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

27929 lines
968 KiB
JSON

{
"context": {
"date": "2023-10-09T17:44:34-04:00",
"host_name": "frontier07936",
"executable": "/lustre/orion/csc465/scratch/cpearson/frontier-gpu-bandwidth/build/comm_scope",
"num_cpus": 128,
"mhz_per_cpu": 1796,
"cpu_scaling_enabled": false,
"caches": [
{
"type": "Data",
"level": 1,
"size": 32768,
"num_sharing": 2
},
{
"type": "Instruction",
"level": 1,
"size": 32768,
"num_sharing": 2
},
{
"type": "Unified",
"level": 2,
"size": 524288,
"num_sharing": 2
},
{
"type": "Unified",
"level": 3,
"size": 33554432,
"num_sharing": 16
}
],
"load_avg": [0.1,3.44,18.39],
"library_build_type": "release"
},
"benchmarks": [
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 78707,
"real_time": 8.8946550371526737e+03,
"cpu_time": 2.1083203260192869e+04,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 1.1512531916333874e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 78707,
"real_time": 8.9399018746996080e+03,
"cpu_time": 2.1139228848768224e+04,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 1.1454264424288300e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 78707,
"real_time": 8.8822038082539020e+03,
"cpu_time": 2.1130249012159020e+04,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 1.1528670385253206e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 78707,
"real_time": 8.8197218299117012e+03,
"cpu_time": 2.0986276087260343e+04,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 1.1610343497763713e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 78707,
"real_time": 8.8473215126098112e+03,
"cpu_time": 2.1024858868969724e+04,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 1.1574124423313031e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.8767608125255392e+03,
"cpu_time": 2.1072763215470040e+04,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 1.1535986929390424e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time_median",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.8822038082539020e+03,
"cpu_time": 2.1083203260192873e+04,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 1.1528670385253206e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5980270570961792e+01,
"cpu_time": 6.6344068166224488e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.9719354062983638e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.1798478681639596e-03,
"cpu_time": 3.1483326362021502e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.1767875976727797e-03,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 78589,
"real_time": 8.9634397051780197e+03,
"cpu_time": 2.1176430543714781e+04,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 2.2848371466334593e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 78589,
"real_time": 8.9726139456816327e+03,
"cpu_time": 2.1190018374072701e+04,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 2.2825009661601099e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 78589,
"real_time": 8.9018022576698768e+03,
"cpu_time": 2.1125435328099349e+04,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 2.3006577103366053e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 78589,
"real_time": 8.7360672893992414e+03,
"cpu_time": 2.0905029037142616e+04,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 2.3443042872221696e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 78589,
"real_time": 8.7523678634582247e+03,
"cpu_time": 2.0947902174604566e+04,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 2.3399382109503755e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.8652582122774002e+03,
"cpu_time": 2.1068963091526803e+04,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 2.3104476642605439e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time_median",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9018022576698750e+03,
"cpu_time": 2.1125435328099345e+04,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 2.3006577103366053e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1394609658430871e+02,
"cpu_time": 1.3315673847766939e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9785579598641354e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2853105217680632e-02,
"cpu_time": 6.3200423247796343e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2891691969215928e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 76563,
"real_time": 9.1758126410856839e+03,
"cpu_time": 2.1678555020048840e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 4.4639098031053090e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 76563,
"real_time": 9.1749560630861542e+03,
"cpu_time": 2.1661326293379272e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 4.4643265557200283e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 76563,
"real_time": 8.8873636969904182e+03,
"cpu_time": 2.1143602823818313e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 4.6087907951680350e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 76563,
"real_time": 8.8058834564940189e+03,
"cpu_time": 2.0943220994475148e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 4.6514356228270864e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 76563,
"real_time": 8.7819553635613138e+03,
"cpu_time": 2.0899924937633055e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 4.6641093360544759e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9651942442435175e+03,
"cpu_time": 2.1265326013870923e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 4.5705144225749874e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time_median",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.8873636969904201e+03,
"cpu_time": 2.1143602823818313e+04,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 4.6087907951680350e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9581505196566229e+02,
"cpu_time": 3.8067721167339243e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.9264466373702940e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1841696524466676e-02,
"cpu_time": 1.7901310867516666e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1718445058046272e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 74859,
"real_time": 9.3583584341838359e+03,
"cpu_time": 2.1749885504748938e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 8.7536719795606375e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 74859,
"real_time": 9.3349202606052932e+03,
"cpu_time": 2.1734048491163372e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 8.7756507514814234e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 74859,
"real_time": 9.0723608122404366e+03,
"cpu_time": 2.1466648004915914e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 9.0296232364869642e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 74859,
"real_time": 8.8957468149671076e+03,
"cpu_time": 2.1171993400927040e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 9.2088951837263930e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 74859,
"real_time": 8.8867957603345749e+03,
"cpu_time": 2.1153040168850766e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 9.2181706668271434e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1096364164662500e+03,
"cpu_time": 2.1455123114121212e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 8.9972023636165130e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time_median",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0723608122404366e+03,
"cpu_time": 2.1466648004915918e+04,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 9.0296232364869642e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2880758447473301e+02,
"cpu_time": 2.8992826539989221e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2532427682427831e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.5117092934812263e-02,
"cpu_time": 1.3513241749196436e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5043815590439496e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 74783,
"real_time": 9.3233176343006526e+03,
"cpu_time": 2.1725976438495378e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.7573143641189454e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 74783,
"real_time": 9.2636954546162724e+03,
"cpu_time": 2.1670255566104588e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.7686246358450339e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 74783,
"real_time": 8.9396207907288917e+03,
"cpu_time": 2.1253246326036617e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.8327399319881141e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 74783,
"real_time": 8.8855296691966942e+03,
"cpu_time": 2.1106793469103930e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.8438968311363721e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 74783,
"real_time": 8.8923117554261426e+03,
"cpu_time": 2.1164502440394230e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.8424905076008365e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0608950608537307e+03,
"cpu_time": 2.1384154848026952e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.8090132541378603e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time_median",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9396207907288936e+03,
"cpu_time": 2.1253246326036620e+04,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 1.8327399319881141e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1440289574711588e+02,
"cpu_time": 2.9197995497163049e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.2439843903577216e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3662441106222731e-02,
"cpu_time": 1.3654032953215852e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3460217224225480e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 74615,
"real_time": 9.4267228447175094e+03,
"cpu_time": 2.1864759337934756e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 3.4760754654373164e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 74615,
"real_time": 9.3264794118711234e+03,
"cpu_time": 2.1722734704818133e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 3.5134372310189791e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 74615,
"real_time": 9.0245445681393903e+03,
"cpu_time": 2.1330328459425029e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 3.6309865558961773e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 74615,
"real_time": 8.9498231561603916e+03,
"cpu_time": 2.1232200254640429e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 3.6613013942565942e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 74615,
"real_time": 8.9232025874020965e+03,
"cpu_time": 2.1201802305166533e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 3.6722241458758678e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1301545136581044e+03,
"cpu_time": 2.1470365012396978e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 3.5908049584969864e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time_median",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0245445681393903e+03,
"cpu_time": 2.1330328459425029e+04,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 3.6309865558961773e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3075863987950260e+02,
"cpu_time": 3.0318969366947397e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.9947226375604928e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.5274341144424558e-02,
"cpu_time": 1.4121310629531094e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5049321089623981e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 74526,
"real_time": 9.3427494888606434e+03,
"cpu_time": 2.1732281713764369e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 7.0146374017775545e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 74526,
"real_time": 9.3523767887819886e+03,
"cpu_time": 2.1789629001959071e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 7.0074165615963297e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 74526,
"real_time": 9.0842728629241174e+03,
"cpu_time": 2.1513722955746936e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 7.2142262775344200e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 74526,
"real_time": 9.0215619077872107e+03,
"cpu_time": 2.1311267450285886e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 7.2643740263457918e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 74526,
"real_time": 8.9296963520675727e+03,
"cpu_time": 2.1205923811824097e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 7.3391073353603868e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1461314800843065e+03,
"cpu_time": 2.1510564986716072e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 7.1679523205228958e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time_median",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0842728629241155e+03,
"cpu_time": 2.1513722955746933e+04,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 7.2142262775344200e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9195311942884425e+02,
"cpu_time": 2.5474043548871538e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5000804791695037e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0987356222335316e-02,
"cpu_time": 1.1842572970353465e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0927601246377631e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 74998,
"real_time": 9.3520810332323872e+03,
"cpu_time": 2.1764504680124803e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 1.4015276336276268e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 74998,
"real_time": 9.3219381380641007e+03,
"cpu_time": 2.1734253566761814e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 1.4060595346025318e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 74998,
"real_time": 8.9867783086506970e+03,
"cpu_time": 2.1310168044481092e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 1.4584982014503433e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 74998,
"real_time": 8.8710032554500849e+03,
"cpu_time": 2.1134989839729020e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 1.4775329940215410e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 74998,
"real_time": 8.8922885050150417e+03,
"cpu_time": 2.1167287260993515e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 1.4739962600862364e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0848178480824645e+03,
"cpu_time": 2.1422240678418049e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 1.4435229247576561e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time_median",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9867783086506970e+03,
"cpu_time": 2.1310168044481092e+04,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 1.4584982014503433e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3454830063015939e+02,
"cpu_time": 3.0601113297496829e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7002290362943447e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.5817611817023457e-02,
"cpu_time": 1.4284739751022440e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5633323675240922e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 76516,
"real_time": 9.1420993720414808e+03,
"cpu_time": 2.1638188548800255e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 2.8674376566250542e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 76516,
"real_time": 9.1997741953995483e+03,
"cpu_time": 2.1715624536044728e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 2.8494612414627319e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 76516,
"real_time": 9.0976966306127324e+03,
"cpu_time": 2.1653628809660804e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 2.8814326377724525e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 76516,
"real_time": 8.9180091048972899e+03,
"cpu_time": 2.1232862734591479e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 2.9394901588073578e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 76516,
"real_time": 8.8703865766987801e+03,
"cpu_time": 2.1209333328976896e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 2.9552714273875538e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0455931759299674e+03,
"cpu_time": 2.1489927591614840e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 2.8986186244110306e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time_median",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0976966306127324e+03,
"cpu_time": 2.1638188548800259e+04,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 2.8814326377724525e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4385326746188511e+02,
"cpu_time": 2.4725189174292797e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.6271161634806275e+08,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5903132571192129e-02,
"cpu_time": 1.1505478121731935e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5963176819857802e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 74850,
"real_time": 9.4167047704050874e+03,
"cpu_time": 2.1845321389445551e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 5.5676376480203300e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 74850,
"real_time": 9.3964081119430866e+03,
"cpu_time": 2.1794509311957241e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 5.5796639923889206e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 74850,
"real_time": 9.0883293987845209e+03,
"cpu_time": 2.1533765691382654e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 5.7688049914885193e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 74850,
"real_time": 8.9647603087111202e+03,
"cpu_time": 2.1238487227788770e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 5.8483214491584984e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 74850,
"real_time": 8.8936077164248745e+03,
"cpu_time": 2.1160328122912517e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 5.8951104739164001e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1519620612537365e+03,
"cpu_time": 2.1514482348697351e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 5.7319077109945343e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time_median",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0883293987845209e+03,
"cpu_time": 2.1533765691382654e+04,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 5.7688049914885193e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.4273604652293261e+02,
"cpu_time": 3.1218581836266185e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5141954382680483e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.6522842304011900e-02,
"cpu_time": 1.4510496385778204e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6416954260509589e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 75358,
"real_time": 9.3604804976560736e+03,
"cpu_time": 2.1865423219830678e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.1202159977391870e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 75358,
"real_time": 9.3105925958204516e+03,
"cpu_time": 2.1823221277103956e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.1262183252124127e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 75358,
"real_time": 9.0990085645169493e+03,
"cpu_time": 2.1614953846970355e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.1524068722048369e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 75358,
"real_time": 8.8920673793312963e+03,
"cpu_time": 2.1143430266196105e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.1792263320420940e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 75358,
"real_time": 8.8778081139068800e+03,
"cpu_time": 2.1171901058945255e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.1811203695171446e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1079914302463312e+03,
"cpu_time": 2.1523785933809275e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.1518375793431351e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time_median",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0990085645169493e+03,
"cpu_time": 2.1614953846970355e+04,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.1524068722048369e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2610075641997531e+02,
"cpu_time": 3.4755666712316952e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8566677591607466e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4824436666587891e-02,
"cpu_time": 1.6147561966653467e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4800959878300156e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 76558,
"real_time": 9.1357539675155858e+03,
"cpu_time": 2.1559371025888824e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.2955434301940906e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 76558,
"real_time": 9.1438940866444227e+03,
"cpu_time": 2.1550364625512717e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.2934998810442279e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 76558,
"real_time": 8.9897869125182842e+03,
"cpu_time": 2.1395398782622320e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3328161394790286e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 76558,
"real_time": 8.9709263659188146e+03,
"cpu_time": 2.1276926944277511e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3377206705956577e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 76558,
"real_time": 8.9708858362032879e+03,
"cpu_time": 2.1277738956085635e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3377312322230701e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0422494337600820e+03,
"cpu_time": 2.1411960066877400e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3194622707072150e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time_median",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9897869125182842e+03,
"cpu_time": 2.1395398782622320e+04,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.3328161394790286e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9452211390144925e+01,
"cpu_time": 1.3911266980827199e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2867042556015997e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.8926945164957251e-03,
"cpu_time": 6.4969610149548246e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.8587689245075438e-03,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 75798,
"real_time": 9.2478302218325389e+03,
"cpu_time": 2.1676233040449621e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 4.5354465851870514e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 75798,
"real_time": 9.1974185520243209e+03,
"cpu_time": 2.1629489973350326e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 4.5603056730269684e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 75798,
"real_time": 9.2196018981317047e+03,
"cpu_time": 2.1637845536821518e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 4.5493330908896942e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 75798,
"real_time": 8.9916270023185662e+03,
"cpu_time": 2.1360696561914476e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 4.6646774815263837e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 75798,
"real_time": 8.9811736664209729e+03,
"cpu_time": 2.1294938942979890e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 4.6701067764470074e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1275302681456233e+03,
"cpu_time": 2.1519840811103168e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 4.5959739214154211e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time_median",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1974185520243227e+03,
"cpu_time": 2.1629489973350326e+04,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 4.5603056730269684e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3011878098455850e+02,
"cpu_time": 1.7770363376152292e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.5816048219992971e+09,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4255639495238162e-02,
"cpu_time": 8.2576648833683139e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4320370251301081e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 75935,
"real_time": 9.2252524073515433e+03,
"cpu_time": 2.1646001422269201e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 9.0930932072006763e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 75935,
"real_time": 9.1976453694550819e+03,
"cpu_time": 2.1638607401066802e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 9.1203864283114734e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 75935,
"real_time": 9.1497301000625303e+03,
"cpu_time": 2.1534954447883214e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 9.1681480308830872e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 75935,
"real_time": 8.8689514220367964e+03,
"cpu_time": 2.1259638743662344e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 9.4583988577913708e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 75935,
"real_time": 8.9008076274023424e+03,
"cpu_time": 2.1294042207150887e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 9.4245470199519116e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0684773852616599e+03,
"cpu_time": 2.1474648844406493e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 9.2529147088277039e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time_median",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.1497301000625303e+03,
"cpu_time": 2.1534954447883214e+04,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 9.1681480308830872e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7013857370957450e+02,
"cpu_time": 1.8623169768837948e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7462347558808338e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8761536968277436e-02,
"cpu_time": 8.6721649810300536e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8872266856786717e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 76383,
"real_time": 9.1832435213790322e+03,
"cpu_time": 2.1612341083748903e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.8269379398403010e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 76383,
"real_time": 9.1827407255110447e+03,
"cpu_time": 2.1636244229737047e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.8270379728124475e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 76383,
"real_time": 8.9516124896869806e+03,
"cpu_time": 2.1378866789730564e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.8742116037003142e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 76383,
"real_time": 8.8851413449603642e+03,
"cpu_time": 2.1190325046149122e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.8882328765108511e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 76383,
"real_time": 8.8979023380848339e+03,
"cpu_time": 2.1220543655002071e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.8855248532218770e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0201280839244500e+03,
"cpu_time": 2.1407664160873541e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.8603890492171582e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time_median",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9516124896869806e+03,
"cpu_time": 2.1378866789730564e+04,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 1.8742116037003142e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5075182953759051e+02,
"cpu_time": 2.1048821447474683e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.0941159438760578e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6712825819653089e-02,
"cpu_time": 9.8323765214634162e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6631553196779166e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 77408,
"real_time": 9.0485900540925541e+03,
"cpu_time": 2.1471196517155884e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.7082497714463027e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 77408,
"real_time": 9.0664676877888887e+03,
"cpu_time": 2.1507375620090934e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.7009376921061064e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 77408,
"real_time": 8.9627881161221849e+03,
"cpu_time": 2.1461209306531713e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.7437493294795825e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 77408,
"real_time": 8.9163154845582430e+03,
"cpu_time": 2.1371139520462992e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.7632620848949746e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 77408,
"real_time": 8.8733104606546858e+03,
"cpu_time": 2.1336832226643255e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.7815009571438237e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9734943606433117e+03,
"cpu_time": 2.1429550638176956e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.7395399670141582e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time_median",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9627881161221849e+03,
"cpu_time": 2.1461209306531713e+04,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.7437493294795825e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.3222989753685056e+01,
"cpu_time": 7.2114389753522843e+01,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4678502954016357e+10,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.2743123702948189e-03,
"cpu_time": 3.3651844115223932e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.2734676617737734e-03,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 77276,
"real_time": 9.1036768586938288e+03,
"cpu_time": 2.1643304027123522e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 7.3716219327262676e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 77276,
"real_time": 9.1521969718240925e+03,
"cpu_time": 2.1712518776851830e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 7.3325414877543633e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 77276,
"real_time": 9.0714718640600877e+03,
"cpu_time": 2.1586477017444118e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 7.3977922222165508e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 77276,
"real_time": 8.8842184367849259e+03,
"cpu_time": 2.1442871952481975e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 7.5537161178002012e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 77276,
"real_time": 8.8302668836560151e+03,
"cpu_time": 2.1358033270355627e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 7.5998681448928945e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0083662030037904e+03,
"cpu_time": 2.1548641008851413e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 7.4511079810780566e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time_median",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0714718640600877e+03,
"cpu_time": 2.1586477017444115e+04,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 7.3977922222165508e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4220211937067518e+02,
"cpu_time": 1.4557384438780949e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1819119195640260e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5785561573113966e-02,
"cpu_time": 6.7555928157145935e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5862230457073877e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 76837,
"real_time": 9.1145764790523281e+03,
"cpu_time": 2.1733090073792402e+04,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.4725613231560164e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 76837,
"real_time": 9.1211666827156350e+03,
"cpu_time": 2.1792262816091432e+04,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.4714973716502625e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 76837,
"real_time": 8.9649375985596635e+03,
"cpu_time": 2.1551706781889021e+04,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.4971406830713900e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 76837,
"real_time": 8.8778236001933783e+03,
"cpu_time": 2.1450491247706388e+04,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.5118314357707721e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 76837,
"real_time": 8.8262126208425198e+03,
"cpu_time": 2.1364456108385468e+04,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.5206718188847352e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9809433962727053e+03,
"cpu_time": 2.1578401405572942e+04,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.4947405265066352e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time_median",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9649375985596635e+03,
"cpu_time": 2.1551706781889025e+04,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 1.4971406830713900e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3449150683509407e+02,
"cpu_time": 1.8201063745846497e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2374389178015207e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4975209273773077e-02,
"cpu_time": 8.4348527046798766e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4968744595629914e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 76033,
"real_time": 9.2351797342299687e+03,
"cpu_time": 2.2189862138808116e+04,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.9066619570494172e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 76033,
"real_time": 9.1274142838408206e+03,
"cpu_time": 2.2077648008101845e+04,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.9409803001408434e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 76033,
"real_time": 8.9842026476551018e+03,
"cpu_time": 2.1916466310680713e+04,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.9878606541679273e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 76033,
"real_time": 8.8929258204204689e+03,
"cpu_time": 2.1733486209935189e+04,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.0185280010275406e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 76033,
"real_time": 8.9517912889184172e+03,
"cpu_time": 2.1860166072626085e+04,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.9986786704053422e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.0383027550129573e+03,
"cpu_time": 2.1955525748030392e+04,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.9705419165582141e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time_median",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.9842026476551036e+03,
"cpu_time": 2.1916466310680713e+04,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 2.9878606541679273e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3986325286606814e+02,
"cpu_time": 1.8010278611448967e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5685934061240118e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5474504080812641e-02,
"cpu_time": 8.2030732573391690e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5379663153911535e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 76789,
"real_time": 9.1097676811269575e+03,
"cpu_time": 2.2585457044628962e+04,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.8933545924805016e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 76789,
"real_time": 9.1654155435420962e+03,
"cpu_time": 2.2681542994439333e+04,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.8575730631032484e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 76789,
"real_time": 9.2970014330258928e+03,
"cpu_time": 2.2933462930888421e+04,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.7746674115039336e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 76789,
"real_time": 9.2245722952099895e+03,
"cpu_time": 2.2725995324851381e+04,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.8200087203910695e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"family_index": 0,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 76789,
"real_time": 9.2202419306079937e+03,
"cpu_time": 2.2718884358436502e+04,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.8227421367087500e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.2033997767025885e+03,
"cpu_time": 2.2729068530648925e+04,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.8336691848375000e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time_median",
"family_index": 0,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.2202419306079955e+03,
"cpu_time": 2.2718884358436502e+04,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 5.8227421367087500e+13,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.0183643117802035e+01,
"cpu_time": 1.2725286668229396e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4499891033343146e+11,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.6258388009466174e-03,
"cpu_time": 5.5986837520728278e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.6281135634163862e-03,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 74438,
"real_time": 9.3404369071041401e+03,
"cpu_time": 2.4037771998173288e+04,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1495627396009009e+14,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 74438,
"real_time": 9.6937157363412043e+03,
"cpu_time": 2.4539952604852406e+04,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1076679502521425e+14,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 74438,
"real_time": 9.6122363763372596e+03,
"cpu_time": 2.4628416803245920e+04,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1170572403351042e+14,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 74438,
"real_time": 9.3672727632406368e+03,
"cpu_time": 2.4133849163061834e+04,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1462694117476897e+14,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"family_index": 0,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 74438,
"real_time": 8.9507168330968270e+03,
"cpu_time": 2.3556344031274453e+04,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1996154542948488e+14,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time_mean",
"family_index": 0,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.3928757232240132e+03,
