Files
frontier-gpu-bandwidth/results/implicit_managed_GPURdHost_coarse.json
2023-10-09 17:04:07 -04:00

25273 lines
898 KiB
JSON

{
"context": {
"date": "2023-10-09T14:45:25-04:00",
"host_name": "frontier10485",
"executable": "/lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope",
"num_cpus": 128,
"mhz_per_cpu": 1797,
"cpu_scaling_enabled": false,
"caches": [
{
"type": "Data",
"level": 1,
"size": 32768,
"num_sharing": 2
},
{
"type": "Instruction",
"level": 1,
"size": 32768,
"num_sharing": 2
},
{
"type": "Unified",
"level": 2,
"size": 524288,
"num_sharing": 2
},
{
"type": "Unified",
"level": 3,
"size": 33554432,
"num_sharing": 16
}
],
"load_avg": [2.47,2.62,2.57],
"library_build_type": "release"
},
"benchmarks": [
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 378,
"real_time": 1.8751100435986668e+06,
"cpu_time": 2.0745011851851849e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1844051307725143e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 378,
"real_time": 1.8677153235311231e+06,
"cpu_time": 2.0668210343915343e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1930536995627671e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 378,
"real_time": 1.8622939680724849e+06,
"cpu_time": 2.0667339391534391e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1994379352683239e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 378,
"real_time": 1.8681128048031561e+06,
"cpu_time": 2.0670184417989426e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1925870801102924e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 378,
"real_time": 1.8641001199535034e+06,
"cpu_time": 2.0669938703703708e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1973068700312981e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8674664519917867e+06,
"cpu_time": 2.0684136941798944e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1933581431490392e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time_median",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8677153235311233e+06,
"cpu_time": 2.0669938703703706e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1930536995627671e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9242000096242473e+03,
"cpu_time": 3.4050814141484502e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.7749452578109249e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.6368345221796275e-03,
"cpu_time": 1.6462284231291227e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6329239827289417e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 378,
"real_time": 1.8670017068668837e+06,
"cpu_time": 2.0676265396825387e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3877838835763233e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 378,
"real_time": 1.8626884780205151e+06,
"cpu_time": 2.0678958280423309e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3979442062720358e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 378,
"real_time": 1.8630216313193727e+06,
"cpu_time": 2.0677932301587311e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3971577475450514e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 378,
"real_time": 1.8677094592247775e+06,
"cpu_time": 2.0675929312169293e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3861211707950663e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 378,
"real_time": 1.8616802594493572e+06,
"cpu_time": 2.0676909179894219e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4003259734961195e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8644203069761812e+06,
"cpu_time": 2.0677198894179899e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3938665963369198e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time_median",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8630216313193727e+06,
"cpu_time": 2.0676909179894216e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3971577475450514e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7361256131991186e+03,
"cpu_time": 1.2450418470591167e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.4454081269421231e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4675476355633119e-03,
"cpu_time": 6.0213274217213431e-05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4669102908849198e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 377,
"real_time": 1.8677965247321476e+06,
"cpu_time": 2.0699868779840847e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7718334320969768e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 377,
"real_time": 1.8637731846149294e+06,
"cpu_time": 2.0700418063660499e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7907692498457469e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 377,
"real_time": 1.8630563602236221e+06,
"cpu_time": 2.0697690954907143e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7941515618096665e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 377,
"real_time": 1.8656884978158802e+06,
"cpu_time": 2.0681071405835564e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7817446584359519e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 377,
"real_time": 1.8613719109769117e+06,
"cpu_time": 2.0683259602122013e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8021098327421919e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8643372956726984e+06,
"cpu_time": 2.0692461761273213e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7881217469861079e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time_median",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8637731846149296e+06,
"cpu_time": 2.0697690954907145e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7907692498457469e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4771221315615626e+03,
"cpu_time": 9.4859246722362695e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1672734701438059e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3286877526460447e-03,
"cpu_time": 4.5842417309619311e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3282399854600594e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 377,
"real_time": 1.8690201203625670e+06,
"cpu_time": 2.0724493740053037e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7532181512119520e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 377,
"real_time": 1.8658787134073833e+06,
"cpu_time": 2.0744431671087488e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7561698820262846e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 377,
"real_time": 1.8698409099665419e+06,
"cpu_time": 2.0736714535809003e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7524485545984946e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 377,
"real_time": 1.8740250987909546e+06,
"cpu_time": 2.0773150583554374e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7485358131617658e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 377,
"real_time": 1.8636378169095884e+06,
"cpu_time": 2.0717073474801136e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7582815557122648e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8684805318874072e+06,
"cpu_time": 2.0739172801061007e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7537307913421523e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time_median",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8690201203625672e+06,
"cpu_time": 2.0736714535809003e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7532181512119520e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9719439241561035e+03,
"cpu_time": 2.1748813405113347e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7267059511173873e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1257614710836329e-03,
"cpu_time": 1.0486827808291700e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1250159770903562e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 377,
"real_time": 1.8697246206519490e+06,
"cpu_time": 2.0776388700265258e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5051150996315405e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 377,
"real_time": 1.8651058856615259e+06,
"cpu_time": 2.0778952466843508e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5137951418106936e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 377,
"real_time": 1.8692548281260871e+06,
"cpu_time": 2.0774052811671009e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5059960265395872e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 377,
"real_time": 1.8754388123953873e+06,
"cpu_time": 2.0834742015915096e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.4944355191356383e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 377,
"real_time": 1.8711968954091778e+06,
"cpu_time": 2.0790209363395199e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5023572431520700e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8701442084488254e+06,
"cpu_time": 2.0790869071618016e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5043398060539059e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time_median",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8697246206519487e+06,
"cpu_time": 2.0778952466843512e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5051150996315405e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7246720854352302e+03,
"cpu_time": 2.5296954750703999e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.9780544517257818e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9916496645596255e-03,
"cpu_time": 1.2167338779136136e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9912607903123081e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 371,
"real_time": 1.8738107309416889e+06,
"cpu_time": 2.0901815498652300e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 6.9949433971983597e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 371,
"real_time": 1.8778901036189885e+06,
"cpu_time": 2.0945401051212894e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 6.9797481624405876e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 371,
"real_time": 1.8702027491623953e+06,
"cpu_time": 2.0904080970350360e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0084379920146629e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 371,
"real_time": 1.8784433911661832e+06,
"cpu_time": 2.0955046684636089e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 6.9776923071728736e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 371,
"real_time": 1.8744248239216181e+06,
"cpu_time": 2.0909626118598357e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 6.9926517365350991e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8749543597621745e+06,
"cpu_time": 2.0923194064690000e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 6.9906947190723166e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time_median",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8744248239216183e+06,
"cpu_time": 2.0909626118598361e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 6.9926517365350991e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3525374907899154e+03,
"cpu_time": 2.5070811064369054e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2505945937333169e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7880635191648941e-03,
"cpu_time": 1.1982305850079828e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7889417918957188e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 378,
"real_time": 1.8769197323265309e+06,
"cpu_time": 2.1097606058201012e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3966713412675357e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 378,
"real_time": 1.8803698822493153e+06,
"cpu_time": 2.1136976481481460e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3941086935854396e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 378,
"real_time": 1.8730606651549579e+06,
"cpu_time": 2.1091816322751283e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3995489034430867e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 378,
"real_time": 1.8724376018831714e+06,
"cpu_time": 2.1080763333333354e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4000146105608714e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 378,
"real_time": 1.8720892366165388e+06,
"cpu_time": 2.1082727089947090e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4002751304407778e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8749754236461029e+06,
"cpu_time": 2.1097977857142841e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3981237358595422e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time_median",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8730606651549574e+06,
"cpu_time": 2.1091816322751283e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3995489034430867e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5818094174025018e+03,
"cpu_time": 2.2846888032722254e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6676311090553732e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9103233952993720e-03,
"cpu_time": 1.0828946824867063e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9080078827324678e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 375,
"real_time": 1.8904089203570038e+06,
"cpu_time": 2.1565853653333322e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7734105269720596e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 375,
"real_time": 1.8960174412156143e+06,
"cpu_time": 2.1599097360000126e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7652066305036598e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 375,
"real_time": 1.8959440943629793e+06,
"cpu_time": 2.1591997360000052e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7653136058115482e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 375,
"real_time": 1.8935455000028012e+06,
"cpu_time": 2.1590812213333379e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7688164873736823e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 375,
"real_time": 1.8908149468867728e+06,
"cpu_time": 2.1567121093333415e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7728149751684600e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8933461805650345e+06,
"cpu_time": 2.1582976336000063e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7691124451658815e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time_median",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8935455000028019e+06,
"cpu_time": 2.1590812213333379e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7688164873736823e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6906857520969861e+03,
"cpu_time": 1.5388650392063330e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9356192422540067e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4211271978239078e-03,
"cpu_time": 7.1299945626105809e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4212565651223479e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 368,
"real_time": 1.9123107617222401e+06,
"cpu_time": 2.2356552608695612e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4832928883151054e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 368,
"real_time": 1.9077574329655718e+06,
"cpu_time": 2.2330040597826228e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4963801051479018e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 368,
"real_time": 1.9116922988399416e+06,
"cpu_time": 2.2362545353260930e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4850668208283293e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 368,
"real_time": 1.9055854068226283e+06,
"cpu_time": 2.2323042173913191e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5026449942665911e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 368,
"real_time": 1.9121385684348238e+06,
"cpu_time": 2.2358612445652266e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4837866737780893e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9098968937570411e+06,
"cpu_time": 2.2346158635869646e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4902342964672029e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time_median",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9116922988399416e+06,
"cpu_time": 2.2356552608695612e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4850668208283293e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0512929795080904e+03,
"cpu_time": 1.8205895470775454e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7785843706146604e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5976218347084484e-03,
"cpu_time": 8.1472148155037620e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5989453084476577e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 360,
"real_time": 1.9559310999789482e+06,
"cpu_time": 2.4151188305555452e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0722013674318956e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 360,
"real_time": 1.9592205077060498e+06,
"cpu_time": 2.4175917472222252e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0704012089254042e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 360,
"real_time": 1.9648862417347524e+06,
"cpu_time": 2.4233646638889024e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0673147154557271e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 360,
"real_time": 1.9555652687106179e+06,
"cpu_time": 2.4142784222222203e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0724019461558223e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 360,
"real_time": 1.9528207561557388e+06,
"cpu_time": 2.4102811694444367e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0739091098808203e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9576847748572216e+06,
"cpu_time": 2.4161269666666659e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0712456695699339e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time_median",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9559310999789480e+06,
"cpu_time": 2.4151188305555452e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0722013674318956e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6218492073225443e+03,
"cpu_time": 4.8253663928453334e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5253594924762691e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3608750840183792e-03,
"cpu_time": 1.9971493466266386e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3574046217522716e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 337,
"real_time": 2.0838907763682504e+06,
"cpu_time": 2.7911161364985155e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0127273691904917e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 337,
"real_time": 2.0852552620467430e+06,
"cpu_time": 2.7922532522255252e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0114103421003528e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 337,
"real_time": 2.0834477708152654e+06,
"cpu_time": 2.7917683946587555e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0131553373947763e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 337,
"real_time": 2.0847837630664872e+06,
"cpu_time": 2.7922711513353228e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0118652467969348e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 337,
"real_time": 2.0853316498428406e+06,
"cpu_time": 2.7919416587537094e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0113366621161196e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0845418444279176e+06,
"cpu_time": 2.7918701186943660e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0120989915197353e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time_median",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0847837630664869e+06,
"cpu_time": 2.7919416587537099e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0118652467969348e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.3847608939130009e+02,
"cpu_time": 4.7211581969369007e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.0943588969108602e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.0223519217548345e-04,
"cpu_time": 1.6910379051389315e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0228432751199798e-04,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 317,
"real_time": 2.2075359525206005e+06,
"cpu_time": 3.4453625078864209e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.7999870355097728e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 317,
"real_time": 2.2235934693096001e+06,
"cpu_time": 3.4594887003154522e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.7725457084583745e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 317,
"real_time": 2.2076444266281715e+06,
"cpu_time": 3.4465603091482515e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.7998003205671463e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 317,
"real_time": 2.2130364831977696e+06,
"cpu_time": 3.4482001955835917e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.7905421187990174e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 317,
"real_time": 2.2065133214061526e+06,
"cpu_time": 3.4455348801261755e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.8017481782771034e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2116647306124587e+06,
"cpu_time": 3.4490293186119786e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.7929246723222828e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time_median",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2076444266281715e+06,
"cpu_time": 3.4465603091482511e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.7998003205671463e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.1400837098075062e+03,
"cpu_time": 5.9548030943671201e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2206396882212212e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.2283752645593166e-03,
"cpu_time": 1.7265156495577605e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2182017669068648e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 211,
"real_time": 3.3299287127869390e+06,
"cpu_time": 5.6254639052132666e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 5.0383108610029478e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 211,
"real_time": 3.3311412749167583e+06,
"cpu_time": 5.6207172180094672e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 5.0364768754574194e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 211,
"real_time": 3.3304075107984776e+06,
"cpu_time": 5.6213563838862600e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 5.0375865252530613e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 211,
"real_time": 3.3343183924995749e+06,
"cpu_time": 5.6216727156398231e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 5.0316778498837185e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 211,
"real_time": 3.3298019591224561e+06,
"cpu_time": 5.6225503838862833e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 5.0385026514974804e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3311195700248410e+06,
"cpu_time": 5.6223521213270202e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 5.0365109526189260e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time_median",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3304075107984771e+06,
"cpu_time": 5.6216727156398222e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 5.0375865252530613e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8637465028597694e+03,
"cpu_time": 1.8606787082715546e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8161780116462810e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.5949552805931570e-04,
"cpu_time": 3.3094311208533607e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.5915256377669584e-04,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 105,
"real_time": 6.6690747315684957e+06,
"cpu_time": 1.0998439619047640e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 5.0313474283273411e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 105,
"real_time": 6.6692529645349300e+06,
"cpu_time": 1.1004949257142827e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 5.0312129676940317e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 105,
"real_time": 6.6869946329721380e+06,
"cpu_time": 1.1024764057142852e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 5.0178643533748751e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 105,
"real_time": 6.6845869778522421e+06,
"cpu_time": 1.1025215085714312e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 5.0196716881947193e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 105,
"real_time": 6.6685915170680908e+06,
"cpu_time": 1.0998481695238145e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 5.0317120060687904e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.6757001647991799e+06,
"cpu_time": 1.1010369942857157e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 5.0263616887319517e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time_median",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.6692529645349290e+06,
"cpu_time": 1.1004949257142829e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 5.0312129676940317e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.2538652312413396e+03,
"cpu_time": 1.3607127578699317e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.9638211105340719e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3862014474581661e-03,
"cpu_time": 1.2358465382470440e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3854596111030962e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52,
"real_time": 1.3532606687826606e+07,
"cpu_time": 2.2247601076922927e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.9590493205103245e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52,
"real_time": 1.3166999910026789e+07,
"cpu_time": 2.1324687884615220e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 5.0967467501003017e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52,
"real_time": 1.3541086505238827e+07,
"cpu_time": 2.2288295134615328e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.9559438213496876e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52,
"real_time": 1.3550086358848672e+07,
"cpu_time": 2.2289645923076928e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.9526521250674982e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52,
"real_time": 1.3625597026055822e+07,
"cpu_time": 2.2349463750000078e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.9252053962604151e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3483275297599345e+07,
"cpu_time": 2.2099938753846098e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.9779194826576452e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time_median",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3541086505238827e+07,
"cpu_time": 2.2288295134615328e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.9559438213496876e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8064124312471267e+05,
"cpu_time": 4.3489876173645270e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.7779322919259682e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3397430456446681e-02,
"cpu_time": 1.9678731537695615e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3615994223167548e-02,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 27,
"real_time": 2.6144349878584895e+07,
"cpu_time": 4.2524824851851769e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 5.1337183224410219e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 27,
"real_time": 2.6134234197713710e+07,
"cpu_time": 4.2491634777777396e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 5.1357054117063704e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 27,
"real_time": 2.6145884422240432e+07,
"cpu_time": 4.2541174814815007e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 5.1334170163251610e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 27,
"real_time": 2.6152929912010830e+07,
"cpu_time": 4.2514185592592768e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 5.1320340952835274e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 27,
"real_time": 2.5940217836587518e+07,
"cpu_time": 4.1534037481481634e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 5.1741172277548065e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6103523249427475e+07,
"cpu_time": 4.2321171503703721e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 5.1417984147021780e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time_median",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6144349878584895e+07,
"cpu_time": 4.2514185592592761e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 5.1337183224410219e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1534312043962564e+04,
"cpu_time": 4.4038854389226495e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8114276317450829e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.5065884083662988e-03,
"cpu_time": 1.0405868463582688e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5229456420648184e-03,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 10,
"real_time": 5.0922773778438568e+07,
"cpu_time": 8.0860656999999493e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.2714225106421719e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 10,
"real_time": 5.1001479104161263e+07,
"cpu_time": 8.0962874799999446e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.2632876676335077e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 10,
"real_time": 4.7256883978843689e+07,
"cpu_time": 7.9316505299999565e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.6803460871473284e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 10,
"real_time": 5.0969207659363747e+07,
"cpu_time": 8.0894641700000137e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.2666201482668076e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 10,
"real_time": 5.0901831313967705e+07,
"cpu_time": 8.0809678300001055e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.2735913241365061e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0210435166954994e+07,
"cpu_time": 8.0568871419999942e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.3510535475652647e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time_median",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0922773778438568e+07,
"cpu_time": 8.0860656999999493e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.2714225106421719e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6515451671188357e+06,
"cpu_time": 7.0230203891479503e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8412422662543026e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.2892468699529769e-02,
"cpu_time": 8.7167913182467603e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4408967316203923e-02,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 1.0074732918292284e+08,
"cpu_time": 1.5863111749999881e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.3288848087002411e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.9162756688892841e+07,
"cpu_time": 1.5542222600000066e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 6.0212462236138887e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 1.0075306985527277e+08,
"cpu_time": 1.5874722274999976e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.3285811814090710e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.9142536744475365e+07,
"cpu_time": 1.5601317112500012e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 6.0226120055224113e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 1.0080764908343554e+08,
"cpu_time": 1.5874967499999925e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.3256961835867004e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.6122668310999870e+07,
"cpu_time": 1.5751268247499973e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.6054040805664635e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time_median",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0074732918292284e+08,
"cpu_time": 1.5863111749999881e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.3288848087002411e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.3627776551029887e+06,
"cpu_time": 1.6525495200811592e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8023593774932867e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.6194351102661392e-02,
"cpu_time": 1.0491533088730493e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.7833813991676276e-02,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.8587203696370125e+08,
"cpu_time": 2.8424355800000000e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.7767797756996117e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.8610463663935661e+08,
"cpu_time": 2.8453568625000256e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.7695597669646111e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.8616894632577896e+08,
"cpu_time": 2.8443631699999726e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.7675667461803656e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.8597462773323059e+08,
"cpu_time": 2.8430385625000197e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.7735930814187088e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.8613179028034210e+08,
"cpu_time": 2.8471290374999827e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.7687180807898827e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8605040758848190e+08,
