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

25273 lines
889 KiB
JSON

{
"context": {
"date": "2023-10-09T17:38:29-04:00",
"host_name": "frontier08444",
"executable": "/lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope",
"num_cpus": 128,
"mhz_per_cpu": 1804,
"cpu_scaling_enabled": false,
"caches": [
{
"type": "Data",
"level": 1,
"size": 32768,
"num_sharing": 2
},
{
"type": "Instruction",
"level": 1,
"size": 32768,
"num_sharing": 2
},
{
"type": "Unified",
"level": 2,
"size": 524288,
"num_sharing": 2
},
{
"type": "Unified",
"level": 3,
"size": 33554432,
"num_sharing": 16
}
],
"load_avg": [0.71,11.7,26.82],
"library_build_type": "release"
},
"benchmarks": [
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52237,
"real_time": 1.3400284570844202e+04,
"cpu_time": 2.5679946551295056e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0566515049328965e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52237,
"real_time": 1.3399247187575495e+04,
"cpu_time": 2.5717080689932420e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0568881539837790e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52237,
"real_time": 1.3397628338803852e+04,
"cpu_time": 2.5488320500794453e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0572575208230424e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52237,
"real_time": 1.3400425779468309e+04,
"cpu_time": 2.6014288033386289e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0566192950941575e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52237,
"real_time": 1.3398446076847365e+04,
"cpu_time": 2.5689979152707841e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0570709293504745e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3399206390707846e+04,
"cpu_time": 2.5717922985623209e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0568974808368701e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time_median",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3399247187575495e+04,
"cpu_time": 2.5689979152707841e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 3.0568881539837790e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1957602766579982e+00,
"cpu_time": 1.8892678436342032e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7280561577797478e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.9241126809363921e-05,
"cpu_time": 7.3461136215795444e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.9242644703704712e-05,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52260,
"real_time": 1.3397411057834412e+04,
"cpu_time": 2.5618317374665148e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1146142076528728e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52260,
"real_time": 1.3395386904925819e+04,
"cpu_time": 2.5654872139303487e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1155381760474551e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52260,
"real_time": 1.3395920566535411e+04,
"cpu_time": 2.5540653195560662e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1152945475539637e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52260,
"real_time": 1.3399812355815231e+04,
"cpu_time": 2.5387169230769236e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1135184452376664e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52260,
"real_time": 1.3396265476355247e+04,
"cpu_time": 2.5885375296593968e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1151370988124192e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3396959272293223e+04,
"cpu_time": 2.5617277447378503e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1148204950608754e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time_median",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3396265476355245e+04,
"cpu_time": 2.5618317374665152e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 6.1151370988124192e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7590336385689216e+00,
"cpu_time": 1.8173604924559288e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.0279479320683196e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3130096186877627e-04,
"cpu_time": 7.0942764944051662e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3128673096050384e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52260,
"real_time": 1.3393965895471767e+04,
"cpu_time": 2.5673377937236892e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2232373986810811e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52260,
"real_time": 1.3393881163649170e+04,
"cpu_time": 2.5588281687715218e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2232451370754263e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52260,
"real_time": 1.3398118764255429e+04,
"cpu_time": 2.5600693628013763e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2228582451224828e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52260,
"real_time": 1.3399794253076754e+04,
"cpu_time": 2.5929857462686530e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2227053408852181e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52260,
"real_time": 1.3398538894421064e+04,
"cpu_time": 2.5854447818599267e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2228199006700673e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3396859794174839e+04,
"cpu_time": 2.5729331706850335e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2229732044868550e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time_median",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3398118764255432e+04,
"cpu_time": 2.5673377937236895e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.2228582451224828e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7505600257369878e+00,
"cpu_time": 1.5446545546691760e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5110482464500758e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0531378755885569e-04,
"cpu_time": 6.0034771686585144e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0532324316162607e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52257,
"real_time": 1.3396556343471111e+04,
"cpu_time": 2.5993877337007412e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4460017305842686e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52257,
"real_time": 1.3396470301516483e+04,
"cpu_time": 2.5722521021107212e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4460174406008019e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52257,
"real_time": 1.3396694067148455e+04,
"cpu_time": 2.5622723903017755e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4459765846526351e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52257,
"real_time": 1.3395108655901766e+04,
"cpu_time": 2.5828989475094269e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4462660842667155e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52257,
"real_time": 1.3397598307154392e+04,
"cpu_time": 2.6021560977476693e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4458114991029181e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3396485535038442e+04,
"cpu_time": 2.5837934542740666e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4460146678414683e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time_median",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3396556343471113e+04,
"cpu_time": 2.5828989475094269e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 2.4460017305842686e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9201868633175463e-01,
"cpu_time": 1.7157559360148937e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6287505689945284e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.6586022430934161e-05,
"cpu_time": 6.6404531413945629e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6587931397478083e-05,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52254,
"real_time": 1.3395963961299001e+04,
"cpu_time": 2.5978959314119438e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.8922197901796227e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52254,
"real_time": 1.3393072908105178e+04,
"cpu_time": 2.6228325927201658e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.8932758336840782e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52254,
"real_time": 1.3395101923269811e+04,
"cpu_time": 2.6269395586940638e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.8925346276127729e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52254,
"real_time": 1.3396511706824154e+04,
"cpu_time": 2.5978742488613334e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.8920197611305113e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52254,
"real_time": 1.3395873094538645e+04,
"cpu_time": 2.6182645481685573e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.8922529750388823e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3395304718807360e+04,
"cpu_time": 2.6127613759712134e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.8924605975291739e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time_median",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3395873094538643e+04,
"cpu_time": 2.6182645481685573e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 4.8922529750388823e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3450442829755485e+00,
"cpu_time": 1.3922492340533123e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9130500506304635e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0041162267007416e-04,
"cpu_time": 5.3286505490222451e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0042084044809044e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52237,
"real_time": 1.3402223187851165e+04,
"cpu_time": 2.6188396672856401e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.7798699635754471e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52237,
"real_time": 1.3401130935258263e+04,
"cpu_time": 2.5993205926833511e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.7806670670719795e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52237,
"real_time": 1.3402527706219347e+04,
"cpu_time": 2.6056862434672737e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.7796477554884663e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52237,
"real_time": 1.3402107254185279e+04,
"cpu_time": 2.6068673737006346e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.7799545634189835e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52237,
"real_time": 1.3404927763791016e+04,
"cpu_time": 2.6380477611654638e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.7778967786792355e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3402583369461014e+04,
"cpu_time": 2.6137523276604727e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.7796072256468239e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time_median",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3402223187851163e+04,
"cpu_time": 2.6068673737006342e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 9.7798699635754471e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4111400314886084e+00,
"cpu_time": 1.5304316330235744e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0295885102700010e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0528865910314106e-04,
"cpu_time": 5.8553047158582125e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0527912691318786e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51062,
"real_time": 1.3710655457486910e+04,
"cpu_time": 2.6662151071246786e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9119727777628044e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51062,
"real_time": 1.3709835418736842e+04,
"cpu_time": 2.6622715385217900e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9120871403148666e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51062,
"real_time": 1.3707747920392687e+04,
"cpu_time": 2.6443628079589536e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9123783244512009e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51062,
"real_time": 1.3707359312963476e+04,
"cpu_time": 2.6339304355489297e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9124325409058350e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51062,
"real_time": 1.3712281519485245e+04,
"cpu_time": 2.6799538423876929e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9117460477127136e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3709575925813033e+04,
"cpu_time": 2.6573467463084089e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9121233662294842e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time_median",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3709835418736842e+04,
"cpu_time": 2.6622715385217900e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.9120871403148666e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0498742930955958e+00,
"cpu_time": 1.8240671997601333e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8589820801117308e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4952134947048188e-04,
"cpu_time": 6.8642423210073383e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4951870421150480e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 50898,
"real_time": 1.3757761828257515e+04,
"cpu_time": 2.6994015481944276e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8108524231255974e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 50898,
"real_time": 1.3753329564147476e+04,
"cpu_time": 2.6833001768242455e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8120805406039795e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 50898,
"real_time": 1.3757038854393855e+04,
"cpu_time": 2.6643768399544162e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8110526949085983e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 50898,
"real_time": 1.3755440043618824e+04,
"cpu_time": 2.6516704133757645e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8114956579903694e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 50898,
"real_time": 1.3758258232263361e+04,
"cpu_time": 2.6889199909623207e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8107149258947273e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3756365704536205e+04,
"cpu_time": 2.6775337938622350e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8112392485046547e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time_median",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3757038854393855e+04,
"cpu_time": 2.6833001768242459e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 3.8110526949085983e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0036809880804540e+00,
"cpu_time": 1.9255617509692252e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.5517306475296514e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4565482127446884e-04,
"cpu_time": 7.1915497588983923e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4566733509862654e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 50622,
"real_time": 1.3829097961651778e+04,
"cpu_time": 2.6977685038125670e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.5823889808844467e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 50622,
"real_time": 1.3830643712235093e+04,
"cpu_time": 2.6953179724230624e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.5815415523457626e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 50622,
"real_time": 1.3835577941691370e+04,
"cpu_time": 2.6786927738927840e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.5788377212655396e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 50622,
"real_time": 1.3832129311247765e+04,
"cpu_time": 2.7059047726285025e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.5807272792579941e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 50622,
"real_time": 1.3835013719615596e+04,
"cpu_time": 2.6815579293587718e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.5791468028203339e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3832492529288322e+04,
"cpu_time": 2.6918483904231380e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.5805284673148148e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time_median",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3832129311247767e+04,
"cpu_time": 2.6953179724230624e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 7.5807272792579941e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7816052694056337e+00,
"cpu_time": 1.1441497473109412e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5243848965801256e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0109212157649702e-04,
"cpu_time": 4.2504241746359637e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0109216701089645e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 50043,
"real_time": 1.3985155716072379e+04,
"cpu_time": 2.7057248925923643e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.4995557021863242e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 50043,
"real_time": 1.3985335592162608e+04,
"cpu_time": 2.7376555742061846e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.4995364152543079e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 50043,
"real_time": 1.3988992424751432e+04,
"cpu_time": 2.7543972563595256e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.4991444246473413e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 50043,
"real_time": 1.3985526739658861e+04,
"cpu_time": 2.7184656895070108e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.4995159203071634e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 50043,
"real_time": 1.3990220615680120e+04,
"cpu_time": 2.7349236176887815e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.4990128158876422e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3987046217665082e+04,
"cpu_time": 2.7302334060707733e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.4993530556565558e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time_median",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3985526739658861e+04,
"cpu_time": 2.7349236176887818e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 1.4995159203071634e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3808388136544325e+00,
"cpu_time": 1.8709120180245927e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5519661665268213e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7021741235454904e-04,
"cpu_time": 6.8525717027143242e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7020448632155778e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 49877,
"real_time": 1.4037276396124815e+04,
"cpu_time": 2.7440417246426161e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.9879756454449353e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 49877,
"real_time": 1.4031587798575954e+04,
"cpu_time": 2.7487853459510490e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.9891870116264917e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 49877,
"real_time": 1.4038710007311560e+04,
"cpu_time": 2.7423082382661352e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.9876705180287549e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 49877,
"real_time": 1.4034857260184528e+04,
"cpu_time": 2.7334771959019148e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.9884906716499469e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 49877,
"real_time": 1.4033496673269579e+04,
"cpu_time": 2.7481398500310854e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.9887804142136121e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4035185627093288e+04,
"cpu_time": 2.7433504709585606e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.9884208521927484e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time_median",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4034857260184528e+04,
"cpu_time": 2.7440417246426157e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 2.9884906716499469e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8590790052041517e+00,
"cpu_time": 6.1547067164782071e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0876314954501636e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0370795806825905e-04,
"cpu_time": 2.2434999762635786e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0370730216874824e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 39809,
"real_time": 1.7552855703223860e+04,
"cpu_time": 3.1275718505865687e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7790559791699872e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 39809,
"real_time": 1.7570999924582506e+04,
"cpu_time": 3.1176743726292782e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7741210153122900e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 39809,
"real_time": 1.7616855476839009e+04,
"cpu_time": 3.0847599361953580e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7616942825174194e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 39809,
"real_time": 1.7625162710698867e+04,
"cpu_time": 3.0803920018086326e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7594499623586041e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 39809,
"real_time": 1.7566895050687916e+04,
"cpu_time": 3.1203664975256881e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7752365889335150e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7586553773206433e+04,
"cpu_time": 3.1061529317491055e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7699115656583636e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time_median",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7570999924582509e+04,
"cpu_time": 3.1176743726292782e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 4.7741210153122900e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2298571160529164e+01,
"cpu_time": 2.1879356174030622e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7559197624105299e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8365491941767962e-03,
"cpu_time": 7.0438760276076099e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8356566242129062e-03,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 27719,
"real_time": 2.5253497997514063e+04,
"cpu_time": 3.9160754969515401e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 6.6435216228862781e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 27719,
"real_time": 2.5248854938897715e+04,
"cpu_time": 3.8985223601140235e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 6.6447433123604614e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 27719,
"real_time": 2.5252289080514605e+04,
"cpu_time": 3.8945594141202993e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 6.6438396719233594e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 27719,
"real_time": 2.5251175331394934e+04,
"cpu_time": 3.9112014286229583e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 6.6441327105834912e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 27719,
"real_time": 2.5249610726730913e+04,
"cpu_time": 3.9339168476496190e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 6.6445444175654260e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5251085615010445e+04,
"cpu_time": 3.9108551094916882e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 6.6441563470638037e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time_median",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5251175331394927e+04,
"cpu_time": 3.9112014286229576e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 6.6441327105834912e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8991562613765023e+00,
"cpu_time": 1.5627400166653746e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9971080812972620e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.5210875695877146e-05,
"cpu_time": 3.9959036397758316e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5210573325921087e-05,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15889,
"real_time": 4.4022590313416040e+04,
"cpu_time": 5.8011982818302778e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 7.6220939661004382e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15889,
"real_time": 4.4031962651223403e+04,
"cpu_time": 5.8387643464031433e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 7.6204715801074353e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15889,
"real_time": 4.4023425848322346e+04,
"cpu_time": 5.8184267732393404e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 7.6219493039019592e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15889,
"real_time": 4.4038367593964264e+04,
"cpu_time": 5.8001235131222973e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 7.6193632582781848e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15889,
"real_time": 4.4061376946045115e+04,
"cpu_time": 5.8609971049153683e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 7.6153843401418701e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.4035544670594230e+04,
"cpu_time": 5.8239020039020848e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 7.6198524897059778e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time_median",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.4031962651223403e+04,
"cpu_time": 5.8184267732393404e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 7.6204715801074353e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5833409576069608e+01,
"cpu_time": 2.6018212439909490e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7389700156401622e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.5955975325184834e-04,
"cpu_time": 4.4674880213432452e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5945184232114301e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8470,
"real_time": 8.2636942916275962e+04,
"cpu_time": 9.8081457615111853e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 8.1209277148589209e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8470,
"real_time": 8.2625491770219116e+04,
"cpu_time": 9.7937581109799328e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 8.1220532020104944e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8470,
"real_time": 8.2650333254507641e+04,
"cpu_time": 9.7902418299881450e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 8.1196120278607556e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8470,
"real_time": 8.2662371134817324e+04,
"cpu_time": 9.7896502833530089e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 8.1184295924138818e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8470,
"real_time": 8.2630011474825282e+04,
"cpu_time": 9.8184193388428495e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 8.1216089411346521e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.2641030110129068e+04,
"cpu_time": 9.8000430649350252e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 8.1205262956557422e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time_median",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.2636942916275948e+04,
"cpu_time": 9.7937581109799328e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 8.1209277148589209e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5178465943753807e+01,
"cpu_time": 1.2717270699910571e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4913711493611777e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8366743400374710e-04,
"cpu_time": 1.2976749811859003e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8365449418703567e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4397,
"real_time": 1.5895635124035110e+05,
"cpu_time": 1.7799103616101708e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 8.4436845053806714e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4397,
"real_time": 1.5898494433730457e+05,
"cpu_time": 1.7822071389583687e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 8.4421659270604822e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4397,
"real_time": 1.5900153878278570e+05,
"cpu_time": 1.7813265703888953e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 8.4412848471458362e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4397,
"real_time": 1.5897933733907959e+05,
"cpu_time": 1.7812361314532885e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 8.4424636714728088e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4397,
"real_time": 1.5899501798253178e+05,
"cpu_time": 1.7821807323174982e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 8.4416310462473755e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5898343793641057e+05,
"cpu_time": 1.7813721869456448e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 8.4422459994614343e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time_median",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5898494433730457e+05,
"cpu_time": 1.7813265703888953e+05,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 8.4421659270604822e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7424919787850758e+01,
"cpu_time": 9.3653827470740580e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.2534766571850598e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0960210707495388e-04,
"cpu_time": 5.2573980977731671e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0960918051636232e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2212,
"real_time": 3.1654137995034695e+05,
"cpu_time": 3.5351854339964077e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 8.4802642877878113e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2212,
"real_time": 3.1590266558985860e+05,
"cpu_time": 3.5372118851717899e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 8.4974102861326904e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2212,
"real_time": 3.1630512760671286e+05,
"cpu_time": 3.5323245569620479e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 8.4865983056008813e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2212,
"real_time": 3.1637384017155156e+05,
"cpu_time": 3.5341999547920545e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 8.4847551192741687e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2212,
"real_time": 3.1636828172149451e+05,
"cpu_time": 3.5351384222423198e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 8.4849041926494153e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1629825900799292e+05,
"cpu_time": 3.5348120506329241e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 8.4867864382889941e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time_median",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1636828172149451e+05,
"cpu_time": 3.5351384222423198e+05,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 8.4849041926494153e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3783650651341685e+02,
"cpu_time": 1.7725282393962348e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.3857084502468312e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.5193745061811004e-04,
"cpu_time": 5.0144907678439531e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5242949692206967e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1106,
"real_time": 6.2867504669602611e+05,
"cpu_time": 7.2002871518987685e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 8.5397203980259961e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1106,
"real_time": 6.3335804763851292e+05,
"cpu_time": 7.2574059132008080e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 8.4765783588245715e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1106,
"real_time": 6.2914984784919303e+05,
"cpu_time": 7.2049390958407568e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 8.5332757185802856e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1106,
"real_time": 6.3206357041468157e+05,
"cpu_time": 7.2333955244124145e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 8.4939385392480701e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1106,
"real_time": 6.2907317178163875e+05,
"cpu_time": 7.1996428300180647e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 8.5343158170216235e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.3046393687601050e+05,
"cpu_time": 7.2191341030741634e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 8.5155657663401099e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time_median",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.2914984784919303e+05,
"cpu_time": 7.2049390958407579e+05,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 8.5332757185802856e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1092587654023764e+03,
"cpu_time": 2.5518302810253963e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8444718038896575e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.3455660855938722e-03,
"cpu_time": 3.5348149024392503e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3403203990663068e-03,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 532,
"real_time": 1.3090368512146091e+06,
"cpu_time": 1.6400401109022477e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 8.2025332060263452e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 532,
"real_time": 1.3117219940269073e+06,
"cpu_time": 1.6428548834586511e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 8.1857423210819055e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 532,
"real_time": 1.3120925229890062e+06,
