Skip to content

Instantly share code, notes, and snippets.

@pashu123
Created April 9, 2025 17:15
Show Gist options
  • Save pashu123/f61fbb3744c71d97716113fac0ad015c to your computer and use it in GitHub Desktop.
Save pashu123/f61fbb3744c71d97716113fac0ad015c to your computer and use it in GitHub Desktop.
---------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
---------------------------------------------------------------------------------------------------------
BM__4_14336_4096/process_time/real_time 0.517 ms 0.524 ms 1353 items_per_second=1.93239k/s
BM__4_14336_4096/process_time/real_time 0.517 ms 0.524 ms 1353 items_per_second=1.93329k/s
BM__4_14336_4096/process_time/real_time 0.517 ms 0.524 ms 1353 items_per_second=1.93427k/s
BM__4_14336_4096/process_time/real_time 0.517 ms 0.524 ms 1353 items_per_second=1.93414k/s
BM__4_14336_4096/process_time/real_time 0.517 ms 0.524 ms 1353 items_per_second=1.93428k/s
BM__4_14336_4096/process_time/real_time_mean 0.517 ms 0.524 ms 5 items_per_second=1.93368k/s
BM__4_14336_4096/process_time/real_time_median 0.517 ms 0.524 ms 5 items_per_second=1.93414k/s
BM__4_14336_4096/process_time/real_time_stddev 0.000 ms 0.000 ms 5 items_per_second=0.829524/s
BM__4_14336_4096/process_time/real_time_cv 0.04 % 0.01 % 5 items_per_second=0.04%
---------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
---------------------------------------------------------------------------------------------------------
BM__4_14336_4096/process_time/real_time 0.510 ms 0.517 ms 1373 items_per_second=1.9605k/s
BM__4_14336_4096/process_time/real_time 0.510 ms 0.517 ms 1373 items_per_second=1.96171k/s
BM__4_14336_4096/process_time/real_time 0.510 ms 0.517 ms 1373 items_per_second=1.96061k/s
BM__4_14336_4096/process_time/real_time 0.510 ms 0.517 ms 1373 items_per_second=1.96102k/s
BM__4_14336_4096/process_time/real_time 0.510 ms 0.517 ms 1373 items_per_second=1.96171k/s
BM__4_14336_4096/process_time/real_time_mean 0.510 ms 0.517 ms 5 items_per_second=1.96111k/s
BM__4_14336_4096/process_time/real_time_median 0.510 ms 0.517 ms 5 items_per_second=1.96102k/s
BM__4_14336_4096/process_time/real_time_stddev 0.000 ms 0.000 ms 5 items_per_second=0.581968/s
BM__4_14336_4096/process_time/real_time_cv 0.03 % 0.03 % 5 items_per_second=0.03%
---------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
---------------------------------------------------------------------------------------------------------
BM__4_4096_14336/process_time/real_time 0.528 ms 0.534 ms 1334 items_per_second=1.89482k/s
BM__4_4096_14336/process_time/real_time 0.529 ms 0.535 ms 1334 items_per_second=1.89186k/s
BM__4_4096_14336/process_time/real_time 0.527 ms 0.534 ms 1334 items_per_second=1.89638k/s
BM__4_4096_14336/process_time/real_time 0.528 ms 0.535 ms 1334 items_per_second=1.89472k/s
BM__4_4096_14336/process_time/real_time 0.529 ms 0.535 ms 1334 items_per_second=1.89149k/s
BM__4_4096_14336/process_time/real_time_mean 0.528 ms 0.535 ms 5 items_per_second=1.89386k/s
BM__4_4096_14336/process_time/real_time_median 0.528 ms 0.535 ms 5 items_per_second=1.89472k/s
BM__4_4096_14336/process_time/real_time_stddev 0.001 ms 0.001 ms 5 items_per_second=2.09838/s
BM__4_4096_14336/process_time/real_time_cv 0.11 % 0.13 % 5 items_per_second=0.11%
---------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
---------------------------------------------------------------------------------------------------------
BM__4_4096_14336/process_time/real_time 0.510 ms 0.517 ms 1388 items_per_second=1.95899k/s
BM__4_4096_14336/process_time/real_time 0.511 ms 0.518 ms 1388 items_per_second=1.95798k/s
BM__4_4096_14336/process_time/real_time 0.511 ms 0.518 ms 1388 items_per_second=1.95783k/s
BM__4_4096_14336/process_time/real_time 0.511 ms 0.518 ms 1388 items_per_second=1.95797k/s
BM__4_4096_14336/process_time/real_time 0.511 ms 0.519 ms 1388 items_per_second=1.95789k/s