"cpu_time": 2.4179266920121579e+04,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1440345592461373e+14,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time_median",
"family_index": 0,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.3672727632406368e+03,
"cpu_time": 2.4133849163061830e+04,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 1.1462694117476897e+14,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time_stddev",
"family_index": 0,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9048822469297579e+02,
"cpu_time": 4.3068152146433670e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5969074298288706e+12,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time_cv",
"family_index": 0,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/0/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.0926441832370859e-02,
"cpu_time": 1.7812017332334042e-02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1440548720827598e-02,
"dst_gpu": NaN,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2687,
"real_time": 2.6025346192716027e+05,
"cpu_time": 5.2394807927055238e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9346258544164808e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2687,
"real_time": 2.6055858456852016e+05,
"cpu_time": 5.2384401898027392e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9300182785983565e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2687,
"real_time": 2.6031111108047655e+05,
"cpu_time": 5.2332412095273857e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9337544822795712e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2687,
"real_time": 2.5984726328566353e+05,
"cpu_time": 5.2356186416077410e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9407765433121524e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2687,
"real_time": 2.6108538687307487e+05,
"cpu_time": 5.2299073018236260e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9220885253827381e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6041116154697910e+05,
"cpu_time": 5.2353376270934037e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9322527367978599e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time_median",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6031111108047655e+05,
"cpu_time": 5.2356186416077410e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9337544822795712e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5529491890567954e+02,
"cpu_time": 3.8972453398814071e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.8710661717752409e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7483694485328069e-03,
"cpu_time": 7.4441146254116775e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7473612790643096e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2675,
"real_time": 2.6058344817807394e+05,
"cpu_time": 5.2445306915887212e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8592865906067295e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2675,
"real_time": 2.5992927241583014e+05,
"cpu_time": 5.2253890205607412e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8790664128188174e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2675,
"real_time": 2.6011780453802340e+05,
"cpu_time": 5.2353837084112212e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8733557037254954e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2675,
"real_time": 2.5967907962371883e+05,
"cpu_time": 5.2325564747663826e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8866576505415868e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2675,
"real_time": 2.6103869585372577e+05,
"cpu_time": 5.2477074691588548e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8455801095007239e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6026966012187442e+05,
"cpu_time": 5.2371134728971851e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8687892934386702e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time_median",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6011780453802337e+05,
"cpu_time": 5.2353837084112206e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8733557037254954e+06,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4258366512257226e+02,
"cpu_time": 9.0618567306414991e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6391438705969726e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0846980968450214e-03,
"cpu_time": 1.7303151397306761e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0830953904989679e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2684,
"real_time": 2.6043657332380483e+05,
"cpu_time": 5.2437657861400151e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5727437770068415e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2684,
"real_time": 2.6160010054947642e+05,
"cpu_time": 5.2514349962741858e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5657486336574718e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2684,
"real_time": 2.6013362215130607e+05,
"cpu_time": 5.2433610543963499e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5745753917260151e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2684,
"real_time": 2.6070877291626835e+05,
"cpu_time": 5.2412137146049843e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5711017140629591e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2684,
"real_time": 2.6054530797778504e+05,
"cpu_time": 5.2340492138599302e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5720874161162168e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6068487538372818e+05,
"cpu_time": 5.2427649530550942e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5712513865139008e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time_median",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6054530797778504e+05,
"cpu_time": 5.2433610543963511e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5720874161162168e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.5299667629051100e+02,
"cpu_time": 6.2228832455899578e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3270811671747280e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1213224414208909e-03,
"cpu_time": 1.1869468307870116e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1174722235608946e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2707,
"real_time": 2.6167014500514665e+05,
"cpu_time": 5.2685423642409418e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1306590210506726e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2707,
"real_time": 2.6276437094346335e+05,
"cpu_time": 5.2730169782046322e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1176220621488292e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2707,
"real_time": 2.6107086589269884e+05,
"cpu_time": 5.2794092944220023e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1378453401870374e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2707,
"real_time": 2.6287514162736683e+05,
"cpu_time": 5.2788007129664149e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1163083543336321e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2707,
"real_time": 2.6182772012084781e+05,
"cpu_time": 5.2728563502032764e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1287749044367585e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6204164871790475e+05,
"cpu_time": 5.2745251400074537e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1262419364313859e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time_median",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6182772012084784e+05,
"cpu_time": 5.2730169782046322e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1287749044367585e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.6538186422445574e+02,
"cpu_time": 4.5549013647087958e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.1315911554168648e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.9208405151213614e-03,
"cpu_time": 8.6356614933156964e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9209483274479395e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2652,
"real_time": 2.6414604477589979e+05,
"cpu_time": 5.3209599849171273e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2026293120913863e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2652,
"real_time": 2.6560812602701091e+05,
"cpu_time": 5.3276899585217331e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1684859740826741e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2652,
"real_time": 2.6390972852055123e+05,
"cpu_time": 5.3303321003018273e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2081834162942357e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2652,
"real_time": 2.6519733353719523e+05,
"cpu_time": 5.3293767835596064e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1780410011935741e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2652,
"real_time": 2.6479727270076022e+05,
"cpu_time": 5.3300968099547015e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1873749049202211e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6473170111228351e+05,
"cpu_time": 5.3276911274509993e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1889429217164189e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time_median",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6479727270076016e+05,
"cpu_time": 5.3293767835596076e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1873749049202211e+07,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.0849596071908013e+02,
"cpu_time": 3.9022994375804001e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6562843711905272e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.6762792583672410e-03,
"cpu_time": 7.3245601973315427e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6761991379477437e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2604,
"real_time": 2.6853901914216450e+05,
"cpu_time": 5.4155939016897883e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2202323559785040e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2604,
"real_time": 2.6930137085662183e+05,
"cpu_time": 5.4216672542242566e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2167780615363427e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2604,
"real_time": 2.6966489317859831e+05,
"cpu_time": 5.4266058333332685e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2151377813313594e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2604,
"real_time": 2.6880336844066542e+05,
"cpu_time": 5.4198261712749570e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2190323428641511e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2604,
"real_time": 2.7006577207757294e+05,
"cpu_time": 5.4187415322579257e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2133340611037450e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6927488473912462e+05,
"cpu_time": 5.4204869385560392e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2169029205628204e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time_median",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6930137085662183e+05,
"cpu_time": 5.4198261712749570e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2167780615363427e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.2091397871960567e+02,
"cpu_time": 4.0699780308621621e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8056925903419999e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3058740859592287e-03,
"cpu_time": 7.5085099862750725e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3056009998269709e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2547,
"real_time": 2.7769817910588614e+05,
"cpu_time": 5.6112344601491769e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3599722623680279e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2547,
"real_time": 2.7770236153314624e+05,
"cpu_time": 5.6120554652532761e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3599367192337576e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2547,
"real_time": 2.7689928553020710e+05,
"cpu_time": 5.6046011307421909e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3667811159032637e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2547,
"real_time": 2.7740566954384168e+05,
"cpu_time": 5.5843822889673710e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3624607279211563e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2547,
"real_time": 2.7901180573515332e+05,
"cpu_time": 5.6027841107185057e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3488611826772955e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7774346028964687e+05,
"cpu_time": 5.6030114911661041e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3596024016207004e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time_median",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7769817910588614e+05,
"cpu_time": 5.6046011307421909e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3599722623680279e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.8089264225587590e+02,
"cpu_time": 1.1169562620523523e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6205422288510483e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.8115608606644280e-03,
"cpu_time": 1.9934927205010784e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8057872056341812e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2382,
"real_time": 2.9070480403071624e+05,
"cpu_time": 5.9057095256088662e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.5087662186054128e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2382,
"real_time": 2.9072388096845074e+05,
"cpu_time": 5.8966810075565265e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.5084703590010172e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2382,
"real_time": 2.9319308734441054e+05,
"cpu_time": 5.8978652728798706e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4705010335400999e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2382,
"real_time": 2.9062950969665870e+05,
"cpu_time": 5.9029026784215390e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.5099343193609250e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2382,
"real_time": 2.9072609475339152e+05,
"cpu_time": 5.8921176364399027e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.5084360284611487e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9119547535872558e+05,
"cpu_time": 5.8990552241813415e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.5012215917937207e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time_median",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9072388096845069e+05,
"cpu_time": 5.8978652728798694e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.5084703590010172e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1173907720302100e+03,
"cpu_time": 5.3447554660776109e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7184138305891280e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.8372532081883803e-03,
"cpu_time": 9.0603584183590092e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8176610405539846e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2154,
"real_time": 3.2612902371240075e+05,
"cpu_time": 6.5556573259053729e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0380457101289320e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2154,
"real_time": 3.2635683978228079e+05,
"cpu_time": 6.5653353481892985e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0324346863660502e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2154,
"real_time": 3.2646031139845232e+05,
"cpu_time": 6.5635203946146567e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0298888056884575e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2154,
"real_time": 3.2565362470768421e+05,
"cpu_time": 6.5355838904365292e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0497798922185433e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2154,
"real_time": 3.2635312286912947e+05,
"cpu_time": 6.5599482358401711e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0325261696705782e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2619058449398953e+05,
"cpu_time": 6.5560090389972052e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0365350528145123e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time_median",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2635312286912941e+05,
"cpu_time": 6.5599482358401699e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0325261696705782e+08,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2362311765821096e+02,
"cpu_time": 1.2002376576135775e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.9806736297132215e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.9212893640151698e-04,
"cpu_time": 1.8307443605922230e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.9304906620400709e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1798,
"real_time": 3.8956866861650982e+05,
"cpu_time": 7.8282837875418086e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3458166486076102e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1798,
"real_time": 3.9017342597992573e+05,
"cpu_time": 7.8378634760842822e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3437306722856476e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1798,
"real_time": 3.8972056634751073e+05,
"cpu_time": 7.8313683259177080e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3452921022712886e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1798,
"real_time": 3.8945778645406704e+05,
"cpu_time": 7.8238894771970238e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3461998148080034e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1798,
"real_time": 3.8976211905817670e+05,
"cpu_time": 7.8279281535037479e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3451486800895181e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8973651329123799e+05,
"cpu_time": 7.8298666440489143e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3452375836124139e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time_median",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8972056634751079e+05,
"cpu_time": 7.8282837875418074e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3452921022712886e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7279256880621722e+02,
"cpu_time": 5.2008190436186339e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.4112472712175618e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.9994101015207616e-04,
"cpu_time": 6.6422830426767399e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.9959740835854494e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1311,
"real_time": 5.2684517931598041e+05,
"cpu_time": 1.0620939344012381e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9902924828151586e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1311,
"real_time": 5.2931060510865843e+05,
"cpu_time": 1.0614673615560716e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9810220877489226e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1311,
"real_time": 5.2730956087833724e+05,
"cpu_time": 1.0628657254004714e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9885397075929961e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1311,
"real_time": 5.2881864319370047e+05,
"cpu_time": 1.0599177337909965e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9828650398316574e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1311,
"real_time": 5.2779065834004560e+05,
"cpu_time": 1.0636093188405682e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9867270923245902e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.2801492936734448e+05,
"cpu_time": 1.0619908147978692e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9858892820626652e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time_median",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.2779065834004560e+05,
"cpu_time": 1.0620939344012379e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9867270923245902e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0296709331692059e+03,
"cpu_time": 1.4113225808852899e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.8713847635180876e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9500792040159436e-03,
"cpu_time": 1.3289404778457615e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9494464260852611e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 905,
"real_time": 7.7036603132664168e+05,
"cpu_time": 1.5439227215469629e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7222799483883133e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 905,
"real_time": 7.7076063765398122e+05,
"cpu_time": 1.5455369370165274e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7208862227101398e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 905,
"real_time": 7.7046909702694800e+05,
"cpu_time": 1.5444235856353864e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7219157888257909e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 905,
"real_time": 7.7041499554668425e+05,
"cpu_time": 1.5450817116022503e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7221069321370974e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 905,
"real_time": 7.7079122143833595e+05,
"cpu_time": 1.5453266331491808e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7207782622207437e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7056039659851824e+05,
"cpu_time": 1.5448583177900615e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7215934308564167e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time_median",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7046909702694800e+05,
"cpu_time": 1.5450817116022501e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7219157888257909e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0039431329828366e+02,
"cpu_time": 6.6971645131152616e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.0773367555882211e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.6006308419545502e-04,
"cpu_time": 4.3351318603091296e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6004386530875635e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 526,
"real_time": 1.3302074109660923e+06,
"cpu_time": 2.6830618992395592e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1531203069706211e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 526,
"real_time": 1.3292200578741389e+06,
"cpu_time": 2.6823879904943425e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1554624647389650e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 526,
"real_time": 1.3294484990404586e+06,
"cpu_time": 2.6809646577946614e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1549202568036871e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 526,
"real_time": 1.3298102229135998e+06,
"cpu_time": 2.6817297072244002e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1540620817384949e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 526,
"real_time": 1.3301517385475961e+06,
"cpu_time": 2.6821082870721379e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1532522782549577e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3297675858683770e+06,
"cpu_time": 2.6820505083650202e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1541634777013454e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time_median",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3298102229135996e+06,
"cpu_time": 2.6821082870721379e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1540620817384949e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.3140486274096656e+02,
"cpu_time": 7.7815951102942790e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0233343373893012e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.2442125024370074e-04,
"cpu_time": 2.9013603905013501e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2443921966120631e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 276,
"real_time": 2.5301617966708392e+06,
"cpu_time": 5.0849314239130812e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3154433092135234e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 276,
"real_time": 2.5404604047239907e+06,
"cpu_time": 5.0885988695652662e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3020030481094561e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 276,
"real_time": 2.5303183330992316e+06,
"cpu_time": 5.0831677862318652e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3152382015607138e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 276,
"real_time": 2.5386430544144325e+06,
"cpu_time": 5.0831090615940625e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3043668685178466e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 276,
"real_time": 2.5307839513634858e+06,
"cpu_time": 5.0846794963768572e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3146282579674773e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5340735080543966e+06,
"cpu_time": 5.0848973275362272e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3103359370738039e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time_median",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5307839513634862e+06,
"cpu_time": 5.0846794963768581e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3146282579674773e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0472074236682583e+03,
"cpu_time": 2.2326685036091867e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.5880248146223612e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9917367857033431e-03,
"cpu_time": 4.3907838443829036e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9901378409485217e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 140,
"real_time": 4.9580540075632082e+06,
"cpu_time": 9.8990017642859928e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3838308284676576e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 140,
"real_time": 4.9588883395439815e+06,
"cpu_time": 9.9015319571427498e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3832614996011043e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 140,
"real_time": 4.9562449766589059e+06,
"cpu_time": 9.8975819571425710e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3850659277358446e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 140,
"real_time": 4.9559615818517553e+06,
"cpu_time": 9.8990283214285616e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3852594946329927e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 140,
"real_time": 4.9591205082833767e+06,
"cpu_time": 9.9018273571427278e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3831031070885415e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9576538827802455e+06,
"cpu_time": 9.8997942714285217e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3841041715052280e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time_median",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9580540075632073e+06,
"cpu_time": 9.8990283214285616e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3838308284676576e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4734205585506411e+03,
"cpu_time": 1.8208562983311172e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0058191824776459e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.9720117486788908e-04,
"cpu_time": 1.8392870077979620e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9721874135755816e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 71,
"real_time": 9.8164474171861801e+06,
"cpu_time": 1.9564316197183520e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4181848660702305e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 71,
"real_time": 9.8363753854179047e+06,
"cpu_time": 1.9643309661971606e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4112598071179061e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 71,
"real_time": 9.8192892496434730e+06,
"cpu_time": 1.9613840169013906e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4171955980641184e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 71,
"real_time": 9.8227235737820752e+06,
"cpu_time": 1.9642507873239975e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4160008421249332e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 71,
"real_time": 9.8035933030113373e+06,
"cpu_time": 1.9588634901408471e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4226666654657326e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.8196857858081944e+06,
"cpu_time": 1.9610521760563497e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4170615557685843e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time_median",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.8192892496434748e+06,
"cpu_time": 1.9613840169013910e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4171955980641184e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1804481837151721e+04,
"cpu_time": 3.4362619255076708e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.1073850850388985e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2021241916123256e-03,
"cpu_time": 1.7522542069318874e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2020225617840950e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 33,
"real_time": 2.1204709780938696e+07,
"cpu_time": 4.2117607151515752e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1648093604339442e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 33,
"real_time": 2.1178949737187587e+07,
"cpu_time": 4.1930105333333910e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1686587310873694e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 33,
"real_time": 2.1222847880739152e+07,
"cpu_time": 4.2080341848485537e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1621045571789074e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 33,
"real_time": 2.1193732705080148e+07,
"cpu_time": 4.1990913515150800e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1664485408893533e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 33,
"real_time": 2.1201363736481376e+07,
"cpu_time": 4.2017415090909213e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1653088373992271e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1200320768085394e+07,
"cpu_time": 4.2027276587879047e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1654660053977604e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time_median",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1201363736481380e+07,
"cpu_time": 4.2017415090909213e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1653088373992271e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6030795030290650e+04,
"cpu_time": 7.3887257865383581e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3934332995427302e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.5615813579684799e-04,
"cpu_time": 1.7580786542493493e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5610772488519603e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 18,
"real_time": 3.9356644989715680e+07,
"cpu_time": 7.7421940555555895e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4102939423589725e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 18,
"real_time": 3.9344075860248670e+07,
"cpu_time": 7.7469421777777836e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4113834183510971e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 18,
"real_time": 3.9327062873376742e+07,
"cpu_time": 7.7355495444445908e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4128591914465456e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 18,
"real_time": 3.9364742736021675e+07,
"cpu_time": 7.7591955444442332e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4095924086195226e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 18,
"real_time": 3.9355862678753003e+07,
"cpu_time": 7.7532199500000045e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4103617317594700e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9349677827623159e+07,
"cpu_time": 7.7474202544444412e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4108981385071220e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time_median",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9355862678753003e+07,
"cpu_time": 7.7469421777777821e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4103617317594700e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4633552101783634e+04,
"cpu_time": 9.2296992242893481e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2687534104939383e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.7188492789923163e-04,
"cpu_time": 1.1913254891516402e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7197047785462301e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 9,
"real_time": 7.5649515622191966e+07,
"cpu_time": 1.4756960855555689e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5484094483911519e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 9,
"real_time": 7.5650668806499898e+07,
"cpu_time": 1.4747835633333278e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5483553580551562e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 9,
"real_time": 7.5640661848915949e+07,
"cpu_time": 1.4757690677777824e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5488247913030009e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 9,
"real_time": 7.5580374234252512e+07,
"cpu_time": 1.4749481277777931e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5516555550256443e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 9,
"real_time": 7.5691077444288462e+07,
"cpu_time": 1.4771848766666710e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5464610237260633e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5642459591229767e+07,
"cpu_time": 1.4756763442222288e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5487412353002038e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time_median",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5649515622191966e+07,
"cpu_time": 1.4756960855555689e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5484094483911519e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9807969831743321e+04,
"cpu_time": 9.5026501830709123e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8680598006702033e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.2626487883742463e-04,
"cpu_time": 6.4395219319446286e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.2640068035622091e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 5,
"real_time": 1.4327096343040466e+08,
"cpu_time": 2.7409749079999983e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.7472415843758221e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 5,
"real_time": 1.4351768195629120e+08,
"cpu_time": 2.7431292680000752e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.7407997724176307e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 5,
"real_time": 1.4346329271793365e+08,
"cpu_time": 2.7423232179999101e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.7422179696903634e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 5,
"real_time": 1.4338159263134003e+08,
"cpu_time": 2.7410789240000212e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.7443503182475595e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"family_index": 1,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 5,
"real_time": 1.4365660548210144e+08,
"cpu_time": 2.7442963779999447e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.7371822214390984e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4345802724361420e+08,
"cpu_time": 2.7423605391999900e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.7423583732340951e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time_median",
"family_index": 1,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4346329271793365e+08,
"cpu_time": 2.7423232179999101e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.7422179696903634e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4478850690995081e+05,
"cpu_time": 1.4055532752561572e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7767410899875038e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0092743479880512e-03,
"cpu_time": 5.1253409431941050e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0091874463438134e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 2.9387553036212921e+08,
"cpu_time": 5.2167253650000590e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6537299402807631e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 2.9346024990081787e+08,
"cpu_time": 5.2176620200000912e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6589003940496116e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 2.9387488961219788e+08,
"cpu_time": 5.2239535100000012e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6537379066885481e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 2.9354144632816315e+08,
"cpu_time": 5.2173495799999613e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6578883065106106e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"family_index": 1,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 2.9386170208454132e+08,
"cpu_time": 5.2220424300000447e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6539018741921473e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time_mean",
"family_index": 1,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9372276365756989e+08,
"cpu_time": 5.2195465810000312e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6556316843443360e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time_median",
"family_index": 1,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9386170208454132e+08,
"cpu_time": 5.2176620200000918e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6539018741921473e+09,
"dst_gpu": 1.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time_stddev",
"family_index": 1,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0467859256882238e+05,
"cpu_time": 3.2399046548270422e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5481402139128842e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time_cv",
