Files
frontier-gpu-bandwidth/results/implicit_managed_GPUWrGPU_coarse.json
2023-10-10 13:23:18 -04:00

25273 lines
894 KiB
JSON

{
"context": {
"date": "2023-10-09T17:57:28-04:00",
"host_name": "frontier08444",
"executable": "/lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope",
"num_cpus": 128,
"mhz_per_cpu": 1796,
"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": [2.09,2.66,9.64],
"library_build_type": "release"
},
"benchmarks": [
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52604,
"real_time": 1.3319161775119794e+04,
"cpu_time": 2.5218342863660549e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0752686011002070e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52604,
"real_time": 1.3305676242048889e+04,
"cpu_time": 2.5182800395407201e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0783854390322018e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52604,
"real_time": 1.3306235573199010e+04,
"cpu_time": 2.5293309672268264e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0782560382818043e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52604,
"real_time": 1.3313799540920885e+04,
"cpu_time": 2.5472604307657235e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0765071889588398e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52604,
"real_time": 1.3306945326532652e+04,
"cpu_time": 2.5362465287810821e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0780918531565660e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3310363691564247e+04,
"cpu_time": 2.5305904505360813e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0773018241059238e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time_median",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3306945326532650e+04,
"cpu_time": 2.5293309672268264e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0780918531565660e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.9141799593223716e+00,
"cpu_time": 1.1615532596723934e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3669612927950814e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):12/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.4432895271453928e-04,
"cpu_time": 4.5900483795247443e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4420774136844278e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52591,
"real_time": 1.3303327701800850e+04,
"cpu_time": 2.5685824209465496e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1578577808701670e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52591,
"real_time": 1.3308652240537440e+04,
"cpu_time": 2.5694487592934151e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1553941390455806e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52591,
"real_time": 1.3307618157962650e+04,
"cpu_time": 2.5765962693236481e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1558724504717577e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52591,
"real_time": 1.3304267059251250e+04,
"cpu_time": 2.5609796790325330e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1574230008436394e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52591,
"real_time": 1.3302335702590970e+04,
"cpu_time": 2.5635055712954676e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1583169927100837e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3305240172428636e+04,
"cpu_time": 2.5678225399783223e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1569728727882469e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time_median",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3304267059251250e+04,
"cpu_time": 2.5685824209465496e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1574230008436394e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7539726785078615e+00,
"cpu_time": 6.0345111547607019e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2743297657984766e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):13/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.0698406363341680e-04,
"cpu_time": 2.3500499200430121e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0697342543615652e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52610,
"real_time": 1.3311058479971016e+04,
"cpu_time": 2.6004237901539604e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2308562857456303e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52610,
"real_time": 1.3306710123221137e+04,
"cpu_time": 2.5821369834632205e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2312585040391598e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52610,
"real_time": 1.3309494213981194e+04,
"cpu_time": 2.6028741551035906e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2310009483898447e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52610,
"real_time": 1.3301689696182539e+04,
"cpu_time": 2.5502100038015586e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2317232151868689e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52610,
"real_time": 1.3304101858946815e+04,
"cpu_time": 2.5788528948869014e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2314998918158460e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3306610874460541e+04,
"cpu_time": 2.5828995654818464e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2312677690354698e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time_median",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3306710123221137e+04,
"cpu_time": 2.5821369834632205e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2312585040391598e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.8281146294386743e+00,
"cpu_time": 2.1163926844984059e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5422795598314935e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):14/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.8768517134486872e-04,
"cpu_time": 8.1938636437208397e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8769368036055928e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52590,
"real_time": 1.3305105829340244e+04,
"cpu_time": 2.6095209184255531e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4628139317569680e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52590,
"real_time": 1.3305670310677066e+04,
"cpu_time": 2.6090151815934612e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4627094490463581e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52590,
"real_time": 1.3309898662158424e+04,
"cpu_time": 2.6204574367750560e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4619270838750410e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52590,
"real_time": 1.3302018918613057e+04,
"cpu_time": 2.5678119680547628e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4633854605445542e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52590,
"real_time": 1.3311707294286807e+04,
"cpu_time": 2.6198353146986115e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4615925873057284e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3306880203015122e+04,
"cpu_time": 2.6053281639094890e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4624857025057302e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time_median",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3305670310677064e+04,
"cpu_time": 2.6095209184255531e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4627094490463581e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.8941055772511626e+00,
"cpu_time": 2.1667894237232744e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.2060235514463868e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):15/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.9263850863922423e-04,
"cpu_time": 8.3167619869884100e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9263209707629229e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52589,
"real_time": 1.3311737917013636e+04,
"cpu_time": 2.6368979767631947e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.9231738491665249e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52589,
"real_time": 1.3308368375146654e+04,
"cpu_time": 2.5941617961931264e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.9244203461025562e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52589,
"real_time": 1.3305373496620627e+04,
"cpu_time": 2.5969508794614816e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.9255287735173464e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52589,
"real_time": 1.3310081896698615e+04,
"cpu_time": 2.6246957253417964e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.9237863830315952e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52589,
"real_time": 1.3306398366144516e+04,
"cpu_time": 2.6042027382152137e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.9251494053224287e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3308392010324813e+04,
"cpu_time": 2.6113818231949634e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.9244117514280910e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time_median",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3308368375146654e+04,
"cpu_time": 2.6042027382152144e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.9244203461025562e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6046788777727161e+00,
"cpu_time": 1.8605475077332491e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.6377293790601939e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):16/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.9571702394639227e-04,
"cpu_time": 7.1247624196790716e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9571331288991483e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52594,
"real_time": 1.3313056014269650e+04,
"cpu_time": 2.6253008270905520e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.8453728324668636e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52594,
"real_time": 1.3309369376873476e+04,
"cpu_time": 2.6291280222078498e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.8480999578952503e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52594,
"real_time": 1.3307968962511117e+04,
"cpu_time": 2.6073490607293599e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.8491362858775158e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52594,
"real_time": 1.3309378249764339e+04,
"cpu_time": 2.6259484465908590e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.8480933925159740e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52594,
"real_time": 1.3306352453303974e+04,
"cpu_time": 2.6090782009354662e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.8503327985615425e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3309225011344510e+04,
"cpu_time": 2.6193609115108175e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.8482070534634304e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time_median",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3309369376873476e+04,
"cpu_time": 2.6253008270905520e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.8480999578952503e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4774056622765270e+00,
"cpu_time": 1.0296763603946003e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8329935862844693e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):17/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8614199250255648e-04,
"cpu_time": 3.9310213261168920e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8612459875524650e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51681,
"real_time": 1.3551560673031219e+04,
"cpu_time": 2.6843285424043625e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9344192622897621e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51681,
"real_time": 1.3549864229279214e+04,
"cpu_time": 2.6722629844623716e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9346614516885445e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51681,
"real_time": 1.3543381228191653e+04,
"cpu_time": 2.6214132834116990e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9355875433405499e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51681,
"real_time": 1.3545087871039526e+04,
"cpu_time": 2.6354748611675444e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9353436647722656e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51681,
"real_time": 1.3549848979364944e+04,
"cpu_time": 2.6721088852769793e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9346636290870762e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3547948596181313e+04,
"cpu_time": 2.6571177113445912e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9349351102356396e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time_median",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3549848979364944e+04,
"cpu_time": 2.6721088852769790e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9346636290870762e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.5132892026029303e+00,
"cpu_time": 2.7100567606817447e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0181567527848314e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):18/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5932259615992360e-04,
"cpu_time": 1.0199234866830059e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5934496336539739e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51504,
"real_time": 1.3596964597759266e+04,
"cpu_time": 2.6881258814849243e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8559194313589729e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51504,
"real_time": 1.3594353967578696e+04,
"cpu_time": 2.6535145580925739e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8566599137434517e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51504,
"real_time": 1.3594027187301357e+04,
"cpu_time": 2.6773934801180501e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8567526221350746e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51504,
"real_time": 1.3595096543920763e+04,
"cpu_time": 2.6918847157502310e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8564492595269035e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51504,
"real_time": 1.3590203726458405e+04,
"cpu_time": 2.6675664783317716e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8578376789104179e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3594129204603698e+04,
"cpu_time": 2.6756970227555103e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8567237811349648e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time_median",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3594353967578698e+04,
"cpu_time": 2.6773934801180498e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8566599137434517e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4721197546445413e+00,
"cpu_time": 1.5633005089627898e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.0143063818570115e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):19/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8185201254430845e-04,
"cpu_time": 5.8425916524467245e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8187214796577491e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51227,
"real_time": 1.3664408083870647e+04,
"cpu_time": 2.6949320026548547e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.6737755017557648e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51227,
"real_time": 1.3664886441811936e+04,
"cpu_time": 2.7261418724500887e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.6735068708039764e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51227,
"real_time": 1.3665361331699922e+04,
"cpu_time": 2.6794068459991860e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.6732402060060333e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51227,
"real_time": 1.3663284735924808e+04,
"cpu_time": 2.6703129833876676e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.6744064129980713e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51227,
"real_time": 1.3666151912743533e+04,
"cpu_time": 2.6894128428368040e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.6727963123416962e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3664818501210169e+04,
"cpu_time": 2.6920413094657200e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.6735450607811081e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time_median",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3664886441811934e+04,
"cpu_time": 2.6894128428368036e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.6735068708039764e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0721643327663730e+00,
"cpu_time": 2.1271243270095147e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0209007851250963e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):20/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.8461659236192646e-05,
"cpu_time": 7.9015292950005925e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.8463092839546242e-05,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 50517,
"real_time": 1.3843383446172982e+04,
"cpu_time": 2.7520953916503473e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.5149128882793173e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 50517,
"real_time": 1.3815204847501149e+04,
"cpu_time": 2.7252342637132224e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.5180028259800479e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 50517,
"real_time": 1.3851623912503235e+04,
"cpu_time": 2.7214600253379929e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.5140116518085620e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 50517,
"real_time": 1.3840612178927026e+04,
"cpu_time": 2.7079353049468486e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.5152162150695987e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 50517,
"real_time": 1.3869015765419288e+04,
"cpu_time": 2.7423016826018818e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.5121130695005731e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3843968030104737e+04,
"cpu_time": 2.7298053336500590e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.5148513301276196e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time_median",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3843383446172980e+04,
"cpu_time": 2.7252342637132224e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.5149128882793173e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.9525148710391694e+01,
"cpu_time": 1.7477431371988735e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1372872689847943e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):21/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4103722767874651e-03,
"cpu_time": 6.4024460486416558e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4108891258686998e-03,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 42863,
"real_time": 1.6360299394772917e+04,
"cpu_time": 3.0158223432797538e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.5637085842940451e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 42863,
"real_time": 1.6343953496099784e+04,
"cpu_time": 2.9876944310944342e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.5662725979983374e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 42863,
"real_time": 1.6352270280316396e+04,
"cpu_time": 2.9848514079742152e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.5649673886865607e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 42863,
"real_time": 1.6360866513469306e+04,
"cpu_time": 2.9902120196906417e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.5636197181530588e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 42863,
"real_time": 1.6357955367613411e+04,
"cpu_time": 3.0124403144903539e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.5640759531011850e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6355069010454361e+04,
"cpu_time": 2.9982041033058798e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.5645288484466373e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time_median",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6357955367613413e+04,
"cpu_time": 2.9902120196906413e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.5640759531011850e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.0831943474900454e+00,
"cpu_time": 1.4711332126890659e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1110181602719840e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):22/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.3308862487601734e-04,
"cpu_time": 4.9067146931957200e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3322505845272115e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 39482,
"real_time": 1.7714926408782871e+04,
"cpu_time": 3.1706114254597062e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7353332474703467e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 39482,
"real_time": 1.7720761540200441e+04,
"cpu_time": 3.1495596727622567e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7337739865016632e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 39482,
"real_time": 1.7707510511396216e+04,
"cpu_time": 3.1494350260878302e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7373164028908813e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 39482,
"real_time": 1.7730159663621245e+04,
"cpu_time": 3.1266047717947400e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7312647822409363e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 39482,
"real_time": 1.7740599708199035e+04,
"cpu_time": 3.1926349425054250e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7284805124840857e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.7722791566439966e+04,
"cpu_time": 3.1577691677219922e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7332337863175830e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time_median",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.7720761540200441e+04,
"cpu_time": 3.1495596727622567e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7337739865016632e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.2950976059287967e+01,
"cpu_time": 2.4943030754190249e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4582474113519549e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):23/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.3075260241801021e-04,
"cpu_time": 7.8989404954460610e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.3063101623012014e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 29369,
"real_time": 2.3830339467114180e+04,
"cpu_time": 3.8199409990125845e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 7.0402757053261975e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 29369,
"real_time": 2.3814132114149987e+04,
"cpu_time": 3.7792519561442066e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 7.0450671557462476e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 29369,
"real_time": 2.3840527193956808e+04,
"cpu_time": 3.7698421294562300e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 7.0372671977877893e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 29369,
"real_time": 2.3855154916492960e+04,
"cpu_time": 3.7879603016786357e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 7.0329520217873669e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 29369,
"real_time": 2.3826329507420520e+04,
"cpu_time": 3.7891303244917908e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 7.0414605803108984e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3833296639826895e+04,
"cpu_time": 3.7892251421566893e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 7.0394045321917004e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time_median",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3830339467114180e+04,
"cpu_time": 3.7879603016786350e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 7.0402757053261975e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.5448543781939838e+01,
"cpu_time": 1.8843024536868947e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5621998773926526e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):24/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.4819164614115447e-04,
"cpu_time": 4.9727909612000991e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.4809457341588855e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 19202,
"real_time": 3.6402475621909871e+04,
"cpu_time": 5.0827184095406461e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 9.2176236442019092e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 19202,
"real_time": 3.6416169226308797e+04,
"cpu_time": 5.0937231590459327e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 9.2141575330110950e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 19202,
"real_time": 3.6416209841437783e+04,
"cpu_time": 5.0891631600874280e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 9.2141472564282666e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 19202,
"real_time": 3.6425779801784782e+04,
"cpu_time": 5.0753528590771544e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 9.2117264702610156e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 19202,
"real_time": 3.6428960933663802e+04,
"cpu_time": 5.1182222268513571e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 9.2109220631084570e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6417919085021007e+04,
"cpu_time": 5.0918359629205042e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 9.2137153934021484e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time_median",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6416209841437783e+04,
"cpu_time": 5.0891631600874287e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 9.2141472564282666e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0346465114925795e+01,
"cpu_time": 1.6292350968912402e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6179632752704352e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):25/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.8410368782387079e-04,
"cpu_time": 3.1997006752683488e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8413763215924092e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 11336,
"real_time": 6.1765670340187135e+04,
"cpu_time": 7.7302944865914891e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 1.0865074989129742e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 11336,
"real_time": 6.1787648030298609e+04,
"cpu_time": 7.7190223006351662e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 1.0861210312956410e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 11336,
"real_time": 6.1777582144092652e+04,
"cpu_time": 7.7077260673959288e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 1.0862980011660612e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 11336,
"real_time": 6.1828309724881154e+04,
"cpu_time": 7.7020379146082807e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 1.0854067384118352e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 11336,
"real_time": 6.1795989701968807e+04,
"cpu_time": 7.7107684721242025e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 1.0859744187875986e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.1791039988285673e+04,
"cpu_time": 7.7139698482710141e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 1.0860615377148221e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time_median",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.1787648030298602e+04,
"cpu_time": 7.7107684721242025e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 1.0861210312956410e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3715875075265053e+01,
"cpu_time": 1.0995746234157704e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.1673962915208840e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):26/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.8380766984600191e-04,
"cpu_time": 1.4254328770318253e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8371640526829503e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 6253,
"real_time": 1.1195672692946390e+05,
"cpu_time": 1.2991731456900774e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.1988357616470977e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 6253,
"real_time": 1.1198740765995756e+05,
"cpu_time": 1.3012446969454557e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.1985073215333582e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 6253,
"real_time": 1.1204254896028397e+05,
"cpu_time": 1.2998274540220528e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.1979174808632437e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 6253,
"real_time": 1.1205160766714500e+05,
"cpu_time": 1.2995767679513856e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.1978206363508911e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 6253,
"real_time": 1.1202021114788527e+05,
"cpu_time": 1.2991934655365619e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.1981563561133655e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.1201170047294714e+05,
"cpu_time": 1.2998031060291070e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.1982475113015913e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time_median",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.1202021114788526e+05,
"cpu_time": 1.2995767679513856e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.1981563561133655e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.9461614723081468e+01,
"cpu_time": 8.5125167808084697e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.2219409239961433e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):27/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.5229904158639360e-04,
"cpu_time": 6.5490817350130615e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5234297456708904e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 3257,
"real_time": 2.1494033421766633e+05,
"cpu_time": 2.4614442523795221e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 1.2488835889133777e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 3257,
"real_time": 2.1505758850632957e+05,
"cpu_time": 2.4670950107460620e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 1.2482026691752820e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 3257,
"real_time": 2.1483579013561120e+05,
"cpu_time": 2.4542550629413515e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 1.2494913246557056e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 3257,
"real_time": 2.1485298890437462e+05,
"cpu_time": 2.4557379735953317e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 1.2493913041138723e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 3257,
"real_time": 2.1488624562446878e+05,
"cpu_time": 2.4590949585507889e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 1.2491979429391345e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.1491458947769008e+05,
"cpu_time": 2.4595254516426110e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 1.2490333659594744e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time_median",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.1488624562446881e+05,
"cpu_time": 2.4590949585507889e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 1.2491979429391345e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.9329243199071954e+01,
"cpu_time": 5.0815187841360449e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.1899464934415931e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):28/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.1564997246659730e-04,
"cpu_time": 2.0660565967074327e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.1551704180895226e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1588,
"real_time": 4.5323158073020860e+05,
"cpu_time": 5.2490483879092010e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 1.1845399456389133e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1588,
"real_time": 4.4069463674577838e+05,
"cpu_time": 5.1218194017631048e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 1.2182379072375742e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1588,
"real_time": 4.5350031710672018e+05,
"cpu_time": 5.2535287657430884e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 1.1838380079316694e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1588,
"real_time": 4.4088931983689865e+05,
"cpu_time": 5.1235949685138831e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 1.2176999710462673e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1588,
"real_time": 4.5392077110994543e+05,
"cpu_time": 5.2565086649873480e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 1.1827414521860754e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.4844732510591036e+05,
"cpu_time": 5.2009000377833255e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 1.1974114568080999e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time_median",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.5323158073020854e+05,
"cpu_time": 5.2490483879092010e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 1.1845399456389133e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.9929975985554220e+03,
"cpu_time": 7.1432112481247241e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8778233391842506e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):29/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.5593799331736180e-02,
"cpu_time": 1.3734567471458708e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5682356540916206e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 717,
"real_time": 9.7282398000133515e+05,
"cpu_time": 1.2237285634588664e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1037370028630732e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 717,
"real_time": 9.7408926825921051e+05,
"cpu_time": 1.2248211562064535e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1023033093454341e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 717,
"real_time": 9.7240158868174243e+05,
"cpu_time": 1.2221209330544036e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1042164435947104e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 717,
"real_time": 9.7343945173375215e+05,
