227769 bytes=8.192k bytes_per_second=2.49508G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):13/manual_time_mean 3062 ns 281193 ns 5 bytes=8.192k bytes_per_second=2.49194G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):13/manual_time_median 3063 ns 280979 ns 5 bytes=8.192k bytes_per_second=2.49123G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):13/manual_time_stddev 15.1 ns 759 ns 5 bytes=0 bytes_per_second=12.639M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):13/manual_time_cv 0.49 % 0.27 % 5 bytes=0.00% bytes_per_second=0.50% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):14/manual_time 3500 ns 305919 ns 199950 bytes=16.384k bytes_per_second=4.35947G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):14/manual_time 3498 ns 305739 ns 199950 bytes=16.384k bytes_per_second=4.36242G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):14/manual_time 3506 ns 305300 ns 199950 bytes=16.384k bytes_per_second=4.35192G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):14/manual_time 3498 ns 305128 ns 199950 bytes=16.384k bytes_per_second=4.36194G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):14/manual_time 3482 ns 305001 ns 199950 bytes=16.384k bytes_per_second=4.38156G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):14/manual_time_mean 3497 ns 305417 ns 5 bytes=16.384k bytes_per_second=4.36346G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):14/manual_time_median 3498 ns 305300 ns 5 bytes=16.384k bytes_per_second=4.36194G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):14/manual_time_stddev 8.76 ns 396 ns 5 bytes=0 bytes_per_second=11.2213M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):14/manual_time_cv 0.25 % 0.13 % 5 bytes=0.00% bytes_per_second=0.25% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):15/manual_time 4306 ns 352079 ns 161987 bytes=32.768k bytes_per_second=7.08712G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):15/manual_time 4348 ns 352247 ns 161987 bytes=32.768k bytes_per_second=7.01909G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):15/manual_time 4334 ns 351926 ns 161987 bytes=32.768k bytes_per_second=7.04178G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):15/manual_time 4335 ns 352437 ns 161987 bytes=32.768k bytes_per_second=7.03933G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):15/manual_time 4311 ns 352361 ns 161987 bytes=32.768k bytes_per_second=7.0784G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):15/manual_time_mean 4327 ns 352210 ns 5 bytes=32.768k bytes_per_second=7.05314G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):15/manual_time_median 4334 ns 352247 ns 5 bytes=32.768k bytes_per_second=7.04178G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):15/manual_time_stddev 17.5 ns 208 ns 5 bytes=0 bytes_per_second=29.2871M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):15/manual_time_cv 0.41 % 0.06 % 5 bytes=0.00% bytes_per_second=0.41% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):16/manual_time 5345 ns 440822 ns 130995 bytes=65.536k bytes_per_second=11.4198G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):16/manual_time 5348 ns 440375 ns 130995 bytes=65.536k bytes_per_second=11.4121G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):16/manual_time 5352 ns 440549 ns 130995 bytes=65.536k bytes_per_second=11.4033G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):16/manual_time 5343 ns 441081 ns 130995 bytes=65.536k bytes_per_second=11.4238G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):16/manual_time 5346 ns 441041 ns 130995 bytes=65.536k bytes_per_second=11.4161G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):16/manual_time_mean 5347 ns 440774 ns 5 bytes=65.536k bytes_per_second=11.415G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):16/manual_time_median 5346 ns 440822 ns 5 bytes=65.536k bytes_per_second=11.4161G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):16/manual_time_stddev 3.69 ns 307 ns 5 bytes=0 bytes_per_second=8.05354M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):16/manual_time_cv 0.07 % 0.07 % 5 bytes=0.00% bytes_per_second=0.07% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):17/manual_time 7329 ns 622063 ns 94802 bytes=131.072k bytes_per_second=16.6566G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):17/manual_time 7300 ns 621012 ns 94802 bytes=131.072k bytes_per_second=16.7228G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):17/manual_time 7390 ns 620054 ns 94802 bytes=131.072k bytes_per_second=16.5193G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):17/manual_time 7328 ns 620951 ns 94802 bytes=131.072k bytes_per_second=16.6571G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):17/manual_time 7328 ns 620685 ns 94802 bytes=131.072k bytes_per_second=16.6581G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):17/manual_time_mean 7335 ns 620953 ns 5 bytes=131.072k bytes_per_second=16.6428G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):17/manual_time_median 7328 ns 620951 ns 5 bytes=131.072k bytes_per_second=16.6571G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):17/manual_time_stddev 33.0 ns 727 ns 5 bytes=0 bytes_per_second=76.421M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):17/manual_time_cv 0.45 % 0.12 % 5 bytes=0.00% bytes_per_second=0.45% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):18/manual_time 12068 ns 975908 ns 58081 bytes=262.144k bytes_per_second=20.2299G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):18/manual_time 12051 ns 976102 ns 58081 bytes=262.144k bytes_per_second=20.2589G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):18/manual_time 12054 ns 976893 ns 58081 bytes=262.144k bytes_per_second=20.2542G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):18/manual_time 12111 ns 976223 ns 58081 bytes=262.144k bytes_per_second=20.158G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):18/manual_time 12095 ns 975846 ns 58081 bytes=262.144k bytes_per_second=20.1851G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):18/manual_time_mean 12076 ns 976194 ns 5 bytes=262.144k bytes_per_second=20.2172G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):18/manual_time_median 12068 ns 976102 ns 5 bytes=262.144k bytes_per_second=20.2299G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):18/manual_time_stddev 26.4 ns 419 ns 5 bytes=0 bytes_per_second=45.2145M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):18/manual_time_cv 0.22 % 0.04 % 5 bytes=0.00% bytes_per_second=0.22% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):19/manual_time 20139 ns 1692873 ns 34655 bytes=524.288k bytes_per_second=24.2451G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):19/manual_time 20149 ns 1689509 ns 34655 bytes=524.288k bytes_per_second=24.2339G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):19/manual_time 20186 ns 1691135 ns 34655 bytes=524.288k bytes_per_second=24.1886G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):19/manual_time 20169 ns 1854165 ns 34655 bytes=524.288k bytes_per_second=24.2097G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):19/manual_time 20073 ns 1691847 ns 34655 bytes=524.288k bytes_per_second=24.3253G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):19/manual_time_mean 20143 ns 1723906 ns 5 bytes=524.288k bytes_per_second=24.2405G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):19/manual_time_median 20149 ns 1691847 ns 5 bytes=524.288k bytes_per_second=24.2339G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):19/manual_time_stddev 43.3 ns 72828 ns 5 bytes=0 bytes_per_second=53.4234M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):19/manual_time_cv 0.21 % 4.22 % 5 bytes=0.00% bytes_per_second=0.22% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):20/manual_time 35785 ns 3132003 ns 19553 bytes=1048.58k bytes_per_second=27.2897G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):20/manual_time 35765 ns 3170002 ns 19553 bytes=1048.58k bytes_per_second=27.3047G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):20/manual_time 35684 ns 3145125 ns 19553 bytes=1048.58k bytes_per_second=27.3668G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):20/manual_time 35685 ns 3191220 ns 19553 bytes=1048.58k bytes_per_second=27.3665G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):20/manual_time 35687 ns 3138235 ns 19553 bytes=1048.58k bytes_per_second=27.3647G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):20/manual_time_mean 35721 ns 3155317 ns 5 bytes=1048.58k bytes_per_second=27.3385G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):20/manual_time_median 35687 ns 3145125 ns 5 bytes=1048.58k bytes_per_second=27.3647G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):20/manual_time_stddev 49.8 ns 24718 ns 5 bytes=0 bytes_per_second=38.9931M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):20/manual_time_cv 0.14 % 0.78 % 5 bytes=0.00% bytes_per_second=0.14% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):21/manual_time 67095 ns 6300374 ns 10473 bytes=2.09715M bytes_per_second=29.1098G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):21/manual_time 67100 ns 6329109 ns 10473 bytes=2.09715M bytes_per_second=29.1076G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):21/manual_time 67299 ns 6052741 ns 10473 bytes=2.09715M bytes_per_second=29.0214G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):21/manual_time 67279 ns 6027409 ns 10473 bytes=2.09715M bytes_per_second=29.0303G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):21/manual_time 67238 ns 6154337 ns 10473 bytes=2.09715M bytes_per_second=29.0479G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):21/manual_time_mean 67202 ns 6172794 ns 5 bytes=2.09715M bytes_per_second=29.0634G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):21/manual_time_median 67238 ns 6154337 ns 5 bytes=2.09715M bytes_per_second=29.0479G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):21/manual_time_stddev 98.1 ns 138384 ns 5 bytes=0 bytes_per_second=43.4775M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):21/manual_time_cv 0.15 % 2.24 % 5 bytes=0.00% bytes_per_second=0.15% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):22/manual_time 129194 ns 12399681 ns 5414 bytes=4.1943M bytes_per_second=30.2356G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):22/manual_time 129198 ns 12335255 ns 5414 bytes=4.1943M bytes_per_second=30.2347G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):22/manual_time 129168 ns 12279013 ns 5414 bytes=4.1943M bytes_per_second=30.2417G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):22/manual_time 129235 ns 12278607 ns 5414 bytes=4.1943M bytes_per_second=30.2258G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):22/manual_time 129125 ns 12277392 ns 5414 bytes=4.1943M bytes_per_second=30.2516G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):22/manual_time_mean 129184 ns 12313990 ns 5 bytes=4.1943M bytes_per_second=30.2379G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):22/manual_time_median 129194 ns 12279013 ns 5 bytes=4.1943M bytes_per_second=30.2356G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):22/manual_time_stddev 40.8 ns 53875 ns 5 bytes=0 bytes_per_second=9.78229M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):22/manual_time_cv 0.03 % 0.44 % 5 bytes=0.00% bytes_per_second=0.03% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):23/manual_time 253974 ns 24478736 ns 2749 bytes=8.38861M bytes_per_second=30.761G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):23/manual_time 253650 ns 24125953 ns 2749 bytes=8.38861M bytes_per_second=30.8003G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):23/manual_time 253572 ns 24432672 ns 2749 bytes=8.38861M bytes_per_second=30.8098G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):23/manual_time 253509 ns 24321586 ns 2749 bytes=8.38861M bytes_per_second=30.8174G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):23/manual_time 253525 ns 24168985 ns 2749 bytes=8.38861M bytes_per_second=30.8155G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):23/manual_time_mean 253646 ns 24305586 ns 5 bytes=8.38861M bytes_per_second=30.8008G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):23/manual_time_median 253572 ns 24321586 ns 5 bytes=8.38861M bytes_per_second=30.8098G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):23/manual_time_stddev 191 ns 155977 ns 5 bytes=0 bytes_per_second=23.7761M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):23/manual_time_cv 0.08 % 0.64 % 5 bytes=0.00% bytes_per_second=0.08% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):24/manual_time 510336 ns 47252602 ns 1264 bytes=16.7772M bytes_per_second=30.6171G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):24/manual_time 521937 ns 47662219 ns 1264 bytes=16.7772M bytes_per_second=29.9366G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):24/manual_time 507653 ns 48209250 ns 1264 bytes=16.7772M bytes_per_second=30.7789G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):24/manual_time 514069 ns 48777460 ns 1264 bytes=16.7772M bytes_per_second=30.3947G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):24/manual_time 717061 ns 47884164 ns 1264 bytes=16.7772M bytes_per_second=21.7903G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):24/manual_time_mean 554211 ns 47957139 ns 5 bytes=16.7772M bytes_per_second=28.7035G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):24/manual_time_median 514069 ns 47884164 ns 5 bytes=16.7772M bytes_per_second=30.3947G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):24/manual_time_stddev 91195 ns 575578 ns 5 bytes=0 bytes_per_second=3.87756G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):24/manual_time_cv 16.45 % 1.20 % 5 bytes=0.00% bytes_per_second=13.51% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):25/manual_time 1151491 ns 94004741 ns 593 bytes=33.5544M bytes_per_second=27.1387G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):25/manual_time 1157849 ns 94034433 ns 593 bytes=33.5544M bytes_per_second=26.9897G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):25/manual_time 1203965 ns 94025400 ns 593 bytes=33.5544M bytes_per_second=25.9559G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):25/manual_time 1901943 ns 94730253 ns 593 bytes=33.5544M bytes_per_second=16.4306G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):25/manual_time 1135259 ns 93864301 ns 593 bytes=33.5544M bytes_per_second=27.5268G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):25/manual_time_mean 1310101 ns 94131826 ns 5 bytes=33.5544M bytes_per_second=24.8083G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):25/manual_time_median 1157849 ns 94025400 ns 5 bytes=33.5544M bytes_per_second=26.9897G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):25/manual_time_stddev 331832 ns 341558 ns 5 bytes=0 bytes_per_second=4.71919G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):25/manual_time_cv 25.33 % 0.36 % 5 bytes=0.00% bytes_per_second=19.02% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):26/manual_time 1550482 ns 188731903 ns 445 bytes=67.1089M bytes_per_second=40.31G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):26/manual_time 1719807 ns 185658476 ns 445 bytes=67.1089M bytes_per_second=36.3413G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):26/manual_time 1564187 ns 188459611 ns 445 bytes=67.1089M bytes_per_second=39.9569G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):26/manual_time 1563356 ns 188618228 ns 445 bytes=67.1089M bytes_per_second=39.9781G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):26/manual_time 1573786 ns 187419078 ns 445 bytes=67.1089M bytes_per_second=39.7132G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):26/manual_time_mean 1594324 ns 187777459 ns 5 bytes=67.1089M bytes_per_second=39.2599G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):26/manual_time_median 1564187 ns 188459611 ns 5 bytes=67.1089M bytes_per_second=39.9569G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):26/manual_time_stddev 70635 ns 1294383 ns 5 bytes=0 bytes_per_second=1.64531G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):26/manual_time_cv 4.43 % 0.69 % 5 bytes=0.00% bytes_per_second=4.19% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):27/manual_time 3336512 ns 385712355 ns 210 bytes=134.218M bytes_per_second=37.4643G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):27/manual_time 3369159 ns 375731436 ns 210 bytes=134.218M bytes_per_second=37.1012G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):27/manual_time 3397897 ns 402907105 ns 210 bytes=134.218M bytes_per_second=36.7875G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):27/manual_time 3461002 ns 391210187 ns 210 bytes=134.218M bytes_per_second=36.1167G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):27/manual_time 3461512 ns 378534318 ns 210 bytes=134.218M bytes_per_second=36.1114G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):27/manual_time_mean 3405216 ns 386819080 ns 5 bytes=134.218M bytes_per_second=36.7162G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):27/manual_time_median 3397897 ns 385712355 ns 5 bytes=134.218M bytes_per_second=36.7875G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):27/manual_time_stddev 55577 ns 10850165 ns 5 bytes=0 bytes_per_second=614.003M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):27/manual_time_cv 1.63 % 2.80 % 5 bytes=0.00% bytes_per_second=1.63% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):28/manual_time 9327202 ns 849555347 ns 69 bytes=268.435M bytes_per_second=26.8033G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):28/manual_time 9284196 ns 713209645 ns 69 bytes=268.435M bytes_per_second=26.9275G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):28/manual_time 9285830 ns 741670062 ns 69 bytes=268.435M bytes_per_second=26.9227G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):28/manual_time 9308141 ns 715843443 ns 69 bytes=268.435M bytes_per_second=26.8582G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):28/manual_time 9238281 ns 749150164 ns 69 bytes=268.435M bytes_per_second=27.0613G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):28/manual_time_mean 9288730 ns 753885732 ns 5 bytes=268.435M bytes_per_second=26.9146G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):28/manual_time_median 9285830 ns 741670062 ns 5 bytes=268.435M bytes_per_second=26.9227G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):28/manual_time_stddev 33283 ns 55736172 ns 5 bytes=0 bytes_per_second=98.9094M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):28/manual_time_cv 0.36 % 7.39 % 5 bytes=0.00% bytes_per_second=0.36% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):29/manual_time 22830803 ns 1655937687 ns 30 bytes=536.871M bytes_per_second=21.9002G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):29/manual_time 22982635 ns 1381108594 ns 30 bytes=536.871M bytes_per_second=21.7556G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):29/manual_time 22703545 ns 1504441189 ns 30 bytes=536.871M bytes_per_second=22.023G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):29/manual_time 22831941 ns 1504764820 ns 30 bytes=536.871M bytes_per_second=21.8991G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):29/manual_time 22634808 ns 1505525483 ns 30 bytes=536.871M bytes_per_second=22.0899G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):29/manual_time_mean 22796746 ns 1510355554 ns 5 bytes=536.871M bytes_per_second=21.9336G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):29/manual_time_median 22830803 ns 1504764820 ns 5 bytes=536.871M bytes_per_second=21.9002G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):29/manual_time_stddev 134037 ns 97453193 ns 5 bytes=0 bytes_per_second=131.945M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):29/manual_time_cv 0.59 % 6.45 % 5 bytes=0.00% bytes_per_second=0.59% dst_numa=-nan% src_gpu=-nan% +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):30/manual_time 50348479 ns 2677031832 ns 13 bytes=1073.74M bytes_per_second=19.8616G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):30/manual_time 50364641 ns 3260842060 ns 13 bytes=1073.74M bytes_per_second=19.8552G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):30/manual_time 50375775 ns 3262408229 ns 13 bytes=1073.74M bytes_per_second=19.8508G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):30/manual_time 50059383 ns 3263541037 ns 13 bytes=1073.74M bytes_per_second=19.9763G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):30/manual_time 50126751 ns 3264115042 ns 13 bytes=1073.74M bytes_per_second=19.9494G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):30/manual_time_mean 50255006 ns 3145587640 ns 5 bytes=1073.74M bytes_per_second=19.8987G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):30/manual_time_median 50348479 ns 3262408229 ns 5 bytes=1073.74M bytes_per_second=19.8616G/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):30/manual_time_stddev 150050 ns 261933639 ns 5 bytes=0 bytes_per_second=60.9155M/s dst_numa=0 src_gpu=0 +Comm_implicit_managed_HostWrGPU_fine/0/0/log2(N):30/manual_time_cv 0.30 % 8.33 % 5 bytes=0.00% bytes_per_second=0.30% dst_numa=-nan% src_gpu=-nan% +[2023-10-09 22:00:36.165] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 22:00:36.165] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Mon 09 Oct 2023 10:00:36 PM EDT diff --git a/results/r6-1465533.out b/results/r6-1465533.out new file mode 100644 index 0000000..1a74c37 --- /dev/null +++ b/results/r6-1465533.out @@ -0,0 +1,1546 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 05:44:30 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:44:32.023] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:44:32.024] [scope] [info] recorded CPU goveror +[2023-10-09 17:44:32.024] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:44:32.024] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:44:34-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1795.77 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.10, 3.44, 18.39 +--------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +--------------------------------------------------------------------------------------------------------------------------- +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time 8895 ns 21083 ns 78707 bytes=1024 bytes_per_second=109.792M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time 8940 ns 21139 ns 78707 bytes=1024 bytes_per_second=109.236M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time 8882 ns 21130 ns 78707 bytes=1024 bytes_per_second=109.946M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time 8820 ns 20986 ns 78707 bytes=1024 bytes_per_second=110.725M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time 8847 ns 21025 ns 78707 bytes=1024 bytes_per_second=110.379M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time_mean 8877 ns 21073 ns 5 bytes=1024 bytes_per_second=110.016M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time_median 8882 ns 21083 ns 5 bytes=1024 bytes_per_second=109.946M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time_stddev 46.0 ns 66.3 ns 5 bytes=0 bytes_per_second=583.197k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time_cv 0.52 % 0.31 % 5 bytes=0.00% bytes_per_second=0.52% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time 8963 ns 21176 ns 78589 bytes=2.048k bytes_per_second=217.899M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time 8973 ns 21190 ns 78589 bytes=2.048k bytes_per_second=217.676M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time 8902 ns 21125 ns 78589 bytes=2.048k bytes_per_second=219.408M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time 8736 ns 20905 ns 78589 bytes=2.048k bytes_per_second=223.57M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time 8752 ns 20948 ns 78589 bytes=2.048k bytes_per_second=223.154M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time_mean 8865 ns 21069 ns 5 bytes=2.048k bytes_per_second=220.341M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time_median 8902 ns 21125 ns 5 bytes=2.048k bytes_per_second=219.408M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time_stddev 114 ns 133 ns 5 bytes=0 bytes_per_second=2.84057M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time_cv 1.29 % 0.63 % 5 bytes=0.00% bytes_per_second=1.29% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time 9176 ns 21679 ns 76563 bytes=4.096k bytes_per_second=425.712M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time 9175 ns 21661 ns 76563 bytes=4.096k bytes_per_second=425.751M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time 8887 ns 21144 ns 76563 bytes=4.096k bytes_per_second=439.529M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time 8806 ns 20943 ns 76563 bytes=4.096k bytes_per_second=443.595M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time 8782 ns 20900 ns 76563 bytes=4.096k bytes_per_second=444.804M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time_mean 8965 ns 21265 ns 5 bytes=4.096k bytes_per_second=435.878M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time_median 8887 ns 21144 ns 5 bytes=4.096k bytes_per_second=439.529M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time_stddev 196 ns 381 ns 5 bytes=0 bytes_per_second=9.4666M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time_cv 2.18 % 1.79 % 5 bytes=0.00% bytes_per_second=2.17% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time 9358 ns 21750 ns 74859 bytes=8.192k bytes_per_second=834.815M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time 9335 ns 21734 ns 74859 bytes=8.192k bytes_per_second=836.911M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time 9072 ns 21467 ns 74859 bytes=8.192k bytes_per_second=861.132M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time 8896 ns 21172 ns 74859 bytes=8.192k bytes_per_second=878.229M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time 8887 ns 21153 ns 74859 bytes=8.192k bytes_per_second=879.113M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time_mean 9110 ns 21455 ns 5 bytes=8.192k bytes_per_second=858.04M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time_median 9072 ns 21467 ns 5 bytes=8.192k bytes_per_second=861.132M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time_stddev 229 ns 290 ns 5 bytes=0 bytes_per_second=21.4886M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time_cv 2.51 % 1.35 % 5 bytes=0.00% bytes_per_second=2.50% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time 9323 ns 21726 ns 74783 bytes=16.384k bytes_per_second=1.63663G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time 9264 ns 21670 ns 74783 bytes=16.384k bytes_per_second=1.64716G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time 8940 ns 21253 ns 74783 bytes=16.384k bytes_per_second=1.70687G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time 8886 ns 21107 ns 74783 bytes=16.384k bytes_per_second=1.71726G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time 8892 ns 21165 ns 74783 bytes=16.384k bytes_per_second=1.71595G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time_mean 9061 ns 21384 ns 5 bytes=16.384k bytes_per_second=1.68477G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time_median 8940 ns 21253 ns 5 bytes=16.384k bytes_per_second=1.70687G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time_stddev 214 ns 292 ns 5 bytes=0 bytes_per_second=40.4738M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time_cv 2.37 % 1.37 % 5 bytes=0.00% bytes_per_second=2.35% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time 9427 ns 21865 ns 74615 bytes=32.768k bytes_per_second=3.23735G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time 9326 ns 21723 ns 74615 bytes=32.768k bytes_per_second=3.27214G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time 9025 ns 21330 ns 74615 bytes=32.768k bytes_per_second=3.38162G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time 8950 ns 21232 ns 74615 bytes=32.768k bytes_per_second=3.40985G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time 8923 ns 21202 ns 74615 bytes=32.768k bytes_per_second=3.42003G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time_mean 9130 ns 21470 ns 5 bytes=32.768k bytes_per_second=3.3442G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time_median 9025 ns 21330 ns 5 bytes=32.768k bytes_per_second=3.38162G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time_stddev 231 ns 303 ns 5 bytes=0 bytes_per_second=85.7804M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time_cv 2.53 % 1.41 % 5 bytes=0.00% bytes_per_second=2.50% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time 9343 ns 21732 ns 74526 bytes=65.536k bytes_per_second=6.53289G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time 9352 ns 21790 ns 74526 bytes=65.536k bytes_per_second=6.52617G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time 9084 ns 21514 ns 74526 bytes=65.536k bytes_per_second=6.71877G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time 9022 ns 21311 ns 74526 bytes=65.536k bytes_per_second=6.76548G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time 8930 ns 21206 ns 74526 bytes=65.536k bytes_per_second=6.83508G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time_mean 9146 ns 21511 ns 5 bytes=65.536k bytes_per_second=6.67568G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time_median 9084 ns 21514 ns 5 bytes=65.536k bytes_per_second=6.71877G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time_stddev 192 ns 255 ns 5 bytes=0 bytes_per_second=143.059M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time_cv 2.10 % 1.18 % 5 bytes=0.00% bytes_per_second=2.09% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time 9352 ns 21765 ns 74998 bytes=131.072k bytes_per_second=13.0527G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time 9322 ns 21734 ns 74998 bytes=131.072k bytes_per_second=13.0949G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time 8987 ns 21310 ns 74998 bytes=131.072k bytes_per_second=13.5833G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time 8871 ns 21135 ns 74998 bytes=131.072k bytes_per_second=13.7606G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time 8892 ns 21167 ns 74998 bytes=131.072k bytes_per_second=13.7277G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time_mean 9085 ns 21422 ns 5 bytes=131.072k bytes_per_second=13.4439G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time_median 8987 ns 21310 ns 5 bytes=131.072k bytes_per_second=13.5833G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time_stddev 235 ns 306 ns 5 bytes=0 bytes_per_second=352.881M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time_cv 2.58 % 1.43 % 5 bytes=0.00% bytes_per_second=2.56% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time 9142 ns 21638 ns 76516 bytes=262.144k bytes_per_second=26.7051G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time 9200 ns 21716 ns 76516 bytes=262.144k bytes_per_second=26.5377G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time 9098 ns 21654 ns 76516 bytes=262.144k bytes_per_second=26.8354G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time 8918 ns 21233 ns 76516 bytes=262.144k bytes_per_second=27.3761G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time 8870 ns 21209 ns 76516 bytes=262.144k bytes_per_second=27.5231G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time_mean 9046 ns 21490 ns 5 bytes=262.144k bytes_per_second=26.9955G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time_median 9098 ns 21638 ns 5 bytes=262.144k bytes_per_second=26.8354G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time_stddev 144 ns 247 ns 5 bytes=0 bytes_per_second=441.276M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time_cv 1.59 % 1.15 % 5 bytes=0.00% bytes_per_second=1.60% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time 9417 ns 21845 ns 74850 bytes=524.288k bytes_per_second=51.8527G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time 9396 ns 21795 ns 74850 bytes=524.288k bytes_per_second=51.9647G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time 9088 ns 21534 ns 74850 bytes=524.288k bytes_per_second=53.7262G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time 8965 ns 21238 ns 74850 bytes=524.288k bytes_per_second=54.4667G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time 8894 ns 21160 ns 74850 bytes=524.288k bytes_per_second=54.9025G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time_mean 9152 ns 21514 ns 5 bytes=524.288k bytes_per_second=53.3826G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time_median 9088 ns 21534 ns 5 bytes=524.288k bytes_per_second=53.7262G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time_stddev 243 ns 312 ns 5 bytes=0 bytes_per_second=1.4102G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time_cv 2.65 % 1.45 % 5 bytes=0.00% bytes_per_second=2.64% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time 9360 ns 21865 ns 75358 bytes=1048.58k bytes_per_second=104.328G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time 9311 ns 21823 ns 75358 bytes=1048.58k bytes_per_second=104.887G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time 9099 ns 21615 ns 75358 bytes=1048.58k bytes_per_second=107.326G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time 8892 ns 21143 ns 75358 bytes=1048.58k bytes_per_second=109.824G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time 8878 ns 21172 ns 75358 bytes=1048.58k bytes_per_second=110G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time_mean 9108 ns 21524 ns 5 bytes=1048.58k bytes_per_second=107.273G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time_median 9099 ns 21615 ns 5 bytes=1048.58k bytes_per_second=107.326G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time_stddev 226 ns 348 ns 5 bytes=0 bytes_per_second=2.66048G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time_cv 2.48 % 1.61 % 5 bytes=0.00% bytes_per_second=2.48% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time 9136 ns 21559 ns 76558 bytes=2.09715M bytes_per_second=213.789G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time 9144 ns 21550 ns 76558 bytes=2.09715M bytes_per_second=213.599G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time 8990 ns 21395 ns 76558 bytes=2.09715M bytes_per_second=217.26G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time 8971 ns 21277 ns 76558 bytes=2.09715M bytes_per_second=217.717G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time 8971 ns 21278 ns 76558 bytes=2.09715M bytes_per_second=217.718G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time_mean 9042 ns 21412 ns 5 bytes=2.09715M bytes_per_second=216.017G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time_median 8990 ns 21395 ns 5 bytes=2.09715M bytes_per_second=217.26G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time_stddev 89.5 ns 139 ns 5 bytes=0 bytes_per_second=2.12966G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time_cv 0.99 % 0.65 % 5 bytes=0.00% bytes_per_second=0.99% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time 9248 ns 21676 ns 75798 bytes=4.1943M bytes_per_second=422.396G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time 9197 ns 21629 ns 75798 bytes=4.1943M bytes_per_second=424.712G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time 9220 ns 21638 ns 75798 bytes=4.1943M bytes_per_second=423.69G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time 8992 ns 21361 ns 75798 bytes=4.1943M bytes_per_second=434.432G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time 8981 ns 21295 ns 75798 bytes=4.1943M bytes_per_second=434.938G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time_mean 9128 ns 21520 ns 5 bytes=4.1943M bytes_per_second=428.033G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time_median 9197 ns 21629 ns 5 bytes=4.1943M bytes_per_second=424.712G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time_stddev 130 ns 178 ns 5 bytes=0 bytes_per_second=6.1296G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time_cv 1.43 % 0.83 % 5 bytes=0.00% bytes_per_second=1.43% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time 9225 ns 21646 ns 75935 bytes=8.38861M bytes_per_second=846.86G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time 9198 ns 21639 ns 75935 bytes=8.38861M bytes_per_second=849.402G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time 9150 ns 21535 ns 75935 bytes=8.38861M bytes_per_second=853.85G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time 8869 ns 21260 ns 75935 bytes=8.38861M bytes_per_second=880.882G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time 8901 ns 21294 ns 75935 bytes=8.38861M bytes_per_second=877.729G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time_mean 9068 ns 21475 ns 5 bytes=8.38861M bytes_per_second=861.745G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time_median 9150 ns 21535 ns 5 bytes=8.38861M bytes_per_second=853.85G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time_stddev 170 ns 186 ns 5 bytes=0 bytes_per_second=16.2631G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time_cv 1.88 % 0.87 % 5 bytes=0.00% bytes_per_second=1.89% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time 9183 ns 21612 ns 76383 bytes=16.7772M bytes_per_second=1.66159T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time 9183 ns 21636 ns 76383 bytes=16.7772M bytes_per_second=1.66168T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time 8952 ns 21379 ns 76383 bytes=16.7772M bytes_per_second=1.70459T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time 8885 ns 21190 ns 76383 bytes=16.7772M bytes_per_second=1.71734T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time 8898 ns 21221 ns 76383 bytes=16.7772M bytes_per_second=1.71487T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time_mean 9020 ns 21408 ns 5 bytes=16.7772M bytes_per_second=1.69201T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time_median 8952 ns 21379 ns 5 bytes=16.7772M bytes_per_second=1.70459T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time_stddev 151 ns 210 ns 5 bytes=0 bytes_per_second=28.8162G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time_cv 1.67 % 0.98 % 5 bytes=0.00% bytes_per_second=1.66% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time 9049 ns 21471 ns 77408 bytes=33.5544M bytes_per_second=3.37263T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time 9066 ns 21507 ns 77408 bytes=33.5544M bytes_per_second=3.36598T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time 8963 ns 21461 ns 77408 bytes=33.5544M bytes_per_second=3.40492T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time 8916 ns 21371 ns 77408 bytes=33.5544M bytes_per_second=3.42267T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time 8873 ns 21337 ns 77408 bytes=33.5544M bytes_per_second=3.43926T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time_mean 8973 ns 21430 ns 5 bytes=33.5544M bytes_per_second=3.40109T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time_median 8963 ns 21461 ns 5 bytes=33.5544M bytes_per_second=3.40492T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time_stddev 83.2 ns 72.1 ns 5 bytes=0 bytes_per_second=32.2969G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time_cv 0.93 % 0.34 % 5 bytes=0.00% bytes_per_second=0.93% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time 9104 ns 21643 ns 77276 bytes=67.1089M bytes_per_second=6.70445T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time 9152 ns 21713 ns 77276 bytes=67.1089M bytes_per_second=6.66891T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time 9071 ns 21586 ns 77276 bytes=67.1089M bytes_per_second=6.72825T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time 8884 ns 21443 ns 77276 bytes=67.1089M bytes_per_second=6.87006T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time 8830 ns 21358 ns 77276 bytes=67.1089M bytes_per_second=6.91204T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time_mean 9008 ns 21549 ns 5 bytes=67.1089M bytes_per_second=6.77674T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time_median 9071 ns 21586 ns 5 bytes=67.1089M bytes_per_second=6.72825T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time_stddev 142 ns 146 ns 5 bytes=0 bytes_per_second=110.074G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time_cv 1.58 % 0.68 % 5 bytes=0.00% bytes_per_second=1.59% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time 9115 ns 21733 ns 76837 bytes=134.218M bytes_per_second=13.3929T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time 9121 ns 21792 ns 76837 bytes=134.218M bytes_per_second=13.3832T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time 8965 ns 21552 ns 76837 bytes=134.218M bytes_per_second=13.6164T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time 8878 ns 21450 ns 76837 bytes=134.218M bytes_per_second=13.75T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time 8826 ns 21364 ns 76837 bytes=134.218M bytes_per_second=13.8304T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time_mean 8981 ns 21578 ns 5 bytes=134.218M bytes_per_second=13.5946T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time_median 8965 ns 21552 ns 5 bytes=134.218M bytes_per_second=13.6164T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time_stddev 134 ns 182 ns 5 bytes=0 bytes_per_second=208.378G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time_cv 1.50 % 0.84 % 5 bytes=0.00% bytes_per_second=1.50% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time 9235 ns 22190 ns 76033 bytes=268.435M bytes_per_second=26.4359T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time 9127 ns 22078 ns 76033 bytes=268.435M bytes_per_second=26.7481T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time 8984 ns 21916 ns 76033 bytes=268.435M bytes_per_second=27.1744T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time 8893 ns 21733 ns 76033 bytes=268.435M bytes_per_second=27.4534T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time 8952 ns 21860 ns 76033 bytes=268.435M bytes_per_second=27.2728T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time_mean 9038 ns 21956 ns 5 bytes=268.435M bytes_per_second=27.0169T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time_median 8984 ns 21916 ns 5 bytes=268.435M bytes_per_second=27.1744T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time_stddev 140 ns 180 ns 5 bytes=0 bytes_per_second=425.483G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time_cv 1.55 % 0.82 % 5 bytes=0.00% bytes_per_second=1.54% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time 9110 ns 22585 ns 76789 bytes=536.871M bytes_per_second=53.5997T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time 9165 ns 22682 ns 76789 bytes=536.871M bytes_per_second=53.2743T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time 9297 ns 22933 ns 76789 bytes=536.871M bytes_per_second=52.5203T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time 9225 ns 22726 ns 76789 bytes=536.871M bytes_per_second=52.9327T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time 9220 ns 22719 ns 76789 bytes=536.871M bytes_per_second=52.9575T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time_mean 9203 ns 22729 ns 5 bytes=536.871M bytes_per_second=53.0569T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time_median 9220 ns 22719 ns 5 bytes=536.871M bytes_per_second=52.9575T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time_stddev 70.2 ns 127 ns 5 bytes=0 bytes_per_second=414.438G/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time_cv 0.76 % 0.56 % 5 bytes=0.00% bytes_per_second=0.76% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time 9340 ns 24038 ns 74438 bytes=1073.74M bytes_per_second=104.552T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time 9694 ns 24540 ns 74438 bytes=1073.74M bytes_per_second=100.742T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time 9612 ns 24628 ns 74438 bytes=1073.74M bytes_per_second=101.596T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time 9367 ns 24134 ns 74438 bytes=1073.74M bytes_per_second=104.253T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time 8951 ns 23556 ns 74438 bytes=1073.74M bytes_per_second=109.104T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time_mean 9393 ns 24179 ns 5 bytes=1073.74M bytes_per_second=104.049T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time_median 9367 ns 24134 ns 5 bytes=1073.74M bytes_per_second=104.253T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time_stddev 290 ns 431 ns 5 bytes=0 bytes_per_second=3.27137T/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time_cv 3.09 % 1.78 % 5 bytes=0.00% bytes_per_second=3.14% dst_gpu=-nan% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time 260253 ns 523948 ns 2687 bytes=1024 bytes_per_second=3.75235M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time 260559 ns 523844 ns 2687 bytes=1024 bytes_per_second=3.74796M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time 260311 ns 523324 ns 2687 bytes=1024 bytes_per_second=3.75152M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time 259847 ns 523562 ns 2687 bytes=1024 bytes_per_second=3.75822M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time 261085 ns 522991 ns 2687 bytes=1024 bytes_per_second=3.7404M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time_mean 260411 ns 523534 ns 5 bytes=1024 bytes_per_second=3.75009M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time_median 260311 ns 523562 ns 5 bytes=1024 bytes_per_second=3.75152M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time_stddev 455 ns 390 ns 5 bytes=0 bytes_per_second=6.71003k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time_cv 0.17 % 0.07 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time 260583 ns 524453 ns 2675 bytes=2.048k bytes_per_second=7.4952M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time 259929 ns 522539 ns 2675 bytes=2.048k bytes_per_second=7.51406M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time 260118 ns 523538 ns 2675 bytes=2.048k bytes_per_second=7.50862M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time 259679 ns 523256 ns 2675 bytes=2.048k bytes_per_second=7.5213M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time 261039 ns 524771 ns 2675 bytes=2.048k bytes_per_second=7.48213M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time_mean 260270 ns 523711 ns 5 bytes=2.048k bytes_per_second=7.50426M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time_median 260118 ns 523538 ns 5 bytes=2.048k bytes_per_second=7.50862M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time_stddev 543 ns 906 ns 5 bytes=0 bytes_per_second=16.0073k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time_cv 0.21 % 0.17 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time 260437 ns 524377 ns 2684 bytes=4.096k bytes_per_second=14.9989M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time 261600 ns 525143 ns 2684 bytes=4.096k bytes_per_second=14.9321M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time 260134 ns 524336 ns 2684 bytes=4.096k bytes_per_second=15.0163M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time 260709 ns 524121 ns 2684 bytes=4.096k bytes_per_second=14.9832M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time 260545 ns 523405 ns 2684 bytes=4.096k bytes_per_second=14.9926M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time_mean 260685 ns 524276 ns 5 bytes=4.096k bytes_per_second=14.9846M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time_median 260545 ns 524336 ns 5 bytes=4.096k bytes_per_second=14.9926M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time_stddev 553 ns 622 ns 5 bytes=0 bytes_per_second=32.491k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time_cv 0.21 % 0.12 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time 261670 ns 526854 ns 2707 bytes=8.192k bytes_per_second=29.8563M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time 262764 ns 527302 ns 2707 bytes=8.192k bytes_per_second=29.732M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time 261071 ns 527941 ns 2707 bytes=8.192k bytes_per_second=29.9248M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time 262875 ns 527880 ns 2707 bytes=8.192k bytes_per_second=29.7194M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time 261828 ns 527286 ns 2707 bytes=8.192k bytes_per_second=29.8383M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time_mean 262042 ns 527453 ns 5 bytes=8.192k bytes_per_second=29.8142M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time_median 261828 ns 527302 ns 5 bytes=8.192k bytes_per_second=29.8383M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time_stddev 765 ns 455 ns 5 bytes=0 bytes_per_second=89.1757k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time_cv 0.29 % 0.09 % 5 bytes=0.00% bytes_per_second=0.29% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time 264146 ns 532096 ns 2652 bytes=16.384k bytes_per_second=59.1529M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time 265608 ns 532769 ns 2652 bytes=16.384k bytes_per_second=58.8273M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time 263910 ns 533033 ns 2652 bytes=16.384k bytes_per_second=59.2059M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time 265197 ns 532938 ns 2652 bytes=16.384k bytes_per_second=58.9184M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time 264797 ns 533010 ns 2652 bytes=16.384k bytes_per_second=59.0074M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time_mean 264732 ns 532769 ns 5 bytes=16.384k bytes_per_second=59.0224M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time_median 264797 ns 532938 ns 5 bytes=16.384k bytes_per_second=59.0074M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time_stddev 708 ns 390 ns 5 bytes=0 bytes_per_second=161.747k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time_cv 0.27 % 0.07 % 5 bytes=0.00% bytes_per_second=0.27% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time 268539 ns 541559 ns 2604 bytes=32.768k bytes_per_second=116.37M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time 269301 ns 542167 ns 2604 bytes=32.768k bytes_per_second=116.041M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time 269665 ns 542661 ns 2604 bytes=32.768k bytes_per_second=115.885M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time 268803 ns 541983 ns 2604 bytes=32.768k bytes_per_second=116.256M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time 270066 ns 541874 ns 2604 bytes=32.768k bytes_per_second=115.713M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time_mean 269275 ns 542049 ns 5 bytes=32.768k bytes_per_second=116.053M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time_median 269301 ns 541983 ns 5 bytes=32.768k bytes_per_second=116.041M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time_stddev 621 ns 407 ns 5 bytes=0 bytes_per_second=273.993k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time_cv 0.23 % 0.08 % 5 bytes=0.00% bytes_per_second=0.23% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time 277698 ns 561123 ns 2547 bytes=65.536k bytes_per_second=225.064M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time 277702 ns 561206 ns 2547 bytes=65.536k bytes_per_second=225.061M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time 276899 ns 560460 ns 2547 bytes=65.536k bytes_per_second=225.714M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time 277406 ns 558438 ns 2547 bytes=65.536k bytes_per_second=225.302M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time 279012 ns 560278 ns 2547 bytes=65.536k bytes_per_second=224.005M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time_mean 277743 ns 560301 ns 5 bytes=65.536k bytes_per_second=225.029M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time_median 277698 ns 560460 ns 5 bytes=65.536k bytes_per_second=225.064M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time_stddev 781 ns 1117 ns 5 bytes=0 bytes_per_second=646.537k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time_cv 0.28 % 0.20 % 5 bytes=0.00% bytes_per_second=0.28% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time 290705 ns 590571 ns 2382 bytes=131.072k bytes_per_second=429.989M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time 290724 ns 589668 ns 2382 bytes=131.072k bytes_per_second=429.961M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time 293193 ns 589787 ns 2382 bytes=131.072k bytes_per_second=426.34M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time 290630 ns 590290 ns 2382 bytes=131.072k bytes_per_second=430.101M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time 290726 ns 589212 ns 2382 bytes=131.072k bytes_per_second=429.958M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time_mean 291195 ns 589906 ns 5 bytes=131.072k bytes_per_second=429.27M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time_median 290724 ns 589787 ns 5 bytes=131.072k bytes_per_second=429.961M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time_stddev 1117 ns 534 ns 5 bytes=0 bytes_per_second=1.63881M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time_cv 0.38 % 0.09 % 5 bytes=0.00% bytes_per_second=0.38% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time 326129 ns 655566 ns 2154 bytes=262.144k bytes_per_second=766.568M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time 326357 ns 656534 ns 2154 bytes=262.144k bytes_per_second=766.033M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time 326460 ns 656352 ns 2154 bytes=262.144k bytes_per_second=765.79M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time 325654 ns 653558 ns 2154 bytes=262.144k bytes_per_second=767.687M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time 326353 ns 655995 ns 2154 bytes=262.144k bytes_per_second=766.041M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time_mean 326191 ns 655601 ns 5 bytes=262.144k bytes_per_second=766.424M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time_median 326353 ns 655995 ns 5 bytes=262.144k bytes_per_second=766.041M/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time_stddev 324 ns 1200 ns 5 