"family_index": 1,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/1/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.9684279835880315e-04,
"cpu_time": 6.2072530717913383e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.9704511666905298e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2508,
"real_time": 2.6446617107648635e+05,
"cpu_time": 5.3297925996809243e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8719507898945929e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2508,
"real_time": 2.6436333136866614e+05,
"cpu_time": 5.3080345374801650e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8734570134917372e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2508,
"real_time": 2.6364243244737433e+05,
"cpu_time": 5.3046309848484863e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8840485216824897e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2508,
"real_time": 2.6403133953016170e+05,
"cpu_time": 5.3108141586922947e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8783274812080525e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2508,
"real_time": 2.6361990957552468e+05,
"cpu_time": 5.3036017783093464e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8843803628065255e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6402463679964264e+05,
"cpu_time": 5.3113748118022433e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8784328338166797e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time_median",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6403133953016170e+05,
"cpu_time": 5.3080345374801639e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8783274812080525e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9357202266354432e+02,
"cpu_time": 1.0683935679848159e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.7813456860746992e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4906640055799406e-03,
"cpu_time": 2.0115198151912975e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4906396304368652e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2645,
"real_time": 2.6390918738266808e+05,
"cpu_time": 5.3066829640832043e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7602451824854501e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2645,
"real_time": 2.6334740113887744e+05,
"cpu_time": 5.3061670737238904e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7767997373172399e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2645,
"real_time": 2.6401251082225848e+05,
"cpu_time": 5.3045704574669059e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7572081475289566e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2645,
"real_time": 2.6380272295206279e+05,
"cpu_time": 5.2990737542532699e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7633770306918127e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2645,
"real_time": 2.6380332587999845e+05,
"cpu_time": 5.3043951795841521e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7633592873336822e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6377502963517309e+05,
"cpu_time": 5.3041778858222859e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7641978770714290e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time_median",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6380332587999845e+05,
"cpu_time": 5.3045704574669059e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7633592873336822e+06,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5437636656194863e+02,
"cpu_time": 3.0201727494566001e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.4943981866249605e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.6436863987382087e-04,
"cpu_time": 5.6939507204864330e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.6525079670583636e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2643,
"real_time": 2.6391868260109425e+05,
"cpu_time": 5.3076382633371919e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5519931971587589e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2643,
"real_time": 2.6329085593771806e+05,
"cpu_time": 5.3064584184638958e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5556939816280274e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2643,
"real_time": 2.6378719843243965e+05,
"cpu_time": 5.3064744797579315e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5527667848707430e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2643,
"real_time": 2.6396118458857283e+05,
"cpu_time": 5.3005160385925299e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5517433013434509e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2643,
"real_time": 2.6401106691323756e+05,
"cpu_time": 5.3071329360575252e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5514501145310231e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6379379769461253e+05,
"cpu_time": 5.3056440272418153e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5527294759064008e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time_median",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6391868260109430e+05,
"cpu_time": 5.3064744797579315e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5519931971587589e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9317848088350058e+02,
"cpu_time": 2.9087359418247775e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7277947160642016e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1113926235024904e-03,
"cpu_time": 5.4823428162347127e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1127467745504136e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2628,
"real_time": 2.6542689954515413e+05,
"cpu_time": 5.3387537823438540e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0863488267534792e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2628,
"real_time": 2.6515109580011235e+05,
"cpu_time": 5.3441253881279170e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0895591720185257e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2628,
"real_time": 2.6554646742756263e+05,
"cpu_time": 5.3341036035007879e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0849591332766131e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2628,
"real_time": 2.6653222953656170e+05,
"cpu_time": 5.3460307191780698e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0735494969009962e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2628,
"real_time": 2.6572072124128166e+05,
"cpu_time": 5.3337296270927927e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0829360848232236e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6567548271013453e+05,
"cpu_time": 5.3393486240486836e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0834705427545682e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time_median",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6554646742756263e+05,
"cpu_time": 5.3387537823438528e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0849591332766131e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.2189122757209032e+02,
"cpu_time": 5.6326076191114691e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0474090097536813e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9643936363578579e-03,
"cpu_time": 1.0549241144775473e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9612345653710469e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2598,
"real_time": 2.6849602398661908e+05,
"cpu_time": 5.3984277559659712e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1021387790891543e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2598,
"real_time": 2.6766446256535838e+05,
"cpu_time": 5.3915292263279785e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1210964813826755e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2598,
"real_time": 2.6911130723732745e+05,
"cpu_time": 5.3940242571207497e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.0881871401825055e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2598,
"real_time": 2.6833686979058798e+05,
"cpu_time": 5.3871212856043235e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1057580394323707e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2598,
"real_time": 2.6891546387659502e+05,
"cpu_time": 5.3946807544265094e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.0926209909291774e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6850482549129758e+05,
"cpu_time": 5.3931566558891069e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1019602862031773e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time_median",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6849602398661908e+05,
"cpu_time": 5.3940242571207508e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1021387790891543e+07,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.6367996746909398e+02,
"cpu_time": 4.1813372774176423e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2821571108146224e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0993290025149406e-03,
"cpu_time": 7.7530425022084089e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1012216577574925e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2561,
"real_time": 2.7315948118136782e+05,
"cpu_time": 5.4772198945722496e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.1995922623034731e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2561,
"real_time": 2.7236921965678787e+05,
"cpu_time": 5.4688404490433482e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2030728010048610e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2561,
"real_time": 2.7252159630110627e+05,
"cpu_time": 5.4780187504880701e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2024001196512505e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2561,
"real_time": 2.7237196706520149e+05,
"cpu_time": 5.4702161577508890e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2030606656431666e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2561,
"real_time": 2.7257395183061325e+05,
"cpu_time": 5.4781334205389279e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2021691647323348e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7259924320701533e+05,
"cpu_time": 5.4744857344786974e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2020590026670173e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time_median",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7252159630110627e+05,
"cpu_time": 5.4772198945722496e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2024001196512505e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2599868172879167e+02,
"cpu_time": 4.5651391042132070e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4356549277246257e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1958899001096057e-03,
"cpu_time": 8.3389368894719003e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1943298328445837e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2496,
"real_time": 2.8156096507304121e+05,
"cpu_time": 5.6534947996794560e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3275953746997195e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2496,
"real_time": 2.8081404099840514e+05,
"cpu_time": 5.6514607772436179e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3337864362833697e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2496,
"real_time": 2.8178288869476557e+05,
"cpu_time": 5.6623375080127723e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3257622314671588e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2496,
"real_time": 2.8125128374785371e+05,
"cpu_time": 5.6588814903845696e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3301582530287781e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2496,
"real_time": 2.8111468016224814e+05,
"cpu_time": 5.6574100000002130e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3312905595031622e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8130477173526277e+05,
"cpu_time": 5.6567169150641258e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3297185709964377e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time_median",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8125128374785371e+05,
"cpu_time": 5.6574100000002119e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3301582530287781e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7882821973069571e+02,
"cpu_time": 4.3233618408881819e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1373787281742063e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3466825229940028e-03,
"cpu_time": 7.6428817383009735e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3466771339820357e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2368,
"real_time": 2.9536499770885613e+05,
"cpu_time": 5.9902065371621295e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4376280539916521e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2368,
"real_time": 2.9857744835385960e+05,
"cpu_time": 5.9982895270270691e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.3898827832656598e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2368,
"real_time": 2.9543540351270977e+05,
"cpu_time": 5.9849601097972703e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4365705139452326e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2368,
"real_time": 2.9533729264437931e+05,
"cpu_time": 5.9956708572633949e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4380443399617004e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2368,
"real_time": 2.9763021619736397e+05,
"cpu_time": 5.9866659459458827e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4038539391136205e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9646907168343384e+05,
"cpu_time": 5.9911585954391491e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4211959260555738e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time_median",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9543540351270983e+05,
"cpu_time": 5.9902065371621295e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4365705139452326e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5298596167855867e+03,
"cpu_time": 5.7166911502904907e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2756972859411682e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.1602671674944658e-03,
"cpu_time": 9.5418791861767748e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.1472436960545665e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2123,
"real_time": 3.2931309474897111e+05,
"cpu_time": 6.6220964861046243e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9603272441937733e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2123,
"real_time": 3.2959487666457094e+05,
"cpu_time": 6.6272978944889258e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9535216885905743e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2123,
"real_time": 3.2940552669122827e+05,
"cpu_time": 6.6276686858218850e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9580935582092845e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2123,
"real_time": 3.3032577566276520e+05,
"cpu_time": 6.6244869477153884e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9359232404445159e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2123,
"real_time": 3.2940781163665879e+05,
"cpu_time": 6.6203308148846845e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9580383566965413e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2960941708083882e+05,
"cpu_time": 6.6243761658031028e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9531808176269388e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time_median",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2940781163665879e+05,
"cpu_time": 6.6244869477153884e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9580383566965413e+08,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.1334126700439521e+02,
"cpu_time": 3.1996586851996511e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.9591952694984351e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2540335487533129e-03,
"cpu_time": 4.8301283096168239e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2522279447520531e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1773,
"real_time": 3.9401212971772027e+05,
"cpu_time": 7.9171547659335448e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3306392378722262e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1773,
"real_time": 3.9637197636764392e+05,
"cpu_time": 7.9585841060348286e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3227171224479077e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1773,
"real_time": 3.9443446800821333e+05,
"cpu_time": 7.9172670332769619e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3292144640591674e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1773,
"real_time": 3.9420498354997102e+05,
"cpu_time": 7.9140996446699055e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3299882596069188e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1773,
"real_time": 3.9439169759021676e+05,
"cpu_time": 7.9193275352510018e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3293586127787833e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9468305104675301e+05,
"cpu_time": 7.9252866170332499e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3283835393530006e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time_median",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9439169759021676e+05,
"cpu_time": 7.9172670332769607e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3293586127787833e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.5888386475494951e+02,
"cpu_time": 1.8707100965132311e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2176384002183960e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4295035274807457e-03,
"cpu_time": 2.3604321041117283e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4222209210643872e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1283,
"real_time": 5.3745240357066400e+05,
"cpu_time": 1.0835820194855507e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9510118347849824e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1283,
"real_time": 5.3621080549054919e+05,
"cpu_time": 1.0755401917380821e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9555294098199248e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1283,
"real_time": 5.3197309369002108e+05,
"cpu_time": 1.0708896500389830e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9711072090630991e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1283,
"real_time": 5.3448908358365181e+05,
"cpu_time": 1.0710240303975213e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9618286550765250e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1283,
"real_time": 5.3235119268942741e+05,
"cpu_time": 1.0721307365549554e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9697072428871913e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3449531580486277e+05,
"cpu_time": 1.0746333256430184e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9618368703263445e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time_median",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3448908358365181e+05,
"cpu_time": 1.0721307365549556e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9618286550765250e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3794001390804879e+03,
"cpu_time": 5.3433743772748294e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7299407865299974e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.4516763173078509e-03,
"cpu_time": 4.9722768220290987e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4498810877572114e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 894,
"real_time": 7.7588147779622464e+05,
"cpu_time": 1.5552310178971207e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7029282951265273e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 894,
"real_time": 7.7561783999927610e+05,
"cpu_time": 1.5549561935122577e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7038470388999271e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 894,
"real_time": 7.7550491010530607e+05,
"cpu_time": 1.5541468064877286e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7042407761354175e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 894,
"real_time": 7.7587019208604074e+05,
"cpu_time": 1.5551647908277144e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7029676115813904e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 894,
"real_time": 7.7574938918272196e+05,
"cpu_time": 1.5552472975391988e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7033885288771157e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7572476183391397e+05,
"cpu_time": 1.5549492212528042e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7034744501240759e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time_median",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7574938918272196e+05,
"cpu_time": 1.5551647908277144e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7033885288771157e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6285224731558947e+02,
"cpu_time": 4.6331607187891814e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.6758941892885917e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0993560516308079e-04,
"cpu_time": 2.9796218779776608e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0994813503889768e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 521,
"real_time": 1.3373407558493330e+06,
"cpu_time": 2.6966973243761472e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1363016356562285e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 521,
"real_time": 1.3372940940857506e+06,
"cpu_time": 2.6967227984643108e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1364110695990639e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 521,
"real_time": 1.3376174962966775e+06,
"cpu_time": 2.6981923358924426e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1356527644205709e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 521,
"real_time": 1.3369615140573019e+06,
"cpu_time": 2.6964845067178239e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1371912773101954e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 521,
"real_time": 1.3372658272836923e+06,
"cpu_time": 2.6981708003837415e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1364773662986946e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3372959375145510e+06,
"cpu_time": 2.6972535531668933e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1364068226569510e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time_median",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3372940940857506e+06,
"cpu_time": 2.6967227984643104e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1364110695990639e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3353683218444786e+02,
"cpu_time": 8.5222927181819455e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.4772978564251913e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7463362120017414e-04,
"cpu_time": 3.1596186825579568e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7463607771982833e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 278,
"real_time": 2.5055975696782200e+06,
"cpu_time": 5.0455149064746099e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3479470532362075e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 278,
"real_time": 2.5416980087154098e+06,
"cpu_time": 5.1012320431653233e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3003952362694955e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 278,
"real_time": 2.5347614863539021e+06,
"cpu_time": 5.1014719172663754e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3094269599568892e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 278,
"real_time": 2.5435719444758170e+06,
"cpu_time": 5.1035070287770294e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.2979637231093678e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 278,
"real_time": 2.5347321697932887e+06,
"cpu_time": 5.1022885935252095e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3094652365910926e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5320722358033275e+06,
"cpu_time": 5.0908028978417087e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3130396418326111e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time_median",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5347614863539017e+06,
"cpu_time": 5.1014719172663745e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3094269599568892e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5330639806435589e+04,
"cpu_time": 2.5332357558479718e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0196036315625895e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.0545823257572972e-03,
"cpu_time": 4.9761026044083528e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0959235321598618e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 139,
"real_time": 4.9914713151645744e+06,
"cpu_time": 9.9506470431653876e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3611764829799156e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 139,
"real_time": 4.9975973674558476e+06,
"cpu_time": 9.9559767338133901e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3570563545700088e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 139,
"real_time": 4.9957268965169247e+06,
"cpu_time": 9.9538009208633006e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3583132840382562e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 139,
"real_time": 4.9995853089921763e+06,
"cpu_time": 9.9608261151084173e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3557215175076141e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 139,
"real_time": 4.9928330360717485e+06,
"cpu_time": 9.9506875539569091e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3602597721152611e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9954427848402541e+06,
"cpu_time": 9.9543876733814813e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3585054822422113e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time_median",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9957268965169247e+06,
"cpu_time": 9.9538009208632987e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3583132840382562e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3341720126328560e+03,
"cpu_time": 4.2428210409526209e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2416037053502565e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.6744273855985669e-04,
"cpu_time": 4.2622622105608076e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6744083557479061e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 69,
"real_time": 9.8551584920589477e+06,
"cpu_time": 1.9677039246376824e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4047582316446118e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 69,
"real_time": 9.8767284492867589e+06,
"cpu_time": 1.9755814637680512e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3973225215504546e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 69,
"real_time": 9.8508546749750767e+06,
"cpu_time": 1.9728923333332203e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4062457631459165e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 69,
"real_time": 9.8941825681190565e+06,
"cpu_time": 1.9738983507245988e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3913293765286665e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 69,
"real_time": 9.8775355415283777e+06,
"cpu_time": 1.9697673565217327e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3970449267356453e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.8708919451936446e+06,
"cpu_time": 1.9719686857970573e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3993401639210587e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time_median",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.8767284492867589e+06,
"cpu_time": 1.9728923333332203e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3973225215504546e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.7816347927917799e+04,
"cpu_time": 3.1883747622511357e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.1350319405329917e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8049379961648730e-03,
"cpu_time": 1.6168485763567867e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8047714099480932e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 33,
"real_time": 2.1335860432097405e+07,
"cpu_time": 4.2675718484846666e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1453554082610254e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 33,
"real_time": 2.1348320625045083e+07,
"cpu_time": 4.2700432666668519e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1435195853893204e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 33,
"real_time": 2.1277512959910162e+07,
"cpu_time": 4.2515126757576361e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1539806426833143e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 33,
"real_time": 2.1340655275818072e+07,
"cpu_time": 4.2700585090907834e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1446487060799704e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 33,
"real_time": 2.1284237504005432e+07,
"cpu_time": 4.2576889545454256e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1529841737281375e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1317317359375235e+07,
"cpu_time": 4.2633750509090729e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1480977032283540e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time_median",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1335860432097405e+07,
"cpu_time": 4.2675718484846666e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1453554082610254e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3646594996874803e+04,
"cpu_time": 8.3635288700982492e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9714559370228760e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5783690991529580e-03,
"cpu_time": 1.9617154883699258e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5791936609606111e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 18,
"real_time": 3.9461461206277214e+07,
"cpu_time": 7.7981712388887241e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4012356333791747e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 18,
"real_time": 3.9421541823281184e+07,
"cpu_time": 7.7887997277779654e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4046798220544238e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 18,
"real_time": 3.9433871499366231e+07,
"cpu_time": 7.7994282055556133e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4036152905290341e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 18,
"real_time": 3.9458120448721781e+07,
"cpu_time": 7.8052957611109570e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4015236020789199e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 18,
"real_time": 3.9418208516306348e+07,
"cpu_time": 7.7941505944446981e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4049677306993141e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9438640698790550e+07,
"cpu_time": 7.7971691055555940e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4032044157481737e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time_median",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9433871499366231e+07,
"cpu_time": 7.7981712388887256e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4036152905290341e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0204127718147698e+04,
"cpu_time": 6.1503704791058684e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7432842619377943e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.1229269975238496e-04,
"cpu_time": 7.8879531735737802e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.1224788433830936e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 9,
"real_time": 7.5653250018755600e+07,
"cpu_time": 1.4766938899999282e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5482342917647390e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 9,
"real_time": 7.5720396306779653e+07,
"cpu_time": 1.4773872899999988e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5450878375284672e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 9,
"real_time": 7.5604698724216878e+07,
"cpu_time": 1.4759300688889551e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5505128719469075e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 9,
"real_time": 7.5640397767225906e+07,
"cpu_time": 1.4768474888887796e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5488371812384882e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 9,
"real_time": 7.5695843332343638e+07,
"cpu_time": 1.4771011322222370e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5462377348968883e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5662917229864344e+07,
"cpu_time": 1.4767919739999801e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5477819834750986e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time_median",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5653250018755600e+07,
"cpu_time": 1.4768474888887793e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5482342917647390e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5765565843232711e+04,
"cpu_time": 5.4899060498109844e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1458624716416476e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.0486123875182706e-04,
"cpu_time": 3.7174538773671989e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0484620578058954e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 5,
"real_time": 1.4917475581169128e+08,
"cpu_time": 2.8526693339999837e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.5989394390409570e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 5,
"real_time": 1.4938601851463318e+08,
"cpu_time": 2.8542624419999355e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.5938497949017267e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 5,
"real_time": 1.4938009679317474e+08,
"cpu_time": 2.8540177840000069e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.5939922621909156e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 5,
"real_time": 1.4939443767070770e+08,
"cpu_time": 2.8491675279999530e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.5936472627137589e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"family_index": 2,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 5,
"real_time": 1.4956922233104706e+08,
"cpu_time": 2.8567448359999621e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.5894477729631023e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4938090622425079e+08,
"cpu_time": 2.8533723847999680e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.5939753063620930e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time_median",
"family_index": 2,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4938601851463318e+08,
"cpu_time": 2.8540177840000069e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.5938497949017267e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3979524258852372e+05,
"cpu_time": 2.7729618722427828e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3639569397481889e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.3583073045937302e-04,
"cpu_time": 9.7181913128986056e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.3599890177132738e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 2.9438081383705139e+08,
"cpu_time": 5.2322199650001264e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6474585758647585e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 2.9471392929553986e+08,
"cpu_time": 5.2382326349999177e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6433358496715269e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 2.9458577930927277e+08,
"cpu_time": 5.2325608550000882e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6449207647349644e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 2.9473392665386200e+08,
"cpu_time": 5.2387826699998641e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6430886535197268e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"family_index": 2,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 2.9491466283798218e+08,
"cpu_time": 5.2407752499999559e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6408560146427293e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time_mean",
"family_index": 2,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9466582238674164e+08,
"cpu_time": 5.2365142749999905e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6439319716867418e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time_median",
"family_index": 2,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9471392929553986e+08,
"cpu_time": 5.2382326349999177e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6433358496715269e+09,
"dst_gpu": 2.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time_stddev",
"family_index": 2,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.9780723172584400e+05,
"cpu_time": 3.8834557092098950e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4465642969029038e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time_cv",
"family_index": 2,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/2/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.7129343377402906e-04,
"cpu_time": 7.4161083218089805e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.7140778585128536e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2700,
"real_time": 2.5914309987220570e+05,
"cpu_time": 5.2335482740739250e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9514847221669313e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2700,
"real_time": 2.5848383904236404e+05,
"cpu_time": 5.2309596962960245e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9615629502940499e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2700,