"cpu_time": 1.6425988966165413e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 8.1834307046729260e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 532,
"real_time": 1.3107141918376705e+06,
"cpu_time": 1.6418816503759825e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 8.1920363011754199e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 532,
"real_time": 1.3121057866767917e+06,
"cpu_time": 1.6429404398496288e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 8.1833479808018909e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3111342693489972e+06,
"cpu_time": 1.6420631962406104e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 8.1894181027516980e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time_median",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3117219940269070e+06,
"cpu_time": 1.6425988966165413e+06,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 8.1857423210819055e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3022235021317936e+03,
"cpu_time": 1.2051071611861901e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.1404481454810059e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.9320377216467097e-04,
"cpu_time": 7.3389816174261699e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.9402033738462585e-04,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 303,
"real_time": 2.2845314377642209e+06,
"cpu_time": 2.6024208943893882e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.7929278329426670e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 303,
"real_time": 2.2729780162275820e+06,
"cpu_time": 2.5721711089108428e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8020411859495468e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 303,
"real_time": 2.2678337107556979e+06,
"cpu_time": 2.5675092937293844e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8061288976232354e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 303,
"real_time": 2.2745416138517875e+06,
"cpu_time": 2.5799104026402584e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8008024012643548e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 303,
"real_time": 2.2680206414889973e+06,
"cpu_time": 2.5677612871287740e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8059800361035957e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2735810840176572e+06,
"cpu_time": 2.5779545973597295e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8015760707766798e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time_median",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2729780162275820e+06,
"cpu_time": 2.5721711089108423e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8020411859495468e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.8034435402933350e+03,
"cpu_time": 1.4567785904748362e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.3788952669300543e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.9923909853573085e-03,
"cpu_time": 5.6509086388364990e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9856609188926180e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2694035667575314e+06,
"cpu_time": 2.5822853863636903e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6097590221489472e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2691381012706403e+06,
"cpu_time": 2.5715724415584467e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6101813262986327e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2833974443847775e+06,
"cpu_time": 2.5854041233767010e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.5876364932199507e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2693791437301445e+06,
"cpu_time": 2.5713832824674700e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6097978703263006e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2765345132135628e+06,
"cpu_time": 2.5785287662338465e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.5984519243840273e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2735705538713313e+06,
"cpu_time": 2.5778348000000310e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6031653272755723e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time_median",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2694035667575309e+06,
"cpu_time": 2.5785287662338465e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6097590221489472e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.3231947774634127e+03,
"cpu_time": 6.2933134400791023e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0000656673751479e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.7811737650703505e-03,
"cpu_time": 2.4413175895053579e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7755197903486660e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 305,
"real_time": 2.2751504196556378e+06,
"cpu_time": 2.5796950918033011e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2012821035717940e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 305,
"real_time": 2.2835014082613541e+06,
"cpu_time": 2.5944730655737659e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1749463086491777e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 305,
"real_time": 2.2749563060761965e+06,
"cpu_time": 2.5794719213114954e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2018965622503879e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 305,
"real_time": 2.2762866576248016e+06,
"cpu_time": 2.5887492163934386e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1976874903338999e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 305,
"real_time": 2.2813489729324812e+06,
"cpu_time": 2.5880349901638799e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1817158156824000e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2782487529100943e+06,
"cpu_time": 2.5860848570491769e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1915056560975313e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time_median",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2762866576248016e+06,
"cpu_time": 2.5880349901638804e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1976874903338999e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9208240664139112e+03,
"cpu_time": 6.4386312810467389e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2367476437717600e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7209815483957545e-03,
"cpu_time": 2.4897215818329593e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7197339512945342e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 306,
"real_time": 2.2953041133720404e+06,
"cpu_time": 2.6036699836601233e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4276103897997377e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 306,
"real_time": 2.2975880587230027e+06,
"cpu_time": 2.6065813235294251e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4261912563304504e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 306,
"real_time": 2.2897244631951931e+06,
"cpu_time": 2.6041484901961302e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4310892217255669e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 306,
"real_time": 2.2901401480696364e+06,
"cpu_time": 2.6036760130719338e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4308294637609934e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 306,
"real_time": 2.2964816703308932e+06,
"cpu_time": 2.6052283333333796e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4268783602038745e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2938476907381536e+06,
"cpu_time": 2.6046608287581988e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4285197383641247e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time_median",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2953041133720400e+06,
"cpu_time": 2.6041484901961302e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4276103897997377e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6672962130215251e+03,
"cpu_time": 1.2474462267144354e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2847287481743595e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5987531464399017e-03,
"cpu_time": 4.7892847043320009e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5993679938862632e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 301,
"real_time": 2.3269730502510588e+06,
"cpu_time": 2.6446252225913098e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8163626558945011e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 301,
"real_time": 2.3207425463177338e+06,
"cpu_time": 2.6448426877076058e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8239237525069032e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 301,
"real_time": 2.3287952447501924e+06,
"cpu_time": 2.6467400033223224e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8141589582741518e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 301,
"real_time": 2.3202375652720267e+06,
"cpu_time": 2.6379666677740091e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8245383568003953e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 301,
"real_time": 2.3206952430208856e+06,
"cpu_time": 2.6498078936876906e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8239813132331308e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3234887299223798e+06,
"cpu_time": 2.6447964950165884e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8205930073418166e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time_median",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3207425463177343e+06,
"cpu_time": 2.6448426877076062e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8239237525069032e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.0686223963459206e+03,
"cpu_time": 4.3465316444697010e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9354109072535692e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7510833359978639e-03,
"cpu_time": 1.6434276333394944e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7497777575166008e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 294,
"real_time": 2.3858862791248425e+06,
"cpu_time": 2.7240332108843811e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4936398749096289e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 294,
"real_time": 2.3905540932109263e+06,
"cpu_time": 2.7283225136054233e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4829129519486301e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 294,
"real_time": 2.3923179191746274e+06,
"cpu_time": 2.7293021598638748e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4788704690729856e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 294,
"real_time": 2.3799439192097001e+06,
"cpu_time": 2.7175765714286347e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5073566625689499e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 294,
"real_time": 2.3911097570050028e+06,
"cpu_time": 2.7291552857142310e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4816387920299791e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3879623935450199e+06,
"cpu_time": 2.7256779482993097e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4888837501060344e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time_median",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3905540932109263e+06,
"cpu_time": 2.7283225136054233e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4829129519486301e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.1039100004404518e+03,
"cpu_time": 5.0139300698294128e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1750264499416598e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1373494047632405e-03,
"cpu_time": 1.8395166871999170e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1407384514546524e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 281,
"real_time": 2.4985167797774184e+06,
"cpu_time": 2.8702029572953796e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0491984769594112e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 281,
"real_time": 2.5008234578214614e+06,
"cpu_time": 2.8687805017794291e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0482307304825152e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 281,
"real_time": 2.5009373318920992e+06,
"cpu_time": 2.8679313701066920e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0481830018574411e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 281,
"real_time": 2.4964965654543708e+06,
"cpu_time": 2.8706479857651484e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0500475090871550e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 281,
"real_time": 2.4959243331899955e+06,
"cpu_time": 2.8677088434163732e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0502882499845600e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4985396936270692e+06,
"cpu_time": 2.8690543316726047e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0491895936742166e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time_median",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4985167797774184e+06,
"cpu_time": 2.8687805017794291e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0491984769594112e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3441019673415281e+03,
"cpu_time": 1.3233894299484175e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.8435120295045097e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.3818880417250946e-04,
"cpu_time": 4.6126328642124610e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.3820145461345609e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 269,
"real_time": 2.5941691591601721e+06,
"cpu_time": 3.0297380855018822e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0210247205688441e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 269,
"real_time": 2.5982239030883214e+06,
"cpu_time": 3.0299811672862140e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0178707438447341e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 269,
"real_time": 2.5924727897121673e+06,
"cpu_time": 3.0274019293679786e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0223471663060725e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 269,
"real_time": 2.5930211967598218e+06,
"cpu_time": 3.0257466133829239e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0219194530886903e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 269,
"real_time": 2.5992855926470133e+06,
"cpu_time": 3.0310086728624245e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0170465357217062e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5954345282734991e+06,
"cpu_time": 3.0287752936802851e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0200417239060095e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time_median",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5941691591601721e+06,
"cpu_time": 3.0297380855018822e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0210247205688441e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1148247126153228e+03,
"cpu_time": 2.1463990599411782e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4234026013025569e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2001168508331919e-03,
"cpu_time": 7.0866896742711972e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1996794782122605e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 253,
"real_time": 2.7581646195484009e+06,
"cpu_time": 3.3309661897233543e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8017165203565156e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 253,
"real_time": 2.7534290991738262e+06,
"cpu_time": 3.3236446561265164e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8082549513064563e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 253,
"real_time": 2.7491027377030477e+06,
"cpu_time": 3.3179343162055332e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8142481385621643e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 253,
"real_time": 2.7522895045269267e+06,
"cpu_time": 3.3246407351778592e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8098317719677275e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 253,
"real_time": 2.7547344646376111e+06,
"cpu_time": 3.3229297944664364e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8064503619514614e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7535440851179631e+06,
"cpu_time": 3.3240231383399395e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8081003488288653e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time_median",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7534290991738262e+06,
"cpu_time": 3.3236446561265169e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8082549513064563e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3196047545330730e+03,
"cpu_time": 4.6636839772774902e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5905546854383510e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2055753065565535e-03,
"cpu_time": 1.4030239210689112e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2054710393464604e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 227,
"real_time": 3.0766427732331245e+06,
"cpu_time": 3.9681082466960168e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8163649619815445e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 227,
"real_time": 3.0772616268270998e+06,
"cpu_time": 3.9671290132158580e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8149941549244535e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 227,
"real_time": 3.0781751055483776e+06,
"cpu_time": 3.9665726475770860e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8129717384170449e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 227,
"real_time": 3.0785141182480799e+06,
"cpu_time": 3.9703792599119716e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8122214790863025e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 227,
"real_time": 3.0720971210855613e+06,
"cpu_time": 3.9594586123348013e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8264508488551521e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0765381489884490e+06,
"cpu_time": 3.9663295559471473e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8166006366529000e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time_median",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0772616268270998e+06,
"cpu_time": 3.9671290132158576e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8149941549244535e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5904235432632504e+03,
"cpu_time": 4.1070650884311708e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.7447569549981831e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.4199298621243134e-04,
"cpu_time": 1.0354825615216477e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4275979497883341e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 194,
"real_time": 3.6071348088054159e+06,
"cpu_time": 5.0209790927835423e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1627799409551423e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 194,
"real_time": 3.6079892252581483e+06,
"cpu_time": 5.0217967989690630e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1625045802901204e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 194,
"real_time": 3.6080173269567108e+06,
"cpu_time": 5.0233247164948247e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1624955259119585e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 194,
"real_time": 3.6206409051899137e+06,
"cpu_time": 5.0325459896907359e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1584424166417012e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 194,
"real_time": 3.6015314345257645e+06,
"cpu_time": 5.0145468144329553e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1645890300419631e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6090627401471906e+06,
"cpu_time": 5.0226386824742239e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1621622987681770e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time_median",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6079892252581478e+06,
"cpu_time": 5.0217967989690630e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1625045802901204e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.0131432386233664e+03,
"cpu_time": 6.4723781006100298e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2547852754530753e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9432034695903752e-03,
"cpu_time": 1.2886409932680331e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9401638461710672e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 138,
"real_time": 4.8973164656132031e+06,
"cpu_time": 7.5690452971014688e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7128989026747828e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 138,
"real_time": 4.8737393833858809e+06,
"cpu_time": 7.5302403550723195e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7211851804378328e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 138,
"real_time": 4.9300065965972086e+06,
"cpu_time": 7.5912432318842215e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7015409281176193e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 138,
"real_time": 4.9261167220285404e+06,
"cpu_time": 7.5886557536232499e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7028845383398933e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 138,
"real_time": 4.9254141572484933e+06,
"cpu_time": 7.5862600362319285e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7031274390712690e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9105186649746653e+06,
"cpu_time": 7.5730889347826391e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7083273977282796e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time_median",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9254141572484933e+06,
"cpu_time": 7.5862600362319294e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7031274390712690e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4351427961404650e+04,
"cpu_time": 2.5483985433426311e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4991424833897222e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.9590337849841539e-03,
"cpu_time": 3.3650714593328281e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9751250812296371e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 88,
"real_time": 7.9415342876348980e+06,
"cpu_time": 1.3688444999999983e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1125912691861579e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 88,
"real_time": 7.9442997653545300e+06,
"cpu_time": 1.3687478920454573e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1118558583559797e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 88,
"real_time": 7.9476107335226098e+06,
"cpu_time": 1.3689998147727262e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1109760609228849e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 88,
"real_time": 7.9379287463697521e+06,
"cpu_time": 1.3695520477272667e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1135508438108258e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 88,
"real_time": 7.9541562008671463e+06,
"cpu_time": 1.3702766090909015e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1092389407905996e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.9451059467497887e+06,
"cpu_time": 1.3692841727272701e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1116425946132898e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time_median",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.9442997653545309e+06,
"cpu_time": 1.3689998147727260e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1118558583559797e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.1866780045174401e+03,
"cpu_time": 6.3609265752197298e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6438292734709405e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.7867784847454526e-04,
"cpu_time": 4.6454393484665515e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.7845999018218278e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 52,
"real_time": 1.3573708514181467e+07,
"cpu_time": 2.5007326826923307e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4720165432271643e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 52,
"real_time": 1.3562874635681510e+07,
"cpu_time": 2.4994525519230790e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4739911634753489e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 52,
"real_time": 1.3582966970996214e+07,
"cpu_time": 2.5031430865384918e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4703315609652123e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 52,
"real_time": 1.3542523553881507e+07,
"cpu_time": 2.4968074192308072e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4777089636578665e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 52,
"real_time": 1.3551415768093787e+07,
"cpu_time": 2.4973335019230746e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4760831321405129e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3562697888566900e+07,
"cpu_time": 2.4994938484615572e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4740262726932211e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time_median",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3562874635681510e+07,
"cpu_time": 2.4994525519230794e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4739911634753489e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6327820128425297e+04,
"cpu_time": 2.5854087377625277e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9784233859946774e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2038770060777764e-03,
"cpu_time": 1.0343729148818875e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2038770238087934e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 28,
"real_time": 2.4621350025492053e+07,
"cpu_time": 4.7668973642857842e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7256370560719829e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 28,
"real_time": 2.4531674238720112e+07,
"cpu_time": 4.7665280607142381e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7356006502840819e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 28,
"real_time": 2.4622675829700060e+07,
"cpu_time": 4.7666441000000000e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7254902945622497e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 28,
"real_time": 2.4540257307567768e+07,
"cpu_time": 4.7663883714285754e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7346438612648473e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 28,
"real_time": 2.4669779198510308e+07,
"cpu_time": 4.7676848035714723e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7202863657593007e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4597147319998063e+07,
"cpu_time": 4.7668285400000140e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7283316455884924e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time_median",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4621350025492057e+07,
"cpu_time": 4.7666441000000000e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7256370560719829e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.9236946712670629e+04,
"cpu_time": 5.1380403583964617e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.5715886942260778e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4082852349511926e-03,
"cpu_time": 1.0778739607018560e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4086473156047007e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 16,
"real_time": 4.4960850849747658e+07,
"cpu_time": 8.7076805937499553e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9852132569406943e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 16,
"real_time": 4.4936058809980750e+07,
"cpu_time": 8.6973259249999657e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9868602533115096e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 16,
"real_time": 4.4920268934220076e+07,
"cpu_time": 8.6941317437499776e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9879101613693476e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 16,
"real_time": 4.4870279263705015e+07,
"cpu_time": 8.6925117750000775e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9912389715962157e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 16,
"real_time": 4.4915589503943920e+07,
"cpu_time": 8.6930255500000447e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9882214501095371e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.4920609472319491e+07,
"cpu_time": 8.6969351175000042e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9878888186654611e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time_median",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.4920268934220076e+07,
"cpu_time": 8.6941317437499776e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9879101613693476e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3228363016630348e+04,
"cpu_time": 6.2914142223657618e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2108370063846861e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.3971309398876222e-04,
"cpu_time": 7.2340590534085468e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.3993282232374209e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.5369773209095001e+07,
"cpu_time": 1.6439538887500051e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1443852538125496e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.5412476211786270e+07,
"cpu_time": 1.6441444587499630e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1428131802945895e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.5332995280623436e+07,
"cpu_time": 1.6439301562500221e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1457404620244665e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.3763759583234787e+07,
"cpu_time": 1.6052745387500522e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.2046729675888023e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.6012801155447960e+07,
"cpu_time": 1.6489506962499690e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1208779669303627e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.5178361088037506e+07,
"cpu_time": 1.6372507477500021e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1516979661301546e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time_median",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.5369773209095001e+07,
"cpu_time": 1.6439538887500051e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1443852538125496e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.3856244076576899e+05,
"cpu_time": 1.8003031588035836e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1321439008127324e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.8447825252127013e-03,
"cpu_time": 1.0995891504570431e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.9379570456066511e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6405433043837547e+08,
"cpu_time": 3.0734573049998915e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2725189915158467e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6685758903622627e+08,
"cpu_time": 3.1158725099999171e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2175396702120667e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6408236697316170e+08,
"cpu_time": 3.0733097300000620e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2719598205687380e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.6688183322548866e+08,
"cpu_time": 3.1161905550000310e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2170722338277931e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6372112184762955e+08,
"cpu_time": 3.0677975950000304e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2791792893995070e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6511944830417636e+08,
"cpu_time": 3.0893255389999872e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2516540011047902e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time_median",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6408236697316170e+08,
"cpu_time": 3.0734573049998915e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2719598205687380e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6040935485117952e+06,
"cpu_time": 2.4485863855554787e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1484130228306450e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.7147462941906109e-03,
"cpu_time": 7.9259578009641708e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.6824970361573896e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.1946991384029388e+08,
"cpu_time": 5.6197194700001776e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3610107790518703e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.1875278055667877e+08,
"cpu_time": 5.6147966449998426e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3685724156657934e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.1801357865333557e+08,
"cpu_time": 5.6053470300000191e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3764024434015713e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.1874062120914459e+08,