"cpu_time": 2.8444646425000000e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.7712434902106361e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time_median",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8610463663935661e+08,
"cpu_time": 2.8443631699999726e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.7695597669646111e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.2366692259828006e+05,
"cpu_time": 1.8745767993772443e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8373851523765502e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.6469578971207848e-04,
"cpu_time": 6.5902622636563300e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6491478983439934e-04,
"dst_gpu": NaN,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 379,
"real_time": 1.8620295801602665e+06,
"cpu_time": 2.0660710976253294e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1997502314906586e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 379,
"real_time": 1.8663027288535323e+06,
"cpu_time": 2.0705984089709762e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1947136103241770e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 379,
"real_time": 1.8618873145321007e+06,
"cpu_time": 2.0660708627968419e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1999183130099042e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 379,
"real_time": 1.8575317976215489e+06,
"cpu_time": 2.0665331266490684e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2050766534627653e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 379,
"real_time": 1.8622617377106489e+06,
"cpu_time": 2.0660174617414109e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1994760011744499e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8620026317756199e+06,
"cpu_time": 2.0670581915567252e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1997869618923911e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time_median",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8620295801602665e+06,
"cpu_time": 2.0660710976253296e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.1997502314906586e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1048491541061398e+03,
"cpu_time": 1.9900454490588406e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.6686179908306731e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6674783918781751e-03,
"cpu_time": 9.6274282803819578e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6677151262296346e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 375,
"real_time": 1.8620746317125547e+06,
"cpu_time": 2.0672955733333158e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3993940202417113e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 375,
"real_time": 1.8668451953756933e+06,
"cpu_time": 2.0725968266666161e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3881517440718487e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 375,
"real_time": 1.8618399599799886e+06,
"cpu_time": 2.0668693573333409e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3999485326805692e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 375,
"real_time": 1.8572925563591223e+06,
"cpu_time": 2.0673934906666698e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4107213868658887e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 375,
"real_time": 1.8610975729534402e+06,
"cpu_time": 2.0671898826666016e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4017036608133512e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8618299832761600e+06,
"cpu_time": 2.0682690261333089e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3999838689346742e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time_median",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8618399599799886e+06,
"cpu_time": 2.0672955733333162e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3999485326805692e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4035633057236446e+03,
"cpu_time": 2.4273263859334302e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.0405274129936006e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8280741723444482e-03,
"cpu_time": 1.1736028317705792e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8273992933843133e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 375,
"real_time": 1.8625426740618423e+06,
"cpu_time": 2.0695588853332840e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7965769741370231e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 375,
"real_time": 1.8685057928863293e+06,
"cpu_time": 2.0756780746666361e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7685037222663425e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 375,
"real_time": 1.8634114011268441e+06,
"cpu_time": 2.0695991226666593e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7924759879070446e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 375,
"real_time": 1.8583831679037150e+06,
"cpu_time": 2.0699826426666733e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8162658180343956e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 375,
"real_time": 1.8625811110056627e+06,
"cpu_time": 2.0695126400000085e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7963954445741121e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8630848293968788e+06,
"cpu_time": 2.0708662730666525e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7940435893837828e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time_median",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8625811110056627e+06,
"cpu_time": 2.0695991226666593e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.7963954445741121e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6106363588962354e+03,
"cpu_time": 2.6963629492117398e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7033194754792406e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9379881699026428e-03,
"cpu_time": 1.3020459043059391e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9369013334610908e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 378,
"real_time": 1.8613665339390058e+06,
"cpu_time": 2.0760868597883033e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7604270519818939e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 378,
"real_time": 1.8701487881703998e+06,
"cpu_time": 2.0803249179894293e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7521600531077273e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 378,
"real_time": 1.8662884685716890e+06,
"cpu_time": 2.0759683333333293e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7557843040780324e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 378,
"real_time": 1.8608531161917006e+06,
"cpu_time": 2.0758662328042586e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7609127617262360e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 378,
"real_time": 1.8657610421036631e+06,
"cpu_time": 2.0751474497354405e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7562806415474180e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8648835897952914e+06,
"cpu_time": 2.0766787587301522e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7571129624882616e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time_median",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8657610421036626e+06,
"cpu_time": 2.0759683333333291e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7562806415474180e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8431861854685931e+03,
"cpu_time": 2.0709075041223141e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.6197743739035381e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0608182765394275e-03,
"cpu_time": 9.9722092086531114e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0600692449377566e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 377,
"real_time": 1.8623322989564359e+06,
"cpu_time": 2.0826821034483330e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5190282656174362e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 377,
"real_time": 1.8670215152990844e+06,
"cpu_time": 2.0824018169761004e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5101898646037601e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 377,
"real_time": 1.8623738841035413e+06,
"cpu_time": 2.0825956021220873e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5189496888561629e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 377,
"real_time": 1.8624617624248189e+06,
"cpu_time": 2.0824231061008151e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5187836508748434e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 377,
"real_time": 1.8673177443528720e+06,
"cpu_time": 2.0820959389920002e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5096330122815713e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8643014410273507e+06,
"cpu_time": 2.0824397135278676e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5153168964467548e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time_median",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8624617624248192e+06,
"cpu_time": 2.0824231061008151e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5187836508748434e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6207967941801830e+03,
"cpu_time": 2.2524820186832721e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9392009171524900e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4057795249763658e-03,
"cpu_time": 1.0816553315088941e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4050513972566690e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 377,
"real_time": 1.8629849828864308e+06,
"cpu_time": 2.0957552015914645e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0355907967074722e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 377,
"real_time": 1.8728298764037886e+06,
"cpu_time": 2.1005798779840758e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 6.9986068489939243e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 377,
"real_time": 1.8643184604147321e+06,
"cpu_time": 2.0958588196286543e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0305585007639751e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 377,
"real_time": 1.8679076523627513e+06,
"cpu_time": 2.0956313633952315e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0170492547746986e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 377,
"real_time": 1.8636322240141376e+06,
"cpu_time": 2.0954882572944032e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0331473297708809e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8663346392163683e+06,
"cpu_time": 2.0966627039787662e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0229905462021917e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time_median",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8643184604147323e+06,
"cpu_time": 2.0957552015914645e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0305585007639751e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.1003261726623296e+03,
"cpu_time": 2.1941417020004496e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5403442267882850e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1969940901830783e-03,
"cpu_time": 1.0464924557663476e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1932881963243620e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 377,
"real_time": 1.8760205580545983e+06,
"cpu_time": 2.1232041909814361e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3973407640683794e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 377,
"real_time": 1.8748907921313916e+06,
"cpu_time": 2.1224822546418696e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3981827693654224e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 377,
"real_time": 1.8761529725703313e+06,
"cpu_time": 2.1232494774536090e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3972421430053353e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 377,
"real_time": 1.8751114689922873e+06,
"cpu_time": 2.1226993183024111e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3980182209694448e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 377,
"real_time": 1.8761716441829400e+06,
"cpu_time": 2.1226479230769165e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3972282376869732e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8756694871863101e+06,
"cpu_time": 2.1228566328912484e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3976024270191112e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time_median",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8760205580545985e+06,
"cpu_time": 2.1226993183024111e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3973407640683794e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.1784318671492326e+02,
"cpu_time": 3.4770325429989595e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.6042686009832221e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.2939875118496981e-04,
"cpu_time": 1.6379026680965147e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2944051269311812e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 371,
"real_time": 1.8945118584801916e+06,
"cpu_time": 2.1805372506738324e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7674041608828586e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 371,
"real_time": 1.8971240610942356e+06,
"cpu_time": 2.1826350404312219e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7635936455183524e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 371,
"real_time": 1.9014419111858732e+06,
"cpu_time": 2.1834050592992064e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7573179959676868e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 371,
"real_time": 1.9017248193236354e+06,
"cpu_time": 2.1841183611859428e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7569078063905561e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 371,
"real_time": 1.8978045426178572e+06,
"cpu_time": 2.1831391671159235e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7626027244975924e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8985214385403588e+06,
"cpu_time": 2.1827669757412253e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7615652666514099e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time_median",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8978045426178575e+06,
"cpu_time": 2.1831391671159235e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7626027244975924e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0550836595281266e+03,
"cpu_time": 1.3565581876916742e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4445069969570305e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6091910249256751e-03,
"cpu_time": 6.2148557439623768e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6094158811413154e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 371,
"real_time": 1.9005310616262679e+06,
"cpu_time": 2.2635313180593201e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5172789394072974e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 371,
"real_time": 1.8960488803252939e+06,
"cpu_time": 2.2624096684636381e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5303215591156173e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 371,
"real_time": 1.9005677159787770e+06,
"cpu_time": 2.2640181886792635e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5171725331553984e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 371,
"real_time": 1.8948171788423681e+06,
"cpu_time": 2.2605709919137750e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5339164733593130e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 371,
"real_time": 1.9005797695145111e+06,
"cpu_time": 2.2644697331536235e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5171375430763996e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8985089212574437e+06,
"cpu_time": 2.2629999800539245e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5231654096228063e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time_median",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9005310616262681e+06,
"cpu_time": 2.2635313180593201e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5172789394072974e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8415164667824547e+03,
"cpu_time": 1.5594625852383419e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.2718819208206784e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4967095676855847e-03,
"cpu_time": 6.8911294696572738e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4976705036588050e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 362,
"real_time": 1.9423320459508086e+06,
"cpu_time": 2.4542321602210086e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0797082838497906e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 362,
"real_time": 1.9412248801229040e+06,
"cpu_time": 2.4544938674033331e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0803240889160786e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 362,
"real_time": 1.9442891997596486e+06,
"cpu_time": 2.4570440662983614e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0786214315541372e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 362,
"real_time": 1.9409769301197249e+06,
"cpu_time": 2.4538311878452739e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0804620948640754e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 362,
"real_time": 1.9426281759785539e+06,
"cpu_time": 2.4544928425414581e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0795436954596875e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9422902463863280e+06,
"cpu_time": 2.4548188248618869e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0797319189287539e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time_median",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9423320459508083e+06,
"cpu_time": 2.4544928425414581e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0797082838497906e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3201858853342153e+03,
"cpu_time": 1.2731028586945602e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.3365371450024028e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.7970576889342317e-04,
"cpu_time": 5.1861377540405142e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.7947765703557986e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 355,
"real_time": 1.9792456597968622e+06,
"cpu_time": 2.8004079492958020e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.1191427043121459e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 355,
"real_time": 1.9787115520391033e+06,
"cpu_time": 2.8011053154928912e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.1197147182355518e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 355,
"real_time": 1.9802218432616915e+06,
"cpu_time": 2.8021416253520655e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.1180980374862535e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 355,
"real_time": 1.9839905858249732e+06,
"cpu_time": 2.8015465633802866e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.1140745475140171e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 355,
"real_time": 1.9838702881341458e+06,
"cpu_time": 2.8022253887323928e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.1142027405152550e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9812079858113553e+06,
"cpu_time": 2.8014853684506877e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.1170465496126451e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time_median",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9802218432616915e+06,
"cpu_time": 2.8015465633802870e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.1180980374862535e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5439191510190753e+03,
"cpu_time": 7.5619445940504795e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7174740901064724e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2840242767229084e-03,
"cpu_time": 2.6992625694962952e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2836156534223053e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 346,
"real_time": 2.0404579037143660e+06,
"cpu_time": 3.5445938554912875e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1111399479154758e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 346,
"real_time": 2.0422382684656002e+06,
"cpu_time": 3.5487322861272171e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1075559740160155e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 346,
"real_time": 2.0406886429197527e+06,
"cpu_time": 3.5443135895954324e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1106751042617874e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 346,
"real_time": 2.0444116678298856e+06,
"cpu_time": 3.5505559393063178e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1031892607541175e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 346,
"real_time": 2.0422724538585010e+06,
"cpu_time": 3.5454258236993910e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1074872180502934e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0420137873576214e+06,
"cpu_time": 3.5467242988439291e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1080095009995384e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time_median",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0422382684656004e+06,
"cpu_time": 3.5454258236993914e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1075559740160155e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5846066213547249e+03,
"cpu_time": 2.7726263371002556e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1866252076075720e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.7600192083189415e-04,
"cpu_time": 7.8174284310850021e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.7571028178786343e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 191,
"real_time": 3.6291871305204029e+06,
"cpu_time": 6.5832194293194013e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6228577906354065e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 191,
"real_time": 3.6453806395345023e+06,
"cpu_time": 6.6126901780105513e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6023221328520498e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 191,
"real_time": 3.6544721434624251e+06,
"cpu_time": 6.6320722565445388e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5908725915487337e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 191,
"real_time": 3.6376444817915638e+06,
"cpu_time": 6.5958894345549764e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6121098650457211e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 191,
"real_time": 3.6369575558142513e+06,
"cpu_time": 6.5918416806283779e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6129809717407808e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6407283902246295e+06,
"cpu_time": 6.6031425958115701e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6082286703645382e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time_median",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6376444817915643e+06,
"cpu_time": 6.5958894345549773e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6121098650457211e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.5846822538967863e+03,
"cpu_time": 1.9399311786960308e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2122085811384112e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.6326276575950286e-03,
"cpu_time": 2.9378907854065517e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6305304442336155e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 98,
"real_time": 7.2721128865164155e+06,
"cpu_time": 1.3348374142857287e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6141241924633675e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 98,
"real_time": 7.2923300607243972e+06,
"cpu_time": 1.3401546673469337e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6013320462166252e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 98,
"real_time": 7.2725259185749656e+06,
"cpu_time": 1.3344556663265238e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6138621402912664e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 98,
"real_time": 7.2736377846829742e+06,
"cpu_time": 1.3375013418367393e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6131568540104980e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 98,
"real_time": 7.2791936275150096e+06,
"cpu_time": 1.3358945295918515e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6096358631216822e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.2779600556027535e+06,
"cpu_time": 1.3365687238775555e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6104222192206879e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time_median",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.2736377846829761e+06,
"cpu_time": 1.3358945295918517e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6131568540104980e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.5208568270402502e+03,
"cpu_time": 2.3262496573827611e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.3913238507809937e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1707754318438012e-03,
"cpu_time": 1.7404639326244410e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1693774657567705e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 49,
"real_time": 1.4378109699761381e+07,
"cpu_time": 2.5923098142857041e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6674330215406370e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 49,
"real_time": 1.4371004392754059e+07,
"cpu_time": 2.5948479244897734e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6697406921562605e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 49,
"real_time": 1.4378805150639039e+07,
"cpu_time": 2.5937488020408452e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6672072746613083e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 49,
"real_time": 1.4390393768494226e+07,
"cpu_time": 2.6003897142857112e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6634487616958447e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 49,
"real_time": 1.4401979079203947e+07,
"cpu_time": 2.5988555061224602e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6596973673502493e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4384058418170532e+07,
"cpu_time": 2.5960303522448990e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6655054234808607e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time_median",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4378805150639037e+07,
"cpu_time": 2.5948479244897738e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6672072746613083e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.2193014451121184e+04,
"cpu_time": 3.4435280335482137e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9532520206230213e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.4767553750466349e-04,
"cpu_time": 1.3264590803302612e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4733628230862967e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 25,
"real_time": 2.3682550415396690e+07,
"cpu_time": 4.8034341600000516e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 5.6673679838443956e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 25,
"real_time": 2.7867418080568314e+07,
"cpu_time": 4.9467176279999875e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8162957763779612e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 25,
"real_time": 2.7814221158623695e+07,
"cpu_time": 4.9436798119999141e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8255073271532640e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 25,
"real_time": 2.7814285308122635e+07,
"cpu_time": 4.9405407199999444e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8254961978406200e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 25,
"real_time": 2.7785082012414932e+07,
"cpu_time": 4.9410874279999465e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8305679983247423e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6992711395025253e+07,
"cpu_time": 4.9150919495999686e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.9930470567081966e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time_median",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7814221158623695e+07,
"cpu_time": 4.9410874279999457e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8255073271532640e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8506749227282566e+06,
"cpu_time": 6.2466623490715411e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7699205017214501e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.8562023860609084e-02,
"cpu_time": 1.2709146467910831e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5503404211993821e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 5.4358589897553124e+07,
"cpu_time": 9.4568923266666621e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9382343527657118e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 5.4310600956281029e+07,
"cpu_time": 9.4676272666667193e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9425977852111282e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 5.4265800118446350e+07,
"cpu_time": 9.4654718266665831e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9466783022471609e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.6106208612521492e+07,
"cpu_time": 9.2189426066666633e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.8221108193029451e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 5.4321917643149696e+07,
"cpu_time": 9.4597465399999693e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9415681118512802e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.2672623445590340e+07,
"cpu_time": 9.4137361133333191e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.1182378742756453e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time_median",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4310600956281021e+07,
"cpu_time": 9.4597465399999693e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9425977852111282e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6708868214525143e+06,
"cpu_time": 1.0897794363138289e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9348847603635335e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.9692500227266252e-02,
"cpu_time": 1.1576481677346996e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.6879677283862372e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 9.8979412578046322e+07,
"cpu_time": 1.7097006399999869e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.4240664600496750e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 1.0547426249831915e+08,
"cpu_time": 1.7943084687500033e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0900655693947668e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 9.9149235524237156e+07,
"cpu_time": 1.7134094625000173e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.4147761115995817e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 1.0562058165669441e+08,
"cpu_time": 1.7982337724999908e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0830141585948391e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 9.8844932392239571e+07,
"cpu_time": 1.7151549749999973e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.4314459933016291e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0161368492990732e+08,
"cpu_time": 1.7461614637499991e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.2886736585880985e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time_median",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.9149235524237156e+07,
"cpu_time": 1.7151549749999970e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.4147761115995817e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5929852787266038e+06,
"cpu_time": 4.5807060121874809e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8463340836179870e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.5359265646207290e-02,
"cpu_time": 2.6233003689991572e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4911098751948658e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.8292541056871414e+08,
"cpu_time": 3.1230585424999899e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8698341617041740e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.8355449289083481e+08,
"cpu_time": 3.1407167049999887e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8497169265074072e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.8357677012681961e+08,
"cpu_time": 3.1400849925000787e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8490070571468887e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.8293696641921997e+08,
"cpu_time": 3.1246936350000000e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8694633731894503e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.8394868820905685e+08,
"cpu_time": 3.1365027200000381e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8371811968547297e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8338846564292911e+08,
"cpu_time": 3.1330113190000188e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8550405430805302e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time_median",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8355449289083481e+08,