bytes=0 bytes_per_second=779.363k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time_cv 0.10 % 0.18 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time 389569 ns 782828 ns 1798 bytes=524.288k bytes_per_second=1.25339G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time 390173 ns 783786 ns 1798 bytes=524.288k bytes_per_second=1.25145G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time 389721 ns 783137 ns 1798 bytes=524.288k bytes_per_second=1.2529G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time 389458 ns 782389 ns 1798 bytes=524.288k bytes_per_second=1.25375G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time 389762 ns 782793 ns 1798 bytes=524.288k bytes_per_second=1.25277G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time_mean 389737 ns 782987 ns 5 bytes=524.288k bytes_per_second=1.25285G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time_median 389721 ns 782828 ns 5 bytes=524.288k bytes_per_second=1.2529G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time_stddev 273 ns 520 ns 5 bytes=0 bytes_per_second=919.067k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time_cv 0.07 % 0.07 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time 526845 ns 1062094 ns 1311 bytes=1048.58k bytes_per_second=1.8536G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time 529311 ns 1061467 ns 1311 bytes=1048.58k bytes_per_second=1.84497G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time 527310 ns 1062866 ns 1311 bytes=1048.58k bytes_per_second=1.85197G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time 528819 ns 1059918 ns 1311 bytes=1048.58k bytes_per_second=1.84669G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time 527791 ns 1063609 ns 1311 bytes=1048.58k bytes_per_second=1.85028G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time_mean 528015 ns 1061991 ns 5 bytes=1048.58k bytes_per_second=1.8495G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time_median 527791 ns 1062094 ns 5 bytes=1048.58k bytes_per_second=1.85028G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time_stddev 1030 ns 1411 ns 5 bytes=0 bytes_per_second=3.69204M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time_cv 0.20 % 0.13 % 5 bytes=0.00% bytes_per_second=0.19% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time 770366 ns 1543923 ns 905 bytes=2.09715M bytes_per_second=2.53532G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time 770761 ns 1545537 ns 905 bytes=2.09715M bytes_per_second=2.53402G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time 770469 ns 1544424 ns 905 bytes=2.09715M bytes_per_second=2.53498G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time 770415 ns 1545082 ns 905 bytes=2.09715M bytes_per_second=2.53516G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time 770791 ns 1545327 ns 905 bytes=2.09715M bytes_per_second=2.53392G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time_mean 770560 ns 1544858 ns 5 bytes=2.09715M bytes_per_second=2.53468G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time_median 770469 ns 1545082 ns 5 bytes=2.09715M bytes_per_second=2.53498G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time_stddev 200 ns 670 ns 5 bytes=0 bytes_per_second=691.146k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time_cv 0.03 % 0.04 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time 1330207 ns 2683062 ns 526 bytes=4.1943M bytes_per_second=2.93657G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time 1329220 ns 2682388 ns 526 bytes=4.1943M bytes_per_second=2.93875G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time 1329448 ns 2680965 ns 526 bytes=4.1943M bytes_per_second=2.93825G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time 1329810 ns 2681730 ns 526 bytes=4.1943M bytes_per_second=2.93745G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time 1330152 ns 2682108 ns 526 bytes=4.1943M bytes_per_second=2.9367G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time_mean 1329768 ns 2682051 ns 5 bytes=4.1943M bytes_per_second=2.93754G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time_median 1329810 ns 2682108 ns 5 bytes=4.1943M bytes_per_second=2.93745G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time_stddev 431 ns 778 ns 5 bytes=0 bytes_per_second=999.35k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time_cv 0.03 % 0.03 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time 2530162 ns 5084931 ns 276 bytes=8.38861M bytes_per_second=3.08775G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time 2540460 ns 5088599 ns 276 bytes=8.38861M bytes_per_second=3.07523G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time 2530318 ns 5083168 ns 276 bytes=8.38861M bytes_per_second=3.08756G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time 2538643 ns 5083109 ns 276 bytes=8.38861M bytes_per_second=3.07743G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time 2530784 ns 5084679 ns 276 bytes=8.38861M bytes_per_second=3.08699G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time_mean 2534074 ns 5084897 ns 5 bytes=8.38861M bytes_per_second=3.08299G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time_median 2530784 ns 5084679 ns 5 bytes=8.38861M bytes_per_second=3.08699G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time_stddev 5047 ns 2233 ns 5 bytes=0 bytes_per_second=6.28283M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time_cv 0.20 % 0.04 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time 4958054 ns 9899002 ns 140 bytes=16.7772M bytes_per_second=3.15144G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time 4958888 ns 9901532 ns 140 bytes=16.7772M bytes_per_second=3.15091G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time 4956245 ns 9897582 ns 140 bytes=16.7772M bytes_per_second=3.15259G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time 4955962 ns 9899028 ns 140 bytes=16.7772M bytes_per_second=3.15277G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time 4959121 ns 9901827 ns 140 bytes=16.7772M bytes_per_second=3.15076G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time_mean 4957654 ns 9899794 ns 5 bytes=16.7772M bytes_per_second=3.15169G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time_median 4958054 ns 9899028 ns 5 bytes=16.7772M bytes_per_second=3.15144G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time_stddev 1473 ns 1821 ns 5 bytes=0 bytes_per_second=982.245k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time_cv 0.03 % 0.02 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time 9816447 ns 19564316 ns 71 bytes=33.5544M bytes_per_second=3.18343G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time 9836375 ns 19643310 ns 71 bytes=33.5544M bytes_per_second=3.17698G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time 9819289 ns 19613840 ns 71 bytes=33.5544M bytes_per_second=3.18251G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time 9822724 ns 19642508 ns 71 bytes=33.5544M bytes_per_second=3.1814G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time 9803593 ns 19588635 ns 71 bytes=33.5544M bytes_per_second=3.18761G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time_mean 9819686 ns 19610522 ns 5 bytes=33.5544M bytes_per_second=3.18239G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time_median 9819289 ns 19613840 ns 5 bytes=33.5544M bytes_per_second=3.18251G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time_stddev 11804 ns 34363 ns 5 bytes=0 bytes_per_second=3.91711M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time_cv 0.12 % 0.18 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time 21204710 ns 42117607 ns 33 bytes=67.1089M bytes_per_second=2.94746G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time 21178950 ns 41930105 ns 33 bytes=67.1089M bytes_per_second=2.95104G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time 21222848 ns 42080342 ns 33 bytes=67.1089M bytes_per_second=2.94494G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time 21193733 ns 41990914 ns 33 bytes=67.1089M bytes_per_second=2.94899G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time 21201364 ns 42017415 ns 33 bytes=67.1089M bytes_per_second=2.94792G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time_mean 21200321 ns 42027277 ns 5 bytes=67.1089M bytes_per_second=2.94807G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time_median 21201364 ns 42017415 ns 5 bytes=67.1089M bytes_per_second=2.94792G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time_stddev 16031 ns 73887 ns 5 bytes=0 bytes_per_second=2.28256M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time_cv 0.08 % 0.18 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time 39356645 ns 77421941 ns 18 bytes=134.218M bytes_per_second=3.17608G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time 39344076 ns 77469422 ns 18 bytes=134.218M bytes_per_second=3.1771G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time 39327063 ns 77355495 ns 18 bytes=134.218M bytes_per_second=3.17847G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time 39364743 ns 77591955 ns 18 bytes=134.218M bytes_per_second=3.17543G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time 39355863 ns 77532200 ns 18 bytes=134.218M bytes_per_second=3.17615G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time_mean 39349678 ns 77474203 ns 5 bytes=134.218M bytes_per_second=3.17665G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time_median 39355863 ns 77469422 ns 5 bytes=134.218M bytes_per_second=3.17615G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time_stddev 14634 ns 92297 ns 5 bytes=0 bytes_per_second=1.20998M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time_cv 0.04 % 0.12 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time 75649516 ns 147569609 ns 9 bytes=268.435M bytes_per_second=3.30471G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time 75650669 ns 147478356 ns 9 bytes=268.435M bytes_per_second=3.30466G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time 75640662 ns 147576907 ns 9 bytes=268.435M bytes_per_second=3.3051G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time 75580374 ns 147494813 ns 9 bytes=268.435M bytes_per_second=3.30774G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time 75691077 ns 147718488 ns 9 bytes=268.435M bytes_per_second=3.3029G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time_mean 75642460 ns 147567634 ns 5 bytes=268.435M bytes_per_second=3.30502G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time_median 75649516 ns 147569609 ns 5 bytes=268.435M bytes_per_second=3.30471G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time_stddev 39808 ns 95027 ns 5 bytes=0 bytes_per_second=1.78152M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time_cv 0.05 % 0.06 % 5 bytes=0.00% bytes_per_second=0.05% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time 143270963 ns 274097491 ns 5 bytes=536.871M bytes_per_second=3.48989G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time 143517682 ns 274312927 ns 5 bytes=536.871M bytes_per_second=3.48389G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time 143463293 ns 274232322 ns 5 bytes=536.871M bytes_per_second=3.48521G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time 143381593 ns 274107892 ns 5 bytes=536.871M bytes_per_second=3.4872G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time 143656605 ns 274429638 ns 5 bytes=536.871M bytes_per_second=3.48052G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time_mean 143458027 ns 274236054 ns 5 bytes=536.871M bytes_per_second=3.48534G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time_median 143463293 ns 274232322 ns 5 bytes=536.871M bytes_per_second=3.48521G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time_stddev 144789 ns 140555 ns 5 bytes=0 bytes_per_second=3.60178M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time_cv 0.10 % 0.05 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time 293875530 ns 521672537 ns 2 bytes=1073.74M bytes_per_second=3.4028G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time 293460250 ns 521766202 ns 2 bytes=1073.74M bytes_per_second=3.40762G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time 293874890 ns 522395351 ns 2 bytes=1073.74M bytes_per_second=3.40281G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time 293541446 ns 521734958 ns 2 bytes=1073.74M bytes_per_second=3.40667G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time 293861702 ns 522204243 ns 2 bytes=1073.74M bytes_per_second=3.40296G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time_mean 293722764 ns 521954658 ns 5 bytes=1073.74M bytes_per_second=3.40457G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time_median 293861702 ns 521766202 ns 5 bytes=1073.74M bytes_per_second=3.40296G/s dst_gpu=1 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time_stddev 204679 ns 323990 ns 5 bytes=0 bytes_per_second=2.4301M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time_cv 0.07 % 0.06 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time 264466 ns 532979 ns 2508 bytes=1024 bytes_per_second=3.69258M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time 264363 ns 530803 ns 2508 bytes=1024 bytes_per_second=3.69402M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time 263642 ns 530463 ns 2508 bytes=1024 bytes_per_second=3.70412M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time 264031 ns 531081 ns 2508 bytes=1024 bytes_per_second=3.69866M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time 263620 ns 530360 ns 2508 bytes=1024 bytes_per_second=3.70443M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time_mean 264025 ns 531137 ns 5 bytes=1024 bytes_per_second=3.69876M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time_median 264031 ns 530803 ns 5 bytes=1024 bytes_per_second=3.69866M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time_stddev 394 ns 1068 ns 5 bytes=0 bytes_per_second=5.64585k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time_cv 0.15 % 0.20 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time 263909 ns 530668 ns 2645 bytes=2.048k bytes_per_second=7.40075M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time 263347 ns 530617 ns 2645 bytes=2.048k bytes_per_second=7.41653M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time 264013 ns 530457 ns 2645 bytes=2.048k bytes_per_second=7.39785M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time 263803 ns 529907 ns 2645 bytes=2.048k bytes_per_second=7.40373M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time 263803 ns 530440 ns 2645 bytes=2.048k bytes_per_second=7.40372M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time_mean 263775 ns 530418 ns 5 bytes=2.048k bytes_per_second=7.40452M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time_median 263803 ns 530457 ns 5 bytes=2.048k bytes_per_second=7.40372M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time_stddev 254 ns 302 ns 5 bytes=0 bytes_per_second=7.31875k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time_cv 0.10 % 0.06 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time 263919 ns 530764 ns 2643 bytes=4.096k bytes_per_second=14.801M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time 263291 ns 530646 ns 2643 bytes=4.096k bytes_per_second=14.8363M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time 263787 ns 530647 ns 2643 bytes=4.096k bytes_per_second=14.8083M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time 263961 ns 530052 ns 2643 bytes=4.096k bytes_per_second=14.7986M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time 264011 ns 530713 ns 2643 bytes=4.096k bytes_per_second=14.7958M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time_mean 263794 ns 530564 ns 5 bytes=4.096k bytes_per_second=14.808M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time_median 263919 ns 530647 ns 5 bytes=4.096k bytes_per_second=14.801M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time_stddev 293 ns 291 ns 5 bytes=0 bytes_per_second=16.873k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time_cv 0.11 % 0.05 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time 265427 ns 533875 ns 2628 bytes=8.192k bytes_per_second=29.4337M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time 265151 ns 534413 ns 2628 bytes=8.192k bytes_per_second=29.4643M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time 265546 ns 533410 ns 2628 bytes=8.192k bytes_per_second=29.4205M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time 266532 ns 534603 ns 2628 bytes=8.192k bytes_per_second=29.3117M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time 265721 ns 533373 ns 2628 bytes=8.192k bytes_per_second=29.4012M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time_mean 265675 ns 533935 ns 5 bytes=8.192k bytes_per_second=29.4063M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time_median 265546 ns 533875 ns 5 bytes=8.192k bytes_per_second=29.4205M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time_stddev 522 ns 563 ns 5 bytes=0 bytes_per_second=59.0567k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time_cv 0.20 % 0.11 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time 268496 ns 539843 ns 2598 bytes=16.384k bytes_per_second=58.1945M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time 267664 ns 539153 ns 2598 bytes=16.384k bytes_per_second=58.3753M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time 269111 ns 539402 ns 2598 bytes=16.384k bytes_per_second=58.0615M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time 268337 ns 538712 ns 2598 bytes=16.384k bytes_per_second=58.229M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time 268915 ns 539468 ns 2598 bytes=16.384k bytes_per_second=58.1038M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time_mean 268505 ns 539316 ns 5 bytes=16.384k bytes_per_second=58.1928M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time_median 268496 ns 539402 ns 5 bytes=16.384k bytes_per_second=58.1945M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time_stddev 564 ns 418 ns 5 bytes=0 bytes_per_second=125.211k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time_cv 0.21 % 0.08 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time 273159 ns 547722 ns 2561 bytes=32.768k bytes_per_second=114.402M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time 272369 ns 546884 ns 2561 bytes=32.768k bytes_per_second=114.734M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time 272522 ns 547802 ns 2561 bytes=32.768k bytes_per_second=114.67M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time 272372 ns 547022 ns 2561 bytes=32.768k bytes_per_second=114.733M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time 272574 ns 547813 ns 2561 bytes=32.768k bytes_per_second=114.648M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time_mean 272599 ns 547449 ns 5 bytes=32.768k bytes_per_second=114.637M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time_median 272522 ns 547722 ns 5 bytes=32.768k bytes_per_second=114.67M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time_stddev 326 ns 457 ns 5 bytes=0 bytes_per_second=140.201k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time_cv 0.12 % 0.08 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time 281561 ns 565349 ns 2496 bytes=65.536k bytes_per_second=221.977M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time 280814 ns 565146 ns 2496 bytes=65.536k bytes_per_second=222.567M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time 281783 ns 566234 ns 2496 bytes=65.536k bytes_per_second=221.802M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time 281251 ns 565888 ns 2496 bytes=65.536k bytes_per_second=222.221M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time 281115 ns 565741 ns 2496 bytes=65.536k bytes_per_second=222.329M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time_mean 281305 ns 565672 ns 5 bytes=65.536k bytes_per_second=222.179M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time_median 281251 ns 565741 ns 5 bytes=65.536k bytes_per_second=222.221M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time_stddev 379 ns 432 ns 5 bytes=0 bytes_per_second=306.385k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time_cv 0.13 % 0.08 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time 295365 ns 599021 ns 2368 bytes=131.072k bytes_per_second=423.205M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time 298577 ns 599829 ns 2368 bytes=131.072k bytes_per_second=418.652M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time 295435 ns 598496 ns 2368 bytes=131.072k bytes_per_second=423.104M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time 295337 ns 599567 ns 2368 bytes=131.072k bytes_per_second=423.245M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time 297630 ns 598667 ns 2368 bytes=131.072k bytes_per_second=419.984M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time_mean 296469 ns 599116 ns 5 bytes=131.072k bytes_per_second=421.638M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time_median 295435 ns 599021 ns 5 bytes=131.072k bytes_per_second=423.104M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time_stddev 1530 ns 572 ns 5 bytes=0 bytes_per_second=2.17027M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time_cv 0.52 % 0.10 % 5 bytes=0.00% bytes_per_second=0.51% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time 329313 ns 662210 ns 2123 bytes=262.144k bytes_per_second=759.156M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time 329595 ns 662730 ns 2123 bytes=262.144k bytes_per_second=758.507M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time 329406 ns 662767 ns 2123 bytes=262.144k bytes_per_second=758.943M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time 330326 ns 662449 ns 2123 bytes=262.144k bytes_per_second=756.829M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time 329408 ns 662033 ns 2123 bytes=262.144k bytes_per_second=758.938M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time_mean 329609 ns 662438 ns 5 bytes=262.144k bytes_per_second=758.474M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time_median 329408 ns 662449 ns 5 bytes=262.144k bytes_per_second=758.938M/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time_stddev 413 ns 320 ns 5 bytes=0 bytes_per_second=972.578k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time_cv 0.13 % 0.05 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time 394012 ns 791715 ns 1773 bytes=524.288k bytes_per_second=1.23925G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time 396372 ns 795858 ns 1773 bytes=524.288k bytes_per_second=1.23188G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time 394434 ns 791727 ns 1773 bytes=524.288k bytes_per_second=1.23793G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time 394205 ns 791410 ns 1773 bytes=524.288k bytes_per_second=1.23865G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time 394392 ns 791933 ns 1773 bytes=524.288k bytes_per_second=1.23806G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time_mean 394683 ns 792529 ns 5 bytes=524.288k bytes_per_second=1.23715G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time_median 394392 ns 791727 ns 5 bytes=524.288k bytes_per_second=1.23806G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time_stddev 959 ns 1871 ns 5 bytes=0 bytes_per_second=3.06858M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time_cv 0.24 % 0.24 % 5 bytes=0.00% bytes_per_second=0.24% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time 537452 ns 1083582 ns 1283 bytes=1048.58k bytes_per_second=1.81702G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time 536211 ns 1075540 ns 1283 bytes=1048.58k bytes_per_second=1.82123G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time 531973 ns 1070890 ns 1283 bytes=1048.58k bytes_per_second=1.83574G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time 534489 ns 1071024 ns 1283 bytes=1048.58k bytes_per_second=1.8271G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time 532351 ns 1072131 ns 1283 bytes=1048.58k bytes_per_second=1.83443G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time_mean 534495 ns 1074633 ns 5 bytes=1048.58k bytes_per_second=1.8271G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time_median 534489 ns 1072131 ns 5 bytes=1048.58k bytes_per_second=1.8271G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time_stddev 2379 ns 5343 ns 5 bytes=0 bytes_per_second=8.32552M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time_cv 0.45 % 0.50 % 5 bytes=0.00% bytes_per_second=0.44% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time 775881 ns 1555231 ns 894 bytes=2.09715M bytes_per_second=2.5173G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time 775618 ns 1554956 ns 894 bytes=2.09715M bytes_per_second=2.51815G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time 775505 ns 1554147 ns 894 bytes=2.09715M bytes_per_second=2.51852G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time 775870 ns 1555165 ns 894 bytes=2.09715M bytes_per_second=2.51733G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time 775749 ns 1555247 ns 894 bytes=2.09715M bytes_per_second=2.51773G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time_mean 775725 ns 1554949 ns 5 bytes=2.09715M bytes_per_second=2.51781G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time_median 775749 ns 1555165 ns 5 bytes=2.09715M bytes_per_second=2.51773G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time_stddev 163 ns 463 ns 5 bytes=0 bytes_per_second=554.287k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time_cv 0.02 % 0.03 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time 1337341 ns 2696697 ns 521 bytes=4.1943M bytes_per_second=2.92091G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time 1337294 ns 2696723 ns 521 bytes=4.1943M bytes_per_second=2.92101G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time 1337617 ns 2698192 ns 521 bytes=4.1943M bytes_per_second=2.9203G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time 1336962 ns 2696485 ns 521 bytes=4.1943M bytes_per_second=2.92174G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time 1337266 ns 2698171 ns 521 bytes=4.1943M bytes_per_second=2.92107G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time_mean 1337296 ns 2697254 ns 5 bytes=4.1943M bytes_per_second=2.92101G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time_median 1337294 ns 2696723 ns 5 bytes=4.1943M bytes_per_second=2.92101G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time_stddev 234 ns 852 ns 5 bytes=0 bytes_per_second=534.892k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time_cv 0.02 % 0.03 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time 2505598 ns 5045515 ns 278 bytes=8.38861M bytes_per_second=3.11802G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time 2541698 ns 5101232 ns 278 bytes=8.38861M bytes_per_second=3.07373G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time 2534761 ns 5101472 ns 278 bytes=8.38861M bytes_per_second=3.08214G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time 2543572 ns 5103507 ns 278 bytes=8.38861M bytes_per_second=3.07147G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time 2534732 ns 5102289 ns 278 bytes=8.38861M bytes_per_second=3.08218G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time_mean 2532072 ns 5090803 ns 5 bytes=8.38861M bytes_per_second=3.08551G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time_median 2534761 ns 5101472 ns 5 bytes=8.38861M bytes_per_second=3.08214G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time_stddev 15331 ns 25332 ns 5 bytes=0 bytes_per_second=19.2604M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time_cv 0.61 % 0.50 % 5 bytes=0.00% bytes_per_second=0.61% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time 4991471 ns 9950647 ns 139 bytes=16.7772M bytes_per_second=3.13034G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time 4997597 ns 9955977 ns 139 bytes=16.7772M bytes_per_second=3.1265G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time 4995727 ns 9953801 ns 139 bytes=16.7772M bytes_per_second=3.12767G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time 4999585 ns 9960826 ns 139 bytes=16.7772M bytes_per_second=3.12526G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time 4992833 ns 9950688 ns 139 bytes=16.7772M bytes_per_second=3.12949G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time_mean 4995443 ns 9954388 ns 5 bytes=16.7772M bytes_per_second=3.12785G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time_median 4995727 ns 9953801 ns 5 bytes=16.7772M bytes_per_second=3.12767G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time_stddev 3334 ns 4243 ns 5 bytes=0 bytes_per_second=2.13776M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time_cv 0.07 % 0.04 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time 9855158 ns 19677039 ns 69 bytes=33.5544M bytes_per_second=3.17093G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time 9876728 ns 19755815 ns 69 bytes=33.5544M bytes_per_second=3.164G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time 9850855 ns 19728923 ns 69 bytes=33.5544M bytes_per_second=3.17231G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time 9894183 ns 19738984 ns 69 bytes=33.5544M bytes_per_second=3.15842G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time 9877536 ns 19697674 ns 69 bytes=33.5544M bytes_per_second=3.16374G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time_mean 9870892 ns 19719687 ns 5 bytes=33.5544M bytes_per_second=3.16588G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time_median 9876728 ns 19728923 ns 5 bytes=33.5544M bytes_per_second=3.164G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time_stddev 17816 ns 31884 ns 5 bytes=0 bytes_per_second=5.85082M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time_cv 0.18 % 0.16 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time 21335860 ns 42675718 ns 33 bytes=67.1089M bytes_per_second=2.92934G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time 21348321 ns 42700433 ns 33 bytes=67.1089M bytes_per_second=2.92763G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time 21277513 ns 42515127 ns 33 bytes=67.1089M bytes_per_second=2.93737G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time 21340655 ns 42700585 ns 33 bytes=67.1089M bytes_per_second=2.92868G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time 21284238 ns 42576890 ns 33 bytes=67.1089M bytes_per_second=2.93645G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time_mean 21317317 ns 42633751 ns 5 bytes=67.1089M bytes_per_second=2.93189G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time_median 21335860 ns 42675718 ns 5 bytes=67.1089M bytes_per_second=2.92934G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time_stddev 33647 ns 83635 ns 5 bytes=0 bytes_per_second=4.74115M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time_cv 0.16 % 0.20 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time 39461461 ns 77981712 ns 18 bytes=134.218M bytes_per_second=3.16765G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time 39421542 ns 77887997 ns 18 bytes=134.218M bytes_per_second=3.17086G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time 39433871 ns 77994282 ns 18 bytes=134.218M bytes_per_second=3.16986G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time 39458120 ns 78052958 ns 18 bytes=134.218M bytes_per_second=3.16792G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time 39418209 ns 77941506 ns 18 bytes=134.218M bytes_per_second=3.17112G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time_mean 39438641 ns 77971691 ns 5 bytes=134.218M bytes_per_second=3.16948G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time_median 39433871 ns 77981712 ns 5 bytes=134.218M bytes_per_second=3.16986G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time_stddev 20204 ns 61504 ns 5 bytes=0 bytes_per_second=1.66253M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time_cv 0.05 % 0.08 % 5 bytes=0.00% bytes_per_second=0.05% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time 75653250 ns 147669389 ns 9 bytes=268.435M bytes_per_second=3.30455G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time 75720396 ns 147738729 ns 9 bytes=268.435M bytes_per_second=3.30162G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time 75604699 ns 147593007 ns 9 bytes=268.435M bytes_per_second=3.30667G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time 75640398 ns 147684749 ns 9 bytes=268.435M bytes_per_second=3.30511G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time 75695843 ns 147710113 ns 9 bytes=268.435M bytes_per_second=3.30269G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time_mean 75662917 ns 147679197 ns 5 bytes=268.435M bytes_per_second=3.30413G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time_median 75653250 ns 147684749 ns 5 bytes=268.435M bytes_per_second=3.30455G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time_stddev 45766 ns 54899 ns 5 bytes=0 bytes_per_second=2.04645M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time_cv 0.06 % 0.04 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time 149174756 ns 285266933 ns 5 bytes=536.871M bytes_per_second=3.35177G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time 149386019 ns 285426244 ns 5 bytes=536.871M bytes_per_second=3.34703G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time 149380097 ns 285401778 ns 5 bytes=536.871M bytes_per_second=3.34717G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time 149394438 ns 284916753 ns 5 bytes=536.871M bytes_per_second=3.34684G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time 149569222 ns 285674484 ns 5 bytes=536.871M bytes_per_second=3.34293G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time_mean 149380906 ns 285337238 ns 5 bytes=536.871M bytes_per_second=3.34715G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time_median 149386019 ns 285401778 ns 5 bytes=536.871M bytes_per_second=3.34703G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time_stddev 139795 ns 277296 ns 5 bytes=0 bytes_per_second=3.20812M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time_cv 0.09 % 0.10 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time 294380814 ns 523221997 ns 2 bytes=1073.74M bytes_per_second=3.39696G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time 294713929 ns 523823263 ns 2 bytes=1073.74M bytes_per_second=3.39312G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time 294585779 ns 523256086 ns 2 bytes=1073.74M bytes_per_second=3.3946G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time 294733927 ns 523878267 ns 2 bytes=1073.74M bytes_per_second=3.39289G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time 294914663 ns 524077525 ns 2 bytes=1073.74M bytes_per_second=3.39081G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time_mean 294665822 ns 523651427 ns 5 bytes=1073.74M bytes_per_second=3.39368G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time_median 294713929 ns 523823263 ns 5 bytes=1073.74M bytes_per_second=3.39312G/s dst_gpu=2 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time_stddev 197807 ns 388346 ns 5 bytes=0 bytes_per_second=2.33323M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time_cv 0.07 % 0.07 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time 259143 ns 523355 ns 2700 bytes=1024 bytes_per_second=3.76843M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time 258484 ns 523096 ns 2700 bytes=1024 bytes_per_second=3.77804M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time 258950 ns 521442 ns 2700 bytes=1024 bytes_per_second=3.77125M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time 258294 ns 522265 ns 2700 bytes=1024 bytes_per_second=3.78082M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time 258468 ns 521741 ns 2700 bytes=1024 bytes_per_second=3.77828M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time_mean 258668 ns 522380 ns 5 bytes=1024 bytes_per_second=3.77536M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time_median 258484 ns 522265 ns 5 bytes=1024 bytes_per_second=3.77804M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time_stddev 360 ns 831 ns 5 bytes=0 bytes_per_second=5.37974k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time_cv 0.14 % 0.16 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time 258897 ns 523097 ns 2705 bytes=2.048k bytes_per_second=7.54402M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time 258899 ns 523029 ns 2705 bytes=2.048k bytes_per_second=7.54397M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time 258875 ns 522869 ns 2705 bytes=2.048k bytes_per_second=7.54468M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time 258553 ns 522811 ns 2705 bytes=2.048k bytes_per_second=7.55406M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time 258339 ns 522372 ns 2705 bytes=2.048k bytes_per_second=7.56032M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time_mean 258713 ns 522836 ns 5 bytes=2.048k bytes_per_second=7.54941M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time_median 258875 ns 522869 ns 5 bytes=2.048k bytes_per_second=7.54468M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time_stddev 255 ns 284 ns 5 bytes=0 bytes_per_second=7.62041k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time_cv 0.10 % 0.05 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time 258855 ns 522907 ns 2704 bytes=4.096k bytes_per_second=15.0905M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time 258232 ns 521792 ns 2704 bytes=4.096k bytes_per_second=15.1269M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time 258976 ns 522492 ns 2704 bytes=4.096k bytes_per_second=15.0835M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time 258267 ns 522138 ns 2704 bytes=4.096k bytes_per_second=15.1249M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time 258714 ns 523129 ns 2704 bytes=4.096k bytes_per_second=15.0987M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time_mean 258609 ns 522492 ns 5 bytes=4.096k bytes_per_second=15.1049M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time_median 258714 ns 522492 ns 5 bytes=4.096k bytes_per_second=15.0987M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time_stddev 341 ns 546 ns 5 bytes=0 bytes_per_second=20.4006k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time_cv 0.13 % 0.10 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time 260740 ns 526190 ns 2676 bytes=8.192k bytes_per_second=29.9627M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time 261462 ns 526198 ns 2676 bytes=8.192k bytes_per_second=29.8801M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time 260748 ns 525859 ns 2676 bytes=8.192k bytes_per_second=29.9619M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time 260909 ns 526214 ns 2676 bytes=8.192k bytes_per_second=29.9434M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time 260766 ns 525352 ns 2676 bytes=8.192k bytes_per_second=29.9598M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time_mean 260925 ns 525963 ns 5 bytes=8.192k bytes_per_second=29.9416M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time_median 260766 ns 526190 ns 5 bytes=8.192k bytes_per_second=29.9598M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time_stddev 308 ns 372 ns 5 bytes=0 bytes_per_second=36.1258k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time_cv 0.12 % 0.07 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time 263473 ns 531193 ns 2657 bytes=16.384k bytes_per_second=59.3041M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time 264179 ns 531524 ns 2657 bytes=16.384k bytes_per_second=59.1455M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time 263676 ns 531693 ns 2657 bytes=16.384k bytes_per_second=59.2584M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time 263756 ns 531766 ns 2657 bytes=16.384k bytes_per_second=59.2403M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time 264207 ns 531447 ns 2657 bytes=16.384k bytes_per_second=59.1393M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time_mean 263858 ns 531525 ns 5 bytes=16.384k bytes_per_second=59.2175M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time_median 263756 ns 531524 ns 5 bytes=16.384k bytes_per_second=59.2403M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time_stddev 323 ns 225 ns 5 bytes=0 bytes_per_second=74.1842k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time_cv 0.12 % 0.04 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time 267637 ns 540084 ns 2619 bytes=32.768k bytes_per_second=116.763M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time 268381 ns 540005 ns 2619 bytes=32.768k bytes_per_second=116.439M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time 267733 ns 539895 ns 2619 bytes=32.768k bytes_per_second=116.721M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time 267718 ns 539832 ns 2619 bytes=32.768k bytes_per_second=116.727M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time 266858 ns 538274 ns 2619 bytes=32.768k bytes_per_second=117.103M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time_mean 267665 ns 539618 ns 5 bytes=32.768k bytes_per_second=116.751M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time_median 267718 ns 539895 ns 5 bytes=32.768k bytes_per_second=116.727M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time_stddev 541 ns 758 ns 5 bytes=0 bytes_per_second=241.837k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time_cv 0.20 % 0.14 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time 276517 ns 557719 ns 2534 bytes=65.536k bytes_per_second=226.026M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time 276460 ns 556942 ns 2534 bytes=65.536k bytes_per_second=226.073M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time 275842 ns 557007 ns 2534 bytes=65.536k bytes_per_second=226.579M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time 275963 ns 557781 ns 2534 bytes=65.536k bytes_per_second=226.48M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time 275781 ns 557585 ns 2534 bytes=65.536k bytes_per_second=226.629M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time_mean 276113 ns 557407 ns 5 bytes=65.536k bytes_per_second=226.357M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time_median 275963 ns 557585 ns 5 bytes=65.536k bytes_per_second=226.48M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time_stddev 350 ns 402 ns 5 bytes=0 bytes_per_second=293.45k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time_cv 0.13 % 0.07 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time 293441 ns 590248 ns 2357 bytes=131.072k bytes_per_second=425.98M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time 294341 ns 591966 ns 2357 bytes=131.072k bytes_per_second=424.677M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time 297233 ns 591485 ns 2357 bytes=131.072k bytes_per_second=420.545M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time 293561 ns 590034 ns 2357 bytes=131.072k bytes_per_second=425.806M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time 294061 ns 591094 ns 2357 bytes=131.072k bytes_per_second=425.082M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time_mean 294528 ns 590965 ns 5 bytes=131.072k bytes_per_second=424.418M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time_median 294061 ns 591094 ns 5 bytes=131.072k bytes_per_second=425.082M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time_stddev 1556 ns 817 ns 5 bytes=0 bytes_per_second=2.22891M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time_cv 0.53 % 0.14 % 5 bytes=0.00% bytes_per_second=0.53% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time 325487 ns 654957 ns 2152 bytes=262.144k bytes_per_second=768.079M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time 325584 ns 654442 ns 2152 bytes=262.144k bytes_per_second=767.852M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time 325199 ns 654899 ns 2152 bytes=262.144k bytes_per_second=768.761M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time 325574 ns 655085 ns 2152 bytes=262.144k bytes_per_second=767.875M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time 326489 ns 655549 ns 2152 bytes=262.144k bytes_per_second=765.722M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time_mean 325667 ns 654986 ns 5 bytes=262.144k bytes_per_second=767.658M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time_median 325574 ns 654957 ns 5 bytes=262.144k bytes_per_second=767.875M/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time_stddev 486 ns 397 ns 5 bytes=0 bytes_per_second=1.14297M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time_cv 0.15 % 0.06 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time 390677 ns 784852 ns 1793 bytes=524.288k bytes_per_second=1.24983G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time 389920 ns 783680 ns 1793 bytes=524.288k bytes_per_second=1.25226G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time 389777 ns 783223 ns 1793 bytes=524.288k bytes_per_second=1.25272G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time 389970 ns 783207 ns 1793 bytes=524.288k bytes_per_second=1.2521G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time 389915 ns 783383 ns 1793 bytes=524.288k bytes_per_second=1.25228G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time_mean 390052 ns 783669 ns 5 bytes=524.288k bytes_per_second=1.25184G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time_median 389920 ns 783383 ns 5 bytes=524.288k bytes_per_second=1.25226G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time_stddev 357 ns 688 ns 5 bytes=0 bytes_per_second=1.17165M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time_cv 0.09 % 0.09 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time 532040 ns 1066738 ns 1286 bytes=1048.58k bytes_per_second=1.83551G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time 534847 ns 1067033 ns 1286 bytes=1048.58k bytes_per_second=1.82587G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time 533093 ns 1067935 ns 1286 bytes=1048.58k bytes_per_second=1.83188G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time 534220 ns 1065941 ns 1286 bytes=1048.58k bytes_per_second=1.82801G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time 532499 ns 1067316 ns 1286 bytes=1048.58k bytes_per_second=1.83393G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time_mean 533340 ns 1066993 ns 5 bytes=1048.58k bytes_per_second=1.83104G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time_median 533093 ns 1067033 ns 5 bytes=1048.58k bytes_per_second=1.83188G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time_stddev 1173 ns 736 ns 5 bytes=0 bytes_per_second=4.12226M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time_cv 0.22 % 0.07 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time 785264 ns 1573669 ns 892 bytes=2.09715M bytes_per_second=2.48722G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time 784268 ns 1572016 ns 892 bytes=2.09715M bytes_per_second=2.49038G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time 784345 ns 1571897 ns 892 bytes=2.09715M bytes_per_second=2.49013G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time 784622 ns 1572487 ns 892 bytes=2.09715M bytes_per_second=2.48926G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time 785379 ns 1573199 ns 892 bytes=2.09715M bytes_per_second=2.48686G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time_mean 784776 ns 1572654 ns 5 bytes=2.09715M bytes_per_second=2.48877G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time_median 784622 ns 1572487 ns 5 bytes=2.09715M bytes_per_second=2.48926G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time_stddev 517 ns 764 ns 5 bytes=0 bytes_per_second=1.67815M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time_cv 0.07 % 0.05 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time 1332813 ns 2685947 ns 522 bytes=4.1943M bytes_per_second=2.93083G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time 1332480 ns 2686622 ns 522 bytes=4.1943M bytes_per_second=2.93156G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time 1332316 ns 2685727 ns 522 bytes=4.1943M bytes_per_second=2.93192G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time 1332048 ns 2686378 ns 522 bytes=4.1943M bytes_per_second=2.93251G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time 1332334 ns 2687290 ns 522 bytes=4.1943M bytes_per_second=2.93188G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time_mean 1332398 ns 2686393 ns 5 bytes=4.1943M bytes_per_second=2.93174G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time_median 1332334 ns 2686378 ns 5 bytes=4.1943M bytes_per_second=2.93188G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time_stddev 279 ns 612 ns 5 bytes=0 bytes_per_second=644.297k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time_cv 0.02 % 0.02 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time 2518485 ns 5056973 ns 277 bytes=8.38861M bytes_per_second=3.10206G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time 2524683 ns 5061601 ns 277 bytes=8.38861M bytes_per_second=3.09445G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time 2519478 ns 5057963 ns 277 bytes=8.38861M bytes_per_second=3.10084G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time 2522860 ns 5059747 ns 277 bytes=8.38861M bytes_per_second=3.09668G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time 2519989 ns 5058356 ns 277 bytes=8.38861M bytes_per_second=3.10021G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time_mean 2521099 ns 5058928 ns 5 bytes=8.38861M bytes_per_second=3.09885G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time_median 2519989 ns 5058356 ns 5 bytes=8.38861M bytes_per_second=3.10021G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time_stddev 2580 ns 1796 ns 5 bytes=0 bytes_per_second=3.24658M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time_cv 0.10 % 0.04 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time 4966174 ns 9894180 ns 139 bytes=16.7772M bytes_per_second=3.14629G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time 4962942 ns 9890441 ns 139 bytes=16.7772M bytes_per_second=3.14833G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time 4961154 ns 9889324 ns 139 bytes=16.7772M bytes_per_second=3.14947G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time 4963251 ns 9892630 ns 139 bytes=16.7772M bytes_per_second=3.14814G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time 4963614 ns 9889797 ns 139 bytes=16.7772M bytes_per_second=3.14791G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time_mean 4963427 ns 9891274 ns 5 bytes=16.7772M bytes_per_second=3.14803G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time_median 4963251 ns 9890441 ns 5 bytes=16.7772M bytes_per_second=3.14814G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time_stddev 1804 ns 2060 ns 5 bytes=0 bytes_per_second=1.17125M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time_cv 0.04 % 0.02 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time 9807269 ns 19577798 ns 70 bytes=33.5544M bytes_per_second=3.18641G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time 9808471 ns 19568157 ns 70 bytes=33.5544M bytes_per_second=3.18602G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time 9805799 ns 19553880 ns 70 bytes=33.5544M bytes_per_second=3.18689G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time 9800702 ns 19545880 ns 70 bytes=33.5544M bytes_per_second=3.18855G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time 9802501 ns 19562303 ns 70 bytes=33.5544M bytes_per_second=3.18796G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time_mean 9804948 ns 19561604 ns 5 bytes=33.5544M bytes_per_second=3.18717G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time_median 9805799 ns 19562303 ns 5 bytes=33.5544M bytes_per_second=3.18689G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time_stddev 3261 ns 12375 ns 5 bytes=0 bytes_per_second=1111.64k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time_cv 0.03 % 0.06 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time 21265817 ns 42314154 ns 33 bytes=67.1089M bytes_per_second=2.93899G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time 21225191 ns 42187754 ns 33 bytes=67.1089M bytes_per_second=2.94461G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time 21283631 ns 42343828 ns 33 bytes=67.1089M bytes_per_second=2.93653G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time 21269822 ns 42339913 ns 33 bytes=67.1089M bytes_per_second=2.93844G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time 21245991 ns 42218215 ns 33 bytes=67.1089M bytes_per_second=2.94173G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time_mean 21258090 ns 42280773 ns 5 bytes=67.1089M bytes_per_second=2.94006G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time_median 21265817 ns 42314154 ns 5 bytes=67.1089M bytes_per_second=2.93899G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time_stddev 22795 ns 72722 ns 5 bytes=0 bytes_per_second=3.22959M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time_cv 0.11 % 0.17 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time 39377885 ns 77484670 ns 18 bytes=134.218M bytes_per_second=3.17437G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time 39347022 ns 77484119 ns 18 bytes=134.218M bytes_per_second=3.17686G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time 39294177 ns 77485220 ns 18 bytes=134.218M bytes_per_second=3.18113G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time 39349724 ns 77533814 ns 18 bytes=134.218M bytes_per_second=3.17664G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time 39344818 ns 77566625 ns 18 bytes=134.218M bytes_per_second=3.17704G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time_mean 39342725 ns 77510890 ns 5 bytes=134.218M bytes_per_second=3.17721G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time_median 39347022 ns 77485220 ns 5 bytes=134.218M bytes_per_second=3.17686G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time_stddev 