"cpu_time": 1.2234382566248472e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1030391485444766e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 717,
"real_time": 9.7216814803479123e+05,
"cpu_time": 1.2222837210599494e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1044815921716184e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.7298448734216637e+05,
"cpu_time": 1.2232785260809041e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1035554993038625e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time_median",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.7282398000133527e+05,
"cpu_time": 1.2234382566248472e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1037370028630732e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.8413595628434803e+02,
"cpu_time": 1.1110146081050393e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.8910582846027970e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/0/log2(N):30/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.0590797333914064e-04,
"cpu_time": 9.0822701814644621e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.0567386870994656e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2655056479076543e+06,
"cpu_time": 2.5682348284789855e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8079848989928272e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2724214300790555e+06,
"cpu_time": 2.5719383689320390e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8024825614575832e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2739862358577331e+06,
"cpu_time": 2.5746093042071215e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8012422130844670e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2679636696456028e+06,
"cpu_time": 2.5754732491909903e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8060254027967078e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2671512519476581e+06,
"cpu_time": 2.5689966796116554e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8066725792913991e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2694056470875405e+06,
"cpu_time": 2.5718504860841585e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8048815311245972e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time_median",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2679636696456028e+06,
"cpu_time": 2.5719383689320390e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8060254027967078e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6210609816635879e+03,
"cpu_time": 3.2388425654462471e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8786663284101314e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):12/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.5955988239963639e-03,
"cpu_time": 1.2593432561383597e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5949336722485457e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2672242530196616e+06,
"cpu_time": 2.5747143236245373e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6132288145247530e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2682318762306450e+06,
"cpu_time": 2.5709937184465667e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6116236994312471e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2686626822431497e+06,
"cpu_time": 2.5824757702264967e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6109378728353418e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2691023523970521e+06,
"cpu_time": 2.5715750064725624e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6102382033785610e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2812402049157899e+06,
"cpu_time": 2.5840370129449815e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.5910291175594986e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2708922737612594e+06,
"cpu_time": 2.5767591663430287e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6074115415458810e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time_median",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2686626822431497e+06,
"cpu_time": 2.5747143236245373e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6109378728353418e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.8263768155085991e+03,
"cpu_time": 6.1225790292166594e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.2248547968490657e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):13/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5656773255291502e-03,
"cpu_time": 2.3760773258084131e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5571950110510394e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2758004594255579e+06,
"cpu_time": 2.5800106363635971e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1992251922365548e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2812633224847643e+06,
"cpu_time": 2.5926756201298591e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1819854545131857e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2750321372000910e+06,
"cpu_time": 2.5801103668831284e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2016565094170412e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2748477330624862e+06,
"cpu_time": 2.5852198538960805e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2022402914604032e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2752944768599970e+06,
"cpu_time": 2.5859965681817885e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2008261640974991e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2764476258065789e+06,
"cpu_time": 2.5848026090908903e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1971867223449368e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time_median",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2752944768599970e+06,
"cpu_time": 2.5852198538960801e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2008261640974991e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7158229003427468e+03,
"cpu_time": 5.2097042603076579e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.5731703108994334e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):14/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.1930091733959795e-03,
"cpu_time": 2.0155133865869864e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1911835334607219e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 306,
"real_time": 2.3023587981774625e+06,
"cpu_time": 2.6108053921568762e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4232360319312096e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 306,
"real_time": 2.2894127432902167e+06,
"cpu_time": 2.5977911241829190e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4312840747495646e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 306,
"real_time": 2.2892052120547378e+06,
"cpu_time": 2.6040253921568999e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4314138298937473e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 306,
"real_time": 2.2956695692199799e+06,
"cpu_time": 2.6043896045751143e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4273831233967124e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 306,
"real_time": 2.2899173550137314e+06,
"cpu_time": 2.6050263790849531e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4309686735311681e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2933127355512260e+06,
"cpu_time": 2.6044075784313525e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4288571467004806e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time_median",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2899173550137309e+06,
"cpu_time": 2.6043896045751148e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4309686735311681e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.7226788282562266e+03,
"cpu_time": 4.6162428159335204e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5586103401095177e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):15/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4953765526796808e-03,
"cpu_time": 1.7724732696077878e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4905291255511910e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 299,
"real_time": 2.3224923127396251e+06,
"cpu_time": 2.6416980434782128e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8217962074842505e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 299,
"real_time": 2.3290524064535182e+06,
"cpu_time": 2.6490035050166822e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8138482336596545e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 299,
"real_time": 2.3288207119299616e+06,
"cpu_time": 2.6481698929765620e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8141281836027820e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 299,
"real_time": 2.3275712118748836e+06,
"cpu_time": 2.6536149130435167e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8156388799468800e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 299,
"real_time": 2.3217196186948381e+06,
"cpu_time": 2.6471683846153934e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8227353325653192e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3259312523385654e+06,
"cpu_time": 2.6479309478260735e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8176293674517769e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time_median",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3275712118748836e+06,
"cpu_time": 2.6481698929765616e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8156388799468800e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.5476827131645537e+03,
"cpu_time": 4.2704078718644978e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.2997307244901975e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):16/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.5252741067035408e-03,
"cpu_time": 1.6127338499406351e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5260100473678735e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 294,
"real_time": 2.3838274630711596e+06,
"cpu_time": 2.7287894659863906e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4983845110642292e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 294,
"real_time": 2.3836039329821966e+06,
"cpu_time": 2.7295267312925630e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4989001396726169e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 294,
"real_time": 2.3893008490099390e+06,
"cpu_time": 2.7346804183673882e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4857888680830069e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 294,
"real_time": 2.3826755849378449e+06,
"cpu_time": 2.7285238095238302e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5010426441843607e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 294,
"real_time": 2.3894603245378453e+06,
"cpu_time": 2.7304244353741426e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4854227397707947e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3857736309077973e+06,
"cpu_time": 2.7303889721088633e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4939077805550016e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time_median",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3838274630711600e+06,
"cpu_time": 2.7295267312925630e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4983845110642292e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.3213711260512400e+03,
"cpu_time": 2.5099043391209511e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.6449934834831613e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):17/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3921568597383830e-03,
"cpu_time": 9.1924790378214254e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3915401912171985e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 280,
"real_time": 2.5049788395075924e+06,
"cpu_time": 2.8802415607142760e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0464918739654106e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 280,
"real_time": 2.5081954846557761e+06,
"cpu_time": 2.8800819178571706e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0451497963524026e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 280,
"real_time": 2.5002885243988461e+06,
"cpu_time": 2.8700542392857843e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0484549980607869e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 280,
"real_time": 2.5008531287312508e+06,
"cpu_time": 2.8761451285714451e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0482182939427260e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 280,
"real_time": 2.4995188469932014e+06,
"cpu_time": 2.8742114249999826e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0487778490462129e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5027669648573333e+06,
"cpu_time": 2.8761468542857314e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0474185622735077e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time_median",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5008531287312508e+06,
"cpu_time": 2.8761451285714451e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0482182939427260e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6985443808903647e+03,
"cpu_time": 4.2754296007076864e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5465672019831534e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):18/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4777821638305006e-03,
"cpu_time": 1.4865129693697283e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4765512639247128e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 271,
"real_time": 2.5877556875279360e+06,
"cpu_time": 3.0251080147601436e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0260336110046327e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 271,
"real_time": 2.5920514395371135e+06,
"cpu_time": 3.0290256974169980e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0226759083671078e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 271,
"real_time": 2.5885113561354112e+06,
"cpu_time": 3.0273132177121728e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0254421475003693e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 271,
"real_time": 2.5911877022856828e+06,
"cpu_time": 3.0249144022140317e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0233501399282128e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 271,
"real_time": 2.5867496735701594e+06,
"cpu_time": 3.0206817195571107e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0268215566309223e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5892511718112607e+06,
"cpu_time": 3.0254086103320918e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0248646726862490e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time_median",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5885113561354112e+06,
"cpu_time": 3.0251080147601436e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0254421475003693e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2711750009013181e+03,
"cpu_time": 3.1380305930295453e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7757947127976251e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):19/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.7715515034895650e-04,
"cpu_time": 1.0372253791811254e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7699426867959536e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 255,
"real_time": 2.7534401199469962e+06,
"cpu_time": 3.3270618627450494e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8082397085874707e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 255,
"real_time": 2.7493240193043854e+06,
"cpu_time": 3.3218148666666071e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8139411456686115e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 255,
"real_time": 2.7509195629653395e+06,
"cpu_time": 3.3211108509804299e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8117290455039442e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 255,
"real_time": 2.7490083265173086e+06,
"cpu_time": 3.3206275098039252e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8143791340509713e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 255,
"real_time": 2.7506893199375449e+06,
"cpu_time": 3.3193359921568246e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8120481015420830e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7506762697343146e+06,
"cpu_time": 3.3219902164705675e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8120674270706159e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time_median",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7506893199375449e+06,
"cpu_time": 3.3211108509804299e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8120481015420830e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.7541982283939942e+03,
"cpu_time": 2.9760503744443181e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4300779271455473e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):20/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.3773343584464426e-04,
"cpu_time": 8.9586367825195113e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.3746981752968131e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 226,
"real_time": 3.0820040512351994e+06,
"cpu_time": 3.9697559867257560e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8045076032898390e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 226,
"real_time": 3.0826270679193260e+06,
"cpu_time": 3.9766436371681304e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8031323731141770e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 226,
"real_time": 3.0827565979937799e+06,
"cpu_time": 3.9774748053097669e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8028465217292881e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 226,
"real_time": 3.0776273255211720e+06,
"cpu_time": 3.9644059115043832e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8141843640696931e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 226,
"real_time": 3.0808082196564800e+06,
"cpu_time": 3.9734567831858508e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8071488079639018e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0811646524651917e+06,
"cpu_time": 3.9723474247787772e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8063639340333796e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time_median",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0820040512351994e+06,
"cpu_time": 3.9734567831858499e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8045076032898390e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.1223375133371210e+03,
"cpu_time": 5.3796220209078874e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.6913828502905194e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):21/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.8881015872977519e-04,
"cpu_time": 1.3542677529540313e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.8926417919449321e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 193,
"real_time": 3.6185814376553725e+06,
"cpu_time": 5.0328191813470777e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1591017287475121e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 193,
"real_time": 3.6176951997792781e+06,
"cpu_time": 5.0271622487046085e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1593856774489741e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 193,
"real_time": 3.6136918252459462e+06,
"cpu_time": 5.0231052124352567e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1606700855611942e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 193,
"real_time": 3.6202867544338186e+06,
"cpu_time": 5.0531507772020241e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1585557400565505e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 193,
"real_time": 3.6116830867092689e+06,
"cpu_time": 5.0209306321244417e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1613156246833322e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6163876607647366e+06,
"cpu_time": 5.0314336103626816e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1598057712995129e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time_median",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6176951997792781e+06,
"cpu_time": 5.0271622487046076e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1593856774489741e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.5751151362938463e+03,
"cpu_time": 1.2956411895234705e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1468902789717943e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):22/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.8858736165962822e-04,
"cpu_time": 2.5750934820147151e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.8886409030949436e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 143,
"real_time": 4.9302749908887427e+06,
"cpu_time": 7.6370821258742372e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7014482996389318e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 143,
"real_time": 4.9525420735036572e+06,
"cpu_time": 7.6561792657341706e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6937984322999420e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 143,
"real_time": 4.9444659404665027e+06,
"cpu_time": 7.6640829580420181e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6965650286608200e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 143,
"real_time": 4.9617740332142459e+06,
"cpu_time": 7.6777227972026290e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6906469226221182e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 143,
"real_time": 4.9411282724850662e+06,
"cpu_time": 7.6620138951047864e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6977110363056970e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9460370621116431e+06,
"cpu_time": 7.6594162083915677e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6960339439055016e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time_median",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9444659404665027e+06,
"cpu_time": 7.6620138951047882e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6965650286608200e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.1884600968984976e+04,
"cpu_time": 1.4772836238523447e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0751517884073961e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):23/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4028531973658536e-03,
"cpu_time": 1.9287156927623929e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4027536730918471e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 88,
"real_time": 7.9950475536117498e+06,
"cpu_time": 1.3781671761363609e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0984510582955720e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 88,
"real_time": 7.9906820637089284e+06,
"cpu_time": 1.3790179761363804e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0995974894554551e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 88,
"real_time": 7.9878256973725827e+06,
"cpu_time": 1.3783974954545319e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1003482844547410e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 88,
"real_time": 8.0014766215092754e+06,
"cpu_time": 1.3793579079545410e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0967649839655976e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 88,
"real_time": 7.9991621049967678e+06,
"cpu_time": 1.3789241079545630e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0973716721555026e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.9948388082398605e+06,
"cpu_time": 1.3787729327272754e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0985066976653738e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time_median",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.9950475536117498e+06,
"cpu_time": 1.3789241079545628e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0984510582955720e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.6845686630151667e+03,
"cpu_time": 4.8295714914499968e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4921640229411779e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):24/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.1102980302196713e-04,
"cpu_time": 3.5028041070525552e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.1105992875850098e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52,
"real_time": 1.3578145567757579e+07,
"cpu_time": 2.5060329076923110e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4712087399974375e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52,
"real_time": 1.3572594706112375e+07,
"cpu_time": 2.4997964076922912e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4722194043625917e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52,
"real_time": 1.3595579478603143e+07,
"cpu_time": 2.5079057692307808e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4680398546313009e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52,
"real_time": 1.3560729871432368e+07,
"cpu_time": 2.4959871865384832e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4743824497741265e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52,
"real_time": 1.3564868239112772e+07,
"cpu_time": 2.5004916711538367e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4736275655999055e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3574383572603649e+07,
"cpu_time": 2.5020427884615410e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4718956028730726e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time_median",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3572594706112375e+07,
"cpu_time": 2.5004916711538367e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4722194043625917e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3634370256295786e+04,
"cpu_time": 4.8584488545905326e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4813063552894876e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):25/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0044191092266764e-03,
"cpu_time": 1.9417928730059418e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0038070994606233e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 28,
"real_time": 2.4551194693361010e+07,
"cpu_time": 4.7682736892857596e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7334255965208564e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 28,
"real_time": 2.4667675540383372e+07,
"cpu_time": 4.7669700642856583e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7205183516434813e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 28,
"real_time": 2.4626092652657203e+07,
"cpu_time": 4.7664402500000082e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7251121380296936e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 28,
"real_time": 2.4654709534453493e+07,
"cpu_time": 4.7663174535713896e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7219490826375117e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 28,
"real_time": 2.4592131775404725e+07,
"cpu_time": 4.7679811071428649e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7288754229561114e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4618360839251962e+07,
"cpu_time": 4.7671965128571369e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7259761183575311e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time_median",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4626092652657203e+07,
"cpu_time": 4.7669700642856583e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7251121380296936e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.7466312456408908e+04,
"cpu_time": 8.9048510839228311e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.2595481806254042e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):26/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.9280858204307311e-03,
"cpu_time": 1.8679429429658363e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9294182899131243e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 16,
"real_time": 4.4878440676257014e+07,
"cpu_time": 8.6938621187499627e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9906949969188218e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 16,
"real_time": 4.4930730946362019e+07,
"cpu_time": 8.6998784062499717e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9872144337074809e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 16,
"real_time": 4.5045532751828432e+07,
"cpu_time": 8.6797669312499434e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9796013011867867e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 16,
"real_time": 4.4967670692130923e+07,
"cpu_time": 8.7004491562499449e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9847605164811730e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 16,
"real_time": 4.4860868481919169e+07,
"cpu_time": 8.6980766499998197e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9918664649592199e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.4936648709699519e+07,
"cpu_time": 8.6944066524999291e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9868275426506968e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time_median",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.4930730946362019e+07,
"cpu_time": 8.6980766499998197e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9872144337074809e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.4134904099876760e+04,
"cpu_time": 8.5810660405493269e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9241442938403012e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):27/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6497648629474862e-03,
"cpu_time": 9.8696396240932518e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6486202244774765e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.5508892312645912e+07,
"cpu_time": 1.6437865512499884e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1392694811028571e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.4170997142791748e+07,
"cpu_time": 1.6137153162500083e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1891680639664173e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.5521608591079712e+07,
"cpu_time": 1.6437616275000265e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1388027005375929e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.5558866150677204e+07,
"cpu_time": 1.6456377574999693e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1374358740011811e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.5441146045923233e+07,
"cpu_time": 1.6450875774999928e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1417586072139096e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.5240302048623562e+07,
"cpu_time": 1.6383977659999973e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1492869453643918e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time_median",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.5508892312645912e+07,
"cpu_time": 1.6437865512499884e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1392694811028571e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.9927215869783680e+05,
"cpu_time": 1.3822123544765990e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2348917023691326e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):28/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.0303852085835464e-03,
"cpu_time": 8.4363662058155025e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.0965007036236961e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6664851829409599e+08,
"cpu_time": 3.1134529749999726e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2215762701984982e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6343548521399498e+08,
"cpu_time": 3.0650404024999034e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2849103197940502e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6666215285658836e+08,
"cpu_time": 3.1133070274999851e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2213127143627729e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.6385103389620781e+08,
"cpu_time": 3.0709383099998885e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2765793369365211e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6660070046782494e+08,
"cpu_time": 3.1135498049999911e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2225009288222299e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6543957814574242e+08,
"cpu_time": 3.0952577039999479e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2453759140228143e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time_median",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6660070046782494e+08,
"cpu_time": 3.1133070274999851e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2225009288222299e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6465335985439108e+06,
"cpu_time": 2.4979817648659674e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2424328879694026e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):29/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.9524770130483085e-03,
"cpu_time": 8.0703514981575481e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.9909316327865278e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.1833836436271667e+08,
"cpu_time": 5.5839567699999297e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3729576582751179e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.1884165108203888e+08,
"cpu_time": 5.5723308749998069e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3676334956743875e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.1864756345748901e+08,
"cpu_time": 5.5802271249999082e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3696847148283582e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.1875763833522797e+08,
"cpu_time": 5.5823924349999738e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3685210795506568e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.1939861178398132e+08,
