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

1698 lines
58 KiB
JSON

{
"context": {
"date": "2023-10-09T16:57:39-04:00",
"host_name": "frontier01024",
"executable": "/lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope",
"num_cpus": 128,
"mhz_per_cpu": 1881,
"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": [0.74,7.12,7.18],
"library_build_type": "release"
},
"benchmarks": [
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52418,
"real_time": 1.3358390169694165e+04,
"cpu_time": 2.0462372448395596e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0662377337147182e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52418,
"real_time": 1.3356491396170082e+04,
"cpu_time": 2.0460801575794569e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0666736334472620e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52418,
"real_time": 1.3361756165410265e+04,
"cpu_time": 2.0413873516730895e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0654653095701319e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52418,
"real_time": 1.3352849635545979e+04,
"cpu_time": 2.0423873764737313e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0675100160614675e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52418,
"real_time": 1.3351372984195657e+04,
"cpu_time": 2.0422418844671676e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0678492802564454e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3356172070203233e+04,
"cpu_time": 2.0436668030066015e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0667471946100050e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time_median",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3356491396170084e+04,
"cpu_time": 2.0423873764737313e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0666736334472620e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.1914750407985126e+00,
"cpu_time": 2.3073076834768418e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.6237729607467365e+04,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.1382307885576189e-04,
"cpu_time": 1.1290038474385245e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1381044311905147e-04,
"own_numa": NaN,
"rd_gpu": NaN
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52340,
"real_time": 1.3375127635009039e+04,
"cpu_time": 2.0505235364921678e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1248013653026080e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52340,
"real_time": 1.3377205640093345e+04,
"cpu_time": 2.0507505464272057e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1238499432552922e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52340,
"real_time": 1.3370425115816619e+04,
"cpu_time": 2.0464759705769950e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1269555223859179e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52340,
"real_time": 1.3372914165293721e+04,
"cpu_time": 2.0560072888803952e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1258151355374908e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52340,
"real_time": 1.3373014663519929e+04,
"cpu_time": 2.0565893714176538e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1257691000271237e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3373737443946531e+04,
"cpu_time": 2.0520693427588834e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1254382133016860e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time_median",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3373014663519929e+04,
"cpu_time": 2.0507505464272057e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1257691000271237e+08,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5560092295271906e+00,
"cpu_time": 4.2235243538726742e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1706793309869274e+05,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9112153504136114e-04,
"cpu_time": 2.0581781842685686e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9111764582732064e-04,
"own_numa": NaN,
"rd_gpu": NaN
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52093,
"real_time": 1.3435814949350908e+04,
"cpu_time": 2.0616280517535961e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2194273337168522e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52093,
"real_time": 1.3435559982769335e+04,
"cpu_time": 2.0627498397097490e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2194504747857137e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52093,
"real_time": 1.3435093526082268e+04,
"cpu_time": 2.0550394045265166e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2194928132203071e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52093,
"real_time": 1.3438097386303059e+04,
"cpu_time": 2.0634596759641423e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2192202161519969e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52093,
"real_time": 1.3435084102712914e+04,
"cpu_time": 2.0628576948918344e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2194936685726902e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3435929989443699e+04,
"cpu_time": 2.0611469333691679e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2194169012895119e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time_median",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3435559982769337e+04,
"cpu_time": 2.0627498397097494e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2194504747857137e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.2512936883410561e+00,
"cpu_time": 3.4777210746793358e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1355273805593593e+05,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.3130411465687082e-05,
"cpu_time": 1.6872747004963030e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.3120521731210958e-05,
"own_numa": NaN,
"rd_gpu": NaN
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 50970,
"real_time": 1.3730673399225387e+04,
"cpu_time": 2.0828173337257205e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.3864816420328374e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 50970,
"real_time": 1.3730441031465822e+04,
"cpu_time": 2.0821078359819559e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.3865220297662778e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 50970,
"real_time": 1.3730653643990508e+04,
"cpu_time": 2.0806441553855213e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.3864850756279593e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 50970,
"real_time": 1.3731015816575458e+04,
"cpu_time": 2.0824535471846157e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.3864221291220102e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 50970,
"real_time": 1.3730094764492513e+04,
"cpu_time": 2.0814677104178867e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.3865822168060732e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3730575731149938e+04,
"cpu_time": 2.0818981165391404e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.3864986186710315e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time_median",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3730653643990508e+04,
"cpu_time": 2.0821078359819556e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.3864850756279593e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3865817261176245e-01,
"cpu_time": 8.5952220550092662e+00,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.8862138595195465e+04,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4664528221017263e-05,
"cpu_time": 4.1285507617911689e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4664643899091801e-05,
"own_numa": NaN,
"rd_gpu": NaN
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 49187,
"real_time": 1.4229580193373125e+04,
"cpu_time": 2.1638558826519231e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.6056172500802832e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 49187,
"real_time": 1.4231293878500532e+04,
"cpu_time": 2.1656113464939910e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.6050626569525347e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 49187,
"real_time": 1.4233649316842781e+04,
"cpu_time": 2.1648352959115207e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.6043005936960077e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 49187,
"real_time": 1.4231573812434501e+04,
"cpu_time": 2.1642227661780566e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.6049720757334290e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 49187,
"real_time": 1.4233639008730754e+04,
"cpu_time": 2.1635782157887294e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.6043039281662941e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4231947241976337e+04,
"cpu_time": 2.1644207014048443e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.6048513009257097e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time_median",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4231573812434499e+04,
"cpu_time": 2.1642227661780566e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.6049720757334290e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7268747952230747e+00,
"cpu_time": 8.1509277349318072e+00,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.5875563231165730e+05,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2133791433190205e-04,