"cpu_time": 5.6025327500000799e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3687009202867007e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.1900304555892944e+08,
"cpu_time": 5.6124025049999201e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3659296954945455e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1879598796367645e+08,
"cpu_time": 5.6109596800000083e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3681232507800965e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time_median",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1875278055667877e+08,
"cpu_time": 5.6124025049999213e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3685724156657934e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.2776548326815199e+05,
"cpu_time": 7.0009455513923254e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.5785172870503860e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6554960011864561e-03,
"cpu_time": 1.2477269398935185e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6562687501885023e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2740403996091094e+06,
"cpu_time": 2.5802008636364462e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8011993105769237e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2664793227291242e+06,
"cpu_time": 2.5728709545453717e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8072081924259095e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2722938931063302e+06,
"cpu_time": 2.5853760551948557e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8025837293434697e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2670486760507156e+06,
"cpu_time": 2.5734621590910084e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8067543248058469e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2666424016964128e+06,
"cpu_time": 2.5796687629869590e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8070781685432382e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2693009386383384e+06,
"cpu_time": 2.5783157590909279e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8049647451390778e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time_median",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2670486760507156e+06,
"cpu_time": 2.5796687629869585e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8067543248058469e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5889513966643208e+03,
"cpu_time": 5.2066147652994805e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8526278785706754e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5815228978919914e-03,
"cpu_time": 2.0193860069083421e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5804341255157713e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 306,
"real_time": 2.2680473329767194e+06,
"cpu_time": 2.5767117581698825e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6119175648985836e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 306,
"real_time": 2.2680457746853530e+06,
"cpu_time": 2.5838065032681189e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6119200465151458e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 306,
"real_time": 2.2759339079759968e+06,
"cpu_time": 2.5844830980393118e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.5994015341531602e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 306,
"real_time": 2.2678773764983499e+06,
"cpu_time": 2.5826587908495953e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6121882447844772e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 306,
"real_time": 2.2676912398120156e+06,
"cpu_time": 2.5826906862744703e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6124847405059827e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2695191263896869e+06,
"cpu_time": 2.5820701673202761e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6095824261714700e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time_median",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2680457746853526e+06,
"cpu_time": 2.5826906862744703e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6119200465151458e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5889718562761968e+03,
"cpu_time": 3.0935888233694636e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.6960868842967129e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5813798678953953e-03,
"cpu_time": 1.1981040881549909e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5780459376677288e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2755634952820353e+06,
"cpu_time": 2.5958982532468727e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1999748782968381e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2822175539316391e+06,
"cpu_time": 2.5937507175324773e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1789825522000873e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2805583324622023e+06,
"cpu_time": 2.5923543311688933e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1842056249054726e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2814482111822474e+06,
"cpu_time": 2.5934014253245061e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1814034259887077e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2750845286305752e+06,
"cpu_time": 2.5876292077921792e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2014906671893634e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2789744242977398e+06,
"cpu_time": 2.5926067870129859e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1892114297160944e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time_median",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2805583324622018e+06,
"cpu_time": 2.5934014253245061e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1842056249054726e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3879197708770944e+03,
"cpu_time": 3.0665047650270394e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0692105002056423e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4865984167071436e-03,
"cpu_time": 1.1827882193273299e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4872430873101557e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 306,
"real_time": 2.2883130461160168e+06,
"cpu_time": 2.6101910784313167e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4319719085471086e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 306,
"real_time": 2.2888296425306038e+06,
"cpu_time": 2.6055486111110123e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4316487077548787e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 306,
"real_time": 2.2940490116346991e+06,
"cpu_time": 2.6167885686275032e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4283914525718914e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 306,
"real_time": 2.2895977462587110e+06,
"cpu_time": 2.6061343823528946e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4311684248267690e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 306,
"real_time": 2.3021671983407312e+06,
"cpu_time": 2.6183921013071560e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4233544819688717e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2925913289761525e+06,
"cpu_time": 2.6114109483659766e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4293069951339040e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time_median",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2895977462587110e+06,
"cpu_time": 2.6101910784313167e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4311684248267690e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.8145859580452106e+03,
"cpu_time": 5.9445884150628754e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.6166605163098146e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.5362505233943915e-03,
"cpu_time": 2.2763894816258423e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5303594879356127e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 301,
"real_time": 2.3247020031353366e+06,
"cpu_time": 2.6494600631228671e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8191140159732856e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 301,
"real_time": 2.3260978653878467e+06,
"cpu_time": 2.6644881096346602e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8174223008915711e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 301,
"real_time": 2.3251096942335167e+06,
"cpu_time": 2.6498823887042692e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8186197048051208e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 301,
"real_time": 2.3363363415473127e+06,
"cpu_time": 2.6618034750831355e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8050755721497152e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 301,
"real_time": 2.3238382037679520e+06,
"cpu_time": 2.6489859900331274e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8201619154783521e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3272168216143930e+06,
"cpu_time": 2.6549240053156121e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8160787018596090e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time_median",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3251096942335172e+06,
"cpu_time": 2.6498823887042692e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8186197048051208e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.1622926877957962e+03,
"cpu_time": 7.5718522097648483e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2292973714687520e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2182259254273987e-03,
"cpu_time": 2.8520033698157476e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2120466190647336e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 294,
"real_time": 2.3802082651440487e+06,
"cpu_time": 2.7382729319727481e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5067450155277744e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 294,
"real_time": 2.3846621490495442e+06,
"cpu_time": 2.7306570918367039e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4964599514543980e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 294,
"real_time": 2.3795628158350280e+06,
"cpu_time": 2.7312209931972972e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5082387036714837e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 294,
"real_time": 2.3794136846400038e+06,
"cpu_time": 2.7292342142857253e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5085839358711891e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 294,
"real_time": 2.3720187949156072e+06,
"cpu_time": 2.7162866020408855e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5257572275966451e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3791731419168469e+06,
"cpu_time": 2.7291343666666723e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5091569668242984e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time_median",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3795628158350280e+06,
"cpu_time": 2.7306570918367039e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5082387036714837e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5440914100979153e+03,
"cpu_time": 7.9884463992943956e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0532947566445966e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9099456571861106e-03,
"cpu_time": 2.9270989720639427e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9118982504718112e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 278,
"real_time": 2.4999116284424346e+06,
"cpu_time": 2.8717994424459329e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0486130670280068e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 278,
"real_time": 2.4887081244022404e+06,
"cpu_time": 2.8692787122301147e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0533336449928777e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 278,
"real_time": 2.4880450545548857e+06,
"cpu_time": 2.8634275971221407e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0536143608818124e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 278,
"real_time": 2.4948900284098205e+06,
"cpu_time": 2.8663096546762986e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0507236672354810e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 278,
"real_time": 2.4954149358832152e+06,
"cpu_time": 2.8705620899280091e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0505026487998399e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4933939543385194e+06,
"cpu_time": 2.8682754992804993e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0513574777876037e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time_median",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4948900284098210e+06,
"cpu_time": 2.8692787122301143e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0507236672354810e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9842354187181409e+03,
"cpu_time": 3.3918950743710111e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1013684205179254e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9989762989701420e-03,
"cpu_time": 1.1825555373679623e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9987192414704508e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 270,
"real_time": 2.5931684360666960e+06,
"cpu_time": 3.0372282481481405e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0218046491235149e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 270,
"real_time": 2.5942422035667631e+06,
"cpu_time": 3.0367456037037368e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0209678158776718e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 270,
"real_time": 2.5983737574683297e+06,
"cpu_time": 3.0422832407408706e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0177543684509379e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 270,
"real_time": 2.5916649822007725e+06,
"cpu_time": 3.0356337037037266e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0229775206315002e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 270,
"real_time": 2.5979542113081724e+06,
"cpu_time": 3.0377084037038712e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0180802175724271e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5950807181221466e+06,
"cpu_time": 3.0379198400000688e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0203169143312106e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time_median",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5942422035667626e+06,
"cpu_time": 3.0372282481481405e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0209678158776718e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9634545902166024e+03,
"cpu_time": 2.5577099456921746e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3068001265822750e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1419508339459354e-03,
"cpu_time": 8.4192805617021055e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1418011254664467e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 254,
"real_time": 2.7590429641335732e+06,
"cpu_time": 3.3365889803149472e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8005062394136584e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 254,
"real_time": 2.7523954054267388e+06,
"cpu_time": 3.3357813228346505e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8096851852483964e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 254,
"real_time": 2.7559425967826149e+06,
"cpu_time": 3.3325873818898979e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8047817150623703e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 254,
"real_time": 2.7557339805259011e+06,
"cpu_time": 3.3370958385827234e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8050697469713348e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 254,
"real_time": 2.7534939920691056e+06,
"cpu_time": 3.3305816102361991e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8081652003607625e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7553217877875869e+06,
"cpu_time": 3.3345270267716842e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8056416174113053e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time_median",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7557339805259006e+06,
"cpu_time": 3.3357813228346501e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8050697469713348e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5645180334510442e+03,
"cpu_time": 2.8174562572764989e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5410975264739600e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.3075082729638259e-04,
"cpu_time": 8.4493429942423170e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.3048633646241892e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 226,
"real_time": 3.0876570000041244e+06,
"cpu_time": 3.9918503362831874e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7920497645858943e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 226,
"real_time": 3.0931550968207614e+06,
"cpu_time": 4.0049350486724889e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7799768661956728e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 226,
"real_time": 3.0936124565623766e+06,
"cpu_time": 4.0098563982301992e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7789745142491317e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 226,
"real_time": 3.0891883529030378e+06,
"cpu_time": 3.9950284955752213e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7886828526632881e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 226,
"real_time": 3.0823281257355637e+06,
"cpu_time": 3.9915204247788815e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8037921806249547e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0891882064051731e+06,
"cpu_time": 3.9986381407079957e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7886952356637883e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time_median",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0891883529030378e+06,
"cpu_time": 3.9950284955752208e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7886828526632881e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6020514142857373e+03,
"cpu_time": 8.2955719921366290e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0120192140073231e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4897284033209010e-03,
"cpu_time": 2.0745993261265250e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4907418566837010e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 193,
"real_time": 3.6158287340360139e+06,
"cpu_time": 5.0643369222795600e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1599841443038392e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 193,
"real_time": 3.6166701622674037e+06,
"cpu_time": 5.0666559378239252e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1597142708115964e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 193,
"real_time": 3.6216634048216548e+06,
"cpu_time": 5.0716556217615977e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1581153550647385e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 193,
"real_time": 3.6184036841258947e+06,
"cpu_time": 5.0694190569948694e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1591586694432704e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 193,
"real_time": 3.6164578955157278e+06,
"cpu_time": 5.0680559326425744e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1597823398416388e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6178047761533386e+06,
"cpu_time": 5.0680246943005044e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1593509558930166e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time_median",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6166701622674041e+06,
"cpu_time": 5.0680559326425735e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1597142708115964e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3587011540937087e+03,
"cpu_time": 2.7659543634119300e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5543048834422883e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.5197026927517570e-04,
"cpu_time": 5.4576576284691739e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.5159776209641469e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 142,
"real_time": 5.0026962671323977e+06,
"cpu_time": 7.7243923239435190e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6768173704873841e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 142,
"real_time": 4.9915525727761043e+06,
"cpu_time": 7.7089918943661656e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6805608831511490e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 142,
"real_time": 4.9842680365004586e+06,
"cpu_time": 7.7098018661971176e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6830170325048945e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 142,
"real_time": 4.9867818236980643e+06,
"cpu_time": 7.7096942042253837e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6821686403314979e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 142,
"real_time": 4.9806601256394470e+06,
"cpu_time": 7.7086792605634509e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6842361832354541e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9891917651492944e+06,
"cpu_time": 7.7123119098591283e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6813600219420762e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time_median",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9867818236980643e+06,
"cpu_time": 7.7096942042253856e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6821686403314979e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.5262063781610177e+03,
"cpu_time": 6.7695596268210647e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8699371305727237e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7089353906415508e-03,
"cpu_time": 8.7776009398259883e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7069141011559002e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 87,
"real_time": 7.8310137668132093e+06,
"cpu_time": 1.3328289494253093e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1424066537974432e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 87,
"real_time": 7.9148305237464523e+06,
"cpu_time": 1.3469970114942562e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1197189187644885e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 87,
"real_time": 7.8411712257683966e+06,
"cpu_time": 1.3342888264367569e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1396313786472526e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 87,
"real_time": 7.9504868668643227e+06,
"cpu_time": 1.3521041390804147e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1102124034596319e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 87,
"real_time": 7.9320114287922438e+06,
"cpu_time": 1.3509693310344698e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1151275626130254e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.8939027623969261e+06,
"cpu_time": 1.3434376514942413e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1254193834563684e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time_median",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.9148305237464514e+06,
"cpu_time": 1.3469970114942562e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1197189187644885e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4377484422839341e+04,
"cpu_time": 9.2296913126719825e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4664730440247444e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.8885424687354533e-03,
"cpu_time": 6.8702044359157562e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.8996879177791164e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51,
"real_time": 1.3716290467510037e+07,
"cpu_time": 2.5098387529411349e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4463197305044565e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51,
"real_time": 1.3791783000616467e+07,
"cpu_time": 2.5200691117647115e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4329292302888017e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51,
"real_time": 1.3774894926623970e+07,
"cpu_time": 2.5180097196078029e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4359120108528996e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51,
"real_time": 1.3759719938331960e+07,
"cpu_time": 2.5136025549019735e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4385984707816429e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51,
"real_time": 1.3808495145948494e+07,
"cpu_time": 2.5239101372549426e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4299847047304859e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3770236695806187e+07,
"cpu_time": 2.5170860552941132e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4367488294316573e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time_median",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3774894926623970e+07,
"cpu_time": 2.5180097196078025e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4359120108528996e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5250706047941683e+04,
"cpu_time": 5.4995009468825046e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2463250473986706e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.5599201253147311e-03,
"cpu_time": 2.1848680681042132e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5633848560647722e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 28,
"real_time": 2.4365937137710195e+07,
"cpu_time": 4.6527072500000238e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.7542082055255027e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 28,
"real_time": 2.5414041376539640e+07,
"cpu_time": 4.8346264250000104e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6406214976084023e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 28,
"real_time": 2.5414927396923304e+07,
"cpu_time": 4.8319043928572118e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6405294397230544e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 28,
"real_time": 2.5380578424249377e+07,
"cpu_time": 4.8316446499999948e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6441030176003456e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 28,
"real_time": 2.5391927720712762e+07,
"cpu_time": 4.8314613500001058e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6429211967730122e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5193482411227059e+07,
"cpu_time": 4.7964688135714695e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6644766714460640e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time_median",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5391927720712766e+07,
"cpu_time": 4.8316446499999955e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6429211967730122e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6284467630482570e+05,
"cpu_time": 8.0375505945367506e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0184688137070656e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8371603764415143e-02,
"cpu_time": 1.6757224756251379e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8834726036401902e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 4.5995108286539711e+07,
"cpu_time": 8.8087951533335239e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9180870096848602e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 4.5896399269501366e+07,
"cpu_time": 8.7993801066666797e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9243629159638472e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 4.6128623684247337e+07,
"cpu_time": 8.8201294733335078e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9096408537728515e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.6641982346773148e+07,
"cpu_time": 8.9244664399999842e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.8776162857341685e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 4.6054171770811081e+07,
"cpu_time": 8.8226635599998340e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9143446258883014e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6143257071574524e+07,
"cpu_time": 8.8350869466667056e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9088103382088060e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time_median",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6054171770811081e+07,
"cpu_time": 8.8201294733335093e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9143446258883014e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9144642042298720e+05,
"cpu_time": 5.0825675580236793e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8250522694612339e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.3161215509974465e-03,
"cpu_time": 5.7527080250650226e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2742223014274241e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.7171018123626709e+07,
"cpu_time": 1.6666201262500378e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0794117331439500e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.7379561737179756e+07,
"cpu_time": 1.6679597499999943e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0720622839400382e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.7991042993962765e+07,
"cpu_time": 1.6819663249999905e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0507134233926272e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.7203377857804298e+07,
"cpu_time": 1.6671786112500086e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0782690142773671e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.7428119033575058e+07,
"cpu_time": 1.6681861612499917e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0703560704184041e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.7434623949229732e+07,
"cpu_time": 1.6703821947500044e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0701625050344772e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time_median",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.7379561737179756e+07,
"cpu_time": 1.6679597499999943e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0720622839400382e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3001481048313581e+05,
"cpu_time": 6.5057471128992795e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1545314167304413e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.7744179087996540e-03,
"cpu_time": 3.8947656011580943e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7604895989617206e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6999528184533119e+08,
"cpu_time": 3.1636755674999505e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1581518391108499e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6916919872164726e+08,
"cpu_time": 3.1405298949999863e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1735736532237935e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6966279968619347e+08,
"cpu_time": 3.1576139750001174e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1643407570368447e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.6935619711875916e+08,
"cpu_time": 3.1438360450000858e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1700694815644994e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6979407519102097e+08,
"cpu_time": 3.1618111724999666e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1618942615990100e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6959551051259041e+08,
"cpu_time": 3.1534933310000217e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1656059985070000e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time_median",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6966279968619347e+08,
"cpu_time": 3.1576139750001174e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1643407570368447e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3271065749994590e+05,
"cpu_time": 1.0620239876626271e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2118540273898905e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9617892979262924e-03,
"cpu_time": 3.3677698862481596e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9622953805115348e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.2319845259189606e+08,
"cpu_time": 5.6536951800001132e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3222368962137885e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.2301260530948639e+08,
"cpu_time": 5.6463897800000501e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3241483655760779e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.2289998233318329e+08,
"cpu_time": 5.6270940050001168e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3253077818135743e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.2324321568012238e+08,
"cpu_time": 5.6498326799999177e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3217768290690503e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.2389615476131439e+08,
"cpu_time": 5.6622772250000250e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3150804917436023e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2325008213520050e+08,