"cpu_time": 5.5973558450000381e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3617610859442406e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.1879676580429077e+08,
"cpu_time": 5.5832526099999309e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3681116068545523e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time_median",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.1875763833522797e+08,
"cpu_time": 5.5823924349999738e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3685210795506568e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.8670319761437364e+05,
"cpu_time": 9.0633166487426159e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0830214634948955e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/1/log2(N):30/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.2130085342577492e-03,
"cpu_time": 1.6233040633894459e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2122583631686691e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2671090729244342e+06,
"cpu_time": 2.5772651396102724e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8067061920035486e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2667771335328361e+06,
"cpu_time": 2.5822860681817667e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8069707601189131e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2744213453155351e+06,
"cpu_time": 2.5852891038960540e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8008976254273388e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2662420841780575e+06,
"cpu_time": 2.5826376720779641e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8073973776219836e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2668831138085430e+06,
"cpu_time": 2.5831289870129973e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8068862814538311e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2682865499518812e+06,
"cpu_time": 2.5821213941558106e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8057716473251232e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time_median",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2668831138085425e+06,
"cpu_time": 2.5826376720779641e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8068862814538311e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.4441972046697256e+03,
"cpu_time": 2.9549321905544271e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7364549578028841e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):12/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.5184136258017270e-03,
"cpu_time": 1.1443815915248639e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5153936888179496e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2741728062925311e+06,
"cpu_time": 2.5872905889968197e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6021888826271752e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2750763413963486e+06,
"cpu_time": 2.5894323042071145e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6007582914655455e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2682309953923845e+06,
"cpu_time": 2.5868045339806746e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6116251019587419e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2675873731296137e+06,
"cpu_time": 2.5861600517799933e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6126502101190486e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2683526723853592e+06,
"cpu_time": 2.5860219288025321e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6114313703192542e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2706840377192474e+06,
"cpu_time": 2.5871418815534269e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6077307712979536e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time_median",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2683526723853592e+06,
"cpu_time": 2.5868045339806741e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6114313703192542e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6230460356078656e+03,
"cpu_time": 1.3784263753519763e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.7530237215674651e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):13/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.5955747146780387e-03,
"cpu_time": 5.3279891032660036e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5946377615915334e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2763356546774604e+06,
"cpu_time": 2.5985404772728696e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1975325635012686e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2815434933434445e+06,
"cpu_time": 2.5986161396104251e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1811035151428906e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2758083824709347e+06,
"cpu_time": 2.5971933409090815e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1992001287082201e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2755501936976011e+06,
"cpu_time": 2.5978951493506762e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2000169652936589e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2836131067922362e+06,
"cpu_time": 2.5999726461039130e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1745953599882806e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2785701661963356e+06,
"cpu_time": 2.5984435506493929e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1904897065268643e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time_median",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2763356546774600e+06,
"cpu_time": 2.5985404772728691e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1975325635012686e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.7420799411557246e+03,
"cpu_time": 1.0296944931755434e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1800135477406870e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):14/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6422930470482095e-03,
"cpu_time": 3.9627356650415055e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6410753591227303e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 306,
"real_time": 2.2894217483577579e+06,
"cpu_time": 2.6157123986928468e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4312784450267870e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 306,
"real_time": 2.2982097583902036e+06,
"cpu_time": 2.6196216928103981e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4258054505413188e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 306,
"real_time": 2.2948424200971727e+06,
"cpu_time": 2.6147066568628689e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4278976069569288e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 306,
"real_time": 2.2951713040337162e+06,
"cpu_time": 2.6159913267973727e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4276929980089467e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 306,
"real_time": 2.2892230433819732e+06,
"cpu_time": 2.6157642941176118e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4314026802556708e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2933736548521654e+06,
"cpu_time": 2.6163592738562198e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4288154361579306e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time_median",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2948424200971727e+06,
"cpu_time": 2.6157642941176118e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4278976069569288e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.9249793588278822e+03,
"cpu_time": 1.8896000741518933e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4455334774754414e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):15/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.7114434669307707e-03,
"cpu_time": 7.2222499907928733e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7115810870936940e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 301,
"real_time": 2.3333618852102580e+06,
"cpu_time": 2.6640279767441349e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8086513461710457e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 301,
"real_time": 2.3237798854931449e+06,
"cpu_time": 2.6616466777408584e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8202326911049999e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 301,
"real_time": 2.3243023961336906e+06,
"cpu_time": 2.6552495847176355e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8195986937420197e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 301,
"real_time": 2.3317873660487393e+06,
"cpu_time": 2.6638293588040257e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8105478635923855e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 301,
"real_time": 2.3322657471603137e+06,
"cpu_time": 2.6639117209302289e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8099713799679294e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3290994560092292e+06,
"cpu_time": 2.6617330637873770e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8138003949156761e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time_median",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3317873660487393e+06,
"cpu_time": 2.6638293588040262e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8105478635923855e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.6563981964097811e+03,
"cpu_time": 3.7566803371265755e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.6291145396056738e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):16/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.9992268618654169e-03,
"cpu_time": 1.4113662967319494e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0005379734031798e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 294,
"real_time": 2.3916211687218472e+06,
"cpu_time": 2.7459815748298741e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4804666271643989e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 294,
"real_time": 2.3832140137207042e+06,
"cpu_time": 2.7419768911564848e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4997998184547730e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 294,
"real_time": 2.3888418083490967e+06,
"cpu_time": 2.7433556292517390e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4868430191525519e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 294,
"real_time": 2.3704868920312142e+06,
"cpu_time": 2.7251113231292660e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5293281916310236e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 294,
"real_time": 2.3771813091802960e+06,
"cpu_time": 2.7292443061224613e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5137569647641420e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3822690384006323e+06,
"cpu_time": 2.7371339448979655e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5020389242333785e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time_median",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3832140137207042e+06,
"cpu_time": 2.7419768911564853e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4997998184547730e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.6061110030168456e+03,
"cpu_time": 9.3171062335405913e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9895412258074724e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):17/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6125688846607657e-03,
"cpu_time": 3.4039643002885321e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.6160071806192887e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 280,
"real_time": 2.4899323221429116e+06,
"cpu_time": 2.8720195607143799e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0528157639818534e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 280,
"real_time": 2.5041672584068561e+06,
"cpu_time": 2.8824062892856058e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0468310338294864e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 280,
"real_time": 2.4900311121850139e+06,
"cpu_time": 2.8712969071429078e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0527739943376346e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 280,
"real_time": 2.4899225657074046e+06,
"cpu_time": 2.8706513678571358e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0528198893025535e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 280,
"real_time": 2.5060735119041055e+06,
"cpu_time": 2.8821455964286914e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0460347581776400e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4960253540692581e+06,
"cpu_time": 2.8757039442857439e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0502550879258336e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time_median",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4900311121850139e+06,
"cpu_time": 2.8720195607143799e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0527739943376346e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.3300072287625117e+03,
"cpu_time": 6.0195825867577423e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5005530675523262e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):18/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.3373087397458282e-03,
"cpu_time": 2.0932553223078263e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3330503301494375e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 270,
"real_time": 2.6007938043524823e+06,
"cpu_time": 3.0453855814814521e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0158768416111773e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 270,
"real_time": 2.5987131822923268e+06,
"cpu_time": 3.0437650592592424e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0174908241990954e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 270,
"real_time": 2.5980696263205674e+06,
"cpu_time": 3.0476056296295072e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0179905676450482e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 270,
"real_time": 2.5992518704798487e+06,
"cpu_time": 3.0439464111111644e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0170727044748113e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 270,
"real_time": 2.5948500303827501e+06,
"cpu_time": 3.0430851222223300e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0204944172541082e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5983357027655952e+06,
"cpu_time": 3.0447575607407391e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0177850710368481e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time_median",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5987131822923264e+06,
"cpu_time": 3.0439464111111648e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0174908241990954e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.1934462675495224e+03,
"cpu_time": 1.7990261221939127e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7042720325699181e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):19/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.4417354740377848e-04,
"cpu_time": 5.9086022000261966e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4462515707590708e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 253,
"real_time": 2.7542117469586991e+06,
"cpu_time": 3.3392219525691005e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8071727824045330e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 253,
"real_time": 2.7562702505337629e+06,
"cpu_time": 3.3408958814227306e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8043294187024623e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 253,
"real_time": 2.7555580998185594e+06,
"cpu_time": 3.3412267470354708e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8053126155062521e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 253,
"real_time": 2.7586334953710376e+06,
"cpu_time": 3.3421837628459712e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8010703551577300e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 253,
"real_time": 2.7571941556578334e+06,
"cpu_time": 3.3403462371542566e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8030546301873416e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7563735496679791e+06,
"cpu_time": 3.3407749162055063e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8041879603916645e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time_median",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7562702505337624e+06,
"cpu_time": 3.3408958814227306e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8043294187024623e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6680654128489557e+03,
"cpu_time": 1.0953417640821144e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3020600417886584e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):20/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.0516667381671973e-04,
"cpu_time": 3.2787056642721000e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0513835429720645e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 226,
"real_time": 3.1047336390423300e+06,
"cpu_time": 4.0172321017699945e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7546921694927645e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 226,
"real_time": 3.0986635103014060e+06,
"cpu_time": 4.0056525442477488e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7679242777671289e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 226,
"real_time": 3.0971116301875594e+06,
"cpu_time": 4.0060256283186190e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7713155042880952e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 226,
"real_time": 3.0960885527650868e+06,
"cpu_time": 4.0140796769912266e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7735530307330966e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 226,
"real_time": 3.0983362987686968e+06,
"cpu_time": 4.0083765619468256e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7686390300285494e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0989867262130165e+06,
"cpu_time": 4.0102733026548834e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7672248024619269e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time_median",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0983362987686968e+06,
"cpu_time": 4.0083765619468256e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7686390300285494e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.3715695858948093e+03,
"cpu_time": 5.1455111880945060e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.3541911343124614e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):21/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0879587051393701e-03,
"cpu_time": 1.2830824235066653e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0867366385755347e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 192,
"real_time": 3.6207315861247480e+06,
"cpu_time": 5.0885915729169305e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1584134035434380e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 192,
"real_time": 3.6210798728764835e+06,
"cpu_time": 5.0830158541668169e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1583019837306609e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 192,
"real_time": 3.6153915377023318e+06,
"cpu_time": 5.0773906666667182e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1601244170266495e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 192,
"real_time": 3.6146815509709995e+06,
"cpu_time": 5.0784186041665794e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1603522857700419e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 192,
"real_time": 3.6168631789526748e+06,
"cpu_time": 5.0771862031249171e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1596523817675993e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6177495453254478e+06,
"cpu_time": 5.0809205802083928e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1593688943676779e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time_median",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6168631789526744e+06,
"cpu_time": 5.0784186041665794e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1596523817675993e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.9892341650102326e+03,
"cpu_time": 4.8964284944730416e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.5779685578936827e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):22/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.2626896294484226e-04,
"cpu_time": 9.6368924039985984e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.2613640959528466e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 142,
"real_time": 4.9907564133090870e+06,
"cpu_time": 7.7879985563378939e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6808289776735446e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 142,
"real_time": 5.4827255465772366e+06,
"cpu_time": 8.4748413591547646e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.5300069151257901e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 142,
"real_time": 4.9338850953524383e+06,
"cpu_time": 7.7094881126759257e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7002033565600870e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 142,
"real_time": 4.9333104889997290e+06,
"cpu_time": 7.7020773028167905e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7004013874060583e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 142,
"real_time": 4.9877817558885459e+06,
"cpu_time": 7.7893241901407093e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6818314053329334e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.0656918600254077e+06,
"cpu_time": 7.8927459042252181e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6586544084196827e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time_median",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9877817558885459e+06,
"cpu_time": 7.7879985563378949e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6818314053329334e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3478727171014337e+05,
"cpu_time": 3.2804005479886633e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.2539967577150732e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):23/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.6348510370894477e-02,
"cpu_time": 4.1562221662711438e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3734226496443394e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 87,
"real_time": 7.8241643709954862e+06,
"cpu_time": 1.3358113022988342e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1442821500777593e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 87,
"real_time": 7.8005687836771728e+06,
"cpu_time": 1.3328027517241810e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1507682920643711e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 87,
"real_time": 7.9154310073575070e+06,
"cpu_time": 1.3513200689655066e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1195581117952182e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 87,
"real_time": 7.7943636757460823e+06,
"cpu_time": 1.3308866206896568e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1524805228432035e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 87,
"real_time": 7.8576927276692167e+06,
"cpu_time": 1.3417981701149721e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1351326122644823e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.8384441130890939e+06,
"cpu_time": 1.3385237827586303e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1404443378090069e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time_median",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.8241643709954862e+06,
"cpu_time": 1.3358113022988342e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1442821500777593e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9696648833239087e+04,
"cpu_time": 8.2595481725336911e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3515097576550456e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):24/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.3401164971314539e-03,
"cpu_time": 6.1706398339155220e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.3141551208870609e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51,
"real_time": 1.3676611542263452e+07,
"cpu_time": 2.5044000823529541e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4534170540934153e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51,
"real_time": 1.3645244999697395e+07,
"cpu_time": 2.5002783745098807e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4590567630514603e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51,
"real_time": 1.3616005670936668e+07,
"cpu_time": 2.4942149058823165e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4643373990084224e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51,
"real_time": 1.3663645340677571e+07,
"cpu_time": 2.5083934941176046e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4557452395303507e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51,
"real_time": 1.3613423770841431e+07,
"cpu_time": 2.4942750411764570e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4648047812828822e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3642986264883306e+07,
"cpu_time": 2.5003123796078425e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4594722473933063e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time_median",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3645244999697397e+07,
"cpu_time": 2.5002783745098807e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4590567630514603e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.8126731405086699e+04,
"cpu_time": 6.2378586663681803e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0703599150198400e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):25/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.0616257217442326e-03,
"cpu_time": 2.4948317327239517e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0615641914210280e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 27,
"real_time": 2.5437472733082596e+07,
"cpu_time": 4.8407711148149282e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6381891276770535e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 27,
"real_time": 2.5253418350109346e+07,
"cpu_time": 4.8171635148146719e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6574170304238997e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 27,
"real_time": 2.5287617066944089e+07,
"cpu_time": 4.8209218555554241e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6538231665855360e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 27,
"real_time": 2.5397804531234283e+07,
"cpu_time": 4.8330569851851091e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6423096499332986e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 27,
"real_time": 2.5444494560360909e+07,
"cpu_time": 4.8431632666666634e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6374610759431849e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5364161448346246e+07,
"cpu_time": 4.8310153474073596e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6458400101125946e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time_median",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5397804531234279e+07,
"cpu_time": 4.8330569851851091e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6423096499332986e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.8151696683491755e+04,
"cpu_time": 1.1626124340890888e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.2054897942825407e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):26/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.4754429734651956e-03,
"cpu_time": 2.4065591816283985e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4792314573437863e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 4.6092402438322701e+07,
"cpu_time": 8.8279592866668597e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9119273654611473e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 4.6236743529637657e+07,
"cpu_time": 8.8365770466665104e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9028369593971667e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 4.6033927053213120e+07,
"cpu_time": 8.8142471733332664e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9156262911232934e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.5941819002230965e+07,
"cpu_time": 8.8011631266666263e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9214717857271237e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 4.5961531500021614e+07,
"cpu_time": 8.8250390066669613e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9202187920987115e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.6053284704685219e+07,
"cpu_time": 8.8209971280000463e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9144162387614884e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time_median",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.6033927053213120e+07,
"cpu_time": 8.8250390066669598e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9156262911232934e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.1874901009681328e+05,
"cpu_time": 1.3661001052196955e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5031459375811154e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):27/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5785133646445938e-03,
"cpu_time": 1.5486912481621300e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5744935942196285e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.8145243935286999e+07,
"cpu_time": 1.6829974962499961e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0453765173884535e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.7316600605845451e+07,
"cpu_time": 1.6690424174999663e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0742774471001277e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.7381476536393166e+07,
"cpu_time": 1.6705389987500042e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0719949655256786e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.7145378813147545e+07,
"cpu_time": 1.6679776587499619e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0803177363605814e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.8227984495460987e+07,
"cpu_time": 1.6880974449999541e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0425205509915061e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.7643336877226830e+07,
"cpu_time": 1.6757308032499763e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0628974434732695e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time_median",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.7381476536393166e+07,
"cpu_time": 1.6705389987500042e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0719949655256786e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.0423536051050387e+05,
"cpu_time": 9.1861205477866379e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7592161552909862e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):28/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.7532652050531850e-03,
"cpu_time": 5.4818593356228363e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.7436338883618231e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6792491823434830e+08,
"cpu_time": 3.1232115199999553e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1970890183836064e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6955873742699623e+08,
"cpu_time": 3.1624364700000739e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1662827887660499e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6895264387130737e+08,
"cpu_time": 3.1371170925000060e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1776413774793544e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.6978977248072624e+08,
"cpu_time": 3.1646866625000316e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1619743884216766e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6958019882440567e+08,
"cpu_time": 3.1493968175000477e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1658820765737572e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6916125416755679e+08,
"cpu_time": 3.1473697125000232e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1737739299248891e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time_median",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6955873742699623e+08,
"cpu_time": 3.1493968175000477e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1662827887660499e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.5838440655883634e+05,
"cpu_time": 1.7462299213359724e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4284416555158282e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):29/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.4832039718010431e-03,
"cpu_time": 5.5482198815114889e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5007668695219065e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.2960829138755798e+08,
"cpu_time": 5.7457173649999046e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2576298960194526e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.2888883352279663e+08,
"cpu_time": 5.7469970249999845e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2647560955442853e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.3022075891494751e+08,
"cpu_time": 5.7793509350000250e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2515878999495478e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.2831498980522156e+08,
"cpu_time": 5.7391187999999714e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2704623832040553e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.2915075123310089e+08,
"cpu_time": 5.7278634450000250e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2621582055560555e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.2923672497272491e+08,
"cpu_time": 5.7478095139999831e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2613188960546799e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time_median",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.2915075123310089e+08,