"cpu_time": 3.7658703456501530e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2134064615709330e-04,
"own_numa": NaN,
"rd_gpu": NaN
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 45925,
"real_time": 1.5234444857167735e+04,
"cpu_time": 2.3655564746869877e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 8.6036610607659416e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 45925,
"real_time": 1.5238500404311129e+04,
"cpu_time": 2.3678326663037638e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 8.6013712978554230e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 45925,
"real_time": 1.5239364961775815e+04,
"cpu_time": 2.3689270898203635e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 8.6008833260940838e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 45925,
"real_time": 1.5239027913773058e+04,
"cpu_time": 2.3616169145345641e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 8.6010735554553928e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 45925,
"real_time": 1.5238414761358836e+04,
"cpu_time": 2.3608568600979812e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 8.6014196392900963e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5237950579677316e+04,
"cpu_time": 2.3649580010887323e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 8.6016817758921871e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time_median",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5238500404311129e+04,
"cpu_time": 2.3655564746869873e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 8.6013712978554230e+09,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9980607697744326e+00,
"cpu_time": 3.6179328659096058e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1280663764867738e+06,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3112398280377833e-04,
"cpu_time": 1.5298085057933602e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3114486281605878e-04,
"own_numa": NaN,
"rd_gpu": NaN
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 37024,
"real_time": 1.8903840236089778e+04,
"cpu_time": 2.9221954380942087e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3867235266807562e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 37024,
"real_time": 1.8908442559862226e+04,
"cpu_time": 2.9241503268150409e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3863859975250658e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 37024,
"real_time": 1.8903118840240546e+04,
"cpu_time": 2.9252199114088147e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3867764479264318e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 37024,
"real_time": 1.8898801074573792e+04,
"cpu_time": 2.9261104661840949e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3870932815557556e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 37024,
"real_time": 1.8904247278792791e+04,
"cpu_time": 2.9266923428046783e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3866936680101461e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8903689997911828e+04,
"cpu_time": 2.9248736970613681e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3867345843396311e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time_median",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8903840236089782e+04,
"cpu_time": 2.9252199114088151e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.3867235266807562e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4332117268321070e+00,
"cpu_time": 1.7785717703593466e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5185583198012309e+06,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8161595578489452e-04,
"cpu_time": 6.0808498231779530e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8161790642876185e-04,
"own_numa": NaN,
"rd_gpu": NaN
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 23887,
"real_time": 2.9311693284488039e+04,
"cpu_time": 4.4401035249298569e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.7886650044794819e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 23887,
"real_time": 2.9314942598556816e+04,
"cpu_time": 4.4156121907313784e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.7884667460539761e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 23887,
"real_time": 2.9294042889368237e+04,
"cpu_time": 4.3973727550550357e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.7897427199790207e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 23887,
"real_time": 2.9288786251919788e+04,
"cpu_time": 4.3989489973625939e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.7900639360418514e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 23887,
"real_time": 2.9298136159463975e+04,
"cpu_time": 4.3979957257085392e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.7894926733441467e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9301520236759370e+04,
"cpu_time": 4.4100066387574807e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.7892862159796955e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time_median",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9298136159463978e+04,
"cpu_time": 4.3989489973625939e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.7894926733441467e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1326603301115782e+01,
"cpu_time": 1.8462077707425183e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.9161111270192880e+06,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.8655343509809843e-04,
"cpu_time": 4.1864058763927108e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8652905640546053e-04,
"own_numa": NaN,
"rd_gpu": NaN
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 14022,
"real_time": 4.9914346831678551e+04,
"cpu_time": 7.6438336257309769e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 2.1007507190988876e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 14022,
"real_time": 4.9917118198893630e+04,
"cpu_time": 7.6495473826843867e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 2.1006340867314747e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 14022,
"real_time": 4.9931645792176256e+04,
"cpu_time": 7.6462936670945623e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 2.1000229080458241e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 14022,
"real_time": 4.9923556309128930e+04,
"cpu_time": 7.6362129938667829e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 2.1003631902887081e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 14022,
"real_time": 4.9924856206020559e+04,
"cpu_time": 7.6365696762231004e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 2.1003085029888374e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9922304667579599e+04,
"cpu_time": 7.6424914691199621e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 2.1004158814307465e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time_median",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9923556309128930e+04,
"cpu_time": 7.6438336257309755e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 2.1003631902887081e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.8110236250369214e+00,
"cpu_time": 5.9272863232660242e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8655906054564039e+06,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3643247583199254e-04,
"cpu_time": 7.7556989722731798e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3642967713158030e-04,
"own_numa": NaN,
"rd_gpu": NaN
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 7691,
"real_time": 9.1018540574250248e+04,
"cpu_time": 1.3152713223247961e+05,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3040931954838425e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 7691,
"real_time": 9.1014194496523560e+04,
"cpu_time": 1.3160289910284677e+05,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3042032197297581e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 7691,
"real_time": 9.1022912875129841e+04,
"cpu_time": 1.3161464269925884e+05,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3039825179809250e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 7691,
"real_time": 9.1043195351036164e+04,
"cpu_time": 1.3161925939409694e+05,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3034692399733887e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 7691,
"real_time": 9.1029068535830927e+04,
"cpu_time": 1.3161493446885981e+05,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3038267157205036e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1025582366554154e+04,
"cpu_time": 1.3159577357950842e+05,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3039149777776836e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time_median",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1022912875129856e+04,
"cpu_time": 1.3161464269925884e+05,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3039825179809250e+10,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1277934269366469e+01,
"cpu_time": 3.8849628167120308e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8542907817669874e+06,
"own_numa": 0.0000000000000000e+00,
"rd_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_mapped_GPURdHost/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2389851266153898e-04,
"cpu_time": 2.9521942164539107e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2388872025651687e-04,
"own_numa": NaN,
"rd_gpu": NaN
}