30269 ns 37733 ns 5 bytes=0 bytes_per_second=2.50437M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time_cv 0.08 % 0.05 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time 74135813 ns 144472559 ns 9 bytes=268.435M bytes_per_second=3.37219G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time 74383102 ns 144936917 ns 9 bytes=268.435M bytes_per_second=3.36098G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time 74213820 ns 144593344 ns 9 bytes=268.435M bytes_per_second=3.36864G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time 74103633 ns 144414566 ns 9 bytes=268.435M bytes_per_second=3.37365G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time 74176327 ns 144494036 ns 9 bytes=268.435M bytes_per_second=3.37035G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time_mean 74202539 ns 144582285 ns 5 bytes=268.435M bytes_per_second=3.36916G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time_median 74176327 ns 144494036 ns 5 bytes=268.435M bytes_per_second=3.37035G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time_stddev 109147 ns 208472 ns 5 bytes=0 bytes_per_second=5.06816M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time_cv 0.15 % 0.14 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time 149282739 ns 284604936 ns 5 bytes=536.871M bytes_per_second=3.34935G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time 148906833 ns 284068278 ns 5 bytes=536.871M bytes_per_second=3.3578G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time 148417011 ns 283784019 ns 5 bytes=536.871M bytes_per_second=3.36889G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time 148535252 ns 283663715 ns 5 bytes=536.871M bytes_per_second=3.3662G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time 148808721 ns 283595243 ns 5 bytes=536.871M bytes_per_second=3.36002G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time_mean 148790111 ns 283943238 ns 5 bytes=536.871M bytes_per_second=3.36045G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time_median 148808721 ns 283784019 ns 5 bytes=536.871M bytes_per_second=3.36002G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time_stddev 339415 ns 411723 ns 5 bytes=0 bytes_per_second=7.84374M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time_cv 0.23 % 0.15 % 5 bytes=0.00% bytes_per_second=0.23% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time 292394146 ns 519779516 ns 2 bytes=1073.74M bytes_per_second=3.42004G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time 292529672 ns 519957600 ns 2 bytes=1073.74M bytes_per_second=3.41846G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time 291912138 ns 518844393 ns 2 bytes=1073.74M bytes_per_second=3.42569G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time 292185351 ns 519056917 ns 2 bytes=1073.74M bytes_per_second=3.42249G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time 292349026 ns 520071218 ns 2 bytes=1073.74M bytes_per_second=3.42057G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time_mean 292274067 ns 519541929 ns 5 bytes=1073.74M bytes_per_second=3.42145G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time_median 292349026 ns 519779516 ns 5 bytes=1073.74M bytes_per_second=3.42057G/s dst_gpu=3 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time_stddev 236767 ns 554790 ns 5 bytes=0 bytes_per_second=2.83946M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time_cv 0.08 % 0.11 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time 262108 ns 529094 ns 2672 bytes=1024 bytes_per_second=3.7258M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time 262672 ns 528767 ns 2672 bytes=1024 bytes_per_second=3.71781M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time 262732 ns 529201 ns 2672 bytes=1024 bytes_per_second=3.71695M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time 261946 ns 528828 ns 2672 bytes=1024 bytes_per_second=3.7281M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time 262530 ns 528893 ns 2672 bytes=1024 bytes_per_second=3.71981M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time_mean 262398 ns 528957 ns 5 bytes=1024 bytes_per_second=3.72169M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time_median 262530 ns 528893 ns 5 bytes=1024 bytes_per_second=3.71981M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time_stddev 351 ns 184 ns 5 bytes=0 bytes_per_second=5.09527k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time_cv 0.13 % 0.03 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time 262387 ns 528695 ns 2672 bytes=2.048k bytes_per_second=7.44367M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time 261873 ns 528083 ns 2672 bytes=2.048k bytes_per_second=7.45829M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time 262520 ns 528686 ns 2672 bytes=2.048k bytes_per_second=7.43992M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time 261913 ns 528824 ns 2672 bytes=2.048k bytes_per_second=7.45716M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time 262515 ns 528751 ns 2672 bytes=2.048k bytes_per_second=7.44006M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time_mean 262241 ns 528608 ns 5 bytes=2.048k bytes_per_second=7.44782M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time_median 262387 ns 528695 ns 5 bytes=2.048k bytes_per_second=7.44367M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time_stddev 323 ns 298 ns 5 bytes=0 bytes_per_second=9.3959k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time_cv 0.12 % 0.06 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time 262593 ns 528757 ns 2674 bytes=4.096k bytes_per_second=14.8757M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time 262497 ns 528340 ns 2674 bytes=4.096k bytes_per_second=14.8811M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time 262032 ns 528811 ns 2674 bytes=4.096k bytes_per_second=14.9075M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time 261848 ns 528313 ns 2674 bytes=4.096k bytes_per_second=14.918M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time 262567 ns 528747 ns 2674 bytes=4.096k bytes_per_second=14.8772M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time_mean 262307 ns 528593 ns 5 bytes=4.096k bytes_per_second=14.8919M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time_median 262497 ns 528747 ns 5 bytes=4.096k bytes_per_second=14.8811M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time_stddev 343 ns 245 ns 5 bytes=0 bytes_per_second=19.9749k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time_cv 0.13 % 0.05 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time 264158 ns 532241 ns 2673 bytes=8.192k bytes_per_second=29.5751M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time 264373 ns 532317 ns 2673 bytes=8.192k bytes_per_second=29.5511M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time 263473 ns 531974 ns 2673 bytes=8.192k bytes_per_second=29.652M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time 264091 ns 531932 ns 2673 bytes=8.192k bytes_per_second=29.5826M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time 264216 ns 531616 ns 2673 bytes=8.192k bytes_per_second=29.5687M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time_mean 264062 ns 532016 ns 5 bytes=8.192k bytes_per_second=29.5859M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time_median 264158 ns 531974 ns 5 bytes=8.192k bytes_per_second=29.5751M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time_stddev 345 ns 278 ns 5 bytes=0 bytes_per_second=39.661k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time_cv 0.13 % 0.05 % 5 bytes=0.00% bytes_per_second=0.13% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time 267128 ns 537971 ns 2642 bytes=16.384k bytes_per_second=58.4925M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time 267190 ns 538186 ns 2642 bytes=16.384k bytes_per_second=58.4791M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time 266626 ns 538118 ns 2642 bytes=16.384k bytes_per_second=58.6027M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time 267424 ns 538293 ns 2642 bytes=16.384k bytes_per_second=58.4278M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time 267109 ns 537698 ns 2642 bytes=16.384k bytes_per_second=58.4967M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time_mean 267095 ns 538053 ns 5 bytes=16.384k bytes_per_second=58.4998M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time_median 267128 ns 538118 ns 5 bytes=16.384k bytes_per_second=58.4925M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time_stddev 291 ns 230 ns 5 bytes=0 bytes_per_second=65.2684k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time_cv 0.11 % 0.04 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time 271179 ns 545933 ns 2603 bytes=32.768k bytes_per_second=115.238M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time 271427 ns 546330 ns 2603 bytes=32.768k bytes_per_second=115.132M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time 270879 ns 546052 ns 2603 bytes=32.768k bytes_per_second=115.365M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time 270759 ns 545966 ns 2603 bytes=32.768k bytes_per_second=115.416M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time 271347 ns 546261 ns 2603 bytes=32.768k bytes_per_second=115.166M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time_mean 271118 ns 546108 ns 5 bytes=32.768k bytes_per_second=115.263M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time_median 271179 ns 546052 ns 5 bytes=32.768k bytes_per_second=115.238M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time_stddev 291 ns 178 ns 5 bytes=0 bytes_per_second=126.509k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time_cv 0.11 % 0.03 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time 280263 ns 563452 ns 2505 bytes=65.536k bytes_per_second=223.005M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time 279228 ns 562999 ns 2505 bytes=65.536k bytes_per_second=223.831M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time 280237 ns 564092 ns 2505 bytes=65.536k bytes_per_second=223.026M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time 279351 ns 563464 ns 2505 bytes=65.536k bytes_per_second=223.733M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time 280014 ns 563289 ns 2505 bytes=65.536k bytes_per_second=223.203M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time_mean 279818 ns 563459 ns 5 bytes=65.536k bytes_per_second=223.36M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time_median 280014 ns 563452 ns 5 bytes=65.536k bytes_per_second=223.203M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time_stddev 495 ns 400 ns 5 bytes=0 bytes_per_second=404.418k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time_cv 0.18 % 0.07 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time 299154 ns 597235 ns 2353 bytes=131.072k bytes_per_second=417.845M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time 296948 ns 597060 ns 2353 bytes=131.072k bytes_per_second=420.949M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time 296449 ns 596812 ns 2353 bytes=131.072k bytes_per_second=421.658M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time 299048 ns 597398 ns 2353 bytes=131.072k bytes_per_second=417.994M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time 296583 ns 596391 ns 2353 bytes=131.072k bytes_per_second=421.467M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time_mean 297636 ns 596979 ns 5 bytes=131.072k bytes_per_second=419.982M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time_median 296948 ns 597060 ns 5 bytes=131.072k bytes_per_second=420.949M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time_stddev 1350 ns 394 ns 5 bytes=0 bytes_per_second=1.90198M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time_cv 0.45 % 0.07 % 5 bytes=0.00% bytes_per_second=0.45% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time 328542 ns 661067 ns 2131 bytes=262.144k bytes_per_second=760.937M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time 328358 ns 661507 ns 2131 bytes=262.144k bytes_per_second=761.365M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time 328469 ns 661502 ns 2131 bytes=262.144k bytes_per_second=761.106M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time 328974 ns 661103 ns 2131 bytes=262.144k bytes_per_second=759.939M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time 328190 ns 661013 ns 2131 bytes=262.144k bytes_per_second=761.753M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time_mean 328507 ns 661238 ns 5 bytes=262.144k bytes_per_second=761.02M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time_median 328469 ns 661103 ns 5 bytes=262.144k bytes_per_second=761.106M/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time_stddev 293 ns 245 ns 5 bytes=0 bytes_per_second=694.549k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time_cv 0.09 % 0.04 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time 392595 ns 789524 ns 1780 bytes=524.288k bytes_per_second=1.24373G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time 394258 ns 793014 ns 1780 bytes=524.288k bytes_per_second=1.23848G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time 394696 ns 793418 ns 1780 bytes=524.288k bytes_per_second=1.23711G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time 394840 ns 794055 ns 1780 bytes=524.288k bytes_per_second=1.23666G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time 392641 ns 789727 ns 1780 bytes=524.288k bytes_per_second=1.24358G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time_mean 393806 ns 791947 ns 5 bytes=524.288k bytes_per_second=1.23991G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time_median 394258 ns 793014 ns 5 bytes=524.288k bytes_per_second=1.23848G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time_stddev 1106 ns 2153 ns 5 bytes=0 bytes_per_second=3.56736M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time_cv 0.28 % 0.27 % 5 bytes=0.00% bytes_per_second=0.28% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time 533706 ns 1068728 ns 1282 bytes=1048.58k bytes_per_second=1.82978G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time 535487 ns 1068859 ns 1282 bytes=1048.58k bytes_per_second=1.82369G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time 533684 ns 1068563 ns 1282 bytes=1048.58k bytes_per_second=1.82985G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time 536081 ns 1070069 ns 1282 bytes=1048.58k bytes_per_second=1.82167G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time 533637 ns 1068853 ns 1282 bytes=1048.58k bytes_per_second=1.83001G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time_mean 534519 ns 1069014 ns 5 bytes=1048.58k bytes_per_second=1.827G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time_median 533706 ns 1068853 ns 5 bytes=1048.58k bytes_per_second=1.82978G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time_stddev 1174 ns 602 ns 5 bytes=0 bytes_per_second=4.10613M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time_cv 0.22 % 0.06 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time 774618 ns 1552421 ns 902 bytes=2.09715M bytes_per_second=2.5214G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time 773667 ns 1551253 ns 902 bytes=2.09715M bytes_per_second=2.5245G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time 774646 ns 1553449 ns 902 bytes=2.09715M bytes_per_second=2.52131G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time 774288 ns 1552164 ns 902 bytes=2.09715M bytes_per_second=2.52248G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time 773879 ns 1551802 ns 902 bytes=2.09715M bytes_per_second=2.52381G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time_mean 774220 ns 1552218 ns 5 bytes=2.09715M bytes_per_second=2.5227G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time_median 774288 ns 1552164 ns 5 bytes=2.09715M bytes_per_second=2.52248G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time_stddev 438 ns 816 ns 5 bytes=0 bytes_per_second=1.46151M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time_cv 0.06 % 0.05 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time 1333303 ns 2691135 ns 524 bytes=4.1943M bytes_per_second=2.92975G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time 1336233 ns 2696461 ns 524 bytes=4.1943M bytes_per_second=2.92333G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time 1337266 ns 2698539 ns 524 bytes=4.1943M bytes_per_second=2.92107G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time 1334289 ns 2692174 ns 524 bytes=4.1943M bytes_per_second=2.92759G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time 1333959 ns 2691712 ns 524 bytes=4.1943M bytes_per_second=2.92831G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time_mean 1335010 ns 2694004 ns 5 bytes=4.1943M bytes_per_second=2.92601G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time_median 1334289 ns 2692174 ns 5 bytes=4.1943M bytes_per_second=2.92759G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time_stddev 1668 ns 3295 ns 5 bytes=0 bytes_per_second=3.74096M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time_cv 0.12 % 0.12 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time 2499653 ns 5026204 ns 280 bytes=8.38861M bytes_per_second=3.12543G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time 2532326 ns 5086091 ns 280 bytes=8.38861M bytes_per_second=3.08511G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time 2530140 ns 5083444 ns 280 bytes=8.38861M bytes_per_second=3.08777G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time 2532136 ns 5085249 ns 280 bytes=8.38861M bytes_per_second=3.08534G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time 2529651 ns 5083927 ns 280 bytes=8.38861M bytes_per_second=3.08837G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time_mean 2524781 ns 5072983 ns 5 bytes=8.38861M bytes_per_second=3.09441G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time_median 2530140 ns 5083927 ns 5 bytes=8.38861M bytes_per_second=3.08777G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time_stddev 14097 ns 26171 ns 5 bytes=0 bytes_per_second=17.8228M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time_cv 0.56 % 0.52 % 5 bytes=0.00% bytes_per_second=0.56% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time 4888745 ns 9774244 ns 143 bytes=16.7772M bytes_per_second=3.19612G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time 4886717 ns 9775684 ns 143 bytes=16.7772M bytes_per_second=3.19744G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time 4890038 ns 9778969 ns 143 bytes=16.7772M bytes_per_second=3.19527G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time 4890563 ns 9783613 ns 143 bytes=16.7772M bytes_per_second=3.19493G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time 4885379 ns 9776509 ns 143 bytes=16.7772M bytes_per_second=3.19832G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time_mean 4888288 ns 9777804 ns 5 bytes=16.7772M bytes_per_second=3.19642G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time_median 4888745 ns 9776509 ns 5 bytes=16.7772M bytes_per_second=3.19612G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time_stddev 2201 ns 3673 ns 5 bytes=0 bytes_per_second=1.47388M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time_cv 0.05 % 0.04 % 5 bytes=0.00% bytes_per_second=0.05% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time 9606140 ns 19146058 ns 72 bytes=33.5544M bytes_per_second=3.25313G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time 9604776 ns 19133488 ns 72 bytes=33.5544M bytes_per_second=3.25359G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time 9621576 ns 19153397 ns 72 bytes=33.5544M bytes_per_second=3.24791G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time 9609167 ns 19141139 ns 72 bytes=33.5544M bytes_per_second=3.2521G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time 9608840 ns 19142190 ns 72 bytes=33.5544M bytes_per_second=3.25221G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time_mean 9610100 ns 19143254 ns 5 bytes=33.5544M bytes_per_second=3.25179G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time_median 9608840 ns 19142190 ns 5 bytes=33.5544M bytes_per_second=3.25221G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time_stddev 6674 ns 7275 ns 5 bytes=0 bytes_per_second=2.31084M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time_cv 0.07 % 0.04 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time 20629645 ns 41014665 ns 34 bytes=67.1089M bytes_per_second=3.02962G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time 20510393 ns 40887099 ns 34 bytes=67.1089M bytes_per_second=3.04724G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time 20542920 ns 40919712 ns 34 bytes=67.1089M bytes_per_second=3.04241G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time 20581217 ns 40949044 ns 34 bytes=67.1089M bytes_per_second=3.03675G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time 20591363 ns 40980868 ns 34 bytes=67.1089M bytes_per_second=3.03525G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time_mean 20571107 ns 40950278 ns 5 bytes=67.1089M bytes_per_second=3.03825G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time_median 20581217 ns 40949044 ns 5 bytes=67.1089M bytes_per_second=3.03675G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time_stddev 45880 ns 50022 ns 5 bytes=0 bytes_per_second=6.9404M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time_cv 0.22 % 0.12 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time 37948468 ns 75104685 ns 18 bytes=134.218M bytes_per_second=3.29394G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time 37882762 ns 74784476 ns 18 bytes=134.218M bytes_per_second=3.29965G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time 37798263 ns 74877013 ns 18 bytes=134.218M bytes_per_second=3.30703G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time 37883686 ns 74935605 ns 18 bytes=134.218M bytes_per_second=3.29957G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time 37976041 ns 75170267 ns 18 bytes=134.218M bytes_per_second=3.29155G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time_mean 37897844 ns 74974409 ns 5 bytes=134.218M bytes_per_second=3.29835G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time_median 37883686 ns 74935605 ns 5 bytes=134.218M bytes_per_second=3.29957G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time_stddev 68960 ns 159999 ns 5 bytes=0 bytes_per_second=6.14912M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time_cv 0.18 % 0.21 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time 75686483 ns 147428402 ns 9 bytes=268.435M bytes_per_second=3.3031G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time 75437343 ns 147153834 ns 9 bytes=268.435M bytes_per_second=3.31401G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time 75528900 ns 147320133 ns 9 bytes=268.435M bytes_per_second=3.30999G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time 75280667 ns 146880657 ns 9 bytes=268.435M bytes_per_second=3.32091G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time 75222993 ns 146723616 ns 9 bytes=268.435M bytes_per_second=3.32345G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time_mean 75431277 ns 147101328 ns 5 bytes=268.435M bytes_per_second=3.31429G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time_median 75437343 ns 147153834 ns 5 bytes=268.435M bytes_per_second=3.31401G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time_stddev 187592 ns 295369 ns 5 bytes=0 bytes_per_second=8.43619M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time_cv 0.25 % 0.20 % 5 bytes=0.00% bytes_per_second=0.25% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time 147940814 ns 282332373 ns 5 bytes=536.871M bytes_per_second=3.37973G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time 147883305 ns 282618073 ns 5 bytes=536.871M bytes_per_second=3.38104G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time 147635344 ns 282064012 ns 5 bytes=536.871M bytes_per_second=3.38672G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time 148122409 ns 282774166 ns 5 bytes=536.871M bytes_per_second=3.37559G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time 147774851 ns 282572495 ns 5 bytes=536.871M bytes_per_second=3.38353G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time_mean 147871345 ns 282472224 ns 5 bytes=536.871M bytes_per_second=3.38132G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time_median 147883305 ns 282572495 ns 5 bytes=536.871M bytes_per_second=3.38104G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time_stddev 182353 ns 277799 ns 5 bytes=0 bytes_per_second=4.26941M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time_cv 0.12 % 0.10 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time 289114565 ns 515224241 ns 2 bytes=1073.74M bytes_per_second=3.45884G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time 287977666 ns 513862864 ns 2 bytes=1073.74M bytes_per_second=3.47249G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time 287747517 ns 513873502 ns 2 bytes=1073.74M bytes_per_second=3.47527G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time 288838640 ns 514733405 ns 2 bytes=1073.74M bytes_per_second=3.46214G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time 289012417 ns 515356359 ns 2 bytes=1073.74M bytes_per_second=3.46006G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time_mean 288538161 ns 514610074 ns 5 bytes=1073.74M bytes_per_second=3.46576G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time_median 288838640 ns 514733405 ns 5 bytes=1073.74M bytes_per_second=3.46214G/s dst_gpu=4 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time_stddev 629825 ns 715928 ns 5 bytes=0 bytes_per_second=7.75252M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time_cv 0.22 % 0.14 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time 259763 ns 521546 ns 2697 bytes=1024 bytes_per_second=3.75944M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time 259185 ns 521254 ns 2697 bytes=1024 bytes_per_second=3.76782M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time 260000 ns 521418 ns 2697 bytes=1024 bytes_per_second=3.75601M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time 259648 ns 520976 ns 2697 bytes=1024 bytes_per_second=3.76109M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time 259094 ns 521224 ns 2697 bytes=1024 bytes_per_second=3.76914M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time_mean 259538 ns 521284 ns 5 bytes=1024 bytes_per_second=3.7627M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time_median 259648 ns 521254 ns 5 bytes=1024 bytes_per_second=3.76109M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time_stddev 386 ns 216 ns 5 bytes=0 bytes_per_second=5.73748k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time_cv 0.15 % 0.04 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time 258974 ns 521374 ns 2692 bytes=2.048k bytes_per_second=7.54178M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time 259138 ns 520642 ns 2692 bytes=2.048k bytes_per_second=7.53702M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time 259812 ns 521341 ns 2692 bytes=2.048k bytes_per_second=7.51746M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time 259514 ns 521125 ns 2692 bytes=2.048k bytes_per_second=7.52607M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time 258972 ns 521231 ns 2692 bytes=2.048k bytes_per_second=7.54184M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time_mean 259282 ns 521143 ns 5 bytes=2.048k bytes_per_second=7.53283M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time_median 259138 ns 521231 ns 5 bytes=2.048k bytes_per_second=7.53702M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time_stddev 370 ns 297 ns 5 bytes=0 bytes_per_second=10.988k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time_cv 0.14 % 0.06 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time 259174 ns 521150 ns 2693 bytes=4.096k bytes_per_second=15.0719M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time 259719 ns 521135 ns 2693 bytes=4.096k bytes_per_second=15.0403M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time 259644 ns 521123 ns 2693 bytes=4.096k bytes_per_second=15.0446M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time 259086 ns 521477 ns 2693 bytes=4.096k bytes_per_second=15.077M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time 259748 ns 521153 ns 2693 bytes=4.096k bytes_per_second=15.0386M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time_mean 259474 ns 521208 ns 5 bytes=4.096k bytes_per_second=15.0545M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time_median 259644 ns 521150 ns 5 bytes=4.096k bytes_per_second=15.0446M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time_stddev 318 ns 151 ns 5 bytes=0 bytes_per_second=18.8977k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time_cv 0.12 % 0.03 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time 261539 ns 524730 ns 2673 bytes=8.192k bytes_per_second=29.8713M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time 262195 ns 524836 ns 2673 bytes=8.192k bytes_per_second=29.7966M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time 262138 ns 524821 ns 2673 bytes=8.192k bytes_per_second=29.8031M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time 261591 ns 524712 ns 2673 bytes=8.192k bytes_per_second=29.8653M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time 261382 ns 523912 ns 2673 bytes=8.192k bytes_per_second=29.8892M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time_mean 261769 ns 524602 ns 5 bytes=8.192k bytes_per_second=29.8451M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time_median 261591 ns 524730 ns 5 bytes=8.192k bytes_per_second=29.8653M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time_stddev 371 ns 390 ns 5 bytes=0 bytes_per_second=43.33k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time_cv 0.14 % 0.07 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time 264100 ns 530111 ns 2649 bytes=16.384k bytes_per_second=59.1633M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time 264714 ns 530033 ns 2649 bytes=16.384k bytes_per_second=59.0259M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time 264874 ns 530185 ns 2649 bytes=16.384k bytes_per_second=58.9903M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time 264086 ns 529637 ns 2649 bytes=16.384k bytes_per_second=59.1663M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time 264289 ns 529469 ns 2649 bytes=16.384k bytes_per_second=59.1208M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time_mean 264413 ns 529887 ns 5 bytes=16.384k bytes_per_second=59.0933M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time_median 264289 ns 530033 ns 5 bytes=16.384k bytes_per_second=59.1208M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time_stddev 362 ns 315 ns 5 bytes=0 bytes_per_second=82.7799k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time_cv 0.14 % 0.06 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time 268680 ns 538270 ns 2605 bytes=32.768k bytes_per_second=116.31M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time 269285 ns 538985 ns 2605 bytes=32.768k bytes_per_second=116.048M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time 269127 ns 538731 ns 2605 bytes=32.768k bytes_per_second=116.116M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time 267739 ns 538110 ns 2605 bytes=32.768k bytes_per_second=116.718M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time 268227 ns 538360 ns 2605 bytes=32.768k bytes_per_second=116.506M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time_mean 268611 ns 538491 ns 5 bytes=32.768k bytes_per_second=116.34M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time_median 268680 ns 538360 ns 5 bytes=32.768k bytes_per_second=116.31M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time_stddev 639 ns 358 ns 5 bytes=0 bytes_per_second=283.534k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time_cv 0.24 % 0.07 % 5 bytes=0.00% bytes_per_second=0.24% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time 276545 ns 555850 ns 2519 bytes=65.536k bytes_per_second=226.003M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time 277302 ns 556546 ns 2519 bytes=65.536k bytes_per_second=225.386M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time 276698 ns 555877 ns 2519 bytes=65.536k bytes_per_second=225.878M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time 277516 ns 556530 ns 2519 bytes=65.536k bytes_per_second=225.213M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time 276786 ns 555965 ns 2519 bytes=65.536k bytes_per_second=225.806M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time_mean 276970 ns 556154 ns 5 bytes=65.536k bytes_per_second=225.657M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time_median 276786 ns 555965 ns 5 bytes=65.536k bytes_per_second=225.806M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time_stddev 417 ns 354 ns 5 bytes=0 bytes_per_second=347.916k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time_cv 0.15 % 0.06 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time 292668 ns 589189 ns 2364 bytes=131.072k bytes_per_second=427.105M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time 296078 ns 589689 ns 2364 bytes=131.072k bytes_per_second=422.186M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time 293013 ns 589070 ns 2364 bytes=131.072k bytes_per_second=426.603M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time 292707 ns 589363 ns 2364 bytes=131.072k bytes_per_second=427.048M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time 295475 ns 588939 ns 2364 bytes=131.072k bytes_per_second=423.047M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time_mean 293988 ns 589250 ns 5 bytes=131.072k bytes_per_second=425.198M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time_median 293013 ns 589189 ns 5 bytes=131.072k bytes_per_second=426.603M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time_stddev 1652 ns 291 ns 5 bytes=0 bytes_per_second=2.38402M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time_cv 0.56 % 0.05 % 5 bytes=0.00% bytes_per_second=0.56% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time 324846 ns 652875 ns 2149 bytes=262.144k bytes_per_second=769.595M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time 324552 ns 653130 ns 2149 bytes=262.144k bytes_per_second=770.292M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time 325190 ns 652846 ns 2149 bytes=262.144k bytes_per_second=768.781M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time 325143 ns 653431 ns 2149 bytes=262.144k bytes_per_second=768.891M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time 324922 ns 653180 ns 2149 bytes=262.144k bytes_per_second=769.416M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time_mean 324931 ns 653092 ns 5 bytes=262.144k bytes_per_second=769.395M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time_median 324922 ns 653130 ns 5 bytes=262.144k bytes_per_second=769.416M/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time_stddev 256 ns 241 ns 5 bytes=0 bytes_per_second=621.965k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time_cv 0.08 % 0.04 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time 389507 ns 782519 ns 1799 bytes=524.288k bytes_per_second=1.25359G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time 389782 ns 782622 ns 1799 bytes=524.288k bytes_per_second=1.2527G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time 389175 ns 781893 ns 1799 bytes=524.288k bytes_per_second=1.25466G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time 389029 ns 781578 ns 1799 bytes=524.288k bytes_per_second=1.25513G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time 389370 ns 781793 ns 1799 bytes=524.288k bytes_per_second=1.25403G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time_mean 389373 ns 782081 ns 5 bytes=524.288k bytes_per_second=1.25402G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time_median 389370 ns 781893 ns 5 bytes=524.288k bytes_per_second=1.25403G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time_stddev 293 ns 463 ns 5 bytes=0 bytes_per_second=988.081k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time_cv 0.08 % 0.06 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time 531602 ns 1059940 ns 1311 bytes=1048.58k bytes_per_second=1.83702G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time 528257 ns 1059301 ns 1311 bytes=1048.58k bytes_per_second=1.84865G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time 531205 ns 1059861 ns 1311 bytes=1048.58k bytes_per_second=1.83839G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time 528538 ns 1059787 ns 1311 bytes=1048.58k bytes_per_second=1.84767G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time 531334 ns 1059806 ns 1311 bytes=1048.58k bytes_per_second=1.83794G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time_mean 530187 ns 1059739 ns 5 bytes=1048.58k bytes_per_second=1.84193G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time_median 531205 ns 1059806 ns 5 bytes=1048.58k bytes_per_second=1.83839G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time_stddev 1643 ns 252 ns 5 bytes=0 bytes_per_second=5.85189M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time_cv 0.31 % 0.02 % 5 bytes=0.00% bytes_per_second=0.31% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time 770302 ns 1543963 ns 905 bytes=2.09715M bytes_per_second=2.53553G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time 769994 ns 1547752 ns 905 bytes=2.09715M bytes_per_second=2.53654G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time 769759 ns 1543394 ns 905 bytes=2.09715M bytes_per_second=2.53732G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time 770247 ns 1543980 ns 905 bytes=2.09715M bytes_per_second=2.53571G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time 770051 ns 1543955 ns 905 bytes=2.09715M bytes_per_second=2.53636G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time_mean 770071 ns 1544609 ns 5 bytes=2.09715M bytes_per_second=2.53629G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time_median 770051 ns 1543963 ns 5 bytes=2.09715M bytes_per_second=2.53636G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time_stddev 217 ns 1775 ns 5 bytes=0 bytes_per_second=748.45k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time_cv 0.03 % 0.11 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time 1329246 ns 2680954 ns 526 bytes=4.1943M bytes_per_second=2.9387G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time 1328340 ns 2681725 ns 526 bytes=4.1943M bytes_per_second=2.9407G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time 1329585 ns 2681033 ns 526 bytes=4.1943M bytes_per_second=2.93795G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time 1330319 ns 2682607 ns 526 bytes=4.1943M bytes_per_second=2.93632G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time 1329477 ns 2682038 ns 526 bytes=4.1943M bytes_per_second=2.93819G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time_mean 1329393 ns 2681672 ns 5 bytes=4.1943M bytes_per_second=2.93837G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time_median 1329477 ns 2681725 ns 5 bytes=4.1943M bytes_per_second=2.93819G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time_stddev 713 ns 696 ns 5 bytes=0 bytes_per_second=1.61375M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time_cv 0.05 % 0.03 % 5 bytes=0.00% bytes_per_second=0.05% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time 2531782 ns 5096527 ns 278 bytes=8.38861M bytes_per_second=3.08577G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time 2539519 ns 5096752 ns 278 bytes=8.38861M bytes_per_second=3.07637G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time 2533118 ns 5098624 ns 278 bytes=8.38861M bytes_per_second=3.08414G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time 2540742 ns 5099095 ns 278 bytes=8.38861M bytes_per_second=3.07489G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time 2532278 ns 5097577 ns 278 bytes=8.38861M bytes_per_second=3.08517G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time_mean 2535488 ns 5097715 ns 5 bytes=8.38861M bytes_per_second=3.08127G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time_median 2533118 ns 5097577 ns 5 bytes=8.38861M bytes_per_second=3.08414G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time_stddev 4287 ns 1128 ns 5 bytes=0 bytes_per_second=5.33163M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time_cv 0.17 % 0.02 % 5 bytes=0.00% bytes_per_second=0.17% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time 5006286 ns 9982046 ns 139 bytes=16.7772M bytes_per_second=3.12108G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time 5009541 ns 9984304 ns 139 bytes=16.7772M bytes_per_second=3.11905G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time 5006696 ns 9985398 ns 139 bytes=16.7772M bytes_per_second=3.12082G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time 5004783 ns 9981595 ns 139 bytes=16.7772M bytes_per_second=3.12201G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time 5009707 ns 9984932 ns 139 bytes=16.7772M bytes_per_second=3.11894G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time_mean 5007403 ns 9983655 ns 5 bytes=16.7772M bytes_per_second=3.12038G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time_median 5006696 ns 9984304 ns 5 bytes=16.7772M bytes_per_second=3.12082G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time_stddev 2150 ns 1726 ns 5 bytes=0 bytes_per_second=1.37207M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time_cv 0.04 % 0.02 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time 9857039 ns 19678459 ns 70 bytes=33.5544M bytes_per_second=3.17032G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time 9909965 ns 19696222 ns 70 bytes=33.5544M bytes_per_second=3.15339G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time 9883851 ns 19675551 ns 70 bytes=33.5544M bytes_per_second=3.16172G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time 9901782 ns 19713525 ns 70 bytes=33.5544M bytes_per_second=3.156G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time 9901211 ns 19685132 ns 70 bytes=33.5544M bytes_per_second=3.15618G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time_mean 9890770 ns 19689778 ns 5 bytes=33.5544M bytes_per_second=3.15952G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time_median 9901211 ns 19685132 ns 5 bytes=33.5544M bytes_per_second=3.15618G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time_stddev 21121 ns 15472 ns 5 bytes=0 bytes_per_second=6.92029M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time_cv 0.21 % 0.08 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time 21216636 ns 42097313 ns 33 bytes=67.1089M bytes_per_second=2.9458G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time 21234958 ns 42337536 ns 33 bytes=67.1089M bytes_per_second=2.94326G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time 21192151 ns 42153443 ns 33 bytes=67.1089M bytes_per_second=2.94921G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time 21252845 ns 42343650 ns 33 bytes=67.1089M bytes_per_second=2.94078G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time 21282687 ns 42431075 ns 33 bytes=67.1089M bytes_per_second=2.93666G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time_mean 21235856 ns 42272603 ns 5 bytes=67.1089M bytes_per_second=2.94314G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time_median 21234958 ns 42337536 ns 5 bytes=67.1089M bytes_per_second=2.94326G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time_stddev 34504 ns 140804 ns 5 bytes=0 bytes_per_second=4.89597M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time_cv 0.16 % 0.33 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time 39362040 ns 77649588 ns 18 bytes=134.218M bytes_per_second=3.17565G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time 39342004 ns 77552584 ns 18 bytes=134.218M bytes_per_second=3.17727G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time 39345427 ns 77581708 ns 18 bytes=134.218M bytes_per_second=3.17699G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time 39334076 ns 77491898 ns 18 bytes=134.218M bytes_per_second=3.17791G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time 39381703 ns 77650627 ns 18 bytes=134.218M bytes_per_second=3.17406G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time_mean 39353050 ns 77585281 ns 5 bytes=134.218M bytes_per_second=3.17637G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time_median 39345427 ns 77581708 ns 5 bytes=134.218M bytes_per_second=3.17699G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time_stddev 18987 ns 67468 ns 5 bytes=0 bytes_per_second=1.56885M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time_cv 0.05 % 0.09 % 5 bytes=0.00% bytes_per_second=0.05% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time 75541587 ns 147623111 ns 9 bytes=268.435M bytes_per_second=3.30944G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time 75589852 ns 147544247 ns 9 bytes=268.435M bytes_per_second=3.30732G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time 75746831 ns 147716494 ns 9 bytes=268.435M bytes_per_second=3.30047G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time 75536019 ns 147528830 ns 9 bytes=268.435M bytes_per_second=3.30968G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time 75571504 ns 147451794 ns 9 bytes=268.435M bytes_per_second=3.30813G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time_mean 75597159 ns 147572895 ns 5 bytes=268.435M bytes_per_second=3.30701G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time_median 75571504 ns 147544247 ns 5 bytes=268.435M bytes_per_second=3.30813G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time_stddev 86515 ns 100710 ns 5 bytes=0 bytes_per_second=3.87044M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time_cv 0.11 % 0.07 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time 148370045 ns 283444016 ns 5 bytes=536.871M bytes_per_second=3.36995G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time 148248002 ns 283214668 ns 5 bytes=536.871M bytes_per_second=3.37273G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time 148524225 ns 283133481 ns 5 bytes=536.871M bytes_per_second=3.36645G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time 148475233 ns 283376579 ns 5 bytes=536.871M bytes_per_second=3.36757G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time 148239806 ns 282897741 ns 5 bytes=536.871M bytes_per_second=3.37291G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time_mean 148371462 ns 283213297 ns 5 bytes=536.871M bytes_per_second=3.36992G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time_median 148370045 ns 283214668 ns 5 bytes=536.871M bytes_per_second=3.36995G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time_stddev 129115 ns 215546 ns 5 bytes=0 bytes_per_second=3.00277M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time_cv 0.09 % 0.08 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time 291707411 ns 517862006 ns 2 bytes=1073.74M bytes_per_second=3.42809G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time 290567428 ns 517382236 ns 2 bytes=1073.74M bytes_per_second=3.44154G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time 290549099 ns 517164043 ns 2 bytes=1073.74M bytes_per_second=3.44176G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time 291001260 ns 517874500 ns 2 bytes=1073.74M bytes_per_second=3.43641G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time 291086301 ns 517940649 ns 2 bytes=1073.74M bytes_per_second=3.43541G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time_mean 290982300 ns 517644687 ns 5 bytes=1073.74M bytes_per_second=3.43664G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time_median 291001260 ns 517862006 ns 5 bytes=1073.74M bytes_per_second=3.43641G/s dst_gpu=5 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time_stddev 473483 ns 349118 ns 5 bytes=0 bytes_per_second=5.72125M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time_cv 0.16 % 0.07 % 5 bytes=0.00% bytes_per_second=0.16% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time 264955 ns 531214 ns 2645 bytes=1024 bytes_per_second=3.68576M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time 264823 ns 531063 ns 2645 bytes=1024 bytes_per_second=3.68761M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time 264567 ns 530788 ns 2645 bytes=1024 bytes_per_second=3.69117M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time 264194 ns 529732 ns 2645 bytes=1024 bytes_per_second=3.69639M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time 264356 ns 530566 ns 2645 bytes=1024 bytes_per_second=3.69411M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time_mean 264579 ns 530672 ns 5 bytes=1024 bytes_per_second=3.69101M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time_median 264567 ns 530788 ns 5 bytes=1024 bytes_per_second=3.69117M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time_stddev 316 ns 582 ns 5 bytes=0 bytes_per_second=4.51393k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time_cv 0.12 % 0.11 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time 265432 ns 530821 ns 2646 bytes=2.048k bytes_per_second=7.35828M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time 265670 ns 531083 ns 2646 bytes=2.048k bytes_per_second=7.35169M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time 264188 ns 531220 ns 2646 bytes=2.048k bytes_per_second=7.39294M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time 264711 ns 529930 ns 2646 bytes=2.048k bytes_per_second=7.37833M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time 263606 ns 530254 ns 2646 bytes=2.048k bytes_per_second=7.40925M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time_mean 264721 ns 530662 ns 5 bytes=2.048k bytes_per_second=7.3781M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time_median 264711 ns 530821 ns 5 bytes=2.048k bytes_per_second=7.37833M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time_stddev 857 ns 551 ns 5 bytes=0 bytes_per_second=24.456k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time_cv 0.32 % 0.10 % 5 bytes=0.00% bytes_per_second=0.32% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time 264828 ns 530256 ns 2653 bytes=4.096k bytes_per_second=14.7502M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time 265865 ns 531201 ns 2653 bytes=4.096k bytes_per_second=14.6926M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time 264317 ns 530323 ns 2653 bytes=4.096k bytes_per_second=14.7787M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time 264199 ns 529503 ns 2653 bytes=4.096k bytes_per_second=14.7853M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time 263656 ns 530134 ns 2653 bytes=4.096k bytes_per_second=14.8157M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time_mean 264573 ns 530283 ns 5 bytes=4.096k bytes_per_second=14.7645M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time_median 264317 ns 530256 ns 5 bytes=4.096k bytes_per_second=14.7787M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time_stddev 834 ns 607 ns 5 bytes=0 bytes_per_second=47.5592k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time_cv 0.32 % 0.11 % 5 bytes=0.00% bytes_per_second=0.31% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time 266285 ns 533382 ns 2648 bytes=8.192k bytes_per_second=29.3388M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time 266879 ns 533960 ns 2648 bytes=8.192k bytes_per_second=29.2735M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time 265629 ns 533770 ns 2648 bytes=8.192k bytes_per_second=29.4113M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time 266449 ns 533376 ns 2648 bytes=8.192k bytes_per_second=29.3208M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time 265076 ns 532065 ns 2648 bytes=8.192k bytes_per_second=29.4727M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time_mean 266064 ns 533311 ns 5 bytes=8.192k bytes_per_second=29.3634M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time_median 266285 ns 533382 ns 5 bytes=8.192k bytes_per_second=29.3388M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time_stddev 712 ns 741 ns 5 bytes=0 bytes_per_second=80.5199k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time_cv 0.27 % 0.14 % 5 bytes=0.00% bytes_per_second=0.27% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time 269212 ns 539169 ns 2609 bytes=16.384k bytes_per_second=58.0397M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time 269314 ns 539189 ns 2609 bytes=16.384k bytes_per_second=58.0177M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time 268700 ns 539351 ns 2609 bytes=16.384k bytes_per_second=58.1503M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time 267759 ns 538267 ns 2609 bytes=16.384k bytes_per_second=58.3547M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time 268629 ns 539117 ns 2609 bytes=16.384k bytes_per_second=58.1658M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time_mean 268723 ns 539019 ns 5 bytes=16.384k bytes_per_second=58.1456M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time_median 268700 ns 539169 ns 5 bytes=16.384k bytes_per_second=58.1503M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time_stddev 618 ns 429 ns 5 bytes=0 bytes_per_second=137.093k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time_cv 0.23 % 0.08 % 5 bytes=0.00% bytes_per_second=0.23% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time 272768 ns 546689 ns 2564 bytes=32.768k bytes_per_second=114.566M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time 272342 ns 546956 ns 2564 bytes=32.768k bytes_per_second=114.745M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time 272907 ns 547505 ns 2564 bytes=32.768k bytes_per_second=114.508M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time 272299 ns 547599 ns 2564 bytes=32.768k bytes_per_second=114.763M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time 