"cpu_time": 5.6478577740000451e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3217100728832188e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time_median",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2319845259189606e+08,
"cpu_time": 5.6498326799999177e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3222368962137885e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8700378236959933e+05,
"cpu_time": 1.3030591305971283e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9724717148294463e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1972271741225223e-03,
"cpu_time": 2.3071741228962439e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1959116321616147e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2617678450342137e+06,
"cpu_time": 2.5706053527507298e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8109727790997224e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2614665343019278e+06,
"cpu_time": 2.5816373009708682e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8112140674521888e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2619253010895937e+06,
"cpu_time": 2.5709759902913468e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8108467145342568e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2615809618980656e+06,
"cpu_time": 2.5772811747574201e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8111224267480439e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2621702328987396e+06,
"cpu_time": 2.5766974919094499e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8106506488467914e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2617821750445077e+06,
"cpu_time": 2.5754394621359631e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8109613273362007e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time_median",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2617678450342133e+06,
"cpu_time": 2.5766974919094495e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8109727790997224e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7901394225090155e+02,
"cpu_time": 4.6550763949436569e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2339368150974315e+02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2336021803046135e-04,
"cpu_time": 1.8074881834275109e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2335640642218454e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2706912143282518e+06,
"cpu_time": 2.5824689288026951e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6077120254430869e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2635139543020609e+06,
"cpu_time": 2.5824472038834020e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6191515340253101e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2631157671845849e+06,
"cpu_time": 2.5810856537216669e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6197883107814710e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2636299597213953e+06,
"cpu_time": 2.5817393333332157e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6189660614883630e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2632964957553688e+06,
"cpu_time": 2.5814587508091372e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6194992637347514e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2648494782583322e+06,
"cpu_time": 2.5818399741100236e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6170234390945965e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time_median",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2635139543020604e+06,
"cpu_time": 2.5817393333332157e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6191515340253101e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2716295157215650e+03,
"cpu_time": 6.1007602247473039e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.2148637824989764e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4445240388502312e-03,
"cpu_time": 2.3629505646841163e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4417555955358551e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2698396532614897e+06,
"cpu_time": 2.5899726623376552e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2181310148750553e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2776438552257302e+06,
"cpu_time": 2.5926029805195378e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1933985475425581e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2755108679971332e+06,
"cpu_time": 2.5893735811688905e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2001413970045876e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2698900626077279e+06,
"cpu_time": 2.5899391948051411e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2179707158052828e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2903421346412655e+06,
"cpu_time": 2.6046404253247674e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1535163904960481e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2766453147466695e+06,
"cpu_time": 2.5933057688311981e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.1966316131447069e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time_median",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2755108679971332e+06,
"cpu_time": 2.5899726623376552e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2001413970045876e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.3940066036735698e+03,
"cpu_time": 6.4589834459351796e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6454088989560350e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.6870067328022074e-03,
"cpu_time": 2.4906370562103983e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.6758987275716240e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 306,
"real_time": 2.2890830741209141e+06,
"cpu_time": 2.6133458398691737e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4314902054214012e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 306,
"real_time": 2.2965932190357372e+06,
"cpu_time": 2.6154015947712669e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4268090547510276e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 306,
"real_time": 2.2942919970423081e+06,
"cpu_time": 2.6119502712417506e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4282401735368883e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 306,
"real_time": 2.2877266849665083e+06,
"cpu_time": 2.6115458333333437e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4323389334630994e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 306,
"real_time": 2.2880054235738381e+06,
"cpu_time": 2.6061423006537738e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4321644373035079e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2911400797478617e+06,
"cpu_time": 2.6116771679738620e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4302085608951850e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time_median",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2890830741209141e+06,
"cpu_time": 2.6119502712417510e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4314902054214012e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.0428924092941952e+03,
"cpu_time": 3.4417441540627842e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5217921856755715e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7645767035506239e-03,
"cpu_time": 1.3178290932232208e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7632338769508909e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 302,
"real_time": 2.3251949818743183e+06,
"cpu_time": 2.6515963443709752e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8185163184539489e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 302,
"real_time": 2.3194566470823740e+06,
"cpu_time": 2.6543156158940797e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8254893266678303e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 302,
"real_time": 2.3195504076741883e+06,
"cpu_time": 2.6534715662252577e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8253751150729638e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 302,
"real_time": 2.3186789310555784e+06,
"cpu_time": 2.6465213807946146e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8264370337019775e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 302,
"real_time": 2.3242635706390273e+06,
"cpu_time": 2.6516844768213513e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8196457935268372e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3214289076650972e+06,
"cpu_time": 2.6515178768212562e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8230927174847115e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time_median",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3195504076741887e+06,
"cpu_time": 2.6516844768213518e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8253751150729638e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0495726955644100e+03,
"cpu_time": 3.0266785202288488e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7068260736949880e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3136618939718825e-03,
"cpu_time": 1.1414890115156796e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3130373121424278e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 293,
"real_time": 2.3914142551517221e+06,
"cpu_time": 2.7461987576792547e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4809408164075777e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 293,
"real_time": 2.3992116993719097e+06,
"cpu_time": 2.7508107372013074e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4631277445968352e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 293,
"real_time": 2.3897673192500761e+06,
"cpu_time": 2.7448081877132640e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4847180704241619e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 293,
"real_time": 2.3925845247435896e+06,
"cpu_time": 2.7387553754267558e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4782599588220119e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 293,
"real_time": 2.3878303677504789e+06,
"cpu_time": 2.7429817918089614e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4891671439575493e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3921616332535557e+06,
"cpu_time": 2.7447109699659087e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4792427468416274e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time_median",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3914142551517221e+06,
"cpu_time": 2.7448081877132640e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4809408164075777e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.3282052838400177e+03,
"cpu_time": 4.4127453842625137e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.8996898480457457e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8093281088006031e-03,
"cpu_time": 1.6077267998521982e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8067624132462783e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 280,
"real_time": 2.5130426003930294e+06,
"cpu_time": 2.8887264714287296e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0431339284061551e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 280,
"real_time": 2.5093534296112400e+06,
"cpu_time": 2.8854687250001477e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0446675103897679e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 280,
"real_time": 2.5041013648400879e+06,
"cpu_time": 2.8830379821428666e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0468585804103042e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 280,
"real_time": 2.5032288112145448e+06,
"cpu_time": 2.8867165964285848e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0472234852267061e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 280,
"real_time": 2.5090242769303066e+06,
"cpu_time": 2.8841511392857102e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0448045577331877e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5077500965978419e+06,
"cpu_time": 2.8856201828572075e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0453376124332243e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time_median",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5090242769303066e+06,
"cpu_time": 2.8854687250001477e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0448045577331877e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.0607903680286208e+03,
"cpu_time": 2.2192307468903091e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6925769653105881e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6192962662179629e-03,
"cpu_time": 7.6906543698101310e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6191677647289374e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 269,
"real_time": 2.5998854067965955e+06,
"cpu_time": 3.0546604237919413e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0165811871146756e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 269,
"real_time": 2.5929672994952109e+06,
"cpu_time": 3.0412316394053753e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0219614805866098e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 269,
"real_time": 2.5894383538071220e+06,
"cpu_time": 3.0425800074348291e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0247170558401808e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 269,
"real_time": 2.5943757742851088e+06,
"cpu_time": 3.0432616171002984e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0208637669092861e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 269,
"real_time": 2.5928786697842483e+06,
"cpu_time": 3.0486680594795793e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0220305952211240e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5939091008336572e+06,
"cpu_time": 3.0460803494424052e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0212308171343753e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time_median",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5929672994952113e+06,
"cpu_time": 3.0432616171002984e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0219614805866098e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8036289890873354e+03,
"cpu_time": 5.5682482498236041e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9614675233741803e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4663694220683700e-03,
"cpu_time": 1.8280043895896869e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4651802744492274e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 255,
"real_time": 2.7545326654160139e+06,
"cpu_time": 3.3371761843136037e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8067292254878187e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 255,
"real_time": 2.7469868926952281e+06,
"cpu_time": 3.3317379137253170e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8171860331345856e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 255,
"real_time": 2.7502471617623870e+06,
"cpu_time": 3.3316905254902812e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8126609658168375e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 255,
"real_time": 2.7496761870661788e+06,
"cpu_time": 3.3312826000002022e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8134526710172331e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 255,
"real_time": 2.7589530985364141e+06,
"cpu_time": 3.3444051960785538e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8006300308484942e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7520792010952444e+06,
"cpu_time": 3.3352584839215917e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8101317852609944e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time_median",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7502471617623875e+06,
"cpu_time": 3.3317379137253170e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8126609658168375e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6992659690400969e+03,
"cpu_time": 5.6628683742474950e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.5009268465350382e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7075329689530488e-03,
"cpu_time": 1.6978799099220351e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7062209952115144e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 227,
"real_time": 3.0880496439232701e+06,
"cpu_time": 3.9960100925111067e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7911861589622450e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 227,
"real_time": 3.0870410072153625e+06,
"cpu_time": 3.9952476123349266e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7934050603743589e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 227,
"real_time": 3.0811194993046806e+06,
"cpu_time": 3.9922086607928895e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8064610946549344e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 227,
"real_time": 3.0849827761199768e+06,
"cpu_time": 3.9942376519824360e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7979374673774207e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 227,
"real_time": 3.0886036218738896e+06,
"cpu_time": 3.9936098590308954e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7899680786090469e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0859593096874366e+06,
"cpu_time": 3.9942627753304513e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7957915719956017e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time_median",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0870410072153625e+06,
"cpu_time": 3.9942376519824364e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7934050603743589e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0376527138733454e+03,
"cpu_time": 1.4721870356938894e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6944365504499327e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.8434632768408612e-04,
"cpu_time": 3.6857540890561298e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.8508561946435537e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 194,
"real_time": 3.6133182494296241e+06,
"cpu_time": 5.0694864742267448e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1607900855846524e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 194,
"real_time": 3.6105479080153187e+06,
"cpu_time": 5.0682160309279589e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1616807495307729e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 194,
"real_time": 3.6116563306986978e+06,
"cpu_time": 5.0710014793815315e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1613242279861619e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 194,
"real_time": 3.6085677061940436e+06,
"cpu_time": 5.0675120567009412e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1623182219362409e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 194,
"real_time": 3.6135252238702527e+06,
"cpu_time": 5.0693598453608742e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1607235981897218e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6115230836415873e+06,
"cpu_time": 5.0691151773196105e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1613673766455102e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time_median",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6116563306986974e+06,
"cpu_time": 5.0693598453608733e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1613242279861619e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0575570366558641e+03,
"cpu_time": 1.3355073238357097e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6179430447836278e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.6972002919642947e-04,
"cpu_time": 2.6345965264531324e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.6984061872814723e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 143,
"real_time": 4.8775992786081936e+06,
"cpu_time": 7.5926146713288985e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7198231180634544e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 143,
"real_time": 4.9225596378889531e+06,
"cpu_time": 7.6511889020979600e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7041150574251785e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 143,
"real_time": 4.9156864089044658e+06,
"cpu_time": 7.6432798321677623e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7064977913978705e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 143,
"real_time": 4.9012493394263145e+06,
"cpu_time": 7.6316267062939759e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7115244336828368e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 143,
"real_time": 4.9758792294749431e+06,
"cpu_time": 7.7281422097903294e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6858544215280662e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9185947788605746e+06,
"cpu_time": 7.6493704643357862e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7055629644194813e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time_median",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9156864089044658e+06,
"cpu_time": 7.6432798321677623e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7064977913978705e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6356506691375216e+04,
"cpu_time": 4.9450610176625567e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2552769582602877e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.3916450380564682e-03,
"cpu_time": 6.4646640409407197e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.3598980773339172e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 87,
"real_time": 7.8139821463532150e+06,
"cpu_time": 1.3315634505747296e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1470763159895275e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 87,
"real_time": 7.8818503146370249e+06,
"cpu_time": 1.3431383034482950e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1285885078080964e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 87,
"real_time": 7.8420799557419345e+06,
"cpu_time": 1.3356930241379371e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1393834409601755e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 87,
"real_time": 7.0550440136214783e+06,
"cpu_time": 1.2511515413792893e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.3780455469317417e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 87,
"real_time": 7.8308246601587059e+06,
"cpu_time": 1.3351079689655386e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1424583907948184e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.6847562181024719e+06,
"cpu_time": 1.3193308577011582e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1871104404968719e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time_median",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.8308246601587059e+06,
"cpu_time": 1.3351079689655384e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1424583907948184e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5290566447809618e+05,
"cpu_time": 3.8345429016643402e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0695260004712817e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.5922818429396578e-02,
"cpu_time": 2.9064300886176220e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.8901325724927946e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51,
"real_time": 1.3754747461016271e+07,
"cpu_time": 2.5071099882353008e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4394800482597027e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51,
"real_time": 1.3699989400657954e+07,
"cpu_time": 2.5015458470588829e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4492305080461245e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51,
"real_time": 1.3709755870057087e+07,
"cpu_time": 2.5001317666666925e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4474857406676989e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51,
"real_time": 1.3728400692343712e+07,
"cpu_time": 2.5014852254902478e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4441617601322784e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51,
"real_time": 1.3730358387179235e+07,
"cpu_time": 2.5001228686273947e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4438132679283562e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3724650362250853e+07,
"cpu_time": 2.5020791392157041e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4448342650068321e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time_median",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3728400692343712e+07,
"cpu_time": 2.5014852254902482e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4441617601322784e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1109777372287343e+04,
"cpu_time": 2.8968012685471836e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7589762854905059e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5380921783150854e-03,
"cpu_time": 1.1577576516845140e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5375178347641497e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 28,
"real_time": 2.5303560309112072e+07,
"cpu_time": 4.8225034035713829e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6521510483184223e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 28,
"real_time": 2.5361097949956145e+07,
"cpu_time": 4.8305348250002973e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6461340172425795e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 28,
"real_time": 2.5523687579802103e+07,
"cpu_time": 4.8492951107139759e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6292777558171444e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 28,
"real_time": 2.5338337690170322e+07,
"cpu_time": 4.8275923428572498e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6485109173532724e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 28,
"real_time": 2.5271040187882524e+07,
"cpu_time": 4.8171336607144408e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6555639776228414e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5359544743384637e+07,
"cpu_time": 4.8294118685714699e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6463275432708521e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time_median",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5338337690170322e+07,
"cpu_time": 4.8275923428572506e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6485109173532724e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.7931526498154140e+04,
"cpu_time": 1.2231070066644539e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0182396052796219e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.8617225777959141e-03,
"cpu_time": 2.5326210311945223e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8477459370773169e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 4.7390252600113548e+07,
"cpu_time": 9.0851348933332101e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.8321800504536328e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 4.5897176116704941e+07,
"cpu_time": 8.8001413400002092e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9243134187323022e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 4.5885218183199562e+07,
"cpu_time": 8.8048880933335260e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9250755104645562e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.5887223631143570e+07,
"cpu_time": 8.7960075799999982e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9249476734283547e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 4.5881142963965736e+07,
"cpu_time": 8.8029465933338240e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9253353192489629e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6188202699025467e+07,
"cpu_time": 8.8578237000001535e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9063703944655619e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time_median",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5887223631143570e+07,
"cpu_time": 8.8029465933338240e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9249476734283547e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.7199221225961146e+05,
"cpu_time": 1.2711465420123679e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.1475367070954300e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4549001108323922e-02,
"cpu_time": 1.4350551388964150e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4270502875316071e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.7700656615197659e+07,
"cpu_time": 1.6708382825000000e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0608146661638880e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.7124891579151154e+07,
"cpu_time": 1.6662926112500998e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0810420665617929e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.7260894477367401e+07,
"cpu_time": 1.6661283925000703e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0762400226097074e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.7061014026403427e+07,
"cpu_time": 1.6663166437500367e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0833026585078626e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.7402153760194778e+07,
"cpu_time": 1.6699241199999905e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0712682062332945e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.7309922091662884e+07,
"cpu_time": 1.6679000100000396e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0745335240153093e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time_median",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.7260894477367401e+07,
"cpu_time": 1.6663166437500364e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0762400226097074e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5484081847121910e+05,
"cpu_time": 2.2890977786925217e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.9587993648434840e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.9188070767452163e-03,
"cpu_time": 1.3724430511229911e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9138727208098169e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6787138953804970e+08,
"cpu_time": 3.1163635574998236e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1981084655185566e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6964251548051834e+08,
"cpu_time": 3.1615873999999166e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1647191181956625e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6738265752792358e+08,
"cpu_time": 3.1069012400001836e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2074464578890834e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.6963607072830200e+08,
"cpu_time": 3.1610924250000495e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1648393510592480e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6748745366930962e+08,
"cpu_time": 3.1125045724999720e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2054395731635399e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6840401738882065e+08,
"cpu_time": 3.1316898389999890e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1881105931652184e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time_median",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6787138953804970e+08,
"cpu_time": 3.1163635574998242e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1981084655185566e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1422336012436764e+06,
"cpu_time": 2.7275539467166741e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1580306267483786e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.7826980552751501e-03,
"cpu_time": 8.7095277212625756e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.7689955027747132e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.2117459177970886e+08,
"cpu_time": 5.6111646300001895e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3431717560537014e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.3171749114990234e+08,
"cpu_time": 5.7348371149998915e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2369165107268300e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.2143411040306091e+08,
"cpu_time": 5.6251707000001264e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3404725548685112e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.2259628176689148e+08,
"cpu_time": 5.6433594500003886e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3284383134207582e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.2488909363746643e+08,
"cpu_time": 5.6741179699997699e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3049488118494825e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2436231374740607e+08,
"cpu_time": 5.6577299730000734e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3107895893838573e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time_median",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2259628176689148e+08,
"cpu_time": 5.6433594500003886e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3284383134207582e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.3655167735347096e+06,
"cpu_time": 4.9114730863909852e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3967337452882908e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3458766905129160e-02,