"real_time": 2.5894950397304018e+05,
"cpu_time": 5.2144215629629832e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9544389322584337e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2700,
"real_time": 2.5829415012763263e+05,
"cpu_time": 5.2226520629628957e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9644722867087931e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2700,
"real_time": 2.5846772655818821e+05,
"cpu_time": 5.2174145037034346e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9618099080910571e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5866766391468616e+05,
"cpu_time": 5.2237992199998524e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9587537599038528e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time_median",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5848383904236401e+05,
"cpu_time": 5.2226520629628963e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9615629502940499e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6012228740007333e+02,
"cpu_time": 8.3117010755999638e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.5088517053753048e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3922199704051487e-03,
"cpu_time": 1.5911218493577929e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3915621024908353e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2705,
"real_time": 2.5889696510312406e+05,
"cpu_time": 5.2309683142328158e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9104828408638891e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2705,
"real_time": 2.5889880129122373e+05,
"cpu_time": 5.2302892680223071e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9104267373424256e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2705,
"real_time": 2.5887455563783963e+05,
"cpu_time": 5.2286938853974658e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9111676114863576e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2705,
"real_time": 2.5855313069634690e+05,
"cpu_time": 5.2281130573013856e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9210025207748767e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2705,
"real_time": 2.5833906711710966e+05,
"cpu_time": 5.2237181552680105e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9275659808417810e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5871250396912885e+05,
"cpu_time": 5.2283565360443975e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9161291382618658e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time_median",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5887455563783963e+05,
"cpu_time": 5.2286938853974658e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9111676114863576e+06,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5487657209930185e+02,
"cpu_time": 2.8392120792381195e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.8033009666783009e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.8517299391804930e-04,
"cpu_time": 5.4304102248278849e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.8574705268030297e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2704,
"real_time": 2.5885460821258320e+05,
"cpu_time": 5.2290691013312386e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5823554497574091e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2704,
"real_time": 2.5823188318541003e+05,
"cpu_time": 5.2179243158283114e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5861712928217618e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2704,
"real_time": 2.5897555188162214e+05,
"cpu_time": 5.2249207655323972e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5816164770148974e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2704,
"real_time": 2.5826667911805675e+05,
"cpu_time": 5.2213778328405577e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5859575900333894e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2704,
"real_time": 2.5871419696551992e+05,
"cpu_time": 5.2312897041417728e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5832142371939074e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5860858387263841e+05,
"cpu_time": 5.2249163439348555e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5838630093642734e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time_median",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5871419696551995e+05,
"cpu_time": 5.2249207655323966e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5832142371939074e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4100949025589000e+02,
"cpu_time": 5.4606467489355941e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0890182854333754e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3186317528571790e-03,
"cpu_time": 1.0451165893353256e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3189387422286349e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2676,
"real_time": 2.6074049415361619e+05,
"cpu_time": 5.2619005530645186e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1418211530939471e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2676,
"real_time": 2.6146187396329912e+05,
"cpu_time": 5.2619774962631834e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1331527904331837e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2676,
"real_time": 2.6074796940068822e+05,
"cpu_time": 5.2585937892376666e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1417310818675842e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2676,
"real_time": 2.6090928507023543e+05,
"cpu_time": 5.2621406390131032e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1397886042249348e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2676,
"real_time": 2.6076602549976020e+05,
"cpu_time": 5.2535176233182533e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1415135404621691e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6092512961751985e+05,
"cpu_time": 5.2596260201793443e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1396014340163637e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time_median",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6076602549976017e+05,
"cpu_time": 5.2619005530645186e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1415135404621691e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0786996428838654e+02,
"cpu_time": 3.7217019104855927e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.6992817060376736e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1799168778403267e-03,
"cpu_time": 7.0759820112812678e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1782647523209129e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2657,
"real_time": 2.6347265469664295e+05,
"cpu_time": 5.3119289461801725e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2184821490731940e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2657,
"real_time": 2.6417914609527122e+05,
"cpu_time": 5.3152410726383619e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2018521303310670e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2657,
"real_time": 2.6367553573522024e+05,
"cpu_time": 5.3169307263834076e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2136974347338051e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2657,
"real_time": 2.6375646663073968e+05,
"cpu_time": 5.3176634362062346e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2117908270805269e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2657,
"real_time": 2.6420678520453535e+05,
"cpu_time": 5.3144677982684504e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2012033443109140e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6385811767248192e+05,
"cpu_time": 5.3152463959353254e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2094051771059014e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time_median",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6375646663073974e+05,
"cpu_time": 5.3152410726383608e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2117908270805269e+07,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2283087676397236e+02,
"cpu_time": 2.2522637662708502e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5964596729331752e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2235017804708638e-03,
"cpu_time": 4.2373647400301167e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2233796082338690e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2619,
"real_time": 2.6763668506516126e+05,
"cpu_time": 5.4008392859870160e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2243463556583060e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2619,
"real_time": 2.6838060158572282e+05,
"cpu_time": 5.4000471744940057e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2209526249807458e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2619,
"real_time": 2.6773288891577482e+05,
"cpu_time": 5.3989539251623326e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2239064140643689e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2619,
"real_time": 2.6771780530834635e+05,
"cpu_time": 5.3983248377244454e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2239753707176541e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2619,
"real_time": 2.6685805530920299e+05,
"cpu_time": 5.3827396449025464e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2279187136409424e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6766520723684167e+05,
"cpu_time": 5.3961809736540692e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2242198958124036e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time_median",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6771780530834640e+05,
"cpu_time": 5.3989539251623326e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2239753707176541e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.4116637683812371e+02,
"cpu_time": 7.5763136570856136e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4764070463576863e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0218032161321451e-03,
"cpu_time": 1.4040140043626540e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0228449601485360e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2534,
"real_time": 2.7651654883220221e+05,
"cpu_time": 5.5771938397789316e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3700570644605085e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2534,
"real_time": 2.7645996771247481e+05,
"cpu_time": 5.5694181176005490e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3705421273925295e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2534,
"real_time": 2.7584206404685596e+05,
"cpu_time": 5.5700695264408237e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3758522916529411e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2534,
"real_time": 2.7596280079363642e+05,
"cpu_time": 5.5778070994475961e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3748128302628544e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2534,
"real_time": 2.7578144888814399e+05,
"cpu_time": 5.5758506945541641e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3763744901703367e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7611256605466269e+05,
"cpu_time": 5.5740678555644129e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3735277607878339e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time_median",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7596280079363647e+05,
"cpu_time": 5.5758506945541641e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3748128302628544e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4968898466715228e+02,
"cpu_time": 4.0168064395597651e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.0049315819166333e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2664725465552462e-03,
"cpu_time": 7.2062388611755335e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2660191431336874e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2357,
"real_time": 2.9344090206876927e+05,
"cpu_time": 5.9024817225287796e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4667256362673891e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2357,
"real_time": 2.9434137738605752e+05,
"cpu_time": 5.9196606788289861e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4530606319778901e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2357,
"real_time": 2.9723320523955364e+05,
"cpu_time": 5.9148471616461151e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4097361159350675e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2357,
"real_time": 2.9356105611533148e+05,
"cpu_time": 5.9003363428088778e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4648974129765254e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2357,
"real_time": 2.9406122150625457e+05,
"cpu_time": 5.9109406618583994e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4573031196910864e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9452755246319331e+05,
"cpu_time": 5.9096533135342319e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4503445833695918e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time_median",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9406122150625457e+05,
"cpu_time": 5.9109406618583994e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4573031196910864e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5562460391138391e+03,
"cpu_time": 8.1703479898862247e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3371828762336932e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.2838725141286097e-03,
"cpu_time": 1.3825426901396350e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.2516896893051099e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2152,
"real_time": 3.2548742122083926e+05,
"cpu_time": 6.5495666310408060e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0538903474902177e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2152,
"real_time": 3.2558370108731772e+05,
"cpu_time": 6.5444220353161462e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0515086942173457e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2152,
"real_time": 3.2519872474679322e+05,
"cpu_time": 6.5489898745350866e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0610402209944391e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2152,
"real_time": 3.2557373765062325e+05,
"cpu_time": 6.5508490985134954e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0517550921539497e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2152,
"real_time": 3.2648921025482868e+05,
"cpu_time": 6.5554890241636336e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0291780483463311e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2566655899208051e+05,
"cpu_time": 6.5498633327138331e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0494744806404579e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time_median",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2557373765062325e+05,
"cpu_time": 6.5495666310408048e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0517550921539497e+08,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.8559127774655661e+02,
"cpu_time": 3.9711086923042524e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1984892651667765e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4910688995807065e-03,
"cpu_time": 6.0628878658738146e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4889037390567869e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1793,
"real_time": 3.9067731910383637e+05,
"cpu_time": 7.8485188455104001e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3419975370022745e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1793,
"real_time": 3.8991961099038069e+05,
"cpu_time": 7.8368048689348483e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3446053628037040e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1793,
"real_time": 3.8977746299662249e+05,
"cpu_time": 7.8322264528722956e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3450957271086326e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1793,
"real_time": 3.8996985316176823e+05,
"cpu_time": 7.8320678750696662e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3444321291741328e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1793,
"real_time": 3.8991471408018132e+05,
"cpu_time": 7.8338256999444612e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3446222496035028e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9005179206655780e+05,
"cpu_time": 7.8366887484663352e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3441506011384497e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time_median",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8991961099038069e+05,
"cpu_time": 7.8338256999444612e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3446053628037040e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5690219545736988e+02,
"cpu_time": 6.8816109993412692e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2285628547209133e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.1501232071372889e-04,
"cpu_time": 8.7812738520309656e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.1400684839954883e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1286,
"real_time": 5.3203970418908400e+05,
"cpu_time": 1.0667382791601680e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9708604296707561e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1286,
"real_time": 5.3484656196775590e+05,
"cpu_time": 1.0670331018662665e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9605174167001846e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1286,
"real_time": 5.3309298421525653e+05,
"cpu_time": 1.0679353429237213e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9669664224592342e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1286,
"real_time": 5.3422035240969423e+05,
"cpu_time": 1.0659408328148904e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9628155222282615e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1286,
"real_time": 5.3249854372863541e+05,
"cpu_time": 1.0673157037324575e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9691621927408705e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3333962930208526e+05,
"cpu_time": 1.0669926520995009e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9660643967598619e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time_median",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3309298421525653e+05,
"cpu_time": 1.0670331018662665e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9669664224592342e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1730924186785892e+03,
"cpu_time": 7.3581484249752680e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3225020381070962e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1995223197902401e-03,
"cpu_time": 6.8961566047308592e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1985556756079403e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 892,
"real_time": 7.8526397617826145e+05,
"cpu_time": 1.5736686524663193e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.6706331419995370e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 892,
"real_time": 7.8426828069430706e+05,
"cpu_time": 1.5720164360986049e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.6740237385903282e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 892,
"real_time": 7.8434541458921775e+05,
"cpu_time": 1.5718973968609849e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.6737607704359865e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 892,
"real_time": 7.8462163669489441e+05,
"cpu_time": 1.5724869080718532e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.6728194863883061e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 892,
"real_time": 7.8537879013686103e+05,
"cpu_time": 1.5731990067264389e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.6702427240676413e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.8477561965870834e+05,
"cpu_time": 1.5726536800448406e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.6722959722963600e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time_median",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.8462163669489429e+05,
"cpu_time": 1.5724869080718532e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.6728194863883061e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.1683815046706991e+02,
"cpu_time": 7.6377470472420123e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7596668608347434e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.5858079369468438e-04,
"cpu_time": 4.8565982098641323e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.5848501778140417e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 522,
"real_time": 1.3328127173164510e+06,
"cpu_time": 2.6859470402298719e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1469567670730309e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 522,
"real_time": 1.3324801608923664e+06,
"cpu_time": 2.6866224904213916e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1477421751563339e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 522,
"real_time": 1.3323164914317173e+06,
"cpu_time": 2.6857274463601289e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1481288620039296e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 522,
"real_time": 1.3320479728013875e+06,
"cpu_time": 2.6863781072795545e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1487634722187166e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 522,
"real_time": 1.3323342585954031e+06,
"cpu_time": 2.6872896436782368e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1480868805563803e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3323983202074650e+06,
"cpu_time": 2.6863929455938367e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1479356314016786e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time_median",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3323342585954028e+06,
"cpu_time": 2.6863781072795545e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1480868805563803e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7926958577383056e+02,
"cpu_time": 6.1210686871404073e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.5976046271355182e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0959917281368687e-04,
"cpu_time": 2.2785455482899667e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0958511861939846e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 277,
"real_time": 2.5184852792293048e+06,
"cpu_time": 5.0569727689530449e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3308147834666095e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 277,
"real_time": 2.5246826022365787e+06,
"cpu_time": 5.0616007509025401e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3226386527037725e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 277,
"real_time": 2.5194781884510703e+06,
"cpu_time": 5.0579627075812463e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3295021320097895e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 277,
"real_time": 2.5228601779506309e+06,
"cpu_time": 5.0597470758126676e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3250388084583554e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 277,
"real_time": 2.5199888289203388e+06,
"cpu_time": 5.0583555379061075e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3288274549986815e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5210990153575847e+06,
"cpu_time": 5.0589277682311218e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3273643663274422e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time_median",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5199888289203392e+06,
"cpu_time": 5.0583555379061075e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3288274549986815e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5804553344245492e+03,
"cpu_time": 1.7956136163185595e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4042854483371396e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0235438269998076e-03,
"cpu_time": 3.5493956399112699e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0231177212775763e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 139,
"real_time": 4.9661736325662341e+06,
"cpu_time": 9.8941803669064194e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3782983120005202e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 139,
"real_time": 4.9629424323441740e+06,
"cpu_time": 9.8904412086335644e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3804978052255030e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 139,
"real_time": 4.9611536832861332e+06,
"cpu_time": 9.8893235611517765e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3817166471826019e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 139,
"real_time": 4.9632509346220559e+06,
"cpu_time": 9.8926301942444406e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3802876826088905e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 139,
"real_time": 4.9636135373612959e+06,
"cpu_time": 9.8897967482010331e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3800407452589321e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9634268440359784e+06,
"cpu_time": 9.8912744158274475e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3801682384552898e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time_median",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9632509346220559e+06,
"cpu_time": 9.8904412086335625e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3802876826088905e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8036463241908982e+03,
"cpu_time": 2.0595057968142837e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2281419102367610e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.6338730898353983e-04,
"cpu_time": 2.0821440294071524e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.6333750973235938e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 70,
"real_time": 9.8072688095271587e+06,
"cpu_time": 1.9577797800000750e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4213839399817338e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 70,
"real_time": 9.8084711735802032e+06,
"cpu_time": 1.9568157300000168e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4209645322077498e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 70,
"real_time": 9.8057991159813739e+06,
"cpu_time": 1.9553880385714300e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4218967371372504e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 70,
"real_time": 9.8007020141397212e+06,
"cpu_time": 1.9545879814285982e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4236763806909108e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 70,
"real_time": 9.8025008769971989e+06,
"cpu_time": 1.9562303328572333e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4230480997701001e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.8049483980451338e+06,
"cpu_time": 1.9561603725714706e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4221939379575491e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time_median",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.8057991159813739e+06,
"cpu_time": 1.9562303328572329e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4218967371372504e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2611391156068466e+03,
"cpu_time": 1.2375158520325886e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1383202985451855e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.3260135425669746e-04,
"cpu_time": 6.3262494700565481e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3262881040124905e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 33,
"real_time": 2.1265816564361256e+07,
"cpu_time": 4.2314153909091361e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1557153611710229e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 33,
"real_time": 2.1225191144780681e+07,
"cpu_time": 4.2187754454547837e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1617554603979249e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 33,
"real_time": 2.1283630563905746e+07,
"cpu_time": 4.2343828030301332e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1530740866085067e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 33,
"real_time": 2.1269821815870024e+07,
"cpu_time": 4.2339913121209480e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1551211185948043e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 33,
"real_time": 2.1245991303162143e+07,
"cpu_time": 4.2218214606061168e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1586600522618055e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1258090278415971e+07,
"cpu_time": 4.2280772824242242e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1568652158068132e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time_median",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1265816564361256e+07,
"cpu_time": 4.2314153909091368e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1557153611710229e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2794565384289559e+04,
"cpu_time": 7.2721692643859147e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3864668693610453e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0722771935649186e-03,
"cpu_time": 1.7199707523359933e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0727309016566777e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 18,
"real_time": 3.9377885146273509e+07,
"cpu_time": 7.7484670388887227e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4084544535958042e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 18,
"real_time": 3.9347022357914180e+07,
"cpu_time": 7.7484118833334982e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4111279572596097e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 18,
"real_time": 3.9294177252385348e+07,
"cpu_time": 7.7485219777776778e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4157154414488297e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 18,
"real_time": 3.9349724435144000e+07,
"cpu_time": 7.7533814277779177e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4108937210276256e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 18,
"real_time": 3.9344818227820925e+07,
"cpu_time": 7.7566624666663602e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4113190515414286e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9342725483907595e+07,
"cpu_time": 7.7510889588888377e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4115021249746599e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time_median",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9347022357914187e+07,
"cpu_time": 7.7485219777776763e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4111279572596097e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.0269459278526956e+04,
"cpu_time": 3.7732609425167619e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6260240505829342e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.6937880907381742e-04,
"cpu_time": 4.8680397845126533e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.6975594749261367e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 9,
"real_time": 7.4135813448164195e+07,
"cpu_time": 1.4447255944444096e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.6208607353811560e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 9,
"real_time": 7.4383102357387543e+07,
"cpu_time": 1.4493691677777559e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.6088230726146860e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 9,
"real_time": 7.4213820199171707e+07,
"cpu_time": 1.4459334366665643e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.6170548191642075e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 9,
"real_time": 7.4103632734881505e+07,
"cpu_time": 1.4441456622221771e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.6224331533161678e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 9,
"real_time": 7.4176327221923411e+07,
"cpu_time": 1.4449403644444677e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.6188830864715796e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.4202539192305669e+07,
"cpu_time": 1.4458228451110750e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.6176109733895593e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time_median",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.4176327221923411e+07,
"cpu_time": 1.4449403644444677e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.6188830864715796e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0914691628988137e+05,
"cpu_time": 2.0847247146067693e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.3143473611121811e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4709323626650123e-03,
"cpu_time": 1.4418949884877567e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4690212408695915e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 5,
"real_time": 1.4928273856639862e+08,
"cpu_time": 2.8460493640000093e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.5963361682382874e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 5,
"real_time": 1.4890683293342590e+08,
"cpu_time": 2.8406827800001794e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6054148854272337e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 5,
"real_time": 1.4841701090335846e+08,
"cpu_time": 2.8378401920001578e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6173138694295816e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 5,
"real_time": 1.4853525161743164e+08,
"cpu_time": 2.8366371540000731e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6144343255483098e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"family_index": 3,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 5,
"real_time": 1.4880872070789337e+08,
"cpu_time": 2.8359524320001131e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6077919993268404e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4879011094570160e+08,
"cpu_time": 2.8394323844001067e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6082582495940509e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time_median",
"family_index": 3,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4880872070789337e+08,
"cpu_time": 2.8378401920001578e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6077919993268404e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3941465686100366e+05,
"cpu_time": 4.1172310632484750e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.2247537615663605e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2811640820999670e-03,
"cpu_time": 1.4500190551705395e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2794249171304995e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 2.9239414632320404e+08,
"cpu_time": 5.1977951649996614e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6722411768569293e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 2.9252967238426208e+08,
"cpu_time": 5.1995759999999791e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6705398643784442e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 2.9191213846206665e+08,
"cpu_time": 5.1884439349998957e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6783048134174471e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 2.9218535125255585e+08,
"cpu_time": 5.1905691700000036e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6748653530953074e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"family_index": 3,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 2.9234902560710907e+08,
"cpu_time": 5.2007121849999297e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6728079451272497e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time_mean",
"family_index": 3,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9227406680583954e+08,
"cpu_time": 5.1954192909998941e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6737518305750756e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time_median",
"family_index": 3,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9234902560710907e+08,
"cpu_time": 5.1977951649996614e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6728079451272497e+09,
"dst_gpu": 3.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time_stddev",
"family_index": 3,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.3676713216210334e+05,
"cpu_time": 5.5479049846219795e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9773858669913779e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time_cv",
"family_index": 3,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/3/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.1008600848391378e-04,
"cpu_time": 1.0678454757699156e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.1044828401631824e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2672,
"real_time": 2.6210799488379454e+05,
"cpu_time": 5.2909412724548473e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9067865917405146e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2672,
"real_time": 2.6267171223682049e+05,
"cpu_time": 5.2876738547903509e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8984022728598136e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2672,
"real_time": 2.6273188433004473e+05,
"cpu_time": 5.2920086302393849e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8975094424156281e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2672,
"real_time": 2.6194643153698172e+05,
"cpu_time": 5.2882801422156719e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9091962199738203e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2672,
"real_time": 2.6253015074800857e+05,
"cpu_time": 5.2889341953594529e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9005043690501428e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6239763474712998e+05,