"cpu_time": 5.7457173649999046e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2621582055560555e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.2187257599079411e+05,
"cpu_time": 1.9191616938668352e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.1488311014542794e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/2/log2(N):30/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.1925639554657714e-03,
"cpu_time": 3.3389444956244962e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1920061574176157e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2564726892231833e+06,
"cpu_time": 2.5671146990291835e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8152225017224094e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2630964000453167e+06,
"cpu_time": 2.5819286537216394e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8099096441132517e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2571355023068711e+06,
"cpu_time": 2.5690336731393156e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8146894574179288e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2626977013032222e+06,
"cpu_time": 2.5745870582524976e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8102285593169916e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2642081460243384e+06,
"cpu_time": 2.5767448899677377e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8090209626672596e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2607220877805864e+06,
"cpu_time": 2.5738817948220745e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8118142250475683e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time_median",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2626977013032218e+06,
"cpu_time": 2.5745870582524971e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8102285593169916e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6267751879019743e+03,
"cpu_time": 5.9737868599348421e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9080659442335109e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):12/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6042552100963812e-03,
"cpu_time": 2.3209250991838163e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6050574634146947e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 310,
"real_time": 2.2619184414525665e+06,
"cpu_time": 2.5835331258063419e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6217044124452309e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 310,
"real_time": 2.2679716994565339e+06,
"cpu_time": 2.5840510967742051e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6120380170365530e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 310,
"real_time": 2.2688268834064086e+06,
"cpu_time": 2.5841463354839240e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6106765394548574e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 310,
"real_time": 2.2606055199679346e+06,
"cpu_time": 2.5819186774194879e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6238078371657687e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 310,
"real_time": 2.2671505583510282e+06,
"cpu_time": 2.5826930967742014e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6133462640250525e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2652946205268945e+06,
"cpu_time": 2.5832684664516319e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6163146140254922e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time_median",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2671505583510282e+06,
"cpu_time": 2.5835331258063419e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6133462640250525e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.7574721238752454e+03,
"cpu_time": 9.4949848985916105e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0018036546837320e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):13/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6587123325270950e-03,
"cpu_time": 3.6755703179522364e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6596464343578885e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2777335509633669e+06,
"cpu_time": 2.5962177792208297e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1931152759594684e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2693854687106493e+06,
"cpu_time": 2.5946163668830968e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2195756189928213e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2695174375730385e+06,
"cpu_time": 2.5931888863636223e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2191558120481391e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2763636933833165e+06,
"cpu_time": 2.5948243571429858e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1974439091711082e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2774286327774744e+06,
"cpu_time": 2.5954646818181854e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1940783408956397e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2740857566815694e+06,
"cpu_time": 2.5948624142857436e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2046737914134357e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time_median",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2763636933833165e+06,
"cpu_time": 2.5948243571429858e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1974439091711082e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.2612341467504721e+03,
"cpu_time": 1.1249915183317694e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3508584634163542e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):14/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8738229788522239e-03,
"cpu_time": 4.3354572949157009e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8749751932229239e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 306,
"real_time": 2.2903509214337841e+06,
"cpu_time": 2.6129054346406180e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4306977892927814e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 306,
"real_time": 2.2833432942884518e+06,
"cpu_time": 2.6128496241829651e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4350886299911967e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 306,
"real_time": 2.2830593557967469e+06,
"cpu_time": 2.6117844444444492e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4352671084438168e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 306,
"real_time": 2.2889924778913460e+06,
"cpu_time": 2.6112970457517141e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4315468624949949e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 306,
"real_time": 2.2826013360720347e+06,
"cpu_time": 2.6053897124182088e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4355551047029573e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2856694770964729e+06,
"cpu_time": 2.6108452522875913e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4336310989851493e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time_median",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2833432942884518e+06,
"cpu_time": 2.6117844444444492e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4350886299911967e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6944419190255990e+03,
"cpu_time": 3.1269382998769638e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3157649428867182e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):15/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6163500261283251e-03,
"cpu_time": 1.1976727832249642e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6153143891242461e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 299,
"real_time": 2.3225032215171736e+06,
"cpu_time": 2.6525224080268098e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8217829535318647e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 299,
"real_time": 2.3222104786431110e+06,
"cpu_time": 2.6554502809365834e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8221386735922959e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 299,
"real_time": 2.3262035654527587e+06,
"cpu_time": 2.6589453846153016e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8172942804016575e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 299,
"real_time": 2.3167137240361809e+06,
"cpu_time": 2.6498116053511444e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8288346255325463e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 299,
"real_time": 2.3165826528429687e+06,
"cpu_time": 2.6555968361204411e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8289946797094665e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3208427284984388e+06,
"cpu_time": 2.6544653030100563e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8238090425535664e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time_median",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3222104786431110e+06,
"cpu_time": 2.6554502809365829e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8221386735922959e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.1401531617820410e+03,
"cpu_time": 3.4551925671941922e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0369785606365745e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):16/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.7839007835143905e-03,
"cpu_time": 1.3016529405286041e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7837532512756749e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 293,
"real_time": 2.3902581310147615e+06,
"cpu_time": 2.7515517167235794e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4835918472267516e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 293,
"real_time": 2.3876729877443137e+06,
"cpu_time": 2.7484229488053573e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4895289544581458e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 293,
"real_time": 2.3890856920452248e+06,
"cpu_time": 2.7498379249146148e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4862829088308334e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 293,
"real_time": 2.3836385666904496e+06,
"cpu_time": 2.7379847235496254e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4988202419457510e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 293,
"real_time": 2.3870215212462195e+06,
"cpu_time": 2.7416290170649579e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4910271580446303e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3875353797481945e+06,
"cpu_time": 2.7458852662116275e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4898502221012227e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time_median",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3876729877443137e+06,
"cpu_time": 2.7484229488053573e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4895289544581458e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5142086826898658e+03,
"cpu_time": 5.8031507892350428e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.7845187170152712e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):17/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0530560945886513e-03,
"cpu_time": 2.1133988592470891e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0536751428532171e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 281,
"real_time": 2.4982014458851884e+06,
"cpu_time": 2.8788468078292129e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0493309113713785e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 281,
"real_time": 2.4948790089436062e+06,
"cpu_time": 2.8802535053381077e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0507283081074072e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 281,
"real_time": 2.4953174563887068e+06,
"cpu_time": 2.8751268540924629e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0505436866513254e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 281,
"real_time": 2.5017306008094465e+06,
"cpu_time": 2.8821319964411766e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0478506355367844e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 281,
"real_time": 2.4991068124002195e+06,
"cpu_time": 2.8841845195728918e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0489507639260475e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4978470648854342e+06,
"cpu_time": 2.8801087366547706e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0494808611185887e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time_median",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4982014458851884e+06,
"cpu_time": 2.8802535053381082e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0493309113713785e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.8285453940079719e+03,
"cpu_time": 3.4328618802142928e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1881546100992076e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):18/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.1323933453618810e-03,
"cpu_time": 1.1919209287221363e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1321355673249854e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 270,
"real_time": 2.5942774636119050e+06,
"cpu_time": 3.0489251444445625e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0209403479535899e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 270,
"real_time": 2.5923349972193441e+06,
"cpu_time": 3.0408255185184991e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0224546617716271e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 270,
"real_time": 2.5885180690912185e+06,
"cpu_time": 3.0425246629630676e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0254368948023915e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 270,
"real_time": 2.5929482895191070e+06,
"cpu_time": 3.0437304518519188e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0219763044223124e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 270,
"real_time": 2.5919189737005918e+06,
"cpu_time": 3.0490488074075598e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0227792817591515e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5919995586284334e+06,
"cpu_time": 3.0450109170371215e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0227174981418145e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time_median",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5923349972193437e+06,
"cpu_time": 3.0437304518519188e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0224546617716271e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.1406029396559488e+03,
"cpu_time": 3.7737364112057339e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6715000218366735e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):19/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.2585004018621714e-04,
"cpu_time": 1.2393178592862591e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.2636355465961532e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 255,
"real_time": 2.7507422099291696e+06,
"cpu_time": 3.3429572274507796e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8119748052544713e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 255,
"real_time": 2.7450003789043892e+06,
"cpu_time": 3.3364585607844177e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8199484708942652e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 255,
"real_time": 2.7528561469094427e+06,
"cpu_time": 3.3435869529411960e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8090475638445836e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 255,
"real_time": 2.7443968070050082e+06,
"cpu_time": 3.3350743254902903e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8207885875815570e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 255,
"real_time": 2.7510164095563632e+06,
"cpu_time": 3.3404875725489762e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8115948576587969e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7488023904608744e+06,
"cpu_time": 3.3397129278431321e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8146708570467353e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time_median",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7507422099291692e+06,
"cpu_time": 3.3404875725489757e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8119748052544713e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.8393417056235221e+03,
"cpu_time": 3.8157948569869041e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.3299092101085547e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):20/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3967325257527165e-03,
"cpu_time": 1.1425517520307464e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3972133926739084e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 227,
"real_time": 3.0898835862851352e+06,
"cpu_time": 4.0045507885462544e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7871553779841149e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 227,
"real_time": 3.0871762992559811e+06,
"cpu_time": 3.9956696828192794e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7931073470129323e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 227,
"real_time": 3.0869303757349430e+06,
"cpu_time": 4.0072940352422846e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7936485269795096e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 227,
"real_time": 3.0731934775077300e+06,
"cpu_time": 3.9933044977974249e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8240155244007909e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 227,
"real_time": 3.0903953767590849e+06,
"cpu_time": 4.0053733303963104e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7860313789340937e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0855158231085753e+06,
"cpu_time": 4.0012384669603119e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7967916310622883e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time_median",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0871762992559816e+06,
"cpu_time": 4.0045507885462544e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7931073470129323e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.0619710468133617e+03,
"cpu_time": 6.2987637798451005e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5598347829177293e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):21/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2887489326496513e-03,
"cpu_time": 1.5742035451913939e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2949574852185644e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 194,
"real_time": 3.6141232229750026e+06,
"cpu_time": 5.0804254845361682e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1605315428474560e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 194,
"real_time": 3.6108860813234886e+06,
"cpu_time": 5.0735906082473826e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1615719536803203e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 194,
"real_time": 3.6080671371123996e+06,
"cpu_time": 5.0640611288661873e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1624794774070575e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 194,
"real_time": 3.6080852690988132e+06,
"cpu_time": 5.0661638659792133e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1624736355101733e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 194,
"real_time": 3.6202304679708383e+06,
"cpu_time": 5.0818327061855616e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1585737529994695e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6122784356961087e+06,
"cpu_time": 5.0732147587629026e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1611260724888954e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time_median",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6108860813234881e+06,
"cpu_time": 5.0735906082473826e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1615719536803203e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.0964298769279603e+03,
"cpu_time": 8.0608448082860414e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6366307826507480e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):22/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4108629685258042e-03,
"cpu_time": 1.5889027355608476e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4095203108673629e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 144,
"real_time": 4.8802905496106381e+06,
"cpu_time": 7.5373389027776718e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7188747093488655e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 144,
"real_time": 4.9177496952729095e+06,
"cpu_time": 7.5858980069444859e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7057818148132641e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 144,
"real_time": 4.9093407675779117e+06,
"cpu_time": 7.5791113888890035e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7087035504644001e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 144,
"real_time": 4.9012917863567257e+06,
"cpu_time": 7.5752886597225051e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7115096112723987e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 144,
"real_time": 4.9707423022482544e+06,
"cpu_time": 7.6681674513889356e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6875966384750731e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9158830202132892e+06,
"cpu_time": 7.5891608819445223e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7064932648748004e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time_median",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9093407675779117e+06,
"cpu_time": 7.5791113888890045e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7087035504644001e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.3673262537823219e+04,
"cpu_time": 4.8040693046208638e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1629035980159318e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):23/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.8498909350292510e-03,
"cpu_time": 6.3301719114300138e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.8145806488210782e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 87,
"real_time": 7.8259912137498800e+06,
"cpu_time": 1.3335225758620623e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1437816043702247e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 87,
"real_time": 7.9808391405847566e+06,
"cpu_time": 1.3629688770115327e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1021869636092844e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 87,
"real_time": 7.8105944337259075e+06,
"cpu_time": 1.3303861666667212e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1480075738610234e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 87,
"real_time": 7.8407003512156419e+06,
"cpu_time": 1.3351152724137407e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1397598745625851e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 87,
"real_time": 7.8342597738936031e+06,
"cpu_time": 1.3329061666666050e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1415189799944272e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.8584769826339576e+06,
"cpu_time": 1.3389798117241325e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1350509992795091e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time_median",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.8342597738936022e+06,
"cpu_time": 1.3335225758620625e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1415189799944272e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.9323594814586919e+04,
"cpu_time": 1.3517870027842367e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8628938587769300e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):24/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.8215051043327546e-03,
"cpu_time": 1.0095648873477884e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7252897443928935e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51,
"real_time": 1.3672612917919954e+07,
"cpu_time": 2.4968078117648046e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4541345682376499e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51,
"real_time": 1.3693165381019022e+07,
"cpu_time": 2.5002986901959762e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4504510875558372e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51,
"real_time": 1.3715000750095237e+07,
"cpu_time": 2.5056506823529266e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4465497750532022e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51,
"real_time": 1.3691515113939257e+07,
"cpu_time": 2.4982934392155316e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4507464455733185e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51,
"real_time": 1.3652631830351025e+07,
"cpu_time": 2.4959067862745740e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4577262770248799e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3684985198664900e+07,
"cpu_time": 2.4993914819607627e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4519216306889777e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time_median",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3691515113939255e+07,
"cpu_time": 2.4982934392155316e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4507464455733185e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3506925982289722e+04,
"cpu_time": 3.8737827092040658e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.2128197745073307e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):25/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.7177165806933458e-03,
"cpu_time": 1.5498903381734735e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7181706469645809e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 27,
"real_time": 2.5427313314543828e+07,
"cpu_time": 4.8171502370370977e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6392432094512830e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 27,
"real_time": 2.4921568179572072e+07,
"cpu_time": 4.6943311333334513e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6928026164504519e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 27,
"real_time": 2.5441998270926651e+07,
"cpu_time": 4.8323659814812988e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6377198553891635e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 27,
"real_time": 2.5248313943545025e+07,
"cpu_time": 4.8132400407410011e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6579542756817245e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 27,
"real_time": 2.5356415176281221e+07,
"cpu_time": 4.8299337222222984e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6466227001510315e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5279121776973762e+07,
"cpu_time": 4.7974042229630291e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6548685314247313e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time_median",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5356415176281221e+07,
"cpu_time": 4.8171502370370977e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6466227001510315e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.1404289948572969e+05,
"cpu_time": 5.8191994473077171e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2664609715850834e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):26/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.4671809952154686e-03,
"cpu_time": 1.2129891868302050e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.5369988937598739e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 4.5987235009670258e+07,
"cpu_time": 8.8157721133332714e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9185866028209028e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 4.5855277031660080e+07,
"cpu_time": 8.8001038000000641e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9269854352276926e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 4.5749730120102562e+07,
"cpu_time": 8.7897971399994880e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9337381367638788e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.5909112940231957e+07,
"cpu_time": 8.8082366466665015e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9235530683142371e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 4.7342442969481148e+07,
"cpu_time": 9.0707495200005427e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.8350401792007685e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.6168759614229202e+07,
"cpu_time": 8.8569318439999729e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9075806844654961e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time_median",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.5909112940231957e+07,
"cpu_time": 8.8082366466665000e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9235530683142371e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.6176983202130289e+05,
"cpu_time": 1.1991647020776926e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0924103079999201e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):27/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4333714779232351e-02,
"cpu_time": 1.3539278874433847e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4074967308266573e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.7171311490237713e+07,
"cpu_time": 1.6687689924999917e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0794013696818361e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.7371034547686577e+07,
"cpu_time": 1.6698298187499461e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0723621093611932e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.7616494856774807e+07,
"cpu_time": 1.6822784099998954e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0637547922774916e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.6928851902484894e+07,
"cpu_time": 1.6639381837499911e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0879903521689863e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.7251216173171997e+07,
"cpu_time": 1.6690378212500435e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0765812532311559e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.7267781794071198e+07,
"cpu_time": 1.6707706452499738e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0760179753441334e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time_median",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.7251216173171997e+07,
"cpu_time": 1.6690378212500435e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0765812532311559e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5333591433128351e+05,
"cpu_time": 6.8375000353771984e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.9282341625206042e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):28/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.9029718542530280e-03,
"cpu_time": 4.0924228916855319e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9025299052492523e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6968788579106331e+08,
"cpu_time": 3.1570625425001711e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1638729511961102e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6865859553217888e+08,
"cpu_time": 3.1316388474999714e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1831814459617553e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6979648545384407e+08,
"cpu_time": 3.1632591599998248e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1618493784780846e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.6849016025662422e+08,
"cpu_time": 3.1315797100000966e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1863635905046439e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6925453022122383e+08,
"cpu_time": 3.1552646475000757e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1719736617878637e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6917753145098689e+08,
"cpu_time": 3.1477609815000278e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1734482055856919e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time_median",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6925453022122383e+08,
"cpu_time": 3.1552646475000757e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1719736617878637e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.8976013499814342e+05,
"cpu_time": 1.5039733453094638e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1067245616213638e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):29/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.4860429156279844e-03,
"cpu_time": 4.7779146960286777e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4874511569887327e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.8685695827007294e+08,
"cpu_time": 6.2776363250003445e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.7755525680641847e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.1934462487697601e+08,
"cpu_time": 5.5911707400002801e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3623294095325613e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.1974454224109650e+08,
"cpu_time": 5.6024478450001431e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3581240088544436e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.2095086574554443e+08,
"cpu_time": 5.6141737800004423e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3455021892705584e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.2025869190692902e+08,
"cpu_time": 5.6055897249996173e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3527328098624787e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.3343113660812378e+08,
"cpu_time": 5.7382036830001664e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2388481971168456e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time_median",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.2025869190692902e+08,
"cpu_time": 5.6055897249996173e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3527328098624787e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.9871983356412269e+07,