"cpu_time": 8.6809959291617167e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3280015617381862e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 310,
"real_time": 2.2542062658636319e+06,
"cpu_time": 2.5662193741936791e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8170475621629681e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 310,
"real_time": 2.2524039568980373e+06,
"cpu_time": 2.5651743161288761e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8185015114433218e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 310,
"real_time": 2.2579002134021251e+06,
"cpu_time": 2.5772364193548746e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8140748540115023e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 310,
"real_time": 2.2581288072791309e+06,
"cpu_time": 2.5720622935483009e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8138912124040260e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 310,
"real_time": 2.2556632727144226e+06,
"cpu_time": 2.5754475451615308e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8158738715778934e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2556605032314700e+06,
"cpu_time": 2.5712279896774525e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8158778023199425e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time_median",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2556632727144226e+06,
"cpu_time": 2.5720622935483009e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8158738715778934e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4407342403665161e+03,
"cpu_time": 5.3929382323329428e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9652840251318578e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0820485781747337e-03,
"cpu_time": 2.0974173639924710e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0822776855474723e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 310,
"real_time": 2.2555956466784398e+06,
"cpu_time": 2.5697965258066156e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6318566282318505e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 310,
"real_time": 2.2580808103685416e+06,
"cpu_time": 2.5740049032257898e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6278595355774635e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 310,
"real_time": 2.2583234093842967e+06,
"cpu_time": 2.5735955903226770e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6274698149781148e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 310,
"real_time": 2.2573752614158778e+06,
"cpu_time": 2.5790608387098708e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6289934332237649e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 310,
"real_time": 2.2624410846601091e+06,
"cpu_time": 2.5826470451614759e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6208677678034212e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2583632425014530e+06,
"cpu_time": 2.5758209806452859e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6274094359629229e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time_median",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2580808103685416e+06,
"cpu_time": 2.5740049032257898e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6278595355774635e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5172328320825441e+03,
"cpu_time": 5.0407438050938017e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0399945545726373e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1146270824415104e-03,
"cpu_time": 1.9569464815179087e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1137409839979066e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2650747333915490e+06,
"cpu_time": 2.5897314433657215e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2333154215480816e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2700352829347537e+06,
"cpu_time": 2.5951078349513868e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2175089626000831e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2702750065710554e+06,
"cpu_time": 2.5891324207120826e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2167468489845321e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2651855464614807e+06,
"cpu_time": 2.5894911229772754e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2329615671413643e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2708792503151596e+06,
"cpu_time": 2.5956130938510294e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2148265909454133e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2682899639347992e+06,
"cpu_time": 2.5918151831714986e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2230718782438952e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time_median",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2700352829347537e+06,
"cpu_time": 2.5897314433657215e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2175089626000831e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9011227108117264e+03,
"cpu_time": 3.2483119865188555e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.2421982523183433e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2789911153065954e-03,
"cpu_time": 1.2532961484329403e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2795384578902110e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 307,
"real_time": 2.2843666670461721e+06,
"cpu_time": 2.6150790032573831e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4344457250538968e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 307,
"real_time": 2.2898692112865006e+06,
"cpu_time": 2.6231436058634487e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4309987591645110e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 307,
"real_time": 2.2889936527886493e+06,
"cpu_time": 2.6141835211726977e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4315461277089695e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 307,
"real_time": 2.2873092125737220e+06,
"cpu_time": 2.6136961368077416e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4326003594034778e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 307,
"real_time": 2.2856492772152349e+06,
"cpu_time": 2.6111942377848574e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4336407744902808e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2872376041820562e+06,
"cpu_time": 2.6154593009772259e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4326463491642274e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time_median",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2873092125737220e+06,
"cpu_time": 2.6141835211726977e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4326003594034778e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2792132970416860e+03,
"cpu_time": 4.5310124136494533e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4277421365897100e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.9649170373655206e-04,
"cpu_time": 1.7323964521093905e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.9657681564094421e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 302,
"real_time": 2.3286334718485046e+06,
"cpu_time": 2.6690772251655795e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8143544612015098e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 302,
"real_time": 2.3348544198489250e+06,
"cpu_time": 2.6710543245033007e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8068559411186099e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 302,
"real_time": 2.3285147929810826e+06,
"cpu_time": 2.6699889569536536e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8144979021626696e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 302,
"real_time": 2.3273169016773929e+06,
"cpu_time": 2.6677696721853348e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8159465499848995e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 302,
"real_time": 2.3203982373341820e+06,
"cpu_time": 2.6548191887416774e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8243427764059950e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3279435647380175e+06,
"cpu_time": 2.6665418735099100e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8151995261747368e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time_median",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3285147929810830e+06,
"cpu_time": 2.6690772251655799e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8144979021626696e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.1450671547683532e+03,
"cpu_time": 6.6633594007637075e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2245259262252257e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2101339709012101e-03,
"cpu_time": 2.4988767163040553e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2110425454223651e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 291,
"real_time": 2.3903348515149448e+06,
"cpu_time": 2.7454048384882072e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4834158451452635e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 291,
"real_time": 2.3910529180221846e+06,
"cpu_time": 2.7470288591066208e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4817690989632830e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 291,
"real_time": 2.3902402918696199e+06,
"cpu_time": 2.7447946048107226e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4836327730663814e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 291,
"real_time": 2.3882213229460712e+06,
"cpu_time": 2.7434619999996847e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4882685595617957e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 291,
"real_time": 2.3894436078152503e+06,
"cpu_time": 2.7441818281786288e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4854611161902919e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3898585984336147e+06,
"cpu_time": 2.7449744261167729e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4845094785854034e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time_median",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3902402918696203e+06,
"cpu_time": 2.7447946048107226e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4836327730663814e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0784009447605856e+03,
"cpu_time": 1.3559064934096741e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4754106250276942e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.5124048153618890e-04,
"cpu_time": 4.9395960869764142e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5134585594082453e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 279,
"real_time": 2.5033355118059237e+06,
"cpu_time": 2.8849856881719963e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0471788490344529e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 279,
"real_time": 2.5041040248407791e+06,
"cpu_time": 2.8931074086018582e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0468574683780086e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 279,
"real_time": 2.5085277828691681e+06,
"cpu_time": 2.8895368817203757e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0450113480512011e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 279,
"real_time": 2.5037890258428766e+06,
"cpu_time": 2.8852342150536897e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0469891723874448e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 279,
"real_time": 2.5090032580932835e+06,
"cpu_time": 2.8945821756269815e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0448133104427145e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5057519206904066e+06,
"cpu_time": 2.8894892738349801e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0461700296587646e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time_median",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5041040248407791e+06,
"cpu_time": 2.8895368817203757e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0468574683780086e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7696639937469104e+03,
"cpu_time": 4.3993926688962774e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1559101859573692e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1053225065407867e-03,
"cpu_time": 1.5225502682200051e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1048970561070262e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 269,
"real_time": 2.5996446711630961e+06,
"cpu_time": 3.0533700557619249e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0167679291548353e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 269,
"real_time": 2.6047260181971421e+06,
"cpu_time": 3.0620893531597992e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0128335814869514e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 269,
"real_time": 2.6013029766957997e+06,
"cpu_time": 3.0580764609667012e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0154822590713969e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 269,
"real_time": 2.5986442091393536e+06,
"cpu_time": 3.0529044200744415e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0175443723927072e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 269,
"real_time": 2.6049805877792570e+06,
"cpu_time": 3.0620703754645810e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0126368789832518e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6018596925949301e+06,
"cpu_time": 3.0577021330854902e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0150530042178285e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time_median",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6013029766958002e+06,
"cpu_time": 3.0580764609667012e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0154822590713969e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8944513985514832e+03,
"cpu_time": 4.4792384085634339e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2414080987183034e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1124548363577362e-03,
"cpu_time": 1.4649034515482673e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1123320796161081e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 252,
"real_time": 2.7776860792766372e+06,
"cpu_time": 3.3640502896824433e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7749982182042307e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 252,
"real_time": 2.7794657748133419e+06,
"cpu_time": 3.3698489325393848e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7725810819542050e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 252,
"real_time": 2.7752429097225624e+06,
"cpu_time": 3.3602920753965224e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7783215167454469e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 252,
"real_time": 2.7819292237316924e+06,
"cpu_time": 3.3739850476191379e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7692403927999127e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 252,
"real_time": 2.7785254670085297e+06,
"cpu_time": 3.3643051230159118e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7738577977798361e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7785698909105523e+06,
"cpu_time": 3.3664962936506802e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7737998014967263e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time_median",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7785254670085297e+06,
"cpu_time": 3.3643051230159113e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.7738577977798361e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4464068182008677e+03,
"cpu_time": 5.3990302791871054e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3226104180297756e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.8045538325442910e-04,
"cpu_time": 1.6037535194587471e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.8044162191963540e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 226,
"real_time": 3.0930701960537550e+06,
"cpu_time": 3.9610048539821319e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7801629677710462e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 226,
"real_time": 3.0942843872559280e+06,
"cpu_time": 3.9645916283185030e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7775024449507546e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 226,
"real_time": 3.0929356323044118e+06,
"cpu_time": 3.9611141238935441e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7804579510033417e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 226,
"real_time": 3.0938192452015602e+06,
"cpu_time": 3.9621902079645740e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7785214124989128e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 226,
"real_time": 3.0984188763803877e+06,
"cpu_time": 3.9676343761062422e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7684586354247868e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0945056674392084e+06,
"cpu_time": 3.9633070380529994e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7770206823297691e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time_median",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0938192452015602e+06,
"cpu_time": 3.9621902079645745e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7785214124989128e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2560437190032617e+03,
"cpu_time": 2.8165697320641953e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9366412452192634e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.2904817811182156e-04,
"cpu_time": 7.1066150187744565e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.2843827348659804e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 187,
"real_time": 3.7380471691130637e+06,
"cpu_time": 5.2039669625668572e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1220575370629134e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 187,
"real_time": 3.7495851153159207e+06,
"cpu_time": 5.2142393957216060e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1186048245357966e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 187,
"real_time": 3.7443684625693341e+06,
"cpu_time": 5.2056913475936316e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1201632643604541e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 187,
"real_time": 3.7478037529629981e+06,
"cpu_time": 5.2105477967916885e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1191365067298417e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 187,
"real_time": 3.7528065986991087e+06,
"cpu_time": 5.2214137754010959e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1176445920378454e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7465222197320857e+06,
"cpu_time": 5.2111718556149760e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1195213449453704e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time_median",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7478037529629976e+06,
"cpu_time": 5.2105477967916895e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1191365067298417e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.6343195836008726e+03,
"cpu_time": 7.0114660495253938e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6848325272263710e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5038799326816178e-03,
"cpu_time": 1.3454682063441493e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5049579312028090e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 135,
"real_time": 5.1633274907039274e+06,
"cpu_time": 7.9411197629623432e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6246515478831973e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 135,
"real_time": 5.1977916034283461e+06,
"cpu_time": 7.9775319481482422e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6138792471916463e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 135,
"real_time": 5.2420667407137379e+06,
"cpu_time": 8.0376934222217472e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6002482255420203e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 135,
"real_time": 5.2318597867808957e+06,
"cpu_time": 8.0225363407407710e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6033701861038244e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 135,
"real_time": 5.2229542699125074e+06,
"cpu_time": 8.0157645333328126e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6061040488758714e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.2115999783078823e+06,
"cpu_time": 7.9989292014811831e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6096506511193120e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time_median",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.2229542699125074e+06,
"cpu_time": 8.0157645333328117e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6061040488758714e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1577316482743008e+04,
"cpu_time": 3.9189168989232377e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.7894862413918339e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.0590445571756316e-03,
"cpu_time": 4.8993018943055038e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0817458959709437e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 83,
"real_time": 8.3963883681649193e+06,
"cpu_time": 1.3894815180722628e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.9981467345663958e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 83,
"real_time": 8.3882264590945588e+06,
"cpu_time": 1.3897941662650231e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0000909705781794e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 83,
"real_time": 8.3842571173985321e+06,
"cpu_time": 1.3892157819276942e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0010378695549400e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 83,
"real_time": 8.3867458020707211e+06,
"cpu_time": 1.3891749939759107e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0004440811664565e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 83,
"real_time": 8.3852268373930315e+06,
"cpu_time": 1.3884807626506796e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0008064570398719e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.3881689168243529e+06,
"cpu_time": 1.3892294445783142e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0001052225811689e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time_median",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.3867458020707201e+06,
"cpu_time": 1.3892157819276944e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.0004440811664565e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.8359578458797387e+03,
"cpu_time": 4.8634550365761706e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1524174268727456e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.7652127583889511e-04,
"cpu_time": 3.5008292226720123e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.7617839994714474e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 49,
"real_time": 1.4495956977563245e+07,
"cpu_time": 2.5256759081631869e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3147441767339230e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 49,
"real_time": 1.4498311304012123e+07,
"cpu_time": 2.5366690122449636e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3143682941001873e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 49,
"real_time": 1.4465938835423820e+07,
"cpu_time": 2.5235227265305150e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3195474819672794e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 49,
"real_time": 1.4560329480742922e+07,
"cpu_time": 2.5339593979593903e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3045104881986456e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 49,
"real_time": 1.4462255682720214e+07,
"cpu_time": 2.5264583142856915e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3201382091516671e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4496558456092468e+07,
"cpu_time": 2.5292570718367495e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3146617300303402e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time_median",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4495956977563247e+07,
"cpu_time": 2.5264583142856911e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.3147441767339230e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9320539377737747e+04,
"cpu_time": 5.7137821262611003e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.2650420667829514e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.7124051199346913e-03,
"cpu_time": 2.2590752794107026e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7066771725218052e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 26,
"real_time": 2.6530709690772571e+07,
"cpu_time": 4.8406277153844714e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5294786600955715e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 26,
"real_time": 2.6494082278357103e+07,
"cpu_time": 4.8389187423074767e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5329756016807170e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 26,
"real_time": 2.6550679181057673e+07,
"cpu_time": 4.8444926500001028e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5275761701748924e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 26,
"real_time": 2.6658691394214448e+07,
"cpu_time": 4.7656928269230567e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5173352662975864e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 26,
"real_time": 2.6465848231544860e+07,
"cpu_time": 4.8301825923077174e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5356778068428731e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6540002155189335e+07,
"cpu_time": 4.8239829053845651e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5286087010183282e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time_median",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6530709690772571e+07,
"cpu_time": 4.8389187423074767e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.5294786600955715e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.3984666851249334e+04,
"cpu_time": 3.3003590386925801e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.0348304474237328e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.7876661960550444e-03,
"cpu_time": 6.8415645399752456e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7820953256194390e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 14,
"real_time": 4.9641674384474754e+07,
"cpu_time": 9.0888550357143626e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.7037308806404018e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 14,
"real_time": 4.9753000693661824e+07,
"cpu_time": 9.0975492642850712e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.6976810670456381e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 14,
"real_time": 4.9677434776510514e+07,
"cpu_time": 9.0872035142857447e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.7017845950343542e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 14,
"real_time": 4.9670429368104257e+07,
"cpu_time": 9.0821018071429595e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.7021656488072882e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 14,
"real_time": 4.9700405714767322e+07,
"cpu_time": 9.0955455142859265e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.7005358622277870e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9688588987503737e+07,
"cpu_time": 9.0902510271428138e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.7011796107510943e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time_median",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9677434776510507e+07,
"cpu_time": 9.0888550357143626e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.7017845950343542e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.1664346594588947e+04,
"cpu_time": 6.3036055699317876e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2639277421684642e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.3850935282278149e-04,
"cpu_time": 6.9344680923658650e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.3812558526567317e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 7,
"real_time": 9.5877393015793398e+07,
"cpu_time": 1.7413566442857179e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.7997784207146935e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 7,
"real_time": 9.5755475972379953e+07,
"cpu_time": 1.7377157457143050e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.8033431328504748e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 7,
"real_time": 9.5719883484499797e+07,
"cpu_time": 1.7374188171429849e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.8043855281485853e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 7,
"real_time": 9.6875709082399100e+07,
"cpu_time": 1.7461989528572175e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.7709263606182036e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 7,
"real_time": 9.5787452799933299e+07,
"cpu_time": 1.7393103642856595e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.8024072898218555e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.6003182871001109e+07,
"cpu_time": 1.7404001048571768e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.7961681464307628e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time_median",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.5787452799933299e+07,
"cpu_time": 1.7393103642856592e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.8024072898218555e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9124377624917607e+05,
"cpu_time": 3.5994097003428615e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4213677691643355e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.1169530171646218e-03,
"cpu_time": 2.0681507029892080e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0832700135672280e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.8634339049458504e+08,
"cpu_time": 3.2994862374999911e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8810837377975097e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.8781987950205803e+08,
"cpu_time": 3.3374029550000727e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8584349719706707e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.8586495146155357e+08,
"cpu_time": 3.3072264525000608e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8884999984036932e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.8780880421400070e+08,
"cpu_time": 3.3383646350000620e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8586035369686761e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.8630335479974747e+08,
"cpu_time": 3.3064548274998629e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8817028688349080e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8682807609438899e+08,
"cpu_time": 3.3177870215000099e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8736650227950916e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time_median",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8634339049458504e+08,
"cpu_time": 3.3072264525000608e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 2.8810837377975097e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1969604627545679e+05,
"cpu_time": 1.8594931822327909e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4129079994462484e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.9226864907114358e-03,
"cpu_time": 5.6046188926017690e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9167456479390663e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.5990819334983826e+08,
"cpu_time": 6.0264872150003159e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.9833769940221968e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.6190642416477203e+08,
"cpu_time": 6.0553839450000167e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.9669045706443086e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.6100058257579803e+08,
"cpu_time": 6.0373644099996686e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.9743492831470714e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.6076891422271729e+08,
"cpu_time": 6.0357428699995804e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.9762592664431605e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.6004149913787842e+08,
"cpu_time": 6.0358780249998748e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.9822723951852255e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6072512269020087e+08,
"cpu_time": 6.0381712929998922e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.9766325018883929e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time_median",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6076891422271729e+08,
"cpu_time": 6.0358780249998736e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 2.9762592664431605e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.0746265068035375e+05,
"cpu_time": 1.0542775299932188e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6573570082067857e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2384430689453851e-03,