"cpu_time": 3.1365027200000381e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8497169265074072e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.4585437646018929e+05,
"cpu_time": 8.5123636306110187e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4235249153742269e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4312018473849968e-03,
"cpu_time": 2.7169910236162051e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4312810558699623e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 379,
"real_time": 1.8614930960069911e+06,
"cpu_time": 2.0739697730871171e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2003842016852782e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 379,
"real_time": 1.8582981641390200e+06,
"cpu_time": 2.0699264564643695e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2041672746836855e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 379,
"real_time": 1.8537218814087899e+06,
"cpu_time": 2.0705608680738846e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2096087018658514e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 379,
"real_time": 1.8579207630012501e+06,
"cpu_time": 2.0697414432718228e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2046150091909189e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 379,
"real_time": 1.8541964087288182e+06,
"cpu_time": 2.0712860580475368e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2090432171681831e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8571260626569740e+06,
"cpu_time": 2.0710969197889466e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2055636809187839e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time_median",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8579207630012501e+06,
"cpu_time": 2.0705608680738849e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2046150091909189e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2112175616108557e+03,
"cpu_time": 1.7163705729655067e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8126860780025586e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7291327854268518e-03,
"cpu_time": 8.2872537570111008e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7286674200285557e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 380,
"real_time": 1.8623628774596576e+06,
"cpu_time": 2.0757418394735719e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.3987131074982760e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 380,
"real_time": 1.8585401155992018e+06,
"cpu_time": 2.0711783552630586e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4077606564649595e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 380,
"real_time": 1.8532361039864267e+06,
"cpu_time": 2.0715131921051759e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4203757861065278e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 380,
"real_time": 1.8581375895193655e+06,
"cpu_time": 2.0709094026314965e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4087155042802729e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 380,
"real_time": 1.8538765233020775e+06,
"cpu_time": 2.0720048289474023e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4188487728452478e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8572306419733458e+06,
"cpu_time": 2.0722695236841410e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4108827654390577e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time_median",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8581375895193655e+06,
"cpu_time": 2.0715131921051755e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4087155042802729e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7444479534340185e+03,
"cpu_time": 1.9836617343068106e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.8898801332852454e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0161459049886587e-03,
"cpu_time": 9.5724118491121715e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0154423969144758e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 379,
"real_time": 1.8599496800040873e+06,
"cpu_time": 2.0743481846965980e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8088404628043473e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 379,
"real_time": 1.8539313016876169e+06,
"cpu_time": 2.0740189155673166e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8374364169188980e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 379,
"real_time": 1.8548030863297333e+06,
"cpu_time": 2.0744920976254449e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8332826922455169e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 379,
"real_time": 1.8589977068987205e+06,
"cpu_time": 2.0738731002638203e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8133513770345990e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 379,
"real_time": 1.8547414450311547e+06,
"cpu_time": 2.0747163693931666e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8335762614744361e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8564846439902626e+06,
"cpu_time": 2.0742897335092698e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8252974420955610e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time_median",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8548030863297333e+06,
"cpu_time": 2.0743481846965980e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8332826922455169e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7707352566440818e+03,
"cpu_time": 3.4398821412745860e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3164330762103424e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4924633314977287e-03,
"cpu_time": 1.6583421716382003e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4916585926397470e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 379,
"real_time": 1.8616551092752416e+06,
"cpu_time": 2.0792250422163433e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7601541680164840e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 379,
"real_time": 1.8574482774992269e+06,
"cpu_time": 2.0796813350922444e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7641406437500998e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 379,
"real_time": 1.8620903701526064e+06,
"cpu_time": 2.0795567968338637e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7597427345760088e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 379,
"real_time": 1.8658995648552994e+06,
"cpu_time": 2.0837219762533479e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7561502568087664e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 379,
"real_time": 1.8570007548286915e+06,
"cpu_time": 2.0796031398416767e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7645657878595129e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8608188153222133e+06,
"cpu_time": 2.0803576580474954e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7609507182021748e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time_median",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8616551092752418e+06,
"cpu_time": 2.0796031398416769e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7601541680164840e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6765597446994498e+03,
"cpu_time": 1.8887525480084423e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4778765019045743e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9757752417517488e-03,
"cpu_time": 9.0789799566537866e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9749993375483429e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 378,
"real_time": 1.8630398779774266e+06,
"cpu_time": 2.0856138915343350e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5176917453397669e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 378,
"real_time": 1.8582286098708643e+06,
"cpu_time": 2.0867081693121349e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5267996441274442e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 378,
"real_time": 1.8634133773274403e+06,
"cpu_time": 2.0864037857143586e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5169866652987950e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 378,
"real_time": 1.8697021441959478e+06,
"cpu_time": 2.0924977883597931e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5051572360571526e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 378,
"real_time": 1.8586250096237687e+06,
"cpu_time": 2.0870497037036191e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5260474630794995e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8626018037990897e+06,
"cpu_time": 2.0876546677248483e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5185365507805318e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time_median",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8630398779774266e+06,
"cpu_time": 2.0867081693121349e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5176917453397669e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6423353868145196e+03,
"cpu_time": 2.7589459699769623e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7580594158323685e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4923928331571977e-03,
"cpu_time": 1.3215528471400377e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4891199194419429e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 379,
"real_time": 1.8612166646576799e+06,
"cpu_time": 2.0994626200526822e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0422752218429729e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 379,
"real_time": 1.8586291872286841e+06,
"cpu_time": 2.1000012031662972e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0520790753014803e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 379,
"real_time": 1.8663992168440786e+06,
"cpu_time": 2.1038825778364874e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0227204778638706e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 379,
"real_time": 1.8573637392035855e+06,
"cpu_time": 2.0992380316623184e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0568837559089020e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 379,
"real_time": 1.8616440052232314e+06,
"cpu_time": 2.0994431688654255e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0406586668691814e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8610505626314520e+06,
"cpu_time": 2.1004055203166427e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0429234395572826e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time_median",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8612166646576799e+06,
"cpu_time": 2.0994626200526827e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0422752218429729e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4800715403122726e+03,
"cpu_time": 1.9641545466715093e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3156986178452877e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8699500218798939e-03,
"cpu_time": 9.3513111047975475e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8681143265813951e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 380,
"real_time": 1.8639245628468127e+06,
"cpu_time": 2.1245473421052005e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4064088495063433e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 380,
"real_time": 1.8697506900934968e+06,
"cpu_time": 2.1283672473683017e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4020264914938551e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 380,
"real_time": 1.8650634839631445e+06,
"cpu_time": 2.1230272578947050e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4055500107854787e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 380,
"real_time": 1.8616714687883167e+06,
"cpu_time": 2.1233943105262127e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4081109604726255e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 380,
"real_time": 1.8617283248443673e+06,
"cpu_time": 2.1233773842105186e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4080679576162875e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8644277061072276e+06,
"cpu_time": 2.1245427084209877e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4060328539749178e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time_median",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8639245628468127e+06,
"cpu_time": 2.1233943105262131e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4064088495063433e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3119114004894595e+03,
"cpu_time": 2.2136230577013457e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4942746422557402e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7763689037878863e-03,
"cpu_time": 1.0419291873621898e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7739803413585353e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 369,
"real_time": 1.8965110043079534e+06,
"cpu_time": 2.1911352439024467e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7644869911594075e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 369,
"real_time": 1.8947917559792395e+06,
"cpu_time": 2.1898564715446029e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7669953616039711e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 369,
"real_time": 1.8935481432306664e+06,
"cpu_time": 2.1877738915987918e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7688126223476368e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 369,
"real_time": 1.8920101629043892e+06,
"cpu_time": 2.1880566747967508e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7710633392961025e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 369,
"real_time": 1.8893850678300390e+06,
"cpu_time": 2.1855891978320205e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7749134304429823e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8932492268504580e+06,
"cpu_time": 2.1884822959349230e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7692543489700198e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time_median",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8935481432306662e+06,
"cpu_time": 2.1880566747967508e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7688126223476368e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7191424979458152e+03,
"cpu_time": 2.1201119198554420e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9788030845971755e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4362306131608909e-03,
"cpu_time": 9.6875899969285661e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4367777687437878e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 372,
"real_time": 1.8860565413037436e+06,
"cpu_time": 2.2678474704300682e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5596212363557673e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 372,
"real_time": 1.8875528913540815e+06,
"cpu_time": 2.2664451854838426e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5552138687238514e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 372,
"real_time": 1.8865735257878117e+06,
"cpu_time": 2.2677685026881699e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5580977134836364e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 372,
"real_time": 1.8874002232996156e+06,
"cpu_time": 2.2671739193548723e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5556632189374483e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 372,
"real_time": 1.8850802139583125e+06,
"cpu_time": 2.2654003252688241e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5625006948547220e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8865326791407131e+06,
"cpu_time": 2.2669270806451556e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5582193464710844e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time_median",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8865735257878122e+06,
"cpu_time": 2.2671739193548718e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5580977134836364e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0163041645023334e+03,
"cpu_time": 1.0221598064346583e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9948588574422000e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.3871537754927434e-04,
"cpu_time": 4.5090105242545203e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.3881624145395363e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 365,
"real_time": 1.9295984689363162e+06,
"cpu_time": 2.4687249452054631e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0868333665065804e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 365,
"real_time": 1.9302401965968821e+06,
"cpu_time": 2.4685210849315496e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0864720378828461e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 365,
"real_time": 1.9319883860290458e+06,
"cpu_time": 2.4706322219178020e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0854889269341969e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 365,
"real_time": 1.9322855874883293e+06,
"cpu_time": 2.4700561260274672e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0853219697850003e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 365,
"real_time": 1.9301783799015188e+06,
"cpu_time": 2.4701498383561336e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0865068336880865e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9308582037904183e+06,
"cpu_time": 2.4696168432876831e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0861246269593420e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time_median",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9302401965968818e+06,
"cpu_time": 2.4700561260274672e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0864720378828461e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1985158974657877e+03,
"cpu_time": 9.3597748308502253e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.7406623199801368e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.2071668189461651e-04,
"cpu_time": 3.7899704386490997e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2061591760891608e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 347,
"real_time": 2.0247974472592778e+06,
"cpu_time": 2.8868662507204688e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0714684353624210e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 347,
"real_time": 2.0209131423539622e+06,
"cpu_time": 2.8857238213255391e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0754499102888064e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 347,
"real_time": 2.0248200254573859e+06,
"cpu_time": 2.8886633141210843e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0714453370010254e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 347,
"real_time": 2.0287674806424300e+06,
"cpu_time": 2.8859885821325746e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0674148417796161e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 347,
"real_time": 2.0285526106686946e+06,
"cpu_time": 2.8860097146973731e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0676338281497095e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0255701412763502e+06,
"cpu_time": 2.8866503365994082e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0706824705163159e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time_median",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0248200254573859e+06,
"cpu_time": 2.8860097146973731e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0714453370010254e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2390381072339746e+03,
"cpu_time": 1.2047243820984947e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3128464284599731e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5990747697302624e-03,
"cpu_time": 4.1734337090432270e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5998814282877126e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 340,
"real_time": 2.0682839779457187e+06,
"cpu_time": 3.6422773176470250e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0558299002692151e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 340,
"real_time": 2.0627150192226775e+06,
"cpu_time": 3.6402054911765363e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0667799098884726e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 340,
"real_time": 2.0673047110904006e+06,
"cpu_time": 3.6409371264707102e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0577511167066536e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 340,
"real_time": 2.0613211508402054e+06,
"cpu_time": 3.6403527705882718e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0695298724222374e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 340,
"real_time": 2.0684482372256324e+06,
"cpu_time": 3.6409476764706527e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0555078193551846e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0656146192649272e+06,
"cpu_time": 3.6409440764706396e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0610797237283525e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time_median",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0673047110904008e+06,
"cpu_time": 3.6409371264707097e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0577511167066536e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3486127131336807e+03,
"cpu_time": 8.1742647343152566e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.5875550209891982e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6211217145264605e-03,
"cpu_time": 2.2450948332716509e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6221191084969310e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 190,
"real_time": 3.6918336121169361e+06,
"cpu_time": 6.7958967052633353e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5444128210262890e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 190,
"real_time": 3.6965670676803901e+06,
"cpu_time": 6.7971149421052095e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5385936986469355e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 190,
"real_time": 3.6937796964163058e+06,
"cpu_time": 6.7927384631577516e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5420185768732243e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 190,
"real_time": 3.6935919344327166e+06,
"cpu_time": 6.7973121000001784e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5422494682203550e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 190,
"real_time": 3.6944508417754583e+06,
"cpu_time": 6.7886599631579332e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5411934597395544e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6940446304843621e+06,
"cpu_time": 6.7943444347368823e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5416936049012718e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time_median",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6937796964163058e+06,
"cpu_time": 6.7958967052633343e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5420185768732243e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7096361465518899e+03,
"cpu_time": 3.6669010690414457e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1016833213783661e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.6280874151965047e-04,
"cpu_time": 5.3969902530904732e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.6275321591713865e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 96,
"real_time": 7.4275628673300771e+06,
"cpu_time": 1.3940494541666718e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5175561081533499e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 96,
"real_time": 7.4316029398081200e+06,
"cpu_time": 1.3929907906250112e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5151002107852602e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 96,
"real_time": 7.4237279137984542e+06,
"cpu_time": 1.3937892781250127e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5198897898227806e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 96,
"real_time": 7.4253645580029115e+06,
"cpu_time": 1.3928573624999886e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5188935489821434e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 96,
"real_time": 7.4166796063461034e+06,
"cpu_time": 1.3941492864583202e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5241851854149199e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.4249875770571334e+06,
"cpu_time": 1.3935672343750011e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5191249686316910e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time_median",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.4253645580029115e+06,
"cpu_time": 1.3937892781250129e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5188935489821434e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.5033259883205019e+03,
"cpu_time": 6.0349595167781536e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3505335140541424e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.4118992539806043e-04,
"cpu_time": 4.3305836761329733e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.4141200726047260e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 49,
"real_time": 1.3907604907848397e+07,
"cpu_time": 2.5790038448979065e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.8253358104909096e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 49,
"real_time": 1.4560561075958671e+07,
"cpu_time": 2.6734471714286085e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6089476669141016e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 49,
"real_time": 1.4544796084566992e+07,
"cpu_time": 2.6761264244897828e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6139432694561472e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 49,
"real_time": 1.4533648115335679e+07,
"cpu_time": 2.6762006857142974e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6174823738293056e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 49,
"real_time": 1.4528139608398993e+07,
"cpu_time": 2.6756905448978938e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6192331440154314e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4414949958421748e+07,
"cpu_time": 2.6560937342856981e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6569884529411783e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time_median",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4533648115335679e+07,
"cpu_time": 2.6756905448978938e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6174823738293056e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8388499594164902e+05,
"cpu_time": 4.3109239106069022e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.4191070935944661e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9693789902877384e-02,
"cpu_time": 1.6230315425092616e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0225747151349952e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 25,
"real_time": 2.8250244781374931e+07,
"cpu_time": 5.0926624999999598e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7510288508540020e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 25,
"real_time": 2.8210705146193504e+07,
"cpu_time": 5.0918302199997924e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7576878105122490e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 25,
"real_time": 2.8256638273596764e+07,
"cpu_time": 5.0917501080000423e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7499538586447544e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 25,
"real_time": 2.5656550377607346e+07,
"cpu_time": 4.8216757920001782e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 5.2313240098381748e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 25,
"real_time": 2.8195153325796127e+07,
"cpu_time": 5.0973466840000585e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7603120454465618e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7713858380913734e+07,
"cpu_time": 5.0390530608000070e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8500613150591497e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time_median",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8210705146193504e+07,
"cpu_time": 5.0918302199997917e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7576878105122490e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1503627835499351e+06,
"cpu_time": 1.2153950261621033e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1317713876297036e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.1508575519826514e-02,
"cpu_time": 2.4119512366657749e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3953493557095477e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 10,
"real_time": 5.4916159436106682e+07,
"cpu_time": 9.5273730099995643e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.8880959403637228e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 10,
"real_time": 5.4751246422529221e+07,
"cpu_time": 9.5207077999998540e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9028190870471821e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 10,
"real_time": 5.2524373307824135e+07,
"cpu_time": 9.3036697299999103e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.1106836520791636e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 10,
"real_time": 5.4848048090934753e+07,
"cpu_time": 9.5306631799996927e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.8941660705035524e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 10,
"real_time": 5.4966976121068001e+07,
"cpu_time": 9.5487843899996966e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.8835769209635096e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4401360675692558e+07,
"cpu_time": 9.4862396219997436e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9358683341914253e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time_median",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4848048090934753e+07,
"cpu_time": 9.5273730099995643e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.8941660705035524e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0523746787246561e+06,
"cpu_time": 1.0258786097457698e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.7990204116452381e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9344638914424703e-02,
"cpu_time": 1.0814386423115777e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9852677883982647e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 1.0733332578092813e+08,
"cpu_time": 1.8380291100000080e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0019032587863369e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 9.7974468953907490e+07,
"cpu_time": 1.7467051412499756e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.4797021890730867e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 1.0764140449464321e+08,
"cpu_time": 1.8396626250000027e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 4.9875873927928677e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 9.8030170425772667e+07,
"cpu_time": 1.7461907624999639e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.4765885815378904e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 1.0734210442751646e+08,
"cpu_time": 1.8381613212500268e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0014941933854666e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0366429481655359e+08,
"cpu_time": 1.8017497919999957e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.1894551231151304e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time_median",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0733332578092813e+08,
"cpu_time": 1.8380291100000077e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0019032587863369e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.1701776841231920e+06,
"cpu_time": 5.0487846602264177e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6360224567825699e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.9874237733179408e-02,
"cpu_time": 2.8021563719022924e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0795746263245768e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.9336525723338127e+08,
"cpu_time": 3.1322833524998826e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.5529201024155674e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.9433301687240601e+08,
"cpu_time": 3.1428466500000238e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.5252670970728092e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.9411337375640869e+08,
"cpu_time": 3.1301560374998873e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.5315190459129829e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.9396562129259109e+08,
"cpu_time": 3.1196299350000346e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.5357326563571482e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.9358805567026138e+08,
"cpu_time": 3.1243790950000519e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.5465293056556387e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9387306496500969e+08,
"cpu_time": 3.1298590139999759e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.5383936414828300e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time_median",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9396562129259109e+08,
"cpu_time": 3.1301560374998868e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.5357326563571482e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9273710560644453e+05,