"cpu_time": 3.0166446087841026e+07,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5906656868803307e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/3/log2(N):30/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.9589663581779791e-02,
"cpu_time": 5.2571236146969222e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.9987252542014373e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 310,
"real_time": 2.2557357483873926e+06,
"cpu_time": 2.5737172322582440e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8158155284492865e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 310,
"real_time": 2.2594983343996350e+06,
"cpu_time": 2.5808855419357666e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8127917766703453e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 310,
"real_time": 2.2586957536517614e+06,
"cpu_time": 2.5764592548383796e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8134359146767620e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 310,
"real_time": 2.2613507094642809e+06,
"cpu_time": 2.5788257129031606e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8113068365987123e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 310,
"real_time": 2.2568093139618156e+06,
"cpu_time": 2.5781528483871478e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8149517438890289e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2584179719729768e+06,
"cpu_time": 2.5776081180645400e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8136603600568268e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time_median",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2586957536517614e+06,
"cpu_time": 2.5781528483871478e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8134359146767620e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2151410105829741e+03,
"cpu_time": 2.6916377274049946e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7787852950411109e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):12/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.8083748804381177e-04,
"cpu_time": 1.0442385359284469e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.8077089526584622e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 310,
"real_time": 2.2610529731478421e+06,
"cpu_time": 2.5776946612902596e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6230907003452829e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 310,
"real_time": 2.2641837837234619e+06,
"cpu_time": 2.5861608935484113e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6180808549596681e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 310,
"real_time": 2.2574678746863240e+06,
"cpu_time": 2.5799723516126596e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6288445527218333e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 310,
"real_time": 2.2585244218428289e+06,
"cpu_time": 2.5796962193548861e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6271469640854220e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 310,
"real_time": 2.2619623773460905e+06,
"cpu_time": 2.5787310612900588e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6216340652011586e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2606382861493095e+06,
"cpu_time": 2.5804510374192549e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6237594274626733e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time_median",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2610529731478421e+06,
"cpu_time": 2.5796962193548861e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6230907003452829e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6933096276830220e+03,
"cpu_time": 3.3150141277378580e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3169563826459917e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):13/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.1913934414827191e-03,
"cpu_time": 1.2846646108244895e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1912922115993470e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2688063282013228e+06,
"cpu_time": 2.5932572103559538e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2214185037949011e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2704814746071701e+06,
"cpu_time": 2.5907870453074411e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2160905883782627e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2695199428216633e+06,
"cpu_time": 2.5890686763752401e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2191478430588245e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2654163622535453e+06,
"cpu_time": 2.5907805307444278e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2322246245727008e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2686484727924117e+06,
"cpu_time": 2.5882891650484405e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2219209791605230e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2685745161352227e+06,
"cpu_time": 2.5904365255663004e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2221605077930428e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time_median",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2688063282013228e+06,
"cpu_time": 2.5907805307444273e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2214185037949011e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.9081053820492114e+03,
"cpu_time": 1.9157005853716407e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0789485311310727e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):14/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.4110324279754677e-04,
"cpu_time": 7.3952809361072663e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4170775830468014e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 307,
"real_time": 2.2879209238975174e+06,
"cpu_time": 2.6141247166125593e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4322173313655913e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 307,
"real_time": 2.2899472907015672e+06,
"cpu_time": 2.6168503420193871e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4309499669732977e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 307,
"real_time": 2.2837015434626355e+06,
"cpu_time": 2.6101289869706132e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4348635045504197e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 307,
"real_time": 2.2893906980510256e+06,
"cpu_time": 2.6207510684036654e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4312978570191462e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 307,
"real_time": 2.2824022885569725e+06,
"cpu_time": 2.6085248892505700e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4356802989676837e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2866725489339437e+06,
"cpu_time": 2.6140760006513591e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4330017917752275e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time_median",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2879209238975174e+06,
"cpu_time": 2.6141247166125597e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4322173313655913e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.4180661753574336e+03,
"cpu_time": 4.9661259437143008e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1429612715418178e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):15/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4947772810544957e-03,
"cpu_time": 1.8997634125698230e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4954351654278674e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 299,
"real_time": 2.3308925230965568e+06,
"cpu_time": 2.6657853812711225e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8116268489692688e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 299,
"real_time": 2.3229887902138624e+06,
"cpu_time": 2.6589355384614011e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8211931231044181e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 299,
"real_time": 2.3283207100694594e+06,
"cpu_time": 2.6690462709031487e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8147325115724672e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 299,
"real_time": 2.3232750730109354e+06,
"cpu_time": 2.6587875685619572e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8208454849500950e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 299,
"real_time": 2.3282891424391479e+06,
"cpu_time": 2.6631641304348223e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8147706745453261e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3267532477659923e+06,
"cpu_time": 2.6631437779264906e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8166337286283154e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time_median",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3282891424391484e+06,
"cpu_time": 2.6631641304348223e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8147706745453261e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.4719717406486561e+03,
"cpu_time": 4.4301169627904919e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.2036118407641421e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):16/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4921959361106443e-03,
"cpu_time": 1.6634914718122195e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4924240230593550e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 291,
"real_time": 2.3880969337747782e+06,
"cpu_time": 2.7493104467353499e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4885544278480880e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 291,
"real_time": 2.3980329086831245e+06,
"cpu_time": 2.7551501958762938e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4658132307274282e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 291,
"real_time": 2.3929481226566834e+06,
"cpu_time": 2.7538620481101535e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4774275613832407e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 291,
"real_time": 2.3912678183059613e+06,
"cpu_time": 2.7493609140892532e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4812764591485590e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 291,
"real_time": 2.3924724952577008e+06,
"cpu_time": 2.7539792096219864e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4785164828355454e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3925636557356501e+06,
"cpu_time": 2.7523325628866078e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4783176323885731e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time_median",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3924724952577013e+06,
"cpu_time": 2.7538620481101540e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4785164828355454e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.5951235224781549e+03,
"cpu_time": 2.7818028680039761e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.2270660908066129e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):17/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.5026239798718124e-03,
"cpu_time": 1.0107073925276168e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5017504721097326e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 278,
"real_time": 2.5094039570674193e+06,
"cpu_time": 2.8925093165468797e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0446464757565418e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 278,
"real_time": 2.5126292778969668e+06,
"cpu_time": 2.8997292266183603e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0433055218532301e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 278,
"real_time": 2.5117538899531681e+06,
"cpu_time": 2.9021617014388223e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0436691311539590e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 278,
"real_time": 2.5077187498066602e+06,
"cpu_time": 2.8902813992808270e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0453484866283779e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 278,
"real_time": 2.5128105541409776e+06,
"cpu_time": 2.8962083741007256e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0432302569248632e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5108632857730384e+06,
"cpu_time": 2.8961780035971231e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0440399744633944e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time_median",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5117538899531681e+06,
"cpu_time": 2.8962083741007252e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0436691311539590e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2204450452323645e+03,
"cpu_time": 4.9154337117414680e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.2366603718551865e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):18/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.8433530324560829e-04,
"cpu_time": 1.6972139508125469e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.8470370845738502e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 268,
"real_time": 2.6076766653611921e+06,
"cpu_time": 3.0645877089549270e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0105560131910765e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 268,
"real_time": 2.6103679903908009e+06,
"cpu_time": 3.0670256753730983e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0084831024973929e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 268,
"real_time": 2.6053476917084805e+06,
"cpu_time": 3.0616844626866053e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0123532903824952e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 268,
"real_time": 2.6058336831073263e+06,
"cpu_time": 3.0590759589552078e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0119779838551047e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 268,
"real_time": 2.6069095135847135e+06,
"cpu_time": 3.0605062089551808e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0111476722452909e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6072271088305023e+06,
"cpu_time": 3.0625760029850034e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0109036124342719e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time_median",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6069095135847135e+06,
"cpu_time": 3.0616844626866048e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0111476722452909e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.9774951803255785e+03,
"cpu_time": 3.2084164675208399e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5243932307642934e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):19/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.5846679164539828e-04,
"cpu_time": 1.0476201943702588e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5806379845275629e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 250,
"real_time": 2.7833141256123781e+06,
"cpu_time": 3.3724455359997591e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7673649206565744e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 250,
"real_time": 2.7916020993143320e+06,
"cpu_time": 3.3871314680000069e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7561800095276803e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 250,
"real_time": 2.7848885180428624e+06,
"cpu_time": 3.3729553680000212e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7652351008179975e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 250,
"real_time": 2.7864680057391524e+06,
"cpu_time": 3.3784324799999013e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7631008066136020e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 250,
"real_time": 2.7845307402312756e+06,
"cpu_time": 3.3740853760000393e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7657188870283693e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7861606977880010e+06,
"cpu_time": 3.3770100455999458e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7635199449288452e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time_median",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7848885180428624e+06,
"cpu_time": 3.3740853760000393e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7652351008179975e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.2435114007936713e+03,
"cpu_time": 6.1297504358417764e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3763932935694890e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):20/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.1641508701808810e-03,
"cpu_time": 1.8151413093450807e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1628457820361655e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 226,
"real_time": 3.1013178414525054e+06,
"cpu_time": 3.9722275752213309e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7621318007760108e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 226,
"real_time": 3.1019932367896610e+06,
"cpu_time": 3.9747942876106892e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7606594854165471e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 226,
"real_time": 3.1060740151813468e+06,
"cpu_time": 3.9795687699115584e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7517772910429466e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 226,
"real_time": 3.0998127026054845e+06,
"cpu_time": 3.9712687389379605e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7654152079487956e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 226,
"real_time": 3.1017292047793097e+06,
"cpu_time": 3.9729600486727566e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7612349806959176e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.1021854001616617e+06,
"cpu_time": 3.9741638840708598e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7602437531760430e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time_median",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.1017292047793092e+06,
"cpu_time": 3.9729600486727571e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7612349806959176e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3317761231727372e+03,
"cpu_time": 3.2859768919740209e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0780167041867832e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):21/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.5165595294569539e-04,
"cpu_time": 8.2683477275428627e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5115881757977594e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 185,
"real_time": 3.7742542065176610e+06,
"cpu_time": 5.2662236324325735e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1112934557394056e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 185,
"real_time": 3.7756216234049280e+06,
"cpu_time": 5.2741234054055158e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1108909785873871e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 185,
"real_time": 3.7750317262032549e+06,
"cpu_time": 5.2759846918919524e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1110645695734136e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 185,
"real_time": 3.7680669989738916e+06,
"cpu_time": 5.2761789243240366e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1131182118423531e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 185,
"real_time": 3.7676483732522340e+06,
"cpu_time": 5.2816254270270737e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1132418910896075e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.7721245856703944e+06,
"cpu_time": 5.2748272162162308e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1119218213664334e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time_median",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.7742542065176615e+06,
"cpu_time": 5.2759846918919533e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1112934557394056e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.9279928512944302e+03,
"cpu_time": 5.5655084792592288e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1582632557411117e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):22/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0413210810205342e-03,
"cpu_time": 1.0551072577599065e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0416768818492380e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 134,
"real_time": 5.1886738840935389e+06,
"cpu_time": 8.0066184626866067e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6167152122850151e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 134,
"real_time": 5.2337987911400953e+06,
"cpu_time": 8.0660813805971928e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6027761736275463e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 134,
"real_time": 5.2881904933323609e+06,
"cpu_time": 8.1433110223877095e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.5862908135735304e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 134,
"real_time": 5.3593276290973620e+06,
"cpu_time": 8.2071629776123706e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.5652351527187452e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 134,
"real_time": 5.2725978286019461e+06,
"cpu_time": 8.1279364552240474e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.5909819547576377e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.2685177252530595e+06,
"cpu_time": 8.1102220597015843e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.5923998613924952e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time_median",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.2725978286019452e+06,
"cpu_time": 8.1279364552240465e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.5909819547576377e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.3699582103226800e+04,
"cpu_time": 7.6629507521577369e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9210390849937435e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):23/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.2090607913854393e-02,
"cpu_time": 9.4485091724352804e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2063798368544603e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 83,
"real_time": 8.4043171548520233e+06,
"cpu_time": 1.3911874373493230e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.9962616463508987e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 83,
"real_time": 8.4143913160246536e+06,
"cpu_time": 1.3920589168674543e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.9938716147000315e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 83,
"real_time": 8.3965637934315633e+06,
"cpu_time": 1.3907235469879109e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.9981049882720387e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 83,
"real_time": 8.4124885679009445e+06,
"cpu_time": 1.3913774361445708e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.9943225912978795e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 83,
"real_time": 8.4356020417917203e+06,
"cpu_time": 1.3941384313252784e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.9888581652953987e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.4126725748001821e+06,
"cpu_time": 1.3918971537349071e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.9942838011832495e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time_median",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.4124885679009445e+06,
"cpu_time": 1.3913774361445706e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.9943225912978795e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4646281661711924e+04,
"cpu_time": 1.3417012584015101e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4685108272456061e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):24/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.7409784502471026e-03,
"cpu_time": 9.6393706589692658e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7392262952683401e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 48,
"real_time": 1.4164700347464532e+07,
"cpu_time": 2.5213454604165498e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3688769389326482e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 48,
"real_time": 1.4471514732576907e+07,
"cpu_time": 2.5283794437501211e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3186537567118273e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 48,
"real_time": 1.4460541521354267e+07,
"cpu_time": 2.5265395520833064e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3204132397427354e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 48,
"real_time": 1.4504024855947742e+07,
"cpu_time": 2.5246892937500339e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3134565979621964e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 48,
"real_time": 1.4425537995217988e+07,
"cpu_time": 2.5257810479165718e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3260437157437849e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4405263890512288e+07,
"cpu_time": 2.5253469595833175e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3294888498186388e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time_median",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4460541521354269e+07,
"cpu_time": 2.5257810479165722e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3204132397427354e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3736846108612648e+05,
"cpu_time": 2.6101336029888618e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2472703182476290e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):25/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.5359906024770017e-03,
"cpu_time": 1.0335742552459147e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.6470533371412742e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 26,
"real_time": 2.6563442455461390e+07,
"cpu_time": 4.8400259730770431e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5263617135663285e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 26,
"real_time": 2.6636882541844480e+07,
"cpu_time": 4.8559409653845564e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5193963255488768e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 26,
"real_time": 2.6616076508966777e+07,
"cpu_time": 4.8566216692305572e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5213657609299207e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 26,
"real_time": 2.6523620964815982e+07,
"cpu_time": 4.8404630230768710e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5301546907573819e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 26,
"real_time": 2.6596519451301832e+07,
"cpu_time": 4.8481061230771817e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5232197815536046e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6587308384478092e+07,
"cpu_time": 4.8482315507692426e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5240996544712224e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time_median",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6596519451301832e+07,
"cpu_time": 4.8481061230771825e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5232197815536046e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.4709383266557648e+04,
"cpu_time": 8.0238148869174503e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.2470586580361705e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):26/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6816062242938207e-03,
"cpu_time": 1.6549982819290790e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6826033990032354e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 14,
"real_time": 4.9688668123313360e+07,
"cpu_time": 9.0970973500004336e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.7011737901066132e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 14,
"real_time": 4.9784063494631223e+07,
"cpu_time": 9.1046774071425527e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.6959978470715675e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 14,
"real_time": 5.0541587173938751e+07,
"cpu_time": 9.1928049428572327e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.6555898915103321e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 14,
"real_time": 4.9743799758808956e+07,
"cpu_time": 9.1067133785713837e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.6981800475793338e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 14,
"real_time": 4.9871435388922691e+07,
"cpu_time": 9.1090056785714880e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.6912746134796848e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9925910787923001e+07,
"cpu_time": 9.1220597514286190e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.6884432379495068e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time_median",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9784063494631223e+07,
"cpu_time": 9.1067133785713851e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.6959978470715675e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.5056887513064337e+05,
"cpu_time": 3.9799715659350564e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8716994941846836e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):27/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.0217822689264877e-03,
"cpu_time": 4.3630185225565395e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.9620197583648491e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 7,
"real_time": 9.5718240099293843e+07,
"cpu_time": 1.7369690885714459e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.8044336766068516e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 7,
"real_time": 9.6884803048201963e+07,
"cpu_time": 1.7476988785714248e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.7706662712257199e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 7,
"real_time": 9.6195612634931296e+07,
"cpu_time": 1.7440097328570962e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.7905166217791066e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 7,
"real_time": 9.5918789505958557e+07,
"cpu_time": 1.7401223585714629e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.7985700964598241e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 7,
"real_time": 9.5920642571789876e+07,
"cpu_time": 1.7392209828571075e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.7985160316153522e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.6127617572035104e+07,
"cpu_time": 1.7416042082857075e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.7925405395373707e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time_median",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.5920642571789891e+07,
"cpu_time": 1.7401223585714629e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.7985160316153522e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.5606767617256287e+05,
"cpu_time": 4.2512213286297384e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3191745798787968e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):28/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.7443979960368789e-03,
"cpu_time": 2.4409801655304289e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.7239227549310328e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.8797419592738152e+08,
"cpu_time": 3.3399792100001943e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8560883548474112e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.8609407916665077e+08,
"cpu_time": 3.3069588974998963e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8849435425574284e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.8805139139294624e+08,
"cpu_time": 3.3447744750000650e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8549159249674015e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.8614443764090538e+08,
"cpu_time": 3.3121469475000256e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8841630660792961e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.8789599463343620e+08,
"cpu_time": 3.3403039449999028e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8572770433312020e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8723201975226402e+08,
"cpu_time": 3.3288326950000167e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8674775863565483e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time_median",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8789599463343620e+08,
"cpu_time": 3.3399792100001943e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8572770433312020e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0174479874416844e+06,
"cpu_time": 1.7796431590962030e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5612702110904442e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):29/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.4341559140788000e-03,
"cpu_time": 5.3461478006067058e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.4447512284628279e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.7224625051021576e+08,
"cpu_time": 6.1585569449999869e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.8844933227085190e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.7160824239253998e+08,
"cpu_time": 6.1640326650001502e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.8894456621491647e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.7108102440834045e+08,
"cpu_time": 6.1637449250002873e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.8935508780380163e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.6749900877475739e+08,
"cpu_time": 6.1308640199996483e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.9217543404534831e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.7075382471084595e+08,
"cpu_time": 6.1606736649997628e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.8961045104185247e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.7063767015933990e+08,
"cpu_time": 6.1555744439999676e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.8970697427535419e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time_median",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.7108102440834045e+08,
"cpu_time": 6.1606736649997628e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.8935508780380163e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8432845251193587e+06,