"cpu_time": 1.7460212352959459e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2365397824499061e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 310,
"real_time": 2.2539294572667247e+06,
"cpu_time": 2.5766783064513691e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8172707166120012e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 310,
"real_time": 2.2537848476560847e+06,
"cpu_time": 2.5773158580642710e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8173873181638443e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 310,
"real_time": 2.2538296998508517e+06,
"cpu_time": 2.5789157516126782e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8173511513629691e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 310,
"real_time": 2.2597187296337178e+06,
"cpu_time": 2.5789198322579595e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8126149711844574e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 310,
"real_time": 2.2603380801757015e+06,
"cpu_time": 2.5797348419356211e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8121183003215201e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2563201629166161e+06,
"cpu_time": 2.5783129180643796e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8153484915289585e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time_median",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2539294572667247e+06,
"cpu_time": 2.5789157516126786e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8172707166120012e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3926250192754733e+03,
"cpu_time": 1.2668567787203197e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7280340189896183e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5036097602788877e-03,
"cpu_time": 4.9135105744704897e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5027605067123833e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 311,
"real_time": 2.2597358288045768e+06,
"cpu_time": 2.5797616495177587e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6252025106552616e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 311,
"real_time": 2.2543588513957630e+06,
"cpu_time": 2.5809644147911118e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6338491518011908e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 311,
"real_time": 2.2595829069853979e+06,
"cpu_time": 2.5817875723474291e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6254478535285448e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 311,
"real_time": 2.2549498818778819e+06,
"cpu_time": 2.5805892797427424e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6328967068562289e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 311,
"real_time": 2.2536729053681018e+06,
"cpu_time": 2.5797302733118655e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6349551793817068e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2564600748863439e+06,
"cpu_time": 2.5805666379421814e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6304702804445866e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time_median",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2549498818778815e+06,
"cpu_time": 2.5805892797427420e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6328967068562289e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9557901250926093e+03,
"cpu_time": 8.6558247018148870e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.7537565655358294e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3099235204688876e-03,
"cpu_time": 3.3542341339099429e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3094051729721598e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2698599509111210e+06,
"cpu_time": 2.5937835663431915e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2180664685605243e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2659562204129584e+06,
"cpu_time": 2.5970935016181529e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2305015659190910e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2637328113396093e+06,
"cpu_time": 2.5873329320386695e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2376032709904658e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2658765011596642e+06,
"cpu_time": 2.6023422038835343e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2307559532104917e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2637255649567614e+06,
"cpu_time": 2.5882222686082604e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2376264391893921e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2658302097560233e+06,
"cpu_time": 2.5937548944983617e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2309107395739928e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time_median",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2658765011596638e+06,
"cpu_time": 2.5937835663431911e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2307559532104917e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5042686157159856e+03,
"cpu_time": 6.2598033738874838e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.9852563811474611e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1052322477356487e-03,
"cpu_time": 2.4134136140485794e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1043223556121383e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 308,
"real_time": 2.2760446806281032e+06,
"cpu_time": 2.6086371720777736e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4396905420572525e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 308,
"real_time": 2.2759771544498377e+06,
"cpu_time": 2.6031034188312711e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4397332563700916e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 308,
"real_time": 2.2870047296119202e+06,
"cpu_time": 2.6140086948051797e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4327910902729254e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 308,
"real_time": 2.2756134797879434e+06,
"cpu_time": 2.6022708474022825e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4399633457547253e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 308,
"real_time": 2.2814608067153143e+06,
"cpu_time": 2.6147448571429639e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4362727557514803e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2792201702386239e+06,
"cpu_time": 2.6085529980518939e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4376901980412953e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time_median",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2760446806281027e+06,
"cpu_time": 2.6086371720777731e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4396905420572525e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9806856489046231e+03,
"cpu_time": 5.8582028344196569e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1366010111464606e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1852586748489365e-03,
"cpu_time": 2.2457672275758437e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1816946484157409e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 303,
"real_time": 2.3085359390210300e+06,
"cpu_time": 2.6448457194716623e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8388555227687530e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 303,
"real_time": 2.3144448833792121e+06,
"cpu_time": 2.6572511188118877e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8316077203063037e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 303,
"real_time": 2.3077396397777023e+06,
"cpu_time": 2.6438287590759117e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8398350866960403e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 303,
"real_time": 2.3155923342645760e+06,
"cpu_time": 2.6516069471947602e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8302045671097804e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 303,
"real_time": 2.3163453562080665e+06,
"cpu_time": 2.6524683201318947e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8292844944021903e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3125316305301175e+06,
"cpu_time": 2.6500001729372228e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8339574782566138e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time_median",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3144448833792121e+06,
"cpu_time": 2.6516069471947597e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8316077203063037e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.0774279076443017e+03,
"cpu_time": 5.6103571576357208e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9994900644653251e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7631879511674424e-03,
"cpu_time": 2.1171157703802259e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7641372895760236e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 296,
"real_time": 2.3809703282470740e+06,
"cpu_time": 2.7350888277024948e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5049825041918211e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 296,
"real_time": 2.3710621855964228e+06,
"cpu_time": 2.7260726689191288e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5279866043255977e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 296,
"real_time": 2.3715016432106495e+06,
"cpu_time": 2.7260868412159542e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5269622256111369e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 296,
"real_time": 2.3704010905144182e+06,
"cpu_time": 2.7248198277027006e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5295283369767226e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 296,
"real_time": 2.3699789205754832e+06,
"cpu_time": 2.7242333817565776e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5305133249106213e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3727828336288100e+06,
"cpu_time": 2.7272603094593715e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5239945992031805e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time_median",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3710621855964232e+06,
"cpu_time": 2.7260726689191284e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5279866043255977e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6144277904235942e+03,
"cpu_time": 4.4494791317864647e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0715860986173719e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9447324571910060e-03,
"cpu_time": 1.6314831101210472e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9398753553668299e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 278,
"real_time": 2.4982848097469737e+06,
"cpu_time": 2.8915120899283602e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0492958968379188e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 278,
"real_time": 2.4973478355853679e+06,
"cpu_time": 2.8942312517988645e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0496895797399186e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 278,
"real_time": 2.4973230801603133e+06,
"cpu_time": 2.8904248345325184e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0496999850863186e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 278,
"real_time": 2.5029207526190248e+06,
"cpu_time": 2.8922960791365448e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0473523771205933e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 278,
"real_time": 2.5057041114732195e+06,
"cpu_time": 2.8952160827337485e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0461889686004204e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5003161179169798e+06,
"cpu_time": 2.8927360676260078e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0484453614770339e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time_median",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4982848097469737e+06,
"cpu_time": 2.8922960791365444e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0492958968379188e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7983478112315920e+03,
"cpu_time": 1.9633873999191462e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5915003537542804e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5191470326544171e-03,
"cpu_time": 6.7873022426496261e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5179621296737855e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 271,
"real_time": 2.5867501418089075e+06,
"cpu_time": 3.0472185608857460e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0268211897472510e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 271,
"real_time": 2.5946887259842395e+06,
"cpu_time": 3.0538424169743448e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0206200256299436e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 271,
"real_time": 2.5884398814235777e+06,
"cpu_time": 3.0467057453874131e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0254980761293733e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 271,
"real_time": 2.5909798231828148e+06,
"cpu_time": 3.0485265756455716e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0235124770518416e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 271,
"real_time": 2.5872608579736464e+06,
"cpu_time": 3.0479483025831333e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0264211023956221e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5896238860746371e+06,
"cpu_time": 3.0488483202952417e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0245745741908064e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time_median",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5884398814235777e+06,
"cpu_time": 3.0479483025831329e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0254980761293733e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2686137609130424e+03,
"cpu_time": 2.8766862930992233e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5532483402520797e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2621963283894562e-03,
"cpu_time": 9.4353211143696812e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2611283243407205e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 254,
"real_time": 2.7484369480718425e+06,
"cpu_time": 3.3379927913386840e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8151721135011858e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 254,
"real_time": 2.7476782006702907e+06,
"cpu_time": 3.3416150905511105e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8162256400483942e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 254,
"real_time": 2.7477327453735191e+06,
"cpu_time": 3.3514589803149379e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8161498849025059e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 254,
"real_time": 2.7450979778939108e+06,
"cpu_time": 3.3404015629919628e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8198126567580169e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 254,
"real_time": 2.7455981476159077e+06,
"cpu_time": 3.3363370433069286e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8191167957718527e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7469088039250942e+06,
"cpu_time": 3.3415610937007247e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8172954181963915e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time_median",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7476782006702907e+06,
"cpu_time": 3.3404015629919628e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8162256400483942e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4665423853159941e+03,
"cpu_time": 5.9020985848628243e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0383204409513241e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.3388826859502312e-04,
"cpu_time": 1.7662698419577136e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.3396979212952725e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 227,
"real_time": 3.0794551766309314e+06,
"cpu_time": 3.9961192907490754e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8101397153453064e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 227,
"real_time": 3.0872818310273243e+06,
"cpu_time": 4.0142229691626616e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7928751399484360e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 227,
"real_time": 3.0885970851792111e+06,
"cpu_time": 4.0014680837004506e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.7899824488706851e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 227,
"real_time": 3.0796941572857718e+06,
"cpu_time": 4.0034443392072124e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8096112564901054e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 227,
"real_time": 3.0712782464806596e+06,
"cpu_time": 3.9811134449341265e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8282709402936733e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0812612993207802e+06,
"cpu_time": 3.9992736255507059e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8061759001896417e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time_median",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0796941572857718e+06,
"cpu_time": 4.0014680837004511e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8096112564901054e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.9899913004675373e+03,
"cpu_time": 1.2097885780792076e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5450262046968653e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2685486953048675e-03,
"cpu_time": 3.0250207696469328e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2700356666565374e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 194,
"real_time": 3.6101138780911253e+06,
"cpu_time": 5.0826293659795113e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1618204138806198e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 194,
"real_time": 3.6025072601575828e+06,
"cpu_time": 5.0762658969074208e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1642735731271033e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 194,
"real_time": 3.5979348959727692e+06,
"cpu_time": 5.0626972010310553e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1657531671000376e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 194,
"real_time": 3.5925707719816836e+06,
"cpu_time": 5.0568943659799490e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1674937715106993e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 194,
"real_time": 3.5909823029177245e+06,
"cpu_time": 5.0539988814431671e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1680102117440312e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5988218218241772e+06,
"cpu_time": 5.0664971422682200e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1654702274724982e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time_median",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5979348959727688e+06,
"cpu_time": 5.0626972010310553e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1657531671000376e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7848138821449102e+03,
"cpu_time": 1.2435198013726003e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5188998732621348e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1631562404495286e-03,
"cpu_time": 2.4543975185504375e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1612734618925078e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 144,
"real_time": 4.8496745390972747e+06,
"cpu_time": 7.5259406597222919e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7297259707579198e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 144,
"real_time": 4.8983302905172519e+06,
"cpu_time": 7.5845295347218346e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7125443778749723e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 144,
"real_time": 4.8988481123362565e+06,
"cpu_time": 7.5883428055555485e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7123633571891823e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 144,
"real_time": 4.8838624788913876e+06,
"cpu_time": 7.5735561736109955e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7176175693432245e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 144,
"real_time": 4.9532038230811143e+06,
"cpu_time": 7.6718353819439746e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6935721403004794e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.8967838487846572e+06,
"cpu_time": 7.5888409111109301e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7131646830931559e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time_median",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.8983302905172529e+06,
"cpu_time": 7.5845295347218364e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7125443778749723e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7336694500200472e+04,
"cpu_time": 5.2671109466045338e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3028805393465664e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.6247381246911982e-03,
"cpu_time": 6.9406000314130734e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.6051097259032183e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 88,
"real_time": 7.8122451933185486e+06,
"cpu_time": 1.3323577829545094e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1475536910117435e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 88,
"real_time": 7.8531108500266615e+06,
"cpu_time": 1.3388211204546576e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1363783499812741e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 88,
"real_time": 7.8488417784683406e+06,
"cpu_time": 1.3386185488636732e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1375403497143734e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 88,
"real_time": 7.8318580688739363e+06,
"cpu_time": 1.3347926465908958e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1421756947661624e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 88,
"real_time": 7.8284707745875828e+06,
"cpu_time": 1.3346577420454703e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1431025909250908e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.8349053330550147e+06,
"cpu_time": 1.3358495681818414e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1413501352797289e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time_median",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.8318580688739363e+06,
"cpu_time": 1.3347926465908958e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1421756947661624e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6506337066691474e+04,
"cpu_time": 2.7940773874289280e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5130330179160004e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1067691778038707e-03,
"cpu_time": 2.0916108025784731e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1075642621735252e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51,
"real_time": 1.3725475097695986e+07,
"cpu_time": 2.5012464254901338e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4446827349264274e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51,
"real_time": 1.3694337934401689e+07,
"cpu_time": 2.5028846745098077e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4502412720302134e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51,
"real_time": 1.3714952704807123e+07,
"cpu_time": 2.5021164254903670e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4465583456397262e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51,
"real_time": 1.3715244537475063e+07,
"cpu_time": 2.5066578058822773e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4465062878257127e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51,
"real_time": 1.3740430549517566e+07,
"cpu_time": 2.5062390823530436e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4420218769038582e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3718088164779488e+07,
"cpu_time": 2.5038288827451263e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4460021034651875e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time_median",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3715244537475064e+07,
"cpu_time": 2.5028846745098077e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4465062878257127e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6850368705283232e+04,
"cpu_time": 2.4650047047888635e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.0048749630691791e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2283321482468466e-03,
"cpu_time": 9.8449407696196201e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2284842105459561e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 27,
"real_time": 2.5511406638004161e+07,
"cpu_time": 4.8405947111110367e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6305434644292955e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 27,
"real_time": 2.5325498233238857e+07,
"cpu_time": 4.8206645592594445e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6498536527080798e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 27,
"real_time": 2.5446310294447120e+07,
"cpu_time": 4.8338933629633240e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6372728786005750e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 27,
"real_time": 2.5477717803032309e+07,
"cpu_time": 4.8418816370367825e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6340217957831697e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 27,
"real_time": 2.5425149196827855e+07,
"cpu_time": 4.8284418111111164e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6394678544648533e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5437216433110062e+07,
"cpu_time": 4.8330952162963405e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6382319291971946e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time_median",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5446310294447120e+07,
"cpu_time": 4.8338933629633240e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6372728786005750e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.0451792304878967e+04,
"cpu_time": 8.8070435472368932e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.3203391405589944e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.7696345034504723e-03,
"cpu_time": 1.8222367143815217e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7747140270516510e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 4.6138092378775276e+07,
"cpu_time": 8.8417745333337441e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9090437224436188e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 4.6338262408971786e+07,
"cpu_time": 8.8564536533332720e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.8964773606619620e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 4.6274092296759285e+07,
"cpu_time": 8.8422008599998966e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9004940202662749e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.6637549748023354e+07,
"cpu_time": 8.9007679399999991e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.8778897846297894e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 4.6032821138699852e+07,
"cpu_time": 8.8151940933335036e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9156963375239019e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6284163594245911e+07,
"cpu_time": 8.8512782160000831e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.8999202451051097e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time_median",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6274092296759285e+07,
"cpu_time": 8.8422008599998966e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9004940202662749e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3044506743356731e+05,
"cpu_time": 3.1427695660195395e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4401794946486358e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.9789182635724769e-03,
"cpu_time": 3.5506392289629848e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9662727693272658e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.7771806865930557e+07,
"cpu_time": 1.6733663362499839e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0583334852617202e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.8093709200620651e+07,
"cpu_time": 1.6769270125000447e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0471580597052302e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.7507283315062523e+07,
"cpu_time": 1.6546858362499961e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0675784441110005e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.7659886106848717e+07,
"cpu_time": 1.6713385725000763e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0622382474100385e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.7684210389852524e+07,
"cpu_time": 1.6728462749999550e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0613887586660113e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.7743379175662994e+07,
"cpu_time": 1.6698328065000111e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0593393990308003e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time_median",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.7684210389852524e+07,
"cpu_time": 1.6728462749999553e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0613887586660113e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1780298041485302e+05,
"cpu_time": 8.7119547557947820e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5809292130819950e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4822725368122598e-03,
"cpu_time": 5.2172617054129745e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4779627966363053e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6998168081045151e+08,
"cpu_time": 3.1664831074999708e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1584045377141013e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6995543614029884e+08,
"cpu_time": 3.1375808149999785e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1588922613620377e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.7029255628585815e+08,
"cpu_time": 3.1664943249998599e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1526387512722077e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.7059879377484322e+08,
"cpu_time": 3.1513186224998432e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1469795308668113e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.7028475552797318e+08,
"cpu_time": 3.1681567724999124e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1527831738984213e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7022264450788498e+08,
"cpu_time": 3.1580067284999138e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1539396510227160e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time_median",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7028475552797318e+08,
"cpu_time": 3.1664831074999708e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1527831738984213e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6443218493749539e+05,
"cpu_time": 1.3312216125254431e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.8973619026083825e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5534489297940998e-03,
"cpu_time": 4.2153856117899636e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5527760339422898e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.2639713585376740e+08,
"cpu_time": 5.6838573800001764e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2896790628734512e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.2704120874404907e+08,
"cpu_time": 5.6875384349996233e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2832003897109437e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.2643881440162659e+08,
"cpu_time": 5.6811588199997234e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2892590483402081e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.2616929709911346e+08,
"cpu_time": 5.6786998600000513e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2919769995203466e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.2659913599491119e+08,
"cpu_time": 5.6668310050002897e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2876444107210689e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2652911841869360e+08,
"cpu_time": 5.6796170999999738e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2883519822332039e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time_median",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2643881440162659e+08,
"cpu_time": 5.6811588199997234e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2892590483402081e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2487865318262315e+05,
"cpu_time": 7.8649535565121868e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2697180776329939e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.9494542709065810e-04,
"cpu_time": 1.3847682718809025e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.9433336069225929e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 313,
"real_time": 2.2467311505918591e+06,