"cpu_time": 8.7935757577041106e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1223348129894216e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0257435228422573e-03,
"cpu_time": 2.8095756768500174e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0264626995507881e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 381,
"real_time": 1.8504813195350140e+06,
"cpu_time": 2.0678760629921700e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2134781674149707e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 381,
"real_time": 1.8534999333286604e+06,
"cpu_time": 2.0680929028871467e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2098732923308406e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 381,
"real_time": 1.8575889615241496e+06,
"cpu_time": 2.0725746456692948e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2050087962620305e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 381,
"real_time": 1.8581500223795322e+06,
"cpu_time": 2.0725092204725235e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2043430028080805e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 381,
"real_time": 1.8530497355901469e+06,
"cpu_time": 2.0674294278215377e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2104101802186831e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8545539944715009e+06,
"cpu_time": 2.0696964519685346e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2086226878069211e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time_median",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8534999333286602e+06,
"cpu_time": 2.0680929028871465e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2098732923308406e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2443397841836686e+03,
"cpu_time": 2.6086514621199281e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8636362020962115e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7493908475327087e-03,
"cpu_time": 1.2604029250950213e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7493418968418984e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 380,
"real_time": 1.8496196565377575e+06,
"cpu_time": 2.0702376421052362e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4290186747551858e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 380,
"real_time": 1.8533358911602255e+06,
"cpu_time": 2.0689556315789418e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4201377845608136e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 380,
"real_time": 1.8599131179814178e+06,
"cpu_time": 2.0753212078948249e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4045068131412817e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 380,
"real_time": 1.8581607345703035e+06,
"cpu_time": 2.0737690578946993e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4086605897925114e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 380,
"real_time": 1.8526504065352797e+06,
"cpu_time": 2.0686603394735630e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4217732450237097e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8547359613569968e+06,
"cpu_time": 2.0713887757894532e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4168194214547006e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time_median",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8533358911602255e+06,
"cpu_time": 2.0702376421052362e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4201377845608136e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.2136187757805164e+03,
"cpu_time": 2.9924667668009606e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0031706488834539e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2718159692647947e-03,
"cpu_time": 1.4446668832896730e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2712512175855604e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 380,
"real_time": 1.8502676378327457e+06,
"cpu_time": 2.0717495842105611e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8549351807238515e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 380,
"real_time": 1.8549350179359624e+06,
"cpu_time": 2.0719598999999347e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8326544280947000e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 380,
"real_time": 1.8590845058880451e+06,
"cpu_time": 2.0761745947368126e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8129398895580117e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 380,
"real_time": 1.8541636607742952e+06,
"cpu_time": 2.0695674368421410e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8363289318042565e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 380,
"real_time": 1.8507021717500479e+06,
"cpu_time": 2.0698129500000339e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8528560943477340e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8538305988362194e+06,
"cpu_time": 2.0718528931578968e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8379429049057104e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time_median",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8541636607742955e+06,
"cpu_time": 2.0717495842105609e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8363289318042565e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5852460953906002e+03,
"cpu_time": 2.6497125502306067e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7079697959355501e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9339664032092861e-03,
"cpu_time": 1.2789095977716555e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9325422378407772e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 379,
"real_time": 1.8533583664265277e+06,
"cpu_time": 2.0752989155671864e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7680336730116688e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 379,
"real_time": 1.8579734733594228e+06,
"cpu_time": 2.0749868258575299e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7636419717420299e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 379,
"real_time": 1.8651177554345555e+06,
"cpu_time": 2.0817664591029736e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7568863898550656e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 379,
"real_time": 1.8597398110732036e+06,
"cpu_time": 2.0769731899735963e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7619669055259138e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 379,
"real_time": 1.8551331479371141e+06,
"cpu_time": 2.0774786279683411e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7663422184244633e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8582645108461652e+06,
"cpu_time": 2.0773008036939255e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7633742317118283e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time_median",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8579734733594228e+06,
"cpu_time": 2.0769731899735965e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7636419717420299e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5580659741454074e+03,
"cpu_time": 2.7130739001951306e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3204074469675310e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4528617683549701e-03,
"cpu_time": 1.3060573102223094e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4500797217465375e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 379,
"real_time": 1.8591918322699401e+06,
"cpu_time": 2.0870676728231404e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5249724564455107e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 379,
"real_time": 1.8614365036662612e+06,
"cpu_time": 2.0845807915566603e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5207217582185119e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 379,
"real_time": 1.8667608352587188e+06,
"cpu_time": 2.0900179604221992e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5106800379662566e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 379,
"real_time": 1.8611359189213486e+06,
"cpu_time": 2.0842849841688913e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5212903761474036e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 379,
"real_time": 1.8541161442423698e+06,
"cpu_time": 2.0827167651714443e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5346221542544939e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8605282468717278e+06,
"cpu_time": 2.0857336348284674e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5224573566064350e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time_median",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8611359189213484e+06,
"cpu_time": 2.0845807915566601e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5212903761474036e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5535814981671010e+03,
"cpu_time": 2.8576319757275801e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.6224620691757751e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4474670061169156e-03,
"cpu_time": 1.3700848123699143e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4478542097902721e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 379,
"real_time": 1.8573123110073686e+06,
"cpu_time": 2.0988705593667706e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0570791580501184e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 379,
"real_time": 1.8650687662967527e+06,
"cpu_time": 2.1026983509233827e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0277301496102065e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 379,
"real_time": 1.8596718064217526e+06,
"cpu_time": 2.0965262427440372e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0481253491818726e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 379,
"real_time": 1.8647491946428802e+06,
"cpu_time": 2.1011996807387588e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0289345278468788e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 379,
"real_time": 1.8563531971543336e+06,
"cpu_time": 2.0970605699208400e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0607253081431210e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8606310551046177e+06,
"cpu_time": 2.0992710807387577e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0445188985664397e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time_median",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8596718064217526e+06,
"cpu_time": 2.0988705593667706e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0481253491818726e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.0892127279724627e+03,
"cpu_time": 2.6479515638581188e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5476991131192134e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1977558187872654e-03,
"cpu_time": 1.2613671422207530e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1970259934062644e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 378,
"real_time": 1.8605822996404539e+06,
"cpu_time": 2.1202308359788815e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4089352567239714e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 378,
"real_time": 1.8677277225328402e+06,
"cpu_time": 2.1238942936508558e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4035450501559427e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 378,
"real_time": 1.8696075203479268e+06,
"cpu_time": 2.1260318227513423e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4021338550842801e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 378,
"real_time": 1.8729192813259067e+06,
"cpu_time": 2.1296740026454423e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3996545532620010e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 378,
"real_time": 1.8682238037134989e+06,
"cpu_time": 2.1251334179894566e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4031723580383256e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8678121255121254e+06,
"cpu_time": 2.1249928746031956e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4034882146529040e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time_median",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8682238037134986e+06,
"cpu_time": 2.1251334179894566e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4031723580383256e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5208812209660682e+03,
"cpu_time": 3.4240333457698325e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4023709565536794e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4204153936127344e-03,
"cpu_time": 1.6113152127200472e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4242248143103349e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 372,
"real_time": 1.8981340258652645e+06,
"cpu_time": 2.1937296774193104e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7621231844311064e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 372,
"real_time": 1.8935422392709742e+06,
"cpu_time": 2.1903093897849103e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7688212553518438e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 372,
"real_time": 1.8921822297915076e+06,
"cpu_time": 2.1885848333332976e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7708113507533008e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 372,
"real_time": 1.8900187679200922e+06,
"cpu_time": 2.1860198064516876e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7739830360360008e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 372,
"real_time": 1.8888032625577042e+06,
"cpu_time": 2.1859093602149482e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7757681829183239e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8925361050811086e+06,
"cpu_time": 2.1889106134408312e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7703014018981153e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time_median",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8921822297915076e+06,
"cpu_time": 2.1885848333332976e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7708113507533008e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6312997164066705e+03,
"cpu_time": 3.2653625961898151e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.3097609931144735e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9187479206643951e-03,
"cpu_time": 1.4917752128109374e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9166726730443148e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 371,
"real_time": 1.8875228523965823e+06,
"cpu_time": 2.2691417088948111e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5553022771015775e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 371,
"real_time": 1.8938452286540337e+06,
"cpu_time": 2.2721630943396292e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5367565634982157e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 371,
"real_time": 1.8886656962765625e+06,
"cpu_time": 2.2697946873315927e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5519407276111937e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 371,
"real_time": 1.8929680459505082e+06,
"cpu_time": 2.2715049838275644e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5393222418262362e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 371,
"real_time": 1.8892341100101201e+06,
"cpu_time": 2.2704819056603550e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5502703155956841e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8904471866575617e+06,
"cpu_time": 2.2706172760107908e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5467184251265812e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time_median",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8892341100101203e+06,
"cpu_time": 2.2704819056603555e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5502703155956841e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7882976339404113e+03,
"cpu_time": 1.2298226550484906e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.1779138288441265e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4749407725429822e-03,
"cpu_time": 5.4162481191420567e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4743697447842773e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 363,
"real_time": 1.9346682493351707e+06,
"cpu_time": 2.4699820275481977e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0839853296401930e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 363,
"real_time": 1.9326389344863226e+06,
"cpu_time": 2.4694064573003626e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0851235388970385e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 363,
"real_time": 1.9328337478305190e+06,
"cpu_time": 2.4692152975207181e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0850141675940404e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 363,
"real_time": 1.9321390700246880e+06,
"cpu_time": 2.4704799311295459e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0854042716362045e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 363,
"real_time": 1.9326988750678739e+06,
"cpu_time": 2.4691993471073695e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0850898849549706e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9329957753489148e+06,
"cpu_time": 2.4696566121212384e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0849234385444894e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time_median",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9326988750678736e+06,
"cpu_time": 2.4694064573003622e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0850898849549706e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.7119145138014972e+02,
"cpu_time": 5.5905650371350498e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.4479929720953200e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.0242812931386015e-04,
"cpu_time": 2.2637013622445266e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0215460174814121e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 346,
"real_time": 2.0266216742197815e+06,
"cpu_time": 2.8861040375722703e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0696038403984518e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 346,
"real_time": 2.0234231168210420e+06,
"cpu_time": 2.8843423208092838e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0728753986905041e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 346,
"real_time": 2.0310651938931618e+06,
"cpu_time": 2.8853202543353089e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0650760067235088e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 346,
"real_time": 2.0290480824348899e+06,
"cpu_time": 2.8846203901734939e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0671289341585088e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 346,
"real_time": 2.0275683030539940e+06,
"cpu_time": 2.8850381676301565e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0686375860593171e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0275452740845743e+06,
"cpu_time": 2.8850850341041023e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0686643532060583e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time_median",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0275683030539942e+06,
"cpu_time": 2.8850381676301570e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0686375860593171e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8501761324854606e+03,
"cpu_time": 6.8253390169087243e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9090375928268787e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4057274917189209e-03,
"cpu_time": 2.3657323566645503e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4062395324395630e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 340,
"real_time": 2.0660219135392897e+06,
"cpu_time": 3.6426908617647099e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0602705833015714e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 340,
"real_time": 2.0712384159731513e+06,
"cpu_time": 3.6430231294116643e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0500446183829074e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 340,
"real_time": 2.0693565160720882e+06,
"cpu_time": 3.6421347882353798e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0537277819689980e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 340,
"real_time": 2.0645776931333409e+06,
"cpu_time": 3.6422950882352469e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0631108375819407e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 340,
"real_time": 2.0723763058948165e+06,
"cpu_time": 3.6422569617647748e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0478208403265557e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0687141689225375e+06,
"cpu_time": 3.6424801658823555e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0549949323123951e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time_median",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0693565160720882e+06,
"cpu_time": 3.6422950882352469e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0537277819689980e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3374522931381775e+03,
"cpu_time": 3.6829392824613694e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.5436856110299183e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6132979332163829e-03,
"cpu_time": 1.0111075736137090e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6137345965308830e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 191,
"real_time": 3.6572477833918878e+06,
"cpu_time": 6.7295950418849112e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5873883842893724e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 191,
"real_time": 3.5219391971260933e+06,
"cpu_time": 6.8215138115184195e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.7636302221487036e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 191,
"real_time": 3.6553445269709639e+06,
"cpu_time": 6.7229219947642796e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5897769351724005e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 191,
"real_time": 3.6582161321338871e+06,
"cpu_time": 6.7224092041885853e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5861740788436203e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 191,
"real_time": 3.6588235190186980e+06,
"cpu_time": 6.7155260261781663e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5854127461440592e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6303142317283065e+06,
"cpu_time": 6.7423932157068728e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6224764733196316e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time_median",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6572477833918878e+06,
"cpu_time": 6.7229219947642786e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5873883842893724e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.0597804246986590e+04,
"cpu_time": 4.4508979344858082e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.8924644934521690e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6692165024551446e-02,
"cpu_time": 6.6013621455911723e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7074104192863950e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 97,
"real_time": 7.3288212213473218e+06,
"cpu_time": 1.3708855391752252e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5784214113809958e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 97,
"real_time": 7.3328657344598128e+06,
"cpu_time": 1.3747849896906974e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5758961387108831e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 97,
"real_time": 7.3367700691229291e+06,
"cpu_time": 1.3779734876288315e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5734610303810778e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 97,
"real_time": 7.3299246801773915e+06,
"cpu_time": 1.3732899247422455e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5777321683458214e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 97,
"real_time": 7.3262990797994677e+06,
"cpu_time": 1.3740817113402275e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5799975723784456e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.3309361569813844e+06,
"cpu_time": 1.3742031305154458e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5771016642394447e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time_median",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.3299246801773906e+06,
"cpu_time": 1.3740817113402274e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5777321683458214e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.0235656750018934e+03,
"cpu_time": 2.5694966705673625e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5116258972386792e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.4884745806579936e-04,
"cpu_time": 1.8698084828285744e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.4873718817779950e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 49,
"real_time": 1.4480136562975086e+07,
"cpu_time": 2.6740455591837008e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6345463461714640e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 49,
"real_time": 1.4497214187012643e+07,
"cpu_time": 2.6736946959183153e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6290868807139235e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 49,
"real_time": 1.4493086736421196e+07,
"cpu_time": 2.6741884999999423e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6304051870023727e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 49,
"real_time": 1.4492231250113370e+07,
"cpu_time": 2.6740318183673322e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6306785229827890e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 49,
"real_time": 1.4498530221836908e+07,
"cpu_time": 2.6738624816326424e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6286666974645634e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4492239791671842e+07,
"cpu_time": 2.6739646110203870e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6306767268670225e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time_median",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4493086736421194e+07,
"cpu_time": 2.6740318183673322e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6304051870023727e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.2718576316434455e+03,
"cpu_time": 1.9005281235908449e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3246246827219226e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.0177596673650919e-04,
"cpu_time": 7.1075290815670217e-05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0200539140090098e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 25,
"real_time": 2.6911565512418747e+07,
"cpu_time": 4.9607792200001761e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.9873623271029406e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 25,
"real_time": 2.8028734177350998e+07,
"cpu_time": 5.0557589640000060e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7885761501301212e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 25,
"real_time": 2.8049841448664665e+07,
"cpu_time": 5.0590910240000546e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7849727865891218e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 25,
"real_time": 2.8060932382941246e+07,
"cpu_time": 5.0570051880001754e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7830815515450735e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 25,
"real_time": 2.7969188168644905e+07,
"cpu_time": 5.0426689639998585e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7987709614848928e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7804052338004112e+07,
"cpu_time": 5.0350606720000550e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8285527553704309e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time_median",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8028734177350998e+07,
"cpu_time": 5.0557589640000068e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7885761501301212e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0017100819194072e+05,
"cpu_time": 4.2021004003387596e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.8983718094542220e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7989140651568956e-02,
"cpu_time": 8.3456797724536218e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8428651938320943e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 14,
"real_time": 5.4892037596021377e+07,
"cpu_time": 9.6418511428571001e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.8902439726423349e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 14,
"real_time": 5.4806699976325035e+07,
"cpu_time": 9.6393145214286894e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.8978584026397619e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 14,
"real_time": 5.4894860567791119e+07,
"cpu_time": 9.6294117999998927e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.8899924915284538e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 14,
"real_time": 4.9944533301251277e+07,
"cpu_time": 9.2230615714287624e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.3746714256167612e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 14,
"real_time": 5.4967660989080153e+07,
"cpu_time": 9.6461495714286074e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.8835160741754541e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3901158486093804e+07,
"cpu_time": 9.5559577214286119e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9872564733205528e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time_median",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4892037596021377e+07,
"cpu_time": 9.6393145214286894e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.8902439726423349e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2125551445329115e+06,
"cpu_time": 1.8619610233616817e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1663110243037808e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.1048378303478184e-02,
"cpu_time": 1.9484818556557194e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3436928417307452e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 1.0240637045353651e+08,
"cpu_time": 1.7761139387499726e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.2425538530690079e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 1.0681978613138199e+08,
"cpu_time": 1.8279985762499961e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0259500738906240e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 1.0262513160705566e+08,
"cpu_time": 1.7748506062500268e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.2313785482452831e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 1.0687274672091007e+08,
"cpu_time": 1.8277000650000730e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0234594737421408e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 1.0218540858477354e+08,
"cpu_time": 1.7695586899999681e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.2538901535497522e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0418188869953156e+08,
"cpu_time": 1.7952443752500075e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.1554464204993620e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time_median",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0262513160705566e+08,
"cpu_time": 1.7761139387499726e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.2313785482452831e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4372684652928682e+06,
"cpu_time": 2.9865713292040741e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1961858061053625e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3394358613733093e-02,
"cpu_time": 1.6636015521776310e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3202371017745901e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.8502469733357430e+08,
"cpu_time": 3.1218213949998128e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8032351327898130e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.8504615128040314e+08,
"cpu_time": 3.1210432125001830e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8025623152407169e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.8525071069598198e+08,
"cpu_time": 3.1442122625000477e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.7961549511253185e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.8533523008227348e+08,
"cpu_time": 3.1271788000000811e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.7935117005188255e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.8482182547450066e+08,
"cpu_time": 3.1368380250000882e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8096051223568354e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8509572297334674e+08,
"cpu_time": 3.1302187390000427e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8010138444063015e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time_median",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8504615128040314e+08,
"cpu_time": 3.1271788000000811e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.8025623152407169e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0242695195027947e+05,