272748 ns 547337 ns 2564 bytes=32.768k bytes_per_second=114.575M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time_mean 272613 ns 547217 ns 5 bytes=32.768k bytes_per_second=114.631M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time_median 272748 ns 547337 ns 5 bytes=32.768k bytes_per_second=114.575M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time_stddev 274 ns 384 ns 5 bytes=0 bytes_per_second=117.981k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time_cv 0.10 % 0.07 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time 280979 ns 565224 ns 2499 bytes=65.536k bytes_per_second=222.437M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time 281690 ns 564538 ns 2499 bytes=65.536k bytes_per_second=221.875M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time 281517 ns 564063 ns 2499 bytes=65.536k bytes_per_second=222.011M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time 282361 ns 564886 ns 2499 bytes=65.536k bytes_per_second=221.348M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time 281003 ns 564481 ns 2499 bytes=65.536k bytes_per_second=222.417M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time_mean 281510 ns 564639 ns 5 bytes=65.536k bytes_per_second=222.018M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time_median 281517 ns 564538 ns 5 bytes=65.536k bytes_per_second=222.011M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time_stddev 569 ns 439 ns 5 bytes=0 bytes_per_second=459.189k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time_cv 0.20 % 0.08 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time 295270 ns 597830 ns 2372 bytes=131.072k bytes_per_second=423.341M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time 298052 ns 599165 ns 2372 bytes=131.072k bytes_per_second=419.39M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time 294920 ns 598823 ns 2372 bytes=131.072k bytes_per_second=423.844M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time 295127 ns 597549 ns 2372 bytes=131.072k bytes_per_second=423.547M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time 297851 ns 599023 ns 2372 bytes=131.072k bytes_per_second=419.672M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time_mean 296244 ns 598478 ns 5 bytes=131.072k bytes_per_second=421.959M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time_median 295270 ns 598823 ns 5 bytes=131.072k bytes_per_second=423.341M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time_stddev 1565 ns 737 ns 5 bytes=0 bytes_per_second=2.22559M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time_cv 0.53 % 0.12 % 5 bytes=0.00% bytes_per_second=0.53% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time 330219 ns 663083 ns 2117 bytes=262.144k bytes_per_second=757.073M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time 329707 ns 662532 ns 2117 bytes=262.144k bytes_per_second=758.248M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time 330410 ns 662794 ns 2117 bytes=262.144k bytes_per_second=756.636M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time 329546 ns 662539 ns 2117 bytes=262.144k bytes_per_second=758.619M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time 330192 ns 662686 ns 2117 bytes=262.144k bytes_per_second=757.135M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time_mean 330015 ns 662727 ns 5 bytes=262.144k bytes_per_second=757.542M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time_median 330192 ns 662686 ns 5 bytes=262.144k bytes_per_second=757.135M/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time_stddev 369 ns 227 ns 5 bytes=0 bytes_per_second=866.502k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time_cv 0.11 % 0.03 % 5 bytes=0.00% bytes_per_second=0.11% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time 393361 ns 790189 ns 1781 bytes=524.288k bytes_per_second=1.2413G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time 393438 ns 789946 ns 1781 bytes=524.288k bytes_per_second=1.24106G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time 395184 ns 793078 ns 1781 bytes=524.288k bytes_per_second=1.23558G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time 393409 ns 789933 ns 1781 bytes=524.288k bytes_per_second=1.24115G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time 393720 ns 790234 ns 1781 bytes=524.288k bytes_per_second=1.24017G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time_mean 393822 ns 790676 ns 5 bytes=524.288k bytes_per_second=1.23985G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time_median 393438 ns 790189 ns 5 bytes=524.288k bytes_per_second=1.24106G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time_stddev 774 ns 1350 ns 5 bytes=0 bytes_per_second=2.48873M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time_cv 0.20 % 0.17 % 5 bytes=0.00% bytes_per_second=0.20% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time 536447 ns 1069997 ns 1313 bytes=1048.58k bytes_per_second=1.82043G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time 533699 ns 1069789 ns 1313 bytes=1048.58k bytes_per_second=1.8298G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time 537302 ns 1071204 ns 1313 bytes=1048.58k bytes_per_second=1.81753G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time 534505 ns 1070807 ns 1313 bytes=1048.58k bytes_per_second=1.82704G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time 537229 ns 1071280 ns 1313 bytes=1048.58k bytes_per_second=1.81778G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time_mean 535836 ns 1070615 ns 5 bytes=1048.58k bytes_per_second=1.82252G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time_median 536447 ns 1070807 ns 5 bytes=1048.58k bytes_per_second=1.82043G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time_stddev 1643 ns 687 ns 5 bytes=0 bytes_per_second=5.72844M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time_cv 0.31 % 0.06 % 5 bytes=0.00% bytes_per_second=0.31% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time 776120 ns 1555608 ns 901 bytes=2.09715M bytes_per_second=2.51652G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time 775974 ns 1554840 ns 901 bytes=2.09715M bytes_per_second=2.517G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time 776163 ns 1554887 ns 901 bytes=2.09715M bytes_per_second=2.51638G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time 776359 ns 1555861 ns 901 bytes=2.09715M bytes_per_second=2.51575G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time 775146 ns 1553520 ns 901 bytes=2.09715M bytes_per_second=2.51969G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time_mean 775953 ns 1554943 ns 5 bytes=2.09715M bytes_per_second=2.51707G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time_median 776120 ns 1554887 ns 5 bytes=2.09715M bytes_per_second=2.51652G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time_stddev 471 ns 911 ns 5 bytes=0 bytes_per_second=1.56699M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time_cv 0.06 % 0.06 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time 1336513 ns 2695788 ns 523 bytes=4.1943M bytes_per_second=2.92272G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time 1337060 ns 2696829 ns 523 bytes=4.1943M bytes_per_second=2.92152G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time 1336773 ns 2696696 ns 523 bytes=4.1943M bytes_per_second=2.92215G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time 1336603 ns 2695942 ns 523 bytes=4.1943M bytes_per_second=2.92252G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time 1337810 ns 2696435 ns 523 bytes=4.1943M bytes_per_second=2.91988G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time_mean 1336952 ns 2696338 ns 5 bytes=4.1943M bytes_per_second=2.92176G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time_median 1336773 ns 2696435 ns 5 bytes=4.1943M bytes_per_second=2.92215G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time_stddev 523 ns 458 ns 5 bytes=0 bytes_per_second=1.17008M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time_cv 0.04 % 0.02 % 5 bytes=0.00% bytes_per_second=0.04% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time 2536440 ns 5080540 ns 277 bytes=8.38861M bytes_per_second=3.0801G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time 2524560 ns 5075090 ns 277 bytes=8.38861M bytes_per_second=3.0946G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time 2534139 ns 5075634 ns 277 bytes=8.38861M bytes_per_second=3.0829G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time 2526545 ns 5079393 ns 277 bytes=8.38861M bytes_per_second=3.09217G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time 2534698 ns 5077216 ns 277 bytes=8.38861M bytes_per_second=3.08222G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time_mean 2531276 ns 5077575 ns 5 bytes=8.38861M bytes_per_second=3.0864G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time_median 2534139 ns 5077216 ns 5 bytes=8.38861M bytes_per_second=3.0829G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time_stddev 5340 ns 2354 ns 5 bytes=0 bytes_per_second=6.67209M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time_cv 0.21 % 0.05 % 5 bytes=0.00% bytes_per_second=0.21% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time 5008205 ns 9977920 ns 139 bytes=16.7772M bytes_per_second=3.11988G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time 5008582 ns 9981536 ns 139 bytes=16.7772M bytes_per_second=3.11965G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time 5009589 ns 9979700 ns 139 bytes=16.7772M bytes_per_second=3.11902G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time 5000132 ns 9968159 ns 139 bytes=16.7772M bytes_per_second=3.12492G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time 5001176 ns 9968757 ns 139 bytes=16.7772M bytes_per_second=3.12427G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time_mean 5005537 ns 9975214 ns 5 bytes=16.7772M bytes_per_second=3.12155G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time_median 5008205 ns 9977920 ns 5 bytes=16.7772M bytes_per_second=3.11988G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time_stddev 4501 ns 6303 ns 5 bytes=0 bytes_per_second=2.87539M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time_cv 0.09 % 0.06 % 5 bytes=0.00% bytes_per_second=0.09% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time 9869404 ns 19702003 ns 70 bytes=33.5544M bytes_per_second=3.16635G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time 9887791 ns 19798466 ns 70 bytes=33.5544M bytes_per_second=3.16046G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time 9869221 ns 19777276 ns 70 bytes=33.5544M bytes_per_second=3.16641G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time 9878643 ns 19732947 ns 70 bytes=33.5544M bytes_per_second=3.16339G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time 9870943 ns 19741995 ns 70 bytes=33.5544M bytes_per_second=3.16586G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time_mean 9875201 ns 19750538 ns 5 bytes=33.5544M bytes_per_second=3.16449G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time_median 9870943 ns 19741995 ns 5 bytes=33.5544M bytes_per_second=3.16586G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time_stddev 8029 ns 37915 ns 5 bytes=0 bytes_per_second=2.63291M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time_cv 0.08 % 0.19 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time 21355073 ns 42624428 ns 33 bytes=67.1089M bytes_per_second=2.92671G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time 21357691 ns 42651600 ns 33 bytes=67.1089M bytes_per_second=2.92635G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time 21364042 ns 42682872 ns 33 bytes=67.1089M bytes_per_second=2.92548G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time 21366942 ns 42717919 ns 33 bytes=67.1089M bytes_per_second=2.92508G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time 21357997 ns 42682018 ns 33 bytes=67.1089M bytes_per_second=2.9263G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time_mean 21360349 ns 42671768 ns 5 bytes=67.1089M bytes_per_second=2.92598G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time_median 21357997 ns 42682018 ns 5 bytes=67.1089M bytes_per_second=2.9263G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time_stddev 4938 ns 35377 ns 5 bytes=0 bytes_per_second=709.266k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time_cv 0.02 % 0.08 % 5 bytes=0.00% bytes_per_second=0.02% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time 39464132 ns 77928735 ns 18 bytes=134.218M bytes_per_second=3.16743G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time 39459982 ns 78006910 ns 18 bytes=134.218M bytes_per_second=3.16777G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time 39384275 ns 77850964 ns 18 bytes=134.218M bytes_per_second=3.17386G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time 39422559 ns 77915300 ns 18 bytes=134.218M bytes_per_second=3.17077G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time 39437742 ns 77961678 ns 18 bytes=134.218M bytes_per_second=3.16955G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time_mean 39433738 ns 77932717 ns 5 bytes=134.218M bytes_per_second=3.16988G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time_median 39437742 ns 77928735 ns 5 bytes=134.218M bytes_per_second=3.16955G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time_stddev 32404 ns 57763 ns 5 bytes=0 bytes_per_second=2.66856M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time_cv 0.08 % 0.07 % 5 bytes=0.00% bytes_per_second=0.08% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time 75570178 ns 147560758 ns 9 bytes=268.435M bytes_per_second=3.30818G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time 75579351 ns 147576244 ns 9 bytes=268.435M bytes_per_second=3.30778G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time 75353555 ns 147210903 ns 9 bytes=268.435M bytes_per_second=3.31769G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time 75579991 ns 147565620 ns 9 bytes=268.435M bytes_per_second=3.30775G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time 75614249 ns 147595085 ns 9 bytes=268.435M bytes_per_second=3.30626G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time_mean 75539465 ns 147501722 ns 5 bytes=268.435M bytes_per_second=3.30953G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time_median 75579351 ns 147565620 ns 5 bytes=268.435M bytes_per_second=3.30778G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time_stddev 105276 ns 163106 ns 5 bytes=0 bytes_per_second=4.73129M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time_cv 0.14 % 0.11 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time 148370513 ns 283261866 ns 5 bytes=536.871M bytes_per_second=3.36994G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time 148218510 ns 283073162 ns 5 bytes=536.871M bytes_per_second=3.3734G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time 148191795 ns 283234381 ns 5 bytes=536.871M bytes_per_second=3.37401G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time 148135760 ns 283338546 ns 5 bytes=536.871M bytes_per_second=3.37528G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time 147814322 ns 282823348 ns 5 bytes=536.871M bytes_per_second=3.38262G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time_mean 148146180 ns 283146260 ns 5 bytes=536.871M bytes_per_second=3.37505G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time_median 148191795 ns 283234381 ns 5 bytes=536.871M bytes_per_second=3.37401G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time_stddev 204864 ns 204768 ns 5 bytes=0 bytes_per_second=4.78397M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time_cv 0.14 % 0.07 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time 296524838 ns 526290269 ns 2 bytes=1073.74M bytes_per_second=3.3724G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time 296725482 ns 525962465 ns 2 bytes=1073.74M bytes_per_second=3.37012G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time 297048599 ns 526895749 ns 2 bytes=1073.74M bytes_per_second=3.36645G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time 295977890 ns 525444799 ns 2 bytes=1073.74M bytes_per_second=3.37863G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time 296274364 ns 526253010 ns 2 bytes=1073.74M bytes_per_second=3.37525G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time_mean 296510234 ns 526169258 ns 5 bytes=1073.74M bytes_per_second=3.37257G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time_median 296524838 ns 526253010 ns 5 bytes=1073.74M bytes_per_second=3.3724G/s dst_gpu=6 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time_stddev 410915 ns 528453 ns 5 bytes=0 bytes_per_second=4.78597M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time_cv 0.14 % 0.10 % 5 bytes=0.00% bytes_per_second=0.14% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time 260707 ns 524921 ns 2691 bytes=1024 bytes_per_second=3.74582M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time 263326 ns 526285 ns 2691 bytes=1024 bytes_per_second=3.70856M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time 259864 ns 523902 ns 2691 bytes=1024 bytes_per_second=3.75797M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time 261255 ns 525404 ns 2691 bytes=1024 bytes_per_second=3.73797M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time 258798 ns 524842 ns 2691 bytes=1024 bytes_per_second=3.77345M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time_mean 260790 ns 525071 ns 5 bytes=1024 bytes_per_second=3.74475M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time_median 260707 ns 524921 ns 5 bytes=1024 bytes_per_second=3.74582M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time_stddev 1694 ns 870 ns 5 bytes=0 bytes_per_second=24.8466k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time_cv 0.65 % 0.17 % 5 bytes=0.00% bytes_per_second=0.65% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time 259435 ns 524705 ns 2699 bytes=2.048k bytes_per_second=7.52838M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time 261153 ns 524350 ns 2699 bytes=2.048k bytes_per_second=7.47885M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time 259723 ns 524423 ns 2699 bytes=2.048k bytes_per_second=7.52004M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time 260934 ns 525290 ns 2699 bytes=2.048k bytes_per_second=7.48512M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time 260625 ns 524596 ns 2699 bytes=2.048k bytes_per_second=7.494M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time_mean 260374 ns 524673 ns 5 bytes=2.048k bytes_per_second=7.50128M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time_median 260625 ns 524596 ns 5 bytes=2.048k bytes_per_second=7.494M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time_stddev 757 ns 373 ns 5 bytes=0 bytes_per_second=22.3389k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time_cv 0.29 % 0.07 % 5 bytes=0.00% bytes_per_second=0.29% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time 260682 ns 524670 ns 2726 bytes=4.096k bytes_per_second=14.9847M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time 261674 ns 525354 ns 2726 bytes=4.096k bytes_per_second=14.9279M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time 260886 ns 524405 ns 2726 bytes=4.096k bytes_per_second=14.973M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time 260384 ns 524009 ns 2726 bytes=4.096k bytes_per_second=15.0019M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time 261569 ns 524473 ns 2726 bytes=4.096k bytes_per_second=14.9339M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time_mean 261039 ns 524582 ns 5 bytes=4.096k bytes_per_second=14.9643M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time_median 260886 ns 524473 ns 5 bytes=4.096k bytes_per_second=14.973M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time_stddev 562 ns 494 ns 5 bytes=0 bytes_per_second=33.002k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time_cv 0.22 % 0.09 % 5 bytes=0.00% bytes_per_second=0.22% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time 262241 ns 527492 ns 2672 bytes=8.192k bytes_per_second=29.7914M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time 261495 ns 528167 ns 2672 bytes=8.192k bytes_per_second=29.8763M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time 263431 ns 529117 ns 2672 bytes=8.192k bytes_per_second=29.6567M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time 263465 ns 527419 ns 2672 bytes=8.192k bytes_per_second=29.6529M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time 263882 ns 528172 ns 2672 bytes=8.192k bytes_per_second=29.6061M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time_mean 262903 ns 528073 ns 5 bytes=8.192k bytes_per_second=29.7167M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time_median 263431 ns 528167 ns 5 bytes=8.192k bytes_per_second=29.6567M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time_stddev 997 ns 685 ns 5 bytes=0 bytes_per_second=115.555k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time_cv 0.38 % 0.13 % 5 bytes=0.00% bytes_per_second=0.38% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time 266836 ns 533485 ns 2645 bytes=16.384k bytes_per_second=58.5566M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time 265748 ns 533362 ns 2645 bytes=16.384k bytes_per_second=58.7964M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time 265245 ns 532464 ns 2645 bytes=16.384k bytes_per_second=58.9078M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time 265798 ns 533386 ns 2645 bytes=16.384k bytes_per_second=58.7853M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time 263909 ns 532586 ns 2645 bytes=16.384k bytes_per_second=59.2061M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time_mean 265507 ns 533057 ns 5 bytes=16.384k bytes_per_second=58.8504M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time_median 265748 ns 533362 ns 5 bytes=16.384k bytes_per_second=58.7964M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time_stddev 1065 ns 490 ns 5 bytes=0 bytes_per_second=241.967k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time_cv 0.40 % 0.09 % 5 bytes=0.00% bytes_per_second=0.40% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time 269486 ns 542262 ns 2583 bytes=32.768k bytes_per_second=115.962M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time 268980 ns 541314 ns 2583 bytes=32.768k bytes_per_second=116.18M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time 270906 ns 542231 ns 2583 bytes=32.768k bytes_per_second=115.354M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time 268138 ns 540883 ns 2583 bytes=32.768k bytes_per_second=116.544M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time 269292 ns 542155 ns 2583 bytes=32.768k bytes_per_second=116.045M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time_mean 269361 ns 541769 ns 5 bytes=32.768k bytes_per_second=116.017M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time_median 269292 ns 542155 ns 5 bytes=32.768k bytes_per_second=116.045M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time_stddev 1006 ns 632 ns 5 bytes=0 bytes_per_second=442.859k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time_cv 0.37 % 0.12 % 5 bytes=0.00% bytes_per_second=0.37% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time 277614 ns 558124 ns 2500 bytes=65.536k bytes_per_second=225.133M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time 278357 ns 560169 ns 2500 bytes=65.536k bytes_per_second=224.532M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time 277893 ns 560290 ns 2500 bytes=65.536k bytes_per_second=224.907M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time 278668 ns 558727 ns 2500 bytes=65.536k bytes_per_second=224.281M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time 278202 ns 560686 ns 2500 bytes=65.536k bytes_per_second=224.657M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time_mean 278147 ns 559599 ns 5 bytes=65.536k bytes_per_second=224.702M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time_median 278202 ns 560169 ns 5 bytes=65.536k bytes_per_second=224.657M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time_stddev 409 ns 1109 ns 5 bytes=0 bytes_per_second=338.06k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time_cv 0.15 % 0.20 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time 297130 ns 592423 ns 2355 bytes=131.072k bytes_per_second=420.692M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time 294654 ns 591906 ns 2355 bytes=131.072k bytes_per_second=424.226M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time 293868 ns 591920 ns 2355 bytes=131.072k bytes_per_second=425.36M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time 296931 ns 591879 ns 2355 bytes=131.072k bytes_per_second=420.974M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time 293984 ns 591128 ns 2355 bytes=131.072k bytes_per_second=425.194M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time_mean 295313 ns 591851 ns 5 bytes=131.072k bytes_per_second=423.289M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time_median 294654 ns 591906 ns 5 bytes=131.072k bytes_per_second=424.226M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time_stddev 1597 ns 463 ns 5 bytes=0 bytes_per_second=2.286M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time_cv 0.54 % 0.08 % 5 bytes=0.00% bytes_per_second=0.54% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time 325625 ns 656080 ns 2153 bytes=262.144k bytes_per_second=767.755M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time 326302 ns 656868 ns 2153 bytes=262.144k bytes_per_second=766.162M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time 326574 ns 656365 ns 2153 bytes=262.144k bytes_per_second=765.524M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time 326151 ns 655920 ns 2153 bytes=262.144k bytes_per_second=766.515M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time 326587 ns 656175 ns 2153 bytes=262.144k bytes_per_second=765.493M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time_mean 326248 ns 656282 ns 5 bytes=262.144k bytes_per_second=766.29M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time_median 326302 ns 656175 ns 5 bytes=262.144k bytes_per_second=766.162M/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time_stddev 394 ns 365 ns 5 bytes=0 bytes_per_second=949.092k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time_cv 0.12 % 0.06 % 5 bytes=0.00% bytes_per_second=0.12% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time 389447 ns 782539 ns 1800 bytes=524.288k bytes_per_second=1.25378G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time 389354 ns 782279 ns 1800 bytes=524.288k bytes_per_second=1.25408G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time 390928 ns 786466 ns 1800 bytes=524.288k bytes_per_second=1.24903G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time 389298 ns 782436 ns 1800 bytes=524.288k bytes_per_second=1.25426G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time 389539 ns 782625 ns 1800 bytes=524.288k bytes_per_second=1.25349G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time_mean 389713 ns 783269 ns 5 bytes=524.288k bytes_per_second=1.25293G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time_median 389447 ns 782539 ns 5 bytes=524.288k bytes_per_second=1.25378G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time_stddev 685 ns 1792 ns 5 bytes=0 bytes_per_second=2.25165M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time_cv 0.18 % 0.23 % 5 bytes=0.00% bytes_per_second=0.18% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time 529972 ns 1062729 ns 1324 bytes=1048.58k bytes_per_second=1.84267G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time 532789 ns 1063065 ns 1324 bytes=1048.58k bytes_per_second=1.83293G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time 529842 ns 1062655 ns 1324 bytes=1048.58k bytes_per_second=1.84312G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time 532161 ns 1062237 ns 1324 bytes=1048.58k bytes_per_second=1.83509G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time 529839 ns 1062864 ns 1324 bytes=1048.58k bytes_per_second=1.84313G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time_mean 530921 ns 1062710 ns 5 bytes=1048.58k bytes_per_second=1.83939G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time_median 529972 ns 1062729 ns 5 bytes=1048.58k bytes_per_second=1.84267G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time_stddev 1437 ns 307 ns 5 bytes=0 bytes_per_second=5.09238M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time_cv 0.27 % 0.03 % 5 bytes=0.00% bytes_per_second=0.27% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time 770392 ns 1543832 ns 899 bytes=2.09715M bytes_per_second=2.53523G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time 770535 ns 1544680 ns 899 bytes=2.09715M bytes_per_second=2.53476G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time 770286 ns 1543908 ns 899 bytes=2.09715M bytes_per_second=2.53559G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time 771370 ns 1545568 ns 899 bytes=2.09715M bytes_per_second=2.53202G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time 770262 ns 1544247 ns 899 bytes=2.09715M bytes_per_second=2.53566G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time_mean 770569 ns 1544447 ns 5 bytes=2.09715M bytes_per_second=2.53465G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time_median 770392 ns 1544247 ns 5 bytes=2.09715M bytes_per_second=2.53523G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time_stddev 460 ns 711 ns 5 bytes=0 bytes_per_second=1.5497M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time_cv 0.06 % 0.05 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time 1331099 ns 2681810 ns 524 bytes=4.1943M bytes_per_second=2.9346G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time 1330394 ns 2681427 ns 524 bytes=4.1943M bytes_per_second=2.93616G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time 1330857 ns 2680923 ns 524 bytes=4.1943M bytes_per_second=2.93514G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time 1331134 ns 2683141 ns 524 bytes=4.1943M bytes_per_second=2.93453G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time 1330393 ns 2682788 ns 524 bytes=4.1943M bytes_per_second=2.93616G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time_mean 1330775 ns 2682018 ns 5 bytes=4.1943M bytes_per_second=2.93532G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time_median 1330857 ns 2681810 ns 5 bytes=4.1943M bytes_per_second=2.93514G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time_stddev 365 ns 928 ns 5 bytes=0 bytes_per_second=843.678k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time_cv 0.03 % 0.03 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time 2504338 ns 5023605 ns 280 bytes=8.38861M bytes_per_second=3.11959G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time 2529903 ns 5075784 ns 280 bytes=8.38861M bytes_per_second=3.08806G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time 2532813 ns 5077733 ns 280 bytes=8.38861M bytes_per_second=3.08452G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time 2530195 ns 5075270 ns 280 bytes=8.38861M bytes_per_second=3.08771G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time 2534781 ns 5080452 ns 280 bytes=8.38861M bytes_per_second=3.08212G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time_mean 2526406 ns 5066569 ns 5 bytes=8.38861M bytes_per_second=3.0924G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time_median 2530195 ns 5075784 ns 5 bytes=8.38861M bytes_per_second=3.08771G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time_stddev 12498 ns 24103 ns 5 bytes=0 bytes_per_second=15.7629M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time_cv 0.49 % 0.48 % 5 bytes=0.00% bytes_per_second=0.50% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time 5006500 ns 9978517 ns 139 bytes=16.7772M bytes_per_second=3.12094G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time 5038581 ns 10050598 ns 139 bytes=16.7772M bytes_per_second=3.10107G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time 5008443 ns 9978964 ns 139 bytes=16.7772M bytes_per_second=3.11973G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time 5005723 ns 9977783 ns 139 bytes=16.7772M bytes_per_second=3.12143G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time 5006656 ns 9977043 ns 139 bytes=16.7772M bytes_per_second=3.12085G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time_mean 5013181 ns 9992581 ns 5 bytes=16.7772M bytes_per_second=3.1168G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time_median 5006656 ns 9978517 ns 5 bytes=16.7772M bytes_per_second=3.12085G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time_stddev 14234 ns 32441 ns 5 bytes=0 bytes_per_second=9.02798M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time_cv 0.28 % 0.32 % 5 bytes=0.00% bytes_per_second=0.28% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time 9913142 ns 19754072 ns 69 bytes=33.5544M bytes_per_second=3.15238G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time 9896729 ns 19714821 ns 69 bytes=33.5544M bytes_per_second=3.15761G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time 9879192 ns 19720379 ns 69 bytes=33.5544M bytes_per_second=3.16321G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time 9907600 ns 19724568 ns 69 bytes=33.5544M bytes_per_second=3.15414G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time 9915065 ns 19754341 ns 69 bytes=33.5544M bytes_per_second=3.15177G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time_mean 9902346 ns 19733636 ns 5 bytes=33.5544M bytes_per_second=3.15582G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time_median 9907600 ns 19724568 ns 5 bytes=33.5544M bytes_per_second=3.15414G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time_stddev 14778 ns 19094 ns 5 bytes=0 bytes_per_second=4.82786M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time_cv 0.15 % 0.10 % 5 bytes=0.00% bytes_per_second=0.15% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time 21270129 ns 42347957 ns 33 bytes=67.1089M bytes_per_second=2.93839G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time 21301717 ns 42558018 ns 33 bytes=67.1089M bytes_per_second=2.93404G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time 21298880 ns 42528635 ns 33 bytes=67.1089M bytes_per_second=2.93443G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time 21281852 ns 42472591 ns 33 bytes=67.1089M bytes_per_second=2.93677G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time 21285207 ns 42438085 ns 33 bytes=67.1089M bytes_per_second=2.93631G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time_mean 21287557 ns 42469057 ns 5 bytes=67.1089M bytes_per_second=2.93599G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time_median 21285207 ns 42472591 ns 5 bytes=67.1089M bytes_per_second=2.93631G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time_stddev 12947 ns 82311 ns 5 bytes=0 bytes_per_second=1.82869M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time_cv 0.06 % 0.19 % 5 bytes=0.00% bytes_per_second=0.06% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time 39346071 ns 77573423 ns 18 bytes=134.218M bytes_per_second=3.17694G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time 39341955 ns 77515137 ns 18 bytes=134.218M bytes_per_second=3.17727G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time 39374667 ns 77623858 ns 18 bytes=134.218M bytes_per_second=3.17463G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time 39349325 ns 77622549 ns 18 bytes=134.218M bytes_per_second=3.17667G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time 39361022 ns 77626025 ns 18 bytes=134.218M bytes_per_second=3.17573G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time_mean 39354608 ns 77592199 ns 5 bytes=134.218M bytes_per_second=3.17625G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time_median 39349325 ns 77622549 ns 5 bytes=134.218M bytes_per_second=3.17667G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time_stddev 13270 ns 48370 ns 5 bytes=0 bytes_per_second=1122.81k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time_cv 0.03 % 0.06 % 5 bytes=0.00% bytes_per_second=0.03% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time 75637894 ns 147567281 ns 9 bytes=268.435M bytes_per_second=3.30522G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time 75583902 ns 147583949 ns 9 bytes=268.435M bytes_per_second=3.30758G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time 75506888 ns 147525051 ns 9 bytes=268.435M bytes_per_second=3.31096G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time 75531440 ns 147418483 ns 9 bytes=268.435M bytes_per_second=3.30988G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time 75557787 ns 147433907 ns 9 bytes=268.435M bytes_per_second=3.30873G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time_mean 75563582 ns 147505734 ns 5 bytes=268.435M bytes_per_second=3.30847G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time_median 75557787 ns 147525051 ns 5 bytes=268.435M bytes_per_second=3.30873G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time_stddev 50537 ns 75912 ns 5 bytes=0 bytes_per_second=2.26522M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time_cv 0.07 % 0.05 % 5 bytes=0.00% bytes_per_second=0.07% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time 148032734 ns 282778698 ns 5 bytes=536.871M bytes_per_second=3.37763G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time 148006332 ns 282885101 ns 5 bytes=536.871M bytes_per_second=3.37823G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time 148057213 ns 282839785 ns 5 bytes=536.871M bytes_per_second=3.37707G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time 148029399 ns 282532785 ns 5 bytes=536.871M bytes_per_second=3.37771G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time 148026237 ns 282512647 ns 5 bytes=536.871M bytes_per_second=3.37778G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time_mean 148030383 ns 282709803 ns 5 bytes=536.871M bytes_per_second=3.37769G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time_median 148029399 ns 282778698 ns 5 bytes=536.871M bytes_per_second=3.37771G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time_stddev 18180 ns 175055 ns 5 bytes=0 bytes_per_second=434.955k/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time_cv 0.01 % 0.06 % 5 bytes=0.00% bytes_per_second=0.01% dst_gpu=0.00% src_gpu=-nan% +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time 293012440 ns 520582969 ns 2 bytes=1073.74M bytes_per_second=3.41282G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time 293627873 ns 521604964 ns 2 bytes=1073.74M bytes_per_second=3.40567G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time 293634117 ns 521715768 ns 2 bytes=1073.74M bytes_per_second=3.4056G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time 293213025 ns 521586736 ns 2 bytes=1073.74M bytes_per_second=3.41049G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time 293547332 ns 521862783 ns 2 bytes=1073.74M bytes_per_second=3.40661G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time_mean 293406957 ns 521470644 ns 5 bytes=1073.74M bytes_per_second=3.40824G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time_median 293547332 ns 521604964 ns 5 bytes=1073.74M bytes_per_second=3.40661G/s dst_gpu=7 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time_stddev 279895 ns 508268 ns 5 bytes=0 bytes_per_second=3.33088M/s dst_gpu=0 src_gpu=0 +Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time_cv 0.10 % 0.10 % 5 bytes=0.00% bytes_per_second=0.10% dst_gpu=0.00% src_gpu=-nan% +[2023-10-09 18:10:33.965] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 18:10:33.965] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Mon 09 Oct 2023 06:10:34 PM EDT diff --git a/results/r7-1465534.out b/results/r7-1465534.out new file mode 100644 index 0000000..6e7f90a --- /dev/null +++ b/results/r7-1465534.out @@ -0,0 +1,434 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 05:44:30 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:44:32.312] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:44:32.313] [scope] [info] recorded CPU goveror +[2023-10-09 17:44:32.313] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:44:32.313] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:44:34-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1795.42 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.40, 3.80, 18.46 +---------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +---------------------------------------------------------------------------------------------------------------------------- +Comm_prefetch_managed_GPUToHost/0/0/log2(N):10/manual_time 199996 ns 277723 ns 3482 bytes=1024 bytes_per_second=4.8829M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):10/manual_time 200650 ns 277790 ns 3482 bytes=1024 bytes_per_second=4.867M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):10/manual_time 200053 ns 277672 ns 3482 bytes=1024 bytes_per_second=4.88151M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):10/manual_time 199943 ns 277657 ns 3482 bytes=1024 bytes_per_second=4.8842M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):10/manual_time 200594 ns 277888 ns 3482 bytes=1024 bytes_per_second=4.86835M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):10/manual_time_mean 200247 ns 277746 ns 5 bytes=1024 bytes_per_second=4.87679M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):10/manual_time_median 200053 ns 277723 ns 5 bytes=1024 bytes_per_second=4.88151M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):10/manual_time_stddev 345 ns 95.1 ns 5 bytes=0 bytes_per_second=8.59454k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):10/manual_time_cv 0.17 % 0.03 % 5 bytes=0.00% bytes_per_second=0.17% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):11/manual_time 200079 ns 277540 ns 3496 bytes=2.048k bytes_per_second=9.76176M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):11/manual_time 200361 ns 277607 ns 3496 bytes=2.048k bytes_per_second=9.74802M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):11/manual_time 199886 ns 277635 ns 3496 bytes=2.048k bytes_per_second=9.7712M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):11/manual_time 200524 ns 278337 ns 3496 bytes=2.048k bytes_per_second=9.74009M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):11/manual_time 199978 ns 277686 ns 3496 bytes=2.048k bytes_per_second=9.76671M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):11/manual_time_mean 200166 ns 277761 ns 5 bytes=2.048k bytes_per_second=9.75756M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):11/manual_time_median 200079 ns 277635 ns 5 bytes=2.048k bytes_per_second=9.76176M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):11/manual_time_stddev 268 ns 326 ns 5 bytes=0 bytes_per_second=13.3859k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):11/manual_time_cv 0.13 % 0.12 % 5 bytes=0.00% bytes_per_second=0.13% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):12/manual_time 199956 ns 277196 ns 3497 bytes=4.096k bytes_per_second=19.5355M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):12/manual_time 200348 ns 277811 ns 3497 bytes=4.096k bytes_per_second=19.4973M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):12/manual_time 200467 ns 277691 ns 3497 bytes=4.096k bytes_per_second=19.4858M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):12/manual_time 199946 ns 277657 ns 3497 bytes=4.096k bytes_per_second=19.5366M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):12/manual_time 199948 ns 277368 ns 3497 bytes=4.096k bytes_per_second=19.5363M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):12/manual_time_mean 200133 ns 277545 ns 5 bytes=4.096k bytes_per_second=19.5183M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):12/manual_time_median 199956 ns 277657 ns 5 bytes=4.096k bytes_per_second=19.5355M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):12/manual_time_stddev 254 ns 254 ns 5 bytes=0 bytes_per_second=25.3614k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):12/manual_time_cv 0.13 % 0.09 % 5 bytes=0.00% bytes_per_second=0.13% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):13/manual_time 201192 ns 279823 ns 3445 bytes=8.192k bytes_per_second=38.831M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):13/manual_time 201114 ns 279673 ns 3445 bytes=8.192k bytes_per_second=38.8461M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):13/manual_time 201474 ns 279593 ns 3445 bytes=8.192k bytes_per_second=38.7766M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):13/manual_time 201081 ns 279776 ns 3445 bytes=8.192k bytes_per_second=38.8525M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):13/manual_time 201119 ns 279791 ns 3445 bytes=8.192k bytes_per_second=38.8452M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):13/manual_time_mean 201196 ns 279731 ns 5 bytes=8.192k bytes_per_second=38.8303M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):13/manual_time_median 201119 ns 279776 ns 5 bytes=8.192k bytes_per_second=38.8452M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):13/manual_time_stddev 161 ns 95.4 ns 5 bytes=0 bytes_per_second=31.7445k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):13/manual_time_cv 0.08 % 0.03 % 5 bytes=0.00% bytes_per_second=0.08% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):14/manual_time 202643 ns 282574 ns 3458 bytes=16.384k bytes_per_second=77.1061M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):14/manual_time 202028 ns 281969 ns 3458 bytes=16.384k bytes_per_second=77.3407M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):14/manual_time 202535 ns 282019 ns 3458 bytes=16.384k bytes_per_second=77.1472M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):14/manual_time 202119 ns 282305 ns 3458 bytes=16.384k bytes_per_second=77.3058M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):14/manual_time 202117 ns 282210 ns 3458 bytes=16.384k bytes_per_second=77.3067M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):14/manual_time_mean 202288 ns 282216 ns 5 bytes=16.384k bytes_per_second=77.2413M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):14/manual_time_median 202119 ns 282210 ns 5 bytes=16.384k bytes_per_second=77.3058M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):14/manual_time_stddev 279 ns 243 ns 5 bytes=0 bytes_per_second=109.133k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):14/manual_time_cv 0.14 % 0.09 % 5 bytes=0.00% bytes_per_second=0.14% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):15/manual_time 205076 ns 288579 ns 3424 bytes=32.768k bytes_per_second=152.383M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):15/manual_time 204637 ns 287047 ns 3424 bytes=32.768k bytes_per_second=152.71M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):15/manual_time 204038 ns 286899 ns 3424 bytes=32.768k bytes_per_second=153.157M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):15/manual_time 204131 ns 287125 ns 3424 bytes=32.768k bytes_per_second=153.088M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):15/manual_time 204721 ns 287134 ns 3424 bytes=32.768k bytes_per_second=152.647M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):15/manual_time_mean 204520 ns 287357 ns 5 bytes=32.768k bytes_per_second=152.797M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):15/manual_time_median 204637 ns 287125 ns 5 bytes=32.768k bytes_per_second=152.71M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):15/manual_time_stddev 432 ns 690 ns 5 bytes=0 bytes_per_second=330.455k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):15/manual_time_cv 0.21 % 0.24 % 5 bytes=0.00% bytes_per_second=0.21% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):16/manual_time 207747 ns 296504 ns 3368 bytes=65.536k bytes_per_second=300.846M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):16/manual_time 208344 ns 296598 ns 3368 bytes=65.536k bytes_per_second=299.984M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):16/manual_time 207711 ns 296068 ns 3368 bytes=65.536k bytes_per_second=300.898M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):16/manual_time 207673 ns 296324 ns 3368 bytes=65.536k bytes_per_second=300.954M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):16/manual_time 208199 ns 296329 ns 3368 bytes=65.536k bytes_per_second=300.194M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):16/manual_time_mean 207935 ns 296365 ns 5 bytes=65.536k bytes_per_second=300.575M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):16/manual_time_median 207747 ns 296329 ns 5 bytes=65.536k bytes_per_second=300.846M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):16/manual_time_stddev 313 ns 203 ns 5 bytes=0 bytes_per_second=462.475k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):16/manual_time_cv 0.15 % 0.07 % 5 bytes=0.00% bytes_per_second=0.15% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):17/manual_time 212733 ns 311804 ns 3290 bytes=131.072k bytes_per_second=587.592M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):17/manual_time 212846 ns 312321 ns 3290 bytes=131.072k bytes_per_second=587.278M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):17/manual_time 212606 ns 311916 ns 3290 bytes=131.072k bytes_per_second=587.943M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):17/manual_time 212656 ns 312287 ns 3290 bytes=131.072k bytes_per_second=587.803M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):17/manual_time 212713 ns 311482 ns 3290 bytes=131.072k bytes_per_second=587.645M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):17/manual_time_mean 212711 ns 311962 ns 5 bytes=131.072k bytes_per_second=587.652M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):17/manual_time_median 212713 ns 311916 ns 5 bytes=131.072k bytes_per_second=587.645M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):17/manual_time_stddev 90.6 ns 351 ns 5 bytes=0 bytes_per_second=256.395k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):17/manual_time_cv 0.04 % 0.11 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):18/manual_time 228506 ns 344365 ns 3045 bytes=262.144k bytes_per_second=1094.06M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):18/manual_time 228873 ns 344757 ns 3045 bytes=262.144k bytes_per_second=1092.31M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):18/manual_time 228649 ns 344312 ns 3045 bytes=262.144k bytes_per_second=1093.38M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):18/manual_time 228991 ns 344848 ns 3045 bytes=262.144k bytes_per_second=1091.75M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):18/manual_time 228465 ns 344342 ns 3045 bytes=262.144k bytes_per_second=1094.26M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):18/manual_time_mean 228697 ns 344525 ns 5 bytes=262.144k bytes_per_second=1093.15M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):18/manual_time_median 228649 ns 344365 ns 5 bytes=262.144k bytes_per_second=1093.38M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):18/manual_time_stddev 229 ns 256 ns 5 bytes=0 bytes_per_second=1121.61k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):18/manual_time_cv 0.10 % 0.07 % 5 bytes=0.00% bytes_per_second=0.10% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):19/manual_time 256763 ns 417101 ns 2722 bytes=524.288k bytes_per_second=1.90168G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):19/manual_time 256798 ns 416398 ns 2722 bytes=524.288k bytes_per_second=1.90142G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):19/manual_time 257090 ns 417306 ns 2722 bytes=524.288k bytes_per_second=1.89926G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):19/manual_time 256155 ns 415732 ns 2722 bytes=524.288k bytes_per_second=1.9062G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):19/manual_time 256654 ns 416333 ns 2722 bytes=524.288k bytes_per_second=1.90249G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):19/manual_time_mean 256692 ns 416574 ns 5 bytes=524.288k bytes_per_second=1.90221G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):19/manual_time_median 256763 ns 416398 ns 5 bytes=524.288k bytes_per_second=1.90168G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):19/manual_time_stddev 341 ns 634 ns 5 bytes=0 bytes_per_second=2.58973M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):19/manual_time_cv 0.13 % 0.15 % 5 bytes=0.00% bytes_per_second=0.13% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):20/manual_time 310930 ns 561263 ns 2250 bytes=1048.58k bytes_per_second=3.14078G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):20/manual_time 311753 ns 562875 ns 2250 bytes=1048.58k bytes_per_second=3.13249G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):20/manual_time 311600 ns 562970 ns 2250 bytes=1048.58k bytes_per_second=3.13403G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):20/manual_time 311333 ns 561970 ns 2250 bytes=1048.58k bytes_per_second=3.13672G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):20/manual_time 310846 ns 560930 ns 2250 bytes=1048.58k bytes_per_second=3.14163G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):20/manual_time_mean 311292 ns 562002 ns 5 bytes=1048.58k bytes_per_second=3.13713G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):20/manual_time_median 311333 ns 561970 ns 5 bytes=1048.58k bytes_per_second=3.13672G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):20/manual_time_stddev 400 ns 921 ns 5 bytes=0 bytes_per_second=4.12563M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):20/manual_time_cv 0.13 % 0.16 % 5 bytes=0.00% bytes_per_second=0.13% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):21/manual_time 424142 ns 851754 ns 1650 bytes=2.09715M bytes_per_second=4.60489G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):21/manual_time 423700 ns 851064 ns 1650 bytes=2.09715M