tree 17ff6b4833d2b5662412676e85195548615646a0
parent dc20db303207841720052527bfc50cae8052fba5
author Ahmed Taei <ataei@google.com> 1628569457 -0700
committer Ahmed Taei <ataei@google.com> 1628569457 -0700

Refactor small_blas_gemm_benchmark

This allows benchmarking both dynamic and static problem sizes.

On my X86 2Ghz machine:

CPU Caches:
  L1 Data 32 KiB (x48)
  L1 Instruction 32 KiB (x48)
  L2 Unified 1024 KiB (x48)
  L3 Unified 39424 KiB (x2)

----------------------------------------------------------------------------------------------
Benchmark                                                    Time             CPU   Iterations
----------------------------------------------------------------------------------------------
BM_MatrixMatrixMultiplyEigen_Static_2x3x4                 10.9 ns         10.9 ns     63960496
BM_MatrixMatrixMultiplyEigen_Static_3x3x3                 11.9 ns         11.9 ns     58093785
BM_MatrixMatrixMultiplyEigen_Static_4x4x4                 24.9 ns         24.9 ns     28540133
BM_MatrixMatrixMultiplyEigen_Static_8x8x8                  258 ns          258 ns      2755921
BM_MatrixMatrixMultiplyEigen_Static_9x9x3                  255 ns          255 ns      2778628
BM_MatrixMatrixMultiplyEigen_Static_9x3x3                 37.7 ns         37.7 ns     18556359
BM_MatrixMatrixMultiplyEigen_Static_3x9x9                  220 ns          220 ns      3195163
BM_MatrixMatrixMultiplyEigen_Dynamic_2x3x4                37.8 ns         37.7 ns     18491162
BM_MatrixMatrixMultiplyEigen_Dynamic_3x3x3                48.8 ns         48.8 ns     13724884
BM_MatrixMatrixMultiplyEigen_Dynamic_4x4x4                74.5 ns         74.5 ns      9313146
BM_MatrixMatrixMultiplyEigen_Dynamic_8x8x8                 271 ns          271 ns      2595807
BM_MatrixMatrixMultiplyEigen_Dynamic_9x9x3                 259 ns          259 ns      2688515
BM_MatrixMatrixMultiplyEigen_Dynamic_9x3x3                 123 ns          123 ns      5792115
BM_MatrixMatrixMultiplyEigen_Dynamic_3x9x9                 236 ns          236 ns      2963896
BM_MatrixMatrixMultiplyNaive_Static_2x3x4                 12.2 ns         12.2 ns     56472772
BM_MatrixMatrixMultiplyNaive_Static_3x3x3                 15.5 ns         15.5 ns     44346456
BM_MatrixMatrixMultiplyNaive_Static_4x4x4                 41.5 ns         41.5 ns     17196984
BM_MatrixMatrixMultiplyNaive_Static_8x8x8                  199 ns          199 ns      3561730
BM_MatrixMatrixMultiplyNaive_Static_9x9x3                  148 ns          148 ns      4764814
BM_MatrixMatrixMultiplyNaive_Static_9x3x3                 38.4 ns         38.4 ns     17259019
BM_MatrixMatrixMultiplyNaive_Static_3x9x9                  115 ns          115 ns      6104752
BM_MatrixMatrixMultiplyNaive_Dynamic_2x3x4                9.66 ns         9.66 ns     74722971
BM_MatrixMatrixMultiplyNaive_Dynamic_3x3x3                13.0 ns         13.0 ns     53435308
BM_MatrixMatrixMultiplyNaive_Dynamic_4x4x4                47.8 ns         47.8 ns     14358184
BM_MatrixMatrixMultiplyNaive_Dynamic_8x8x8                 200 ns          200 ns      3572809
BM_MatrixMatrixMultiplyNaive_Dynamic_9x9x3                 104 ns          104 ns      6793797
BM_MatrixMatrixMultiplyNaive_Dynamic_9x3x3                34.0 ns         34.0 ns     20790695
BM_MatrixMatrixMultiplyNaive_Dynamic_3x9x9                 130 ns          130 ns      5170402
BM_MatrixTransposeMatrixMultiplyEigen_Static_2x3x4        10.3 ns         10.3 ns     69105234
BM_MatrixTransposeMatrixMultiplyEigen_Static_3x3x3        28.9 ns         28.9 ns     24478934
BM_MatrixTransposeMatrixMultiplyEigen_Static_4x4x4        23.7 ns         23.7 ns     29351926
BM_MatrixTransposeMatrixMultiplyEigen_Static_8x8x8         233 ns          233 ns      2929398
BM_MatrixTransposeMatrixMultiplyEigen_Static_9x9x3         211 ns          211 ns      3287409
BM_MatrixTransposeMatrixMultiplyEigen_Static_9x3x3        26.5 ns         26.5 ns     26515136
BM_MatrixTransposeMatrixMultiplyEigen_Static_3x9x9         196 ns          196 ns      3594314
BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_2x3x4       9.05 ns         9.05 ns     77621001
BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_3x3x3       11.1 ns         11.1 ns     62227812
BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_4x4x4       25.5 ns         25.5 ns     27356089
BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_8x8x8        248 ns          248 ns      2834983
BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_9x9x3        229 ns          229 ns      3082369
BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_9x3x3       28.4 ns         28.4 ns     24318629
BM_MatrixTransposeMatrixMultiplyEigen_Dynamic_3x9x9        229 ns          229 ns      3091288
BM_MatrixTransposeMatrixMultiplyNaive_Static_2x3x4        11.0 ns         11.0 ns     63773538
BM_MatrixTransposeMatrixMultiplyNaive_Static_3x3x3        19.1 ns         19.1 ns     37003139
BM_MatrixTransposeMatrixMultiplyNaive_Static_4x4x4        49.1 ns         49.1 ns     14142301
BM_MatrixTransposeMatrixMultiplyNaive_Static_8x8x8         244 ns          244 ns      2874755
BM_MatrixTransposeMatrixMultiplyNaive_Static_9x9x3         140 ns          140 ns      4992156
BM_MatrixTransposeMatrixMultiplyNaive_Static_9x3x3        46.2 ns         46.2 ns     15068317
BM_MatrixTransposeMatrixMultiplyNaive_Static_3x9x9         112 ns          112 ns      6213574
BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_2x3x4       9.74 ns         9.74 ns     72155001
BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_3x3x3       11.5 ns         11.5 ns     60070577
BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_4x4x4       52.5 ns         52.5 ns     13473642
BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_8x8x8        224 ns          224 ns      3124264
BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_9x9x3       98.0 ns         98.0 ns      7199292
BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_9x3x3       34.7 ns         34.6 ns     20203685
BM_MatrixTransposeMatrixMultiplyNaive_Dynamic_3x9x9        105 ns          105 ns      6653151

Change-Id: Iee403b4d27801d1614ecc1f78a1f8c0011514bd7