"cpu_time": 1.0044657149718512e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.3449378974801637e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0936338706185470e-03,
"cpu_time": 3.2089313837943816e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0937636191987970e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 381,
"real_time": 1.8495616817090958e+06,
"cpu_time": 2.0681772860891975e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2145787515532179e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 381,
"real_time": 1.8512498740489676e+06,
"cpu_time": 2.0705354094489750e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2125592322345003e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 381,
"real_time": 1.8465863502001709e+06,
"cpu_time": 2.0662488635170530e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2181470146554434e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 381,
"real_time": 1.8458186856828802e+06,
"cpu_time": 2.0686705223096663e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2190695282102646e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 381,
"real_time": 1.8486293943348620e+06,
"cpu_time": 2.0676159711285145e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2156955918542794e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8483691971951958e+06,
"cpu_time": 2.0682496104986812e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2160100237015416e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time_median",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8486293943348620e+06,
"cpu_time": 2.0681772860891973e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2156955918542794e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2063359549073289e+03,
"cpu_time": 1.5661865910096374e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6449322893385279e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1936662644320892e-03,
"cpu_time": 7.5725221127057767e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1935561035597349e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 383,
"real_time": 1.8481950452996541e+06,
"cpu_time": 2.0683600496082415e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4324326162619935e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 383,
"real_time": 1.8488367260026431e+06,
"cpu_time": 2.0690741827675749e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4308942400294403e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 383,
"real_time": 1.8463945218585930e+06,
"cpu_time": 2.0668132036556138e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4367549313100642e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 383,
"real_time": 1.8456584475358506e+06,
"cpu_time": 2.0697940704960926e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4385243710379815e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 383,
"real_time": 1.8467078323823437e+06,
"cpu_time": 2.0669675926891123e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4360021960982950e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8471585146158170e+06,
"cpu_time": 2.0682018198433269e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4349216709475545e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time_median",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8467078323823437e+06,
"cpu_time": 2.0683600496082413e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4360021960982950e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3160347615585149e+03,
"cpu_time": 1.3012385887779933e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1592490856461841e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.1246444262648017e-04,
"cpu_time": 6.2916422193099440e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.1235735826901010e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 382,
"real_time": 1.8479710401799860e+06,
"cpu_time": 2.0695845183243612e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8659398030416407e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 382,
"real_time": 1.8517645663707955e+06,
"cpu_time": 2.0735296178010770e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8477770325362645e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 382,
"real_time": 1.8475350066301774e+06,
"cpu_time": 2.0692768455497876e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8680322382002920e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 382,
"real_time": 1.8455697651644705e+06,
"cpu_time": 2.0719366518325571e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8774752974672392e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 382,
"real_time": 1.8475832122112005e+06,
"cpu_time": 2.0694609319370987e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8678008609915413e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8480847181113262e+06,
"cpu_time": 2.0707577130889762e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8654050464473963e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time_median",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8475832122112003e+06,
"cpu_time": 2.0695845183243614e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8678008609915413e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2601374454596225e+03,
"cpu_time": 1.8923760382356315e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0832426581543548e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2229620337802474e-03,
"cpu_time": 9.1385681013002209e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2218761043393488e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 381,
"real_time": 1.8521007619624936e+06,
"cpu_time": 2.0764239160105721e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7692341946492638e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 381,
"real_time": 1.8546653895544468e+06,
"cpu_time": 2.0794116194224742e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7667877011427909e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 381,
"real_time": 1.8528881365333421e+06,
"cpu_time": 2.0768805984251236e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7684823683585797e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 381,
"real_time": 1.8545784632114051e+06,
"cpu_time": 2.0825008845146156e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7668705126262832e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 381,
"real_time": 1.8552449394392984e+06,
"cpu_time": 2.0795172519684739e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7662357839339163e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8538955381401971e+06,
"cpu_time": 2.0789468540682520e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7675221121421669e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time_median",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8545784632114053e+06,
"cpu_time": 2.0794116194224742e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7668705126262832e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3337935786100929e+03,
"cpu_time": 2.4396271146504546e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2719964834488537e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.1945454917494241e-04,
"cpu_time": 1.1734918138366038e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.1964954481233863e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 383,
"real_time": 1.8605728235214890e+06,
"cpu_time": 2.0899902219322724e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5223560814975582e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 383,
"real_time": 1.8601596820909549e+06,
"cpu_time": 2.0895257467364774e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5231383967172526e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 383,
"real_time": 1.8553675821103586e+06,
"cpu_time": 2.0850752271542058e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5322380660255536e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 383,
"real_time": 1.8569608926806506e+06,
"cpu_time": 2.0910815378592054e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5292073332462206e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 383,
"real_time": 1.8571960909551075e+06,
"cpu_time": 2.0867972819843392e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5287603888018392e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8580514142717118e+06,
"cpu_time": 2.0884940031333000e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5271400532576852e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time_median",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8571960909551072e+06,
"cpu_time": 2.0895257467364774e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5287603888018392e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2319312372104291e+03,
"cpu_time": 2.4781743968268952e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.2364049875749603e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2012214624778099e-03,
"cpu_time": 1.1865843967514248e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2010878285545238e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 379,
"real_time": 1.8621184086024095e+06,
"cpu_time": 2.1051236147758691e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0388649505041152e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 379,
"real_time": 1.8590636181861339e+06,
"cpu_time": 2.1054835804748554e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0504311266058430e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 379,
"real_time": 1.8633887072915144e+06,
"cpu_time": 2.1064318469657614e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0340664557593405e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 379,
"real_time": 1.8594925387671567e+06,
"cpu_time": 2.1026614749341104e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0488048361248448e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 379,
"real_time": 1.8624025012279239e+06,
"cpu_time": 2.1062554221636294e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0377912354381651e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8612931548150280e+06,
"cpu_time": 2.1051911878628451e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0419917208864614e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time_median",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8621184086024095e+06,
"cpu_time": 2.1054835804748554e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0388649505041152e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9049990282405452e+03,
"cpu_time": 1.5133850076316312e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.2088956591838665e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0234814560578238e-03,
"cpu_time": 7.1888245417177257e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0237012403468710e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 377,
"real_time": 1.8712539012440101e+06,
"cpu_time": 2.1344028488062485e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4009002189693582e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 377,
"real_time": 1.8695261634655287e+06,
"cpu_time": 2.1321779787799628e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4021948722775045e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 377,
"real_time": 1.8707581844618693e+06,
"cpu_time": 2.1338046392571265e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4012714319643974e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 377,
"real_time": 1.8696683047207159e+06,
"cpu_time": 2.1326897108754162e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4020882706205907e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 377,
"real_time": 1.8704543088591197e+06,
"cpu_time": 2.1331314137931149e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4014990837166950e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8703321725502487e+06,
"cpu_time": 2.1332413183023739e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4015907755097091e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time_median",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8704543088591197e+06,
"cpu_time": 2.1331314137931149e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4014990837166950e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.3081433221272925e+02,
"cpu_time": 8.8225907515999074e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.4765187665158235e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.9074039517603126e-04,
"cpu_time": 4.1357677989384224e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9073593107262044e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 372,
"real_time": 1.8951969635259781e+06,
"cpu_time": 2.1981687338708406e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7664037569191337e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 372,
"real_time": 1.8945780142413210e+06,
"cpu_time": 2.1953553897850313e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7673075273701501e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 372,
"real_time": 1.8965431878822653e+06,
"cpu_time": 2.1966292043010350e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7644400789282054e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 372,
"real_time": 1.8955212704034932e+06,
"cpu_time": 2.1978034247311330e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7659304497722495e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 372,
"real_time": 1.8950752369898011e+06,
"cpu_time": 2.1961613360215374e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7665814515775955e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8953829346085719e+06,
"cpu_time": 2.1968236177419159e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7661326529134673e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time_median",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8951969635259781e+06,
"cpu_time": 2.1966292043010350e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7664037569191337e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.3186137980316005e+02,
"cpu_time": 1.1620527237127112e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0678179161261530e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.8612850545386048e-04,
"cpu_time": 5.2896951504334652e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8603279383635453e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 369,
"real_time": 1.9068530537339489e+06,
"cpu_time": 2.2828953712736457e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4989869195568395e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 369,
"real_time": 1.9036304701919740e+06,
"cpu_time": 2.2819791246612854e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5082959451382124e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 369,
"real_time": 1.9089504382333297e+06,
"cpu_time": 2.2841993902439266e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4929451231349003e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 369,
"real_time": 1.9032467332691320e+06,
"cpu_time": 2.2810859024387635e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5094065402592468e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 369,
"real_time": 1.9102395282014650e+06,
"cpu_time": 2.2860943523035645e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4892383102723181e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9065840447259701e+06,
"cpu_time": 2.2832508281842372e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4997745676723039e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time_median",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9068530537339491e+06,
"cpu_time": 2.2828953712736457e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.4989869195568395e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1183326395031604e+03,
"cpu_time": 1.9631532252816730e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.9953208952210261e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6355600206186308e-03,
"cpu_time": 8.5980620308933687e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6355799286929971e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 360,
"real_time": 1.9717222640691844e+06,
"cpu_time": 2.4984514249998331e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0636143021847091e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 360,
"real_time": 1.9469878806072907e+06,
"cpu_time": 2.4731190305554187e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0771263760233941e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 360,
"real_time": 1.9475345771449308e+06,
"cpu_time": 2.4753228027776685e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0768240136071973e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 360,
"real_time": 1.9522927929453240e+06,
"cpu_time": 2.4792104861110905e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0741995296904898e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 360,
"real_time": 1.9450710056440181e+06,
"cpu_time": 2.4721600888887625e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0781878882131748e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9527217040821500e+06,
"cpu_time": 2.4796527666665548e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0739904219437931e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time_median",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9475345771449306e+06,
"cpu_time": 2.4753228027776685e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0768240136071973e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0948989093473192e+04,
"cpu_time": 1.0853152564406282e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.9830961903549572e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.6070401996272242e-03,
"cpu_time": 4.3768840179169051e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.5709027456001658e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 347,
"real_time": 2.0241023330501034e+06,
"cpu_time": 2.8906264755041040e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0721798159679198e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 347,
"real_time": 2.0251780773864614e+06,
"cpu_time": 2.8910917608070886e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0710791050102839e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 347,
"real_time": 2.0288488400230450e+06,
"cpu_time": 2.8909453746396652e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0673319358540082e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 347,
"real_time": 2.0296571988301077e+06,
"cpu_time": 2.8946594927956355e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0665085721951432e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 347,
"real_time": 2.0236352465977031e+06,
"cpu_time": 2.8887146772333337e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0726581072610781e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0262843391774842e+06,
"cpu_time": 2.8912075561959655e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0699515072576866e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time_median",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0251780773864612e+06,
"cpu_time": 2.8909453746396648e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0710791050102839e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7818835439853251e+03,
"cpu_time": 2.1534921815722578e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8407074895666395e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3728989017970481e-03,
"cpu_time": 7.4484177967688403e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3723546081183642e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 326,
"real_time": 2.1448431374430885e+06,
"cpu_time": 3.7328274386502234e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.9110589737579746e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 326,
"real_time": 2.1490079973555780e+06,
"cpu_time": 3.7325350828219191e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.9034791914792528e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 326,
"real_time": 2.1401525395093886e+06,
"cpu_time": 3.7305162331290515e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.9196308885174212e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 326,
"real_time": 2.1458422990824366e+06,
"cpu_time": 3.7339174355829414e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.9092378799630218e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 326,
"real_time": 2.1421480777479163e+06,
"cpu_time": 3.7363427791411802e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.9159795194079742e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1443988102276819e+06,
"cpu_time": 3.7332277938650632e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.9118772906251292e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time_median",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1448431374430889e+06,
"cpu_time": 3.7328274386502234e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.9110589737579746e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4140263777429036e+03,
"cpu_time": 2.1313982194944720e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2271735495841131e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5920669054001286e-03,
"cpu_time": 5.7092637716805517e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5918632121993256e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 175,
"real_time": 4.0119184407272511e+06,
"cpu_time": 7.1580054171428336e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.1818437358259830e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 175,
"real_time": 4.0125940540539366e+06,
"cpu_time": 7.1580851142860930e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.1811396253877025e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 175,
"real_time": 4.0137771623475212e+06,
"cpu_time": 7.1583012342853183e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.1799071850285730e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 175,
"real_time": 4.0174901512052333e+06,
"cpu_time": 7.1628068285709955e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.1760440893593464e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 175,
"real_time": 4.0339318410094297e+06,
"cpu_time": 7.1775875999998925e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.1590231717454500e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.0179423298686752e+06,
"cpu_time": 7.1629572388570262e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.1755915614694118e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time_median",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.0137771623475207e+06,
"cpu_time": 7.1583012342853174e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.1799071850285730e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1938681620416428e+03,
"cpu_time": 8.4262477574780605e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.5290558771454375e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2882031167286913e-03,
"cpu_time": 1.1763643808688456e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2820852415441021e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 91,
"real_time": 7.8228838424515594e+06,
"cpu_time": 1.3974281736263299e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.2892662956228442e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 91,
"real_time": 7.8336743146672351e+06,
"cpu_time": 1.3984357472527886e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.2833580580666952e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 91,
"real_time": 7.9086180315813525e+06,
"cpu_time": 1.4067147978021938e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.2427680621326823e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 91,
"real_time": 7.8443591636452042e+06,
"cpu_time": 1.3989186527472876e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.2775236701945643e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 91,
"real_time": 7.8262473241640972e+06,
"cpu_time": 1.3970681681318916e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.2874229001680408e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.8471565353018893e+06,
"cpu_time": 1.3997131079120984e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.2760677972369652e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time_median",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.8336743146672351e+06,
"cpu_time": 1.3984357472527886e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.2833580580666952e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5332243825365091e+04,
"cpu_time": 3.9844416707069919e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9152536054519776e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.5025537169312776e-03,
"cpu_time": 2.8466131010592877e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4790066394399608e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 47,
"real_time": 1.5231551939344153e+07,
"cpu_time": 2.7221261744680885e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.4059111157710171e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 47,
"real_time": 1.5242428538647104e+07,
"cpu_time": 2.7270055446808059e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.4027671725569057e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 47,
"real_time": 1.5231613149034215e+07,
"cpu_time": 2.7250683787235387e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.4058934101970110e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 47,
"real_time": 1.5246748527947893e+07,
"cpu_time": 2.7263369489361972e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.4015196995599947e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 47,
"real_time": 1.5222166367667787e+07,
"cpu_time": 2.7242926234042354e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.4086276801271000e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5234901704528231e+07,
"cpu_time": 2.7249659340425737e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.4049438156424055e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time_median",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5231613149034213e+07,
"cpu_time": 2.7250683787235387e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.4058934101970110e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.7624892529542867e+03,
"cpu_time": 1.9083874051124250e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8227027375053153e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.4079765280353640e-04,
"cpu_time": 7.0033440832094058e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.4080334634044808e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 24,
"real_time": 2.9973543404291075e+07,
"cpu_time": 5.2200686166666329e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.4778732427339611e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 24,
"real_time": 3.0051517765969038e+07,
"cpu_time": 5.2276954708332829e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.4662545514420223e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 24,
"real_time": 2.9974863864481449e+07,
"cpu_time": 5.2216589000001550e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.4776759823433447e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 24,
"real_time": 2.9641681195547182e+07,
"cpu_time": 5.0824407041664205e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.5280065970132084e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 24,
"real_time": 3.0002350841338437e+07,
"cpu_time": 5.2257046583330669e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.4735737112663002e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9928791414325438e+07,
"cpu_time": 5.1955136699999116e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.4846768169597683e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time_median",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9974863864481449e+07,
"cpu_time": 5.2216589000001557e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.4776759823433447e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6357753183593700e+05,
"cpu_time": 6.3283445981883770e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4675032775363844e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.4655575486299282e-03,
"cpu_time": 1.2180402170298754e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.5020760207402037e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 10,
"real_time": 5.8860427513718605e+07,
"cpu_time": 9.9357217800002217e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.5605420711128159e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 10,
"real_time": 5.8955963328480721e+07,
"cpu_time": 9.9415354799998567e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.5531518924451694e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 10,
"real_time": 5.9739521890878677e+07,
"cpu_time": 9.8037372099997804e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.4934316094850779e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 10,
"real_time": 5.8992460742592812e+07,
"cpu_time": 9.9436392399991289e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.5503349516354122e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 10,
"real_time": 5.9031324833631516e+07,
"cpu_time": 9.9351197500004679e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.5473391755400019e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.9115939661860481e+07,
"cpu_time": 9.9119506919998914e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.5409599400436954e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time_median",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.8992460742592812e+07,
"cpu_time": 9.9357217800002217e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.5503349516354122e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5430932604611904e+05,
"cpu_time": 6.0604148610737780e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7016806131176941e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.9934651816878235e-03,
"cpu_time": 6.1142504128528863e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.9495803724084325e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 7,
"real_time": 1.1530271598270962e+08,
"cpu_time": 1.9039912242856511e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 4.6561861741444778e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 7,
"real_time": 1.0935783705541065e+08,
"cpu_time": 1.8220304957143137e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 4.9093044125220966e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 7,
"real_time": 1.1527188335146223e+08,
"cpu_time": 1.9057230757141498e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 4.6574315990230570e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 7,
"real_time": 1.0945353763444082e+08,
"cpu_time": 1.8139612985714847e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 4.9050119676631384e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 7,
"real_time": 1.1526573449373245e+08,
"cpu_time": 1.9055464842857161e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 4.6576800499995270e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1293034170355117e+08,
"cpu_time": 1.8702505157142633e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 4.7571228406704597e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time_median",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1526573449373245e+08,
"cpu_time": 1.9039912242856514e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 4.6576800499995270e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2177629064972671e+06,
"cpu_time": 4.7791708539718045e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3697248594233689e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.8493342515017669e-02,
"cpu_time": 2.5553640080920398e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8793136214879046e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 2.1480339393019676e+08,
"cpu_time": 3.3517436725000495e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 4.9987190814542103e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 2.1480798721313477e+08,
"cpu_time": 3.3650692025000238e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 4.9986121928260612e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 2.1478202566504478e+08,
"cpu_time": 3.3651698900001746e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 4.9992163947392578e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 2.1454587206244469e+08,
"cpu_time": 3.3638314300000614e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.0047191012255030e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 2.1467530727386475e+08,
"cpu_time": 3.3635003825000352e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.0017015819626160e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1472291722893715e+08,
"cpu_time": 3.3618629155000693e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.0005936704415302e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time_median",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1478202566504478e+08,
"cpu_time": 3.3638314300000614e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 4.9992163947392578e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1271524707542386e+05,