bytes_per_second=4.60969G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):21/manual_time 424015 ns 851996 ns 1650 bytes=2.09715M bytes_per_second=4.60626G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):21/manual_time 424420 ns 852058 ns 1650 bytes=2.09715M bytes_per_second=4.60187G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):21/manual_time 424189 ns 851931 ns 1650 bytes=2.09715M bytes_per_second=4.60437G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):21/manual_time_mean 424093 ns 851761 ns 5 bytes=2.09715M bytes_per_second=4.60542G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):21/manual_time_median 424142 ns 851931 ns 5 bytes=2.09715M bytes_per_second=4.60489G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):21/manual_time_stddev 264 ns 406 ns 5 bytes=0 bytes_per_second=2.93678M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):21/manual_time_cv 0.06 % 0.05 % 5 bytes=0.00% bytes_per_second=0.06% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):22/manual_time 667102 ns 1473592 ns 1049 bytes=4.1943M bytes_per_second=5.85555G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):22/manual_time 667538 ns 1473816 ns 1049 bytes=4.1943M bytes_per_second=5.85173G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):22/manual_time 666577 ns 1473497 ns 1049 bytes=4.1943M bytes_per_second=5.86016G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):22/manual_time 667601 ns 1474445 ns 1049 bytes=4.1943M bytes_per_second=5.85118G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):22/manual_time 667140 ns 1473558 ns 1049 bytes=4.1943M bytes_per_second=5.85522G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):22/manual_time_mean 667192 ns 1473782 ns 5 bytes=4.1943M bytes_per_second=5.85477G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):22/manual_time_median 667140 ns 1473592 ns 5 bytes=4.1943M bytes_per_second=5.85522G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):22/manual_time_stddev 411 ns 390 ns 5 bytes=0 bytes_per_second=3.69211M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):22/manual_time_cv 0.06 % 0.03 % 5 bytes=0.00% bytes_per_second=0.06% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):23/manual_time 1155645 ns 2732343 ns 605 bytes=8.38861M bytes_per_second=6.76029G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):23/manual_time 1158448 ns 2727449 ns 605 bytes=8.38861M bytes_per_second=6.74394G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):23/manual_time 1154708 ns 2730412 ns 605 bytes=8.38861M bytes_per_second=6.76578G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):23/manual_time 1155234 ns 2732382 ns 605 bytes=8.38861M bytes_per_second=6.7627G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):23/manual_time 1153364 ns 2727263 ns 605 bytes=8.38861M bytes_per_second=6.77367G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):23/manual_time_mean 1155480 ns 2729970 ns 5 bytes=8.38861M bytes_per_second=6.76128G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):23/manual_time_median 1155234 ns 2730412 ns 5 bytes=8.38861M bytes_per_second=6.7627G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):23/manual_time_stddev 1869 ns 2516 ns 5 bytes=0 bytes_per_second=11.1868M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):23/manual_time_cv 0.16 % 0.09 % 5 bytes=0.00% bytes_per_second=0.16% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):24/manual_time 2172881 ns 5347177 ns 321 bytes=16.7772M bytes_per_second=7.19091G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):24/manual_time 2174735 ns 5350254 ns 321 bytes=16.7772M bytes_per_second=7.18478G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):24/manual_time 2183086 ns 5356541 ns 321 bytes=16.7772M bytes_per_second=7.1573G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):24/manual_time 2174613 ns 5347350 ns 321 bytes=16.7772M bytes_per_second=7.18518G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):24/manual_time 2173049 ns 5349198 ns 321 bytes=16.7772M bytes_per_second=7.19036G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):24/manual_time_mean 2175673 ns 5350104 ns 5 bytes=16.7772M bytes_per_second=7.18171G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):24/manual_time_median 2174613 ns 5349198 ns 5 bytes=16.7772M bytes_per_second=7.18518G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):24/manual_time_stddev 4232 ns 3822 ns 5 bytes=0 bytes_per_second=14.2713M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):24/manual_time_cv 0.19 % 0.07 % 5 bytes=0.00% bytes_per_second=0.19% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):25/manual_time 4204809 ns 10809165 ns 163 bytes=33.5544M bytes_per_second=7.43197G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):25/manual_time 4190270 ns 10771673 ns 163 bytes=33.5544M bytes_per_second=7.45775G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):25/manual_time 4208690 ns 10800487 ns 163 bytes=33.5544M bytes_per_second=7.42511G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):25/manual_time 4233257 ns 10855466 ns 163 bytes=33.5544M bytes_per_second=7.38202G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):25/manual_time 4180116 ns 10756252 ns 163 bytes=33.5544M bytes_per_second=7.47587G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):25/manual_time_mean 4203429 ns 10798609 ns 5 bytes=33.5544M bytes_per_second=7.43454G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):25/manual_time_median 4204809 ns 10800487 ns 5 bytes=33.5544M bytes_per_second=7.43197G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):25/manual_time_stddev 20223 ns 38299 ns 5 bytes=0 bytes_per_second=36.5658M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):25/manual_time_cv 0.48 % 0.35 % 5 bytes=0.00% bytes_per_second=0.48% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):26/manual_time 8988264 ns 23019243 ns 77 bytes=67.1089M bytes_per_second=6.95351G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):26/manual_time 8999044 ns 23022153 ns 77 bytes=67.1089M bytes_per_second=6.94518G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):26/manual_time 8986167 ns 22993757 ns 77 bytes=67.1089M bytes_per_second=6.95513G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):26/manual_time 8988378 ns 23032328 ns 77 bytes=67.1089M bytes_per_second=6.95342G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):26/manual_time 8982543 ns 22970113 ns 77 bytes=67.1089M bytes_per_second=6.95794G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):26/manual_time_mean 8988879 ns 23007519 ns 5 bytes=67.1089M bytes_per_second=6.95304G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):26/manual_time_median 8988264 ns 23019243 ns 5 bytes=67.1089M bytes_per_second=6.95351G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):26/manual_time_stddev 6153 ns 25277 ns 5 bytes=0 bytes_per_second=4.87122M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):26/manual_time_cv 0.07 % 0.11 % 5 bytes=0.00% bytes_per_second=0.07% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):27/manual_time 16993940 ns 43404790 ns 41 bytes=134.218M bytes_per_second=7.35556G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):27/manual_time 17013928 ns 43434386 ns 41 bytes=134.218M bytes_per_second=7.34692G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):27/manual_time 17009924 ns 43432133 ns 41 bytes=134.218M bytes_per_second=7.34865G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):27/manual_time 17003844 ns 43413431 ns 41 bytes=134.218M bytes_per_second=7.35128G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):27/manual_time 17002989 ns 43393069 ns 41 bytes=134.218M bytes_per_second=7.35165G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):27/manual_time_mean 17004925 ns 43415562 ns 5 bytes=134.218M bytes_per_second=7.35081G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):27/manual_time_median 17003844 ns 43413431 ns 5 bytes=134.218M bytes_per_second=7.35128G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):27/manual_time_stddev 7610 ns 17716 ns 5 bytes=0 bytes_per_second=3.36887M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):27/manual_time_cv 0.04 % 0.04 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):28/manual_time 32920341 ns 83824041 ns 21 bytes=268.435M bytes_per_second=7.59409G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):28/manual_time 32898315 ns 83822345 ns 21 bytes=268.435M bytes_per_second=7.59917G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):28/manual_time 32950391 ns 83804190 ns 21 bytes=268.435M bytes_per_second=7.58716G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):28/manual_time 32877286 ns 83823741 ns 21 bytes=268.435M bytes_per_second=7.60403G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):28/manual_time 33011016 ns 83963997 ns 21 bytes=268.435M bytes_per_second=7.57323G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):28/manual_time_mean 32931470 ns 83847663 ns 5 bytes=268.435M bytes_per_second=7.59154G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):28/manual_time_median 32920341 ns 83823741 ns 5 bytes=268.435M bytes_per_second=7.59409G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):28/manual_time_stddev 52069 ns 65565 ns 5 bytes=0 bytes_per_second=12.2805M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):28/manual_time_cv 0.16 % 0.08 % 5 bytes=0.00% bytes_per_second=0.16% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):29/manual_time 65180983 ns 164643161 ns 10 bytes=536.871M bytes_per_second=7.67095G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):29/manual_time 65075768 ns 164564410 ns 10 bytes=536.871M bytes_per_second=7.68335G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):29/manual_time 64986294 ns 164350736 ns 10 bytes=536.871M bytes_per_second=7.69393G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):29/manual_time 64945159 ns 164359111 ns 10 bytes=536.871M bytes_per_second=7.6988G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):29/manual_time 65094536 ns 164514284 ns 10 bytes=536.871M bytes_per_second=7.68114G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):29/manual_time_mean 65056548 ns 164486340 ns 5 bytes=536.871M bytes_per_second=7.68563G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):29/manual_time_median 65075768 ns 164514284 ns 5 bytes=536.871M bytes_per_second=7.68335G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):29/manual_time_stddev 93059 ns 128495 ns 5 bytes=0 bytes_per_second=11.2563M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):29/manual_time_cv 0.14 % 0.08 % 5 bytes=0.00% bytes_per_second=0.14% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_GPUToHost/0/0/log2(N):30/manual_time 141545585 ns 318507417 ns 5 bytes=1073.74M bytes_per_second=7.06486G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):30/manual_time 141671637 ns 318519215 ns 5 bytes=1073.74M bytes_per_second=7.05858G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):30/manual_time 141563731 ns 318307099 ns 5 bytes=1073.74M bytes_per_second=7.06396G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):30/manual_time 141662574 ns 318863186 ns 5 bytes=1073.74M bytes_per_second=7.05903G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):30/manual_time 141622743 ns 318616878 ns 5 bytes=1073.74M bytes_per_second=7.06101G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):30/manual_time_mean 141613254 ns 318562759 ns 5 bytes=1073.74M bytes_per_second=7.06149G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):30/manual_time_median 141622743 ns 318519215 ns 5 bytes=1073.74M bytes_per_second=7.06101G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):30/manual_time_stddev 56927 ns 202180 ns 5 bytes=0 bytes_per_second=2.90693M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_GPUToHost/0/0/log2(N):30/manual_time_cv 0.04 % 0.06 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +[2023-10-09 17:47:38.525] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 17:47:38.525] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:47:38.698] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:47:38.698] [scope] [info] recorded CPU goveror +[2023-10-09 17:47:38.698] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:47:38.698] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:47:41-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1744.5 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 1.90, 3.00, 15.50 +---------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +---------------------------------------------------------------------------------------------------------------------------- +Comm_prefetch_managed_HostToGPU/0/0/log2(N):10/manual_time 76772 ns 278832 ns 9239 bytes=1024 bytes_per_second=12.7202M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):10/manual_time 76585 ns 278457 ns 9239 bytes=1024 bytes_per_second=12.7514M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):10/manual_time 76530 ns 278253 ns 9239 bytes=1024 bytes_per_second=12.7605M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):10/manual_time 76379 ns 278527 ns 9239 bytes=1024 bytes_per_second=12.7857M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):10/manual_time 76532 ns 278518 ns 9239 bytes=1024 bytes_per_second=12.7602M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):10/manual_time_mean 76560 ns 278518 ns 5 bytes=1024 bytes_per_second=12.7556M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):10/manual_time_median 76532 ns 278518 ns 5 bytes=1024 bytes_per_second=12.7602M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):10/manual_time_stddev 141 ns 208 ns 5 bytes=0 bytes_per_second=24.1128k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):10/manual_time_cv 0.18 % 0.07 % 5 bytes=0.00% bytes_per_second=0.18% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):11/manual_time 76799 ns 278600 ns 9042 bytes=2.048k bytes_per_second=25.4316M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):11/manual_time 76706 ns 278655 ns 9042 bytes=2.048k bytes_per_second=25.4625M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):11/manual_time 76635 ns 278201 ns 9042 bytes=2.048k bytes_per_second=25.486M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):11/manual_time 76804 ns 278581 ns 9042 bytes=2.048k bytes_per_second=25.43M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):11/manual_time 76510 ns 278519 ns 9042 bytes=2.048k bytes_per_second=25.5277M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):11/manual_time_mean 76691 ns 278511 ns 5 bytes=2.048k bytes_per_second=25.4675M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):11/manual_time_median 76706 ns 278581 ns 5 bytes=2.048k bytes_per_second=25.4625M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):11/manual_time_stddev 123 ns 180 ns 5 bytes=0 bytes_per_second=41.8676k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):11/manual_time_cv 0.16 % 0.06 % 5 bytes=0.00% bytes_per_second=0.16% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):12/manual_time 76405 ns 278285 ns 9261 bytes=4.096k bytes_per_second=51.1257M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):12/manual_time 76600 ns 278465 ns 9261 bytes=4.096k bytes_per_second=50.9956M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):12/manual_time 76695 ns 278369 ns 9261 bytes=4.096k bytes_per_second=50.9321M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):12/manual_time 76731 ns 278468 ns 9261 bytes=4.096k bytes_per_second=50.9083M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):12/manual_time 76551 ns 278277 ns 9261 bytes=4.096k bytes_per_second=51.0281M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):12/manual_time_mean 76596 ns 278373 ns 5 bytes=4.096k bytes_per_second=50.998M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):12/manual_time_median 76600 ns 278369 ns 5 bytes=4.096k bytes_per_second=50.9956M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):12/manual_time_stddev 129 ns 92.9 ns 5 bytes=0 bytes_per_second=88.0661k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):12/manual_time_cv 0.17 % 0.03 % 5 bytes=0.00% bytes_per_second=0.17% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):13/manual_time 77365 ns 280189 ns 9178 bytes=8.192k bytes_per_second=100.982M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):13/manual_time 77558 ns 280500 ns 9178 bytes=8.192k bytes_per_second=100.73M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):13/manual_time 77301 ns 280022 ns 9178 bytes=8.192k bytes_per_second=101.066M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):13/manual_time 77401 ns 280315 ns 9178 bytes=8.192k bytes_per_second=100.936M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):13/manual_time 77276 ns 280105 ns 9178 bytes=8.192k bytes_per_second=101.098M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):13/manual_time_mean 77380 ns 280226 ns 5 bytes=8.192k bytes_per_second=100.963M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):13/manual_time_median 77365 ns 280189 ns 5 bytes=8.192k bytes_per_second=100.982M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):13/manual_time_stddev 111 ns 187 ns 5 bytes=0 bytes_per_second=148.531k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):13/manual_time_cv 0.14 % 0.07 % 5 bytes=0.00% bytes_per_second=0.14% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):14/manual_time 78649 ns 282805 ns 8980 bytes=16.384k bytes_per_second=198.669M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):14/manual_time 78579 ns 282627 ns 8980 bytes=16.384k bytes_per_second=198.844M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):14/manual_time 78843 ns 282970 ns 8980 bytes=16.384k bytes_per_second=198.178M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):14/manual_time 78925 ns 283064 ns 8980 bytes=16.384k bytes_per_second=197.972M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):14/manual_time 78945 ns 282851 ns 8980 bytes=16.384k bytes_per_second=197.924M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):14/manual_time_mean 78788 ns 282864 ns 5 bytes=16.384k bytes_per_second=198.317M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):14/manual_time_median 78843 ns 282851 ns 5 bytes=16.384k bytes_per_second=198.178M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):14/manual_time_stddev 165 ns 167 ns 5 bytes=0 bytes_per_second=426.75k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):14/manual_time_cv 0.21 % 0.06 % 5 bytes=0.00% bytes_per_second=0.21% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):15/manual_time 81663 ns 287880 ns 8510 bytes=32.768k bytes_per_second=382.668M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):15/manual_time 81434 ns 287665 ns 8510 bytes=32.768k bytes_per_second=383.749M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):15/manual_time 81430 ns 287686 ns 8510 bytes=32.768k bytes_per_second=383.765M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):15/manual_time 81539 ns 287535 ns 8510 bytes=32.768k bytes_per_second=383.251M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):15/manual_time 81335 ns 287574 ns 8510 bytes=32.768k bytes_per_second=384.215M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):15/manual_time_mean 81480 ns 287668 ns 5 bytes=32.768k bytes_per_second=383.53M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):15/manual_time_median 81434 ns 287665 ns 5 bytes=32.768k bytes_per_second=383.749M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):15/manual_time_stddev 125 ns 134 ns 5 bytes=0 bytes_per_second=604.149k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):15/manual_time_cv 0.15 % 0.05 % 5 bytes=0.00% bytes_per_second=0.15% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):16/manual_time 86327 ns 296062 ns 8191 bytes=65.536k bytes_per_second=723.993M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):16/manual_time 86294 ns 296033 ns 8191 bytes=65.536k bytes_per_second=724.271M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):16/manual_time 86335 ns 295946 ns 8191 bytes=65.536k bytes_per_second=723.926M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):16/manual_time 86250 ns 295756 ns 8191 bytes=65.536k bytes_per_second=724.637M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):16/manual_time 86276 ns 296049 ns 8191 bytes=65.536k bytes_per_second=724.42M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):16/manual_time_mean 86296 ns 295969 ns 5 bytes=65.536k bytes_per_second=724.249M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):16/manual_time_median 86294 ns 296033 ns 5 bytes=65.536k bytes_per_second=724.271M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):16/manual_time_stddev 35.2 ns 127 ns 5 bytes=0 bytes_per_second=302.897k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):16/manual_time_cv 0.04 % 0.04 % 5 bytes=0.00% bytes_per_second=0.04% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):17/manual_time 94309 ns 311630 ns 7191 bytes=131.072k bytes_per_second=1.29437G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):17/manual_time 94474 ns 311750 ns 7191 bytes=131.072k bytes_per_second=1.2921G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):17/manual_time 97115 ns 311590 ns 7191 bytes=131.072k bytes_per_second=1.25696G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):17/manual_time 94511 ns 311752 ns 7191 bytes=131.072k bytes_per_second=1.2916G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):17/manual_time 94445 ns 311738 ns 7191 bytes=131.072k bytes_per_second=1.2925G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):17/manual_time_mean 94971 ns 311692 ns 5 bytes=131.072k bytes_per_second=1.28551G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):17/manual_time_median 94474 ns 311738 ns 5 bytes=131.072k bytes_per_second=1.2921G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):17/manual_time_stddev 1201 ns 76.5 ns 5 bytes=0 bytes_per_second=16.3748M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):17/manual_time_cv 1.26 % 0.02 % 5 bytes=0.00% bytes_per_second=1.24% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):18/manual_time 115056 ns 345957 ns 6088 bytes=262.144k bytes_per_second=2.12193G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):18/manual_time 115091 ns 345791 ns 6088 bytes=262.144k bytes_per_second=2.12128G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):18/manual_time 114937 ns 345555 ns 6088 bytes=262.144k bytes_per_second=2.12413G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):18/manual_time 115045 ns 345503 ns 6088 bytes=262.144k bytes_per_second=2.12213G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):18/manual_time 115137 ns 345971 ns 6088 bytes=262.144k bytes_per_second=2.12044G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):18/manual_time_mean 115053 ns 345755 ns 5 bytes=262.144k bytes_per_second=2.12198G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):18/manual_time_median 115056 ns 345791 ns 5 bytes=262.144k bytes_per_second=2.12193G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):18/manual_time_stddev 74.3 ns 219 ns 5 bytes=0 bytes_per_second=1.40464M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):18/manual_time_cv 0.06 % 0.06 % 5 bytes=0.00% bytes_per_second=0.06% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):19/manual_time 159436 ns 417965 ns 4419 bytes=524.288k bytes_per_second=3.06255G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):19/manual_time 159286 ns 417843 ns 4419 bytes=524.288k bytes_per_second=3.06544G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):19/manual_time 159368 ns 417575 ns 4419 bytes=524.288k bytes_per_second=3.06386G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):19/manual_time 159328 ns 417511 ns 4419 bytes=524.288k bytes_per_second=3.06462G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):19/manual_time 159841 ns 418549 ns 4419 bytes=524.288k bytes_per_second=3.0548G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):19/manual_time_mean 159452 ns 417889 ns 5 bytes=524.288k bytes_per_second=3.06225G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):19/manual_time_median 159368 ns 417843 ns 5 bytes=524.288k bytes_per_second=3.06386G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):19/manual_time_stddev 224 ns 414 ns 5 bytes=0 bytes_per_second=4.40233M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):19/manual_time_cv 0.14 % 0.10 % 5 bytes=0.00% bytes_per_second=0.14% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):20/manual_time 250611 ns 564123 ns 2822 bytes=1048.58k bytes_per_second=3.89673G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):20/manual_time 247867 ns 564164 ns 2822 bytes=1048.58k bytes_per_second=3.93986G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):20/manual_time 250532 ns 564208 ns 2822 bytes=1048.58k bytes_per_second=3.89795G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):20/manual_time 247845 ns 564034 ns 2822 bytes=1048.58k bytes_per_second=3.94022G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):20/manual_time 250555 ns 564024 ns 2822 bytes=1048.58k bytes_per_second=3.8976G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):20/manual_time_mean 249482 ns 564110 ns 5 bytes=1048.58k bytes_per_second=3.91447G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):20/manual_time_median 250532 ns 564123 ns 5 bytes=1048.58k bytes_per_second=3.89795G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):20/manual_time_stddev 1485 ns 80.3 ns 5 bytes=0 bytes_per_second=23.905M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):20/manual_time_cv 0.60 % 0.01 % 5 bytes=0.00% bytes_per_second=0.60% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):21/manual_time 427869 ns 854476 ns 1637 bytes=2.09715M bytes_per_second=4.56477G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):21/manual_time 428125 ns 854698 ns 1637 bytes=2.09715M bytes_per_second=4.56204G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):21/manual_time 428488 ns 855197 ns 1637 bytes=2.09715M bytes_per_second=4.55817G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):21/manual_time 427887 ns 854128 ns 1637 bytes=2.09715M bytes_per_second=4.56458G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):21/manual_time 428141 ns 854318 ns 1637 bytes=2.09715M bytes_per_second=4.56188G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):21/manual_time_mean 428102 ns 854564 ns 5 bytes=2.09715M bytes_per_second=4.56229G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):21/manual_time_median 428125 ns 854476 ns 5 bytes=2.09715M bytes_per_second=4.56204G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):21/manual_time_stddev 251 ns 411 ns 5 bytes=0 bytes_per_second=2.73786M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):21/manual_time_cv 0.06 % 0.05 % 5 bytes=0.00% bytes_per_second=0.06% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):22/manual_time 807061 ns 1475443 ns 867 bytes=4.1943M bytes_per_second=4.84009G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):22/manual_time 807193 ns 1476032 ns 867 bytes=4.1943M bytes_per_second=4.8393G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):22/manual_time 806957 ns 1475212 ns 867 bytes=4.1943M bytes_per_second=4.84072G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):22/manual_time 807206 ns 1476170 ns 867 bytes=4.1943M bytes_per_second=4.83922G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):22/manual_time 807334 ns 1475655 ns 867 bytes=4.1943M bytes_per_second=4.83846G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):22/manual_time_mean 807150 ns 1475702 ns 5 bytes=4.1943M bytes_per_second=4.83956G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):22/manual_time_median 807193 ns 1475655 ns 5 bytes=4.1943M bytes_per_second=4.8393G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):22/manual_time_stddev 145 ns 399 ns 5 bytes=0 bytes_per_second=911.893k/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):22/manual_time_cv 0.02 % 0.03 % 5 bytes=0.00% bytes_per_second=0.02% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):23/manual_time 1575980 ns 2729735 ns 444 bytes=8.38861M bytes_per_second=4.95723G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):23/manual_time 1577158 ns 2735197 ns 444 bytes=8.38861M bytes_per_second=4.95353G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):23/manual_time 1580035 ns 2736844 ns 444 bytes=8.38861M bytes_per_second=4.94451G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):23/manual_time 1577732 ns 2737107 ns 444 bytes=8.38861M bytes_per_second=4.95173G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):23/manual_time 1580360 ns 2736941 ns 444 bytes=8.38861M bytes_per_second=4.94349G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):23/manual_time_mean 1578253 ns 2735165 ns 5 bytes=8.38861M bytes_per_second=4.9501G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):23/manual_time_median 1577732 ns 2736844 ns 5 bytes=8.38861M bytes_per_second=4.95173G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):23/manual_time_stddev 1887 ns 3131 ns 5 bytes=0 bytes_per_second=6.06148M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):23/manual_time_cv 0.12 % 0.11 % 5 bytes=0.00% bytes_per_second=0.12% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):24/manual_time 3173115 ns 5344197 ns 220 bytes=16.7772M bytes_per_second=4.92418G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):24/manual_time 3182228 ns 5364157 ns 220 bytes=16.7772M bytes_per_second=4.91008G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):24/manual_time 3172605 ns 5345182 ns 220 bytes=16.7772M bytes_per_second=4.92497G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):24/manual_time 3173060 ns 5346755 ns 220 bytes=16.7772M bytes_per_second=4.92427G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):24/manual_time 3173764 ns 5346094 ns 220 bytes=16.7772M bytes_per_second=4.92318G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):24/manual_time_mean 3174954 ns 5349277 ns 5 bytes=16.7772M bytes_per_second=4.92134G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):24/manual_time_median 3173115 ns 5346094 ns 5 bytes=16.7772M bytes_per_second=4.92418G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):24/manual_time_stddev 4087 ns 8374 ns 5 bytes=0 bytes_per_second=6.47642M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):24/manual_time_cv 0.13 % 0.16 % 5 bytes=0.00% bytes_per_second=0.13% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):25/manual_time 6710074 ns 10978727 ns 102 bytes=33.5544M bytes_per_second=4.65718G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):25/manual_time 6590351 ns 10749629 ns 102 bytes=33.5544M bytes_per_second=4.74178G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):25/manual_time 6790222 ns 11144646 ns 102 bytes=33.5544M bytes_per_second=4.60221G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):25/manual_time 6693872 ns 10958121 ns 102 bytes=33.5544M bytes_per_second=4.66845G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):25/manual_time 6654882 ns 10872203 ns 102 bytes=33.5544M bytes_per_second=4.6958G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):25/manual_time_mean 6687880 ns 10940665 ns 5 bytes=33.5544M bytes_per_second=4.67308G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):25/manual_time_median 6693872 ns 10958121 ns 5 bytes=33.5544M bytes_per_second=4.66845G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):25/manual_time_stddev 73490 ns 145381 ns 5 bytes=0 bytes_per_second=52.5481M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):25/manual_time_cv 1.10 % 1.33 % 5 bytes=0.00% bytes_per_second=1.10% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):26/manual_time 14027418 ns 22831178 ns 51 bytes=67.1089M bytes_per_second=4.45556G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):26/manual_time 14021498 ns 22821029 ns 51 bytes=67.1089M bytes_per_second=4.45744G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):26/manual_time 14020209 ns 22810221 ns 51 bytes=67.1089M bytes_per_second=4.45785G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):26/manual_time 13984701 ns 22771878 ns 51 bytes=67.1089M bytes_per_second=4.46917G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):26/manual_time 14006904 ns 22796106 ns 51 bytes=67.1089M bytes_per_second=4.46209G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):26/manual_time_mean 14012146 ns 22806082 ns 5 bytes=67.1089M bytes_per_second=4.46042G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):26/manual_time_median 14020209 ns 22810221 ns 5 bytes=67.1089M bytes_per_second=4.45785G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):26/manual_time_stddev 17076 ns 23129 ns 5 bytes=0 bytes_per_second=5.57174M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):26/manual_time_cv 0.12 % 0.10 % 5 bytes=0.00% bytes_per_second=0.12% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):27/manual_time 26351949 ns 42719198 ns 27 bytes=134.218M bytes_per_second=4.74348G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):27/manual_time 26401040 ns 42821852 ns 27 bytes=134.218M bytes_per_second=4.73466G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):27/manual_time 26381698 ns 42738681 ns 27 bytes=134.218M bytes_per_second=4.73813G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):27/manual_time 26398586 ns 42747790 ns 27 bytes=134.218M bytes_per_second=4.7351G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):27/manual_time 26385704 ns 42732626 ns 27 bytes=134.218M bytes_per_second=4.73741G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):27/manual_time_mean 26383795 ns 42752029 ns 5 bytes=134.218M bytes_per_second=4.73776G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):27/manual_time_median 26385704 ns 42738681 ns 5 bytes=134.218M bytes_per_second=4.73741G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):27/manual_time_stddev 19611 ns 40391 ns 5 bytes=0 bytes_per_second=3.60819M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):27/manual_time_cv 0.07 % 0.09 % 5 bytes=0.00% bytes_per_second=0.07% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):28/manual_time 50603139 ns 80306016 ns 10 bytes=268.435M bytes_per_second=4.9404G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):28/manual_time 50435475 ns 80080427 ns 10 bytes=268.435M bytes_per_second=4.95683G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):28/manual_time 50612308 ns 80219879 ns 10 bytes=268.435M bytes_per_second=4.93951G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):28/manual_time 50526370 ns 80143898 ns 10 bytes=268.435M bytes_per_second=4.94791G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):28/manual_time 50460274 ns 80097572 ns 10 bytes=268.435M bytes_per_second=4.95439G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):28/manual_time_mean 50527513 ns 80169558 ns 5 bytes=268.435M bytes_per_second=4.94781G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):28/manual_time_median 50526370 ns 80143898 ns 5 bytes=268.435M bytes_per_second=4.94791G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):28/manual_time_stddev 80472 ns 93458 ns 5 bytes=0 bytes_per_second=8.06944M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):28/manual_time_cv 0.16 % 0.12 % 5 bytes=0.00% bytes_per_second=0.16% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):29/manual_time 99050653 ns 156039621 ns 8 bytes=536.871M bytes_per_second=5.04792G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):29/manual_time 99029912 ns 155947654 ns 8 bytes=536.871M bytes_per_second=5.04898G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):29/manual_time 98958233 ns 156041481 ns 8 bytes=536.871M bytes_per_second=5.05264G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):29/manual_time 99049472 ns 156145311 ns 8 bytes=536.871M bytes_per_second=5.04798G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):29/manual_time 98944511 ns 156013351 ns 8 bytes=536.871M bytes_per_second=5.05334G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):29/manual_time_mean 99006556 ns 156037483 ns 5 bytes=536.871M bytes_per_second=5.05017G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):29/manual_time_median 99029912 ns 156039621 ns 5 bytes=536.871M bytes_per_second=5.04898G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):29/manual_time_stddev 51275 ns 71237 ns 5 bytes=0 bytes_per_second=2.67867M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):29/manual_time_cv 0.05 % 0.05 % 5 bytes=0.00% bytes_per_second=0.05% hip_id=-nan% numa_id=-nan% +Comm_prefetch_managed_HostToGPU/0/0/log2(N):30/manual_time 176006086 ns 282514937 ns 4 bytes=1073.74M bytes_per_second=5.68162G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):30/manual_time 176396493 ns 282857366 ns 4 bytes=1073.74M bytes_per_second=5.66905G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):30/manual_time 176149722 ns 282453645 ns 4 bytes=1073.74M bytes_per_second=5.67699G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):30/manual_time 176305447 ns 282722920 ns 4 bytes=1073.74M bytes_per_second=5.67197G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):30/manual_time 176194366 ns 282943784 ns 4 bytes=1073.74M bytes_per_second=5.67555G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):30/manual_time_mean 176210423 ns 282698530 ns 5 bytes=1073.74M bytes_per_second=5.67504G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):30/manual_time_median 176194366 ns 282722920 ns 5 bytes=1073.74M bytes_per_second=5.67555G/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):30/manual_time_stddev 149455 ns 211925 ns 5 bytes=0 bytes_per_second=4.92934M/s hip_id=0 numa_id=0 +Comm_prefetch_managed_HostToGPU/0/0/log2(N):30/manual_time_cv 0.08 % 0.07 % 5 bytes=0.00% bytes_per_second=0.08% hip_id=-nan% numa_id=-nan% +[2023-10-09 17:51:28.132] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 17:51:28.132] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Mon 09 Oct 2023 05:51:28 PM EDT diff --git a/results/r8-1465535.out b/results/r8-1465535.out new file mode 100644 index 0000000..796e595 --- /dev/null +++ b/results/r8-1465535.out @@ -0,0 +1,31 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 05:44:31 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:44:32.336] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:44:32.337] [scope] [info] recorded CPU goveror +[2023-10-09 17:44:32.337] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:44:32.337] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:44:34-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1795.58 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.39, 3.82, 18.50 +srun: error: frontier10439: task 0: Segmentation fault (core dumped) +srun: Terminating StepId=1465535.0 +Mon 09 Oct 2023 05:44:40 PM EDT diff --git a/results/r9-1465536.out b/results/r9-1465536.out new file mode 100644 index 0000000..d9bfd42 --- /dev/null +++ b/results/r9-1465536.out @@ -0,0 +1,1402 @@ + +Lmod is automatically replacing "cce/15.0.0" with "amd/5.3.0". + + +Lmod is automatically replacing "PrgEnv-cray/8.3.3" with "PrgEnv-amd/8.3.3". + + +Due to MODULEPATH changes, the following have been reloaded: + 1) cray-mpich/8.1.23 + +Mon 09 Oct 2023 05:45:29 PM EDT +Comm|Scope 0.12.0 v0.12.0@124999d + scope 1.1.2 HEAD@124999d + spdlog 1.6.1 + benchmark 1.5.1 +[2023-10-09 17:45:31.397] [scope] [info] recorded system CPU turbo state +[2023-10-09 17:45:31.398] [scope] [info] recorded CPU goveror +[2023-10-09 17:45:31.398] [scope] [error] unable to disable CPU turbo: no permission. Run with higher privileges? +[2023-10-09 17:45:31.398] [scope] [error] unable to set OS CPU governor to maximum: no permission. Run with higher privileges? +2023-10-09T17:45:33-04:00 +Running /lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope +Run on (128 X 1795.92 MHz CPU s) +CPU Caches: + L1 Data 32 KiB (x64) + L1 Instruction 32 KiB (x64) + L2 Unified 512 KiB (x64) + L3 Unified 32768 KiB (x8) +Load Average: 0.29, 3.20, 19.10 +-------------------------------------------------------------------------------------------------------------------------- +Benchmark Time CPU Iterations UserCounters... +-------------------------------------------------------------------------------------------------------------------------- +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):12/manual_time 12267 ns 28660 ns 57046 bytes=4.096k bytes_per_second=318.429M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):12/manual_time 12267 ns 28686 ns 57046 bytes=4.096k bytes_per_second=318.426M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):12/manual_time 12267 ns 28643 ns 57046 bytes=4.096k bytes_per_second=318.44M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):12/manual_time 12268 ns 28659 ns 57046 bytes=4.096k bytes_per_second=318.411M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):12/manual_time 12271 ns 28656 ns 57046 bytes=4.096k bytes_per_second=318.343M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):12/manual_time_mean 12268 ns 28661 ns 5 bytes=4.096k bytes_per_second=318.41M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):12/manual_time_median 12267 ns 28659 ns 5 bytes=4.096k bytes_per_second=318.426M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):12/manual_time_stddev 1.49 ns 15.5 ns 5 bytes=0 bytes_per_second=39.5298k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):12/manual_time_cv 0.01 % 0.05 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):13/manual_time 12266 ns 28631 ns 57079 bytes=8.192k bytes_per_second=636.903M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):13/manual_time 12262 ns 28662 ns 57079 bytes=8.192k bytes_per_second=637.115M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):13/manual_time 12262 ns 28634 ns 57079 bytes=8.192k bytes_per_second=637.148M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):13/manual_time 12266 ns 28639 ns 57079 bytes=8.192k bytes_per_second=636.943M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):13/manual_time 12265 ns 28624 ns 57079 bytes=8.192k bytes_per_second=636.989M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):13/manual_time_mean 12264 ns 28638 ns 5 bytes=8.192k bytes_per_second=637.02M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):13/manual_time_median 12265 ns 28634 ns 5 bytes=8.192k bytes_per_second=636.989M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):13/manual_time_stddev 2.06 ns 14.1 ns 5 bytes=0 bytes_per_second=109.726k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):13/manual_time_cv 0.02 % 0.05 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):14/manual_time 12259 ns 28883 ns 57092 bytes=16.384k bytes_per_second=1.24465G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):14/manual_time 12262 ns 28931 ns 57092 bytes=16.384k bytes_per_second=1.24435G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):14/manual_time 12255 ns 28862 ns 57092 bytes=16.384k bytes_per_second=1.2451G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):14/manual_time 12259 ns 28872 ns 57092 bytes=16.384k bytes_per_second=1.24472G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):14/manual_time 12260 ns 28873 ns 57092 bytes=16.384k bytes_per_second=1.24457G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):14/manual_time_mean 12259 ns 28884 ns 5 bytes=16.384k bytes_per_second=1.24468G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):14/manual_time_median 12259 ns 28873 ns 5 bytes=16.384k bytes_per_second=1.24465G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):14/manual_time_stddev 2.70 ns 27.2 ns 5 bytes=0 bytes_per_second=286.974k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):14/manual_time_cv 0.02 % 0.09 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):15/manual_time 12271 ns 29220 ns 57059 bytes=32.768k bytes_per_second=2.487G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):15/manual_time 12270 ns 29266 ns 57059 bytes=32.768k bytes_per_second=2.48723G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):15/manual_time 12263 ns 29196 ns 57059 bytes=32.768k bytes_per_second=2.4886G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):15/manual_time 12272 ns 29219 ns 57059 bytes=32.768k bytes_per_second=2.48679G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):15/manual_time 12271 ns 29293 ns 57059 bytes=32.768k bytes_per_second=2.48706G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):15/manual_time_mean 12269 ns 29239 ns 5 bytes=32.768k bytes_per_second=2.48734G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):15/manual_time_median 12271 ns 29220 ns 5 bytes=32.768k bytes_per_second=2.48706G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):15/manual_time_stddev 3.56 ns 39.8 ns 5 bytes=0 bytes_per_second=757.416k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):15/manual_time_cv 0.03 % 0.14 % 5 bytes=0.00% bytes_per_second=0.03% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):16/manual_time 12270 ns 29963 ns 57040 bytes=65.536k bytes_per_second=4.97452G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):16/manual_time 12269 ns 29999 ns 57040 bytes=65.536k bytes_per_second=4.97487G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):16/manual_time 12270 ns 29891 ns 57040 bytes=65.536k bytes_per_second=4.97418G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):16/manual_time 12272 ns 29900 ns 57040 bytes=65.536k bytes_per_second=4.97359G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):16/manual_time 12271 ns 29890 ns 57040 bytes=65.536k bytes_per_second=4.97385G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):16/manual_time_mean 12270 ns 29929 ns 5 bytes=65.536k bytes_per_second=4.9742G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):16/manual_time_median 12270 ns 29900 ns 5 bytes=65.536k bytes_per_second=4.97418G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):16/manual_time_stddev 1.26 ns 49.7 ns 5 bytes=0 bytes_per_second=534.458k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):16/manual_time_cv 0.01 % 0.17 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):17/manual_time 12283 ns 31169 ns 57017 bytes=131.072k bytes_per_second=9.93793G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):17/manual_time 12265 ns 31219 ns 57017 bytes=131.072k bytes_per_second=9.95237G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):17/manual_time 12276 ns 31179 ns 57017 bytes=131.072k bytes_per_second=9.94413G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):17/manual_time 12275 ns 31187 ns 57017 bytes=131.072k bytes_per_second=9.9445G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):17/manual_time 12278 ns 31194 ns 57017 bytes=131.072k bytes_per_second=9.94222G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):17/manual_time_mean 12275 ns 31190 ns 5 bytes=131.072k bytes_per_second=9.94423G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):17/manual_time_median 12276 ns 31187 ns 5 bytes=131.072k bytes_per_second=9.94413G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):17/manual_time_stddev 6.47 ns 19.1 ns 5 bytes=0 bytes_per_second=5.36988M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):17/manual_time_cv 0.05 % 0.06 % 5 bytes=0.00% bytes_per_second=0.05% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):18/manual_time 12502 ns 32938 ns 55980 bytes=262.144k bytes_per_second=19.5278G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):18/manual_time 12504 ns 32993 ns 55980 bytes=262.144k bytes_per_second=19.5253G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):18/manual_time 12495 ns 32944 ns 55980 bytes=262.144k bytes_per_second=19.5393G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):18/manual_time 12498 ns 32939 ns 55980 bytes=262.144k bytes_per_second=19.5344G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):18/manual_time 12498 ns 32958 ns 55980 bytes=262.144k bytes_per_second=19.5342G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):18/manual_time_mean 12499 ns 32955 ns 5 bytes=262.144k bytes_per_second=19.5322G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):18/manual_time_median 12498 ns 32944 ns 5 bytes=262.144k bytes_per_second=19.5342G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):18/manual_time_stddev 3.59 ns 23.2 ns 5 bytes=0 bytes_per_second=5.74242M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):18/manual_time_cv 0.03 % 0.07 % 5 bytes=0.00% bytes_per_second=0.03% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):19/manual_time 12548 ns 33048 ns 55774 bytes=524.288k bytes_per_second=38.9139G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):19/manual_time 12549 ns 33089 ns 55774 bytes=524.288k bytes_per_second=38.9102G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):19/manual_time 12549 ns 33068 ns 55774 bytes=524.288k bytes_per_second=38.9111G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):19/manual_time 12545 ns 33038 ns 55774 bytes=524.288k bytes_per_second=38.9213G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):19/manual_time 12542 ns 33055 ns 55774 bytes=524.288k bytes_per_second=38.9329G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):19/manual_time_mean 12546 ns 33060 ns 5 bytes=524.288k bytes_per_second=38.9179G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):19/manual_time_median 12548 ns 33055 ns 5 bytes=524.288k bytes_per_second=38.9139G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):19/manual_time_stddev 3.06 ns 19.7 ns 5 bytes=0 bytes_per_second=9.7213M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):19/manual_time_cv 0.02 % 0.06 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):20/manual_time 12623 ns 33160 ns 55465 bytes=1048.58k bytes_per_second=77.3647G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):20/manual_time 12611 ns 33212 ns 55465 bytes=1048.58k bytes_per_second=77.4382G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):20/manual_time 12624 ns 33151 ns 55465 bytes=1048.58k bytes_per_second=77.3595G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):20/manual_time 12625 ns 33155 ns 55465 bytes=1048.58k bytes_per_second=77.353G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):20/manual_time 12629 ns 33148 ns 55465 bytes=1048.58k bytes_per_second=77.3247G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):20/manual_time_mean 12622 ns 33165 ns 5 bytes=1048.58k bytes_per_second=77.368G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):20/manual_time_median 12624 ns 33155 ns 5 bytes=1048.58k bytes_per_second=77.3595G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):20/manual_time_stddev 6.88 ns 26.5 ns 5 bytes=0 bytes_per_second=43.1929M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):20/manual_time_cv 0.05 % 0.08 % 5 bytes=0.00% bytes_per_second=0.05% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):21/manual_time 12789 ns 33555 ns 54855 bytes=2.09715M bytes_per_second=152.722G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):21/manual_time 12790 ns 33588 ns 54855 bytes=2.09715M bytes_per_second=152.709G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):21/manual_time 12759 ns 33483 ns 54855 bytes=2.09715M bytes_per_second=153.074G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):21/manual_time 12758 ns 33470 ns 54855 bytes=2.09715M bytes_per_second=153.091G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):21/manual_time 12784 ns 33551 ns 54855 bytes=2.09715M bytes_per_second=152.774G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):21/manual_time_mean 12776 ns 33529 ns 5 bytes=2.09715M bytes_per_second=152.874G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):21/manual_time_median 12784 ns 33551 ns 5 bytes=2.09715M bytes_per_second=152.774G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):21/manual_time_stddev 16.0 ns 50.2 ns 5 bytes=0 bytes_per_second=196.641M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):21/manual_time_cv 0.13 % 0.15 % 5 bytes=0.00% bytes_per_second=0.13% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):22/manual_time 13379 ns 34667 ns 52432 bytes=4.1943M bytes_per_second=291.968G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):22/manual_time 13353 ns 34652 ns 52432 bytes=4.1943M bytes_per_second=292.538G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):22/manual_time 13377 ns 34658 ns 52432 bytes=4.1943M bytes_per_second=292.021G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):22/manual_time 13347 ns 34624 ns 52432 bytes=4.1943M bytes_per_second=292.663G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):22/manual_time 13375 ns 34636 ns 52432 bytes=4.1943M bytes_per_second=292.058G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):22/manual_time_mean 13366 ns 34647 ns 5 bytes=4.1943M bytes_per_second=292.249G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):22/manual_time_median 13375 ns 34652 ns 5 bytes=4.1943M bytes_per_second=292.058G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):22/manual_time_stddev 14.9 ns 17.5 ns 5 bytes=0 bytes_per_second=332.732M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):22/manual_time_cv 0.11 % 0.05 % 5 bytes=0.00% bytes_per_second=0.11% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):23/manual_time 14473 ns 37737 ns 48505 bytes=8.38861M bytes_per_second=539.816G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):23/manual_time 14416 ns 37734 ns 48505 bytes=8.38861M bytes_per_second=541.924G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):23/manual_time 14436 ns 37691 ns 48505 bytes=8.38861M bytes_per_second=541.174G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):23/manual_time 14406 ns 37692 ns 48505 bytes=8.38861M bytes_per_second=542.318G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):23/manual_time 14464 ns 37745 ns 48505 bytes=8.38861M bytes_per_second=540.117G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):23/manual_time_mean 14439 ns 37720 ns 5 bytes=8.38861M bytes_per_second=541.07G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):23/manual_time_median 14436 ns 37734 ns 5 bytes=8.38861M bytes_per_second=541.174G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):23/manual_time_stddev 29.2 ns 26.1 ns 5 bytes=0 