martin-frbg:issue5497 - Branch - OpenMathLib/OpenBLAS

Add test for SHGEMM

#5499

Comparing

martin-frbg:issue5497

(

87470a3

) with

develop

(

b6d5057

)

Untouched: 62

Benchmarks

Passed

test_daxpy[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

+1%

27.6 µs27.4 µs

test_daxpy[100-d]

benchmark/pybench/benchmarks/bench_blas.py

+1%

24.3 µs24.1 µs

test_daxpy[100-z]

benchmark/pybench/benchmarks/bench_blas.py

+1%

25.9 µs25.8 µs

test_nrm2[100-dz]

benchmark/pybench/benchmarks/bench_blas.py

+1%

29 µs28.9 µs

test_daxpy[100-c]

benchmark/pybench/benchmarks/bench_blas.py

25.2 µs25.1 µs

test_daxpy[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

32.8 µs32.7 µs

test_dot[1000]

benchmark/pybench/benchmarks/bench_blas.py

28.5 µs28.4 µs

test_dot[100]

benchmark/pybench/benchmarks/bench_blas.py

22.4 µs22.4 µs

test_daxpy[100-s]

benchmark/pybench/benchmarks/bench_blas.py

24.1 µs24.1 µs

test_dgbmv[1-100-d]

benchmark/pybench/benchmarks/bench_blas.py

38 µs37.9 µs

test_daxpy[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

40.6 µs40.5 µs

test_nrm2[1000-dz]

benchmark/pybench/benchmarks/bench_blas.py

35.5 µs35.5 µs

test_dgemv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

104 µs103.8 µs

test_dgbmv[1-1000-s]

benchmark/pybench/benchmarks/bench_blas.py

75 µs74.9 µs

test_dgbmv[1-1000-c]

benchmark/pybench/benchmarks/bench_blas.py

99.5 µs99.4 µs

test_dgbmv[1-100-s]

benchmark/pybench/benchmarks/bench_blas.py

37.2 µs37.2 µs

test_daxpy[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

32.4 µs32.4 µs

test_dgbmv[1-1000-z]

benchmark/pybench/benchmarks/bench_blas.py

118.8 µs118.8 µs

test_dgemv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

231.2 µs231.1 µs

test_syev[50-d]

benchmark/pybench/benchmarks/bench_blas.py

1.4 ms1.4 ms

test_gesv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

257.1 µs257 µs

test_dgbmv[1-1000-d]

benchmark/pybench/benchmarks/bench_blas.py

83.7 µs83.6 µs

test_syrk[100-d]

benchmark/pybench/benchmarks/bench_blas.py

339.6 µs339.5 µs

test_dgemv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

141.3 µs141.2 µs

test_dgemv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

149.8 µs149.8 µs

test_gesv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

937.7 µs937.6 µs

test_gemm[100-z]

benchmark/pybench/benchmarks/bench_blas.py

1.2 ms1.2 ms

test_dgemv[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

7 ms7 ms

test_gemm[100-d]

benchmark/pybench/benchmarks/bench_blas.py

471.3 µs471.3 µs

test_nrm2[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

30.5 µs30.5 µs

test_syrk[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

227.5 ms227.5 ms

test_syrk[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

65.4 ms65.4 ms

test_syrk[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

130.4 ms130.4 ms

test_syrk[100-s]

benchmark/pybench/benchmarks/bench_blas.py

213.4 µs213.4 µs

test_gemm[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

426 ms426 ms

test_gemm[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

239.4 ms239.4 ms

test_gesv[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

188.6 ms188.6 ms

test_gemm[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

875.6 ms875.6 ms

test_syev[50-s]

benchmark/pybench/benchmarks/bench_blas.py

1.3 ms1.3 ms

test_syrk[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

476.4 ms476.4 ms

test_gesv[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

93.3 ms93.3 ms

test_syrk[100-z]

benchmark/pybench/benchmarks/bench_blas.py

856.5 µs856.5 µs

test_gemm[100-c]

benchmark/pybench/benchmarks/bench_blas.py

659.6 µs659.6 µs

test_gesv[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

353.6 ms353.6 ms

test_dgemv[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

26.3 ms26.3 ms

test_syev[200-s]

benchmark/pybench/benchmarks/bench_blas.py

49.1 ms49.1 ms

test_gesdd[mn1-s]

benchmark/pybench/benchmarks/bench_blas.py

65.2 ms65.2 ms

test_gemm[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

117.4 ms117.4 ms

test_gesv[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

52.6 ms52.6 ms

test_syrk[100-c]

benchmark/pybench/benchmarks/bench_blas.py

472.4 µs472.4 µs

test_dgemv[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

14.8 ms14.8 ms

test_syev[200-d]

benchmark/pybench/benchmarks/bench_blas.py

58.6 ms58.6 ms

test_gesdd[mn1-d]

benchmark/pybench/benchmarks/bench_blas.py

93.9 ms93.9 ms

test_gesv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

395 µs395 µs

test_gemm[100-s]

benchmark/pybench/benchmarks/bench_blas.py

273.2 µs273.2 µs

test_dgemv[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

13.9 ms13.9 ms

test_gesv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

696.1 µs696.2 µs

test_gesdd[mn0-d]

benchmark/pybench/benchmarks/bench_blas.py

120 µs120.1 µs

test_dgbmv[1-100-c]

benchmark/pybench/benchmarks/bench_blas.py

40.2 µs40.3 µs

test_gesdd[mn0-s]

benchmark/pybench/benchmarks/bench_blas.py

109.1 µs109.3 µs

test_dgbmv[1-100-z]

benchmark/pybench/benchmarks/bench_blas.py

42.1 µs42.2 µs

test_nrm2[100-d]

benchmark/pybench/benchmarks/bench_blas.py

-1%

38 µs38.5 µs

Commits

Click on a commit to change the comparison range

Base

develop

b6d5057

-0.01%

Add test for SHGEMM

09c1877

3 days ago

by martin-frbg

+0.09%

remove spurious POSIX define

fba2014

3 days ago

by martin-frbg

-0.02%

fix missed bfloat/hfloat edit Co-authored-by: Christopher Sidebottom <chris.sidebottom@arm.com>

a5fda2e

3 days ago

by martin-frbg

remove unused definitions

87470a3

15 hours ago

by martin-frbg

Home Terms Privacy Docs