"cpu_time": 5.7046424752515904e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6260175570471724e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.2493347487099886e-04,
"cpu_time": 1.6968694496584012e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.2514115925265861e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 382,
"real_time": 1.8448775106910262e+06,
"cpu_time": 2.0675181020940046e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2202015994361504e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 382,
"real_time": 1.8389344356188562e+06,
"cpu_time": 2.0664143534032444e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2273768551305500e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 382,
"real_time": 1.8437989660471992e+06,
"cpu_time": 2.0665129397906144e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2215003237479562e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 382,
"real_time": 1.8478626551916299e+06,
"cpu_time": 2.0703016465966769e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2166149570110939e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 382,
"real_time": 1.8433717469390999e+06,
"cpu_time": 2.0659443089002657e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2220151777856890e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8437690628975625e+06,
"cpu_time": 2.0673382701569614e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2215417826222880e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time_median",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8437989660471990e+06,
"cpu_time": 2.0665129397906144e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2215003237479562e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2217436844457261e+03,
"cpu_time": 1.7529874368502794e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8840569822490274e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7473683387346881e-03,
"cpu_time": 8.4794417157342365e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7483609863345993e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 382,
"real_time": 1.8481717638892953e+06,
"cpu_time": 2.0719113141360320e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4324884515932351e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 382,
"real_time": 1.8387099324991615e+06,
"cpu_time": 2.0675085026178958e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4552976275412245e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 382,
"real_time": 1.8437792741440916e+06,
"cpu_time": 2.0671652617798678e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4430480995632419e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 382,
"real_time": 1.8491409866985588e+06,
"cpu_time": 2.0720075209424163e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4301651734116441e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 382,
"real_time": 1.8437311095522330e+06,
"cpu_time": 2.0668396544504084e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4431641672464395e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8447066133566680e+06,
"cpu_time": 2.0690864507853244e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4408327038711570e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time_median",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8437792741440919e+06,
"cpu_time": 2.0675085026178956e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4430480995632419e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.1666137972816150e+03,
"cpu_time": 2.6335093123564347e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0037435784303849e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2586864312802318e-03,
"cpu_time": 1.2727884382776192e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2602598327007518e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 382,
"real_time": 1.8488121770314095e+06,
"cpu_time": 2.0743977905759250e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8619061490104254e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 382,
"real_time": 1.8449922438762125e+06,
"cpu_time": 2.0698568324606232e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8802541335232109e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 382,
"real_time": 1.8500260001838363e+06,
"cpu_time": 2.0746413612565061e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8560917513439972e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 382,
"real_time": 1.8506052820633668e+06,
"cpu_time": 2.0759172382199673e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8533195915945694e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 382,
"real_time": 1.8446818823805470e+06,
"cpu_time": 2.0702524738219059e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8817482062850762e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8478235171070744e+06,
"cpu_time": 2.0730131392669857e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8666639663514551e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time_median",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8488121770314095e+06,
"cpu_time": 2.0743977905759248e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8619061490104254e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8041296905173449e+03,
"cpu_time": 2.7652171333929355e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3460199032268478e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5175311194802032e-03,
"cpu_time": 1.3339120148416967e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5180680223530810e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 382,
"real_time": 1.8540645506470990e+06,
"cpu_time": 2.0820072774868642e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7673602566082951e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 382,
"real_time": 1.8497181540743341e+06,
"cpu_time": 2.0777905183243698e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7715131317613248e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 382,
"real_time": 1.8555744993508030e+06,
"cpu_time": 2.0837191806283463e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7659220910539735e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 382,
"real_time": 1.8545215193173699e+06,
"cpu_time": 2.0826159869108959e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7669247651578378e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 382,
"real_time": 1.8475547933112036e+06,
"cpu_time": 2.0758048795811068e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7735874529205658e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8522867033401621e+06,
"cpu_time": 2.0803875685863167e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7690615395003993e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time_median",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8540645506470990e+06,
"cpu_time": 2.0820072774868645e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7673602566082951e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4624111525048056e+03,
"cpu_time": 3.4071488274665708e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3094750912625859e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8692630823625544e-03,
"cpu_time": 1.6377471577480279e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8707518180499333e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 381,
"real_time": 1.8544072087869728e+06,
"cpu_time": 2.0888491469815988e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5340673660813250e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 381,
"real_time": 1.8489516128486774e+06,
"cpu_time": 2.0830623569554400e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5444951368429147e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 381,
"real_time": 1.8553713919732992e+06,
"cpu_time": 2.0891097664042504e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5322308128454275e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 381,
"real_time": 1.8552420660662416e+06,
"cpu_time": 2.0889224881888526e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5324770389105670e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 381,
"real_time": 1.8491439579634957e+06,
"cpu_time": 2.0825536850391536e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5441264439019822e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8526232475277376e+06,
"cpu_time": 2.0864994887138593e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5374793597164437e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time_median",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8544072087869730e+06,
"cpu_time": 2.0888491469815988e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5340673660813250e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2855510683642292e+03,
"cpu_time": 3.3759669506645978e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2772807632963173e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7734588361388024e-03,
"cpu_time": 1.6180051655539009e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7745066825773620e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 381,
"real_time": 1.8557355028156708e+06,
"cpu_time": 2.1045180236220532e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0630755191743135e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 381,
"real_time": 1.8473755571092269e+06,
"cpu_time": 2.0994207952756626e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0950381201915130e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 381,
"real_time": 1.8553680491959432e+06,
"cpu_time": 2.1030241469816840e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0644743535818890e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 381,
"real_time": 1.8527979490144323e+06,
"cpu_time": 2.1009471207346204e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0742738067970008e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 381,
"real_time": 1.8560622166108896e+06,
"cpu_time": 2.1046385931758108e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0618322396182001e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8534678549492327e+06,
"cpu_time": 2.1025097359579662e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0717388078725830e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time_median",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8553680491959429e+06,
"cpu_time": 2.1030241469816845e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0644743535818890e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6417215840937642e+03,
"cpu_time": 2.2810738681240819e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3921648033727903e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9648150758964805e-03,
"cpu_time": 1.0849290393819537e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9686315363103752e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 380,
"real_time": 1.8602413098530010e+06,
"cpu_time": 2.1288735131580131e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4091935202789095e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 380,
"real_time": 1.8593630033903634e+06,
"cpu_time": 2.1282410894735605e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4098591803860059e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 380,
"real_time": 1.8587246855435967e+06,
"cpu_time": 2.1277815447367751e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4103433501413590e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 380,
"real_time": 1.8597120602958295e+06,
"cpu_time": 2.1280394763158783e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4095945581935948e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 380,
"real_time": 1.8604004747574339e+06,
"cpu_time": 2.1283861789473388e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4090729579833037e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8596883067680448e+06,
"cpu_time": 2.1282643605263131e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4096127133966348e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time_median",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8597120602958295e+06,
"cpu_time": 2.1282410894735605e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4095945581935948e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.7969626219369388e+02,
"cpu_time": 4.0930801171348645e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.1525828862814036e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.6548934556400952e-04,
"cpu_time": 1.9232009862358730e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.6553181149066280e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 374,
"real_time": 1.8833050484716753e+06,
"cpu_time": 2.1915884786098260e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7838718981052274e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 374,
"real_time": 1.8832257955508146e+06,
"cpu_time": 2.1903976310162288e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7839890534562999e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 374,
"real_time": 1.8852428929384716e+06,
"cpu_time": 2.1916770401068232e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7810103513123870e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 374,
"real_time": 1.8852459087645395e+06,
"cpu_time": 2.1922621470586797e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7810059025328016e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 374,
"real_time": 1.8811021198582072e+06,
"cpu_time": 2.1900729866310428e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7871320459705794e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8836243531167419e+06,
"cpu_time": 2.1911996566845202e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7834018502754593e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time_median",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8833050484716755e+06,
"cpu_time": 2.1915884786098260e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7838718981052274e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7227578231559733e+03,
"cpu_time": 9.2474236916440714e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5465636324270398e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.1459734012538604e-04,
"cpu_time": 4.2202560882271422e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.1491051936141358e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 375,
"real_time": 1.8754846017497282e+06,
"cpu_time": 2.2692994586665616e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5909603257831812e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 375,
"real_time": 1.8794845884355404e+06,
"cpu_time": 2.2717815813333192e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5790614429715621e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 375,
"real_time": 1.8755114488303661e+06,
"cpu_time": 2.2694798506666608e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5908802937669528e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 375,
"real_time": 1.8811353886655222e+06,
"cpu_time": 2.2726140266665122e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5741655083309031e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 375,
"real_time": 1.8747771332661312e+06,
"cpu_time": 2.2687112080002408e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5930701382794762e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8772786321894575e+06,
"cpu_time": 2.2703772250666590e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5856275418264151e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time_median",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8755114488303661e+06,
"cpu_time": 2.2694798506666608e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5908802937669528e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8434043231740284e+03,
"cpu_time": 1.7115761749764254e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4544972600385884e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5146416064288680e-03,
"cpu_time": 7.5387303751964512e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5136163657045590e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 366,
"real_time": 1.9194959396308113e+06,
"cpu_time": 2.4719223579237084e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0925534963118277e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 366,
"real_time": 1.9186605478934639e+06,
"cpu_time": 2.4710519016391411e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0930291980530405e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 366,
"real_time": 1.9182185790325957e+06,
"cpu_time": 2.4710797950818683e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0932810384193258e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 366,
"real_time": 1.9205276589698154e+06,
"cpu_time": 2.4721486038251002e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0919665698149471e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 366,
"real_time": 1.9209447027059384e+06,
"cpu_time": 2.4721109918034114e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0917295000974505e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9195694856465249e+06,
"cpu_time": 2.4716627300546458e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0925119605393183e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time_median",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9194959396308116e+06,
"cpu_time": 2.4719223579237084e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0925534963118277e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1689571862897401e+03,
"cpu_time": 5.5166635805831515e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6528866588872531e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.0896841454844591e-04,
"cpu_time": 2.2319645449608673e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0895321050792497e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 349,
"real_time": 2.0156135394993136e+06,
"cpu_time": 2.8869493667621245e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0809068394340525e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 349,
"real_time": 2.0166579103577656e+06,
"cpu_time": 2.8872358595988271e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0798291958480496e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 349,
"real_time": 2.0133281596282492e+06,
"cpu_time": 2.8866652234955314e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0832689295789998e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 349,
"real_time": 2.0128527267924096e+06,
"cpu_time": 2.8863194441261129e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0837609946177492e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 349,
"real_time": 2.0112229389722932e+06,
"cpu_time": 2.8866731432665940e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0854495634100270e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0139350550500061e+06,
"cpu_time": 2.8867686074498380e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0826431045777757e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time_median",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0133281596282492e+06,
"cpu_time": 2.8866731432665940e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0832689295789998e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1866973499463475e+03,
"cpu_time": 3.4371057552330313e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2610973682705485e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0857834489067233e-03,
"cpu_time": 1.1906412402999486e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0856864353285109e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 344,
"real_time": 2.0395864757606324e+06,
"cpu_time": 3.6472685174418911e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1128964619514828e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 344,
"real_time": 2.0378803973746768e+06,
"cpu_time": 3.6474702325582323e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1163397080646744e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 344,
"real_time": 2.0379083042255016e+06,
"cpu_time": 3.6487464912792230e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1162833394449778e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 344,
"real_time": 2.0431502066352298e+06,
"cpu_time": 3.6472416656974559e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1057226104853120e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 344,
"real_time": 2.0340222768555935e+06,
"cpu_time": 3.6453632267440897e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1241475550444784e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0385095321703267e+06,
"cpu_time": 3.6472180267441785e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1150779349981852e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time_median",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0379083042255018e+06,
"cpu_time": 3.6472685174418911e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.1162833394449778e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3010760699338070e+03,
"cpu_time": 1.2086358796415122e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6630323488573879e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6193576815994924e-03,
"cpu_time": 3.3138569473469204e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6191752511390350e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 189,
"real_time": 3.7016252427800465e+06,
"cpu_time": 6.8701339259258593e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5323918278122988e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 189,
"real_time": 3.6957475218783924e+06,
"cpu_time": 6.8673138624338508e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5396001487333336e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 189,
"real_time": 3.6927617214147062e+06,
"cpu_time": 6.8684546296295868e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5432706645292587e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 189,
"real_time": 3.6953251424526409e+06,
"cpu_time": 6.8653850582014602e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5401190296518040e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 189,
"real_time": 3.6972967646621838e+06,
"cpu_time": 6.8714596878303308e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5376979636453142e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6965512786375941e+06,
"cpu_time": 6.8685494328042176e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5386159268744011e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time_median",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6957475218783924e+06,
"cpu_time": 6.8684546296295868e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.5396001487333336e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2715073107378880e+03,
"cpu_time": 2.3732409866135504e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0148679596519736e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.8501607691578925e-04,
"cpu_time": 3.4552288075251271e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.8460183111746234e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 96,
"real_time": 7.4185488580648480e+06,
"cpu_time": 1.3931253145833248e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5230452264963284e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 96,
"real_time": 7.4056787755883606e+06,
"cpu_time": 1.3932688218749451e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5309056761423187e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 96,
"real_time": 7.4191405486393096e+06,
"cpu_time": 1.3935714635415763e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5226845050339384e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 96,
"real_time": 7.4099039047723636e+06,
"cpu_time": 1.3917241645832708e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5283221525166073e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 96,
"real_time": 7.4032521515619010e+06,
"cpu_time": 1.3938129572916105e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5323908078587942e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.4113048477253569e+06,
"cpu_time": 1.3931005443749458e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5274696736095982e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time_median",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.4099039047723636e+06,
"cpu_time": 1.3932688218749454e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5283221525166073e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.2858619768451390e+03,
"cpu_time": 8.1434778120442088e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4503923005505931e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.8307411805915405e-04,
"cpu_time": 5.8455779411801254e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.8297561803488485e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 49,
"real_time": 1.4519269559152272e+07,
"cpu_time": 2.6786606081632920e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6220551059125214e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 49,
"real_time": 1.4518306438564038e+07,
"cpu_time": 2.6759709877549596e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6223617254518795e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 49,
"real_time": 1.4544023980139470e+07,
"cpu_time": 2.6857333102041095e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6141882117108870e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 49,
"real_time": 1.4530165957248941e+07,
"cpu_time": 2.6825935591836132e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6185889546925735e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 49,
"real_time": 1.4534032029308835e+07,
"cpu_time": 2.6839294326529332e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6173604038212204e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4529159592882713e+07,
"cpu_time": 2.6813775795917820e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6189108803178167e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time_median",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4530165957248941e+07,
"cpu_time": 2.6825935591836132e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6185889546925735e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0739030917139153e+04,
"cpu_time": 3.9867317005041819e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4134183368582292e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.3913641380880693e-04,
"cpu_time": 1.4868221957428053e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.3900935205386772e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 28,
"real_time": 2.8186086831348281e+07,
"cpu_time": 5.1086727785713851e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7618432740625916e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 28,
"real_time": 2.8158069654767003e+07,
"cpu_time": 5.1155324035712674e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7665812907483063e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 28,
"real_time": 2.8154583448278051e+07,
"cpu_time": 5.1071942892856933e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7671715067838736e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 28,
"real_time": 2.8174132441303559e+07,
"cpu_time": 5.1085365571428351e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7638637420201616e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 28,
"real_time": 2.8176292111831050e+07,
"cpu_time": 5.1078754999999933e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7634985990098677e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8169832897505593e+07,
"cpu_time": 5.1095623057142347e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7645916825249605e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time_median",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8174132441303562e+07,
"cpu_time": 5.1085365571428351e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7638637420201616e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3184436597029184e+04,
"cpu_time": 3.3888900246529498e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2300511256560911e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.6803389445013898e-04,
"cpu_time": 6.6324468161646922e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.6804663951272566e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 10,
"real_time": 5.1808930933475494e+07,
"cpu_time": 9.2547179700000018e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.1812583499296799e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 10,
"real_time": 5.4739557206630707e+07,
"cpu_time": 9.5645050899997845e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9038660467550125e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 10,
"real_time": 5.4677268862724304e+07,
"cpu_time": 9.5614573700004250e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9094525308853397e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 10,
"real_time": 5.4764563962817192e+07,
"cpu_time": 9.5643009100001559e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9016268290249920e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 10,
"real_time": 5.1790754869580269e+07,
"cpu_time": 9.2592047899995580e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.1830767223991127e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3556215167045593e+07,
"cpu_time": 9.4408372259999841e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.0158560957988272e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time_median",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4677268862724304e+07,
"cpu_time": 9.5614573700004250e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9094525308853397e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6036691396836899e+06,
"cpu_time": 1.6786673304535244e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5184898643964300e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.9943660781138720e-02,
"cpu_time": 1.7780915932227800e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.0273792457249409e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 9.6866594627499580e+07,
"cpu_time": 1.7536841100000799e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.5423741700070772e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 1.0708353482186794e+08,
"cpu_time": 1.8428507462500933e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0135710676069641e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 9.6901213750243187e+07,
"cpu_time": 1.7543114887500623e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.5403940902510386e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 1.0690589249134064e+08,
"cpu_time": 1.8363667037499455e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0219019690003195e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 9.6725872717797756e+07,
"cpu_time": 1.7538594900000247e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.5504375087557592e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0089662168174982e+08,
"cpu_time": 1.7882145077500409e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.3337357611242323e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time_median",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.6901213750243187e+07,
"cpu_time": 1.7543114887500623e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.5403940902510386e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.5675124468610566e+06,
"cpu_time": 4.6972818862983203e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8850608441182077e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.5180365348824242e-02,
"cpu_time": 2.6268000096971098e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.4090809393791593e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.8047043308615685e+08,
"cpu_time": 3.2223051799999779e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.9496827576592236e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.8141903728246689e+08,
"cpu_time": 3.2160944000000316e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.9185730454968681e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.8042083457112312e+08,
"cpu_time": 3.2186691075000340e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.9513183527411499e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.8105695024132729e+08,
"cpu_time": 3.2107916974999285e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.9304093135824413e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.8062078952789307e+08,
"cpu_time": 3.2182101200001514e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.9447299882064972e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8079760894179344e+08,
"cpu_time": 3.2172141010000247e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.9389426915372362e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time_median",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8062078952789307e+08,
"cpu_time": 3.2182101200001514e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.9447299882064972e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.2828120560725091e+05,
"cpu_time": 4.2287462737212126e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4051155045248060e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3688433055833891e-03,