"cpu_time": 1.3998220275730046e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4482199350849994e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/4/log2(N):30/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9732789555009798e-03,
"cpu_time": 2.2740721281300645e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9989129143592093e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 311,
"real_time": 2.2516541978062829e+06,
"cpu_time": 2.5739511736333407e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8191070387231780e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 311,
"real_time": 2.2594752104599569e+06,
"cpu_time": 2.5869287556271888e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8128103291587720e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 311,
"real_time": 2.2508423817358981e+06,
"cpu_time": 2.5728422765273373e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8197631398965735e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 311,
"real_time": 2.2507605728336950e+06,
"cpu_time": 2.5792025369775929e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8198292832378699e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 311,
"real_time": 2.2590610751181459e+06,
"cpu_time": 2.5810260482312427e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8131426569712309e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2543586875907956e+06,
"cpu_time": 2.5787901581993410e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8169304895975247e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time_median",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2516541978062829e+06,
"cpu_time": 2.5792025369775924e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8191070387231780e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.4976759662320101e+03,
"cpu_time": 5.7052409368087438e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.6224189579693380e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):12/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.9951021951340932e-03,
"cpu_time": 2.2123711456974345e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9937025542302138e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 311,
"real_time": 2.2651694020274370e+06,
"cpu_time": 2.5884518360131970e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6165065591420056e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 311,
"real_time": 2.2517293564364361e+06,
"cpu_time": 2.5759160160771771e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6380926404781500e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 311,
"real_time": 2.2513584280236838e+06,
"cpu_time": 2.5815215755625935e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6386920438924539e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 311,
"real_time": 2.2573159929736252e+06,
"cpu_time": 2.5816985627011419e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6290887166437209e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 311,
"real_time": 2.2512349566606465e+06,
"cpu_time": 2.5813883344052760e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6388916118073906e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2553616272243657e+06,
"cpu_time": 2.5817952649518773e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6322543143927441e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time_median",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2517293564364361e+06,
"cpu_time": 2.5815215755625935e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6380926404781500e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.0469082372718840e+03,
"cpu_time": 4.4476217041126201e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.7159267971631016e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):13/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6811257956506551e-03,
"cpu_time": 1.7226856693439323e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6749026792160205e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2607890498737013e+06,
"cpu_time": 2.5879452750807023e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2470273159343600e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2705376824864387e+06,
"cpu_time": 2.6005925177992950e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2159119517708579e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2663341881858008e+06,
"cpu_time": 2.5942505987055358e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2292956993758194e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2627711861204463e+06,
"cpu_time": 2.5982838543688385e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2406790843446273e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2608496318043820e+06,
"cpu_time": 2.5969637766989842e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2468331239366606e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2642563476941539e+06,
"cpu_time": 2.5956072045306703e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2359494350724658e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time_median",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2627711861204463e+06,
"cpu_time": 2.5969637766989837e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2406790843446273e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.1715153153597093e+03,
"cpu_time": 4.8580766012458489e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3316499592845335e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):14/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8423334970918144e-03,
"cpu_time": 1.8716532273319339e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8403251311155651e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 307,
"real_time": 2.2768980272854483e+06,
"cpu_time": 2.6145778729639226e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4391509679977411e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 307,
"real_time": 2.2762304002036876e+06,
"cpu_time": 2.6140338273615967e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4395730764806483e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 307,
"real_time": 2.2766796693035951e+06,
"cpu_time": 2.6081632410424282e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4392889980004644e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 307,
"real_time": 2.2819586521384674e+06,
"cpu_time": 2.6201082019544733e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4359594101011636e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 307,
"real_time": 2.2768463927293834e+06,
"cpu_time": 2.6091839055375601e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4391836052110288e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2777226283321166e+06,
"cpu_time": 2.6132134097719966e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4386312115582094e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time_median",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2768463927293834e+06,
"cpu_time": 2.6140338273615967e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4391836052110288e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3825491455637316e+03,
"cpu_time": 4.7909840490288143e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5027974800403495e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):15/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0460225121038443e-03,
"cpu_time": 1.8333688443175520e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0446023052792248e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 304,
"real_time": 2.3029978527981592e+06,
"cpu_time": 2.6508730526313535e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8456822015866529e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 304,
"real_time": 2.3033983820105754e+06,
"cpu_time": 2.6470629769739006e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8451873766966596e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 304,
"real_time": 2.3089810243905769e+06,
"cpu_time": 2.6574321315792594e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8383082973710150e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 304,
"real_time": 2.3029021004300662e+06,
"cpu_time": 2.6461227335528145e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8458005222089630e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 304,
"real_time": 2.3182584179602074e+06,
"cpu_time": 2.6613117631577821e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8269497262373328e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3073075555179170e+06,
"cpu_time": 2.6525605315790223e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8403856248201251e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time_median",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3033983820105754e+06,
"cpu_time": 2.6508730526313530e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8451873766966596e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.6329687145745365e+03,
"cpu_time": 6.6112116131133735e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.1435606510028825e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):16/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.8747657410091768e-03,
"cpu_time": 2.4923885937403424e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8670616341112468e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 296,
"real_time": 2.3621171539825564e+06,
"cpu_time": 2.7292035472973529e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5489203733612925e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 296,
"real_time": 2.3686960921622813e+06,
"cpu_time": 2.7309713614865383e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5335085169305101e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 296,
"real_time": 2.3626209161168821e+06,
"cpu_time": 2.7337253716218676e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5477372229238190e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 296,
"real_time": 2.3620485538943997e+06,
"cpu_time": 2.7242265033783503e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5490815285696216e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 296,
"real_time": 2.3623361264833729e+06,
"cpu_time": 2.7337381925678058e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5484060261617705e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3635637685278985e+06,
"cpu_time": 2.7303729952703831e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5455307335894026e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time_median",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3623361264833729e+06,
"cpu_time": 2.7309713614865383e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5484060261617705e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.8777330738876008e+03,
"cpu_time": 3.9391621356645142e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.7410570146676546e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):17/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.2175398490221158e-03,
"cpu_time": 1.4427194169031206e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2155837445525137e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 281,
"real_time": 2.4908162053555143e+06,
"cpu_time": 2.8910274341640072e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0524421650877455e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 281,
"real_time": 2.4925420562872575e+06,
"cpu_time": 2.8892442028470030e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0517134478784847e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 281,
"real_time": 2.4970106861729743e+06,
"cpu_time": 2.8889119039146351e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0498313101005311e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 281,
"real_time": 2.4983522041412434e+06,
"cpu_time": 2.8906412775803125e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0492675915168115e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 281,
"real_time": 2.4944472862440706e+06,
"cpu_time": 2.8898351672600727e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0509101613236110e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4946336876402129e+06,
"cpu_time": 2.8899319971532067e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0508329351814370e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time_median",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4944472862440711e+06,
"cpu_time": 2.8898351672600731e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0509101613236110e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.1008194551813963e+03,
"cpu_time": 8.9806572963907183e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3061815500725769e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):18/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.2429959037852177e-03,
"cpu_time": 3.1075669964681941e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2429963948998718e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 271,
"real_time": 2.5823362793677188e+06,
"cpu_time": 3.0482064501843373e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0302855371275315e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 271,
"real_time": 2.5881918961683982e+06,
"cpu_time": 3.0551845202953331e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0256921473873886e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 271,
"real_time": 2.5811377050169501e+06,
"cpu_time": 3.0476618856090852e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0312283183533484e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 271,
"real_time": 2.5850556699758414e+06,
"cpu_time": 3.0466498560884837e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0281497458230743e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 271,
"real_time": 2.5858928679705104e+06,
"cpu_time": 3.0483040295201815e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0274931204380387e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5845228836998837e+06,
"cpu_time": 3.0492013483394841e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0285697738258764e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time_median",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5850556699758414e+06,
"cpu_time": 3.0482064501843369e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0281497458230743e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.8223679696827335e+03,
"cpu_time": 3.4085703842656194e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2151773445934302e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):19/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0920266899097297e-03,
"cpu_time": 1.1178567745688025e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0919897225992934e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 254,
"real_time": 2.7403224728942858e+06,
"cpu_time": 3.3403207795272712e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8264693676452994e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 254,
"real_time": 2.7477448195673702e+06,
"cpu_time": 3.3457566338582430e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8161331159022886e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 254,
"real_time": 2.7395111030172994e+06,
"cpu_time": 3.3364872125982014e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8276026654723084e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 254,
"real_time": 2.7401964391002390e+06,
"cpu_time": 3.3382656614173008e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8266453639517421e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 254,
"real_time": 2.7336515614572237e+06,
"cpu_time": 3.3305017716532517e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8358070749917996e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7402852792072841e+06,
"cpu_time": 3.3382664118108535e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8265315175926876e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time_median",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7401964391002385e+06,
"cpu_time": 3.3382656614173008e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8266453639517421e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.0064852509036191e+03,
"cpu_time": 5.5628014573066412e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.9879700943836325e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):20/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8269941779024941e-03,
"cpu_time": 1.6663743305882772e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8261890859270487e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 228,
"real_time": 3.0772856369271483e+06,
"cpu_time": 4.0000788289475758e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8149409818652070e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 228,
"real_time": 3.0787200513785998e+06,
"cpu_time": 4.0008418859647582e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8117658150208557e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 228,
"real_time": 3.0772751146159545e+06,
"cpu_time": 3.9901776754384013e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8149642846012676e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 228,
"real_time": 3.0896070601189868e+06,
"cpu_time": 4.0085009429825884e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7877628423053730e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 228,
"real_time": 3.0892288308231193e+06,
"cpu_time": 4.0081765570176374e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7885939010908997e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0824233387727621e+06,
"cpu_time": 4.0015551780701922e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8036055649767208e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time_median",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0787200513785994e+06,
"cpu_time": 4.0008418859647578e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8117658150208557e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.4135618841707146e+03,
"cpu_time": 7.4870265773095352e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4146057600900684e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):21/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.0806882051198762e-03,
"cpu_time": 1.8710291984328608e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0792001337821657e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 164,
"real_time": 3.6231956825160035e+06,
"cpu_time": 5.1077842926828200e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1576255790544026e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 164,
"real_time": 3.6024785552332858e+06,
"cpu_time": 5.0726448658539113e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1642828501801836e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 164,
"real_time": 3.6034082991025615e+06,
"cpu_time": 5.0741224512194097e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1639824443554184e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 164,
"real_time": 3.6058912377395644e+06,
"cpu_time": 5.0766335000001313e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1631809512450230e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 164,
"real_time": 3.6033370983559731e+06,
"cpu_time": 5.0713823536583977e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1640054442626688e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6076621745894775e+06,
"cpu_time": 5.0805134926829347e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1626154538195393e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time_median",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6034082991025611e+06,
"cpu_time": 5.0741224512194097e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1639824443554184e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.7763565412459229e+03,
"cpu_time": 1.5369525650566651e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8195560240576882e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):22/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4326991044400100e-03,
"cpu_time": 3.0251913852216267e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4251836794312374e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 142,
"real_time": 4.9549815422055172e+06,
"cpu_time": 7.6927324436620036e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6929645304523451e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 142,
"real_time": 4.9475268952705907e+06,
"cpu_time": 7.6810932323945025e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6955153913400218e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 142,
"real_time": 4.9513015095931543e+06,
"cpu_time": 7.7163418521124674e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6942228187370651e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 142,
"real_time": 4.9514243425145531e+06,
"cpu_time": 7.7205867394361161e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6941807891463997e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 142,
"real_time": 4.9507595716752633e+06,
"cpu_time": 7.7198702535207607e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6944082778718781e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9511987722518165e+06,
"cpu_time": 7.7061249042251725e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6942583615095422e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time_median",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9513015095931543e+06,
"cpu_time": 7.7163418521124674e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6942228187370651e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6479408571007502e+03,
"cpu_time": 1.8085960878144499e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.0607373757327278e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):23/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.3480802910614328e-04,
"cpu_time": 2.3469592178850091e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.3479077226804036e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 87,
"real_time": 7.8414595182770966e+06,
"cpu_time": 1.3370762597700136e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1395527147586732e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 87,
"real_time": 7.9317053180487677e+06,
"cpu_time": 1.3523532965517258e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1152091923817544e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 87,
"real_time": 7.8487643683008077e+06,
"cpu_time": 1.3390581011494447e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1375614316769364e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 87,
"real_time": 7.8699911259457301e+06,
"cpu_time": 1.3425131770115212e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1317960505303488e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 87,
"real_time": 7.8324093697485570e+06,
"cpu_time": 1.3347183678160684e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1420249131511621e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.8648659400641918e+06,
"cpu_time": 1.3411438404597547e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1332288604997749e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time_median",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.8487643683008077e+06,
"cpu_time": 1.3390581011494447e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1375614316769364e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.9856994776559812e+04,
"cpu_time": 6.8867482947422599e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0757488454958249e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):24/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.0677271653831275e-03,
"cpu_time": 5.1349811161056583e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0428196684147494e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51,
"real_time": 1.3717449617152121e+07,
"cpu_time": 2.5018465313725274e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4461130120021710e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51,
"real_time": 1.3743159489012232e+07,
"cpu_time": 2.5017632764707275e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4415369716714005e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51,
"real_time": 1.3714381183187166e+07,
"cpu_time": 2.4977930098039977e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4466603014604325e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51,
"real_time": 1.3750870748623913e+07,
"cpu_time": 2.5098813803921591e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4401677983452706e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51,
"real_time": 1.3686876999689084e+07,
"cpu_time": 2.4980000647059675e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4515769375849752e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3722547607532904e+07,
"cpu_time": 2.5018568525490757e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4452110042128501e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time_median",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3717449617152119e+07,
"cpu_time": 2.5017632764707275e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4461130120021710e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5456444350155802e+04,
"cpu_time": 4.8936576411519716e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5379408546167724e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):25/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8550815109711588e-03,
"cpu_time": 1.9560102474152161e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8558483692402666e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 27,
"real_time": 2.5280004643179752e+07,
"cpu_time": 4.8152698148147397e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6546222972354231e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 27,
"real_time": 2.5533130944327071e+07,
"cpu_time": 4.8430864148149006e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6283053240249090e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 27,
"real_time": 2.5476656785165820e+07,
"cpu_time": 4.8394072592596211e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6341314940143628e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 27,
"real_time": 2.5338641540319830e+07,
"cpu_time": 4.8274759962964714e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6484791575433817e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 27,
"real_time": 2.5381640151694968e+07,
"cpu_time": 4.8290729962963670e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6439924133712263e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5402014812937491e+07,
"cpu_time": 4.8308624962964199e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6419061372378612e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time_median",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5381640151694968e+07,
"cpu_time": 4.8290729962963670e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6439924133712263e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0256783603460995e+05,
"cpu_time": 1.0957184473298893e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0661672786425214e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):26/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.0377834904013659e-03,
"cpu_time": 2.2681631865322637e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0355986293941909e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 4.5976659407218300e+07,
"cpu_time": 8.8069820999999136e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9192579393649449e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 4.6133630226055779e+07,
"cpu_time": 8.8285410533338413e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9093250919628534e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 4.6003699302673340e+07,
"cpu_time": 8.8122344066664487e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9175420680180044e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.6192106356223427e+07,
"cpu_time": 8.8325462866661534e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9056420801628361e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 4.5994377136230469e+07,
"cpu_time": 8.8225377866668478e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9181333970989828e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.6060094485680260e+07,
"cpu_time": 8.8205683266666412e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9139801153215241e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time_median",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.6003699302673340e+07,
"cpu_time": 8.8225377866668463e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9175420680180044e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.6559875311308599e+04,
"cpu_time": 1.0781401190239980e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.1029655896260794e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):27/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.0963889976675656e-03,
"cpu_time": 1.2223023268971552e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0943744802982937e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.6735498160123825e+07,
"cpu_time": 1.6476265887500575e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0948742059962220e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.7685842067003250e+07,
"cpu_time": 1.6712701699999854e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0613317916805863e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.7514041922986507e+07,
"cpu_time": 1.6715732875000811e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0673415385867639e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.7573600932955742e+07,
"cpu_time": 1.6718349525000066e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0652554324619789e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.6679159663617611e+07,
"cpu_time": 1.6514984849999335e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0968857686407881e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.7237628549337387e+07,
"cpu_time": 1.6627606967500132e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0771377474732685e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time_median",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.7514041922986507e+07,
"cpu_time": 1.6712701699999854e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0673415385867639e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.8841569825178303e+05,
"cpu_time": 1.2127382720425513e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7259415242414210e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):28/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.5986815136264117e-03,
"cpu_time": 7.2935226001729333e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.6089186311488468e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6712774336338043e+08,
"cpu_time": 3.1155459224999046e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2123386649977016e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.7004135251045227e+08,
"cpu_time": 3.1634329599998522e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1572961757464209e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6853203251957893e+08,
"cpu_time": 3.1271664625000995e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1855719294053483e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.7017734795808792e+08,
"cpu_time": 3.1642078400000173e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1547730555315924e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6815091297030449e+08,
"cpu_time": 3.1272779475000334e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1927921324745445e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6880587786436084e+08,
"cpu_time": 3.1395262264999819e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1805543916311221e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time_median",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6853203251957893e+08,
"cpu_time": 3.1272779475000334e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1855719294053483e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.2968648260118258e+06,
"cpu_time": 2.2685639929937329e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4447903370751448e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):29/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.6825809765574925e-03,
"cpu_time": 7.2258163472097561e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.6866798552731354e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.2943345606327057e+08,
"cpu_time": 5.7380436350001669e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2593587695409374e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.2819971442222595e+08,
"cpu_time": 5.7419784149999487e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2716110856167316e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.2859697937965393e+08,
"cpu_time": 5.7258918000002265e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2676557953365164e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.3091129362583160e+08,
"cpu_time": 5.7719948449999952e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2448025941783133e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.2835920155048370e+08,
"cpu_time": 5.7361568950000215e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2700220335836005e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.2910012900829315e+08,
"cpu_time": 5.7428131180000710e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2626900556512203e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time_median",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.2859697937965393e+08,
"cpu_time": 5.7380436350001669e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2676557953365164e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.1185150502662798e+06,