"cpu_time": 2.5798558178914287e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8230930740961088e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 313,
"real_time": 2.2435019673488010e+06,
"cpu_time": 2.5779414376993719e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8257171420448271e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 313,
"real_time": 2.2514805193252554e+06,
"cpu_time": 2.5920550543130189e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8192473640533774e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 313,
"real_time": 2.2430798134055380e+06,
"cpu_time": 2.5770478785942397e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8260607471569548e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 313,
"real_time": 2.2431983636281551e+06,
"cpu_time": 2.5887573322684043e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8259642421346628e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2455983628599215e+06,
"cpu_time": 2.5831315041532926e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8240165138971861e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time_median",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2435019673488010e+06,
"cpu_time": 2.5798558178914287e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8257171420448271e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6187337058094154e+03,
"cpu_time": 6.8183044018375031e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9352258134889512e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6114785999401572e-03,
"cpu_time": 2.6395498606535048e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6092101091878604e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 312,
"real_time": 2.2543973598378496e+06,
"cpu_time": 2.5901749102563197e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6337870802817210e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 312,
"real_time": 2.2435978552004178e+06,
"cpu_time": 2.5915998589745653e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6512782275182814e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 312,
"real_time": 2.2436537166448454e+06,
"cpu_time": 2.5793571602566070e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6511873196949027e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 312,
"real_time": 2.2560974100950914e+06,
"cpu_time": 2.5916415128203854e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6310488914814712e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 312,
"real_time": 2.2434188524643197e+06,
"cpu_time": 2.5793039198716977e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6515695635709600e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2482330388485049e+06,
"cpu_time": 2.5864154724359149e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6437742165094675e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time_median",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2436537166448450e+06,
"cpu_time": 2.5901749102563197e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6511873196949027e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.4319261928004125e+03,
"cpu_time": 6.4945493549201074e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0412834664114642e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.8608805589364983e-03,
"cpu_time": 2.5110232381974841e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8577057867459079e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 311,
"real_time": 2.2512832851152136e+06,
"cpu_time": 2.6009064758843714e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2776269909370905e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 311,
"real_time": 2.2519268664468522e+06,
"cpu_time": 2.5923213729905635e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2755471077313861e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 311,
"real_time": 2.2585872452933691e+06,
"cpu_time": 2.6024865787781789e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2540921472669858e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 311,
"real_time": 2.2514684798070183e+06,
"cpu_time": 2.5895642379422076e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2770283692376325e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 311,
"real_time": 2.2576395759113445e+06,
"cpu_time": 2.5958957749194168e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2571371333204275e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2541810905147595e+06,
"cpu_time": 2.5962348881029477e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2682863496987047e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time_median",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2519268664468518e+06,
"cpu_time": 2.5958957749194168e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2755471077313861e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6129067350447754e+03,
"cpu_time": 5.4962610143215079e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1642266747482265e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6027579817111056e-03,
"cpu_time": 2.1170122316388680e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6017897737291096e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 307,
"real_time": 2.2624560741022085e+06,
"cpu_time": 2.6045610716609862e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4483375113924831e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 307,
"real_time": 2.2684272260371754e+06,
"cpu_time": 2.6167442214984256e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4445250711103478e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 307,
"real_time": 2.2628282353051421e+06,
"cpu_time": 2.6047750260587242e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4480993072627645e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 307,
"real_time": 2.2624644681398761e+06,
"cpu_time": 2.6107098078178982e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4483321378717950e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 307,
"real_time": 2.2681838429323626e+06,
"cpu_time": 2.6105062052118299e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4446800730948133e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2648719693033532e+06,
"cpu_time": 2.6094592664495734e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4467948201464407e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time_median",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2628282353051421e+06,
"cpu_time": 2.6105062052118303e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4480993072627645e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1391805260308984e+03,
"cpu_time": 5.0414512983292934e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0042981617248843e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3860300134300623e-03,
"cpu_time": 1.9319908009863994e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3853368382408327e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 304,
"real_time": 2.3107426187427910e+06,
"cpu_time": 2.6615917368418784e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8361445133883525e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 304,
"real_time": 2.3204474127851427e+06,
"cpu_time": 2.6714592697371729e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8242829222895291e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 304,
"real_time": 2.3027246467168690e+06,
"cpu_time": 2.6604286710524224e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8460198267056622e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 304,
"real_time": 2.3111162843538057e+06,
"cpu_time": 2.6624383914473900e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8356859602295626e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 304,
"real_time": 2.3032431000549542e+06,
"cpu_time": 2.6609533782896139e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8453791959014811e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3096548125307122e+06,
"cpu_time": 2.6633742894736952e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8375024837029178e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time_median",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3107426187427910e+06,
"cpu_time": 2.6615917368418779e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8361445133883525e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.2273213844089769e+03,
"cpu_time": 4.5814240064237547e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.8669099993141630e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.1291781547606789e-03,
"cpu_time": 1.7201577805007204e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1248994671338286e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 296,
"real_time": 2.3583934148395988e+06,
"cpu_time": 2.7339229560807878e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5576817326262161e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 296,
"real_time": 2.3671994119492434e+06,
"cpu_time": 2.7421733513513976e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5370071206662834e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 296,
"real_time": 2.3608226250429209e+06,
"cpu_time": 2.7299706013515964e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5519630576912589e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 296,
"real_time": 2.3641507581782504e+06,
"cpu_time": 2.7388758006755882e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5441472819187082e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 296,
"real_time": 2.3570469261235180e+06,
"cpu_time": 2.7319432635136009e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5608566188185997e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3615226272267061e+06,
"cpu_time": 2.7353771945945946e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5503311623442143e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time_median",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3608226250429214e+06,
"cpu_time": 2.7339229560807878e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5519630576912589e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.1667382527417221e+03,
"cpu_time": 5.0389962788816538e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.7883816793175778e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7644286803362120e-03,
"cpu_time": 1.8421577429391688e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7635671445563616e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 280,
"real_time": 2.4897267285268754e+06,
"cpu_time": 2.8928891321429871e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0529027021174556e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 280,
"real_time": 2.4959656393288500e+06,
"cpu_time": 2.8955053500003000e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0502708685945249e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 280,
"real_time": 2.5009125196707570e+06,
"cpu_time": 2.9005259714283836e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0481934011610731e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 280,
"real_time": 2.4902827605339033e+06,
"cpu_time": 2.8936781428569704e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0526676092950895e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 280,
"real_time": 2.4952553345688754e+06,
"cpu_time": 2.8982864892855431e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0505698409629597e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4944285965258526e+06,
"cpu_time": 2.8961770171428369e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0509208844262205e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time_median",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4952553345688749e+06,
"cpu_time": 2.8955053500003000e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0505698409629597e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5930048570505869e+03,
"cpu_time": 3.1964422926262314e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9341384507061535e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8413054049522821e-03,
"cpu_time": 1.1036764236806271e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8404225088381892e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 270,
"real_time": 2.5784969855858772e+06,
"cpu_time": 3.0504236925922767e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0333085628210384e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 270,
"real_time": 2.5843920686316709e+06,
"cpu_time": 3.0566709629628924e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0286705193209669e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 270,
"real_time": 2.5766510326691247e+06,
"cpu_time": 3.0448905814814176e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0347652567328677e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 270,
"real_time": 2.5760762091657077e+06,
"cpu_time": 3.0480800074070869e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0352192925604355e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 270,
"real_time": 2.5813361060702140e+06,
"cpu_time": 3.0495282370368303e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0310721984909123e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5793904804245187e+06,
"cpu_time": 3.0499186962961005e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0326071659852445e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time_median",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5784969855858767e+06,
"cpu_time": 3.0495282370368303e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0333085628210384e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4672988316820056e+03,
"cpu_time": 4.3203964008351268e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7306515065090236e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3442318477934964e-03,
"cpu_time": 1.4165611713131653e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3434231425556464e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 254,
"real_time": 2.7343525292762504e+06,
"cpu_time": 3.3397055708662705e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8348237426340383e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 254,
"real_time": 2.7386404594083824e+06,
"cpu_time": 3.3459995669291378e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8288195020186031e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 254,
"real_time": 2.7329270429102574e+06,
"cpu_time": 3.3381841417323141e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8368239749400175e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 254,
"real_time": 2.7362996112833931e+06,
"cpu_time": 3.3402710039372034e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8320949784742016e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 254,
"real_time": 2.7387027993548927e+06,
"cpu_time": 3.3445048031494948e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8287323482014710e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7361844884466352e+06,
"cpu_time": 3.3417330173228839e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8322589092536664e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time_median",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7362996112833926e+06,
"cpu_time": 3.3402710039372034e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8320949784742016e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5668055189123779e+03,
"cpu_time": 3.3439790086191119e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5955258052195929e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.3809665603710227e-04,
"cpu_time": 1.0006721037511331e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.3822622384347795e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 228,
"real_time": 3.0801579041667935e+06,
"cpu_time": 4.0088476842106301e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8085860051622772e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 228,
"real_time": 3.0833544554760712e+06,
"cpu_time": 4.0094556140353801e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8015274607025313e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 228,
"real_time": 3.0810295301898005e+06,
"cpu_time": 4.0065427500003516e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8066598500625503e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 228,
"real_time": 3.0687950651586186e+06,
"cpu_time": 4.0057992543862388e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8337961821233678e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 228,
"real_time": 3.0677016628415962e+06,
"cpu_time": 3.9933231096490705e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8362319106917942e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0762077235665764e+06,
"cpu_time": 4.0047936824563341e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8173602817485046e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time_median",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0801579041667935e+06,
"cpu_time": 4.0065427500003511e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8085860051622772e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.3693638904654481e+03,
"cpu_time": 6.5919077091482741e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6343520048019032e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3956002171145185e-03,
"cpu_time": 1.6460043217769807e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3973384671738770e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 195,
"real_time": 3.5923625521648386e+06,
"cpu_time": 5.0736965538461823e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1675614415567319e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 195,
"real_time": 3.5915979040929903e+06,
"cpu_time": 5.0684022307689535e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1678100143727572e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 195,
"real_time": 3.5927030687721875e+06,
"cpu_time": 5.0710353846153133e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1674507800148957e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 195,
"real_time": 3.5899756750903833e+06,
"cpu_time": 5.0678629435896464e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1683377213675416e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 195,
"real_time": 3.5855482141367900e+06,
"cpu_time": 5.0643699025636707e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1697803932640092e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5904374828514382e+06,
"cpu_time": 5.0690734030767540e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1681880701151872e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time_median",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5915979040929908e+06,
"cpu_time": 5.0684022307689535e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1678100143727572e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9284622175851514e+03,
"cpu_time": 3.5093267196946304e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.5355580501615116e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.1562824351405711e-04,
"cpu_time": 6.9230142091937139e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.1626908321545124e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 142,
"real_time": 4.9241766805799911e+06,
"cpu_time": 7.6808203521124255e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7035554457424450e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 142,
"real_time": 4.9255400909189610e+06,
"cpu_time": 7.6719397957749031e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7030838943866830e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 142,
"real_time": 4.9171062402794482e+06,
"cpu_time": 7.6714108521128492e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7060050342787104e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 142,
"real_time": 4.9532190929363733e+06,
"cpu_time": 7.7051032816899344e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6935669193318594e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 142,
"real_time": 4.9255288756964076e+06,
"cpu_time": 7.6838829154928112e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7030877722372417e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9291141960822362e+06,
"cpu_time": 7.6826314394365847e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7018598131953881e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time_median",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9255288756964076e+06,
"cpu_time": 7.6808203521124255e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7030877722372417e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3921609678953591e+04,
"cpu_time": 1.3693454166081146e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.7915648374033300e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.8243633896773545e-03,
"cpu_time": 1.7823911343435958e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8154873863592534e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 82,
"real_time": 7.7598416360049713e+06,
"cpu_time": 1.3273240365853181e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1620564938020406e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 82,
"real_time": 7.7920330109120142e+06,
"cpu_time": 1.3321902939023359e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1531243484858284e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 82,
"real_time": 7.7439938535595816e+06,
"cpu_time": 1.3247519853658702e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1664810583867178e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 82,
"real_time": 7.7931686565734260e+06,
"cpu_time": 1.3331182317072921e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1528105882642045e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 82,
"real_time": 7.7372620836263746e+06,
"cpu_time": 1.3235539548780130e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1683659954474092e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7652598481352730e+06,
"cpu_time": 1.3281877004877660e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1605676968772402e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time_median",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7598416360049713e+06,
"cpu_time": 1.3273240365853181e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1620564938020406e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6273457133225493e+04,
"cpu_time": 4.3113960690910448e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.3070854403106580e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.3834614226766302e-03,
"cpu_time": 3.2460743820378096e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3820210544070880e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 53,
"real_time": 1.3679108477004293e+07,
"cpu_time": 2.4964502433961589e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4529692162619925e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 53,
"real_time": 1.3750236393567527e+07,
"cpu_time": 2.5022043283019111e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4402803733394022e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 53,
"real_time": 1.3700772024128797e+07,
"cpu_time": 2.5005635396226197e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4490906016760507e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 53,
"real_time": 1.3731368307797413e+07,
"cpu_time": 2.4998768150942609e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4436335292926326e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 53,
"real_time": 1.3718975936326215e+07,
"cpu_time": 2.4960782037735630e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4458408671125269e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3716092227764850e+07,
"cpu_time": 2.4990346260377031e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4463629175365214e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time_median",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3718975936326217e+07,
"cpu_time": 2.4998768150942612e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4458408671125269e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7431755842976687e+04,
"cpu_time": 2.6698940911671270e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.8939473931295993e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9999687511175999e-03,
"cpu_time": 1.0683701871711665e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0004993364017253e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 28,
"real_time": 2.5307103858462401e+07,
"cpu_time": 4.8164615428569436e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6517796890282874e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 28,
"real_time": 2.5342475556369338e+07,
"cpu_time": 4.8164641178573214e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6480784740515804e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 28,
"real_time": 2.5283840884055410e+07,
"cpu_time": 4.8163330892854057e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6542195194053941e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 28,
"real_time": 2.5401933052177940e+07,
"cpu_time": 4.8248415785715386e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6418802010914736e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 28,
"real_time": 2.5421201384493284e+07,
"cpu_time": 4.8304818999996863e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6398777534147477e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5351310947111677e+07,
"cpu_time": 4.8209164457141794e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6471671273982968e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time_median",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5342475556369338e+07,
"cpu_time": 4.8164641178573221e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6480784740515804e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.9227972664591718e+04,
"cpu_time": 6.4726563828928840e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.1832247528550988e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3362883595311537e-03,
"cpu_time": 1.3426194906669892e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3357893382924141e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 4.5261677106221519e+07,
"cpu_time": 8.6318898599999249e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9653723984865527e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 4.5544216285149254e+07,
"cpu_time": 8.7257309400001764e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9469763440361314e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 4.5757796367009483e+07,
"cpu_time": 8.7694692799997628e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9332209733939128e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.5727897683779396e+07,
"cpu_time": 8.7646090533333629e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9351388276835155e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 4.5735599348942436e+07,
"cpu_time": 8.7725882000002772e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9346445637670116e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5605437358220421e+07,
"cpu_time": 8.7328574666667014e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9430706214734249e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time_median",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5727897683779396e+07,
"cpu_time": 8.7646090533333629e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9351388276835155e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1039906924963338e+05,
"cpu_time": 5.9523869751568360e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3634068497384043e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.6134645655735336e-03,
"cpu_time": 6.8160816753016808e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.6325998424591851e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.7242315523326397e+07,
"cpu_time": 1.6735660612499714e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0768951327091627e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.6270649917423725e+07,
"cpu_time": 1.6512092562500414e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1115501767627835e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.6642671376466751e+07,
"cpu_time": 1.6571775962499657e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0981899765490203e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.6534993723034859e+07,
"cpu_time": 1.6542719225000724e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1020451316973381e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.7502876296639442e+07,
"cpu_time": 1.6743091924999475e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0677329404577446e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.6838701367378250e+07,
"cpu_time": 1.6621068057499999e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0912826716352100e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time_median",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.6642671376466751e+07,
"cpu_time": 1.6571775962499657e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0981899765490203e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.1414522848530125e+05,
"cpu_time": 1.1007405075032634e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8275012221132986e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.9206922764789829e-03,
"cpu_time": 6.6225618215104490e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.9117894292940766e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6837120056152344e+08,
"cpu_time": 3.1233410375000405e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1886148593673859e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6812176257371902e+08,
"cpu_time": 3.1334652250001228e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1933457262238116e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6830627620220184e+08,
"cpu_time": 3.1237660625001240e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1898448715899787e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.6851808503270149e+08,
"cpu_time": 3.1424648724998862e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1858355849214549e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6852339729666710e+08,
"cpu_time": 3.1310815025000238e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1857351596994996e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6836814433336258e+08,
"cpu_time": 3.1308237400000393e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1886752403604264e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time_median",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6837120056152344e+08,
"cpu_time": 3.1310815025000238e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1886148593673859e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6667833813190699e+05,
"cpu_time": 7.8797445832739270e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1580388920214395e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.8996362282101368e-04,
"cpu_time": 2.5168279142005700e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.9039213904532851e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.1837236881256104e+08,
"cpu_time": 5.6323866750000203e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3725974022329688e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.2410241663455963e+08,
"cpu_time": 5.6631119849998868e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3129707428584008e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.2256808876991272e+08,
"cpu_time": 5.6769834950000584e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3287292245634942e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.1846623122692108e+08,
"cpu_time": 5.6185022400001121e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3716033874715972e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.2743707299232483e+08,
"cpu_time": 5.7101642550003362e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.2792310723629289e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2218923568725586e+08,
"cpu_time": 5.6602297300000834e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3330263658978782e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time_median",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2256808876991272e+08,
"cpu_time": 5.6631119849998868e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3287292245634942e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8656442647588127e+06,
"cpu_time": 3.6396675521337381e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9902006703254409e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1998055293539150e-02,
"cpu_time": 6.4302470495904845e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1971704488003736e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 312,
"real_time": 2.2417214021492652e+06,
"cpu_time": 2.5715869487178894e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8271672813905121e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 312,
"real_time": 2.2474860590404999e+06,