"cpu_time": 5.2895676190119411e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9024797792079840e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time_median",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6253015074800857e+05,
"cpu_time": 5.2889341953594517e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9005043690501428e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.5066983467558299e+02,
"cpu_time": 1.8364792771678245e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.2175607779106331e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3364062332860585e-03,
"cpu_time": 3.4718892156082641e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3369859866306719e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2672,
"real_time": 2.6238727516461228e+05,
"cpu_time": 5.2869500748502044e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8052565571831129e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2672,
"real_time": 2.6187301890007540e+05,
"cpu_time": 5.2808297492513852e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8205842228498869e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2672,
"real_time": 2.6251979161424754e+05,
"cpu_time": 5.2868573166169075e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8013165689594075e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2672,
"real_time": 2.6191266086592106e+05,
"cpu_time": 5.2882357335329533e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8194005330976220e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2672,
"real_time": 2.6251463823210070e+05,
"cpu_time": 5.2875108982032584e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8014697153355442e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6224147695539141e+05,
"cpu_time": 5.2860767544909415e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8096055194851151e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time_median",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6238727516461234e+05,
"cpu_time": 5.2869500748502044e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8052565571831129e+06,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2296075978248228e+02,
"cpu_time": 2.9841660630138290e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.6214045526838891e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2315395853167023e-03,
"cpu_time": 5.6453324490200469e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2319962293458101e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2674,
"real_time": 2.6259252490864461e+05,
"cpu_time": 5.2875673111442686e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5598311495824145e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2674,
"real_time": 2.6249708045307454e+05,
"cpu_time": 5.2833980067313428e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5603983072612589e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2674,
"real_time": 2.6203233973494411e+05,
"cpu_time": 5.2881074121163622e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5631658306540573e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2674,
"real_time": 2.6184751134276635e+05,
"cpu_time": 5.2831273223633715e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5642692111128036e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2674,
"real_time": 2.6256673642242269e+05,
"cpu_time": 5.2874738107706129e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5599843513346914e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6230723857237044e+05,
"cpu_time": 5.2859347726251918e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5615297699890450e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time_median",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6249708045307454e+05,
"cpu_time": 5.2874738107706117e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5603983072612589e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4339695104597570e+02,
"cpu_time": 2.4531174522640762e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0454260057312938e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3091402010670498e-03,
"cpu_time": 4.6408394310279514e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3098860137297566e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2673,
"real_time": 2.6415794921400957e+05,
"cpu_time": 5.3224138346426480e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1011748934207499e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2673,
"real_time": 2.6437278089695045e+05,
"cpu_time": 5.3231657201643160e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0986548510049339e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2673,
"real_time": 2.6347334763870336e+05,
"cpu_time": 5.3197379274222930e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1092328971481219e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2673,
"real_time": 2.6409066822435579e+05,
"cpu_time": 5.3193167227833893e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1019649634270921e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2673,
"real_time": 2.6421558938833739e+05,
"cpu_time": 5.3161616647961095e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1004983540012110e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6406206707247131e+05,
"cpu_time": 5.3201591739617509e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1023051918004222e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time_median",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6415794921400957e+05,
"cpu_time": 5.3197379274222930e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1011748934207499e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4522245175559840e+02,
"cpu_time": 2.7834361408645873e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0612831069749373e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3073534399806572e-03,
"cpu_time": 5.2318662841658030e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3091178513671546e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2642,
"real_time": 2.6712809677401814e+05,
"cpu_time": 5.3797061809238326e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1333870146427698e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2642,
"real_time": 2.6718968690149515e+05,
"cpu_time": 5.3818597918241704e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1319732022592217e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2642,
"real_time": 2.6662616702464648e+05,
"cpu_time": 5.3811820590460917e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1449332534887649e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2642,
"real_time": 2.6742393267208769e+05,
"cpu_time": 5.3829309538224945e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1266019971704938e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2642,
"real_time": 2.6710896226129780e+05,
"cpu_time": 5.3769828993188334e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1338263835462205e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6709536912670906e+05,
"cpu_time": 5.3805323769870843e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1341443702214934e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time_median",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6712809677401814e+05,
"cpu_time": 5.3811820590460917e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1333870146427698e+07,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9079904176498468e+02,
"cpu_time": 2.3031868888148787e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6834883626553885e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0887461011240172e-03,
"cpu_time": 4.2805929366130589e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0895551130326688e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2603,
"real_time": 2.7117865548576106e+05,
"cpu_time": 5.4593341029581102e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2083546893210617e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2603,
"real_time": 2.7142747287578380e+05,
"cpu_time": 5.4633009412217594e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2072469913535969e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2603,
"real_time": 2.7087875207393424e+05,
"cpu_time": 5.4605154821361834e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2096925192218927e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2603,
"real_time": 2.7075932143650349e+05,
"cpu_time": 5.4596611409912386e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2102261087873390e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2603,
"real_time": 2.7134670884061506e+05,
"cpu_time": 5.4626064809833269e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2076063181310751e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7111818214251951e+05,
"cpu_time": 5.4610836296581232e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2086253253629930e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time_median",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7117865548576100e+05,
"cpu_time": 5.4605154821361834e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2083546893210617e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9053829299088511e+02,
"cpu_time": 1.7778256378384444e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2954569224794779e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0716296881857852e-03,
"cpu_time": 3.2554448135227340e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0718432712721838e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2505,
"real_time": 2.8026273900256335e+05,
"cpu_time": 5.6345172335328721e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3383772039493483e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2505,
"real_time": 2.7922807176998944e+05,
"cpu_time": 5.6299891497008514e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3470419569413653e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2505,
"real_time": 2.8023687428320770e+05,
"cpu_time": 5.6409221157684142e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3385930266182327e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2505,
"real_time": 2.7935051128264522e+05,
"cpu_time": 5.6346426227545075e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3460132469094017e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2505,
"real_time": 2.8001389841729414e+05,
"cpu_time": 5.6328924231538281e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3404552549150318e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7981841895114002e+05,
"cpu_time": 5.6345927089820954e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3420961378666759e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time_median",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8001389841729414e+05,
"cpu_time": 5.6345172335328721e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3404552549150318e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9451612086650158e+02,
"cpu_time": 4.0047880133561773e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.1412445092025172e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7672750876090491e-03,
"cpu_time": 7.1075022103587917e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7681787020812116e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2353,
"real_time": 2.9915434803251264e+05,
"cpu_time": 5.9723498725032876e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.3814171801960528e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2353,
"real_time": 2.9694819546835410e+05,
"cpu_time": 5.9705999787500978e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4139685642227918e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2353,
"real_time": 2.9644881983630400e+05,
"cpu_time": 5.9681155376114929e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4214040073553550e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2353,
"real_time": 2.9904759228809370e+05,
"cpu_time": 5.9739783977899782e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.3829812839198202e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2353,
"real_time": 2.9658338249106111e+05,
"cpu_time": 5.9639090055248444e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4193979750011933e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9763646762326511e+05,
"cpu_time": 5.9697905584359402e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4038338021390432e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time_median",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9694819546835416e+05,
"cpu_time": 5.9705999787500966e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4139685642227918e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3498562772749333e+03,
"cpu_time": 3.9414974184637157e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9943679738904755e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.5352516378588418e-03,
"cpu_time": 6.6024048580631811e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5287085378239410e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2131,
"real_time": 3.2854220429852739e+05,
"cpu_time": 6.6106657015484560e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9790053323500812e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2131,
"real_time": 3.2835765109156666e+05,
"cpu_time": 6.6150664148288826e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9834899271738875e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2131,
"real_time": 3.2846915268709383e+05,
"cpu_time": 6.6150161379633681e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9807798648819697e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2131,
"real_time": 3.2897392792462453e+05,
"cpu_time": 6.6110278320038947e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9685342134487689e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2131,
"real_time": 3.2819028980815841e+05,
"cpu_time": 6.6101279727823054e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9875611235553205e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2850664516199421e+05,
"cpu_time": 6.6123808118253818e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9798740922820055e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time_median",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2846915268709383e+05,
"cpu_time": 6.6110278320038947e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9807798648819697e+08,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9296043290740977e+02,
"cpu_time": 2.4497371663926964e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.1121855217647413e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.9179454121223107e-04,
"cpu_time": 3.7047732671591764e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.9126538082142455e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1780,
"real_time": 3.9259472406035021e+05,
"cpu_time": 7.8952351910109760e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3354433156350970e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1780,
"real_time": 3.9425793607795110e+05,
"cpu_time": 7.9301382134831382e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3298096297453854e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1780,
"real_time": 3.9469622825390106e+05,
"cpu_time": 7.9341768146067532e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3283329367483463e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1780,
"real_time": 3.9483969100800686e+05,
"cpu_time": 7.9405486460677558e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3278502945373039e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1780,
"real_time": 3.9264099884011754e+05,
"cpu_time": 7.8972692415729573e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3352859267085576e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9380591564806539e+05,
"cpu_time": 7.9194736213483172e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3313444206749382e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time_median",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9425793607795110e+05,
"cpu_time": 7.9301382134831371e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3298096297453854e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1056318025670630e+03,
"cpu_time": 2.1532591986926718e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7406532120045559e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.8075550890280152e-03,
"cpu_time": 2.7189423207221596e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8096810666831014e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1282,
"real_time": 5.3370554238418338e+05,
"cpu_time": 1.0687280085803487e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9647088454726813e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1282,
"real_time": 5.3548739915938873e+05,
"cpu_time": 1.0688587917317213e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9581711944035673e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1282,
"real_time": 5.3368358152363496e+05,
"cpu_time": 1.0685629219969132e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9647896924360642e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1282,
"real_time": 5.3608136652211857e+05,
"cpu_time": 1.0700690967238075e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9560015801383691e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1282,
"real_time": 5.3363714420546126e+05,
"cpu_time": 1.0688525156006278e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9649606692225997e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3451900675895740e+05,
"cpu_time": 1.0690142669266840e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9617263963346562e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time_median",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3370554238418327e+05,
"cpu_time": 1.0688525156006278e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9647088454726813e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.1743182114002141e+03,
"cpu_time": 6.0180104990449968e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.3055861457227869e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1969624962836459e-03,
"cpu_time": 5.6294950266157022e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1947944187158124e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 902,
"real_time": 7.7461842012575141e+05,
"cpu_time": 1.5524207882483697e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7073355674391899e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 902,
"real_time": 7.7366675397364656e+05,
"cpu_time": 1.5512527771619172e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7106657863075695e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 902,
"real_time": 7.7464627371760213e+05,
"cpu_time": 1.5534486662971291e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7072382210470920e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 902,
"real_time": 7.7428830679900490e+05,
"cpu_time": 1.5521638747229457e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7084898242488809e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 902,
"real_time": 7.7387926091559790e+05,
"cpu_time": 1.5518018458980366e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7099214385443039e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7421980310632079e+05,
"cpu_time": 1.5522175904656800e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7087301675174074e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time_median",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7428830679900490e+05,
"cpu_time": 1.5521638747229460e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7084898242488809e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.3797767996040949e+02,
"cpu_time": 8.1600102285865421e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5325081801543508e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.6570198566758135e-04,
"cpu_time": 5.2570015175117698e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.6576627621750817e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 524,
"real_time": 1.3333029941947178e+06,
"cpu_time": 2.6911354179387344e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1457995806371503e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 524,
"real_time": 1.3362325057885004e+06,
"cpu_time": 2.6964610400765310e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1389028345220308e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 524,
"real_time": 1.3372660856711755e+06,
"cpu_time": 2.6985391526717846e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1364767602663560e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 524,
"real_time": 1.3342886889452925e+06,
"cpu_time": 2.6921738034349857e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1434756471745610e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 524,
"real_time": 1.3339588823390570e+06,
"cpu_time": 2.6917124389312956e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1442528368231359e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3350098313877487e+06,
"cpu_time": 2.6940043706106665e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1417815318846469e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time_median",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3342886889452927e+06,
"cpu_time": 2.6921738034349857e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1434756471745610e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6675917974019671e+03,
"cpu_time": 3.2952348034845368e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9226773677986823e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2491232335483985e-03,
"cpu_time": 1.2231735179915784e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2485519212552003e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 280,
"real_time": 2.4996534006537073e+06,
"cpu_time": 5.0262037357141152e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3559084622716970e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 280,
"real_time": 2.5323262172085899e+06,
"cpu_time": 5.0860909964285381e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3126095457191339e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 280,
"real_time": 2.5301398925616271e+06,
"cpu_time": 5.0834442464288743e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3154720119080043e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 280,
"real_time": 2.5321358981143152e+06,
"cpu_time": 5.0852489392858455e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3128585263717508e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 280,
"real_time": 2.5296513373697442e+06,
"cpu_time": 5.0839266892856881e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3161123337741175e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5247813491815967e+06,
"cpu_time": 5.0729829214286115e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3225921760089412e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time_median",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5301398925616271e+06,
"cpu_time": 5.0839266892856872e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3154720119080043e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4096621872562047e+04,
"cpu_time": 2.6171427244421859e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8688611942241188e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.5833040263591309e-03,
"cpu_time": 5.1589819342525347e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.6247083458463238e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 143,
"real_time": 4.8887445428571505e+06,
"cpu_time": 9.7742440419580340e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.4318045978722420e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 143,
"real_time": 4.8867170926886834e+06,
"cpu_time": 9.7756836713285018e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.4332284193618283e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 143,
"real_time": 4.8900380033765221e+06,
"cpu_time": 9.7789685244755987e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.4308968536472521e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 143,
"real_time": 4.8905627417762382e+06,
"cpu_time": 9.7836131538464837e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.4305287317317119e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 143,
"real_time": 4.8853788830965133e+06,
"cpu_time": 9.7765085874130707e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.4341688539346309e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.8882882527590226e+06,
"cpu_time": 9.7778035958043393e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.4321254913095331e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time_median",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.8887445428571505e+06,
"cpu_time": 9.7765085874130707e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.4318045978722420e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.2009148054772932e+03,
"cpu_time": 3.6725186652165075e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5454728535694182e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.5024243491268427e-04,
"cpu_time": 3.7559750809398418e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5029613791299351e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 72,
"real_time": 9.6061401224384699e+06,
"cpu_time": 1.9146057736110024e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4930192119123883e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 72,
"real_time": 9.6047757478016950e+06,
"cpu_time": 1.9133488097221769e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4935154011981816e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 72,
"real_time": 9.6215759404003620e+06,
"cpu_time": 1.9153397486112073e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4874153888976912e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 72,
"real_time": 9.6091668173256852e+06,
"cpu_time": 1.9141139236111827e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4919189808943801e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 72,
"real_time": 9.6088400524523519e+06,
"cpu_time": 1.9142189819444552e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4920377295109925e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.6100997360837143e+06,
"cpu_time": 1.9143254475000050e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4915813424827271e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time_median",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.6088400524523519e+06,
"cpu_time": 1.9142189819444552e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4920377295109925e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.6742751867628203e+03,
"cpu_time": 7.2754520305726228e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4230925324469144e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.9450633916966046e-04,
"cpu_time": 3.8005303852978233e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.9398140692433297e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 34,
"real_time": 2.0629645215676110e+07,
"cpu_time": 4.1014664558825672e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.2530304471259222e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 34,
"real_time": 2.0510392756584812e+07,
"cpu_time": 4.0887099499998920e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.2719443648125587e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 34,
"real_time": 2.0542919800123747e+07,
"cpu_time": 4.0919712411764793e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.2667636661656899e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 34,
"real_time": 2.0581216660930831e+07,
"cpu_time": 4.0949044176470041e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.2606849782302837e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 34,
"real_time": 2.0591362817760777e+07,
"cpu_time": 4.0980867970588140e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.2590783132681360e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0571107450215258e+07,
"cpu_time": 4.0950277723529518e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.2623003539205179e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time_median",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0581216660930831e+07,
"cpu_time": 4.0949044176470049e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.2606849782302837e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5880180036624304e+04,
"cpu_time": 5.0021684355874742e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.2775383692234838e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2303213450058671e-03,
"cpu_time": 1.2215224691170510e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2307996136767707e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 18,
"real_time": 3.7948468493090734e+07,
"cpu_time": 7.5104685166669086e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.5368417575122161e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 18,
"real_time": 3.7882761615845889e+07,
"cpu_time": 7.4784475888887107e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.5429763373918962e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 18,
"real_time": 3.7798263132572174e+07,
"cpu_time": 7.4877012722222641e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.5508967046779346e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 18,
"real_time": 3.7883686108721629e+07,
"cpu_time": 7.4935604833336174e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.5428898765239277e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 18,
"real_time": 3.7976041022274226e+07,
"cpu_time": 7.5170267055556104e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.5342738312631583e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7897844074500933e+07,
"cpu_time": 7.4974409133334234e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.5415757014738269e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time_median",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7883686108721629e+07,
"cpu_time": 7.4935604833336174e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.5428898765239277e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.8959928487404395e+04,
"cpu_time": 1.5999893945024014e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.4478188512519486e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.8196266877830967e-03,
"cpu_time": 2.1340473542872289e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.8206073778314800e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 9,
"real_time": 7.5686482919587031e+07,
"cpu_time": 1.4742840155555665e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5466763105533490e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 9,
"real_time": 7.5437342955006495e+07,
"cpu_time": 1.4715383355556041e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5583895917450914e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 9,
"real_time": 7.5528899828592941e+07,
"cpu_time": 1.4732013311110374e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5540760769611864e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 9,
"real_time": 7.5280667179160655e+07,
"cpu_time": 1.4688065666666716e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5657953902181787e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 9,
"real_time": 7.5222993062602147e+07,
"cpu_time": 1.4672361566666344e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5685293162504501e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5431277188989863e+07,
"cpu_time": 1.4710132811111030e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5586933371456513e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time_median",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5437342955006495e+07,
"cpu_time": 1.4715383355556041e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5583895917450914e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8759170462199819e+05,
"cpu_time": 2.9536928787552851e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.8459867143106200e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.4869220250904028e-03,
"cpu_time": 2.0079308029933404e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4857400951006892e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 5,
"real_time": 1.4794081449508667e+08,
"cpu_time": 2.8233237340000415e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6289573896987720e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 5,
"real_time": 1.4788330495357513e+08,
"cpu_time": 2.8261807259998477e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6303686353813868e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 5,
"real_time": 1.4763534367084503e+08,
"cpu_time": 2.8206401200000072e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6364660294147511e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 5,
"real_time": 1.4812240898609161e+08,
"cpu_time": 2.8277416559999436e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6245083757070889e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"family_index": 4,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 5,
"real_time": 1.4777485132217407e+08,
"cpu_time": 2.8257249539999521e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6330330039008532e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4787134468555453e+08,
"cpu_time": 2.8247222379999590e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6306666868205705e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time_median",
"family_index": 4,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4788330495357513e+08,
"cpu_time": 2.8257249539999521e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6303686353813868e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8235256617981344e+05,
"cpu_time": 2.7779944418170396e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4768057283737473e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2331839313937569e-03,
"cpu_time": 9.8345756069240817e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2330533520536840e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 2.8911456465721130e+08,
"cpu_time": 5.1522424050000381e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.7138973793073416e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 2.8797766566276550e+08,
"cpu_time": 5.1386286350003731e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.7285593711888714e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 2.8774751722812653e+08,
"cpu_time": 5.1387350249996191e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.7315415762518511e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 2.8883863985538483e+08,
"cpu_time": 5.1473340500001544e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.7174452301035590e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"family_index": 4,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 2.8901241719722748e+08,
"cpu_time": 5.1535635850001425e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.7152100052063107e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time_mean",
"family_index": 4,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8853816092014313e+08,
"cpu_time": 5.1461007400000656e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.7213307124115868e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time_median",
"family_index": 4,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8883863985538483e+08,
"cpu_time": 5.1473340500001544e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.7174452301035590e+09,
"dst_gpu": 4.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time_stddev",
"family_index": 4,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.2982542350366875e+05,
"cpu_time": 7.1592818878905941e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.1291100155429067e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time_cv",
"family_index": 4,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/4/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1828149922879059e-03,
"cpu_time": 1.3912051569924190e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1844632051728841e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2697,
"real_time": 2.5976254703345112e+05,
"cpu_time": 5.2154636262512952e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9420617471391424e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2697,
"real_time": 2.5918531072476908e+05,
"cpu_time": 5.2125367259918887e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9508411843887004e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2697,
"real_time": 2.5999985999073097e+05,
"cpu_time": 5.2141775454208732e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9384636593131470e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2697,
"real_time": 2.5964846362231707e+05,
"cpu_time": 5.2097619651462726e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9437937960977252e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2697,
"real_time": 2.5909418691217992e+05,
"cpu_time": 5.2122385539486952e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9522307011352796e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5953807365668967e+05,
"cpu_time": 5.2128356833518052e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9454782176147993e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time_median",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5964846362231710e+05,
"cpu_time": 5.2125367259918881e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9437937960977252e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8642527989137517e+02,
"cpu_time": 2.1564067508940693e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.8751812914598249e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4888963089189321e-03,
"cpu_time": 4.1367249648420148e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4890923146476294e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2692,