"cpu_time": 1.7361265761720985e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1057350403086627e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/5/log2(N):30/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.3987074196439888e-03,
"cpu_time": 3.0231291537773440e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3890287506575987e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 311,
"real_time": 2.2557498325692592e+06,
"cpu_time": 2.5811920803858414e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8158041910767776e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 311,
"real_time": 2.2505644680423080e+06,
"cpu_time": 2.5832163954982911e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8199878555636201e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 311,
"real_time": 2.2568153060218049e+06,
"cpu_time": 2.5822285594854308e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8149469250189608e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 311,
"real_time": 2.2545228113339455e+06,
"cpu_time": 2.5797172636653320e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8167924402488074e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 311,
"real_time": 2.2512502568531362e+06,
"cpu_time": 2.5828672829580228e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8194334403877023e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2537805349640907e+06,
"cpu_time": 2.5818443163985834e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8173929704591737e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time_median",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2545228113339455e+06,
"cpu_time": 2.5822285594854308e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8167924402488074e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7560994357804148e+03,
"cpu_time": 1.4165512284491228e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2228889418508370e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):12/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.2228783561769145e-03,
"cpu_time": 5.4865865437815056e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2231195883239344e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 311,
"real_time": 2.2573338954790323e+06,
"cpu_time": 2.5850292154340879e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6290599349998077e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 311,
"real_time": 2.2500535807126109e+06,
"cpu_time": 2.5787973987137852e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6408021880996828e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 311,
"real_time": 2.2568379437485021e+06,
"cpu_time": 2.5848825401930404e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6298574395614211e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 311,
"real_time": 2.2503545596129545e+06,
"cpu_time": 2.5846542315109842e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6403152405499015e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 311,
"real_time": 2.2569773561497880e+06,
"cpu_time": 2.5850142668812014e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6296332250204128e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2543114671405777e+06,
"cpu_time": 2.5836755305466196e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6339336056462452e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time_median",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2568379437485021e+06,
"cpu_time": 2.5848825401930399e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6298574395614211e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.7553906366060100e+03,
"cpu_time": 2.7310975719125131e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0573046400154853e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):13/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6658703516996421e-03,
"cpu_time": 1.0570590384214010e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6668726777517107e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2576278175360388e+06,
"cpu_time": 2.5882699512989167e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2571749305788567e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2575379494432504e+06,
"cpu_time": 2.5954883603896466e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2574638242695276e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2632979610995329e+06,
"cpu_time": 2.5932127272726903e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2389938406697847e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2642044668001207e+06,
"cpu_time": 2.5952256883116420e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2360956089600129e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2642616078245468e+06,
"cpu_time": 2.5946983116881852e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2359129984725537e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2613859605406979e+06,
"cpu_time": 2.5933790077922163e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2451282405901477e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time_median",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2632979610995329e+06,
"cpu_time": 2.5946983116881852e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2389938406697847e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.4928462326551062e+03,
"cpu_time": 2.9887400165841132e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1196309081602796e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):14/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.5445599705677690e-03,
"cpu_time": 1.1524501461621971e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5453569225837205e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2825187838684721e+06,
"cpu_time": 2.6183722759739128e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4356070246424848e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2794430162273832e+06,
"cpu_time": 2.6156757175322301e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4375441617414517e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2722611342883343e+06,
"cpu_time": 2.6135705194805381e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4420877735191666e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2724465589498640e+06,
"cpu_time": 2.6146909740260057e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4419701035848625e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2787197769692093e+06,
"cpu_time": 2.6150085292210979e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4380004216043966e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2770778540606527e+06,
"cpu_time": 2.6154636032467568e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4390418970184727e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time_median",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2787197769692093e+06,
"cpu_time": 2.6150085292210979e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4380004216043966e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.5426672741669254e+03,
"cpu_time": 1.7953539992730730e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8713231961719321e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):15/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.9949547469648907e-03,
"cpu_time": 6.8643815079069551e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9953020145702357e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 303,
"real_time": 2.3181448412425937e+06,
"cpu_time": 2.6628765148515333e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8270882316771362e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 303,
"real_time": 2.3198135215604659e+06,
"cpu_time": 2.6659088745874055e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8250546602520011e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 303,
"real_time": 2.3094572706252532e+06,
"cpu_time": 2.6609651518152896e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8377229937775400e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 303,
"real_time": 2.3131579039280270e+06,
"cpu_time": 2.6647430264026928e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8331831514273971e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 303,
"real_time": 2.3179737522140783e+06,
"cpu_time": 2.6634333894390236e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8272968983104933e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3157094579140833e+06,
"cpu_time": 2.6635853914191891e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8300691870889142e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time_median",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3179737522140783e+06,
"cpu_time": 2.6634333894390231e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8272968983104933e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.2866575755613994e+03,
"cpu_time": 1.8794918833872841e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.2439176755075016e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):16/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8511206407658251e-03,
"cpu_time": 7.0562479034541831e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8529291437222909e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 295,
"real_time": 2.3761902272827546e+06,
"cpu_time": 2.7451024508474991e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5160566900354944e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 295,
"real_time": 2.3821590634031314e+06,
"cpu_time": 2.7461995355933742e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5022354306077145e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 295,
"real_time": 2.3761224246315532e+06,
"cpu_time": 2.7494277186440863e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5162140907080710e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 295,
"real_time": 2.3760112381335031e+06,
"cpu_time": 2.7434957118646060e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5164722243891731e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 295,
"real_time": 2.3847082258849326e+06,
"cpu_time": 2.7521600542371036e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4963537500006303e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3790382358671753e+06,
"cpu_time": 2.7472770942373341e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5094664371482171e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time_median",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3761902272827541e+06,
"cpu_time": 2.7461995355933742e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5160566900354944e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.1129118227343479e+03,
"cpu_time": 3.4877479427466765e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.5167396777336515e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):17/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.7288128289519331e-03,
"cpu_time": 1.2695290002098982e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7273432529810743e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 280,
"real_time": 2.4999175752912248e+06,
"cpu_time": 2.8981136357145943e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0486105725684249e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 280,
"real_time": 2.5019872750687813e+06,
"cpu_time": 2.8959274392856774e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0477431384729704e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 280,
"real_time": 2.4948187122520590e+06,
"cpu_time": 2.8920693750003628e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0507537029148065e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 280,
"real_time": 2.4948123800900900e+06,
"cpu_time": 2.8962375499998773e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0507563698659125e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 280,
"real_time": 2.5013278537829006e+06,
"cpu_time": 2.8948223285713731e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0480193534148060e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4985727592970114e+06,
"cpu_time": 2.8954340657143770e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0491766274473841e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time_median",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4999175752912248e+06,
"cpu_time": 2.8959274392856774e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0486105725684249e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.5103886761699760e+03,
"cpu_time": 2.2228622202550050e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4745630785083424e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):18/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4049575555116695e-03,
"cpu_time": 7.6771294728362896e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4054478911676778e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 271,
"real_time": 2.5851481561497459e+06,
"cpu_time": 3.0527927638376984e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0280771868056539e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 271,
"real_time": 2.5890342344794548e+06,
"cpu_time": 3.0568945276751523e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0250330915589926e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 271,
"real_time": 2.5831372236551172e+06,
"cpu_time": 3.0506437933577574e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0296560136210531e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 271,
"real_time": 2.5881645742226462e+06,
"cpu_time": 3.0495367269371171e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0257135315959173e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 271,
"real_time": 2.5859227673772625e+06,
"cpu_time": 3.0499193837635159e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0274696778038427e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5862813911768454e+06,
"cpu_time": 3.0519574391142484e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0271899002770922e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time_median",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5859227673772625e+06,
"cpu_time": 3.0506437933577569e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0274696778038427e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3676542553787867e+03,
"cpu_time": 3.0336361466854646e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8559873515194008e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):19/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.1546660910761296e-04,
"cpu_time": 9.9399687158347101e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.1554686182370479e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 254,
"real_time": 2.7603840823908607e+06,
"cpu_time": 3.3588906771655716e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7986597832131875e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 254,
"real_time": 2.7504105058564679e+06,
"cpu_time": 3.3502263661416047e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8124345357438821e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 254,
"real_time": 2.7472123633850161e+06,
"cpu_time": 3.3451583582680677e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8168727469906348e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 254,
"real_time": 2.7492375738229458e+06,
"cpu_time": 3.3481841850392073e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8140610690908945e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 254,
"real_time": 2.7441830524632079e+06,
"cpu_time": 3.3443567677163016e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8210862029003024e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7502855155836996e+06,
"cpu_time": 3.3493632708661510e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8126228675877810e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time_median",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7492375738229458e+06,
"cpu_time": 3.3481841850392073e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8140610690908945e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.1192151586111986e+03,
"cpu_time": 5.8235086372368842e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4670115332388680e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):20/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2249381469445374e-03,
"cpu_time": 1.7386912574971049e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2207839136725014e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 228,
"real_time": 3.0778903471256951e+06,
"cpu_time": 3.9959618114032606e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8136020568713152e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 228,
"real_time": 3.0789801579279206e+06,
"cpu_time": 4.0060362324563731e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8111903696428263e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 228,
"real_time": 3.0746804754527514e+06,
"cpu_time": 3.9960361754382523e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8207152474638557e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 228,
"real_time": 3.0730860828618077e+06,
"cpu_time": 3.9989699912279830e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8242540021756554e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 228,
"real_time": 3.0737794535397962e+06,
"cpu_time": 3.9965102938595014e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8227146146900618e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0756833033815939e+06,
"cpu_time": 3.9987029008770743e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8184952581687427e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time_median",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0746804754527514e+06,
"cpu_time": 3.9965102938595014e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8207152474638557e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6036586989000689e+03,
"cpu_time": 4.2802339569146552e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.7705994017952762e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):21/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.4653016649583108e-04,
"cpu_time": 1.0704055947682008e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4631567278454015e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 194,
"real_time": 3.6017217051679478e+06,
"cpu_time": 5.0729440000001900e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1645275074922593e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 194,
"real_time": 3.6018793135113325e+06,
"cpu_time": 5.0720403350510430e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1644765509678156e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 194,
"real_time": 3.6002941340803332e+06,
"cpu_time": 5.0725289175257906e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1649892602653706e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 194,
"real_time": 3.5949745263481876e+06,
"cpu_time": 5.0626354278350491e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1667131350331478e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 194,
"real_time": 3.5965869349629148e+06,
"cpu_time": 5.0643615412371261e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1661900784954190e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.5990913228141433e+06,
"cpu_time": 5.0689020443298398e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1653793064508026e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time_median",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6002941340803327e+06,
"cpu_time": 5.0720403350510430e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1649892602653706e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.1368188518638703e+03,
"cpu_time": 4.9806408744000701e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0160111895446822e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):22/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.7155856034549833e-04,
"cpu_time": 9.8258771442851205e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7182875474164250e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 141,
"real_time": 4.9565851272262158e+06,
"cpu_time": 7.7001673900711350e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6924168121156428e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 141,
"real_time": 4.9463426727299569e+06,
"cpu_time": 7.6984077801414719e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6959213210697768e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 141,
"real_time": 4.9502066376202917e+06,
"cpu_time": 7.7053161843971647e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6945975418983009e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 141,
"real_time": 4.9509907451768713e+06,
"cpu_time": 7.7099158936175155e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6943291619302595e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 141,
"real_time": 4.9475966787613034e+06,
"cpu_time": 7.6978605106379734e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6954914769043381e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9503443723029289e+06,
"cpu_time": 7.7023335517730536e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6945512627836637e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time_median",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.9502066376202917e+06,
"cpu_time": 7.7001673900711359e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6945975418983009e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.9669638902159809e+03,
"cpu_time": 5.1599428675972113e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3572409969640616e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):23/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.0135109638251835e-04,
"cpu_time": 6.6991942544599467e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.0094419494545262e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 88,
"real_time": 7.7557583678175099e+06,
"cpu_time": 1.3219462409091936e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1631947779106932e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 88,
"real_time": 7.7711056960238656e+06,
"cpu_time": 1.3247394318181127e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1589226367856722e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 88,
"real_time": 7.7760621471415190e+06,
"cpu_time": 1.3286786806818636e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1575465425218220e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 88,
"real_time": 7.7613984097049320e+06,
"cpu_time": 1.3232479863635726e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1616228306256766e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 88,
"real_time": 7.7331201120449062e+06,
"cpu_time": 1.3206481238636445e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1695274038053861e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.7594889465465471e+06,
"cpu_time": 1.3238520927272772e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1621628383298502e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time_median",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.7613984097049311e+06,
"cpu_time": 1.3232479863635726e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1616228306256766e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6751854722415301e+04,
"cpu_time": 3.0962055033727822e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.6744632123057721e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):24/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.1588863439094032e-03,
"cpu_time": 2.3387850654783245e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1619385595936583e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51,
"real_time": 1.3780360055320403e+07,
"cpu_time": 2.5024514686274238e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4349459568035817e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51,
"real_time": 1.3757310479002841e+07,
"cpu_time": 2.4977292647057693e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4390255676218553e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51,
"real_time": 1.3793574061756041e+07,
"cpu_time": 2.5020050235293731e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4326133205050001e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51,
"real_time": 1.3747327650586763e+07,
"cpu_time": 2.4977882764705654e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4407967026644506e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51,
"real_time": 1.3775067330867637e+07,
"cpu_time": 2.4998168803922098e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4358815237737598e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3770727915506735e+07,
"cpu_time": 2.4999581827450681e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4366526142737293e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time_median",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3775067330867637e+07,
"cpu_time": 2.4998168803922094e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4358815237737598e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8446917371957526e+04,
"cpu_time": 2.2417943095250921e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2644881154631274e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):25/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3395746023843150e-03,
"cpu_time": 8.9673272337039637e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3397429310768386e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 28,
"real_time": 2.5235588130142007e+07,
"cpu_time": 4.8012729571427472e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6592946300246325e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 28,
"real_time": 2.3803769078637872e+07,
"cpu_time": 4.5595197071427099e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.8192536979458961e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 28,
"real_time": 2.5249839560793977e+07,
"cpu_time": 4.8062098571429193e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6577936797745643e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 28,
"real_time": 2.5309577118605375e+07,
"cpu_time": 4.8078813821429588e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6515205562509170e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 28,
"real_time": 2.5395057363701720e+07,
"cpu_time": 4.8240135249999739e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6425954877314701e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4998766250376195e+07,
"cpu_time": 4.7597794857142620e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6860916103454962e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time_median",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5249839560793981e+07,
"cpu_time": 4.8062098571429193e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6577936797745643e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.7096771396092058e+05,
"cpu_time": 1.1227340593245935e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.4729617733993530e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):26/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6840033113667099e-02,
"cpu_time": 2.3587942733362025e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7820949012376202e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 4.5510763178269066e+07,
"cpu_time": 8.7397548333334878e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9491425462205305e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 4.5511542012294136e+07,
"cpu_time": 8.7394567400004536e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9490920778677082e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 4.5583765457073845e+07,
"cpu_time": 8.7567032133332163e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9444195022983041e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.5560118059317268e+07,
"cpu_time": 8.7394592999999076e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9459477656588688e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 4.4457371532917023e+07,
"cpu_time": 8.5305697533332631e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.0190207691568727e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.5324712047974274e+07,
"cpu_time": 8.7011887680000648e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9615245322404575e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time_median",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.5511542012294129e+07,
"cpu_time": 8.7394592999999076e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9490920778677082e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.8588184948912531e+05,
"cpu_time": 9.5667542173915112e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2206033850489568e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):27/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0720020658373739e-02,
"cpu_time": 1.0994766890444549e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0874815825390110e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.6213306523859501e+07,
"cpu_time": 1.6519723224999440e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1136197742944775e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.6643931455910206e+07,
"cpu_time": 1.6577495549999809e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0981449189733105e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.7588933296501637e+07,
"cpu_time": 1.6745025437499806e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0647188622711711e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.6383188143372536e+07,
"cpu_time": 1.6543791987500355e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1074965137252212e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.6429128423333168e+07,
"cpu_time": 1.6547396875000685e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1058447643390884e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.6651697568595424e+07,
"cpu_time": 1.6586686615000021e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0979649667206540e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time_median",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.6429128423333168e+07,
"cpu_time": 1.6547396875000685e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1058447643390884e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.4596065932663996e+05,
"cpu_time": 9.0861689842490759e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9386531683454882e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):28/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 6.3006343169958699e-03,
"cpu_time": 5.4779891820178729e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2578279263036550e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6837164014577866e+08,
"cpu_time": 3.1388611899998862e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1886065345397196e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6713074594736099e+08,
"cpu_time": 3.1166410525000286e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2122809537934527e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6848930716514587e+08,
"cpu_time": 3.1356534724997687e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1863797236330404e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.6686786711215973e+08,
"cpu_time": 3.1122797249997801e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2173414887549553e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6814399883151054e+08,
"cpu_time": 3.1311663125001132e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1929234211800442e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6780071184039116e+08,
"cpu_time": 3.1269203504999155e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1995064243802428e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time_median",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6814399883151054e+08,
"cpu_time": 3.1311663125001132e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1929234211800442e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.4783390439291159e+05,
"cpu_time": 1.1799270565872099e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4280510540117254e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):29/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.4566789746651190e-03,
"cpu_time": 3.7734477515507219e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4633479812072720e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.2075805962085724e+08,
"cpu_time": 5.6147782100003946e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3475131545227122e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.2014526426792145e+08,
"cpu_time": 5.6145920650004649e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3539206848970056e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.2014636695384979e+08,
"cpu_time": 5.6138625450000751e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3539091329272637e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.2007141411304474e+08,
"cpu_time": 5.6066867399999869e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3546945358287120e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.2110342383384705e+08,
"cpu_time": 5.6250724600005245e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3439127218886366e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.2044490575790405e+08,
"cpu_time": 5.6149984040002894e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3507900460128665e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time_median",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.2014636695384979e+08,
"cpu_time": 5.6145920650004649e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3539091329272637e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.6100917751724122e+05,
"cpu_time": 6.5588515603525913e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.8169037942645270e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/6/log2(N):30/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4386534759442654e-03,
"cpu_time": 1.1680949999344386e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4375427072777067e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 312,