bytes_per_second=1119.04M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):23/manual_time_cv 0.20 % 0.07 % 5 bytes=0.00% bytes_per_second=0.20% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):24/manual_time 20768 ns 49479 ns 33722 bytes=16.7772M bytes_per_second=752.362G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):24/manual_time 20762 ns 49471 ns 33722 bytes=16.7772M bytes_per_second=752.572G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):24/manual_time 20768 ns 49478 ns 33722 bytes=16.7772M bytes_per_second=752.342G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):24/manual_time 20764 ns 49428 ns 33722 bytes=16.7772M bytes_per_second=752.494G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):24/manual_time 20766 ns 49463 ns 33722 bytes=16.7772M bytes_per_second=752.418G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):24/manual_time_mean 20766 ns 49464 ns 5 bytes=16.7772M bytes_per_second=752.438G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):24/manual_time_median 20766 ns 49471 ns 5 bytes=16.7772M bytes_per_second=752.418G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):24/manual_time_stddev 2.64 ns 21.2 ns 5 bytes=0 bytes_per_second=97.8441M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):24/manual_time_cv 0.01 % 0.04 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):25/manual_time 32661 ns 73498 ns 21432 bytes=33.5544M bytes_per_second=956.801G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):25/manual_time 32659 ns 73514 ns 21432 bytes=33.5544M bytes_per_second=956.852G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):25/manual_time 32660 ns 73457 ns 21432 bytes=33.5544M bytes_per_second=956.827G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):25/manual_time 32660 ns 73456 ns 21432 bytes=33.5544M bytes_per_second=956.832G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):25/manual_time 32649 ns 73475 ns 21432 bytes=33.5544M bytes_per_second=957.153G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):25/manual_time_mean 32658 ns 73480 ns 5 bytes=33.5544M bytes_per_second=956.893G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):25/manual_time_median 32660 ns 73475 ns 5 bytes=33.5544M bytes_per_second=956.832G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):25/manual_time_stddev 5.00 ns 25.5 ns 5 bytes=0 bytes_per_second=149.99M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):25/manual_time_cv 0.02 % 0.03 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):26/manual_time 59709 ns 124590 ns 11732 bytes=67.1089M bytes_per_second=1046.74G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):26/manual_time 59742 ns 124652 ns 11732 bytes=67.1089M bytes_per_second=1046.16G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):26/manual_time 59726 ns 124587 ns 11732 bytes=67.1089M bytes_per_second=1046.45G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):26/manual_time 59720 ns 124663 ns 11732 bytes=67.1089M bytes_per_second=1046.55G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):26/manual_time 59708 ns 124605 ns 11732 bytes=67.1089M bytes_per_second=1046.76G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):26/manual_time_mean 59721 ns 124619 ns 5 bytes=67.1089M bytes_per_second=1046.53G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):26/manual_time_median 59720 ns 124605 ns 5 bytes=67.1089M bytes_per_second=1046.55G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):26/manual_time_stddev 14.1 ns 35.8 ns 5 bytes=0 bytes_per_second=252.301M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):26/manual_time_cv 0.02 % 0.03 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):27/manual_time 109614 ns 221839 ns 6385 bytes=134.218M bytes_per_second=1.11364T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):27/manual_time 109595 ns 221839 ns 6385 bytes=134.218M bytes_per_second=1.11383T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):27/manual_time 109585 ns 221779 ns 6385 bytes=134.218M bytes_per_second=1.11393T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):27/manual_time 109627 ns 221810 ns 6385 bytes=134.218M bytes_per_second=1.11351T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):27/manual_time 109603 ns 221820 ns 6385 bytes=134.218M bytes_per_second=1.11375T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):27/manual_time_mean 109605 ns 221817 ns 5 bytes=134.218M bytes_per_second=1.11373T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):27/manual_time_median 109603 ns 221820 ns 5 bytes=134.218M bytes_per_second=1.11375T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):27/manual_time_stddev 16.3 ns 25.0 ns 5 bytes=0 bytes_per_second=173.595M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):27/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):28/manual_time 213660 ns 421660 ns 3274 bytes=268.435M bytes_per_second=1.14266T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):28/manual_time 213647 ns 421678 ns 3274 bytes=268.435M bytes_per_second=1.14273T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):28/manual_time 213631 ns 421801 ns 3274 bytes=268.435M bytes_per_second=1.14282T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):28/manual_time 213667 ns 421742 ns 3274 bytes=268.435M bytes_per_second=1.14262T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):28/manual_time 213674 ns 421770 ns 3274 bytes=268.435M bytes_per_second=1.14259T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):28/manual_time_mean 213655 ns 421730 ns 5 bytes=268.435M bytes_per_second=1.14268T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):28/manual_time_median 213660 ns 421742 ns 5 bytes=268.435M bytes_per_second=1.14266T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):28/manual_time_stddev 17.1 ns 60.2 ns 5 bytes=0 bytes_per_second=95.7543M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):28/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):29/manual_time 439388 ns 836600 ns 1591 bytes=536.871M bytes_per_second=1.11128T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):29/manual_time 439657 ns 836835 ns 1591 bytes=536.871M bytes_per_second=1.11059T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):29/manual_time 439921 ns 837141 ns 1591 bytes=536.871M bytes_per_second=1.10993T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):29/manual_time 439891 ns 837094 ns 1591 bytes=536.871M bytes_per_second=1.11T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):29/manual_time 440687 ns 837939 ns 1591 bytes=536.871M bytes_per_second=1.108T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):29/manual_time_mean 439909 ns 837122 ns 5 bytes=536.871M bytes_per_second=1.10996T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):29/manual_time_median 439891 ns 837094 ns 5 bytes=536.871M bytes_per_second=1.11T/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):29/manual_time_stddev 485 ns 506 ns 5 bytes=0 bytes_per_second=1.25198G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):29/manual_time_cv 0.11 % 0.06 % 5 bytes=0.00% bytes_per_second=0.11% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):30/manual_time 966570 ns 1743446 ns 718 bytes=1073.74M bytes_per_second=1034.59G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):30/manual_time 964082 ns 1740899 ns 718 bytes=1073.74M bytes_per_second=1037.26G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):30/manual_time 967090 ns 1744062 ns 718 bytes=1073.74M bytes_per_second=1034.03G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):30/manual_time 963761 ns 1740672 ns 718 bytes=1073.74M bytes_per_second=1037.6G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):30/manual_time 969393 ns 1746423 ns 718 bytes=1073.74M bytes_per_second=1031.57G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):30/manual_time_mean 966179 ns 1743100 ns 5 bytes=1073.74M bytes_per_second=1035.01G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):30/manual_time_median 966570 ns 1743446 ns 5 bytes=1073.74M bytes_per_second=1034.59G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):30/manual_time_stddev 2322 ns 2389 ns 5 bytes=0 bytes_per_second=2.48564G/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/0/log2(N):30/manual_time_cv 0.24 % 0.14 % 5 bytes=0.00% bytes_per_second=0.24% own_gpu=-nan% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):12/manual_time 12278 ns 31260 ns 57071 bytes=4.096k bytes_per_second=318.16M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):12/manual_time 12273 ns 31260 ns 57071 bytes=4.096k bytes_per_second=318.283M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):12/manual_time 12287 ns 31233 ns 57071 bytes=4.096k bytes_per_second=317.912M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):12/manual_time 12283 ns 31248 ns 57071 bytes=4.096k bytes_per_second=318.033M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):12/manual_time 12273 ns 31257 ns 57071 bytes=4.096k bytes_per_second=318.282M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):12/manual_time_mean 12279 ns 31252 ns 5 bytes=4.096k bytes_per_second=318.134M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):12/manual_time_median 12278 ns 31257 ns 5 bytes=4.096k bytes_per_second=318.16M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):12/manual_time_stddev 6.24 ns 11.4 ns 5 bytes=0 bytes_per_second=165.424k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):12/manual_time_cv 0.05 % 0.04 % 5 bytes=0.00% bytes_per_second=0.05% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):13/manual_time 12294 ns 31234 ns 56885 bytes=8.192k bytes_per_second=635.455M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):13/manual_time 12308 ns 31221 ns 56885 bytes=8.192k bytes_per_second=634.733M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):13/manual_time 12288 ns 31236 ns 56885 bytes=8.192k bytes_per_second=635.806M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):13/manual_time 12279 ns 31256 ns 56885 bytes=8.192k bytes_per_second=636.248M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):13/manual_time 12274 ns 31261 ns 56885 bytes=8.192k bytes_per_second=636.486M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):13/manual_time_mean 12289 ns 31242 ns 5 bytes=8.192k bytes_per_second=635.746M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):13/manual_time_median 12288 ns 31236 ns 5 bytes=8.192k bytes_per_second=635.806M/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):13/manual_time_stddev 13.4 ns 16.8 ns 5 bytes=0 bytes_per_second=708.319k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):13/manual_time_cv 0.11 % 0.05 % 5 bytes=0.00% bytes_per_second=0.11% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):14/manual_time 12265 ns 31442 ns 57050 bytes=16.384k bytes_per_second=1.24412G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):14/manual_time 12269 ns 31461 ns 57050 bytes=16.384k bytes_per_second=1.24365G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):14/manual_time 12270 ns 31413 ns 57050 bytes=16.384k bytes_per_second=1.24362G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):14/manual_time 12273 ns 31485 ns 57050 bytes=16.384k bytes_per_second=1.2433G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):14/manual_time 12269 ns 31458 ns 57050 bytes=16.384k bytes_per_second=1.24368G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):14/manual_time_mean 12269 ns 31452 ns 5 bytes=16.384k bytes_per_second=1.24367G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):14/manual_time_median 12269 ns 31458 ns 5 bytes=16.384k bytes_per_second=1.24365G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):14/manual_time_stddev 2.87 ns 26.7 ns 5 bytes=0 bytes_per_second=305.406k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):14/manual_time_cv 0.02 % 0.08 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):15/manual_time 12286 ns 32066 ns 56968 bytes=32.768k bytes_per_second=2.484G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):15/manual_time 12286 ns 32039 ns 56968 bytes=32.768k bytes_per_second=2.48385G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):15/manual_time 12285 ns 32044 ns 56968 bytes=32.768k bytes_per_second=2.48412G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):15/manual_time 12291 ns 32081 ns 56968 bytes=32.768k bytes_per_second=2.48296G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):15/manual_time 12291 ns 32048 ns 56968 bytes=32.768k bytes_per_second=2.48293G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):15/manual_time_mean 12288 ns 32056 ns 5 bytes=32.768k bytes_per_second=2.48357G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):15/manual_time_median 12286 ns 32048 ns 5 bytes=32.768k bytes_per_second=2.48385G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):15/manual_time_stddev 2.88 ns 17.7 ns 5 bytes=0 bytes_per_second=609.616k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):15/manual_time_cv 0.02 % 0.06 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):16/manual_time 12302 ns 32745 ns 56912 bytes=65.536k bytes_per_second=4.96134G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):16/manual_time 12301 ns 32723 ns 56912 bytes=65.536k bytes_per_second=4.96187G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):16/manual_time 12302 ns 32756 ns 56912 bytes=65.536k bytes_per_second=4.96143G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):16/manual_time 12301 ns 32699 ns 56912 bytes=65.536k bytes_per_second=4.9618G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):16/manual_time 12303 ns 32722 ns 56912 bytes=65.536k bytes_per_second=4.96108G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):16/manual_time_mean 12302 ns 32729 ns 5 bytes=65.536k bytes_per_second=4.9615G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):16/manual_time_median 12302 ns 32723 ns 5 bytes=65.536k bytes_per_second=4.96143G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):16/manual_time_stddev 0.818 ns 22.0 ns 5 bytes=0 bytes_per_second=346.057k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):16/manual_time_cv 0.01 % 0.07 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):17/manual_time 12307 ns 34105 ns 56875 bytes=131.072k bytes_per_second=9.91892G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):17/manual_time 12306 ns 34084 ns 56875 bytes=131.072k bytes_per_second=9.91969G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):17/manual_time 12307 ns 34071 ns 56875 bytes=131.072k bytes_per_second=9.91902G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):17/manual_time 12304 ns 34047 ns 56875 bytes=131.072k bytes_per_second=9.92143G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):17/manual_time 12304 ns 34094 ns 56875 bytes=131.072k bytes_per_second=9.92112G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):17/manual_time_mean 12305 ns 34080 ns 5 bytes=131.072k bytes_per_second=9.92003G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):17/manual_time_median 12306 ns 34084 ns 5 bytes=131.072k bytes_per_second=9.91969G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):17/manual_time_stddev 1.46 ns 22.5 ns 5 bytes=0 bytes_per_second=1.20188M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):17/manual_time_cv 0.01 % 0.07 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):18/manual_time 12536 ns 35717 ns 55847 bytes=262.144k bytes_per_second=19.4745G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):18/manual_time 12537 ns 35723 ns 55847 bytes=262.144k bytes_per_second=19.4731G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):18/manual_time 12532 ns 35650 ns 55847 bytes=262.144k bytes_per_second=19.4808G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):18/manual_time 12532 ns 35715 ns 55847 bytes=262.144k bytes_per_second=19.4816G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):18/manual_time 12535 ns 35650 ns 55847 bytes=262.144k bytes_per_second=19.4764G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):18/manual_time_mean 12535 ns 35691 ns 5 bytes=262.144k bytes_per_second=19.4773G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):18/manual_time_median 12535 ns 35715 ns 5 bytes=262.144k bytes_per_second=19.4764G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):18/manual_time_stddev 2.42 ns 37.5 ns 5 bytes=0 bytes_per_second=3.85323M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):18/manual_time_cv 0.02 % 0.11 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):19/manual_time 15772 ns 38949 ns 44386 bytes=524.288k bytes_per_second=30.9582G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):19/manual_time 15773 ns 38997 ns 44386 bytes=524.288k bytes_per_second=30.9574G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):19/manual_time 15771 ns 38961 ns 44386 bytes=524.288k bytes_per_second=30.9607G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):19/manual_time 15769 ns 38953 ns 44386 bytes=524.288k bytes_per_second=30.9652G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):19/manual_time 15768 ns 38946 ns 44386 bytes=524.288k bytes_per_second=30.9662G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):19/manual_time_mean 15771 ns 38961 ns 5 bytes=524.288k bytes_per_second=30.9615G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):19/manual_time_median 15771 ns 38953 ns 5 bytes=524.288k bytes_per_second=30.9607G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):19/manual_time_stddev 2.04 ns 20.9 ns 5 bytes=0 bytes_per_second=4.09406M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):19/manual_time_cv 0.01 % 0.05 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):20/manual_time 19277 ns 42949 ns 36315 bytes=1048.58k bytes_per_second=50.6605G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):20/manual_time 19284 ns 42898 ns 36315 bytes=1048.58k bytes_per_second=50.6408G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):20/manual_time 19287 ns 42904 ns 36315 bytes=1048.58k bytes_per_second=50.6319G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):20/manual_time 19285 ns 42932 ns 36315 bytes=1048.58k bytes_per_second=50.6386G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):20/manual_time 19287 ns 42881 ns 36315 bytes=1048.58k bytes_per_second=50.6324G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):20/manual_time_mean 19284 ns 42913 ns 5 bytes=1048.58k bytes_per_second=50.6408G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):20/manual_time_median 19285 ns 42904 ns 5 bytes=1048.58k bytes_per_second=50.6386G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):20/manual_time_stddev 4.43 ns 27.4 ns 5 bytes=0 bytes_per_second=11.9149M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):20/manual_time_cv 0.02 % 0.06 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):21/manual_time 26191 ns 50755 ns 26681 bytes=2.09715M bytes_per_second=74.5726G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):21/manual_time 26296 ns 50887 ns 26681 bytes=2.09715M bytes_per_second=74.2739G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):21/manual_time 26152 ns 50699 ns 26681 bytes=2.09715M bytes_per_second=74.6822G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):21/manual_time 26223 ns 50809 ns 26681 bytes=2.09715M bytes_per_second=74.4808G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):21/manual_time 26292 ns 50913 ns 26681 bytes=2.09715M bytes_per_second=74.2851G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):21/manual_time_mean 26231 ns 50813 ns 5 bytes=2.09715M bytes_per_second=74.4589G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):21/manual_time_median 26223 ns 50809 ns 5 bytes=2.09715M bytes_per_second=74.4808G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):21/manual_time_stddev 62.9 ns 89.1 ns 5 bytes=0 bytes_per_second=182.991M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):21/manual_time_cv 0.24 % 0.18 % 5 bytes=0.00% bytes_per_second=0.24% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):22/manual_time 36770 ns 62625 ns 19019 bytes=4.1943M bytes_per_second=106.236G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):22/manual_time 36810 ns 62626 ns 19019 bytes=4.1943M bytes_per_second=106.121G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):22/manual_time 36776 ns 62572 ns 19019 bytes=4.1943M bytes_per_second=106.218G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):22/manual_time 36808 ns 62649 ns 19019 bytes=4.1943M bytes_per_second=106.125G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):22/manual_time 36779 ns 62637 ns 19019 bytes=4.1943M bytes_per_second=106.208G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):22/manual_time_mean 36788 ns 62622 ns 5 bytes=4.1943M bytes_per_second=106.181G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):22/manual_time_median 36779 ns 62626 ns 5 bytes=4.1943M bytes_per_second=106.208G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):22/manual_time_stddev 18.9 ns 29.5 ns 5 bytes=0 bytes_per_second=55.8289M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):22/manual_time_cv 0.05 % 0.05 % 5 bytes=0.00% bytes_per_second=0.05% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):23/manual_time 64473 ns 92192 ns 10852 bytes=8.38861M bytes_per_second=121.175G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):23/manual_time 64500 ns 92155 ns 10852 bytes=8.38861M bytes_per_second=121.124G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):23/manual_time 64463 ns 92073 ns 10852 bytes=8.38861M bytes_per_second=121.194G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):23/manual_time 64487 ns 92122 ns 10852 bytes=8.38861M bytes_per_second=121.148G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):23/manual_time 64465 ns 92084 ns 10852 bytes=8.38861M bytes_per_second=121.189G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):23/manual_time_mean 64478 ns 92125 ns 5 bytes=8.38861M bytes_per_second=121.166G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):23/manual_time_median 64473 ns 92122 ns 5 bytes=8.38861M bytes_per_second=121.175G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):23/manual_time_stddev 15.7 ns 49.5 ns 5 bytes=0 bytes_per_second=30.2981M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):23/manual_time_cv 0.02 % 0.05 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):24/manual_time 120492 ns 154211 ns 5811 bytes=16.7772M bytes_per_second=129.677G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):24/manual_time 120487 ns 154179 ns 5811 bytes=16.7772M bytes_per_second=129.683G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):24/manual_time 120523 ns 154134 ns 5811 bytes=16.7772M bytes_per_second=129.643G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):24/manual_time 120478 ns 154141 ns 5811 bytes=16.7772M bytes_per_second=129.692G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):24/manual_time 120517 ns 154167 ns 5811 bytes=16.7772M bytes_per_second=129.65G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):24/manual_time_mean 120499 ns 154166 ns 5 bytes=16.7772M bytes_per_second=129.669G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):24/manual_time_median 120492 ns 154167 ns 5 bytes=16.7772M bytes_per_second=129.677G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):24/manual_time_stddev 19.6 ns 31.1 ns 5 bytes=0 bytes_per_second=21.6063M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):24/manual_time_cv 0.02 % 0.02 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):25/manual_time 229321 ns 274501 ns 3052 bytes=33.5544M bytes_per_second=136.272G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):25/manual_time 229361 ns 274576 ns 3052 bytes=33.5544M bytes_per_second=136.248G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):25/manual_time 229312 ns 274509 ns 3052 bytes=33.5544M bytes_per_second=136.277G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):25/manual_time 229353 ns 274510 ns 3052 bytes=33.5544M bytes_per_second=136.253G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):25/manual_time 229311 ns 274491 ns 3052 bytes=33.5544M bytes_per_second=136.278G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):25/manual_time_mean 229332 ns 274517 ns 5 bytes=33.5544M bytes_per_second=136.266G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):25/manual_time_median 229321 ns 274509 ns 5 bytes=33.5544M bytes_per_second=136.272G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):25/manual_time_stddev 23.7 ns 33.8 ns 5 bytes=0 bytes_per_second=14.4126M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):25/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):26/manual_time 448581 ns 517596 ns 1560 bytes=67.1089M bytes_per_second=139.328G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):26/manual_time 448543 ns 517596 ns 1560 bytes=67.1089M bytes_per_second=139.34G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):26/manual_time 448585 ns 517676 ns 1560 bytes=67.1089M bytes_per_second=139.327G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):26/manual_time 448579 ns 517605 ns 1560 bytes=67.1089M bytes_per_second=139.329G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):26/manual_time 448572 ns 517590 ns 1560 bytes=67.1089M bytes_per_second=139.331G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):26/manual_time_mean 448572 ns 517613 ns 5 bytes=67.1089M bytes_per_second=139.331G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):26/manual_time_median 448579 ns 517596 ns 5 bytes=67.1089M bytes_per_second=139.329G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):26/manual_time_stddev 16.8 ns 35.7 ns 5 bytes=0 bytes_per_second=5.33655M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):26/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):27/manual_time 888499 ns 1004956 ns 788 bytes=134.218M bytes_per_second=140.687G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):27/manual_time 888654 ns 1005161 ns 788 bytes=134.218M bytes_per_second=140.662G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):27/manual_time 888538 ns 1005015 ns 788 bytes=134.218M bytes_per_second=140.681G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):27/manual_time 888588 ns 1005110 ns 788 bytes=134.218M bytes_per_second=140.673G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):27/manual_time 888372 ns 1004813 ns 788 bytes=134.218M bytes_per_second=140.707G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):27/manual_time_mean 888530 ns 1005011 ns 5 bytes=134.218M bytes_per_second=140.682G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):27/manual_time_median 888538 ns 1005015 ns 5 bytes=134.218M bytes_per_second=140.681G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):27/manual_time_stddev 106 ns 137 ns 5 bytes=0 bytes_per_second=17.1297M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):27/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):28/manual_time 1768672 ns 1981252 ns 396 bytes=268.435M bytes_per_second=141.349G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):28/manual_time 1768602 ns 1981143 ns 396 bytes=268.435M bytes_per_second=141.355G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):28/manual_time 1768582 ns 1981223 ns 396 bytes=268.435M bytes_per_second=141.356G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):28/manual_time 1768854 ns 1981368 ns 396 bytes=268.435M bytes_per_second=141.334G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):28/manual_time 1768512 ns 1981072 ns 396 bytes=268.435M bytes_per_second=141.362G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):28/manual_time_mean 1768645 ns 1981212 ns 5 bytes=268.435M bytes_per_second=141.351G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):28/manual_time_median 1768602 ns 1981223 ns 5 bytes=268.435M bytes_per_second=141.355G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):28/manual_time_stddev 130 ns 112 ns 5 bytes=0 bytes_per_second=10.6423M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):28/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):29/manual_time 3529867 ns 3945134 ns 198 bytes=536.871M bytes_per_second=141.648G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):29/manual_time 3529890 ns 3945960 ns 198 bytes=536.871M bytes_per_second=141.647G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):29/manual_time 3529946 ns 3945457 ns 198 bytes=536.871M bytes_per_second=141.645G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):29/manual_time 3530053 ns 3945817 ns 198 bytes=536.871M bytes_per_second=141.641G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):29/manual_time 3529616 ns 3945099 ns 198 bytes=536.871M bytes_per_second=141.658G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):29/manual_time_mean 3529874 ns 3945493 ns 5 bytes=536.871M bytes_per_second=141.648G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):29/manual_time_median 3529890 ns 3945457 ns 5 bytes=536.871M bytes_per_second=141.647G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):29/manual_time_stddev 161 ns 390 ns 5 bytes=0 bytes_per_second=6.63407M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):29/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):30/manual_time 7059815 ns 7862113 ns 99 bytes=1073.74M bytes_per_second=141.647G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):30/manual_time 7059834 ns 7862312 ns 99 bytes=1073.74M bytes_per_second=141.646G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):30/manual_time 7059315 ns 7861625 ns 99 bytes=1073.74M bytes_per_second=141.657G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):30/manual_time 7060014 ns 7862481 ns 99 bytes=1073.74M bytes_per_second=141.643G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):30/manual_time 7059372 ns 7861708 ns 99 bytes=1073.74M bytes_per_second=141.656G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):30/manual_time_mean 7059670 ns 7862048 ns 5 bytes=1073.74M bytes_per_second=141.65G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):30/manual_time_median 7059815 ns 7862113 ns 5 bytes=1073.74M bytes_per_second=141.647G/s own_gpu=1 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):30/manual_time_stddev 308 ns 373 ns 5 bytes=0 bytes_per_second=6.33681M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/1/log2(N):30/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):12/manual_time 12293 ns 33594 ns 56920 bytes=4.096k bytes_per_second=317.766M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):12/manual_time 12299 ns 33579 ns 56920 bytes=4.096k bytes_per_second=317.616M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):12/manual_time 12292 ns 33641 ns 56920 bytes=4.096k bytes_per_second=317.785M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):12/manual_time 12298 ns 33649 ns 56920 bytes=4.096k bytes_per_second=317.637M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):12/manual_time 12293 ns 33646 ns 56920 bytes=4.096k bytes_per_second=317.774M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):12/manual_time_mean 12295 ns 33622 ns 5 bytes=4.096k bytes_per_second=317.716M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):12/manual_time_median 12293 ns 33641 ns 5 bytes=4.096k bytes_per_second=317.766M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):12/manual_time_stddev 3.17 ns 32.9 ns 5 bytes=0 bytes_per_second=83.8487k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):12/manual_time_cv 0.03 % 0.10 % 5 bytes=0.00% bytes_per_second=0.03% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):13/manual_time 12293 ns 33616 ns 56880 bytes=8.192k bytes_per_second=635.542M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):13/manual_time 12296 ns 33599 ns 56880 bytes=8.192k bytes_per_second=635.351M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):13/manual_time 12293 ns 33571 ns 56880 bytes=8.192k bytes_per_second=635.536M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):13/manual_time 12292 ns 33580 ns 56880 bytes=8.192k bytes_per_second=635.592M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):13/manual_time 12292 ns 33593 ns 56880 bytes=8.192k bytes_per_second=635.564M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):13/manual_time_mean 12293 ns 33592 ns 5 bytes=8.192k bytes_per_second=635.517M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):13/manual_time_median 12293 ns 33593 ns 5 bytes=8.192k bytes_per_second=635.542M/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):13/manual_time_stddev 1.84 ns 17.3 ns 5 bytes=0 bytes_per_second=97.6362k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):13/manual_time_cv 0.02 % 0.05 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):14/manual_time 12290 ns 33945 ns 56923 bytes=16.384k bytes_per_second=1.24154G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):14/manual_time 12301 ns 33917 ns 56923 bytes=16.384k bytes_per_second=1.24046G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):14/manual_time 12288 ns 33947 ns 56923 bytes=16.384k bytes_per_second=1.24172G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):14/manual_time 12290 ns 33925 ns 56923 bytes=16.384k bytes_per_second=1.24153G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):14/manual_time 12288 ns 33943 ns 56923 bytes=16.384k bytes_per_second=1.24172G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):14/manual_time_mean 12292 ns 33936 ns 5 bytes=16.384k bytes_per_second=1.24139G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):14/manual_time_median 12290 ns 33943 ns 5 bytes=16.384k bytes_per_second=1.24154G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):14/manual_time_stddev 5.25 ns 13.5 ns 5 bytes=0 bytes_per_second=555.298k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):14/manual_time_cv 0.04 % 0.04 % 5 bytes=0.00% bytes_per_second=0.04% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):15/manual_time 12294 ns 34505 ns 56904 bytes=32.768k bytes_per_second=2.48226G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):15/manual_time 12299 ns 34492 ns 56904 bytes=32.768k bytes_per_second=2.48127G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):15/manual_time 12296 ns 34357 ns 56904 bytes=32.768k bytes_per_second=2.48186G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):15/manual_time 12303 ns 34349 ns 56904 bytes=32.768k bytes_per_second=2.48047G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):15/manual_time 12295 ns 34404 ns 56904 bytes=32.768k bytes_per_second=2.48208G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):15/manual_time_mean 12298 ns 34422 ns 5 bytes=32.768k bytes_per_second=2.48159G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):15/manual_time_median 12296 ns 34404 ns 5 bytes=32.768k bytes_per_second=2.48186G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):15/manual_time_stddev 3.60 ns 73.5 ns 5 bytes=0 bytes_per_second=762.422k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):15/manual_time_cv 0.03 % 0.21 % 5 bytes=0.00% bytes_per_second=0.03% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):16/manual_time 12282 ns 35185 ns 56889 bytes=65.536k bytes_per_second=4.96943G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):16/manual_time 12292 ns 35178 ns 56889 bytes=65.536k bytes_per_second=4.96529G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):16/manual_time 12312 ns 35084 ns 56889 bytes=65.536k bytes_per_second=4.9575G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):16/manual_time 12314 ns 35102 ns 56889 bytes=65.536k bytes_per_second=4.95659G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):16/manual_time 12304 ns 35097 ns 56889 bytes=65.536k bytes_per_second=4.96067G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):16/manual_time_mean 12301 ns 35129 ns 5 bytes=65.536k bytes_per_second=4.96189G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):16/manual_time_median 12304 ns 35102 ns 5 bytes=65.536k bytes_per_second=4.96067G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):16/manual_time_stddev 13.4 ns 48.4 ns 5 bytes=0 bytes_per_second=5.54788M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):16/manual_time_cv 0.11 % 0.14 % 5 bytes=0.00% bytes_per_second=0.11% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):17/manual_time 15425 ns 39743 ns 45359 bytes=131.072k bytes_per_second=7.91377G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):17/manual_time 15432 ns 39725 ns 45359 bytes=131.072k bytes_per_second=7.91002G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):17/manual_time 15433 ns 39754 ns 45359 bytes=131.072k bytes_per_second=7.90945G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):17/manual_time 15432 ns 39759 ns 45359 bytes=131.072k bytes_per_second=7.91031G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):17/manual_time 15426 ns 39781 ns 45359 bytes=131.072k bytes_per_second=7.91341G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):17/manual_time_mean 15430 ns 39752 ns 5 bytes=131.072k bytes_per_second=7.91139G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):17/manual_time_median 15432 ns 39754 ns 5 bytes=131.072k bytes_per_second=7.91031G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):17/manual_time_stddev 3.97 ns 20.6 ns 5 bytes=0 bytes_per_second=2.08448M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):17/manual_time_cv 0.03 % 0.05 % 5 bytes=0.00% bytes_per_second=0.03% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):18/manual_time 18927 ns 45109 ns 36955 bytes=262.144k bytes_per_second=12.8989G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):18/manual_time 18935 ns 45080 ns 36955 bytes=262.144k bytes_per_second=12.8939G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):18/manual_time 18928 ns 45132 ns 36955 bytes=262.144k bytes_per_second=12.8983G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):18/manual_time 18936 ns 45134 ns 36955 bytes=262.144k bytes_per_second=12.8929G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):18/manual_time 18930 ns 45142 ns 36955 bytes=262.144k bytes_per_second=12.897G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):18/manual_time_mean 18931 ns 45119 ns 5 bytes=262.144k bytes_per_second=12.8962G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):18/manual_time_median 18930 ns 45132 ns 5 bytes=262.144k bytes_per_second=12.897G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):18/manual_time_stddev 3.94 ns 25.4 ns 5 bytes=0 bytes_per_second=2.75086M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):18/manual_time_cv 0.02 % 0.06 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):19/manual_time 25513 ns 51737 ns 27431 bytes=524.288k bytes_per_second=19.1387G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):19/manual_time 25519 ns 51760 ns 27431 bytes=524.288k bytes_per_second=19.1337G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):19/manual_time 25519 ns 51781 ns 27431 bytes=524.288k bytes_per_second=19.134G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):19/manual_time 25520 ns 51791 ns 27431 bytes=524.288k bytes_per_second=19.1335G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):19/manual_time 25511 ns 51772 ns 27431 bytes=524.288k bytes_per_second=19.14G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):19/manual_time_mean 25516 ns 51768 ns 5 bytes=524.288k bytes_per_second=19.136G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):19/manual_time_median 25519 ns 51772 ns 5 bytes=524.288k bytes_per_second=19.134G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):19/manual_time_stddev 4.17 ns 20.9 ns 5 bytes=0 bytes_per_second=3.20625M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):19/manual_time_cv 0.02 % 0.04 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):20/manual_time 38659 ns 64984 ns 18102 bytes=1048.58k bytes_per_second=25.261G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):20/manual_time 38671 ns 64968 ns 18102 bytes=1048.58k bytes_per_second=25.253G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):20/manual_time 38673 ns 65018 ns 18102 bytes=1048.58k bytes_per_second=25.2518G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):20/manual_time 38675 ns 65001 ns 18102 bytes=1048.58k bytes_per_second=25.2503G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):20/manual_time 38668 ns 65025 ns 18102 bytes=1048.58k bytes_per_second=25.2551G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):20/manual_time_mean 38669 ns 64999 ns 5 bytes=1048.58k bytes_per_second=25.2543G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):20/manual_time_median 38671 ns 65001 ns 5 bytes=1048.58k bytes_per_second=25.253G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):20/manual_time_stddev 6.35 ns 23.7 ns 5 bytes=0 bytes_per_second=4.24818M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):20/manual_time_cv 0.02 % 0.04 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):21/manual_time 64631 ns 91187 ns 10845 bytes=2.09715M bytes_per_second=30.2196G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):21/manual_time 64574 ns 91147 ns 10845 bytes=2.09715M bytes_per_second=30.2462G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):21/manual_time 64573 ns 91214 ns 10845 bytes=2.09715M bytes_per_second=30.2469G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):21/manual_time 64615 ns 91211 ns 10845 bytes=2.09715M bytes_per_second=30.2273G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):21/manual_time 64618 ns 91186 ns 10845 bytes=2.09715M bytes_per_second=30.2259G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):21/manual_time_mean 64602 ns 91189 ns 5 bytes=2.09715M bytes_per_second=30.2332G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):21/manual_time_median 64615 ns 91187 ns 5 bytes=2.09715M bytes_per_second=30.2273G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):21/manual_time_stddev 26.8 ns 26.8 ns 5 bytes=0 bytes_per_second=12.8392M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):21/manual_time_cv 0.04 % 0.03 % 5 bytes=0.00% bytes_per_second=0.04% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):22/manual_time 113721 ns 141176 ns 6161 bytes=4.1943M bytes_per_second=34.3493G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):22/manual_time 113630 ns 141189 ns 6161 bytes=4.1943M bytes_per_second=34.3769G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):22/manual_time 113747 ns 141192 ns 6161 bytes=4.1943M bytes_per_second=34.3416G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):22/manual_time 113650 ns 141165 ns 6161 bytes=4.1943M bytes_per_second=34.371G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):22/manual_time 113770 ns 141228 ns 6161 bytes=4.1943M bytes_per_second=34.3347G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):22/manual_time_mean 113703 ns 141190 ns 5 bytes=4.1943M bytes_per_second=34.3547G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):22/manual_time_median 113721 ns 141189 ns 5 bytes=4.1943M bytes_per_second=34.3493G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):22/manual_time_stddev 61.0 ns 23.8 ns 5 bytes=0 bytes_per_second=18.8684M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):22/manual_time_cv 0.05 % 0.02 % 5 bytes=0.00% bytes_per_second=0.05% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):23/manual_time 220402 ns 250108 ns 3176 bytes=8.38861M bytes_per_second=35.4466G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):23/manual_time 220346 ns 250081 ns 3176 bytes=8.38861M bytes_per_second=35.4556G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):23/manual_time 220375 ns 250096 ns 3176 bytes=8.38861M bytes_per_second=35.4509G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):23/manual_time 220313 ns 250141 ns 3176 bytes=8.38861M bytes_per_second=35.4609G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):23/manual_time 220354 ns 250195 ns 3176 bytes=8.38861M bytes_per_second=35.4544G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):23/manual_time_mean 220358 ns 250124 ns 5 bytes=8.38861M bytes_per_second=35.4537G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):23/manual_time_median 220354 ns 250108 ns 5 bytes=8.38861M bytes_per_second=35.4544G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):23/manual_time_stddev 33.2 ns 45.2 ns 5 bytes=0 bytes_per_second=5.47741M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):23/manual_time_cv 0.02 % 0.02 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):24/manual_time 434292 ns 469215 ns 1611 bytes=16.7772M bytes_per_second=35.9781G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):24/manual_time 434411 ns 469298 ns 1611 bytes=16.7772M bytes_per_second=35.9682G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):24/manual_time 434325 ns 469215 ns 1611 bytes=16.7772M bytes_per_second=35.9754G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):24/manual_time 434480 ns 469586 ns 1611 bytes=16.7772M bytes_per_second=35.9625G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):24/manual_time 434357 ns 469306 ns 1611 bytes=16.7772M bytes_per_second=35.9727G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):24/manual_time_mean 434373 ns 469324 ns 5 bytes=16.7772M bytes_per_second=35.9714G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):24/manual_time_median 434357 ns 469298 ns 5 bytes=16.7772M bytes_per_second=35.9727G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):24/manual_time_stddev 74.2 ns 153 ns 5 bytes=0 bytes_per_second=6.29232M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):24/manual_time_cv 0.02 % 0.03 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):25/manual_time 863743 ns 910219 ns 810 bytes=33.5544M bytes_per_second=36.1797G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):25/manual_time 863765 ns 910208 ns 810 bytes=33.5544M bytes_per_second=36.1788G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):25/manual_time 863703 ns 910221 ns 810 bytes=33.5544M bytes_per_second=36.1814G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):25/manual_time 863754 ns 910236 ns 810 bytes=33.5544M bytes_per_second=36.1793G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):25/manual_time 863741 ns 910454 ns 810 bytes=33.5544M bytes_per_second=36.1798G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):25/manual_time_mean 863741 ns 910268 ns 5 bytes=33.5544M bytes_per_second=36.1798G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):25/manual_time_median 863743 ns 910221 ns 5 bytes=33.5544M bytes_per_second=36.1797G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):25/manual_time_stddev 23.5 ns 105 ns 5 bytes=0 bytes_per_second=1031.55k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):25/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):26/manual_time 1725552 ns 1795954 ns 406 bytes=67.1089M bytes_per_second=36.2203G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):26/manual_time 1725408 ns 1795682 ns 406 bytes=67.1089M bytes_per_second=36.2233G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):26/manual_time 1725405 ns 1795711 ns 406 bytes=67.1089M bytes_per_second=36.2234G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):26/manual_time 1725382 ns 1795633 ns 406 bytes=67.1089M bytes_per_second=36.2239G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):26/manual_time 1725475 ns 1795825 ns 406 bytes=67.1089M bytes_per_second=36.2219G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):26/manual_time_mean 1725444 ns 1795761 ns 5 bytes=67.1089M bytes_per_second=36.2226G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):26/manual_time_median 1725408 ns 1795711 ns 5 bytes=67.1089M bytes_per_second=36.2233G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):26/manual_time_stddev 69.5 ns 129 ns 5 bytes=0 bytes_per_second=1.49478M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):26/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):27/manual_time 3450781 ns 3576637 ns 203 bytes=134.218M bytes_per_second=36.2237G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):27/manual_time 3450839 ns 3576627 ns 203 bytes=134.218M bytes_per_second=36.2231G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):27/manual_time 3450792 ns 3576487 ns 203 bytes=134.218M bytes_per_second=36.2236G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):27/manual_time 3450712 ns 3576432 ns 203 bytes=134.218M bytes_per_second=36.2244G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):27/manual_time 3450429 ns 3575999 ns 203 bytes=134.218M bytes_per_second=36.2274G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):27/manual_time_mean 3450711 ns 3576436 ns 5 bytes=134.218M bytes_per_second=36.2244G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):27/manual_time_median 3450781 ns 3576487 ns 5 bytes=134.218M bytes_per_second=36.2237G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):27/manual_time_stddev 164 ns 260 ns 5 bytes=0 bytes_per_second=1.75986M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):27/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):28/manual_time 6903543 ns 7138024 ns 101 bytes=268.435M bytes_per_second=36.2133G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):28/manual_time 6903593 ns 7138287 ns 101 bytes=268.435M bytes_per_second=36.213G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):28/manual_time 6903719 ns 7138312 ns 101 bytes=268.435M bytes_per_second=36.2124G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):28/manual_time 6903714 ns 7138027 ns 101 bytes=268.435M bytes_per_second=36.2124G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):28/manual_time 6903685 ns 7138071 ns 101 bytes=268.435M bytes_per_second=36.2125G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):28/manual_time_mean 6903651 ns 7138144 ns 5 bytes=268.435M bytes_per_second=36.2127G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):28/manual_time_median 6903685 ns 7138071 ns 5 bytes=268.435M bytes_per_second=36.2125G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):28/manual_time_stddev 78.6 ns 143 ns 5 bytes=0 bytes_per_second=432.308k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):28/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):29/manual_time 13815276 ns 14239926 ns 51 bytes=536.871M bytes_per_second=36.1918G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):29/manual_time 13815957 ns 14241024 ns 51 bytes=536.871M bytes_per_second=36.19G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):29/manual_time 13815559 ns 14240406 ns 51 bytes=536.871M bytes_per_second=36.1911G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):29/manual_time 13815763 ns 14240803 ns 51 bytes=536.871M bytes_per_second=36.1905G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):29/manual_time 13815697 ns 14240182 ns 51 bytes=536.871M bytes_per_second=36.1907G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):29/manual_time_mean 13815650 ns 14240468 ns 5 bytes=536.871M bytes_per_second=36.1908G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):29/manual_time_median 13815697 ns 14240406 ns 5 bytes=536.871M bytes_per_second=36.1907G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):29/manual_time_stddev 254 ns 447 ns 5 bytes=0 bytes_per_second=696.495k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):29/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):30/manual_time 27648044 ns 28452818 ns 25 bytes=1073.74M bytes_per_second=36.1689G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):30/manual_time 27645644 ns 28449221 ns 25 bytes=1073.74M bytes_per_second=36.1721G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):30/manual_time 27648012 ns 28451292 ns 25 bytes=1073.74M bytes_per_second=36.169G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):30/manual_time 27646424 ns 28449871 ns 25 bytes=1073.74M bytes_per_second=36.171G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):30/manual_time 27647468 ns 28452428 ns 25 bytes=1073.74M bytes_per_second=36.1697G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):30/manual_time_mean 27647118 ns 28451126 ns 5 bytes=1073.74M bytes_per_second=36.1701G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):30/manual_time_median 27647468 ns 28451292 ns 5 bytes=1073.74M bytes_per_second=36.1697G/s own_gpu=2 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):30/manual_time_stddev 1053 ns 1564 ns 5 bytes=0 bytes_per_second=1.41017M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/2/log2(N):30/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):12/manual_time 12218 ns 31228 ns 57223 bytes=4.096k bytes_per_second=319.705M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):12/manual_time 12242 ns 31218 ns 57223 bytes=4.096k bytes_per_second=319.094M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):12/manual_time 12254 ns 31226 ns 57223 bytes=4.096k bytes_per_second=318.774M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):12/manual_time 12297 ns 31206 ns 57223 bytes=4.096k bytes_per_second=317.65M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):12/manual_time 12246 ns 31206 ns 57223 bytes=4.096k bytes_per_second=318.992M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):12/manual_time_mean 12251 ns 31217 ns 5 bytes=4.096k bytes_per_second=318.843M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):12/manual_time_median 12246 ns 31218 ns 5 bytes=4.096k bytes_per_second=318.992M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):12/manual_time_stddev 28.9 ns 10.3 ns 5 bytes=0 bytes_per_second=769.245k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):12/manual_time_cv 0.24 % 0.03 % 5 bytes=0.00% bytes_per_second=0.24% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):13/manual_time 12230 ns 31214 ns 57301 bytes=8.192k bytes_per_second=638.776M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):13/manual_time 12258 ns 31207 ns 57301 bytes=8.192k bytes_per_second=637.335M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):13/manual_time 12278 ns 31198 ns 57301 bytes=8.192k bytes_per_second=636.293M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):13/manual_time 12271 ns 31191 ns 57301 bytes=8.192k bytes_per_second=636.671M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):13/manual_time 12234 ns 31194 ns 57301 bytes=8.192k bytes_per_second=638.577M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):13/manual_time_mean 