"real_time": 2.5897404285532492e+05,
"cpu_time": 5.2137402414561744e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9081284649987454e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2692,
"real_time": 2.5913767025523706e+05,
"cpu_time": 5.2064162704308273e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9031350323664909e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2692,
"real_time": 2.5981179458251083e+05,
"cpu_time": 5.2134088930161367e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8826290518908594e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2692,
"real_time": 2.5951443440054252e+05,
"cpu_time": 5.2112523031207465e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8916612277491055e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2692,
"real_time": 2.5897208306046529e+05,
"cpu_time": 5.2123088224368542e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9081883104822123e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5928200503081613e+05,
"cpu_time": 5.2114253060921479e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8987484174974831e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time_median",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5913767025523708e+05,
"cpu_time": 5.2123088224368542e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.9031350323664909e+06,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6960290772187170e+02,
"cpu_time": 2.9662481450342273e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1251682838545476e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4254861523380451e-03,
"cpu_time": 5.6918174411263033e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4244893296791804e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2693,
"real_time": 2.5917411573441140e+05,
"cpu_time": 5.2114975232082012e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5804047361725640e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2693,
"real_time": 2.5971918120877206e+05,
"cpu_time": 5.2113490345337644e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5770879843901407e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2693,
"real_time": 2.5964437518917257e+05,
"cpu_time": 5.2112324136650370e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5775423584723230e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2693,
"real_time": 2.5908630406350864e+05,
"cpu_time": 5.2147729372445890e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5809403800040184e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2693,
"real_time": 2.5974781119687960e+05,
"cpu_time": 5.2115274118083867e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5769141542045094e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5947435747854886e+05,
"cpu_time": 5.2120758640919963e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5785779226487113e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time_median",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5964437518917251e+05,
"cpu_time": 5.2114975232082017e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5775423584723230e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1794345985809144e+02,
"cpu_time": 1.5123798697329639e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9351283559253246e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2253367267105626e-03,
"cpu_time": 2.9016842984814036e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2258681235566464e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2673,
"real_time": 2.6153909517676849e+05,
"cpu_time": 5.2473021436586895e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1322277055608869e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2673,
"real_time": 2.6219454171499069e+05,
"cpu_time": 5.2483576169096457e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1243976119475525e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2673,
"real_time": 2.6213755821148920e+05,
"cpu_time": 5.2482122334457713e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1250767939902760e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2673,
"real_time": 2.6159147426483923e+05,
"cpu_time": 5.2471168237933470e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1316005320977293e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2673,
"real_time": 2.6138161112729629e+05,
"cpu_time": 5.2391220800597116e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1341148922715873e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6176885609907680e+05,
"cpu_time": 5.2460221795734332e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1294835071736068e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time_median",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6159147426483926e+05,
"cpu_time": 5.2473021436586895e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1316005320977293e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.7126895773648857e+02,
"cpu_time": 3.8954630919973772e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4369921839715920e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4183083628404103e-03,
"cpu_time": 7.4255558948363551e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4178033448014116e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2649,
"real_time": 2.6409956265130860e+05,
"cpu_time": 5.3011146055119392e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2037209889786296e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2649,
"real_time": 2.6471420513930428e+05,
"cpu_time": 5.3003290977723768e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1893165088658601e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2649,
"real_time": 2.6487407680877222e+05,
"cpu_time": 5.3018533937335189e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1855807851776108e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2649,
"real_time": 2.6408597298628144e+05,
"cpu_time": 5.2963718195548689e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2040402277826034e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2649,
"real_time": 2.6428934354398353e+05,
"cpu_time": 5.2946897923738603e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1992662209906109e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6441263222593005e+05,
"cpu_time": 5.2988717417893128e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1963849463590637e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time_median",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6428934354398359e+05,
"cpu_time": 5.3003290977723780e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1992662209906109e+07,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6186884422269640e+02,
"cpu_time": 3.1536837399065394e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.4766636405486803e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3685762332016494e-03,
"cpu_time": 5.9516136520821120e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3680014579354834e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2605,
"real_time": 2.6867963607608917e+05,
"cpu_time": 5.3827026602687465e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2195937317229436e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2605,
"real_time": 2.6928469956085633e+05,
"cpu_time": 5.3898495547027094e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2168533917239766e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2605,
"real_time": 2.6912659802384704e+05,
"cpu_time": 5.3873104145871825e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2175682463424318e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2605,
"real_time": 2.6773886519149947e+05,
"cpu_time": 5.3811010134355433e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2238790948995313e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2605,
"real_time": 2.6822672599806823e+05,
"cpu_time": 5.3836037159306568e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2216530578028975e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6861130497007206e+05,
"cpu_time": 5.3849134717849689e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2199095044983561e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time_median",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6867963607608911e+05,
"cpu_time": 5.3836037159306568e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2195937317229436e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.3888741165392003e+02,
"cpu_time": 3.5793936624947781e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9033882606361830e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3784829596993438e-03,
"cpu_time": 6.6470773973426468e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3800029837705845e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2519,
"real_time": 2.7654531185188761e+05,
"cpu_time": 5.5584987892025558e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3698105587521160e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2519,
"real_time": 2.7730237166576588e+05,
"cpu_time": 5.5654642794758338e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3633407679250184e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2519,
"real_time": 2.7669794091166585e+05,
"cpu_time": 5.5587715244145750e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3685033500455996e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2519,
"real_time": 2.7751566956071876e+05,
"cpu_time": 5.5653008614524745e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3615243097349182e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2519,
"real_time": 2.7678635313786397e+05,
"cpu_time": 5.5596529297344398e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3677467930421162e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7696952942558040e+05,
"cpu_time": 5.5615376768559753e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3661851558999538e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time_median",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7678635313786392e+05,
"cpu_time": 5.5596529297344398e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3677467930421162e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.1723117907238111e+02,
"cpu_time": 3.5361870581397989e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.5626643970489275e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.5064154527672977e-03,
"cpu_time": 6.3582902132542252e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.5056574876085322e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2364,
"real_time": 2.9266794494238199e+05,
"cpu_time": 5.8918929822335695e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4785225804556203e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2364,
"real_time": 2.9607832903757866e+05,
"cpu_time": 5.8968948265648226e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4269366294405204e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2364,
"real_time": 2.9301258427872561e+05,
"cpu_time": 5.8907047377327387e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4732549737631381e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2364,
"real_time": 2.9270706987169973e+05,
"cpu_time": 5.8936309010154800e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4779239550808209e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2364,
"real_time": 2.9547526540268958e+05,
"cpu_time": 5.8893896192894445e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4359719863985240e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9398823870661517e+05,
"cpu_time": 5.8925026133672113e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4585220250277245e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time_median",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9301258427872561e+05,
"cpu_time": 5.8918929822335695e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4732549737631381e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6519834106600351e+03,
"cpu_time": 2.9094376089635136e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4998291652830997e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.6192159860810895e-03,
"cpu_time": 4.9375245118490419e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.6068561537891137e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2149,
"real_time": 3.2484616828898620e+05,
"cpu_time": 6.5287520195441321e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0697888905617082e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2149,
"real_time": 3.2455215529937833e+05,
"cpu_time": 6.5312984690551471e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0770993419590509e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2149,
"real_time": 3.2518999643219489e+05,
"cpu_time": 6.5284608282918856e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0612565846458757e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2149,
"real_time": 3.2514345868951746e+05,
"cpu_time": 6.5343097347608535e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0624103912951159e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2149,
"real_time": 3.2492181840773090e+05,
"cpu_time": 6.5317973941367131e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0679100370861030e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2493071942356165e+05,
"cpu_time": 6.5309236891577474e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0676930491095722e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time_median",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2492181840773090e+05,
"cpu_time": 6.5312984690551483e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0679100370861030e+08,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5642809955884411e+02,
"cpu_time": 2.4057721058940683e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.3689192301363032e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.8917776692138096e-04,
"cpu_time": 3.6836628636282930e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.8943499602271536e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1799,
"real_time": 3.8950698020008119e+05,
"cpu_time": 7.8251872984988661e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3460297931777365e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1799,
"real_time": 3.8978180333543848e+05,
"cpu_time": 7.8262195942192455e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3450807490590014e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1799,
"real_time": 3.8917514733623830e+05,
"cpu_time": 7.8189306225675193e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3471774947309966e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1799,
"real_time": 3.8902902913685178e+05,
"cpu_time": 7.8157796331294777e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3476834907750986e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1799,
"real_time": 3.8936982835860940e+05,
"cpu_time": 7.8179260867159115e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3465039194488666e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8937255767344392e+05,
"cpu_time": 7.8208086470262054e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3464950894383402e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time_median",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8936982835860946e+05,
"cpu_time": 7.8189306225675205e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3465039194488666e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9263525645183893e+02,
"cpu_time": 4.6254202195131791e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0117944464761605e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 7.5155593450235928e-04,
"cpu_time": 5.9142480378572559e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.5142824835566801e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1311,
"real_time": 5.3160225825659884e+05,
"cpu_time": 1.0599402471395377e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9724822152539902e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1311,
"real_time": 5.2825687386551592e+05,
"cpu_time": 1.0593014012204451e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9849736972224374e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1311,
"real_time": 5.3120500841984292e+05,
"cpu_time": 1.0598609290618219e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9739572921557395e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1311,
"real_time": 5.2853804825812951e+05,
"cpu_time": 1.0597870633103210e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9839177206933880e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1311,
"real_time": 5.3133411918327061e+05,
"cpu_time": 1.0598056971777331e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9734776332673631e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3018726159667154e+05,
"cpu_time": 1.0597390675819716e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9777617117185838e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time_median",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3120500841984292e+05,
"cpu_time": 1.0598056971777331e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9739572921557395e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6431378439039406e+03,
"cpu_time": 2.5180268609596556e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.1361470139885014e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.0991650741581220e-03,
"cpu_time": 2.3760819412887069e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1025714461103975e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 905,
"real_time": 7.7030222910554125e+05,
"cpu_time": 1.5439628375689150e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7225054280774560e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 905,
"real_time": 7.6999422915290156e+05,
"cpu_time": 1.5477521613259979e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7235944382429366e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 905,
"real_time": 7.6975912821751856e+05,
"cpu_time": 1.5433939745857141e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7244262823569751e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 905,
"real_time": 7.7024650990252919e+05,
"cpu_time": 1.5439796596685925e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7227023726019664e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 905,
"real_time": 7.7005087504760257e+05,
"cpu_time": 1.5439550276243498e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7233940872677531e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7007059428521863e+05,
"cpu_time": 1.5446087321547139e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7233245217094178e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time_median",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7005087504760246e+05,
"cpu_time": 1.5439628375689150e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7233940872677531e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1669828534094830e+02,
"cpu_time": 1.7746143613061304e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.6641286335760308e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.8140054554620170e-04,
"cpu_time": 1.1489086681716219e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8142546260940263e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 526,
"real_time": 1.3292459620538207e+06,
"cpu_time": 2.6809538060837365e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1554009714796290e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 526,
"real_time": 1.3283397991320000e+06,
"cpu_time": 2.6817251387835587e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1575535135970159e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 526,
"real_time": 1.3295845068838913e+06,
"cpu_time": 2.6810334106462523e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1545975289905176e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 526,
"real_time": 1.3303194525244401e+06,
"cpu_time": 2.6826071673003715e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1528547463098483e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 526,
"real_time": 1.3294768167355102e+06,
"cpu_time": 2.6820382281368761e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1548530573846226e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3293933074659326e+06,
"cpu_time": 2.6816715501901591e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1550519635523267e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time_median",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3294768167355100e+06,
"cpu_time": 2.6817251387835587e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1548530573846226e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.1289307817086387e+02,
"cpu_time": 6.9553621564728803e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6921434038520495e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.3625445093429046e-04,
"cpu_time": 2.5936666837442007e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.3632822007369937e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 278,
"real_time": 2.5317815020211418e+06,
"cpu_time": 5.0965269244603636e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3133222567995329e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 278,
"real_time": 2.5395191133879931e+06,
"cpu_time": 5.0967522482018163e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3032269596934400e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 278,
"real_time": 2.5331179113897812e+06,
"cpu_time": 5.0986236942450153e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3115742312199106e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 278,
"real_time": 2.5407421417708555e+06,
"cpu_time": 5.0990949712237166e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3016368965932441e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 278,
"real_time": 2.5322781992982402e+06,
"cpu_time": 5.0975766258994332e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3126723605347548e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5354877735736025e+06,
"cpu_time": 5.0977148928060690e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3084865409681764e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time_median",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5331179113897812e+06,
"cpu_time": 5.0975766258994332e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3115742312199106e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.2870196075852373e+03,
"cpu_time": 1.1277862874689649e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.5906146214097068e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6908066575067591e-03,
"cpu_time": 2.2123369219029980e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6897800707914325e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 139,
"real_time": 5.0062860174627183e+06,
"cpu_time": 9.9820455395680293e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3512300219121346e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 139,
"real_time": 5.0095413248691196e+06,
"cpu_time": 9.9843036043154355e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3490523207607884e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 139,
"real_time": 5.0066958094457928e+06,
"cpu_time": 9.9853982374108396e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3509557277970767e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 139,
"real_time": 5.0047827020233916e+06,
"cpu_time": 9.9815952086318098e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3522366501980424e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 139,
"real_time": 5.0097069830345595e+06,
"cpu_time": 9.9849316762586795e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3489415761872439e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0074025673671160e+06,
"cpu_time": 9.9836548532369584e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3504832593710575e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time_median",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0066958094457928e+06,
"cpu_time": 9.9843036043154337e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3509557277970767e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1502616157373263e+03,
"cpu_time": 1.7264537202533370e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4387175231295405e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.2941656613559040e-04,
"cpu_time": 1.7292802542082837e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.2940597273708278e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 70,
"real_time": 9.8570393531450201e+06,
"cpu_time": 1.9678458528570835e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.4041085561146727e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 70,
"real_time": 9.9099653240825441e+06,
"cpu_time": 1.9696221857144076e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3859282956781120e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 70,
"real_time": 9.8838508927396368e+06,
"cpu_time": 1.9675551071428083e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3948743626482692e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 70,
"real_time": 9.9017824977636337e+06,
"cpu_time": 1.9713525157141831e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3887264245178514e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 70,
"real_time": 9.9012109584042002e+06,
"cpu_time": 1.9685132357143890e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3889220359979119e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.8907698052270077e+06,
"cpu_time": 1.9689777794285741e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3925119349913635e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time_median",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.9012109584042002e+06,
"cpu_time": 1.9685132357143886e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3889220359979119e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1120959780887450e+04,
"cpu_time": 1.5472303435538201e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.2564532806599122e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1354212257296279e-03,
"cpu_time": 7.8580386214558947e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1389617545084288e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 33,
"real_time": 2.1216636128497846e+07,
"cpu_time": 4.2097312757574186e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1630303500308633e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 33,
"real_time": 2.1234958460836701e+07,
"cpu_time": 4.2337535909093112e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1603011667655401e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 33,
"real_time": 2.1192151319348451e+07,
"cpu_time": 4.2153442575757556e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1666848253735123e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 33,
"real_time": 2.1252844877766840e+07,
"cpu_time": 4.2343649515149795e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1576414539309206e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 33,
"real_time": 2.1282687275247142e+07,
"cpu_time": 4.2431074666665435e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1532138367719693e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1235855612339396e+07,
"cpu_time": 4.2272603084848024e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1601743265745616e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time_median",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1234958460836701e+07,
"cpu_time": 4.2337535909093112e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1603011667655401e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.4503979683888538e+04,
"cpu_time": 1.4080397271345387e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.1337952611143347e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6247981863202867e-03,
"cpu_time": 3.3308564516558695e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6245291337073353e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 18,
"real_time": 3.9362040244870715e+07,
"cpu_time": 7.7649587944443330e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4098265020063324e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 18,
"real_time": 3.9342004391882151e+07,
"cpu_time": 7.7552584444434717e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4115630373854194e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 18,
"real_time": 3.9345426691903010e+07,
"cpu_time": 7.7581707944444954e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4112662966143661e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 18,
"real_time": 3.9334075525403023e+07,
"cpu_time": 7.7491898388896316e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4122507318957710e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 18,
"real_time": 3.9381702947947711e+07,
"cpu_time": 7.7650627166665092e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4081240259569435e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9353049960401326e+07,
"cpu_time": 7.7585281177776888e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4106061187717667e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time_median",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9345426691903010e+07,
"cpu_time": 7.7581707944444939e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4112662966143661e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8986619624808289e+04,
"cpu_time": 6.7467859253988689e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6450583104558939e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.8246882119463199e-04,
"cpu_time": 8.6959611707012566e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.8233605792284072e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 9,
"real_time": 7.5541586511664927e+07,
"cpu_time": 1.4762311111111456e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5534791946492805e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 9,
"real_time": 7.5589852200614080e+07,
"cpu_time": 1.4754424655555138e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5512102244568124e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 9,
"real_time": 7.5746830966737539e+07,
"cpu_time": 1.4771649400000164e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5438506479284554e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 9,
"real_time": 7.5536019272274435e+07,
"cpu_time": 1.4752883000000513e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5537410971103354e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 9,
"real_time": 7.5571503904130727e+07,
"cpu_time": 1.4745179433331639e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5520724364640751e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5597158571084350e+07,
"cpu_time": 1.4757289519999784e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5508707201217914e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time_median",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5571503904130727e+07,
"cpu_time": 1.4754424655555138e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5520724364640751e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.6515372404182694e+04,
"cpu_time": 1.0071017781204016e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0584480533327023e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1444262461641583e-03,
"cpu_time": 6.8244359965665032e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1429444700238203e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 5,
"real_time": 1.4837004542350769e+08,
"cpu_time": 2.8344401559998006e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6184589043398538e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 5,
"real_time": 1.4824800193309784e+08,
"cpu_time": 2.8321466759998655e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6214377596959586e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 5,
"real_time": 1.4852422475814819e+08,
"cpu_time": 2.8313348140000015e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6147026713939924e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 5,
"real_time": 1.4847523272037506e+08,
"cpu_time": 2.8337657920001221e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6158954066843896e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"family_index": 5,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 5,
"real_time": 1.4823980629444122e+08,
"cpu_time": 2.8289774139998370e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6216379757920117e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4837146222591403e+08,
"cpu_time": 2.8321329703999251e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6184265435812416e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time_median",
"family_index": 5,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4837004542350769e+08,
"cpu_time": 2.8321466759998655e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6184589043398538e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.2911471864105125e+05,
"cpu_time": 2.1554575761041295e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1486363957497538e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.7021261841079673e-04,
"cpu_time": 7.6107216667858555e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.7016728343847335e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 2.9170741140842438e+08,
"cpu_time": 5.1786200649996769e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6808863333836803e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 2.9056742787361145e+08,
"cpu_time": 5.1738223600000310e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6953275591063395e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 2.9054909944534302e+08,
"cpu_time": 5.1716404299997973e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6955606678863177e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 2.9100126028060913e+08,
"cpu_time": 5.1787450000006175e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6898184666437640e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"family_index": 5,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 2.9108630120754242e+08,
"cpu_time": 5.1794064850002998e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6887404853670177e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time_mean",
"family_index": 5,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9098230004310608e+08,
"cpu_time": 5.1764468680000859e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6900667024774241e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time_median",
"family_index": 5,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9100126028060913e+08,
"cpu_time": 5.1786200649996775e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6898184666437640e+09,
"dst_gpu": 5.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time_stddev",
"family_index": 5,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.7348281379339797e+05,
"cpu_time": 3.4911823629138211e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.9991648986838162e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time_cv",
"family_index": 5,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/5/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.6271876802240418e-03,
"cpu_time": 6.7443604695253739e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6257605572972754e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2645,
"real_time": 2.6495531601884135e+05,
"cpu_time": 5.3121409792062733e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8648026217642752e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2645,
"real_time": 2.6482284037811798e+05,
"cpu_time": 5.3106315160688770e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8667359603043213e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2645,
"real_time": 2.6456696229559038e+05,
"cpu_time": 5.3078760491495347e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8704757053374061e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2645,
"real_time": 2.6419354394291283e+05,
"cpu_time": 5.2973155879016989e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8759463411462731e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2645,
"real_time": 2.6435632244789432e+05,
"cpu_time": 5.3056562948960811e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8735597110669990e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6457899701667140e+05,
"cpu_time": 5.3067240854444937e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8703040679238550e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time_median",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6456696229559038e+05,
"cpu_time": 5.3078760491495347e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8704757053374061e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.1598197989439268e+02,
"cpu_time": 5.8223228858452217e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.6222619088286847e+03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1942821745389049e-03,
"cpu_time": 1.0971595266870825e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1942890862598819e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2646,
"real_time": 2.6543235759309249e+05,
"cpu_time": 5.3082115986395907e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7157134065002799e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2646,
"real_time": 2.6567030401039135e+05,
"cpu_time": 5.3108333295539918e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7088028623624248e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2646,
"real_time": 2.6418772979779559e+05,
"cpu_time": 5.3121969160993444e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7520632830582317e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2646,
"real_time": 2.6471084694106004e+05,