"real_time": 2.2411254848031183e+06,
"cpu_time": 2.5714421314102053e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8276531268662233e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 312,
"real_time": 2.2521029138424173e+06,
"cpu_time": 2.5827152532054367e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8187445941409599e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 312,
"real_time": 2.2406085336115211e+06,
"cpu_time": 2.5730151442305581e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8280748013566963e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 312,
"real_time": 2.2405208482478675e+06,
"cpu_time": 2.5776093044873378e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8281463451693186e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 312,
"real_time": 2.2406500640313309e+06,
"cpu_time": 2.5767947243589507e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8280409180140169e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2430015689072511e+06,
"cpu_time": 2.5763153115384979e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8261319571094431e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time_median",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2406500640313304e+06,
"cpu_time": 2.5767947243589507e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8280409180140169e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.0932391287386699e+03,
"cpu_time": 4.4017751125301484e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.1341148935859464e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):12/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2707247285698520e-03,
"cpu_time": 1.7085544975089018e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2638642719608141e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 312,
"real_time": 2.2474798494770834e+06,
"cpu_time": 2.5851462852561101e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6449715008150195e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 312,
"real_time": 2.2535106601515929e+06,
"cpu_time": 2.5859422628207230e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6352168839746811e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 312,
"real_time": 2.2485342014055601e+06,
"cpu_time": 2.5805936794868628e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6432623505922994e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 312,
"real_time": 2.2466798874143609e+06,
"cpu_time": 2.5786228685896834e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6462693443292170e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 312,
"real_time": 2.2408347144030416e+06,
"cpu_time": 2.5790153974360791e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6557805657622316e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2474078625703277e+06,
"cpu_time": 2.5818640987178916e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6451001290946901e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time_median",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2474798494770834e+06,
"cpu_time": 2.5805936794868624e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6449715008150195e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.5347046280990189e+03,
"cpu_time": 3.4510435985875847e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.3571614908629481e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):13/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.0177488490730573e-03,
"cpu_time": 1.3366480444502529e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0183702039181565e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 311,
"real_time": 2.2504651481794775e+06,
"cpu_time": 2.5911647363343923e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2802727086237706e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 311,
"real_time": 2.2512142309901030e+06,
"cpu_time": 2.5951106205787421e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2778502260951763e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 311,
"real_time": 2.2562257069615209e+06,
"cpu_time": 2.5937302218648447e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2616848347430974e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 311,
"real_time": 2.2536723625957007e+06,
"cpu_time": 2.5881152926045335e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2699121096420083e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 311,
"real_time": 2.2481515804467383e+06,
"cpu_time": 2.5891110739550665e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2877648208864443e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2519458058347078e+06,
"cpu_time": 2.5914463890675157e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2754969399980996e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time_median",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2512142309901034e+06,
"cpu_time": 2.5911647363343919e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2778502260951763e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0992840723418167e+03,
"cpu_time": 2.9694996801189423e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0010137419253731e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):14/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3762693863731920e-03,
"cpu_time": 1.1458850519332803e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3758699236366314e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2655122914927197e+06,
"cpu_time": 2.6103616148864599e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4463836776806694e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2724989883022979e+06,
"cpu_time": 2.6121559773464086e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4419368355573963e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2649649684362621e+06,
"cpu_time": 2.6048657087381696e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4467331926384326e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2653429723769715e+06,
"cpu_time": 2.6162592038834128e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4464917851100180e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2650965245314017e+06,
"cpu_time": 2.6047836440131981e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4466491668287283e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2666831490279306e+06,
"cpu_time": 2.6096852297735298e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4456389315630488e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time_median",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2653429723769715e+06,
"cpu_time": 2.6103616148864594e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4464917851100180e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.2580856771003173e+03,
"cpu_time": 4.9252551195090400e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0739758546576970e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):15/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.4373802877996208e-03,
"cpu_time": 1.8872985382748469e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4346430560051948e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 302,
"real_time": 2.2949274492123169e+06,
"cpu_time": 2.6488557450331720e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8556894041462522e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 302,
"real_time": 2.2953268909974899e+06,
"cpu_time": 2.6435825827812906e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8551924458794512e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 302,
"real_time": 2.2950227902770438e+06,
"cpu_time": 2.6547232417219644e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8555707715690624e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 302,
"real_time": 2.2950795084386077e+06,
"cpu_time": 2.6428929801325868e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8555002020206943e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 302,
"real_time": 2.3034652278740080e+06,
"cpu_time": 2.6577541192052001e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8451048102204997e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2967643733598934e+06,
"cpu_time": 2.6495617337748432e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8534115267671920e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time_median",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.2950795084386077e+06,
"cpu_time": 2.6488557450331720e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8555002020206943e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.7487990918162855e+03,
"cpu_time": 6.6044925083244261e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.6472260665974172e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):16/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6322088305176195e-03,
"cpu_time": 2.4926735709286437e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6286560921910025e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 295,
"real_time": 2.3809506250071828e+06,
"cpu_time": 2.7470283118642112e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5050280599415869e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 295,
"real_time": 2.3749937177083250e+06,
"cpu_time": 2.7465644101693663e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5188356509201117e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 295,
"real_time": 2.3803046265206598e+06,
"cpu_time": 2.7462419830506840e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5065220871158257e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 295,
"real_time": 2.3732429283465873e+06,
"cpu_time": 2.7441162644066224e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5229070077253506e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 295,
"real_time": 2.3863331541040186e+06,
"cpu_time": 2.7524932677968508e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4926111123495989e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3791650103373551e+06,
"cpu_time": 2.7472888474575472e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5091807836104959e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time_median",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3803046265206602e+06,
"cpu_time": 2.7465644101693658e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5065220871158257e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.2043291391521179e+03,
"cpu_time": 3.1160827790990347e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2046716126967964e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):17/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.1874603554354419e-03,
"cpu_time": 1.1342392271503539e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1866619739192928e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 282,
"real_time": 2.4921002959607975e+06,
"cpu_time": 2.8884979184396849e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0518998790894718e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 282,
"real_time": 2.4824764097360433e+06,
"cpu_time": 2.8832127624111553e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0559778089809653e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 282,
"real_time": 2.4892639596649306e+06,
"cpu_time": 2.8848273900709972e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0530984429440986e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 282,
"real_time": 2.4957718007292943e+06,
"cpu_time": 2.8914575106387502e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0503524397679242e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 282,
"real_time": 2.4827413759623650e+06,
"cpu_time": 2.8825981347520142e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0558651115982117e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4884707684106864e+06,
"cpu_time": 2.8861187432625210e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0534387364761344e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time_median",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4892639596649306e+06,
"cpu_time": 2.8848273900709972e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0530984429440986e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 5.8280779264144685e+03,
"cpu_time": 3.7639710970356705e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4669462161749697e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):18/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.3420319018401378e-03,
"cpu_time": 1.3041636300732411e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3418032114778404e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 271,
"real_time": 2.5821105358826607e+06,
"cpu_time": 3.0485076494459365e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0304630367838958e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 271,
"real_time": 2.5778235644239560e+06,
"cpu_time": 3.0476108413285483e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0338397368834594e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 271,
"real_time": 2.5831207390737161e+06,
"cpu_time": 3.0485627380073555e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0296689661823744e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 271,
"real_time": 2.5816747714246442e+06,
"cpu_time": 3.0481018007378890e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0308057614502794e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 271,
"real_time": 2.5848907253591558e+06,
"cpu_time": 3.0477291439114520e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0282791642078146e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5819240672328267e+06,
"cpu_time": 3.0481024346862370e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0306113331015646e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time_median",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5821105358826607e+06,
"cpu_time": 3.0481018007378886e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0304630367838958e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.6050012559003653e+03,
"cpu_time": 4.3505418416851381e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0499666046060360e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):19/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0089379811592492e-03,
"cpu_time": 1.4272951565464599e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0095317460259163e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 256,
"real_time": 2.7361910497347708e+06,
"cpu_time": 3.3387034257810200e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8322470212803394e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 256,
"real_time": 2.7434879375505261e+06,
"cpu_time": 3.3519328046871522e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8220543478540033e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 256,
"real_time": 2.7360398098608130e+06,
"cpu_time": 3.3355474375005299e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8324588561207479e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 256,
"real_time": 2.7336779221514007e+06,
"cpu_time": 3.3409960078127910e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8357700865315259e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 256,
"real_time": 2.7370654352125712e+06,
"cpu_time": 3.3365578828128404e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8310227680711752e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7372924309020163e+06,
"cpu_time": 3.3407475117188664e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8307106159715587e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time_median",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7361910497347708e+06,
"cpu_time": 3.3387034257810200e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8322470212803394e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.6838364217601761e+03,
"cpu_time": 6.5944025254855715e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.1488723009995109e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):20/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3457957141050677e-03,
"cpu_time": 1.9739302363777408e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3441036969830296e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 227,
"real_time": 3.0720440798032912e+06,
"cpu_time": 3.9999133127751434e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8265687129537690e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 227,
"real_time": 3.0723704837492383e+06,
"cpu_time": 3.9981316475767633e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8258434687239563e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 227,
"real_time": 3.0671185885642199e+06,
"cpu_time": 3.9906367621143637e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8375315118862724e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 227,
"real_time": 3.0663348149737990e+06,
"cpu_time": 4.0032843964766148e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8392792259964585e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 227,
"real_time": 3.0680708453830513e+06,
"cpu_time": 3.9984487180617088e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8354093033929563e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0691877624947205e+06,
"cpu_time": 3.9980829674009187e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8329264445906830e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time_median",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.0680708453830513e+06,
"cpu_time": 3.9984487180617088e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8354093033929563e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.8265065580499509e+03,
"cpu_time": 4.6364626896783320e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2912312569162482e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):21/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 9.2092982794656018e-04,
"cpu_time": 1.1596714544151675e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.2072281297521212e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 195,
"real_time": 3.5889030792392218e+06,
"cpu_time": 5.0652147794876210e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1686868960777597e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 195,
"real_time": 3.5891673479897855e+06,
"cpu_time": 5.0647088410245581e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1686008461960232e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 195,
"real_time": 3.5898384327689805e+06,
"cpu_time": 5.0687555487177009e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1683823878292961e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 195,
"real_time": 3.5954237855875338e+06,
"cpu_time": 5.0799495230771406e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1665673506453154e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 195,
"real_time": 3.5898713227839042e+06,
"cpu_time": 5.0714617128202617e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1683716832355332e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.5906407936738855e+06,
"cpu_time": 5.0700180810254561e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1681218327967854e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time_median",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.5898384327689805e+06,
"cpu_time": 5.0687555487176999e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1683823878292961e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.7066387710035588e+03,
"cpu_time": 6.1961951401327387e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7969870914989978e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):22/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.5380382681893661e-04,
"cpu_time": 1.2221248605250542e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5308814924182513e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 145,
"real_time": 4.8355869306572555e+06,
"cpu_time": 7.5353626689649960e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7347652147078278e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 145,
"real_time": 4.8690844776815381e+06,
"cpu_time": 7.5788123517229212e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7228306550134692e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 145,
"real_time": 4.8737322462016139e+06,
"cpu_time": 7.5839925448266948e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7211877009734657e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 145,
"real_time": 4.8731518395501990e+06,
"cpu_time": 7.5946835379313435e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7213926994678426e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 145,
"real_time": 4.9455726487112455e+06,
"cpu_time": 7.6861900137922438e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6961853754561601e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.8794256285603708e+06,
"cpu_time": 7.5958082234476404e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7192723291237531e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time_median",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.8731518395501990e+06,
"cpu_time": 7.5839925448266957e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7213926994678426e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.0236718744750215e+04,
"cpu_time": 5.5344981518201515e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4087789360174293e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):23/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.2461998209862435e-03,
"cpu_time": 7.2862531399036741e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.1940418173043570e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 88,
"real_time": 7.7479400894265957e+06,
"cpu_time": 1.3257060852272285e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1653776108691669e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 88,
"real_time": 7.7318617841228843e+06,
"cpu_time": 1.3195417545455772e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1698804852476082e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 88,
"real_time": 7.7215527046725834e+06,
"cpu_time": 1.3191665272725832e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1727775023600521e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 88,
"real_time": 7.7315345882776789e+06,
"cpu_time": 1.3202483431818090e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1699723138323812e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 88,
"real_time": 7.7531655498949643e+06,
"cpu_time": 1.3243108897726912e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1639181947078753e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.7372109432789413e+06,
"cpu_time": 1.3217947199999779e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1683852214034166e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time_median",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.7318617841228843e+06,
"cpu_time": 1.3202483431818087e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1698804852476082e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.2996913050112231e+04,
"cpu_time": 3.0001841560126060e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.6416636641183654e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):24/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6797930346467056e-03,
"cpu_time": 2.2697807084693573e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6794357516241589e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51,
"real_time": 1.3737269476348279e+07,
"cpu_time": 2.4958427039216664e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4425838087963052e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51,
"real_time": 1.3709225454459004e+07,
"cpu_time": 2.4910494843135323e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4475804349024134e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51,
"real_time": 1.3778170077678036e+07,
"cpu_time": 2.5027808529410534e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4353329804196143e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51,
"real_time": 1.3758756676871402e+07,
"cpu_time": 2.4957122647060268e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4387691989934897e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51,
"real_time": 1.3745705651886323e+07,
"cpu_time": 2.4977176137255415e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4410847176401834e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3745825467448607e+07,
"cpu_time": 2.4966205839215644e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4410702281504016e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time_median",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.3745705651886323e+07,
"cpu_time": 2.4958427039216664e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4410847176401834e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5623086652473237e+04,
"cpu_time": 4.2314205864787669e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5520510480090184e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):25/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.8640631450727412e-03,
"cpu_time": 1.6948592884835820e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8647767669749127e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 28,
"real_time": 2.5315405601369482e+07,
"cpu_time": 4.8155784607144728e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6509100844258099e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 28,
"real_time": 2.5268279481679201e+07,
"cpu_time": 4.8100264071430437e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6558541134016414e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 28,
"real_time": 2.5361970865300722e+07,
"cpu_time": 4.8156133428571068e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6460429418683615e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 28,
"real_time": 2.5338599657905955e+07,
"cpu_time": 4.8158008392858520e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6484835352399282e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 28,
"real_time": 2.5359771014856439e+07,
"cpu_time": 4.8149506749999605e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6462724746483636e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5328805324222364e+07,
"cpu_time": 4.8143939450000875e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6495126299168210e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time_median",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.5338599657905951e+07,
"cpu_time": 4.8155784607144728e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6484835352399282e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.8722365216854698e+04,
"cpu_time": 2.4624528090321612e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0547400986006488e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):26/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.5287876676845810e-03,
"cpu_time": 5.1147721544255896e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5303720589276617e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 4.5137899617354073e+07,
"cpu_time": 8.6562828600002229e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9735040650495305e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 4.5698658128579460e+07,
"cpu_time": 8.7483092866659716e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9370168292985754e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 4.5572427163521446e+07,
"cpu_time": 8.7347057733328864e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9451520657086020e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.5548406243324280e+07,
"cpu_time": 8.7433825133333206e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9467052542518187e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 4.5594539741675057e+07,
"cpu_time": 8.7356615733324364e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9437237169283266e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.5510386178890862e+07,
"cpu_time": 8.7236684013329685e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9492203862473712e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time_median",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.5572427163521446e+07,
"cpu_time": 8.7356615733324364e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9451520657086020e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.1596816708011119e+05,
"cpu_time": 3.8086383320828795e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4068709543892076e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):27/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 4.7454698852958535e-03,
"cpu_time": 4.3658678400716414e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.7703147616558073e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.4820338524878025e+07,
"cpu_time": 1.6229351662499881e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1647534149049311e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.6297065950930119e+07,
"cpu_time": 1.6518500062500152e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1105977131671739e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.6418905295431614e+07,
"cpu_time": 1.6522167949997878e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1062121775591431e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.6384426802396774e+07,
"cpu_time": 1.6525678275002065e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1074519555942941e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.4718359634280205e+07,
"cpu_time": 1.6207006262499136e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1685629556427460e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.5727819241583347e+07,
"cpu_time": 1.6400540842499822e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1315156433736577e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time_median",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.6297065950930119e+07,
"cpu_time": 1.6518500062500152e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1105977131671739e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 8.7682740445540531e+05,
"cpu_time": 1.6667954049596041e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2148635502211910e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):28/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.0228038135257840e-02,
"cpu_time": 1.0163051456451518e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0266158360166262e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6411680728197098e+08,
"cpu_time": 3.0592655249995458e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2712731918894567e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6760784015059471e+08,
"cpu_time": 3.1280565324999541e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2031372250702858e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6401332244277000e+08,
"cpu_time": 3.0513230075001729e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2733372143432622e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.6760527342557907e+08,
"cpu_time": 3.1301496300000054e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2031862782550459e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6397401317954063e+08,
"cpu_time": 3.0546471625001460e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2741219269431558e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6546345129609108e+08,
"cpu_time": 3.0846883714999646e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2450111673002415e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time_median",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.6411680728197098e+08,
"cpu_time": 3.0592655249995458e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2712731918894567e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.9570740461677960e+06,
"cpu_time": 4.0649619586503282e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8217285307554744e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):29/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 1.1827832858784509e-02,
"cpu_time": 1.3177869104079689e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1777243077825971e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.1779828667640686e+08,
"cpu_time": 5.5897992749999046e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3786897822181177e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.1768591701984406e+08,
"cpu_time": 5.5706606900002956e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3798848689063210e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.1924095749855042e+08,
"cpu_time": 5.5791950900004399e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3634212615243006e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.1777060031890869e+08,
"cpu_time": 5.5677715700005591e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3789841568805060e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.1719118356704712e+08,
"cpu_time": 5.5675439399999499e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3851565857694621e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.1793738901615143e+08,
"cpu_time": 5.5749941130002296e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3772273310597420e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time_median",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 3.1777060031890869e+08,
"cpu_time": 5.5706606900002956e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3789841568805060e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 7.6917479417134426e+05,
"cpu_time": 9.5300811855434626e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.1512015067227976e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_coarse/0/7/log2(N):30/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_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": 2.4192649897249725e-03,
"cpu_time": 1.7094334078883481e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4135779761574497e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
}
]
}