12254 ns 31201 ns 5 bytes=8.192k bytes_per_second=637.53M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):13/manual_time_median 12258 ns 31198 ns 5 bytes=8.192k bytes_per_second=637.335M/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):13/manual_time_stddev 21.4 ns 9.76 ns 5 bytes=0 bytes_per_second=1.11289M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):13/manual_time_cv 0.17 % 0.03 % 5 bytes=0.00% bytes_per_second=0.17% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):14/manual_time 12229 ns 31488 ns 57243 bytes=16.384k bytes_per_second=1.24777G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):14/manual_time 12230 ns 31460 ns 57243 bytes=16.384k bytes_per_second=1.2477G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):14/manual_time 12224 ns 31493 ns 57243 bytes=16.384k bytes_per_second=1.24827G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):14/manual_time 12229 ns 31488 ns 57243 bytes=16.384k bytes_per_second=1.24779G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):14/manual_time 12228 ns 31470 ns 57243 bytes=16.384k bytes_per_second=1.24787G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):14/manual_time_mean 12228 ns 31480 ns 5 bytes=16.384k bytes_per_second=1.24788G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):14/manual_time_median 12229 ns 31488 ns 5 bytes=16.384k bytes_per_second=1.24779G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):14/manual_time_stddev 2.20 ns 14.2 ns 5 bytes=0 bytes_per_second=235.737k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):14/manual_time_cv 0.02 % 0.05 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):15/manual_time 12241 ns 31841 ns 57181 bytes=32.768k bytes_per_second=2.49301G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):15/manual_time 12239 ns 31813 ns 57181 bytes=32.768k bytes_per_second=2.49338G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):15/manual_time 12243 ns 31807 ns 57181 bytes=32.768k bytes_per_second=2.4927G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):15/manual_time 12241 ns 31782 ns 57181 bytes=32.768k bytes_per_second=2.49297G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):15/manual_time 12241 ns 31805 ns 57181 bytes=32.768k bytes_per_second=2.49309G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):15/manual_time_mean 12241 ns 31810 ns 5 bytes=32.768k bytes_per_second=2.49303G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):15/manual_time_median 12241 ns 31807 ns 5 bytes=32.768k bytes_per_second=2.49301G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):15/manual_time_stddev 1.20 ns 20.8 ns 5 bytes=0 bytes_per_second=255.604k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):15/manual_time_cv 0.01 % 0.07 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):16/manual_time 12262 ns 32592 ns 57070 bytes=65.536k bytes_per_second=4.97744G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):16/manual_time 12264 ns 32578 ns 57070 bytes=65.536k bytes_per_second=4.97661G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):16/manual_time 12263 ns 32579 ns 57070 bytes=65.536k bytes_per_second=4.97731G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):16/manual_time 12264 ns 32569 ns 57070 bytes=65.536k bytes_per_second=4.97696G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):16/manual_time 12264 ns 32575 ns 57070 bytes=65.536k bytes_per_second=4.97694G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):16/manual_time_mean 12263 ns 32578 ns 5 bytes=65.536k bytes_per_second=4.97705G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):16/manual_time_median 12264 ns 32578 ns 5 bytes=65.536k bytes_per_second=4.97696G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):16/manual_time_stddev 0.812 ns 8.55 ns 5 bytes=0 bytes_per_second=345.7k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):16/manual_time_cv 0.01 % 0.03 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):17/manual_time 15755 ns 37601 ns 44426 bytes=131.072k bytes_per_second=7.74784G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):17/manual_time 15758 ns 37634 ns 44426 bytes=131.072k bytes_per_second=7.7468G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):17/manual_time 15756 ns 37637 ns 44426 bytes=131.072k bytes_per_second=7.74771G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):17/manual_time 15756 ns 37608 ns 44426 bytes=131.072k bytes_per_second=7.74754G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):17/manual_time 15758 ns 37604 ns 44426 bytes=131.072k bytes_per_second=7.74672G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):17/manual_time_mean 15756 ns 37617 ns 5 bytes=131.072k bytes_per_second=7.74732G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):17/manual_time_median 15756 ns 37608 ns 5 bytes=131.072k bytes_per_second=7.74754G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):17/manual_time_stddev 1.07 ns 17.5 ns 5 bytes=0 bytes_per_second=551.077k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):17/manual_time_cv 0.01 % 0.05 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):18/manual_time 19468 ns 43319 ns 35952 bytes=262.144k bytes_per_second=12.5403G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):18/manual_time 19469 ns 43303 ns 35952 bytes=262.144k bytes_per_second=12.54G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):18/manual_time 19467 ns 43313 ns 35952 bytes=262.144k bytes_per_second=12.5412G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):18/manual_time 19471 ns 43305 ns 35952 bytes=262.144k bytes_per_second=12.5388G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):18/manual_time 19467 ns 43320 ns 35952 bytes=262.144k bytes_per_second=12.5414G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):18/manual_time_mean 19468 ns 43312 ns 5 bytes=262.144k bytes_per_second=12.5404G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):18/manual_time_median 19468 ns 43313 ns 5 bytes=262.144k bytes_per_second=12.5403G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):18/manual_time_stddev 1.63 ns 7.83 ns 5 bytes=0 bytes_per_second=1101.23k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):18/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):19/manual_time 26509 ns 50500 ns 26402 bytes=524.288k bytes_per_second=18.4193G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):19/manual_time 26512 ns 50495 ns 26402 bytes=524.288k bytes_per_second=18.4173G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):19/manual_time 26511 ns 50500 ns 26402 bytes=524.288k bytes_per_second=18.418G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):19/manual_time 26512 ns 50546 ns 26402 bytes=524.288k bytes_per_second=18.4171G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):19/manual_time 26510 ns 50549 ns 26402 bytes=524.288k bytes_per_second=18.4186G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):19/manual_time_mean 26511 ns 50518 ns 5 bytes=524.288k bytes_per_second=18.418G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):19/manual_time_median 26511 ns 50500 ns 5 bytes=524.288k bytes_per_second=18.418G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):19/manual_time_stddev 1.29 ns 27.1 ns 5 bytes=0 bytes_per_second=938.031k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):19/manual_time_cv 0.00 % 0.05 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):20/manual_time 40516 ns 65420 ns 17276 bytes=1048.58k bytes_per_second=24.1033G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):20/manual_time 40516 ns 65393 ns 17276 bytes=1048.58k bytes_per_second=24.1033G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):20/manual_time 40512 ns 65430 ns 17276 bytes=1048.58k bytes_per_second=24.1057G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):20/manual_time 40516 ns 65434 ns 17276 bytes=1048.58k bytes_per_second=24.1034G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):20/manual_time 40512 ns 65440 ns 17276 bytes=1048.58k bytes_per_second=24.1054G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):20/manual_time_mean 40514 ns 65423 ns 5 bytes=1048.58k bytes_per_second=24.1042G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):20/manual_time_median 40516 ns 65430 ns 5 bytes=1048.58k bytes_per_second=24.1034G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):20/manual_time_stddev 2.06 ns 18.5 ns 5 bytes=0 bytes_per_second=1.25608M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):20/manual_time_cv 0.01 % 0.03 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):21/manual_time 68335 ns 93945 ns 10289 bytes=2.09715M bytes_per_second=28.5817G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):21/manual_time 68142 ns 93675 ns 10289 bytes=2.09715M bytes_per_second=28.6625G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):21/manual_time 67982 ns 93615 ns 10289 bytes=2.09715M bytes_per_second=28.7301G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):21/manual_time 68328 ns 93993 ns 10289 bytes=2.09715M bytes_per_second=28.5847G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):21/manual_time 68132 ns 93678 ns 10289 bytes=2.09715M bytes_per_second=28.6669G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):21/manual_time_mean 68184 ns 93781 ns 5 bytes=2.09715M bytes_per_second=28.6452G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):21/manual_time_median 68142 ns 93678 ns 5 bytes=2.09715M bytes_per_second=28.6625G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):21/manual_time_stddev 149 ns 174 ns 5 bytes=0 bytes_per_second=64.0879M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):21/manual_time_cv 0.22 % 0.19 % 5 bytes=0.00% bytes_per_second=0.22% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):22/manual_time 120721 ns 147482 ns 5792 bytes=4.1943M bytes_per_second=32.3577G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):22/manual_time 120844 ns 147715 ns 5792 bytes=4.1943M bytes_per_second=32.3246G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):22/manual_time 120723 ns 147543 ns 5792 bytes=4.1943M bytes_per_second=32.3571G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):22/manual_time 120845 ns 147760 ns 5792 bytes=4.1943M bytes_per_second=32.3244G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):22/manual_time 120724 ns 147620 ns 5792 bytes=4.1943M bytes_per_second=32.3569G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):22/manual_time_mean 120772 ns 147624 ns 5 bytes=4.1943M bytes_per_second=32.3441G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):22/manual_time_median 120724 ns 147620 ns 5 bytes=4.1943M bytes_per_second=32.3569G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):22/manual_time_stddev 66.9 ns 116 ns 5 bytes=0 bytes_per_second=18.351M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):22/manual_time_cv 0.06 % 0.08 % 5 bytes=0.00% bytes_per_second=0.06% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):23/manual_time 232129 ns 260222 ns 3015 bytes=8.38861M bytes_per_second=33.6558G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):23/manual_time 232159 ns 260286 ns 3015 bytes=8.38861M bytes_per_second=33.6515G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):23/manual_time 232130 ns 260281 ns 3015 bytes=8.38861M bytes_per_second=33.6557G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):23/manual_time 232154 ns 260264 ns 3015 bytes=8.38861M bytes_per_second=33.6523G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):23/manual_time 232128 ns 260226 ns 3015 bytes=8.38861M bytes_per_second=33.656G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):23/manual_time_mean 232140 ns 260256 ns 5 bytes=8.38861M bytes_per_second=33.6543G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):23/manual_time_median 232130 ns 260264 ns 5 bytes=8.38861M bytes_per_second=33.6557G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):23/manual_time_stddev 15.1 ns 30.0 ns 5 bytes=0 bytes_per_second=2.24815M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):23/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):24/manual_time 455179 ns 489253 ns 1538 bytes=16.7772M bytes_per_second=34.3272G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):24/manual_time 455206 ns 489277 ns 1538 bytes=16.7772M bytes_per_second=34.3251G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):24/manual_time 455178 ns 489206 ns 1538 bytes=16.7772M bytes_per_second=34.3273G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):24/manual_time 455199 ns 489285 ns 1538 bytes=16.7772M bytes_per_second=34.3257G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):24/manual_time 455161 ns 489333 ns 1538 bytes=16.7772M bytes_per_second=34.3285G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):24/manual_time_mean 455185 ns 489271 ns 5 bytes=16.7772M bytes_per_second=34.3267G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):24/manual_time_median 455179 ns 489277 ns 5 bytes=16.7772M bytes_per_second=34.3272G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):24/manual_time_stddev 17.9 ns 46.4 ns 5 bytes=0 bytes_per_second=1.38247M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):24/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):25/manual_time 901659 ns 947421 ns 776 bytes=33.5544M bytes_per_second=34.6583G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):25/manual_time 901664 ns 947436 ns 776 bytes=33.5544M bytes_per_second=34.6581G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):25/manual_time 901664 ns 947420 ns 776 bytes=33.5544M bytes_per_second=34.6581G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):25/manual_time 901657 ns 947428 ns 776 bytes=33.5544M bytes_per_second=34.6584G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):25/manual_time 901674 ns 947460 ns 776 bytes=33.5544M bytes_per_second=34.6578G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):25/manual_time_mean 901664 ns 947433 ns 5 bytes=33.5544M bytes_per_second=34.6582G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):25/manual_time_median 901664 ns 947428 ns 5 bytes=33.5544M bytes_per_second=34.6581G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):25/manual_time_stddev 6.41 ns 16.4 ns 5 bytes=0 bytes_per_second=258.171k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):25/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):26/manual_time 1794725 ns 1864570 ns 390 bytes=67.1089M bytes_per_second=34.8243G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):26/manual_time 1794671 ns 1864437 ns 390 bytes=67.1089M bytes_per_second=34.8253G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):26/manual_time 1794674 ns 1864501 ns 390 bytes=67.1089M bytes_per_second=34.8253G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):26/manual_time 1794678 ns 1864488 ns 390 bytes=67.1089M bytes_per_second=34.8252G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):26/manual_time 1794716 ns 1864670 ns 390 bytes=67.1089M bytes_per_second=34.8245G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):26/manual_time_mean 1794693 ns 1864533 ns 5 bytes=67.1089M bytes_per_second=34.8249G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):26/manual_time_median 1794678 ns 1864501 ns 5 bytes=67.1089M bytes_per_second=34.8252G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):26/manual_time_stddev 25.4 ns 90.0 ns 5 bytes=0 bytes_per_second=517.384k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):26/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):27/manual_time 3580933 ns 3710401 ns 195 bytes=134.218M bytes_per_second=34.9071G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):27/manual_time 3580906 ns 3710264 ns 195 bytes=134.218M bytes_per_second=34.9074G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):27/manual_time 3580836 ns 3709821 ns 195 bytes=134.218M bytes_per_second=34.9081G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):27/manual_time 3580951 ns 3710360 ns 195 bytes=134.218M bytes_per_second=34.9069G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):27/manual_time 3580886 ns 3710136 ns 195 bytes=134.218M bytes_per_second=34.9076G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):27/manual_time_mean 3580902 ns 3710196 ns 5 bytes=134.218M bytes_per_second=34.9074G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):27/manual_time_median 3580906 ns 3710264 ns 5 bytes=134.218M bytes_per_second=34.9074G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):27/manual_time_stddev 44.8 ns 233 ns 5 bytes=0 bytes_per_second=457.655k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):27/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):28/manual_time 7153014 ns 7386154 ns 98 bytes=268.435M bytes_per_second=34.9503G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):28/manual_time 7152953 ns 7386082 ns 98 bytes=268.435M bytes_per_second=34.9506G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):28/manual_time 7153095 ns 7386386 ns 98 bytes=268.435M bytes_per_second=34.9499G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):28/manual_time 7152849 ns 7385936 ns 98 bytes=268.435M bytes_per_second=34.9511G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):28/manual_time 7152876 ns 7385847 ns 98 bytes=268.435M bytes_per_second=34.951G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):28/manual_time_mean 7152957 ns 7386081 ns 5 bytes=268.435M bytes_per_second=34.9506G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):28/manual_time_median 7152953 ns 7386082 ns 5 bytes=268.435M bytes_per_second=34.9506G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):28/manual_time_stddev 101 ns 209 ns 5 bytes=0 bytes_per_second=515.803k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):28/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):29/manual_time 14297100 ns 14720707 ns 49 bytes=536.871M bytes_per_second=34.9721G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):29/manual_time 14296812 ns 14720468 ns 49 bytes=536.871M bytes_per_second=34.9728G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):29/manual_time 14297028 ns 14720668 ns 49 bytes=536.871M bytes_per_second=34.9723G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):29/manual_time 14296630 ns 14719948 ns 49 bytes=536.871M bytes_per_second=34.9733G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):29/manual_time 14296616 ns 14720305 ns 49 bytes=536.871M bytes_per_second=34.9733G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):29/manual_time_mean 14296837 ns 14720419 ns 5 bytes=536.871M bytes_per_second=34.9728G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):29/manual_time_median 14296812 ns 14720468 ns 5 bytes=536.871M bytes_per_second=34.9728G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):29/manual_time_stddev 222 ns 309 ns 5 bytes=0 bytes_per_second=570.225k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):29/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):30/manual_time 28585108 ns 29388082 ns 24 bytes=1073.74M bytes_per_second=34.9833G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):30/manual_time 28585061 ns 29387933 ns 24 bytes=1073.74M bytes_per_second=34.9833G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):30/manual_time 28584861 ns 29388330 ns 24 bytes=1073.74M bytes_per_second=34.9836G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):30/manual_time 28585374 ns 29388558 ns 24 bytes=1073.74M bytes_per_second=34.9829G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):30/manual_time 28585895 ns 29389574 ns 24 bytes=1073.74M bytes_per_second=34.9823G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):30/manual_time_mean 28585260 ns 29388496 ns 5 bytes=1073.74M bytes_per_second=34.9831G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):30/manual_time_median 28585108 ns 29388330 ns 5 bytes=1073.74M bytes_per_second=34.9833G/s own_gpu=3 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):30/manual_time_stddev 399 ns 648 ns 5 bytes=0 bytes_per_second=512.381k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/3/log2(N):30/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):12/manual_time 12261 ns 33466 ns 57080 bytes=4.096k bytes_per_second=318.585M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):12/manual_time 12264 ns 33404 ns 57080 bytes=4.096k bytes_per_second=318.508M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):12/manual_time 12263 ns 33506 ns 57080 bytes=4.096k bytes_per_second=318.531M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):12/manual_time 12262 ns 33458 ns 57080 bytes=4.096k bytes_per_second=318.575M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):12/manual_time 12265 ns 33635 ns 57080 bytes=4.096k bytes_per_second=318.499M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):12/manual_time_mean 12263 ns 33494 ns 5 bytes=4.096k bytes_per_second=318.54M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):12/manual_time_median 12263 ns 33466 ns 5 bytes=4.096k bytes_per_second=318.531M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):12/manual_time_stddev 1.50 ns 86.8 ns 5 bytes=0 bytes_per_second=39.8668k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):12/manual_time_cv 0.01 % 0.26 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):13/manual_time 12262 ns 33628 ns 57081 bytes=8.192k bytes_per_second=637.117M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):13/manual_time 12260 ns 33563 ns 57081 bytes=8.192k bytes_per_second=637.212M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):13/manual_time 12263 ns 33563 ns 57081 bytes=8.192k bytes_per_second=637.071M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):13/manual_time 12261 ns 33634 ns 57081 bytes=8.192k bytes_per_second=637.2M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):13/manual_time 12260 ns 33590 ns 57081 bytes=8.192k bytes_per_second=637.249M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):13/manual_time_mean 12261 ns 33596 ns 5 bytes=8.192k bytes_per_second=637.17M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):13/manual_time_median 12261 ns 33590 ns 5 bytes=8.192k bytes_per_second=637.2M/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):13/manual_time_stddev 1.41 ns 33.9 ns 5 bytes=0 bytes_per_second=74.9762k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):13/manual_time_cv 0.01 % 0.10 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):14/manual_time 12263 ns 33964 ns 57071 bytes=16.384k bytes_per_second=1.24428G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):14/manual_time 12262 ns 33922 ns 57071 bytes=16.384k bytes_per_second=1.24436G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):14/manual_time 12262 ns 33978 ns 57071 bytes=16.384k bytes_per_second=1.24444G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):14/manual_time 12261 ns 34040 ns 57071 bytes=16.384k bytes_per_second=1.24447G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):14/manual_time 12262 ns 34012 ns 57071 bytes=16.384k bytes_per_second=1.24443G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):14/manual_time_mean 12262 ns 33983 ns 5 bytes=16.384k bytes_per_second=1.2444G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):14/manual_time_median 12262 ns 33978 ns 5 bytes=16.384k bytes_per_second=1.24443G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):14/manual_time_stddev 0.760 ns 45.0 ns 5 bytes=0 bytes_per_second=80.8963k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):14/manual_time_cv 0.01 % 0.13 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):15/manual_time 12265 ns 34485 ns 57086 bytes=32.768k bytes_per_second=2.48824G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):15/manual_time 12264 ns 34382 ns 57086 bytes=32.768k bytes_per_second=2.4884G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):15/manual_time 12265 ns 34419 ns 57086 bytes=32.768k bytes_per_second=2.48822G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):15/manual_time 12264 ns 34455 ns 57086 bytes=32.768k bytes_per_second=2.48839G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):15/manual_time 12266 ns 34459 ns 57086 bytes=32.768k bytes_per_second=2.48806G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):15/manual_time_mean 12265 ns 34440 ns 5 bytes=32.768k bytes_per_second=2.48826G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):15/manual_time_median 12265 ns 34455 ns 5 bytes=32.768k bytes_per_second=2.48824G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):15/manual_time_stddev 0.678 ns 39.8 ns 5 bytes=0 bytes_per_second=144.164k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):15/manual_time_cv 0.01 % 0.12 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):16/manual_time 12254 ns 35282 ns 57122 bytes=65.536k bytes_per_second=4.98085G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):16/manual_time 12253 ns 35219 ns 57122 bytes=65.536k bytes_per_second=4.98127G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):16/manual_time 12251 ns 35227 ns 57122 bytes=65.536k bytes_per_second=4.98211G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):16/manual_time 12252 ns 35219 ns 57122 bytes=65.536k bytes_per_second=4.98185G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):16/manual_time 12254 ns 35240 ns 57122 bytes=65.536k bytes_per_second=4.98091G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):16/manual_time_mean 12253 ns 35237 ns 5 bytes=65.536k bytes_per_second=4.9814G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):16/manual_time_median 12253 ns 35227 ns 5 bytes=65.536k bytes_per_second=4.98127G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):16/manual_time_stddev 1.38 ns 26.2 ns 5 bytes=0 bytes_per_second=587.881k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):16/manual_time_cv 0.01 % 0.07 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):17/manual_time 15733 ns 40323 ns 44488 bytes=131.072k bytes_per_second=7.75868G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):17/manual_time 15732 ns 40266 ns 44488 bytes=131.072k bytes_per_second=7.75938G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):17/manual_time 15731 ns 40400 ns 44488 bytes=131.072k bytes_per_second=7.75979G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):17/manual_time 15733 ns 40355 ns 44488 bytes=131.072k bytes_per_second=7.75874G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):17/manual_time 15733 ns 40410 ns 44488 bytes=131.072k bytes_per_second=7.75886G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):17/manual_time_mean 15733 ns 40351 ns 5 bytes=131.072k bytes_per_second=7.75909G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):17/manual_time_median 15733 ns 40355 ns 5 bytes=131.072k bytes_per_second=7.75886G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):17/manual_time_stddev 0.971 ns 58.9 ns 5 bytes=0 bytes_per_second=502.261k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):17/manual_time_cv 0.01 % 0.15 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):18/manual_time 19456 ns 45985 ns 35977 bytes=262.144k bytes_per_second=12.5484G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):18/manual_time 19455 ns 45870 ns 35977 bytes=262.144k bytes_per_second=12.5491G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):18/manual_time 19454 ns 45963 ns 35977 bytes=262.144k bytes_per_second=12.5496G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):18/manual_time 19457 ns 46038 ns 35977 bytes=262.144k bytes_per_second=12.548G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):18/manual_time 19455 ns 45966 ns 35977 bytes=262.144k bytes_per_second=12.549G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):18/manual_time_mean 19455 ns 45964 ns 5 bytes=262.144k bytes_per_second=12.5488G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):18/manual_time_median 19455 ns 45966 ns 5 bytes=262.144k bytes_per_second=12.549G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):18/manual_time_stddev 0.973 ns 60.6 ns 5 bytes=0 bytes_per_second=657.871k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):18/manual_time_cv 0.00 % 0.13 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):19/manual_time 26478 ns 53052 ns 26436 bytes=524.288k bytes_per_second=18.4411G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):19/manual_time 26475 ns 53037 ns 26436 bytes=524.288k bytes_per_second=18.4428G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):19/manual_time 26478 ns 53004 ns 26436 bytes=524.288k bytes_per_second=18.4412G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):19/manual_time 26477 ns 52978 ns 26436 bytes=524.288k bytes_per_second=18.4417G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):19/manual_time 26476 ns 52988 ns 26436 bytes=524.288k bytes_per_second=18.4427G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):19/manual_time_mean 26477 ns 53012 ns 5 bytes=524.288k bytes_per_second=18.4419G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):19/manual_time_median 26477 ns 53004 ns 5 bytes=524.288k bytes_per_second=18.4417G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):19/manual_time_stddev 1.16 ns 31.8 ns 5 bytes=0 bytes_per_second=847.54k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):19/manual_time_cv 0.00 % 0.06 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):20/manual_time 40500 ns 67159 ns 17285 bytes=1048.58k bytes_per_second=24.1128G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):20/manual_time 40495 ns 67049 ns 17285 bytes=1048.58k bytes_per_second=24.1154G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):20/manual_time 40494 ns 67088 ns 17285 bytes=1048.58k bytes_per_second=24.1163G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):20/manual_time 40497 ns 67113 ns 17285 bytes=1048.58k bytes_per_second=24.1147G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):20/manual_time 40493 ns 67105 ns 17285 bytes=1048.58k bytes_per_second=24.1171G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):20/manual_time_mean 40496 ns 67103 ns 5 bytes=1048.58k bytes_per_second=24.1153G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):20/manual_time_median 40495 ns 67105 ns 5 bytes=1048.58k bytes_per_second=24.1154G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):20/manual_time_stddev 2.77 ns 39.9 ns 5 bytes=0 bytes_per_second=1.69178M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):20/manual_time_cv 0.01 % 0.06 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):21/manual_time 68078 ns 94875 ns 10286 bytes=2.09715M bytes_per_second=28.6894G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):21/manual_time 68192 ns 95045 ns 10286 bytes=2.09715M bytes_per_second=28.6417G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):21/manual_time 68213 ns 95196 ns 10286 bytes=2.09715M bytes_per_second=28.6327G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):21/manual_time 68235 ns 95123 ns 10286 bytes=2.09715M bytes_per_second=28.6235G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):21/manual_time 68080 ns 94931 ns 10286 bytes=2.09715M bytes_per_second=28.6885G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):21/manual_time_mean 68160 ns 95034 ns 5 bytes=2.09715M bytes_per_second=28.6552G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):21/manual_time_median 68192 ns 95045 ns 5 bytes=2.09715M bytes_per_second=28.6417G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):21/manual_time_stddev 74.9 ns 133 ns 5 bytes=0 bytes_per_second=32.2663M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):21/manual_time_cv 0.11 % 0.14 % 5 bytes=0.00% bytes_per_second=0.11% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):22/manual_time 120732 ns 148431 ns 5794 bytes=4.1943M bytes_per_second=32.3546G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):22/manual_time 120810 ns 148570 ns 5794 bytes=4.1943M bytes_per_second=32.3338G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):22/manual_time 120730 ns 148480 ns 5794 bytes=4.1943M bytes_per_second=32.3553G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):22/manual_time 120813 ns 148636 ns 5794 bytes=4.1943M bytes_per_second=32.333G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):22/manual_time 120732 ns 148576 ns 5794 bytes=4.1943M bytes_per_second=32.3548G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):22/manual_time_mean 120763 ns 148538 ns 5 bytes=4.1943M bytes_per_second=32.3463G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):22/manual_time_median 120732 ns 148570 ns 5 bytes=4.1943M bytes_per_second=32.3546G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):22/manual_time_stddev 44.0 ns 82.1 ns 5 bytes=0 bytes_per_second=12.0765M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):22/manual_time_cv 0.04 % 0.06 % 5 bytes=0.00% bytes_per_second=0.04% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):23/manual_time 232135 ns 261873 ns 3016 bytes=8.38861M bytes_per_second=33.6551G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):23/manual_time 232086 ns 261860 ns 3016 bytes=8.38861M bytes_per_second=33.6621G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):23/manual_time 232140 ns 261971 ns 3016 bytes=8.38861M bytes_per_second=33.6542G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):23/manual_time 232086 ns 262002 ns 3016 bytes=8.38861M bytes_per_second=33.662G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):23/manual_time 232138 ns 261976 ns 3016 bytes=8.38861M bytes_per_second=33.6545G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):23/manual_time_mean 232117 ns 261936 ns 5 bytes=8.38861M bytes_per_second=33.6576G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):23/manual_time_median 232135 ns 261971 ns 5 bytes=8.38861M bytes_per_second=33.6551G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):23/manual_time_stddev 28.3 ns 65.2 ns 5 bytes=0 bytes_per_second=4.20487M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):23/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):24/manual_time 455177 ns 490092 ns 1538 bytes=16.7772M bytes_per_second=34.3273G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):24/manual_time 455169 ns 490084 ns 1538 bytes=16.7772M bytes_per_second=34.3279G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):24/manual_time 455182 ns 490180 ns 1538 bytes=16.7772M bytes_per_second=34.3269G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):24/manual_time 455169 ns 490102 ns 1538 bytes=16.7772M bytes_per_second=34.3279G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):24/manual_time 455187 ns 490184 ns 1538 bytes=16.7772M bytes_per_second=34.3265G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):24/manual_time_mean 455177 ns 490129 ns 5 bytes=16.7772M bytes_per_second=34.3273G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):24/manual_time_median 455177 ns 490102 ns 5 bytes=16.7772M bytes_per_second=34.3273G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):24/manual_time_stddev 8.23 ns 49.3 ns 5 bytes=0 bytes_per_second=651.16k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):24/manual_time_cv 0.00 % 0.01 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):25/manual_time 901676 ns 948100 ns 776 bytes=33.5544M bytes_per_second=34.6577G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):25/manual_time 901575 ns 947915 ns 776 bytes=33.5544M bytes_per_second=34.6616G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):25/manual_time 901675 ns 948197 ns 776 bytes=33.5544M bytes_per_second=34.6577G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):25/manual_time 901532 ns 948016 ns 776 bytes=33.5544M bytes_per_second=34.6632G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):25/manual_time 901679 ns 948101 ns 776 bytes=33.5544M bytes_per_second=34.6576G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):25/manual_time_mean 901628 ns 948066 ns 5 bytes=33.5544M bytes_per_second=34.6595G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):25/manual_time_median 901675 ns 948100 ns 5 bytes=33.5544M bytes_per_second=34.6577G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):25/manual_time_stddev 69.3 ns 106 ns 5 bytes=0 bytes_per_second=2.72675M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):25/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):26/manual_time 1794620 ns 1865280 ns 390 bytes=67.1089M bytes_per_second=34.8263G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):26/manual_time 1794671 ns 1865184 ns 390 bytes=67.1089M bytes_per_second=34.8253G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):26/manual_time 1794600 ns 1865311 ns 390 bytes=67.1089M bytes_per_second=34.8267G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):26/manual_time 1794603 ns 1865251 ns 390 bytes=67.1089M bytes_per_second=34.8267G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):26/manual_time 1794630 ns 1865286 ns 390 bytes=67.1089M bytes_per_second=34.8261G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):26/manual_time_mean 1794625 ns 1865262 ns 5 bytes=67.1089M bytes_per_second=34.8262G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):26/manual_time_median 1794620 ns 1865280 ns 5 bytes=67.1089M bytes_per_second=34.8263G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):26/manual_time_stddev 28.7 ns 48.6 ns 5 bytes=0 bytes_per_second=583.688k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):26/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):27/manual_time 3580929 ns 3711284 ns 195 bytes=134.218M bytes_per_second=34.9071G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):27/manual_time 3580923 ns 3711111 ns 195 bytes=134.218M bytes_per_second=34.9072G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):27/manual_time 3580971 ns 3711521 ns 195 bytes=134.218M bytes_per_second=34.9067G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):27/manual_time 3581038 ns 3711297 ns 195 bytes=134.218M bytes_per_second=34.9061G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):27/manual_time 3580900 ns 3711503 ns 195 bytes=134.218M bytes_per_second=34.9074G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):27/manual_time_mean 3580952 ns 3711343 ns 5 bytes=134.218M bytes_per_second=34.9069G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):27/manual_time_median 3580929 ns 3711297 ns 5 bytes=134.218M bytes_per_second=34.9071G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):27/manual_time_stddev 54.6 ns 171 ns 5 bytes=0 bytes_per_second=558.42k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):27/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):28/manual_time 7152961 ns 7387127 ns 98 bytes=268.435M bytes_per_second=34.9506G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):28/manual_time 7153062 ns 7386789 ns 98 bytes=268.435M bytes_per_second=34.9501G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):28/manual_time 7153002 ns 7386825 ns 98 bytes=268.435M bytes_per_second=34.9504G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):28/manual_time 7152876 ns 7387043 ns 98 bytes=268.435M bytes_per_second=34.951G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):28/manual_time 7152754 ns 7386533 ns 98 bytes=268.435M bytes_per_second=34.9516G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):28/manual_time_mean 7152931 ns 7386863 ns 5 bytes=268.435M bytes_per_second=34.9507G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):28/manual_time_median 7152961 ns 7386825 ns 5 bytes=268.435M bytes_per_second=34.9506G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):28/manual_time_stddev 120 ns 233 ns 5 bytes=0 bytes_per_second=614.851k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):28/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):29/manual_time 14296756 ns 14720904 ns 49 bytes=536.871M bytes_per_second=34.973G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):29/manual_time 14296965 ns 14721432 ns 49 bytes=536.871M bytes_per_second=34.9725G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):29/manual_time 14297037 ns 14721083 ns 49 bytes=536.871M bytes_per_second=34.9723G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):29/manual_time 14296870 ns 14721004 ns 49 bytes=536.871M bytes_per_second=34.9727G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):29/manual_time 14296812 ns 14721384 ns 49 bytes=536.871M bytes_per_second=34.9728G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):29/manual_time_mean 14296888 ns 14721162 ns 5 bytes=536.871M bytes_per_second=34.9726G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):29/manual_time_median 14296870 ns 14721083 ns 5 bytes=536.871M bytes_per_second=34.9727G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):29/manual_time_stddev 114 ns 235 ns 5 bytes=0 bytes_per_second=291.444k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):29/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):30/manual_time 28586001 ns 29390132 ns 24 bytes=1073.74M bytes_per_second=34.9822G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):30/manual_time 28586895 ns 29391025 ns 24 bytes=1073.74M bytes_per_second=34.9811G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):30/manual_time 28584968 ns 29388645 ns 24 bytes=1073.74M bytes_per_second=34.9834G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):30/manual_time 28585628 ns 29389113 ns 24 bytes=1073.74M bytes_per_second=34.9826G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):30/manual_time 28585281 ns 29389290 ns 24 bytes=1073.74M bytes_per_second=34.983G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):30/manual_time_mean 28585755 ns 29389641 ns 5 bytes=1073.74M bytes_per_second=34.9825G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):30/manual_time_median 28585628 ns 29389290 ns 5 bytes=1073.74M bytes_per_second=34.9826G/s own_gpu=4 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):30/manual_time_stddev 745 ns 942 ns 5 bytes=0 bytes_per_second=956.187k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/4/log2(N):30/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):12/manual_time 12251 ns 31201 ns 57030 bytes=4.096k bytes_per_second=318.861M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):12/manual_time 12262 ns 31172 ns 57030 bytes=4.096k bytes_per_second=318.576M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):12/manual_time 12264 ns 31213 ns 57030 bytes=4.096k bytes_per_second=318.507M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):12/manual_time 12252 ns 31195 ns 57030 bytes=4.096k bytes_per_second=318.814M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):12/manual_time 12257 ns 31201 ns 57030 bytes=4.096k bytes_per_second=318.684M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):12/manual_time_mean 12257 ns 31197 ns 5 bytes=4.096k bytes_per_second=318.688M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):12/manual_time_median 12257 ns 31201 ns 5 bytes=4.096k bytes_per_second=318.684M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):12/manual_time_stddev 5.80 ns 15.1 ns 5 bytes=0 bytes_per_second=154.442k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):12/manual_time_cv 0.05 % 0.05 % 5 bytes=0.00% bytes_per_second=0.05% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):13/manual_time 12252 ns 31204 ns 57241 bytes=8.192k bytes_per_second=637.626M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):13/manual_time 12256 ns 31137 ns 57241 bytes=8.192k bytes_per_second=637.449M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):13/manual_time 12254 ns 31198 ns 57241 bytes=8.192k bytes_per_second=637.525M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):13/manual_time 12252 ns 31191 ns 57241 bytes=8.192k bytes_per_second=637.667M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):13/manual_time 12247 ns 31206 ns 57241 bytes=8.192k bytes_per_second=637.929M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):13/manual_time_mean 12252 ns 31187 ns 5 bytes=8.192k bytes_per_second=637.639M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):13/manual_time_median 12252 ns 31198 ns 5 bytes=8.192k bytes_per_second=637.626M/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):13/manual_time_stddev 3.51 ns 28.7 ns 5 bytes=0 bytes_per_second=187.349k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):13/manual_time_cv 0.03 % 0.09 % 5 bytes=0.00% bytes_per_second=0.03% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):14/manual_time 12228 ns 31467 ns 57244 bytes=16.384k bytes_per_second=1.24782G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):14/manual_time 12228 ns 31281 ns 57244 bytes=16.384k bytes_per_second=1.24786G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):14/manual_time 12227 ns 31467 ns 57244 bytes=16.384k bytes_per_second=1.24793G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):14/manual_time 12224 ns 31346 ns 57244 bytes=16.384k bytes_per_second=1.24822G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):14/manual_time 12227 ns 31454 ns 57244 bytes=16.384k bytes_per_second=1.24798G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):14/manual_time_mean 12227 ns 31403 ns 5 bytes=16.384k bytes_per_second=1.24796G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):14/manual_time_median 12227 ns 31454 ns 5 bytes=16.384k bytes_per_second=1.24793G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):14/manual_time_stddev 1.52 ns 85.2 ns 5 bytes=0 bytes_per_second=162.467k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):14/manual_time_cv 0.01 % 0.27 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):15/manual_time 12243 ns 31913 ns 57186 bytes=32.768k bytes_per_second=2.49259G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):15/manual_time 12237 ns 31758 ns 57186 bytes=32.768k bytes_per_second=2.49384G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):15/manual_time 12244 ns 31870 ns 57186 bytes=32.768k bytes_per_second=2.49254G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):15/manual_time 12242 ns 31822 ns 57186 bytes=32.768k bytes_per_second=2.4929G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):15/manual_time 12245 ns 31935 ns 57186 bytes=32.768k bytes_per_second=2.49229G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):15/manual_time_mean 12242 ns 31859 ns 5 bytes=32.768k bytes_per_second=2.49283G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):15/manual_time_median 12243 ns 31870 ns 5 bytes=32.768k bytes_per_second=2.49259G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):15/manual_time_stddev 2.96 ns 71.4 ns 5 bytes=0 bytes_per_second=632.471k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):15/manual_time_cv 0.02 % 0.22 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):16/manual_time 12273 ns 32719 ns 57027 bytes=65.536k bytes_per_second=4.97301G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):16/manual_time 12277 ns 32610 ns 57027 bytes=65.536k bytes_per_second=4.97156G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):16/manual_time 12273 ns 32685 ns 57027 bytes=65.536k bytes_per_second=4.97313G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):16/manual_time 12277 ns 32673 ns 57027 bytes=65.536k bytes_per_second=4.97168G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):16/manual_time 12273 ns 32737 ns 57027 bytes=65.536k bytes_per_second=4.97322G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):16/manual_time_mean 12274 ns 32685 ns 5 bytes=65.536k bytes_per_second=4.97252G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):16/manual_time_median 12273 ns 32685 ns 5 bytes=65.536k bytes_per_second=4.97301G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):16/manual_time_stddev 2.04 ns 49.2 ns 5 bytes=0 bytes_per_second=865.605k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):16/manual_time_cv 0.02 % 0.15 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):17/manual_time 15935 ns 38032 ns 43925 bytes=131.072k bytes_per_second=7.66047G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):17/manual_time 15932 ns 37915 ns 43925 bytes=131.072k bytes_per_second=7.66193G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):17/manual_time 15937 ns 37991 ns 43925 bytes=131.072k bytes_per_second=7.65979G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):17/manual_time 15935 ns 37998 ns 43925 bytes=131.072k bytes_per_second=7.66037G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):17/manual_time 15936 ns 38024 ns 43925 bytes=131.072k bytes_per_second=7.66026G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):17/manual_time_mean 15935 ns 37992 ns 5 bytes=131.072k bytes_per_second=7.66056G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):17/manual_time_median 15935 ns 37998 ns 5 bytes=131.072k bytes_per_second=7.66037G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):17/manual_time_stddev 1.68 ns 46.4 ns 5 bytes=0 bytes_per_second=847.385k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):17/manual_time_cv 0.01 % 0.12 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):18/manual_time 19851 ns 44164 ns 35258 bytes=262.144k bytes_per_second=12.2987G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):18/manual_time 19850 ns 43863 ns 35258 bytes=262.144k bytes_per_second=12.2995G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):18/manual_time 19854 ns 44097 ns 35258 bytes=262.144k bytes_per_second=12.2971G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):18/manual_time 19854 ns 43988 ns 35258 bytes=262.144k bytes_per_second=12.2966G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):18/manual_time 19852 ns 44125 ns 35258 bytes=262.144k bytes_per_second=12.2979G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):18/manual_time_mean 19852 ns 44047 ns 5 bytes=262.144k bytes_per_second=12.298G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):18/manual_time_median 19852 ns 44097 ns 5 bytes=262.144k bytes_per_second=12.2979G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):18/manual_time_stddev 1.91 ns 122 ns 5 bytes=0 bytes_per_second=1.20934M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):18/manual_time_cv 0.01 % 0.28 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):19/manual_time 27265 ns 51517 ns 25675 bytes=524.288k bytes_per_second=17.9089G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):19/manual_time 27263 ns 51342 ns 25675 bytes=524.288k bytes_per_second=17.9102G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):19/manual_time 27270 ns 51514 ns 25675 bytes=524.288k bytes_per_second=17.9054G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):19/manual_time 27268 ns 51415 ns 25675 bytes=524.288k bytes_per_second=17.9065G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):19/manual_time 27267 ns 51488 ns 25675 bytes=524.288k bytes_per_second=17.9077G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):19/manual_time_mean 27267 ns 51455 ns 5 bytes=524.288k bytes_per_second=17.9077G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):19/manual_time_median 27267 ns 51488 ns 5 bytes=524.288k bytes_per_second=17.9077G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):19/manual_time_stddev 2.90 ns 75.5 ns 5 bytes=0 bytes_per_second=1.94835M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):19/manual_time_cv 0.01 % 0.15 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):20/manual_time 42075 ns 67561 ns 16637 bytes=1048.58k bytes_per_second=23.2098G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):20/manual_time 42076 ns 67426 ns 16637 bytes=1048.58k bytes_per_second=23.2097G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):20/manual_time 42080 ns 67506 ns 16637 bytes=1048.58k bytes_per_second=23.2075G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):20/manual_time 42079 ns 67447 ns 16637 bytes=1048.58k bytes_per_second=23.208G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):20/manual_time 42077 ns 67552 ns 16637 bytes=1048.58k bytes_per_second=23.2089G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):20/manual_time_mean 42077 ns 67498 ns 5 bytes=1048.58k bytes_per_second=23.2088G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):20/manual_time_median 42077 ns 67506 ns 5 bytes=1048.58k bytes_per_second=23.2089G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):20/manual_time_stddev 1.90 ns 60.6 ns 5 bytes=0 bytes_per_second=1101.45k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):20/manual_time_cv 0.00 % 0.09 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):21/manual_time 71267 ns 97091 ns 9826 bytes=2.09715M bytes_per_second=27.4057G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):21/manual_time 71180 ns 96884 ns 9826 bytes=2.09715M bytes_per_second=27.4393G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):21/manual_time 71248 ns 97111 ns 9826 bytes=2.09715M bytes_per_second=27.4132G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):21/manual_time 71277 ns 97200 ns 9826 bytes=2.09715M bytes_per_second=27.402G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):21/manual_time 71185 ns 96831 ns 9826 bytes=2.09715M bytes_per_second=27.4374G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):21/manual_time_mean 71231 ns 97024 ns 5 bytes=2.09715M bytes_per_second=27.4195G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):21/manual_time_median 71248 ns 97091 ns 5 bytes=2.09715M bytes_per_second=27.4132G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):21/manual_time_stddev 45.9 ns 158 ns 5 bytes=0 bytes_per_second=18.103M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):21/manual_time_cv 0.06 % 0.16 % 5 bytes=0.00% bytes_per_second=0.06% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):22/manual_time 127050 ns 153855 ns 5510 bytes=4.1943M bytes_per_second=30.7458G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):22/manual_time 127045 ns 153726 ns 5510 bytes=4.1943M bytes_per_second=30.747G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):22/manual_time 127048 ns 153798 ns 5510 bytes=4.1943M bytes_per_second=30.7463G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):22/manual_time 127051 ns 153829 ns 5510 bytes=4.1943M bytes_per_second=30.7455G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):22/manual_time 127030 ns 153842 ns 5510 bytes=4.1943M bytes_per_second=30.7505G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):22/manual_time_mean 