"cpu_time": 5.2992994520025968e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7367437854029592e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2646,
"real_time": 2.6360613680061005e+05,
"cpu_time": 5.3025403439156630e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7691666243305011e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6472147502858995e+05,
"cpu_time": 5.3066163280422380e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7364979923308790e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time_median",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6471084694106004e+05,
"cpu_time": 5.3082115986395918e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.7367437854029592e+06,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.5653469683956610e+02,
"cpu_time": 5.5141018007468449e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5042950298211108e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.2356071480300580e-03,
"cpu_time": 1.0390993921320774e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.2369878881938520e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2653,
"real_time": 2.6482777551153192e+05,
"cpu_time": 5.3025578326420055e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5466655610758020e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2653,
"real_time": 2.6586503469065053e+05,
"cpu_time": 5.3120061402188428e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5406313224926079e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2653,
"real_time": 2.6431702352695860e+05,
"cpu_time": 5.3032255597439583e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5496542543285090e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2653,
"real_time": 2.6419863679086108e+05,
"cpu_time": 5.2950306445530104e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5503486504521152e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2653,
"real_time": 2.6365608883311827e+05,
"cpu_time": 5.3013437429323583e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5535389370782075e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6457291187062406e+05,
"cpu_time": 5.3028327840180357e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5481677450854484e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time_median",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6431702352695860e+05,
"cpu_time": 5.3025578326420055e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5496542543285090e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.3376585731310729e+02,
"cpu_time": 6.0718810631264955e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.8700611820784652e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.1513651621327661e-03,
"cpu_time": 1.1450259343319779e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.1456934802692655e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2648,
"real_time": 2.6628535736664874e+05,
"cpu_time": 5.3338231986404327e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0763989732715275e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2648,
"real_time": 2.6687931724121649e+05,
"cpu_time": 5.3396007515103929e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0695522173401445e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2648,
"real_time": 2.6562909925922053e+05,
"cpu_time": 5.3376963557406922e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0839994649854381e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2648,
"real_time": 2.6644904021072778e+05,
"cpu_time": 5.3337608345921664e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0745091044505756e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2648,
"real_time": 2.6507598997390579e+05,
"cpu_time": 5.3206457439579803e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0904345583341684e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6606376081034390e+05,
"cpu_time": 5.3331053768883343e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0789788636763711e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time_median",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6628535736664874e+05,
"cpu_time": 5.3338231986404327e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.0763989732715275e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.1191632782308602e+02,
"cpu_time": 7.4069954079415970e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.2452353025095654e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.6757357922582914e-03,
"cpu_time": 1.3888710018820779e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6779122779246904e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2609,
"real_time": 2.6921206982758135e+05,
"cpu_time": 5.3916851054045104e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.0859084106047854e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2609,
"real_time": 2.6931420471747691e+05,
"cpu_time": 5.3918878267537104e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.0836003868372172e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2609,
"real_time": 2.6870025891200959e+05,
"cpu_time": 5.3935110617091565e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.0975006374538757e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2609,
"real_time": 2.6775919832289219e+05,
"cpu_time": 5.3826741433498601e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1189307790810049e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2609,
"real_time": 2.6862867625059694e+05,
"cpu_time": 5.3911707665768254e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.0991254651888974e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6872288160611142e+05,
"cpu_time": 5.3901857807588135e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.0970131358331561e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time_median",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6870025891200959e+05,
"cpu_time": 5.3916851054045104e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.0975006374538757e+07,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.1786730849882406e+02,
"cpu_time": 4.2894440773747465e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4038335342242327e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.2992731575589517e-03,
"cpu_time": 7.9578779875948775e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3024938653546118e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2564,
"real_time": 2.7276839166131394e+05,
"cpu_time": 5.4668885335415008e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2013122121820758e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2564,
"real_time": 2.7234243418501585e+05,
"cpu_time": 5.4695573829952814e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2031911258360516e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2564,
"real_time": 2.7290680380349228e+05,
"cpu_time": 5.4750485140403523e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2007029338702285e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2564,
"real_time": 2.7229937759911653e+05,
"cpu_time": 5.4759892160681740e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2033813771047826e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2564,
"real_time": 2.7274767722565442e+05,
"cpu_time": 5.4733748673953593e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2014034485393545e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7261293689491868e+05,
"cpu_time": 5.4721717028081347e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2019982195064986e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time_median",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7274767722565442e+05,
"cpu_time": 5.4733748673953605e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2014034485393545e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7393888417604546e+02,
"cpu_time": 3.8419917013730986e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2081260161920196e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.0048638457742667e-03,
"cpu_time": 7.0209633579324958e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.0050980081218730e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2499,
"real_time": 2.8097861718588404e+05,
"cpu_time": 5.6522431052416249e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3324194793315551e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2499,
"real_time": 2.8168994364986086e+05,
"cpu_time": 5.6453844817928248e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3265296286707667e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2499,
"real_time": 2.8151708016195905e+05,
"cpu_time": 5.6406270828330971e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3279582170394996e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2499,
"real_time": 2.8236080281564646e+05,
"cpu_time": 5.6488634053622861e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3210020422979352e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2499,
"real_time": 2.8100312846916250e+05,
"cpu_time": 5.6448093997593294e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3322160275234079e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8150991445650265e+05,
"cpu_time": 5.6463854949978332e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3280250789726329e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time_median",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.8151708016195905e+05,
"cpu_time": 5.6453844817928248e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3279582170394996e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.6911810817244077e+02,
"cpu_time": 4.3902463443339821e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.7020923674466455e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.0216627512789705e-03,
"cpu_time": 7.7753216605974348e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.0197773683442010e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2372,
"real_time": 2.9527046164337930e+05,
"cpu_time": 5.9782977698147006e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4390488391725975e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2372,
"real_time": 2.9805218391829135e+05,
"cpu_time": 5.9916457293430227e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.3976191778528404e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2372,
"real_time": 2.9491976680529333e+05,
"cpu_time": 5.9882343086003372e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4443273985949546e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2372,
"real_time": 2.9512685026435973e+05,
"cpu_time": 5.9754932166940568e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4412089202521670e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2372,
"real_time": 2.9785130730505032e+05,
"cpu_time": 5.9902266610460135e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4005850162598079e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9624411398727482e+05,
"cpu_time": 5.9847795370996254e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4245578704264736e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time_median",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9527046164337930e+05,
"cpu_time": 5.9882343086003361e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4390488391725975e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5654360261488712e+03,
"cpu_time": 7.3654642605206345e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3337045517631406e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.2842772302848680e-03,
"cpu_time": 1.2306993457089186e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.2744355935798841e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2117,
"real_time": 3.3021911021168478e+05,
"cpu_time": 6.6308269957490405e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9384866560858428e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2117,
"real_time": 3.2970744085506513e+05,
"cpu_time": 6.6253206376949837e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9508063063470531e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2117,
"real_time": 3.3040987219638156e+05,
"cpu_time": 6.6279446291925246e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9339033745393884e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2117,
"real_time": 3.2954630991045863e+05,
"cpu_time": 6.6253922720839782e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9546938356320071e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2117,
"real_time": 3.3019213310548884e+05,
"cpu_time": 6.6268551251770789e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9391352402769375e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3001497325581580e+05,
"cpu_time": 6.6272679319795209e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9434050825762463e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time_median",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.3019213310548884e+05,
"cpu_time": 6.6268551251770789e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 7.9391352402769375e+08,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6851872108758232e+02,
"cpu_time": 2.2696540784187292e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.8729784591195756e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.1166727298822282e-03,
"cpu_time": 3.4247205661727312e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1170245463853199e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1781,
"real_time": 3.9336144545242080e+05,
"cpu_time": 7.9018883043244004e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3328403331368568e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1781,
"real_time": 3.9343816532289574e+05,
"cpu_time": 7.8994628467145120e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3325804312088418e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1781,
"real_time": 3.9518398035943595e+05,
"cpu_time": 7.9307798652440414e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3266934543326850e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1781,
"real_time": 3.9340897187682631e+05,
"cpu_time": 7.8993312184162636e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3326793171462064e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1781,
"real_time": 3.9371989530410274e+05,
"cpu_time": 7.9023375238637719e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3316268907240479e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9382249166313634e+05,
"cpu_time": 7.9067599517125986e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3312840853097277e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time_median",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9343816532289574e+05,
"cpu_time": 7.9018883043243992e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3325804312088418e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7386149291026800e+02,
"cpu_time": 1.3497044881359664e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.6096216290336037e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.9650007536192353e-03,
"cpu_time": 1.7070260086037156e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9602289682794987e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1313,
"real_time": 5.3644657485408359e+05,
"cpu_time": 1.0699971035797205e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9546699506567237e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1313,
"real_time": 5.3369925731207163e+05,
"cpu_time": 1.0697890464585989e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9647319827294850e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1313,
"real_time": 5.3730153341076116e+05,
"cpu_time": 1.0712041462299691e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9515596639817796e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1313,
"real_time": 5.3450499368854216e+05,
"cpu_time": 1.0708068728103405e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9617702591774266e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1313,
"real_time": 5.3722890168754710e+05,
"cpu_time": 1.0712797814165696e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9518235089478731e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3583625219060108e+05,
"cpu_time": 1.0706153900990398e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9569110730986576e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time_median",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3644657485408359e+05,
"cpu_time": 1.0708068728103405e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9546699506567237e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6430164134454176e+03,
"cpu_time": 6.8735676051787982e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0067011563286548e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.0662658726960937e-03,
"cpu_time": 6.4202025010521679e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.0694808971658506e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 901,
"real_time": 7.7612014238275052e+05,
"cpu_time": 1.5556080632631369e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7020971180590377e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 901,
"real_time": 7.7597418321672815e+05,
"cpu_time": 1.5548399178689506e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7026053770325875e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 901,
"real_time": 7.7616349630136357e+05,
"cpu_time": 1.5548865660376870e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7019461878760290e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 901,
"real_time": 7.7635917488793610e+05,
"cpu_time": 1.5558609667036827e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7012651718873734e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 901,
"real_time": 7.7514593251986010e+05,
"cpu_time": 1.5535204339624222e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7054931362182808e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7595258586172783e+05,
"cpu_time": 1.5549431895671759e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7026813982146621e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time_median",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7612014238275052e+05,
"cpu_time": 1.5548865660376870e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7020971180590377e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.7144169760361382e+02,
"cpu_time": 9.1138310845785350e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6431117101889329e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.0756508347743722e-04,
"cpu_time": 5.8611987535798029e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0795612508168372e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 523,
"real_time": 1.3365129077447362e+06,
"cpu_time": 2.6957878661565674e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1382442890713034e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 523,
"real_time": 1.3370601888603566e+06,
"cpu_time": 2.6968294359464566e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1369597531544304e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 523,
"real_time": 1.3367726383410238e+06,
"cpu_time": 2.6966964608029062e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1376345383649244e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 523,
"real_time": 1.3366028391373260e+06,
"cpu_time": 2.6959424397707465e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1380331368344989e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 523,
"real_time": 1.3378097261275460e+06,
"cpu_time": 2.6964345372849028e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1352022025889478e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3369516600421979e+06,
"cpu_time": 2.6963381479923162e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1372147840028210e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time_median",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3367726383410238e+06,
"cpu_time": 2.6964345372849023e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1376345383649244e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.2304021873291754e+02,
"cpu_time": 4.5783127691852394e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2269169133727027e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.9121849679771438e-04,
"cpu_time": 1.6979742591240773e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.9108476717276600e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 277,
"real_time": 2.5364404951057495e+06,
"cpu_time": 5.0805397364622243e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3072362691679316e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 277,
"real_time": 2.5245600030337214e+06,
"cpu_time": 5.0750901985565266e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3228000086825228e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 277,
"real_time": 2.5341386935381144e+06,
"cpu_time": 5.0756339927795213e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3102402885013332e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 277,
"real_time": 2.5265453205131236e+06,
"cpu_time": 5.0793934981956081e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3201890074532018e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 277,
"real_time": 2.5346978266625949e+06,
"cpu_time": 5.0772157725637518e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3095100772012634e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5312764677706608e+06,
"cpu_time": 5.0775746397115272e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3139951302012506e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time_median",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5341386935381144e+06,
"cpu_time": 5.0772157725637518e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3102402885013332e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3399406425922662e+03,
"cpu_time": 2.3541128313739619e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.9961907413677620e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1095841211273315e-03,
"cpu_time": 4.6362938970163643e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1111047139477541e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 139,
"real_time": 5.0082054598886762e+06,
"cpu_time": 9.9779202517985143e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3499456310989542e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 139,
"real_time": 5.0085818716626372e+06,
"cpu_time": 9.9815361007199995e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3496938714172750e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 139,
"real_time": 5.0095890501259472e+06,
"cpu_time": 9.9797001438847147e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3490204150734081e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 139,
"real_time": 5.0001317038864112e+06,
"cpu_time": 9.9681585755389687e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3553548173460536e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 139,
"real_time": 5.0011758303953158e+06,
"cpu_time": 9.9687565179870985e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3546542991018677e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0055367831917983e+06,
"cpu_time": 9.9752143179858588e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3517338068075123e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time_median",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0082054598886762e+06,
"cpu_time": 9.9779202517985143e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3499456310989542e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.5013347467906515e+03,
"cpu_time": 6.3027043982678915e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.0150620228446377e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.9927113549655288e-04,
"cpu_time": 6.3183648965854980e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.9955294681245870e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 70,
"real_time": 9.8694043899221085e+06,
"cpu_time": 1.9702002842856407e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3998436657700701e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 70,
"real_time": 9.8877906400178168e+06,
"cpu_time": 1.9798466414285291e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3935216896885614e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 70,
"real_time": 9.8692214781684540e+06,
"cpu_time": 1.9777276414285034e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3999066769577742e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 70,
"real_time": 9.8786432961268090e+06,
"cpu_time": 1.9732947142857224e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3966639946556153e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 70,
"real_time": 9.8709427219416406e+06,
"cpu_time": 1.9741995242855281e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3993138188729911e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.8752005052353647e+06,
"cpu_time": 1.9750537611427851e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3978499691890025e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time_median",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.8709427219416406e+06,
"cpu_time": 1.9741995242855277e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3993138188729911e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 8.0286477514000289e+03,
"cpu_time": 3.7914885357771906e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7608091127059110e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.1301111275093791e-04,
"cpu_time": 1.9196887752480213e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.1251648475958458e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 33,
"real_time": 2.1355072713711046e+07,
"cpu_time": 4.2624428363641337e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1425256612173786e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 33,
"real_time": 2.1357691197684318e+07,
"cpu_time": 4.2651599939393818e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1421403830052662e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 33,
"real_time": 2.1364042366092857e+07,
"cpu_time": 4.2682872242425442e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1412062778207808e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 33,
"real_time": 2.1366942165927455e+07,
"cpu_time": 4.2717919424245395e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1407799711750226e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 33,
"real_time": 2.1357996558601204e+07,
"cpu_time": 4.2682017878784493e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1420954589944530e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1360349000403378e+07,
"cpu_time": 4.2671767569698103e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1417495504425807e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time_median",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1357996558601208e+07,
"cpu_time": 4.2682017878784493e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1420954589944530e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.9383165183031088e+03,
"cpu_time": 3.5376934621322827e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 7.2628848130753112e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.3119081613366205e-04,
"cpu_time": 8.2904779052191298e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3117325860847767e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 18,
"real_time": 3.9464132239421211e+07,
"cpu_time": 7.7928735222220287e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4010054290748663e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 18,
"real_time": 3.9459981852107577e+07,
"cpu_time": 7.8006909666656703e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4013631456556630e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 18,
"real_time": 3.9384274640017085e+07,
"cpu_time": 7.7850963944443822e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4079014842036905e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 18,
"real_time": 3.9422559448414378e+07,
"cpu_time": 7.7915300111107573e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4045919361381898e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 18,
"real_time": 3.9437742075986333e+07,
"cpu_time": 7.7961678111111924e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4032812462081919e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9433738051189318e+07,
"cpu_time": 7.7932717411108062e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4036286482561207e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time_median",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9437742075986333e+07,
"cpu_time": 7.7928735222220287e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4032812462081919e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2404344559644138e+04,
"cpu_time": 5.7762579604403385e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7981922580408943e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 8.2174163954682009e-04,
"cpu_time": 7.4118523674333284e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.2212031546819093e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 9,
"real_time": 7.5570177700784475e+07,
"cpu_time": 1.4756075755556393e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5521347728313394e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 9,
"real_time": 7.5579351021183863e+07,
"cpu_time": 1.4757624433332241e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5517036382696805e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 9,
"real_time": 7.5353554553455770e+07,
"cpu_time": 1.4721090277776563e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5623462966112900e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 9,
"real_time": 7.5579990943272904e+07,
"cpu_time": 1.4756561999999776e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5516735666385050e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 9,
"real_time": 7.5614248712857559e+07,
"cpu_time": 1.4759508522221649e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5500644464428148e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5539464586310938e+07,
"cpu_time": 1.4750172197777325e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5535845441587257e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time_median",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5579351021183863e+07,
"cpu_time": 1.4756561999999779e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5517036382696805e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0527560803794271e+05,
"cpu_time": 1.6310597833179616e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9611206628180295e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3936504397334647e-03,
"cpu_time": 1.1057903334604749e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3960891041618719e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 5,
"real_time": 1.4837051331996918e+08,
"cpu_time": 2.8326186620001864e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6184474932846551e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 5,
"real_time": 1.4821850955486298e+08,
"cpu_time": 2.8307316199998242e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6221583499412913e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 5,
"real_time": 1.4819179475307465e+08,
"cpu_time": 2.8323438060001534e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6228113229518809e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 5,
"real_time": 1.4813576042652130e+08,
"cpu_time": 2.8333854580000663e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6241816996396365e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"family_index": 6,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 5,
"real_time": 1.4781432151794434e+08,
"cpu_time": 2.8282334780001295e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6320628913810968e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4814617991447449e+08,
"cpu_time": 2.8314626048000717e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6239323514397125e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time_median",
"family_index": 6,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4819179475307465e+08,
"cpu_time": 2.8323438060001534e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6228113229518809e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.0486356939489886e+05,
"cpu_time": 2.0476783742799706e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0163559835402435e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3828474653424583e-03,
"cpu_time": 7.2318750415725731e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3842300288931580e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 2.9652483761310577e+08,
"cpu_time": 5.2629026900001460e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6210856150977044e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 2.9672548174858093e+08,
"cpu_time": 5.2596246500002050e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6186370569609332e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 2.9704859852790833e+08,
"cpu_time": 5.2689574949999952e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6147008581126828e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 2.9597789049148560e+08,
"cpu_time": 5.2544479899995619e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6277771363833961e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"family_index": 6,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 2.9627436399459839e+08,
"cpu_time": 5.2625300950001019e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6241469208573718e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time_mean",
"family_index": 6,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9651023447513580e+08,
"cpu_time": 5.2616925840000027e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6212695174824176e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time_median",
"family_index": 6,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9652483761310577e+08,
"cpu_time": 5.2625300950001019e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6210856150977044e+09,
"dst_gpu": 6.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time_stddev",
"family_index": 6,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.1091528757182538e+05,
"cpu_time": 5.2845341866465495e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0184536549339574e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time_cv",
"family_index": 6,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/6/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.3858384628753283e-03,
"cpu_time": 1.0043411131079767e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.3858271610843512e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2691,
"real_time": 2.6070693310650237e+05,
"cpu_time": 5.2492139130433253e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9277820033335355e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2691,
"real_time": 2.6332634110598976e+05,
"cpu_time": 5.2628542028986081e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.8887108509506700e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2691,
"real_time": 2.5986424133201299e+05,
"cpu_time": 5.2390166926789947e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9405190754648559e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2691,
"real_time": 2.6125507864015075e+05,
"cpu_time": 5.2540437532514718e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9195410299006812e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2691,
"real_time": 2.5879846348412352e+05,
"cpu_time": 5.2484246339655295e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9567468300012499e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6079021153375591e+05,
"cpu_time": 5.2507106391675852e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9266599579301984e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time_median",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6070693310650234e+05,
"cpu_time": 5.2492139130433253e+05,
"time_unit": "ns",
"bytes": 1.0240000000000000e+03,
"bytes_per_second": 3.9277820033335355e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.6940684046049241e+03,
"cpu_time": 8.7004336519040021e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.5442915775259971e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 0,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):10/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.4959048679081614e-03,
"cpu_time": 1.6570011660904083e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.4795312168236018e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2699,
"real_time": 2.5943509031210691e+05,
"cpu_time": 5.2470466320860095e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8940747665869128e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2699,
"real_time": 2.6115313166172410e+05,
"cpu_time": 5.2434999147834512e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8421422211884782e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2699,
"real_time": 2.5972255176777265e+05,
"cpu_time": 5.2442263542052510e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8853375883631054e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2699,
"real_time": 2.6093449594500251e+05,
"cpu_time": 5.2529039422009967e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8487131131625446e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2699,
"real_time": 2.6062505073469615e+05,
"cpu_time": 5.2459599814747577e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8580320434537437e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6037406408426049e+05,