"cpu_time": 1.3144124515700611e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3659354492964568e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 383,
"real_time": 1.8406364214624821e+06,
"cpu_time": 2.0688655404700448e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2253172610512148e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 383,
"real_time": 1.8362169785533883e+06,
"cpu_time": 2.0692797650131891e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2306731981243948e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 383,
"real_time": 1.8444580504170426e+06,
"cpu_time": 2.0775811644909491e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2207065100091980e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 383,
"real_time": 1.8412216808566370e+06,
"cpu_time": 2.0688157624020020e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2246099112271573e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 383,
"real_time": 1.8453917285971837e+06,
"cpu_time": 2.0747129895559023e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2195829408608368e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8415849719773468e+06,
"cpu_time": 2.0718510443864174e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2241779642545604e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time_median",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8412216808566370e+06,
"cpu_time": 2.0692797650131888e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2246099112271573e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6260535571700225e+03,
"cpu_time": 4.0547088223529236e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3828607372568322e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9689852015227164e-03,
"cpu_time": 1.9570464939257901e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9705530796973614e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 383,
"real_time": 1.8401956705654019e+06,
"cpu_time": 2.0697489712793150e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4517005071982378e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 383,
"real_time": 1.8381975551972326e+06,
"cpu_time": 2.0730014229765197e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4565394926341446e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 383,
"real_time": 1.8423320934150305e+06,
"cpu_time": 2.0720747754566818e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4465381834688317e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 383,
"real_time": 1.8475979159500415e+06,
"cpu_time": 2.0765598250652952e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4338651441851426e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 383,
"real_time": 1.8454807002797078e+06,
"cpu_time": 2.0748929608355938e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4389518669896638e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8427607870814831e+06,
"cpu_time": 2.0732555911226813e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4455190388952047e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time_median",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8423320934150300e+06,
"cpu_time": 2.0730014229765194e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4465381834688317e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8204197979231722e+03,
"cpu_time": 2.6150645945912024e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.2146705770078097e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0732044141083855e-03,
"cpu_time": 1.2613324694690094e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0727997105367993e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 383,
"real_time": 1.8429269871459277e+06,
"cpu_time": 2.0733562375978820e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8902056968481913e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 383,
"real_time": 1.8390393196813357e+06,
"cpu_time": 2.0750092375980995e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.9089992936306447e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 383,
"real_time": 1.8437044144592579e+06,
"cpu_time": 2.0743382663184393e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8864570001071896e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 383,
"real_time": 1.8494143219326995e+06,
"cpu_time": 2.0803324125326935e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8590208292959332e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 383,
"real_time": 1.8467786932185076e+06,
"cpu_time": 2.0771026919060289e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8716639736873303e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8443727472875458e+06,
"cpu_time": 2.0760277691906285e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8832693587138578e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time_median",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8437044144592576e+06,
"cpu_time": 2.0750092375980995e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.8864570001071896e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9429808492143770e+03,
"cpu_time": 2.7710251151792004e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8993285233084680e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1378438035441483e-03,
"cpu_time": 1.3347726635947296e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1380962870897989e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 382,
"real_time": 1.8453161843658637e+06,
"cpu_time": 2.0793927670157431e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7757390455696139e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 382,
"real_time": 1.8428797614276141e+06,
"cpu_time": 2.0820795078531571e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7780867035305541e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 382,
"real_time": 1.8457279288454081e+06,
"cpu_time": 2.0797859345550085e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7753429141909320e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 382,
"real_time": 1.8498733229177860e+06,
"cpu_time": 2.0844501361256910e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7713645358329386e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 382,
"real_time": 1.8501317191051370e+06,
"cpu_time": 2.0848482905758894e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7711171405595418e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8467857833323616e+06,
"cpu_time": 2.0821113272250979e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7743300679367162e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time_median",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8457279288454081e+06,
"cpu_time": 2.0820795078531574e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7753429141909320e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1330484853493640e+03,
"cpu_time": 2.5377169173772318e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.0100111909312312e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6964872231667574e-03,
"cpu_time": 1.2188190344074132e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6964212269881835e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 382,
"real_time": 1.8479419507109744e+06,
"cpu_time": 2.0861821020941238e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5464317466674633e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 382,
"real_time": 1.8430221458421277e+06,
"cpu_time": 2.0869284502616343e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5558986715297878e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 382,
"real_time": 1.8475205921010282e+06,
"cpu_time": 2.0862084083769119e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5472405709682234e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 382,
"real_time": 1.8540437688931569e+06,
"cpu_time": 2.0928460471206456e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5347601334743164e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 382,
"real_time": 1.8548952958501475e+06,
"cpu_time": 2.0934520785339568e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5331374308091670e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8494847506794869e+06,
"cpu_time": 2.0891234172774546e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5434937106897913e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time_median",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8479419507109742e+06,
"cpu_time": 2.0869284502616343e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5464317466674633e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9513144229657819e+03,
"cpu_time": 3.6932970811797591e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.4879130311939516e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.6771317909740568e-03,
"cpu_time": 1.7678692654706167e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6775588743311175e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 385,
"real_time": 1.8488040054065790e+06,
"cpu_time": 2.0996968337660246e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0895562545676842e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 385,
"real_time": 1.8453022828340747e+06,
"cpu_time": 2.0996292259738976e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.1030096921950042e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 385,
"real_time": 1.8517093519398989e+06,
"cpu_time": 2.1032680805192641e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0784326850585669e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 385,
"real_time": 1.8444216407626842e+06,
"cpu_time": 2.1001675350648779e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.1064011125894502e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 385,
"real_time": 1.8476170762865383e+06,
"cpu_time": 2.1000619870129451e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0941106619038776e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8475708714459552e+06,
"cpu_time": 2.1005647324674022e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0943020812629163e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time_median",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8476170762865383e+06,
"cpu_time": 2.1000619870129446e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.0941106619038776e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9031845976935506e+03,
"cpu_time": 1.5286456432740290e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1142332514446873e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5713522239184500e-03,
"cpu_time": 7.2773079526971987e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5706030539459821e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 377,
"real_time": 1.8553337717533174e+06,
"cpu_time": 2.1270033899204209e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4129209740642521e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 377,
"real_time": 1.8645930117853379e+06,
"cpu_time": 2.1364522599469637e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4059046577086464e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 377,
"real_time": 1.8488077113861267e+06,
"cpu_time": 2.1204710795756006e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4179084086763135e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 377,
"real_time": 1.8465481714338721e+06,
"cpu_time": 2.1215887984085828e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4196434409639111e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 377,
"real_time": 1.8480480021725479e+06,
"cpu_time": 2.1217454084880929e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4184912929308435e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8526661337062407e+06,
"cpu_time": 2.1254521872679321e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4149737548687932e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time_median",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8488077113861269e+06,
"cpu_time": 2.1217454084880934e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4179084086763135e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.4667720182566818e+03,
"cpu_time": 6.6499106170754985e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.6844891491672315e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.0302847244902537e-03,
"cpu_time": 3.1287039327021178e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0173813327684929e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 373,
"real_time": 1.8731012435420230e+06,
"cpu_time": 2.1837169410187760e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7990371679460031e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 373,
"real_time": 1.8736056879851918e+06,
"cpu_time": 2.1853096058980883e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7982835628760314e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 373,
"real_time": 1.8755518653412568e+06,
"cpu_time": 2.1860651796245212e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7953799075804591e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 373,
"real_time": 1.8783310904534629e+06,
"cpu_time": 2.1869950214475822e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7912437943697536e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 373,
"real_time": 1.8802351898347696e+06,
"cpu_time": 2.1885104369972399e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7884171237432969e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8761650154313408e+06,
"cpu_time": 2.1861194369972418e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7944723113031083e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time_median",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8755518653412566e+06,
"cpu_time": 2.1860651796245212e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.7953799075804591e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0647597327134799e+03,
"cpu_time": 1.7968226347505865e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5627815998577006e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6335235480386962e-03,
"cpu_time": 8.2192336079250255e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6327882661073857e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 374,
"real_time": 1.8793994916153492e+06,
"cpu_time": 2.2691480534757329e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5793140557824981e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 374,
"real_time": 1.8708480339631799e+06,
"cpu_time": 2.2647848128344705e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.6048165375501430e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 374,
"real_time": 1.8780673089882927e+06,
"cpu_time": 2.2685835748662236e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5832716696658957e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 374,
"real_time": 1.8697994803813072e+06,
"cpu_time": 2.2644040695187119e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.6079596288376570e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 374,
"real_time": 1.8828296914844858e+06,
"cpu_time": 2.2734929732621065e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5691494814555836e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8761888012865230e+06,
"cpu_time": 2.2680826967914486e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5889022746583557e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time_median",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8780673089882925e+06,
"cpu_time": 2.2685835748662236e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.5832716696658957e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.6410540553520714e+03,
"cpu_time": 3.7102995972037170e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6809647563229874e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.0066558607981988e-03,
"cpu_time": 1.6358749186934430e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.0076832152620583e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 366,
"real_time": 1.9192412427863199e+06,
"cpu_time": 2.4654336803278779e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0926984858638160e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 366,
"real_time": 1.9207734559265680e+06,
"cpu_time": 2.4670354808746031e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0918268333671594e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 366,
"real_time": 1.9200408024601436e+06,
"cpu_time": 2.4666158989071236e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0922434550937274e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 366,
"real_time": 1.9182296666377757e+06,
"cpu_time": 2.4651541639342648e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0932747191194444e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 366,
"real_time": 1.9191507381435402e+06,
"cpu_time": 2.4658475191258132e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0927500160975611e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9194871811908695e+06,
"cpu_time": 2.4660173486339366e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0925587019083416e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time_median",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9192412427863199e+06,
"cpu_time": 2.4658475191258132e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0926984858638160e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.6384927234144959e+02,
"cpu_time": 7.9206285490094137e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.4859671803611808e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.0213894720748677e-04,
"cpu_time": 3.2119111219542268e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0212104583296038e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 349,
"real_time": 2.0131426349677211e+06,
"cpu_time": 2.8756120716333338e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0834609168501625e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 349,
"real_time": 2.0170326032448977e+06,
"cpu_time": 2.8764783123209192e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0794428375884559e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 349,
"real_time": 2.0221292500232044e+06,
"cpu_time": 2.8811733094556187e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0742017355972023e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 349,
"real_time": 2.0141383268761004e+06,
"cpu_time": 2.8757871575931795e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0824309552290311e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 349,
"real_time": 2.0142204166899694e+06,
"cpu_time": 2.8752231489969948e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0823460854858325e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0161326463603787e+06,
"cpu_time": 2.8768548000000096e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0803765061501369e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time_median",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0142204166899696e+06,
"cpu_time": 2.8757871575931795e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0823460854858325e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6518241513641574e+03,
"cpu_time": 2.4565110412358367e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7620845786558283e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8113015321470089e-03,
"cpu_time": 8.5388773921986902e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8083671717759370e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 340,
"real_time": 2.0696518658523392e+06,
"cpu_time": 3.6221154852940426e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0531492945289817e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 340,
"real_time": 2.0667831314152437e+06,
"cpu_time": 3.6229382676471206e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0587751431161742e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 340,
"real_time": 2.0702282750896888e+06,
"cpu_time": 3.6297166029411904e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0520207848270154e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 340,
"real_time": 2.0696165221606325e+06,
"cpu_time": 3.6221706470588711e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0532185118248301e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 340,
"real_time": 2.0687623832867865e+06,
"cpu_time": 3.6217085147059686e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0548919816844487e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0690084355609384e+06,
"cpu_time": 3.6237299035294391e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0544111431962900e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time_median",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0696165221606325e+06,
"cpu_time": 3.6221706470588716e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0532185118248301e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3494721738580133e+03,
"cpu_time": 3.3760515749092347e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6459471714151814e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.5223135423909072e-04,
"cpu_time": 9.3165099629004624e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.5260948580790753e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 192,
"real_time": 3.6390056593518239e+06,
"cpu_time": 6.6662588125000848e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6103846958535213e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 192,
"real_time": 3.6411565330733233e+06,
"cpu_time": 6.6654903958334923e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6076612877280416e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 192,
"real_time": 3.6372006118957265e+06,
"cpu_time": 6.6655398593749031e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6126727090963602e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 192,
"real_time": 3.6376597236085217e+06,
"cpu_time": 6.6587637604171112e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6120905402765846e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 192,
"real_time": 3.6384155597867598e+06,
"cpu_time": 6.6607393958335593e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6111324350710716e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6386876175432308e+06,
"cpu_time": 6.6633584447918311e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6107883336051159e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time_median",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6384155597867602e+06,
"cpu_time": 6.6654903958334932e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6111324350710716e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5442200015810733e+03,
"cpu_time": 3.3795879776507418e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9561670682025091e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.2438927544533202e-04,
"cpu_time": 5.0718988114653693e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.2425870082676452e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 97,
"real_time": 7.3375041481376309e+06,
"cpu_time": 1.3683975597937489e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5730034794619665e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 97,
"real_time": 7.3268253442629715e+06,
"cpu_time": 1.3688205484536693e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5796686045305681e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 97,
"real_time": 7.3317209757941281e+06,
"cpu_time": 1.3665614762885526e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5766106089935570e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 97,
"real_time": 7.3285191751939738e+06,
"cpu_time": 1.3712114690721728e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5786101117913599e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 97,
"real_time": 7.3281776870495267e+06,
"cpu_time": 1.3684944742268862e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5788234719387236e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.3305494660876468e+06,
"cpu_time": 1.3686971055670058e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5773432553432350e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time_median",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.3285191751939729e+06,
"cpu_time": 1.3684944742268864e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.5786101117913599e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.2824215596425374e+03,
"cpu_time": 1.6604940175348103e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6727158772753980e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.8418834487833956e-04,
"cpu_time": 1.2131931972245407e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.8390112521176495e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 49,
"real_time": 1.4500217474236781e+07,
"cpu_time": 2.6617099428570013e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6281281035429630e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 49,
"real_time": 1.2378869217117222e+07,
"cpu_time": 2.5805156020408280e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 5.4212434773285570e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 49,
"real_time": 1.4483005910807727e+07,
"cpu_time": 2.6558464081633747e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6336281579448242e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 49,
"real_time": 1.4529886047298811e+07,
"cpu_time": 2.6596021918368597e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6186779291690264e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 49,
"real_time": 1.4496674533097111e+07,
"cpu_time": 2.6568231816327170e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6292592033286591e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4077730636511531e+07,
"cpu_time": 2.6428994653061565e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.7861873742628059e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time_median",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4496674533097113e+07,
"cpu_time": 2.6568231816327170e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6292592033286591e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.4984627733960398e+05,
"cpu_time": 3.4950160016930418e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5504899894713932e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.7471547926632028e-02,
"cpu_time": 1.3224173100690288e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.4182009851176345e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 25,
"real_time": 2.7992481440305710e+07,
"cpu_time": 4.9991184800001070e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7947777793912573e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 25,
"real_time": 2.8055348768830299e+07,
"cpu_time": 5.0125176679998733e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7840334870160980e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 25,
"real_time": 2.8017396703362465e+07,
"cpu_time": 5.0066055360002793e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7905138875337429e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 25,
"real_time": 2.8030715137720108e+07,
"cpu_time": 4.9980486320000641e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7882377363746653e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 25,
"real_time": 2.6444602087140083e+07,
"cpu_time": 4.8867392880001716e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 5.0754300464694691e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7708108827471741e+07,
"cpu_time": 4.9806059208000995e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8465985873570471e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time_median",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8017396703362472e+07,
"cpu_time": 4.9991184800001070e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.7905138875337429e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.0668707081931294e+05,
"cpu_time": 5.2802100751887984e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2797959513147898e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.5504702439982273e-02,
"cpu_time": 1.0601541577777688e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6406064547068044e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 10,
"real_time": 5.4515822976827621e+07,
"cpu_time": 9.4048266499999046e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9239916292578135e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 10,
"real_time": 5.4455584287643433e+07,
"cpu_time": 9.4086675600010484e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9294385417311726e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 10,
"real_time": 4.9163064733147621e+07,
"cpu_time": 9.0780930300002187e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.4601041952335920e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 10,
"real_time": 5.4360303655266762e+07,
"cpu_time": 9.3987927200009838e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9380786704636507e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 10,
"real_time": 5.4580578207969666e+07,
"cpu_time": 9.4206901100005776e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9181497304256115e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3415070772171028e+07,
"cpu_time": 9.3422140140005469e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.0339525534223680e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time_median",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4455584287643433e+07,
"cpu_time": 9.4048266499999046e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9294385417311726e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3783267192510259e+06,
"cpu_time": 1.4786476741288612e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3833899206220707e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.4525387402278266e-02,
"cpu_time": 1.5827593672259183e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.7346292904602495e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 1.0663972888141870e+08,
"cpu_time": 1.8139289362500221e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0344362052625809e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 9.3293572776019573e+07,
"cpu_time": 1.7877007449999383e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.7546398537970743e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 1.0673420876264572e+08,
"cpu_time": 1.8156231925000554e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0299797808394051e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 9.3309409916400909e+07,
"cpu_time": 1.7753615525001010e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.7536631351650496e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 1.0662806872278452e+08,
"cpu_time": 1.8164014887500456e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0349867387711601e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0132099781185389e+08,
"cpu_time": 1.8018031830000323e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.3215411427670546e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time_median",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0662806872278452e+08,
"cpu_time": 1.8139289362500221e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0349867387711601e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.3208921579662086e+06,
"cpu_time": 1.9034019979196347e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9492233703851557e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.2254441982111159e-02,
"cpu_time": 1.0563872990558484e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.4212023630652019e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.8973470851778984e+08,
"cpu_time": 3.0833785849998206e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.6591744988994684e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.8971751257777214e+08,
"cpu_time": 3.0700468399999183e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.6596874448258114e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.9149832427501678e+08,
"cpu_time": 3.0900815349997401e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.6070559785054073e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.8973119184374809e+08,
"cpu_time": 3.0711257175002515e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.6592793918897276e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.8985195085406303e+08,
"cpu_time": 3.0659702900001663e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.6556796976259289e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9010673761367801e+08,
"cpu_time": 3.0761205934999800e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.6481754023492699e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time_median",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8973470851778984e+08,
"cpu_time": 3.0711257175002515e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.6591744988994684e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7980223950397607e+05,
"cpu_time": 1.0154484934464868e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3043042851512469e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.1019179503707925e-03,
"cpu_time": 3.3010685458567130e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0797321630500491e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 385,