"cpu_time": 2.5833100544871697e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8224807150744556e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 312,
"real_time": 2.2410865483554797e+06,
"cpu_time": 2.5711752756409510e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8276848803566578e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 312,
"real_time": 2.2409455111930864e+06,
"cpu_time": 2.5772109262818824e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8277999083606799e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 312,
"real_time": 2.2414224199914876e+06,
"cpu_time": 2.5770434647435024e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8274110062732201e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2425323881459637e+06,
"cpu_time": 2.5760653339742785e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8265087582911053e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time_median",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2414224199914872e+06,
"cpu_time": 2.5770434647435024e+06,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.8274110062732201e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7855526418453437e+03,
"cpu_time": 4.9679900828802001e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2651251544521842e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2421460026931105e-03,
"cpu_time": 1.9285186665726872e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2401392241729251e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 312,
"real_time": 2.2488173398857890e+06,
"cpu_time": 2.5859493621796812e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6428036438104166e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 312,
"real_time": 2.2416342249832666e+06,
"cpu_time": 2.5737435000001467e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6544766798700853e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 312,
"real_time": 2.2470891178669170e+06,
"cpu_time": 2.5783613205127208e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6456053010378061e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 312,
"real_time": 2.2482009483680418e+06,
"cpu_time": 2.5803277660255381e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6438023949534111e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 312,
"real_time": 2.2483804204966873e+06,
"cpu_time": 2.5800882147436622e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6435115362685439e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2468244103201400e+06,
"cpu_time": 2.5796940326923500e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6460399111880530e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time_median",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2482009483680413e+06,
"cpu_time": 2.5800882147436617e+06,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.6438023949534111e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9705170776628875e+03,
"cpu_time": 4.3838084325220425e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.8280569837442108e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3220957828385138e-03,
"cpu_time": 1.6993520847690578e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3241920278845769e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 311,
"real_time": 2.2497546231715530e+06,
"cpu_time": 2.5840314598070695e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2825719886300033e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 311,
"real_time": 2.2573195281064203e+06,
"cpu_time": 2.5922235948554100e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2581660664336318e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 311,
"real_time": 2.2562184704952780e+06,
"cpu_time": 2.5901607652735873e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2617081254562354e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 311,
"real_time": 2.2508376203118032e+06,
"cpu_time": 2.5911296527330931e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2790679577011708e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 311,
"real_time": 2.2572808355464335e+06,
"cpu_time": 2.5912145755627449e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2582904802954337e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2542822155262977e+06,
"cpu_time": 2.5897520096463813e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2679609237032952e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time_median",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2562184704952780e+06,
"cpu_time": 2.5911296527330931e+06,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 7.2617081254562354e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6854579688250242e+03,
"cpu_time": 3.2801488002415549e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1889108598280980e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6348698239473072e-03,
"cpu_time": 1.2665879929906665e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6358245074635099e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 309,
"real_time": 2.2733881519534732e+06,
"cpu_time": 2.6104258122977274e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4413728677103894e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 309,
"real_time": 2.2653881136424430e+06,
"cpu_time": 2.6102105210357024e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4464629615855718e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 309,
"real_time": 2.2659550848926348e+06,
"cpu_time": 2.6102155728155612e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4461010378567414e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 309,
"real_time": 2.2714303393507660e+06,
"cpu_time": 2.6097368543690392e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4426152293697877e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 309,
"real_time": 2.2657676614989741e+06,
"cpu_time": 2.6044042006473802e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4462206587555198e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2683858702676585e+06,
"cpu_time": 2.6089985922330823e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4445545510556022e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time_median",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2659550848926348e+06,
"cpu_time": 2.6102105210357024e+06,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.4461010378567414e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7430566900414187e+03,
"cpu_time": 2.5807089774333776e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3818923440558508e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6500969870702630e-03,
"cpu_time": 9.8915690683623928e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6488767020361350e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 305,
"real_time": 2.3038666848032200e+06,
"cpu_time": 2.6510516459017606e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8446090406310823e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 305,
"real_time": 2.2950713705943255e+06,
"cpu_time": 2.6493751508198450e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8555103270286959e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 305,
"real_time": 2.2955576553330068e+06,
"cpu_time": 2.6486990918034487e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8549054234271877e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 305,
"real_time": 2.2952685964706005e+06,
"cpu_time": 2.6426742098360816e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8552649611803044e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 305,
"real_time": 2.3040660153158377e+06,
"cpu_time": 2.6573269278686461e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8443629463896431e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2987660645033987e+06,
"cpu_time": 2.6498254052459570e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8509305397313830e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time_median",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2955576553330072e+06,
"cpu_time": 2.6493751508198450e+06,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.8549054234271877e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.7508615318786742e+03,
"cpu_time": 5.2532707576844141e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.8876140020809791e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0667007422980211e-03,
"cpu_time": 1.9824969400943629e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0651551905700640e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 295,
"real_time": 2.3816872561760880e+06,
"cpu_time": 2.7483247016951251e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5033254118528701e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 295,
"real_time": 2.3807082735633445e+06,
"cpu_time": 2.7478425796609093e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5055884610262185e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 295,
"real_time": 2.3899053207645980e+06,
"cpu_time": 2.7565973355934657e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4844013635680914e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 295,
"real_time": 2.3737257291262937e+06,
"cpu_time": 2.7403847016947079e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5217836834183939e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 295,
"real_time": 2.3871533477963028e+06,
"cpu_time": 2.7527360915254867e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.4907239252559513e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3826359854853256e+06,
"cpu_time": 2.7491770820339392e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5011645690243058e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time_median",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3816872561760875e+06,
"cpu_time": 2.7483247016951251e+06,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 5.5033254118528701e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.2701400818531611e+03,
"cpu_time": 6.0733045432227427e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4486200675340998e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.6315979948468627e-03,
"cpu_time": 2.2091354474443295e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6332970943841972e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 282,
"real_time": 2.4935254490280403e+06,
"cpu_time": 2.8903059539007340e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0512986747425497e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 282,
"real_time": 2.4827192099897047e+06,
"cpu_time": 2.8834245390071501e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0558745384706113e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 282,
"real_time": 2.4830562373002372e+06,
"cpu_time": 2.8824103723404380e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0557312237318572e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 282,
"real_time": 2.4942142842667745e+06,
"cpu_time": 2.8908952907799087e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0510083341819310e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 282,
"real_time": 2.4884950851770579e+06,
"cpu_time": 2.8848890602838644e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0534238205310673e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4884020531523628e+06,
"cpu_time": 2.8863850432624193e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0534673183316034e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time_median",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4884950851770579e+06,
"cpu_time": 2.8848890602838648e+06,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 1.0534238205310673e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4980070098135884e+03,
"cpu_time": 3.9533666776177392e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3276321971587351e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2094528506149524e-03,
"cpu_time": 1.3696601868298671e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2094963523358762e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 271,
"real_time": 2.5797819227282633e+06,
"cpu_time": 3.0497255793357319e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0322958129946744e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 271,
"real_time": 2.5816824754555728e+06,
"cpu_time": 3.0492316605170509e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0307997012974352e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 271,
"real_time": 2.5810070707019405e+06,
"cpu_time": 3.0582209520294559e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0313311263320664e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 271,
"real_time": 2.5813565761318286e+06,
"cpu_time": 3.0520235719564394e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0310560921639401e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 271,
"real_time": 2.5778324076926466e+06,
"cpu_time": 3.0472416273062085e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0338327597847104e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5803320905420510e+06,
"cpu_time": 3.0512886782289771e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0318630985145655e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time_median",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5810070707019409e+06,
"cpu_time": 3.0497255793357315e+06,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 2.0313311263320664e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5716080394562437e+03,
"cpu_time": 4.2323075862767109e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2381311146239722e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.0907200480775944e-04,
"cpu_time": 1.3870557762935818e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0935754752824295e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 256,
"real_time": 2.7440267513156869e+06,
"cpu_time": 3.3439942148438818e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8213038538973284e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 256,
"real_time": 2.7412499021011172e+06,
"cpu_time": 3.3463739023442683e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8251747832121617e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 256,
"real_time": 2.7387167519918876e+06,
"cpu_time": 3.3400703710935176e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8287128423827088e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 256,
"real_time": 2.7424661320765154e+06,
"cpu_time": 3.3503936757819373e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8234783931718016e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 256,
"real_time": 2.7429411275079474e+06,
"cpu_time": 3.3437685859372122e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8228162809774411e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7418801329986313e+06,
"cpu_time": 3.3449201500001634e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8242972307282877e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time_median",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7424661320765154e+06,
"cpu_time": 3.3439942148438818e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 3.8234783931718016e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0298549730642633e+03,
"cpu_time": 3.8005490231820381e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8324784482851764e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.4031499358228031e-04,
"cpu_time": 1.1362151718873924e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.4065332200807198e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 229,
"real_time": 3.0653476501575075e+06,
"cpu_time": 3.9903235109174633e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8414817480563474e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 229,
"real_time": 3.0620756374029485e+06,
"cpu_time": 3.9918360960696968e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8487922844997609e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 229,
"real_time": 3.0609940607751431e+06,
"cpu_time": 3.9927178777291900e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8512122479222751e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 229,
"real_time": 3.0706520995540000e+06,
"cpu_time": 4.0031970917034294e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8296633158298945e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 229,
"real_time": 3.0651303490127670e+06,
"cpu_time": 3.9945388427945166e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8419667720671701e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0648399593804730e+06,
"cpu_time": 3.9945226838428592e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8426232736750901e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time_median",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0651303490127665e+06,
"cpu_time": 3.9927178777291900e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 6.8419667720671701e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7601682653784469e+03,
"cpu_time": 5.0831521977589709e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.3893050310499500e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2268726312673526e-03,
"cpu_time": 1.2725305624923413e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2260363745765820e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 195,
"real_time": 3.5799258830360114e+06,
"cpu_time": 5.0600514461539444e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1716175521608720e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 195,
"real_time": 3.5846488013003883e+06,
"cpu_time": 5.0655058205125108e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1700738991441643e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 195,
"real_time": 3.5839538280971539e+06,
"cpu_time": 5.0611389743596353e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1703007910196495e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 195,
"real_time": 3.6009614272281909e+06,
"cpu_time": 5.0844785076932544e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1647733764336736e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 195,
"real_time": 3.5862553542336593e+06,
"cpu_time": 5.0650287743594209e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1695497352268920e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5871490587790809e+06,
"cpu_time": 5.0672407046157531e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1692630707970505e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time_median",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5846488013003878e+06,
"cpu_time": 5.0650287743594209e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 1.1700738991441643e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.0655948999868633e+03,
"cpu_time": 9.9242236800029532e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6228524706662400e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2484694022534050e-03,
"cpu_time": 1.9585064650595677e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2431671162575265e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 145,
"real_time": 4.8348013793343101e+06,
"cpu_time": 7.5289033241382455e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7350470767746418e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 145,
"real_time": 4.8697323217217261e+06,
"cpu_time": 7.5744489103444414e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7226014585200346e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 145,
"real_time": 4.8674205960384728e+06,
"cpu_time": 7.5452717172413087e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7234195883600800e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 145,
"real_time": 4.8704881895461986e+06,
"cpu_time": 7.5740996482761996e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7223341220711589e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 145,
"real_time": 4.9360686302955812e+06,
"cpu_time": 7.6655197310346607e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.6994512492217262e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.8757022233872581e+06,
"cpu_time": 7.5776486662069727e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7205706989895284e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time_median",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.8697323217217270e+06,
"cpu_time": 7.5740996482761996e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 1.7226014585200346e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6906616458262200e+04,
"cpu_time": 5.2840640603351618e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2951317386187399e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.5694976369213868e-03,
"cpu_time": 6.9732238760287172e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5273381057770891e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 88,
"real_time": 7.6893580103801051e+06,
"cpu_time": 1.3137896863637168e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1818747387430668e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 88,
"real_time": 7.7454474733465100e+06,
"cpu_time": 1.3270335977272846e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1660744660309744e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 88,
"real_time": 7.7161018429747364e+06,
"cpu_time": 1.3176711806819826e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1743124107770972e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 88,
"real_time": 7.7026490630073985e+06,
"cpu_time": 1.3159993056818433e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1781098765844016e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 88,
"real_time": 7.7213491736487905e+06,
"cpu_time": 1.3194362045453547e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1728347757224636e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7149811126715075e+06,
"cpu_time": 1.3187859950000364e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1746412535716009e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time_median",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7161018429747354e+06,
"cpu_time": 1.3176711806819823e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 2.1743124107770972e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1086904643336184e+04,
"cpu_time": 5.0600709359771805e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.9396128218596876e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.7332412530086296e-03,
"cpu_time": 3.8369158871580530e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7313069740144721e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 51,
"real_time": 1.3753458017519876e+07,
"cpu_time": 2.4960114901962999e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4397087595902505e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 51,
"real_time": 1.3761392173667749e+07,
"cpu_time": 2.4983173431373157e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4383021409858508e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 51,
"real_time": 1.3771312402597830e+07,
"cpu_time": 2.4973215156861961e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4365456986997309e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 51,
"real_time": 1.3789373541287348e+07,
"cpu_time": 2.5012161549016930e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4333543434394069e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 51,
"real_time": 1.3766292646965560e+07,
"cpu_time": 2.5018882568626091e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4374341633218331e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3768365756407673e+07,
"cpu_time": 2.4989509521568231e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4370690212074142e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time_median",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3766292646965558e+07,
"cpu_time": 2.4983173431373157e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 2.4374341633218331e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3464574509701915e+04,
"cpu_time": 2.5226901628189076e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3819545157706100e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.7793556242763407e-04,
"cpu_time": 1.0094996705083772e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.7738492223355317e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 28,
"real_time": 2.5148832837917976e+07,
"cpu_time": 4.8011087214279413e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6684683314136586e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 28,
"real_time": 2.5328645349613257e+07,
"cpu_time": 4.8147259321426973e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6495244050240803e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 28,
"real_time": 2.3902112751134805e+07,
"cpu_time": 4.5728522107140183e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.8076540638364224e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 28,
"real_time": 2.5153198479009528e+07,
"cpu_time": 4.7953267750001155e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6680051865373182e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 28,
"real_time": 2.5312073595289674e+07,
"cpu_time": 4.8101873178568766e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6512590423444524e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4968972602593049e+07,
"cpu_time": 4.7588401914283298e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6889822058311863e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time_median",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5153198479009524e+07,
"cpu_time": 4.8011087214279413e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 2.6680051865373182e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.0240385054057802e+05,
"cpu_time": 1.0424630903165148e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6939934591537811e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4126096821381345e-02,
"cpu_time": 2.1905822603461439e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4894153054034855e-02,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 15,
"real_time": 4.5620814214150108e+07,
"cpu_time": 8.7420578266664967e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9420283331631107e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 15,
"real_time": 4.5616771529118218e+07,
"cpu_time": 8.7524696199989185e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9422890638879557e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 15,
"real_time": 4.5621955146392189e+07,
"cpu_time": 8.7431549533327296e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9419547577327805e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 15,
"real_time": 4.5761742194493614e+07,
"cpu_time": 8.7623395866664097e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9329680550525470e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 15,
"real_time": 4.4686493277549744e+07,
"cpu_time": 8.5619994799996376e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.0035412975094709e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5461555272340775e+07,
"cpu_time": 8.7124042933328375e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9525563014691734e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time_median",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5620814214150108e+07,
"cpu_time": 8.7431549533327296e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 2.9420283331631107e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.3761195724981243e+05,
"cpu_time": 8.4476782201634091e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8774190834404361e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.6259785796650801e-03,
"cpu_time": 9.6961503802434745e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.7455180854930708e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 8,
"real_time": 8.6463508196175098e+07,
"cpu_time": 1.6541374574998713e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1046098128583083e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 8,
"real_time": 8.6581669747829437e+07,
"cpu_time": 1.6549916350001583e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1003728246616492e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 8,
"real_time": 8.5272543132305145e+07,
"cpu_time": 1.6218351662499231e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1479705675425591e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 8,
"real_time": 8.6576090194284916e+07,
"cpu_time": 1.6547820162500671e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1005726338254075e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 8,
"real_time": 8.6364588700234890e+07,
"cpu_time": 1.6524189225000897e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1081657429264169e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.6251679994165897e+07,
"cpu_time": 1.6476330395000219e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1123383163628683e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time_median",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.6463508196175098e+07,
"cpu_time": 1.6541374574998713e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.1046098128583083e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.5463135792756546e+05,
"cpu_time": 1.4456825292428460e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0176730017879508e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.4303832454635206e-03,
"cpu_time": 8.7742992194520548e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.4828203000303576e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 4,
"real_time": 1.6793927177786827e+08,
"cpu_time": 3.1333452475001878e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1968157674883466e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 4,
"real_time": 1.6651555150747299e+08,
"cpu_time": 3.0795347775000435e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2241487785355949e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 4,
"real_time": 1.6801107302308083e+08,
"cpu_time": 3.1339058750000960e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1954495756731844e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 4,
"real_time": 1.6626326739788055e+08,
"cpu_time": 3.0783957150003970e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2290410287392426e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 4,
"real_time": 1.6781470179557800e+08,
"cpu_time": 3.1314683299996203e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1991887853424463e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6730877310037616e+08,
"cpu_time": 3.1113299890000689e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.2089287871557627e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time_median",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6781470179557800e+08,
"cpu_time": 3.1314683299996203e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.1991887853424463e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.4690617510872183e+05,
"cpu_time": 2.9561363686196841e+06,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6274461758404179e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.0619352435309793e-03,
"cpu_time": 9.5011984555509604e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0716182370718994e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 3.2104605436325073e+08,
"cpu_time": 5.6116946300005567e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3445102638922458e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 3.1965814530849457e+08,
"cpu_time": 5.5927035700005949e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3590316397655282e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 3.2057686150074005e+08,
"cpu_time": 5.6014630949994171e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3494052533093419e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 3.2020078599452972e+08,
"cpu_time": 5.5981792350007713e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3533391264640546e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 3.2004632055759430e+08,
"cpu_time": 5.6032971850004292e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3549575640466504e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2030563354492193e+08,
"cpu_time": 5.6014675430003536e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3522487694955640e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time_median",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2020078599452972e+08,
"cpu_time": 5.6014630949994171e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.3533391264640546e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.2897656911325490e+05,
"cpu_time": 6.9921582932018279e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.5340723844055384e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_implicit_managed_GPUWrGPU_fine/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6514744472612202e-03,
"cpu_time": 1.2482725713441462e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6508537298197856e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
}
]
}