"cpu_time": 5.2467273649500939e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8656599465509569e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time_median",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6062505073469612e+05,
"cpu_time": 5.2459599814747577e+05,
"time_unit": "ns",
"bytes": 2.0480000000000000e+03,
"bytes_per_second": 7.8580320434537437e+06,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5666447365032627e+02,
"cpu_time": 3.7253323582118270e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.2875068626946239e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 1,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):11/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.9060669936981881e-03,
"cpu_time": 7.1002971930622921e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.9082198801356541e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2726,
"real_time": 2.6068190593232814e+05,
"cpu_time": 5.2466955429195950e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5712636384756612e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2726,
"real_time": 2.6167407224249633e+05,
"cpu_time": 5.2535411702129920e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5653060178633938e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2726,
"real_time": 2.6088568767553545e+05,
"cpu_time": 5.2440509354359237e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5700363007625818e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2726,
"real_time": 2.6038361841449564e+05,
"cpu_time": 5.2400854732208961e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5730636300935492e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2726,
"real_time": 2.6156906825927601e+05,
"cpu_time": 5.2447267754955136e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5659343924947226e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6103887050482631e+05,
"cpu_time": 5.2458199794569844e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5691207959379820e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time_median",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6088568767553545e+05,
"cpu_time": 5.2447267754955136e+05,
"time_unit": "ns",
"bytes": 4.0960000000000000e+03,
"bytes_per_second": 1.5700363007625818e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.6232439334626247e+02,
"cpu_time": 4.9394476283545964e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3794068659492601e+04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 2,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):12/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.1541787713790527e-03,
"cpu_time": 9.4159686144355619e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.1536945241549320e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2672,
"real_time": 2.6224052090763149e+05,
"cpu_time": 5.2749163922157325e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1238498046171337e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2672,
"real_time": 2.6149513406832743e+05,
"cpu_time": 5.2816703181146027e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1327542782725237e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2672,
"real_time": 2.6343100828902511e+05,
"cpu_time": 5.2911698952091078e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1097326215340953e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2672,
"real_time": 2.6346477776194899e+05,
"cpu_time": 5.2741875598801975e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1093340330303282e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2672,
"real_time": 2.6388154852437205e+05,
"cpu_time": 5.2817221744007862e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1044231951077051e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6290259791026101e+05,
"cpu_time": 5.2807332679640851e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1160187865123570e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time_median",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6343100828902511e+05,
"cpu_time": 5.2816703181146015e+05,
"time_unit": "ns",
"bytes": 8.1920000000000000e+03,
"bytes_per_second": 3.1097326215340953e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.9660780181954453e+02,
"cpu_time": 6.8458294778311347e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1832804700215309e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 3,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):13/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.7907871954910299e-03,
"cpu_time": 1.2963785766953631e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7974112195450927e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2645,
"real_time": 2.6683606093376171e+05,
"cpu_time": 5.3348514366737986e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1400996337099642e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2645,
"real_time": 2.6574777563574369e+05,
"cpu_time": 5.3336248393192957e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1652444543721385e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2645,
"real_time": 2.6524508843332221e+05,
"cpu_time": 5.3246372703218344e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1769287027226672e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2645,
"real_time": 2.6579792083140695e+05,
"cpu_time": 5.3338588922498992e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1640813249221057e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2645,
"real_time": 2.6390850584688183e+05,
"cpu_time": 5.3258606729678833e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.2082121784683593e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6550707033622329e+05,
"cpu_time": 5.3305666223065439e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1709132588390470e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time_median",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6574777563574369e+05,
"cpu_time": 5.3336248393192957e+05,
"time_unit": "ns",
"bytes": 1.6384000000000000e+04,
"bytes_per_second": 6.1652444543721385e+07,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0645177316685217e+03,
"cpu_time": 4.8952666162237273e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.4777434942781102e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 4,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):14/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.0093762110382817e-03,
"cpu_time": 9.1833888647761407e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.0151974113864890e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2583,
"real_time": 2.6948588049440185e+05,
"cpu_time": 5.4226219279908750e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2159449667597966e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2583,
"real_time": 2.6898017401523609e+05,
"cpu_time": 5.4131371196282981e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2182310506700724e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2583,
"real_time": 2.7090575353307719e+05,
"cpu_time": 5.4223124932246527e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2095719479061960e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2583,
"real_time": 2.6813848127799912e+05,
"cpu_time": 5.4088292140924453e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2220551054000703e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2583,
"real_time": 2.6929230617443653e+05,
"cpu_time": 5.4215502400311956e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2168190196556984e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6936051909903018e+05,
"cpu_time": 5.4176901989934931e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2165244180783668e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time_median",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.6929230617443647e+05,
"cpu_time": 5.4215502400311944e+05,
"time_unit": "ns",
"bytes": 3.2768000000000000e+04,
"bytes_per_second": 1.2168190196556984e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.0057530459122012e+03,
"cpu_time": 6.3212945033662163e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.5348785118236631e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 5,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):15/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.7338547210864150e-03,
"cpu_time": 1.1667877400115267e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.7277332410532286e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2500,
"real_time": 2.7761368296341971e+05,
"cpu_time": 5.5812431760004989e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3606905574836338e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2500,
"real_time": 2.7835697757545859e+05,
"cpu_time": 5.6016861359994439e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3543868226631442e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2500,
"real_time": 2.7789303646422923e+05,
"cpu_time": 5.6029011119999271e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3583174603382292e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2500,
"real_time": 2.7866839324124157e+05,
"cpu_time": 5.5872731879999267e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3517557638216212e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2500,
"real_time": 2.7820197464898229e+05,
"cpu_time": 5.6068593199997849e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3556985920998293e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7814681297866633e+05,
"cpu_time": 5.5959925863999152e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3561698392812917e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time_median",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7820197464898229e+05,
"cpu_time": 5.6016861359994439e+05,
"time_unit": "ns",
"bytes": 6.5536000000000000e+04,
"bytes_per_second": 2.3556985920998293e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.0862209629311690e+02,
"cpu_time": 1.1088317588065670e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4617356051553099e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 6,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):16/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4690878242220159e-03,
"cpu_time": 1.9814746743971553e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4692215932155602e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2355,
"real_time": 2.9712956363627897e+05,
"cpu_time": 5.9242307473463879e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4112742736177987e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2355,
"real_time": 2.9465393909705983e+05,
"cpu_time": 5.9190623397025501e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4483369338844812e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2355,
"real_time": 2.9386840691501292e+05,
"cpu_time": 5.9191994522302062e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4602276704724562e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2355,
"real_time": 2.9693063555657072e+05,
"cpu_time": 5.9187920636935090e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4142295979098588e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2355,
"real_time": 2.9398363978095795e+05,
"cpu_time": 5.9112821698512090e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4584793935356212e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9531323699717608e+05,
"cpu_time": 5.9185133545647725e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4385095738840431e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time_median",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9465393909705989e+05,
"cpu_time": 5.9190623397025501e+05,
"time_unit": "ns",
"bytes": 1.3107200000000000e+05,
"bytes_per_second": 4.4483369338844812e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.5972677456013639e+03,
"cpu_time": 4.6321810762221895e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3970425709778289e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 7,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):17/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.4087238413110398e-03,
"cpu_time": 7.8265956308935694e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.4005573967484521e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2153,
"real_time": 3.2562459170164284e+05,
"cpu_time": 6.5608016720857262e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0504976184413111e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2153,
"real_time": 3.2630174687507277e+05,
"cpu_time": 6.5686823827218555e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0337908855990255e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2153,
"real_time": 3.2657374278534093e+05,
"cpu_time": 6.5636507338599395e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0270997222305453e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2153,
"real_time": 3.2615141305976012e+05,
"cpu_time": 6.5591990339070361e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0374939216335034e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2153,
"real_time": 3.2658689705433504e+05,
"cpu_time": 6.5617480910357216e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0267764066598940e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2624767829523038e+05,
"cpu_time": 6.5628163827220572e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0351317109128571e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time_median",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.2630174687507277e+05,
"cpu_time": 6.5617480910357239e+05,
"time_unit": "ns",
"bytes": 2.6214400000000000e+05,
"bytes_per_second": 8.0337908855990255e+08,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9427614947397439e+02,
"cpu_time": 3.6534783534625933e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.7187051277420693e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 8,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):18/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2085178706380958e-03,
"cpu_time": 5.5669367241191058e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2095265488358676e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1800,
"real_time": 3.8944718421488587e+05,
"cpu_time": 7.8253891166670853e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3462364635064683e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1800,
"real_time": 3.8935412377921038e+05,
"cpu_time": 7.8227893333329726e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3465582306181149e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1800,
"real_time": 3.9092843773283268e+05,
"cpu_time": 7.8646581777775288e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3411354851557448e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1800,
"real_time": 3.8929767843607505e+05,
"cpu_time": 7.8243645555554994e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3467534718065143e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1800,
"real_time": 3.8953882435129746e+05,
"cpu_time": 7.8262505111107812e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3459197574801474e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8971324970286025e+05,
"cpu_time": 7.8326903388887749e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3453206817133980e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time_median",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.8944718421488593e+05,
"cpu_time": 7.8253891166670865e+05,
"time_unit": "ns",
"bytes": 5.2428800000000000e+05,
"bytes_per_second": 1.3462364635064683e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 6.8548667060273215e+02,
"cpu_time": 1.7916964936085842e+03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3610290677753207e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 9,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):19/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.7589514113912897e-03,
"cpu_time": 2.2874598842659889e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.7549935118579447e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 1324,
"real_time": 5.2997230652725359e+05,
"cpu_time": 1.0627290800603435e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9785486658180268e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 1324,
"real_time": 5.3278863184003497e+05,
"cpu_time": 1.0630647243201262e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9680900404699802e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 1324,
"real_time": 5.2984216527625069e+05,
"cpu_time": 1.0626547522658086e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9790346422378266e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 1324,
"real_time": 5.3216095871694409e+05,
"cpu_time": 1.0622367484895394e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9704113629984205e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 1324,
"real_time": 5.2983877476792946e+05,
"cpu_time": 1.0628644342900866e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9790473063419693e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.3092056742568256e+05,
"cpu_time": 1.0627099478851811e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9750264035732446e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time_median",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.2997230652725371e+05,
"cpu_time": 1.0627290800603435e+06,
"time_unit": "ns",
"bytes": 1.0485760000000000e+06,
"bytes_per_second": 1.9785486658180268e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4370682389338563e+03,
"cpu_time": 3.0702712895285777e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.3397495306053450e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 10,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):20/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.7067481033968698e-03,
"cpu_time": 2.8890962163650519e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7036345037942770e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 899,
"real_time": 7.7039247404087801e+05,
"cpu_time": 1.5438317274749940e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7221865096889853e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 899,
"real_time": 7.7053539430851059e+05,
"cpu_time": 1.5446796785317778e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7216815937209663e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 899,
"real_time": 7.7028551665461052e+05,
"cpu_time": 1.5439076440488801e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7225644967440624e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 899,
"real_time": 7.7136956337628025e+05,
"cpu_time": 1.5455682736371330e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7187383318843660e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 899,
"real_time": 7.7026183526596264e+05,
"cpu_time": 1.5442471768631057e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7226482008885684e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7056895672924840e+05,
"cpu_time": 1.5444469001111784e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7215638265853901e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time_median",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.7039247404087801e+05,
"cpu_time": 1.5442471768631057e+06,
"time_unit": "ns",
"bytes": 2.0971520000000000e+06,
"bytes_per_second": 2.7221865096889853e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 4.6040890729516150e+02,
"cpu_time": 7.1077215487587637e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6249793874384991e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 11,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):21/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 5.9749215599004903e-04,
"cpu_time": 4.6021145487404639e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.9707561203048453e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 524,
"real_time": 1.3310991675070424e+06,
"cpu_time": 2.6818104751907783e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1510079056358585e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 524,
"real_time": 1.3303935400277858e+06,
"cpu_time": 2.6814272958013690e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1526791688363128e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 524,
"real_time": 1.3308570769576372e+06,
"cpu_time": 2.6809227041982352e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1515810920795894e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 524,
"real_time": 1.3311339947945999e+06,
"cpu_time": 2.6831412671755888e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1509254638539977e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 524,
"real_time": 1.3303929139621812e+06,
"cpu_time": 2.6827879522900605e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1526806524461317e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3307753386498494e+06,
"cpu_time": 2.6820179389312067e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1517748565703783e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time_median",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3308570769576370e+06,
"cpu_time": 2.6818104751907783e+06,
"time_unit": "ns",
"bytes": 4.1943040000000000e+06,
"bytes_per_second": 3.1515810920795894e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.6475996868684945e+02,
"cpu_time": 9.2820075261232159e+02,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 8.6392610202493588e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 12,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):22/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.7409582826874452e-04,
"cpu_time": 3.4608297697748171e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.7410780951689611e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 280,
"real_time": 2.5043375099942619e+06,
"cpu_time": 5.0236052928572204e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3496315758251052e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 280,
"real_time": 2.5299028917548382e+06,
"cpu_time": 5.0757836607138934e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3157826046759205e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 280,
"real_time": 2.5328125987601066e+06,
"cpu_time": 5.0777330392861590e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3119734180517316e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 280,
"real_time": 2.5301949079481089e+06,
"cpu_time": 5.0752703071428388e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3153999218197937e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 280,
"real_time": 2.5347812009775746e+06,
"cpu_time": 5.0804515642856322e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3094012204149270e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5264058218869781e+06,
"cpu_time": 5.0665687728571482e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3204377481574955e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time_median",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.5301949079481084e+06,
"cpu_time": 5.0757836607138934e+06,
"time_unit": "ns",
"bytes": 8.3886080000000000e+06,
"bytes_per_second": 3.3153999218197937e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.2497908079423572e+04,
"cpu_time": 2.4103237404757190e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.6528607455555353e+07,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 13,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):23/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 4.9469123175503362e-03,
"cpu_time": 4.7573098255142901e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.9778398841318575e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 139,
"real_time": 5.0064998397456231e+06,
"cpu_time": 9.9785172733816244e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3510868944424934e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 139,
"real_time": 5.0385806227116277e+06,
"cpu_time": 1.0050597812948627e+07,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3297504309796987e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 139,
"real_time": 5.0084428901938228e+06,
"cpu_time": 9.9789644532376770e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3497868235352359e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 139,
"real_time": 5.0057228688123841e+06,
"cpu_time": 9.9777828848921750e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3516070385215755e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 139,
"real_time": 5.0066564493417311e+06,
"cpu_time": 9.9770427841723952e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3509820715191765e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0131805341610378e+06,
"cpu_time": 9.9925810417264998e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3466426517996364e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time_median",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0066564493417311e+06,
"cpu_time": 9.9785172733816244e+06,
"time_unit": "ns",
"bytes": 1.6777216000000000e+07,
"bytes_per_second": 3.3509820715191765e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4233955017668171e+04,
"cpu_time": 3.2440598402029573e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.4665190516641326e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 14,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):24/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 2.8393062888269279e-03,
"cpu_time": 3.2464683815488526e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.8286614486830765e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 69,
"real_time": 9.9131423116162196e+06,
"cpu_time": 1.9754072231884547e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3848431652878537e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 69,
"real_time": 9.8967294519146290e+06,
"cpu_time": 1.9714820942028936e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3904566314590459e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 69,
"real_time": 9.8791920269529019e+06,
"cpu_time": 1.9720379333332106e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3964753300123262e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 69,
"real_time": 9.9076000784618258e+06,
"cpu_time": 1.9724568072463270e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3867366197939420e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 69,
"real_time": 9.9150645344153699e+06,
"cpu_time": 1.9754340985509373e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3841869494174199e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.9023456806721911e+06,
"cpu_time": 1.9733636313043647e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3885397391941175e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time_median",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 9.9076000784618277e+06,
"cpu_time": 1.9724568072463267e+07,
"time_unit": "ns",
"bytes": 3.3554432000000000e+07,
"bytes_per_second": 3.3867366197939420e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4778183941188234e+04,
"cpu_time": 1.9093905607024033e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 5.0623797430694588e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 15,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):25/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.4923922490438712e-03,
"cpu_time": 9.6758171196269769e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.4939708938675228e-03,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 33,
"real_time": 2.1270128531437933e+07,
"cpu_time": 4.2347956666665629e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1550756217016249e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 33,
"real_time": 2.1301716566085815e+07,
"cpu_time": 4.2558018454545878e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1503970016596289e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 33,
"real_time": 2.1298880096186291e+07,
"cpu_time": 4.2528634515147962e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1508165545293765e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 33,
"real_time": 2.1281852415113740e+07,
"cpu_time": 4.2472590666668773e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1533375333597035e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 33,
"real_time": 2.1285207377690256e+07,
"cpu_time": 4.2438085333335981e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1528405060473623e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1287556997302808e+07,
"cpu_time": 4.2469057127272844e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1524934434595394e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time_median",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.1285207377690259e+07,
"cpu_time": 4.2472590666668773e+07,
"time_unit": "ns",
"bytes": 6.7108864000000000e+07,
"bytes_per_second": 3.1528405060473623e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.2947203839234737e+04,
"cpu_time": 8.2311363697613153e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.9175250568584495e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 16,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):26/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.0820524595072995e-04,
"cpu_time": 1.9381490728870999e-03,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.0825663597706382e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 18,
"real_time": 3.9346071374085218e+07,
"cpu_time": 7.7573423444442198e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4112104032932954e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 18,
"real_time": 3.9341955135265984e+07,
"cpu_time": 7.7515137499997556e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4115673087046890e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 18,
"real_time": 3.9374667116337352e+07,
"cpu_time": 7.7623858111110166e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4087330212452850e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 18,
"real_time": 3.9349325208200350e+07,
"cpu_time": 7.7622549499993622e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4109283269749489e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 18,
"real_time": 3.9361022205816373e+07,
"cpu_time": 7.7626025444437295e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4099146942420278e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9354608207941063e+07,
"cpu_time": 7.7592198799996182e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4104707508920493e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time_median",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 3.9349325208200350e+07,
"cpu_time": 7.7622549499993622e+07,
"time_unit": "ns",
"bytes": 1.3421772800000000e+08,
"bytes_per_second": 3.4109283269749489e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.3270145447655255e+04,
"cpu_time": 4.8370127073688971e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.1497612680204529e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 17,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):27/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 3.3719419534146384e-04,
"cpu_time": 6.2338904969517822e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.3712685198068894e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 9,
"real_time": 7.5637893544303045e+07,
"cpu_time": 1.4756728088890564e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5489546763061361e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 9,
"real_time": 7.5583902498086289e+07,
"cpu_time": 1.4758394877779007e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5514897634029484e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 9,
"real_time": 7.5506888329982758e+07,
"cpu_time": 1.4752505055556262e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5551121485350356e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 9,
"real_time": 7.5531440476576492e+07,
"cpu_time": 1.4741848311109605e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5539565286491013e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 9,
"real_time": 7.5557786557409495e+07,
"cpu_time": 1.4743390744443887e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5527173072498660e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5563582281271622e+07,
"cpu_time": 1.4750573415555868e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5524460848286171e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time_median",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 7.5557786557409495e+07,
"cpu_time": 1.4752505055556262e+08,
"time_unit": "ns",
"bytes": 2.6843545600000000e+08,
"bytes_per_second": 3.5527173072498660e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 5.0537028896814387e+04,
"cpu_time": 7.5911909492567385e+04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 2.3752569321570247e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 18,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):28/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 6.6880139044625411e-04,
"cpu_time": 5.1463700667060935e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 6.6862575122561378e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 5,
"real_time": 1.4803273379802704e+08,
"cpu_time": 2.8277869799999279e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6267040283975039e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 5,
"real_time": 1.4800633192062378e+08,
"cpu_time": 2.8288510140000653e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6273509723078971e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 5,
"real_time": 1.4805721342563629e+08,
"cpu_time": 2.8283978460003710e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6261043928781667e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 5,
"real_time": 1.4802939891815186e+08,
"cpu_time": 2.8253278500001216e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6267857325884686e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"family_index": 7,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 5,
"real_time": 1.4802623689174652e+08,
"cpu_time": 2.8251264720001924e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6268632052885365e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4803038299083710e+08,
"cpu_time": 2.8270980324001360e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6267616662921143e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time_median",
"family_index": 7,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.4802939891815186e+08,
"cpu_time": 2.8277869799999279e+08,
"time_unit": "ns",
"bytes": 5.3687091200000000e+08,
"bytes_per_second": 3.6267857325884686e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 1.8179734830143512e+04,
"cpu_time": 1.7505502580968695e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 4.4539348320333561e+05,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 19,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):29/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 1.2281083425467334e-04,
"cpu_time": 6.1920394624967998e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 1.2280748617779776e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 0,
"threads": 1,
"iterations": 2,
"real_time": 2.9301244020462036e+08,
"cpu_time": 5.2058296850009358e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6644922763353333e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 1,
"threads": 1,
"iterations": 2,
"real_time": 2.9362787306308746e+08,
"cpu_time": 5.2160496449994296e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6568116398449035e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 2,
"threads": 1,
"iterations": 2,
"real_time": 2.9363411664962769e+08,
"cpu_time": 5.2171576750004077e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6567338845070863e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 3,
"threads": 1,
"iterations": 2,
"real_time": 2.9321302473545074e+08,
"cpu_time": 5.2158673550002277e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6619854284057660e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"family_index": 7,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"run_type": "iteration",
"repetitions": 5,
"repetition_index": 4,
"threads": 1,
"iterations": 2,
"real_time": 2.9354733228683472e+08,
"cpu_time": 5.2186278300007415e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6578149616798820e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time_mean",
"family_index": 7,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "mean",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9340695738792419e+08,
"cpu_time": 5.2147064380003482e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6595676381545944e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time_median",
"family_index": 7,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "median",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.9354733228683472e+08,
"cpu_time": 5.2160496449994296e+08,
"time_unit": "ns",
"bytes": 1.0737418240000000e+09,
"bytes_per_second": 3.6578149616798820e+09,
"dst_gpu": 7.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time_stddev",
"family_index": 7,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "stddev",
"aggregate_unit": "time",
"iterations": 5,
"real_time": 2.7989456028732890e+05,
"cpu_time": 5.0826802769406058e+05,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 3.4926827853900502e+06,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": 0.0000000000000000e+00
},
{
"name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time_cv",
"family_index": 7,
"per_family_instance_index": 20,
"run_name": "Comm_prefetch_managed_GPUToGPU/0/7/log2(N):30/manual_time",
"run_type": "aggregate",
"repetitions": 5,
"threads": 1,
"aggregate_name": "cv",
"aggregate_unit": "percentage",
"iterations": 5,
"real_time": 9.5394656888544733e-04,
"cpu_time": 9.7468195714764535e-04,
"time_unit": "ns",
"bytes": 0.0000000000000000e+00,
"bytes_per_second": 9.5439765861283577e-04,
"dst_gpu": 0.0000000000000000e+00,
"src_gpu": NaN
}
]
}