BM__4_4096_14336/process_time/real_time_mean 0.511 ms 0.518 ms 5 items_per_second=1.95813k/s
BM__4_4096_14336/process_time/real_time_median 0.511 ms 0.518 ms 5 items_per_second=1.95797k/s
BM__4_4096_14336/process_time/real_time_stddev 0.000 ms 0.001 ms 5 items_per_second=0.485124/s
BM__4_4096_14336/process_time/real_time_cv 0.02 % 0.12 % 5 items_per_second=0.02%
----------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
----------------------------------------------------------------------------------------------------------
BM__4_128256_4096/process_time/real_time 4.26 ms 4.23 ms 164 items_per_second=234.968/s
BM__4_128256_4096/process_time/real_time 4.25 ms 4.23 ms 164 items_per_second=235.246/s
BM__4_128256_4096/process_time/real_time 4.25 ms 4.23 ms 164 items_per_second=235.096/s
BM__4_128256_4096/process_time/real_time 4.25 ms 4.23 ms 164 items_per_second=235.117/s
BM__4_128256_4096/process_time/real_time 4.25 ms 4.23 ms 164 items_per_second=235.24/s
BM__4_128256_4096/process_time/real_time_mean 4.25 ms 4.23 ms 5 items_per_second=235.133/s
BM__4_128256_4096/process_time/real_time_median 4.25 ms 4.23 ms 5 items_per_second=235.117/s
BM__4_128256_4096/process_time/real_time_stddev 0.002 ms 0.003 ms 5 items_per_second=0.115226/s
BM__4_128256_4096/process_time/real_time_cv 0.05 % 0.06 % 5 items_per_second=0.05%
----------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
----------------------------------------------------------------------------------------------------------
BM__4_128256_4096/process_time/real_time 4.25 ms 4.23 ms 165 items_per_second=235.115/s
BM__4_128256_4096/process_time/real_time 4.25 ms 4.23 ms 165 items_per_second=235.169/s
BM__4_128256_4096/process_time/real_time 4.25 ms 4.22 ms 165 items_per_second=235.291/s
BM__4_128256_4096/process_time/real_time 4.25 ms 4.23 ms 165 items_per_second=235.062/s
BM__4_128256_4096/process_time/real_time 4.25 ms 4.22 ms 165 items_per_second=235.306/s
BM__4_128256_4096/process_time/real_time_mean 4.25 ms 4.23 ms 5 items_per_second=235.189/s
BM__4_128256_4096/process_time/real_time_median 4.25 ms 4.23 ms 5 items_per_second=235.169/s
BM__4_128256_4096/process_time/real_time_stddev 0.002 ms 0.004 ms 5 items_per_second=0.10726/s
BM__4_128256_4096/process_time/real_time_cv 0.05 % 0.09 % 5 items_per_second=0.05%
--------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
--------------------------------------------------------------------------------------------------------
BM__4_4096_4096/process_time/real_time 0.141 ms 0.152 ms 4989 items_per_second=7.06838k/s
BM__4_4096_4096/process_time/real_time 0.140 ms 0.150 ms 4989 items_per_second=7.13353k/s
BM__4_4096_4096/process_time/real_time 0.139 ms 0.149 ms 4989 items_per_second=7.16936k/s
BM__4_4096_4096/process_time/real_time 0.139 ms 0.149 ms 4989 items_per_second=7.19062k/s
BM__4_4096_4096/process_time/real_time 0.139 ms 0.149 ms 4989 items_per_second=7.18283k/s
BM__4_4096_4096/process_time/real_time_mean 0.140 ms 0.150 ms 5 items_per_second=7.14894k/s
BM__4_4096_4096/process_time/real_time_median 0.139 ms 0.149 ms 5 items_per_second=7.16936k/s
BM__4_4096_4096/process_time/real_time_stddev 0.001 ms 0.001 ms 5 items_per_second=50.0748/s
BM__4_4096_4096/process_time/real_time_cv 0.70 % 0.83 % 5 items_per_second=0.70%
--------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
--------------------------------------------------------------------------------------------------------
BM__4_4096_4096/process_time/real_time 0.161 ms 0.172 ms 4382 items_per_second=6.20173k/s
BM__4_4096_4096/process_time/real_time 0.162 ms 0.172 ms 4382 items_per_second=6.19135k/s
BM__4_4096_4096/process_time/real_time 0.161 ms 0.172 ms 4382 items_per_second=6.21373k/s
BM__4_4096_4096/process_time/real_time 0.161 ms 0.172 ms 4382 items_per_second=6.20224k/s
BM__4_4096_4096/process_time/real_time 0.161 ms 0.172 ms 4382 items_per_second=6.19629k/s