127045 ns 153810 ns 5 bytes=4.1943M bytes_per_second=30.747G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):22/manual_time_median 127048 ns 153829 ns 5 bytes=4.1943M bytes_per_second=30.7463G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):22/manual_time_stddev 8.46 ns 51.4 ns 5 bytes=0 bytes_per_second=2.09767M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):22/manual_time_cv 0.01 % 0.03 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):23/manual_time 244472 ns 272531 ns 2863 bytes=8.38861M bytes_per_second=31.9566G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):23/manual_time 244511 ns 272537 ns 2863 bytes=8.38861M bytes_per_second=31.9515G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):23/manual_time 244504 ns 272563 ns 2863 bytes=8.38861M bytes_per_second=31.9525G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):23/manual_time 244518 ns 272700 ns 2863 bytes=8.38861M bytes_per_second=31.9506G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):23/manual_time 244467 ns 272571 ns 2863 bytes=8.38861M bytes_per_second=31.9573G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):23/manual_time_mean 244494 ns 272580 ns 5 bytes=8.38861M bytes_per_second=31.9537G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):23/manual_time_median 244504 ns 272563 ns 5 bytes=8.38861M bytes_per_second=31.9525G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):23/manual_time_stddev 23.4 ns 68.7 ns 5 bytes=0 bytes_per_second=3.13326M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):23/manual_time_cv 0.01 % 0.03 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):24/manual_time 480183 ns 513991 ns 1458 bytes=16.7772M bytes_per_second=32.5397G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):24/manual_time 480125 ns 513852 ns 1458 bytes=16.7772M bytes_per_second=32.5436G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):24/manual_time 480144 ns 514016 ns 1458 bytes=16.7772M bytes_per_second=32.5423G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):24/manual_time 480070 ns 513895 ns 1458 bytes=16.7772M bytes_per_second=32.5474G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):24/manual_time 480148 ns 514012 ns 1458 bytes=16.7772M bytes_per_second=32.542G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):24/manual_time_mean 480134 ns 513953 ns 5 bytes=16.7772M bytes_per_second=32.543G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):24/manual_time_median 480144 ns 513991 ns 5 bytes=16.7772M bytes_per_second=32.5423G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):24/manual_time_stddev 41.6 ns 74.9 ns 5 bytes=0 bytes_per_second=2.88553M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):24/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):25/manual_time 951074 ns 996874 ns 736 bytes=33.5544M bytes_per_second=32.8576G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):25/manual_time 951028 ns 996731 ns 736 bytes=33.5544M bytes_per_second=32.8592G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):25/manual_time 951176 ns 996998 ns 736 bytes=33.5544M bytes_per_second=32.8541G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):25/manual_time 951096 ns 996943 ns 736 bytes=33.5544M bytes_per_second=32.8568G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):25/manual_time 951163 ns 996996 ns 736 bytes=33.5544M bytes_per_second=32.8545G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):25/manual_time_mean 951108 ns 996908 ns 5 bytes=33.5544M bytes_per_second=32.8564G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):25/manual_time_median 951096 ns 996943 ns 5 bytes=33.5544M bytes_per_second=32.8568G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):25/manual_time_stddev 61.8 ns 111 ns 5 bytes=0 bytes_per_second=2.18664M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):25/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):26/manual_time 1886747 ns 1956594 ns 371 bytes=67.1089M bytes_per_second=33.1258G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):26/manual_time 1887182 ns 1956857 ns 371 bytes=67.1089M bytes_per_second=33.1182G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):26/manual_time 1886879 ns 1956711 ns 371 bytes=67.1089M bytes_per_second=33.1235G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):26/manual_time 1887315 ns 1957051 ns 371 bytes=67.1089M bytes_per_second=33.1158G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):26/manual_time 1886648 ns 1956517 ns 371 bytes=67.1089M bytes_per_second=33.1275G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):26/manual_time_mean 1886954 ns 1956746 ns 5 bytes=67.1089M bytes_per_second=33.1222G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):26/manual_time_median 1886879 ns 1956711 ns 5 bytes=67.1089M bytes_per_second=33.1235G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):26/manual_time_stddev 285 ns 213 ns 5 bytes=0 bytes_per_second=5.11707M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):26/manual_time_cv 0.02 % 0.01 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):27/manual_time 3747724 ns 3879132 ns 187 bytes=134.218M bytes_per_second=33.3536G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):27/manual_time 3748637 ns 3879784 ns 187 bytes=134.218M bytes_per_second=33.3455G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):27/manual_time 3748681 ns 3880440 ns 187 bytes=134.218M bytes_per_second=33.3451G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):27/manual_time 3748901 ns 3880697 ns 187 bytes=134.218M bytes_per_second=33.3431G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):27/manual_time 3748591 ns 3881041 ns 187 bytes=134.218M bytes_per_second=33.3459G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):27/manual_time_mean 3748507 ns 3880219 ns 5 bytes=134.218M bytes_per_second=33.3466G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):27/manual_time_median 3748637 ns 3880440 ns 5 bytes=134.218M bytes_per_second=33.3455G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):27/manual_time_stddev 453 ns 762 ns 5 bytes=0 bytes_per_second=4.1299M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):27/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):28/manual_time 7477955 ns 7711400 ns 94 bytes=268.435M bytes_per_second=33.4316G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):28/manual_time 7478349 ns 7711486 ns 94 bytes=268.435M bytes_per_second=33.4298G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):28/manual_time 7479372 ns 7712811 ns 94 bytes=268.435M bytes_per_second=33.4253G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):28/manual_time 7477086 ns 7711502 ns 94 bytes=268.435M bytes_per_second=33.4355G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):28/manual_time 7478195 ns 7711591 ns 94 bytes=268.435M bytes_per_second=33.4305G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):28/manual_time_mean 7478191 ns 7711758 ns 5 bytes=268.435M bytes_per_second=33.4305G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):28/manual_time_median 7478195 ns 7711502 ns 5 bytes=268.435M bytes_per_second=33.4305G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):28/manual_time_stddev 821 ns 593 ns 5 bytes=0 bytes_per_second=3.75812M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):28/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):29/manual_time 14941838 ns 15365464 ns 47 bytes=536.871M bytes_per_second=33.4631G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):29/manual_time 14938668 ns 15362947 ns 47 bytes=536.871M bytes_per_second=33.4702G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):29/manual_time 14938920 ns 15362803 ns 47 bytes=536.871M bytes_per_second=33.4696G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):29/manual_time 14939182 ns 15362690 ns 47 bytes=536.871M bytes_per_second=33.469G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):29/manual_time 14940292 ns 15364400 ns 47 bytes=536.871M bytes_per_second=33.4665G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):29/manual_time_mean 14939780 ns 15363661 ns 5 bytes=536.871M bytes_per_second=33.4677G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):29/manual_time_median 14939182 ns 15362947 ns 5 bytes=536.871M bytes_per_second=33.469G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):29/manual_time_stddev 1307 ns 1223 ns 5 bytes=0 bytes_per_second=2.99705M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):29/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):30/manual_time 29843612 ns 30646972 ns 23 bytes=1073.74M bytes_per_second=33.508G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):30/manual_time 29850422 ns 30653481 ns 23 bytes=1073.74M bytes_per_second=33.5004G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):30/manual_time 29844043 ns 30647140 ns 23 bytes=1073.74M bytes_per_second=33.5075G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):30/manual_time 29848203 ns 30651951 ns 23 bytes=1073.74M bytes_per_second=33.5029G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):30/manual_time 29846304 ns 30648938 ns 23 bytes=1073.74M bytes_per_second=33.505G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):30/manual_time_mean 29846517 ns 30649696 ns 5 bytes=1073.74M bytes_per_second=33.5047G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):30/manual_time_median 29846304 ns 30648938 ns 5 bytes=1073.74M bytes_per_second=33.505G/s own_gpu=5 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):30/manual_time_stddev 2859 ns 2913 ns 5 bytes=0 bytes_per_second=3.28654M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/5/log2(N):30/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):12/manual_time 12262 ns 33540 ns 57084 bytes=4.096k bytes_per_second=318.568M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):12/manual_time 12258 ns 33527 ns 57084 bytes=4.096k bytes_per_second=318.657M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):12/manual_time 12260 ns 33370 ns 57084 bytes=4.096k bytes_per_second=318.623M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):12/manual_time 12256 ns 33372 ns 57084 bytes=4.096k bytes_per_second=318.734M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):12/manual_time 12253 ns 33404 ns 57084 bytes=4.096k bytes_per_second=318.792M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):12/manual_time_mean 12258 ns 33443 ns 5 bytes=4.096k bytes_per_second=318.675M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):12/manual_time_median 12258 ns 33404 ns 5 bytes=4.096k bytes_per_second=318.657M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):12/manual_time_stddev 3.42 ns 84.4 ns 5 bytes=0 bytes_per_second=91.03k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):12/manual_time_cv 0.03 % 0.25 % 5 bytes=0.00% bytes_per_second=0.03% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):13/manual_time 12255 ns 33441 ns 57092 bytes=8.192k bytes_per_second=637.517M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):13/manual_time 12250 ns 33383 ns 57092 bytes=8.192k bytes_per_second=637.748M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):13/manual_time 12257 ns 33405 ns 57092 bytes=8.192k bytes_per_second=637.378M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):13/manual_time 12264 ns 33470 ns 57092 bytes=8.192k bytes_per_second=637.032M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):13/manual_time 12265 ns 33447 ns 57092 bytes=8.192k bytes_per_second=636.963M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):13/manual_time_mean 12258 ns 33429 ns 5 bytes=8.192k bytes_per_second=637.328M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):13/manual_time_median 12257 ns 33441 ns 5 bytes=8.192k bytes_per_second=637.378M/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):13/manual_time_stddev 6.35 ns 35.0 ns 5 bytes=0 bytes_per_second=338.058k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):13/manual_time_cv 0.05 % 0.10 % 5 bytes=0.00% bytes_per_second=0.05% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):14/manual_time 12260 ns 33759 ns 57092 bytes=16.384k bytes_per_second=1.2446G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):14/manual_time 12261 ns 33726 ns 57092 bytes=16.384k bytes_per_second=1.24453G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):14/manual_time 12262 ns 33763 ns 57092 bytes=16.384k bytes_per_second=1.24441G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):14/manual_time 12261 ns 33857 ns 57092 bytes=16.384k bytes_per_second=1.2445G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):14/manual_time 12259 ns 33875 ns 57092 bytes=16.384k bytes_per_second=1.24467G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):14/manual_time_mean 12261 ns 33796 ns 5 bytes=16.384k bytes_per_second=1.24454G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):14/manual_time_median 12261 ns 33763 ns 5 bytes=16.384k bytes_per_second=1.24453G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):14/manual_time_stddev 0.970 ns 65.9 ns 5 bytes=0 bytes_per_second=103.204k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):14/manual_time_cv 0.01 % 0.19 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):15/manual_time 12260 ns 34166 ns 57074 bytes=32.768k bytes_per_second=2.48915G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):15/manual_time 12261 ns 34189 ns 57074 bytes=32.768k bytes_per_second=2.48902G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):15/manual_time 12260 ns 34025 ns 57074 bytes=32.768k bytes_per_second=2.4892G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):15/manual_time 12260 ns 34025 ns 57074 bytes=32.768k bytes_per_second=2.48921G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):15/manual_time 12263 ns 34072 ns 57074 bytes=32.768k bytes_per_second=2.48865G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):15/manual_time_mean 12261 ns 34095 ns 5 bytes=32.768k bytes_per_second=2.48904G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):15/manual_time_median 12260 ns 34072 ns 5 bytes=32.768k bytes_per_second=2.48915G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):15/manual_time_stddev 1.15 ns 77.9 ns 5 bytes=0 bytes_per_second=245.299k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):15/manual_time_cv 0.01 % 0.23 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):16/manual_time 12275 ns 34872 ns 57057 bytes=65.536k bytes_per_second=4.97218G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):16/manual_time 12271 ns 34830 ns 57057 bytes=65.536k bytes_per_second=4.97374G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):16/manual_time 12266 ns 34753 ns 57057 bytes=65.536k bytes_per_second=4.97609G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):16/manual_time 12269 ns 34791 ns 57057 bytes=65.536k bytes_per_second=4.97457G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):16/manual_time 12273 ns 34769 ns 57057 bytes=65.536k bytes_per_second=4.97308G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):16/manual_time_mean 12271 ns 34803 ns 5 bytes=65.536k bytes_per_second=4.97393G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):16/manual_time_median 12271 ns 34791 ns 5 bytes=65.536k bytes_per_second=4.97374G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):16/manual_time_stddev 3.68 ns 48.1 ns 5 bytes=0 bytes_per_second=1.526M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):16/manual_time_cv 0.03 % 0.14 % 5 bytes=0.00% bytes_per_second=0.03% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):17/manual_time 12262 ns 36186 ns 57092 bytes=131.072k bytes_per_second=9.95499G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):17/manual_time 12261 ns 36202 ns 57092 bytes=131.072k bytes_per_second=9.95627G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):17/manual_time 12260 ns 35951 ns 57092 bytes=131.072k bytes_per_second=9.95661G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):17/manual_time 12260 ns 36143 ns 57092 bytes=131.072k bytes_per_second=9.95715G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):17/manual_time 12260 ns 36178 ns 57092 bytes=131.072k bytes_per_second=9.95678G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):17/manual_time_mean 12261 ns 36132 ns 5 bytes=131.072k bytes_per_second=9.95636G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):17/manual_time_median 12260 ns 36178 ns 5 bytes=131.072k bytes_per_second=9.95661G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):17/manual_time_stddev 1.02 ns 103 ns 5 bytes=0 bytes_per_second=870.314k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):17/manual_time_cv 0.01 % 0.29 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):18/manual_time 15658 ns 41371 ns 44705 bytes=262.144k bytes_per_second=15.5925G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):18/manual_time 15658 ns 41296 ns 44705 bytes=262.144k bytes_per_second=15.5917G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):18/manual_time 15654 ns 41216 ns 44705 bytes=262.144k bytes_per_second=15.5958G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):18/manual_time 15658 ns 41290 ns 44705 bytes=262.144k bytes_per_second=15.5917G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):18/manual_time 15655 ns 41253 ns 44705 bytes=262.144k bytes_per_second=15.5953G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):18/manual_time_mean 15657 ns 41285 ns 5 bytes=262.144k bytes_per_second=15.5934G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):18/manual_time_median 15658 ns 41290 ns 5 bytes=262.144k bytes_per_second=15.5925G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):18/manual_time_stddev 2.01 ns 57.6 ns 5 bytes=0 bytes_per_second=2.05123M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):18/manual_time_cv 0.01 % 0.14 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):19/manual_time 18984 ns 44748 ns 36875 bytes=524.288k bytes_per_second=25.7202G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):19/manual_time 18980 ns 44703 ns 36875 bytes=524.288k bytes_per_second=25.7266G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):19/manual_time 18982 ns 44701 ns 36875 bytes=524.288k bytes_per_second=25.7228G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):19/manual_time 18977 ns 44599 ns 36875 bytes=524.288k bytes_per_second=25.7299G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):19/manual_time 18981 ns 44659 ns 36875 bytes=524.288k bytes_per_second=25.7246G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):19/manual_time_mean 18981 ns 44682 ns 5 bytes=524.288k bytes_per_second=25.7248G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):19/manual_time_median 18981 ns 44701 ns 5 bytes=524.288k bytes_per_second=25.7246G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):19/manual_time_stddev 2.72 ns 56.3 ns 5 bytes=0 bytes_per_second=3.78162M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):19/manual_time_cv 0.01 % 0.13 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):20/manual_time 25609 ns 51476 ns 27325 bytes=1048.58k bytes_per_second=38.1342G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):20/manual_time 25615 ns 51434 ns 27325 bytes=1048.58k bytes_per_second=38.125G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):20/manual_time 25610 ns 51375 ns 27325 bytes=1048.58k bytes_per_second=38.132G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):20/manual_time 25613 ns 51330 ns 27325 bytes=1048.58k bytes_per_second=38.1283G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):20/manual_time 25610 ns 51348 ns 27325 bytes=1048.58k bytes_per_second=38.132G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):20/manual_time_mean 25611 ns 51393 ns 5 bytes=1048.58k bytes_per_second=38.1303G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):20/manual_time_median 25610 ns 51375 ns 5 bytes=1048.58k bytes_per_second=38.132G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):20/manual_time_stddev 2.44 ns 61.1 ns 5 bytes=0 bytes_per_second=3.7154M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):20/manual_time_cv 0.01 % 0.12 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):21/manual_time 38702 ns 64855 ns 18064 bytes=2.09715M bytes_per_second=50.4652G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):21/manual_time 38686 ns 64785 ns 18064 bytes=2.09715M bytes_per_second=50.4862G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):21/manual_time 38690 ns 64700 ns 18064 bytes=2.09715M bytes_per_second=50.481G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):21/manual_time 38746 ns 64719 ns 18064 bytes=2.09715M bytes_per_second=50.4085G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):21/manual_time 38687 ns 64585 ns 18064 bytes=2.09715M bytes_per_second=50.4859G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):21/manual_time_mean 38702 ns 64729 ns 5 bytes=2.09715M bytes_per_second=50.4654G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):21/manual_time_median 38690 ns 64719 ns 5 bytes=2.09715M bytes_per_second=50.481G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):21/manual_time_stddev 25.3 ns 101 ns 5 bytes=0 bytes_per_second=33.7145M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):21/manual_time_cv 0.07 % 0.16 % 5 bytes=0.00% bytes_per_second=0.07% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):22/manual_time 61802 ns 88604 ns 11347 bytes=4.1943M bytes_per_second=63.2061G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):22/manual_time 61697 ns 88364 ns 11347 bytes=4.1943M bytes_per_second=63.3134G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):22/manual_time 61805 ns 88340 ns 11347 bytes=4.1943M bytes_per_second=63.2028G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):22/manual_time 61712 ns 88158 ns 11347 bytes=4.1943M bytes_per_second=63.2984G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):22/manual_time 61802 ns 88279 ns 11347 bytes=4.1943M bytes_per_second=63.2062G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):22/manual_time_mean 61763 ns 88349 ns 5 bytes=4.1943M bytes_per_second=63.2454G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):22/manual_time_median 61802 ns 88340 ns 5 bytes=4.1943M bytes_per_second=63.2062G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):22/manual_time_stddev 54.2 ns 163 ns 5 bytes=0 bytes_per_second=56.8412M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):22/manual_time_cv 0.09 % 0.18 % 5 bytes=0.00% bytes_per_second=0.09% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):23/manual_time 114944 ns 143114 ns 6085 bytes=8.38861M bytes_per_second=67.9677G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):23/manual_time 115004 ns 143168 ns 6085 bytes=8.38861M bytes_per_second=67.9323G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):23/manual_time 114949 ns 143049 ns 6085 bytes=8.38861M bytes_per_second=67.9648G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):23/manual_time 115022 ns 143138 ns 6085 bytes=8.38861M bytes_per_second=67.9216G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):23/manual_time 114951 ns 143089 ns 6085 bytes=8.38861M bytes_per_second=67.9636G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):23/manual_time_mean 114974 ns 143112 ns 5 bytes=8.38861M bytes_per_second=67.95G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):23/manual_time_median 114951 ns 143114 ns 5 bytes=8.38861M bytes_per_second=67.9636G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):23/manual_time_stddev 36.3 ns 45.7 ns 5 bytes=0 bytes_per_second=21.9492M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):23/manual_time_cv 0.03 % 0.03 % 5 bytes=0.00% bytes_per_second=0.03% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):24/manual_time 222490 ns 256323 ns 3146 bytes=16.7772M bytes_per_second=70.2278G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):24/manual_time 222505 ns 256424 ns 3146 bytes=16.7772M bytes_per_second=70.2232G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):24/manual_time 222514 ns 256514 ns 3146 bytes=16.7772M bytes_per_second=70.2204G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):24/manual_time 222515 ns 256448 ns 3146 bytes=16.7772M bytes_per_second=70.22G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):24/manual_time 222461 ns 256412 ns 3146 bytes=16.7772M bytes_per_second=70.2369G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):24/manual_time_mean 222497 ns 256424 ns 5 bytes=16.7772M bytes_per_second=70.2257G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):24/manual_time_median 222505 ns 256424 ns 5 bytes=16.7772M bytes_per_second=70.2232G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):24/manual_time_stddev 22.2 ns 68.9 ns 5 bytes=0 bytes_per_second=7.19084M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):24/manual_time_cv 0.01 % 0.03 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):25/manual_time 438577 ns 484391 ns 1596 bytes=33.5544M bytes_per_second=71.2531G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):25/manual_time 438641 ns 484405 ns 1596 bytes=33.5544M bytes_per_second=71.2428G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):25/manual_time 438534 ns 484116 ns 1596 bytes=33.5544M bytes_per_second=71.2601G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):25/manual_time 438607 ns 484201 ns 1596 bytes=33.5544M bytes_per_second=71.2483G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):25/manual_time 438518 ns 484159 ns 1596 bytes=33.5544M bytes_per_second=71.2628G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):25/manual_time_mean 438575 ns 484255 ns 5 bytes=33.5544M bytes_per_second=71.2534G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):25/manual_time_median 438577 ns 484201 ns 5 bytes=33.5544M bytes_per_second=71.2531G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):25/manual_time_stddev 50.8 ns 134 ns 5 bytes=0 bytes_per_second=8.44657M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):25/manual_time_cv 0.01 % 0.03 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):26/manual_time 872442 ns 942800 ns 802 bytes=67.1089M bytes_per_second=71.638G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):26/manual_time 872393 ns 942881 ns 802 bytes=67.1089M bytes_per_second=71.642G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):26/manual_time 872328 ns 942615 ns 802 bytes=67.1089M bytes_per_second=71.6474G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):26/manual_time 872479 ns 942833 ns 802 bytes=67.1089M bytes_per_second=71.635G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):26/manual_time 872429 ns 942713 ns 802 bytes=67.1089M bytes_per_second=71.6391G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):26/manual_time_mean 872414 ns 942768 ns 5 bytes=67.1089M bytes_per_second=71.6403G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):26/manual_time_median 872429 ns 942800 ns 5 bytes=67.1089M bytes_per_second=71.6391G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):26/manual_time_stddev 57.1 ns 105 ns 5 bytes=0 bytes_per_second=4.80022M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):26/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):27/manual_time 1740101 ns 1857551 ns 402 bytes=134.218M bytes_per_second=71.8349G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):27/manual_time 1740110 ns 1857567 ns 402 bytes=134.218M bytes_per_second=71.8346G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):27/manual_time 1740072 ns 1857638 ns 402 bytes=134.218M bytes_per_second=71.8361G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):27/manual_time 1740089 ns 1857511 ns 402 bytes=134.218M bytes_per_second=71.8354G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):27/manual_time 1740127 ns 1857559 ns 402 bytes=134.218M bytes_per_second=71.8338G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):27/manual_time_mean 1740100 ns 1857565 ns 5 bytes=134.218M bytes_per_second=71.835G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):27/manual_time_median 1740101 ns 1857559 ns 5 bytes=134.218M bytes_per_second=71.8349G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):27/manual_time_stddev 20.9 ns 46.4 ns 5 bytes=0 bytes_per_second=906.595k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):27/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):28/manual_time 3477178 ns 3699721 ns 201 bytes=268.435M bytes_per_second=71.8974G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):28/manual_time 3477155 ns 3699988 ns 201 bytes=268.435M bytes_per_second=71.8979G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):28/manual_time 3477292 ns 3700162 ns 201 bytes=268.435M bytes_per_second=71.895G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):28/manual_time 3477226 ns 3700046 ns 201 bytes=268.435M bytes_per_second=71.8964G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):28/manual_time 3477202 ns 3700076 ns 201 bytes=268.435M bytes_per_second=71.8969G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):28/manual_time_mean 3477210 ns 3699998 ns 5 bytes=268.435M bytes_per_second=71.8967G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):28/manual_time_median 3477202 ns 3700046 ns 5 bytes=268.435M bytes_per_second=71.8969G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):28/manual_time_stddev 52.7 ns 168 ns 5 bytes=0 bytes_per_second=1.11505M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):28/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):29/manual_time 6953666 ns 7378277 ns 101 bytes=536.871M bytes_per_second=71.9045G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):29/manual_time 6953300 ns 7377907 ns 101 bytes=536.871M bytes_per_second=71.9083G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):29/manual_time 6953905 ns 7378263 ns 101 bytes=536.871M bytes_per_second=71.902G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):29/manual_time 6953682 ns 7377628 ns 101 bytes=536.871M bytes_per_second=71.9044G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):29/manual_time 6953680 ns 7377917 ns 101 bytes=536.871M bytes_per_second=71.9044G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):29/manual_time_mean 6953647 ns 7377998 ns 5 bytes=536.871M bytes_per_second=71.9047G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):29/manual_time_median 6953680 ns 7377917 ns 5 bytes=536.871M bytes_per_second=71.9044G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):29/manual_time_stddev 218 ns 274 ns 5 bytes=0 bytes_per_second=2.30624M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):29/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):30/manual_time 13912737 ns 14716494 ns 50 bytes=1073.74M bytes_per_second=71.8766G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):30/manual_time 13911941 ns 14716060 ns 50 bytes=1073.74M bytes_per_second=71.8807G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):30/manual_time 13913163 ns 14717758 ns 50 bytes=1073.74M bytes_per_second=71.8744G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):30/manual_time 13912792 ns 14716281 ns 50 bytes=1073.74M bytes_per_second=71.8763G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):30/manual_time 13913214 ns 14716734 ns 50 bytes=1073.74M bytes_per_second=71.8741G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):30/manual_time_mean 13912769 ns 14716665 ns 5 bytes=1073.74M bytes_per_second=71.8764G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):30/manual_time_median 13912792 ns 14716494 ns 5 bytes=1073.74M bytes_per_second=71.8763G/s own_gpu=6 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):30/manual_time_stddev 510 ns 660 ns 5 bytes=0 bytes_per_second=2.69939M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/6/log2(N):30/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):12/manual_time 12261 ns 31165 ns 57207 bytes=4.096k bytes_per_second=318.593M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):12/manual_time 12255 ns 31173 ns 57207 bytes=4.096k bytes_per_second=318.747M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):12/manual_time 12261 ns 31179 ns 57207 bytes=4.096k bytes_per_second=318.594M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):12/manual_time 12258 ns 31151 ns 57207 bytes=4.096k bytes_per_second=318.663M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):12/manual_time 12245 ns 31150 ns 57207 bytes=4.096k bytes_per_second=319.014M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):12/manual_time_mean 12256 ns 31164 ns 5 bytes=4.096k bytes_per_second=318.722M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):12/manual_time_median 12258 ns 31165 ns 5 bytes=4.096k bytes_per_second=318.663M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):12/manual_time_stddev 6.73 ns 13.0 ns 5 bytes=0 bytes_per_second=179.334k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):12/manual_time_cv 0.05 % 0.04 % 5 bytes=0.00% bytes_per_second=0.05% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):13/manual_time 12243 ns 31130 ns 56959 bytes=8.192k bytes_per_second=638.102M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):13/manual_time 12243 ns 31202 ns 56959 bytes=8.192k bytes_per_second=638.124M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):13/manual_time 12252 ns 31194 ns 56959 bytes=8.192k bytes_per_second=637.638M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):13/manual_time 12252 ns 31198 ns 56959 bytes=8.192k bytes_per_second=637.663M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):13/manual_time 12243 ns 31213 ns 56959 bytes=8.192k bytes_per_second=638.103M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):13/manual_time_mean 12247 ns 31187 ns 5 bytes=8.192k bytes_per_second=637.926M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):13/manual_time_median 12243 ns 31198 ns 5 bytes=8.192k bytes_per_second=638.102M/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):13/manual_time_stddev 4.83 ns 32.8 ns 5 bytes=0 bytes_per_second=257.688k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):13/manual_time_cv 0.04 % 0.11 % 5 bytes=0.00% bytes_per_second=0.04% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):14/manual_time 12231 ns 31231 ns 57266 bytes=16.384k bytes_per_second=1.24758G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):14/manual_time 12219 ns 31315 ns 57266 bytes=16.384k bytes_per_second=1.24881G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):14/manual_time 12223 ns 31362 ns 57266 bytes=16.384k bytes_per_second=1.24832G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):14/manual_time 12223 ns 31349 ns 57266 bytes=16.384k bytes_per_second=1.24832G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):14/manual_time 12221 ns 31345 ns 57266 bytes=16.384k bytes_per_second=1.24856G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):14/manual_time_mean 12223 ns 31320 ns 5 bytes=16.384k bytes_per_second=1.24832G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):14/manual_time_median 12223 ns 31345 ns 5 bytes=16.384k bytes_per_second=1.24832G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):14/manual_time_stddev 4.48 ns 52.7 ns 5 bytes=0 bytes_per_second=480.017k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):14/manual_time_cv 0.04 % 0.17 % 5 bytes=0.00% bytes_per_second=0.04% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):15/manual_time 12231 ns 31590 ns 57234 bytes=32.768k bytes_per_second=2.49514G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):15/manual_time 12234 ns 31713 ns 57234 bytes=32.768k bytes_per_second=2.49455G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):15/manual_time 12236 ns 31736 ns 57234 bytes=32.768k bytes_per_second=2.49406G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):15/manual_time 12235 ns 31683 ns 57234 bytes=32.768k bytes_per_second=2.49427G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):15/manual_time 12236 ns 31720 ns 57234 bytes=32.768k bytes_per_second=2.49409G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):15/manual_time_mean 12234 ns 31689 ns 5 bytes=32.768k bytes_per_second=2.49442G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):15/manual_time_median 12235 ns 31713 ns 5 bytes=32.768k bytes_per_second=2.49427G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):15/manual_time_stddev 2.19 ns 58.4 ns 5 bytes=0 bytes_per_second=468.167k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):15/manual_time_cv 0.02 % 0.18 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):16/manual_time 12258 ns 32293 ns 57081 bytes=65.536k bytes_per_second=4.97917G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):16/manual_time 12263 ns 32445 ns 57081 bytes=65.536k bytes_per_second=4.97702G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):16/manual_time 12263 ns 32409 ns 57081 bytes=65.536k bytes_per_second=4.97738G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):16/manual_time 12264 ns 32413 ns 57081 bytes=65.536k bytes_per_second=4.97677G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):16/manual_time 12264 ns 32418 ns 57081 bytes=65.536k bytes_per_second=4.97687G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):16/manual_time_mean 12262 ns 32395 ns 5 bytes=65.536k bytes_per_second=4.97744G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):16/manual_time_median 12263 ns 32413 ns 5 bytes=65.536k bytes_per_second=4.97702G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):16/manual_time_stddev 2.45 ns 59.2 ns 5 bytes=0 bytes_per_second=1042.22k/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):16/manual_time_cv 0.02 % 0.18 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):17/manual_time 12285 ns 33657 ns 56956 bytes=131.072k bytes_per_second=9.93667G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):17/manual_time 12286 ns 33806 ns 56956 bytes=131.072k bytes_per_second=9.93588G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):17/manual_time 12289 ns 33803 ns 56956 bytes=131.072k bytes_per_second=9.93316G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):17/manual_time 12289 ns 33830 ns 56956 bytes=131.072k bytes_per_second=9.93334G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):17/manual_time 12289 ns 33808 ns 56956 bytes=131.072k bytes_per_second=9.93296G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):17/manual_time_mean 12288 ns 33781 ns 5 bytes=131.072k bytes_per_second=9.9344G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):17/manual_time_median 12289 ns 33806 ns 5 bytes=131.072k bytes_per_second=9.93334G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):17/manual_time_stddev 2.15 ns 70.3 ns 5 bytes=0 bytes_per_second=1.77938M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):17/manual_time_cv 0.02 % 0.21 % 5 bytes=0.00% bytes_per_second=0.02% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):18/manual_time 16183 ns 39329 ns 43266 bytes=262.144k bytes_per_second=15.0864G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):18/manual_time 16183 ns 39380 ns 43266 bytes=262.144k bytes_per_second=15.0863G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):18/manual_time 16186 ns 39367 ns 43266 bytes=262.144k bytes_per_second=15.0839G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):18/manual_time 16185 ns 39395 ns 43266 bytes=262.144k bytes_per_second=15.0845G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):18/manual_time 16186 ns 39370 ns 43266 bytes=262.144k bytes_per_second=15.0838G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):18/manual_time_mean 16184 ns 39368 ns 5 bytes=262.144k bytes_per_second=15.085G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):18/manual_time_median 16185 ns 39370 ns 5 bytes=262.144k bytes_per_second=15.0845G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):18/manual_time_stddev 1.39 ns 24.3 ns 5 bytes=0 bytes_per_second=1.32295M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):18/manual_time_cv 0.01 % 0.06 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):19/manual_time 19902 ns 43179 ns 35168 bytes=524.288k bytes_per_second=24.534G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):19/manual_time 19907 ns 43340 ns 35168 bytes=524.288k bytes_per_second=24.5278G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):19/manual_time 19902 ns 43216 ns 35168 bytes=524.288k bytes_per_second=24.5339G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):19/manual_time 19905 ns 43253 ns 35168 bytes=524.288k bytes_per_second=24.5311G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):19/manual_time 19905 ns 43233 ns 35168 bytes=524.288k bytes_per_second=24.5309G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):19/manual_time_mean 19904 ns 43244 ns 5 bytes=524.288k bytes_per_second=24.5316G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):19/manual_time_median 19905 ns 43233 ns 5 bytes=524.288k bytes_per_second=24.5311G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):19/manual_time_stddev 2.08 ns 60.3 ns 5 bytes=0 bytes_per_second=2.62957M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):19/manual_time_cv 0.01 % 0.14 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):20/manual_time 27337 ns 51090 ns 25606 bytes=1048.58k bytes_per_second=35.7225G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):20/manual_time 27338 ns 51176 ns 25606 bytes=1048.58k bytes_per_second=35.7213G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):20/manual_time 27344 ns 51158 ns 25606 bytes=1048.58k bytes_per_second=35.7139G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):20/manual_time 27345 ns 51234 ns 25606 bytes=1048.58k bytes_per_second=35.7123G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):20/manual_time 27342 ns 51193 ns 25606 bytes=1048.58k bytes_per_second=35.7163G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):20/manual_time_mean 27341 ns 51170 ns 5 bytes=1048.58k bytes_per_second=35.7172G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):20/manual_time_median 27342 ns 51176 ns 5 bytes=1048.58k bytes_per_second=35.7163G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):20/manual_time_stddev 3.44 ns 52.8 ns 5 bytes=0 bytes_per_second=4.59937M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):20/manual_time_cv 0.01 % 0.10 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):21/manual_time 41932 ns 66642 ns 16671 bytes=2.09715M bytes_per_second=46.5787G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):21/manual_time 41991 ns 66757 ns 16671 bytes=2.09715M bytes_per_second=46.5126G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):21/manual_time 41919 ns 66718 ns 16671 bytes=2.09715M bytes_per_second=46.5926G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):21/manual_time 41997 ns 66877 ns 16671 bytes=2.09715M bytes_per_second=46.5066G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):21/manual_time 42009 ns 66840 ns 16671 bytes=2.09715M bytes_per_second=46.4926G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):21/manual_time_mean 41970 ns 66767 ns 5 bytes=2.09715M bytes_per_second=46.5366G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):21/manual_time_median 41991 ns 66757 ns 5 bytes=2.09715M bytes_per_second=46.5126G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):21/manual_time_stddev 41.1 ns 94.2 ns 5 bytes=0 bytes_per_second=46.6657M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):21/manual_time_cv 0.10 % 0.14 % 5 bytes=0.00% bytes_per_second=0.10% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):22/manual_time 68199 ns 94196 ns 10264 bytes=4.1943M bytes_per_second=57.277G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):22/manual_time 68192 ns 94266 ns 10264 bytes=4.1943M bytes_per_second=57.2834G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):22/manual_time 68187 ns 94135 ns 10264 bytes=4.1943M bytes_per_second=57.2875G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):22/manual_time 68186 ns 94205 ns 10264 bytes=4.1943M bytes_per_second=57.2884G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):22/manual_time 68195 ns 94216 ns 10264 bytes=4.1943M bytes_per_second=57.2808G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):22/manual_time_mean 68192 ns 94204 ns 5 bytes=4.1943M bytes_per_second=57.2834G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):22/manual_time_median 68192 ns 94205 ns 5 bytes=4.1943M bytes_per_second=57.2834G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):22/manual_time_stddev 5.63 ns 47.0 ns 5 bytes=0 bytes_per_second=4.84377M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):22/manual_time_cv 0.01 % 0.05 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):23/manual_time 126777 ns 154414 ns 5522 bytes=8.38861M bytes_per_second=61.624G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):23/manual_time 126743 ns 154466 ns 5522 bytes=8.38861M bytes_per_second=61.6406G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):23/manual_time 126782 ns 154350 ns 5522 bytes=8.38861M bytes_per_second=61.6213G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):23/manual_time 126757 ns 154301 ns 5522 bytes=8.38861M bytes_per_second=61.6339G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):23/manual_time 126778 ns 154360 ns 5522 bytes=8.38861M bytes_per_second=61.6234G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):23/manual_time_mean 126767 ns 154378 ns 5 bytes=8.38861M bytes_per_second=61.6287G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):23/manual_time_median 126777 ns 154360 ns 5 bytes=8.38861M bytes_per_second=61.624G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):23/manual_time_stddev 17.0 ns 63.3 ns 5 bytes=0 bytes_per_second=8.48301M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):23/manual_time_cv 0.01 % 0.04 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):24/manual_time 244349 ns 277997 ns 2865 bytes=16.7772M bytes_per_second=63.9455G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):24/manual_time 244311 ns 277944 ns 2865 bytes=16.7772M bytes_per_second=63.9554G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):24/manual_time 244366 ns 278051 ns 2865 bytes=16.7772M bytes_per_second=63.9408G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):24/manual_time 244344 ns 278078 ns 2865 bytes=16.7772M bytes_per_second=63.9468G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):24/manual_time 244362 ns 278093 ns 2865 bytes=16.7772M bytes_per_second=63.9421G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):24/manual_time_mean 244346 ns 278033 ns 5 bytes=16.7772M bytes_per_second=63.9461G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):24/manual_time_median 244349 ns 278051 ns 5 bytes=16.7772M bytes_per_second=63.9455G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):24/manual_time_stddev 21.9 ns 61.5 ns 5 bytes=0 bytes_per_second=5.86793M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):24/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):25/manual_time 479494 ns 524658 ns 1460 bytes=33.5544M bytes_per_second=65.1729G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):25/manual_time 479597 ns 524794 ns 1460 bytes=33.5544M bytes_per_second=65.1589G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):25/manual_time 479528 ns 524777 ns 1460 bytes=33.5544M bytes_per_second=65.1682G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):25/manual_time 479585 ns 524673 ns 1460 bytes=33.5544M bytes_per_second=65.1605G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):25/manual_time 479482 ns 524578 ns 1460 bytes=33.5544M bytes_per_second=65.1744G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):25/manual_time_mean 479537 ns 524696 ns 5 bytes=33.5544M bytes_per_second=65.167G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):25/manual_time_median 479528 ns 524673 ns 5 bytes=33.5544M bytes_per_second=65.1682G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):25/manual_time_stddev 52.0 ns 89.4 ns 5 bytes=0 bytes_per_second=7.2395M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):25/manual_time_cv 0.01 % 0.02 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):26/manual_time 949067 ns 1018092 ns 738 bytes=67.1089M bytes_per_second=65.8541G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):26/manual_time 949057 ns 1018166 ns 738 bytes=67.1089M bytes_per_second=65.8549G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):26/manual_time 949182 ns 1018151 ns 738 bytes=67.1089M bytes_per_second=65.8462G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):26/manual_time 949189 ns 1018170 ns 738 bytes=67.1089M bytes_per_second=65.8457G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):26/manual_time 949215 ns 1018191 ns 738 bytes=67.1089M bytes_per_second=65.8439G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):26/manual_time_mean 949142 ns 1018154 ns 5 bytes=67.1089M bytes_per_second=65.8489G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):26/manual_time_median 949182 ns 1018166 ns 5 bytes=67.1089M bytes_per_second=65.8462G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):26/manual_time_stddev 74.1 ns 37.6 ns 5 bytes=0 bytes_per_second=5.26573M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):26/manual_time_cv 0.01 % 0.00 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):27/manual_time 1886525 ns 2002989 ns 371 bytes=134.218M bytes_per_second=66.2594G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):27/manual_time 1886478 ns 2003047 ns 371 bytes=134.218M bytes_per_second=66.261G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):27/manual_time 1886604 ns 2003170 ns 371 bytes=134.218M bytes_per_second=66.2566G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):27/manual_time 1886495 ns 2003172 ns 371 bytes=134.218M bytes_per_second=66.2605G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):27/manual_time 1886408 ns 2003002 ns 371 bytes=134.218M bytes_per_second=66.2635G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):27/manual_time_mean 1886502 ns 2003076 ns 5 bytes=134.218M bytes_per_second=66.2602G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):27/manual_time_median 1886495 ns 2003047 ns 5 bytes=134.218M bytes_per_second=66.2605G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):27/manual_time_stddev 71.6 ns 89.3 ns 5 bytes=0 bytes_per_second=2.57597M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):27/manual_time_cv 0.00 % 0.00 % 5 bytes=0.00% bytes_per_second=0.00% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):28/manual_time 3761619 ns 3997042 ns 186 bytes=268.435M bytes_per_second=66.4608G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):28/manual_time 3761253 ns 3999055 ns 186 bytes=268.435M bytes_per_second=66.4672G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):28/manual_time 3761349 ns 4000187 ns 186 bytes=268.435M bytes_per_second=66.4655G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):28/manual_time 3762089 ns 4000238 ns 186 bytes=268.435M bytes_per_second=66.4524G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):28/manual_time 3762284 ns 3997711 ns 186 bytes=268.435M bytes_per_second=66.449G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):28/manual_time_mean 3761719 ns 3998846 ns 5 bytes=268.435M bytes_per_second=66.459G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):28/manual_time_median 3761619 ns 3999055 ns 5 bytes=268.435M bytes_per_second=66.4608G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):28/manual_time_stddev 453 ns 1443 ns 5 bytes=0 bytes_per_second=8.19349M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):28/manual_time_cv 0.01 % 0.04 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):29/manual_time 7512133 ns 7935656 ns 93 bytes=536.871M bytes_per_second=66.559G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):29/manual_time 7512028 ns 7935793 ns 93 bytes=536.871M bytes_per_second=66.5599G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):29/manual_time 7512701 ns 7936192 ns 93 bytes=536.871M bytes_per_second=66.554G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):29/manual_time 7512453 ns 7936301 ns 93 bytes=536.871M bytes_per_second=66.5562G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):29/manual_time 7511651 ns 7935065 ns 93 bytes=536.871M bytes_per_second=66.5633G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):29/manual_time_mean 7512193 ns 7935801 ns 5 bytes=536.871M bytes_per_second=66.5585G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):29/manual_time_median 7512133 ns 7935793 ns 5 bytes=536.871M bytes_per_second=66.559G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):29/manual_time_stddev 403 ns 491 ns 5 bytes=0 bytes_per_second=3.65633M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):29/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):30/manual_time 15014225 ns 15817491 ns 47 bytes=1073.74M bytes_per_second=66.6035G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):30/manual_time 15012615 ns 15816774 ns 47 bytes=1073.74M bytes_per_second=66.6106G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):30/manual_time 15012999 ns 15816390 ns 47 bytes=1073.74M bytes_per_second=66.6089G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):30/manual_time 15013214 ns 15816718 ns 47 bytes=1073.74M bytes_per_second=66.608G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):30/manual_time 15011161 ns 15814757 ns 47 bytes=1073.74M bytes_per_second=66.6171G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):30/manual_time_mean 15012843 ns 15816426 ns 5 bytes=1073.74M bytes_per_second=66.6096G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):30/manual_time_median 15012999 ns 15816718 ns 5 bytes=1073.74M bytes_per_second=66.6089G/s own_gpu=7 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):30/manual_time_stddev 1113 ns 1016 ns 5 bytes=0 bytes_per_second=5.05624M/s own_gpu=0 wr_gpu=0 +Comm_implicit_mapped_GPUWrGPU/0/7/log2(N):30/manual_time_cv 0.01 % 0.01 % 5 bytes=0.00% bytes_per_second=0.01% own_gpu=0.00% wr_gpu=-nan% +[2023-10-09 18:02:56.806] [scope] [warning] unable to restore turbo state: no permission. (use enable-turbo tool if needed) +[2023-10-09 18:02:56.806] [scope] [warning] unable to restore CPU governor: no permission. (use set-minimum tool if needed) +Mon 09 Oct 2023 06:02:56 PM EDT