"real_time": 1.8328108072247624e+06,
"cpu_time": 2.0716483844155362e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2348187733583660e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 385,
"real_time": 1.8308890198792827e+06,
"cpu_time": 2.0685386753248405e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2371645443971609e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 385,
"real_time": 1.8272812022410284e+06,
"cpu_time": 2.0693189480520138e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2415816432503941e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 385,
"real_time": 1.8306222357242913e+06,
"cpu_time": 2.0687409272727857e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2374905756453928e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 385,
"real_time": 1.8344249327435738e+06,
"cpu_time": 2.0729901480521008e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2328523380207247e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8312056395625877e+06,
"cpu_time": 2.0702474166234557e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2367815749344076e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time_median",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8308890198792827e+06,
"cpu_time": 2.0693189480520138e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 2.2371645443971609e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6824535486578861e+03,
"cpu_time": 1.9708277019654311e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2780137358977577e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4648565353362676e-03,
"cpu_time": 9.5197689229813078e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4655046217438032e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 385,
"real_time": 1.8341784659348272e+06,
"cpu_time": 2.0745803506492670e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4663047528609913e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 385,
"real_time": 1.8296249162076139e+06,
"cpu_time": 2.0693757558443726e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4774204414422316e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 385,
"real_time": 1.8254973282531060e+06,
"cpu_time": 2.0701001792209449e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4875442287495779e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 385,
"real_time": 1.8303534628894459e+06,
"cpu_time": 2.0700816233766561e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4756382666481724e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 385,
"real_time": 1.8351534470143218e+06,
"cpu_time": 2.0740282233764329e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4639318926315745e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8309615240598631e+06,
"cpu_time": 2.0716332264935351e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4741679164665099e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time_median",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8303534628894459e+06,
"cpu_time": 2.0701001792209451e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 4.4756382666481724e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8708728936354623e+03,
"cpu_time": 2.4635051634478723e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.4640385736242042e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1141202820321547e-03,
"cpu_time": 1.1891608668671643e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1152622678271009e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 384,
"real_time": 1.8381891872725950e+06,
"cpu_time": 2.0781362369793516e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.9131195599674303e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 384,
"real_time": 1.8323820729809387e+06,
"cpu_time": 2.0721786510418856e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.9413666732431687e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 384,
"real_time": 1.8283316008478322e+06,
"cpu_time": 2.0727902916665524e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.9611753099943288e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 384,
"real_time": 1.8334549618354384e+06,
"cpu_time": 2.0725880651042417e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.9361344243756477e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 384,
"real_time": 1.8388720587078447e+06,
"cpu_time": 2.0783460572918837e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.9098096425005533e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8342459763289304e+06,
"cpu_time": 2.0748078604167835e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.9323211220162269e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time_median",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8334549618354384e+06,
"cpu_time": 2.0727902916665524e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 8.9361344243756477e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.3597370239159118e+03,
"cpu_time": 3.1427593167982841e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1239080316607698e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3768551656531437e-03,
"cpu_time": 1.5147230626777039e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3777784101668702e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 384,
"real_time": 1.8399133163976937e+06,
"cpu_time": 2.0832328046873629e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7809534670989502e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 384,
"real_time": 1.8353508168994875e+06,
"cpu_time": 2.0780472161456842e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7853807401985392e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 384,
"real_time": 1.8315382698119720e+06,
"cpu_time": 2.0792235624999360e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7890972053433534e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 384,
"real_time": 1.8357099532977373e+06,
"cpu_time": 2.0789347135418504e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7850314501555298e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 384,
"real_time": 1.8394078672940850e+06,
"cpu_time": 2.0827606692709702e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7814428535746306e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8363840447401956e+06,
"cpu_time": 2.0804397932291608e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7843811432742007e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time_median",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8357099532977373e+06,
"cpu_time": 2.0792235624999360e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.7850314501555298e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4133105251505285e+03,
"cpu_time": 2.3799309737715616e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3183521817829627e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8587127975365472e-03,
"cpu_time": 1.1439557066333290e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8596655732945285e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 384,
"real_time": 1.8431266142708107e+06,
"cpu_time": 2.0910555546874339e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5556971231695749e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 384,
"real_time": 1.8364182597376080e+06,
"cpu_time": 2.0847128229168160e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5686859272115894e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 384,
"real_time": 1.8323303315241903e+06,
"cpu_time": 2.0854434635418549e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5766476640423834e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 384,
"real_time": 1.8370261755270197e+06,
"cpu_time": 2.0849235286458286e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5675049638962574e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 384,
"real_time": 1.8440961879377936e+06,
"cpu_time": 2.0925736119791577e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5538276380955622e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8385995137994848e+06,
"cpu_time": 2.0877417963542182e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5644726632830739e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time_median",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8370261755270199e+06,
"cpu_time": 2.0854434635418549e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 3.5675049638962574e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9306179700101729e+03,
"cpu_time": 3.7658691959323405e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.5590761705499026e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.6817248307767698e-03,
"cpu_time": 1.8038002604098854e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6817644778191316e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 383,
"real_time": 1.8348281711200736e+06,
"cpu_time": 2.0997648015664727e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.1435572040507138e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 383,
"real_time": 1.8435429801280529e+06,
"cpu_time": 2.1046466031329297e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.1097881314866722e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 383,
"real_time": 1.8391118442801414e+06,
"cpu_time": 2.0996039268930103e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.1269183768050686e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 383,
"real_time": 1.8412210985330632e+06,
"cpu_time": 2.1040429373366167e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.1187539673767388e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 383,
"real_time": 1.8350228210716620e+06,
"cpu_time": 2.0996756788511332e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.1427994515868366e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8387453830265987e+06,
"cpu_time": 2.1015467895560325e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.1283634262612060e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time_median",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8391118442801412e+06,
"cpu_time": 2.0997648015664723e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 7.1269183768050686e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8236898309573144e+03,
"cpu_time": 2.5637301800813179e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4821615588811497e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0795102281445143e-03,
"cpu_time": 1.2199253391940541e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0792452211692812e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 381,
"real_time": 1.8477790429134024e+06,
"cpu_time": 2.1281455118111172e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4186977658685654e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 381,
"real_time": 1.8517013654947584e+06,
"cpu_time": 2.1320566062990366e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4156926429114416e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 381,
"real_time": 1.8488822253255951e+06,
"cpu_time": 2.1287681207349505e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4178512639107418e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 381,
"real_time": 1.8484081214448449e+06,
"cpu_time": 2.1288542440944300e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4182149329396474e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 381,
"real_time": 1.8477890995854214e+06,
"cpu_time": 2.1282925590553400e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4186900445446715e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8489119709528047e+06,
"cpu_time": 2.1292234083989752e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4178293300350139e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time_median",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8484081214448449e+06,
"cpu_time": 2.1287681207349510e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.4182149329396474e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6263330753102855e+03,
"cpu_time": 1.6123679042637109e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2459547363367579e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.7961628290620178e-04,
"cpu_time": 7.5725633012653059e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7877624615509159e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 377,
"real_time": 1.8698023832884841e+06,
"cpu_time": 2.1872669496020530e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.8039754611817163e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 377,
"real_time": 1.8673616203458470e+06,
"cpu_time": 2.1871991591512356e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.8076404392572796e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 377,
"real_time": 1.8628629490199550e+06,
"cpu_time": 2.1853347586205378e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.8144206758517897e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 377,
"real_time": 1.8653164291785243e+06,
"cpu_time": 2.1845858992044027e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.8107188238882005e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 377,
"real_time": 1.8677419249619299e+06,
"cpu_time": 2.1869341803715876e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.8070687550191736e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8666170613589485e+06,
"cpu_time": 2.1862641893899636e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.8087648310396320e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time_median",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8673616203458472e+06,
"cpu_time": 2.1869341803715876e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.8076404392572796e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6339592595213498e+03,
"cpu_time": 1.2256716433846289e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9650240533948847e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4110871019274599e-03,
"cpu_time": 5.6062375687845379e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4116611008431336e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 377,
"real_time": 1.8681200551281655e+06,
"cpu_time": 2.2687736923078303e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.6130011404864478e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 377,
"real_time": 1.8639018702313344e+06,
"cpu_time": 2.2672884376656031e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.6257038889598739e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 377,
"real_time": 1.8667908262959199e+06,
"cpu_time": 2.2662228832890429e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.6169978190892494e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 377,
"real_time": 1.8628412919873691e+06,
"cpu_time": 2.2673196631300780e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.6289067915245128e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 377,
"real_time": 1.8682278622780489e+06,
"cpu_time": 2.2675687241379111e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.6126772390676403e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8659763811841682e+06,
"cpu_time": 2.2674346801060932e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.6194573758255446e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time_median",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8667908262959202e+06,
"cpu_time": 2.2673196631300785e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 5.6169978190892494e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4728630116158683e+03,
"cpu_time": 9.1021820952802477e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.4500508717726218e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3252381094162424e-03,
"cpu_time": 4.0143084055035955e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3257598329372768e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 369,
"real_time": 1.9095951701050024e+06,
"cpu_time": 2.4664495149051659e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0982181107447422e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 369,
"real_time": 1.9109276601941220e+06,
"cpu_time": 2.4651477750676051e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0974523231229801e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 369,
"real_time": 1.9118117900794942e+06,
"cpu_time": 2.4674042276423858e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0969447991074474e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 369,
"real_time": 1.9086663908423570e+06,
"cpu_time": 2.4641436937668803e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0987525164491727e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 369,
"real_time": 1.9085740350025294e+06,
"cpu_time": 2.4647235880761361e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0988056850502112e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9099150092447014e+06,
"cpu_time": 2.4655737598916348e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0980346868949108e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time_median",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9095951701050024e+06,
"cpu_time": 2.4651477750676055e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.0982181107447422e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4215129604042727e+03,
"cpu_time": 1.3291823936055871e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.1706252588158764e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.4428074208727590e-04,
"cpu_time": 5.3909658483062629e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.4411358369026270e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 350,
"real_time": 2.0065896409297630e+06,
"cpu_time": 2.8746787628571317e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0902649522582750e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 350,
"real_time": 2.0043427853046786e+06,
"cpu_time": 2.8733051257141340e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0926081260907812e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 350,
"real_time": 2.0026024241399553e+06,
"cpu_time": 2.8732762142856573e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0944267066895721e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 350,
"real_time": 2.0070120392899427e+06,
"cpu_time": 2.8735481828571861e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0898250323819160e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 350,
"real_time": 2.0055999224340275e+06,
"cpu_time": 2.8736421000001295e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0912964510437987e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0052293624196735e+06,
"cpu_time": 2.8736900771428477e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0916842536928689e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time_median",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0055999224340278e+06,
"cpu_time": 2.8735481828571856e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.0912964510437987e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7925144964453270e+03,
"cpu_time": 5.7432684741149103e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8705680942430296e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.9391993257186930e-04,
"cpu_time": 1.9985691984659415e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.9428798392517475e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 341,
"real_time": 2.0500296864063202e+06,
"cpu_time": 3.6183503900295170e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0919446462773614e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 341,
"real_time": 2.0528740206558551e+06,
"cpu_time": 3.6185388651026520e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0862751029018307e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 341,
"real_time": 2.0580752267941963e+06,
"cpu_time": 3.6252006363635818e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0759481921691899e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 341,
"real_time": 2.0502661918139744e+06,
"cpu_time": 3.6177323079180527e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0914726260877242e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 341,
"real_time": 2.0465908354951227e+06,
"cpu_time": 3.6186279501463631e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0988202695486913e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0515671922330938e+06,
"cpu_time": 3.6196900299120336e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0888921673969598e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time_median",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0502661918139749e+06,
"cpu_time": 3.6185388651026515e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.0914726260877242e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.2685760802226723e+03,
"cpu_time": 3.1002938457600371e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4991047761231884e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0806416169954463e-03,
"cpu_time": 8.5650810432388912e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0785837405768088e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 195,
"real_time": 3.5908633544563483e+06,
"cpu_time": 6.6031943846155629e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6721956097769823e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 195,
"real_time": 3.6105508653399274e+06,
"cpu_time": 6.6226114820513735e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6467191920921612e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 195,
"real_time": 3.5892773156937882e+06,
"cpu_time": 6.5987640153841702e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6742601711612396e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 195,
"real_time": 3.5935004492505239e+06,
"cpu_time": 6.5983230307694655e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6687669131916008e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 195,
"real_time": 3.5943423588879597e+06,
"cpu_time": 6.6113076564102490e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6676733390501623e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5957068687257096e+06,
"cpu_time": 6.6068401138461642e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6659230450544300e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time_median",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5935004492505239e+06,
"cpu_time": 6.6031943846155629e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 4.6687669131916008e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.5421483267262538e+03,
"cpu_time": 1.0243905550493399e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1054318426794119e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3756520313218759e-03,
"cpu_time": 1.5504999930337228e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3691600397291093e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 106,
"real_time": 7.2510257793836435e+06,
"cpu_time": 1.3545328933961207e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6275427809680490e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 106,
"real_time": 7.2560748085379601e+06,
"cpu_time": 1.3479260905659482e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6243227757957668e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 106,
"real_time": 7.2422000702540828e+06,
"cpu_time": 1.3489682811322346e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6331821372649250e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 106,
"real_time": 7.2552945051904554e+06,
"cpu_time": 1.3526208141510289e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6248201194307241e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 106,
"real_time": 7.2609805633788398e+06,
"cpu_time": 1.3521699499999570e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6211984327893190e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.2531151453489978e+06,
"cpu_time": 1.3512436058490580e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6262132492497568e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time_median",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.2552945051904563e+06,
"cpu_time": 1.3521699499999572e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 4.6248201194307241e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.0512114346917388e+03,
"cpu_time": 2.7275098064631235e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4998927614599885e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.7216317311786668e-04,
"cpu_time": 2.0185181966128778e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.7269462495913823e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 49,
"real_time": 1.4362072933237163e+07,
"cpu_time": 2.6206644102038417e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6726447019144812e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 49,
"real_time": 1.4397576755406905e+07,
"cpu_time": 2.6246826244900782e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6611221554903507e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 49,
"real_time": 1.4368730939316506e+07,
"cpu_time": 2.6204028367346283e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6704795491975603e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 49,
"real_time": 1.4353403498475648e+07,
"cpu_time": 2.6196851673473377e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6754669724938097e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 49,
"real_time": 1.4432871714234352e+07,
"cpu_time": 2.6308722387753103e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6497235843795519e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4382931168134117e+07,
"cpu_time": 2.6232614555102389e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6658873926951504e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time_median",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4368730939316507e+07,
"cpu_time": 2.6206644102038421e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 4.6704795491975603e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2469782522715395e+04,
"cpu_time": 4.6810769551008379e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0517766674209882e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2575219295113730e-03,
"cpu_time": 1.7844492569614424e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2541835644547172e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 25,
"real_time": 2.7870135307312012e+07,
"cpu_time": 4.9957665559995800e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8158262067994566e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 25,
"real_time": 2.7095507606863976e+07,
"cpu_time": 4.8344358919994190e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.9535048373110847e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 25,
"real_time": 2.7820502817630768e+07,
"cpu_time": 4.9917401160000734e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8244177641153851e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 25,
"real_time": 2.7901194319128990e+07,
"cpu_time": 4.9941238720002726e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8104653322306223e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 25,
"real_time": 2.7906442582607269e+07,
"cpu_time": 4.9950326520001911e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8095606454565220e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7718756526708603e+07,
"cpu_time": 4.9622198175999083e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8427549571826143e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time_median",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7870135307312012e+07,
"cpu_time": 4.9941238720002733e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 4.8158262067994566e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5007737098481075e+05,
"cpu_time": 7.1449482337677642e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2192098384280294e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2629620331182288e-02,
"cpu_time": 1.4398693521045149e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2842297191196722e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 10,
"real_time": 5.4403833299875259e+07,
"cpu_time": 9.3927522900003165e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9341276104640865e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 10,
"real_time": 5.3257106617093086e+07,
"cpu_time": 9.0991950300008282e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 5.0403687517234468e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 10,
"real_time": 5.4294505715370178e+07,
"cpu_time": 9.3782965700006574e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9440629850693874e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 10,
"real_time": 5.4274409636855125e+07,
"cpu_time": 9.3694914499997139e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9458936135109701e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 10,
"real_time": 5.4221912845969200e+07,
"cpu_time": 9.3641491300013512e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9506821487939301e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4090353623032570e+07,
"cpu_time": 9.3207768940005749e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9630270219123640e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time_median",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4274409636855125e+07,
"cpu_time": 9.3694914499997139e+07,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 4.9458936135109701e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.7048714192596741e+05,
"cpu_time": 1.2434000968306987e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3653474722462125e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.6981709382951081e-03,
"cpu_time": 1.3340090756072356e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7957358542935099e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 1.0617277398705482e+08,
"cpu_time": 1.8065783187500983e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0565779892447596e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 1.0485049057751894e+08,
"cpu_time": 1.7588086662502179e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.1203471633075113e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 1.0667163506150246e+08,
"cpu_time": 1.8086895812498939e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0329303726380720e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 1.0466591082513332e+08,
"cpu_time": 1.7543277575001070e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.1293769649313717e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 1.0620841477066278e+08,
"cpu_time": 1.8069827150000605e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0548811330935726e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0571384504437447e+08,
"cpu_time": 1.7870774077500755e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0788227246430578e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time_median",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0617277398705482e+08,
"cpu_time": 1.8065783187500983e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.0565779892447596e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9667772482566908e+05,
"cpu_time": 2.7907230995780118e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3168698871199720e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.4821219439069635e-03,
"cpu_time": 1.5616128811630620e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4997451597867372e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 2.0105309784412384e+08,
"cpu_time": 3.1200736925001138e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.3405883098228626e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 2.0107398554682732e+08,
"cpu_time": 3.1188340425001115e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.3400335258682213e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 2.0187630504369736e+08,
"cpu_time": 3.1252353025001866e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.3188105645562611e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 2.0105969905853271e+08,
"cpu_time": 3.1281694099999416e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.3404129670332947e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 2.0167966559529305e+08,
"cpu_time": 3.1273674524999249e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.3239964516534767e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0134855061769485e+08,
"cpu_time": 3.1239359800000560e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.3327683637868233e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time_median",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0107398554682732e+08,
"cpu_time": 3.1252353025001866e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 5.3400335258682213e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9820704580748687e+05,
"cpu_time": 4.2524170485393441e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0537322913332399e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPURdHost_coarse/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9777000856766626e-03,
"cpu_time": 1.3612369381971994e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9759573629501877e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_numa": NaN
}
]
}