BM__4_4096_4096/process_time/real_time_mean 0.161 ms 0.172 ms 5 items_per_second=6.20107k/s
BM__4_4096_4096/process_time/real_time_median 0.161 ms 0.172 ms 5 items_per_second=6.20173k/s
BM__4_4096_4096/process_time/real_time_stddev 0.000 ms 0.000 ms 5 items_per_second=8.35796/s
BM__4_4096_4096/process_time/real_time_cv 0.13 % 0.21 % 5 items_per_second=0.13%
--------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
--------------------------------------------------------------------------------------------------------
BM__4_1024_4096/process_time/real_time 0.072 ms 0.082 ms 11476 items_per_second=13.9637k/s
BM__4_1024_4096/process_time/real_time 0.072 ms 0.083 ms 11476 items_per_second=13.9834k/s
BM__4_1024_4096/process_time/real_time 0.072 ms 0.084 ms 11476 items_per_second=13.8915k/s
BM__4_1024_4096/process_time/real_time 0.073 ms 0.085 ms 11476 items_per_second=13.6625k/s
BM__4_1024_4096/process_time/real_time 0.073 ms 0.086 ms 11476 items_per_second=13.6266k/s
BM__4_1024_4096/process_time/real_time_mean 0.072 ms 0.084 ms 5 items_per_second=13.8255k/s
BM__4_1024_4096/process_time/real_time_median 0.072 ms 0.084 ms 5 items_per_second=13.8915k/s
BM__4_1024_4096/process_time/real_time_stddev 0.001 ms 0.001 ms 5 items_per_second=169.214/s
BM__4_1024_4096/process_time/real_time_cv 1.23 % 1.58 % 5 items_per_second=1.22%
--------------------------------------------------------------------------------------------------------
Benchmark Time CPU Iterations UserCounters...
--------------------------------------------------------------------------------------------------------
BM__4_1024_4096/process_time/real_time 0.079 ms 0.090 ms 10644 items_per_second=12.7058k/s
BM__4_1024_4096/process_time/real_time 0.079 ms 0.090 ms 10644 items_per_second=12.7143k/s
BM__4_1024_4096/process_time/real_time 0.077 ms 0.088 ms 10644 items_per_second=13.0377k/s
BM__4_1024_4096/process_time/real_time 0.079 ms 0.090 ms 10644 items_per_second=12.7061k/s
BM__4_1024_4096/process_time/real_time 0.079 ms 0.090 ms 10644 items_per_second=12.656k/s
BM__4_1024_4096/process_time/real_time_mean 0.078 ms 0.090 ms 5 items_per_second=12.764k/s
BM__4_1024_4096/process_time/real_time_median 0.079 ms 0.090 ms 5 items_per_second=12.7061k/s
BM__4_1024_4096/process_time/real_time_stddev 0.001 ms 0.001 ms 5 items_per_second=154.753/s
BM__4_1024_4096/process_time/real_time_cv 1.19 % 1.24 % 5 items_per_second=1.21%
Running with vector distribution
iree-benchmark-module --benchmark_repetitions=5 --device=hip://0 --device_allocator=caching --module=file_4_14336_4096.mlir_w.vmfb --function=_4_14336_4096 --input=4x4096xf16=0.5 --input=14336x4096xf16=0.5
Running without vector distribution
Running with vector distribution
iree-benchmark-module --benchmark_repetitions=5 --device=hip://0 --device_allocator=caching --module=file_4_4096_14336.mlir_w.vmfb --function=_4_4096_14336 --input=4x14336xf16=0.5 --input=4096x14336xf16=0.5
Running without vector distribution
Running with vector distribution
iree-benchmark-module --benchmark_repetitions=5 --device=hip://0 --device_allocator=caching --module=file_4_128256_4096.mlir_w.vmfb --function=_4_128256_4096 --input=4x4096xf16=0.5 --input=128256x4096xf16=0.5
Running without vector distribution
Running with vector distribution
iree-benchmark-module --benchmark_repetitions=5 --device=hip://0 --device_allocator=caching --module=file_4_4096_4096.mlir_w.vmfb --function=_4_4096_4096 --input=4x4096xf16=0.5 --input=4096x4096xf16=0.5
Running without vector distribution
Running with vector distribution
iree-benchmark-module --benchmark_repetitions=5 --device=hip://0 --device_allocator=caching --module=file_4_1024_4096.mlir_w.vmfb --function=_4_1024_4096 --input=4x4096xf16=0.5 --input=1024x4096xf16=0.5
Running without vector distribution
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment