ChipKerchner:fixbfloat16Tobf16conversions - Branch - OpenMathLib/OpenBLAS

Prevent possible conversion from bfloat16 to __bf16 - RISC-V

#5527Merged

Comparing

ChipKerchner:fixbfloat16Tobf16conversions

(

00a7336

) with

develop

(

3a9da52

)

Untouched: 62

Benchmarks

Passed

test_nrm2[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

+1%

30.5 µs30.2 µs

test_nrm2[100-dz]

benchmark/pybench/benchmarks/bench_blas.py

+1%

28.8 µs28.6 µs

test_nrm2[100-d]

benchmark/pybench/benchmarks/bench_blas.py

+1%

37.8 µs37.6 µs

test_daxpy[100-c]

benchmark/pybench/benchmarks/bench_blas.py

25.2 µs25.1 µs

test_nrm2[1000-dz]

benchmark/pybench/benchmarks/bench_blas.py

35.4 µs35.2 µs

test_dot[100]

benchmark/pybench/benchmarks/bench_blas.py

22.5 µs22.4 µs

test_daxpy[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

40.7 µs40.5 µs

test_daxpy[100-s]

benchmark/pybench/benchmarks/bench_blas.py

24.1 µs24 µs

test_daxpy[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

32.4 µs32.3 µs

test_dgbmv[1-1000-s]

benchmark/pybench/benchmarks/bench_blas.py

75.2 µs74.9 µs

test_daxpy[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

32.8 µs32.7 µs

test_gesv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

395.3 µs394.6 µs

test_dgbmv[1-100-d]

benchmark/pybench/benchmarks/bench_blas.py

38 µs37.9 µs

test_dgbmv[1-100-z]

benchmark/pybench/benchmarks/bench_blas.py

42.2 µs42.1 µs

test_dgbmv[1-1000-z]

benchmark/pybench/benchmarks/bench_blas.py

119 µs118.8 µs

test_daxpy[100-z]

benchmark/pybench/benchmarks/bench_blas.py

25.9 µs25.8 µs

test_dot[1000]

benchmark/pybench/benchmarks/bench_blas.py

28.5 µs28.4 µs

test_gesv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

696.1 µs695.5 µs

test_dgbmv[1-100-c]

benchmark/pybench/benchmarks/bench_blas.py

40.3 µs40.3 µs

test_dgemv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

103.8 µs103.7 µs

test_syrk[100-d]

benchmark/pybench/benchmarks/bench_blas.py

339.7 µs339.5 µs

test_gesv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

257 µs256.8 µs

test_syrk[100-s]

benchmark/pybench/benchmarks/bench_blas.py

213.5 µs213.4 µs

test_gesv[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

353.6 ms353.4 ms

test_gemm[100-d]

benchmark/pybench/benchmarks/bench_blas.py

471.2 µs471.1 µs

test_syrk[100-z]

benchmark/pybench/benchmarks/bench_blas.py

856.6 µs856.4 µs

test_dgemv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

149.8 µs149.8 µs

test_gemm[100-s]

benchmark/pybench/benchmarks/bench_blas.py

273 µs273 µs

test_dgemv[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

13.9 ms13.9 ms

test_syev[200-d]

benchmark/pybench/benchmarks/bench_blas.py

58.6 ms58.6 ms

test_syev[200-s]

benchmark/pybench/benchmarks/bench_blas.py

49.1 ms49.1 ms

test_syev[50-s]

benchmark/pybench/benchmarks/bench_blas.py

1.3 ms1.3 ms

test_dgbmv[1-1000-c]

benchmark/pybench/benchmarks/bench_blas.py

99.5 µs99.5 µs

test_gesv[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

93.3 ms93.3 ms

test_gesdd[mn1-s]

benchmark/pybench/benchmarks/bench_blas.py

65.2 ms65.2 ms

test_gemm[100-z]

benchmark/pybench/benchmarks/bench_blas.py

1.2 ms1.2 ms

test_syrk[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

227.6 ms227.5 ms

test_syrk[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

130.4 ms130.3 ms

test_gesdd[mn1-d]

benchmark/pybench/benchmarks/bench_blas.py

93.8 ms93.8 ms

test_gesv[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

188.6 ms188.6 ms

test_gemm[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

117.4 ms117.4 ms

test_dgemv[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

26.3 ms26.3 ms

test_gemm[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

239.4 ms239.4 ms

test_dgemv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

231 µs231 µs

test_gemm[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

875.6 ms875.6 ms

test_gemm[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

426 ms426 ms

test_syrk[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

476.4 ms476.4 ms

test_dgemv[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

14.8 ms14.8 ms

test_syrk[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

65.4 ms65.4 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_dgbmv[1-1000-d]

benchmark/pybench/benchmarks/bench_blas.py

83.6 µs83.6 µs

test_gesdd[mn0-s]

benchmark/pybench/benchmarks/bench_blas.py

109.1 µs109.2 µs

test_gemm[100-c]

benchmark/pybench/benchmarks/bench_blas.py

659.5 µs659.6 µs

test_dgemv[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

7 ms7 ms

test_gesdd[mn0-d]

benchmark/pybench/benchmarks/bench_blas.py

119.9 µs120 µs

test_syev[50-d]

benchmark/pybench/benchmarks/bench_blas.py

1.4 ms1.4 ms

test_dgemv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

141.1 µs141.2 µs

test_dgbmv[1-100-s]

benchmark/pybench/benchmarks/bench_blas.py

37.3 µs37.3 µs

test_gesv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

937.2 µs938.3 µs

test_daxpy[100-d]

benchmark/pybench/benchmarks/bench_blas.py

24.2 µs24.2 µs

test_daxpy[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

27.4 µs27.5 µs

Commits

Click on a commit to change the comparison range

Base

develop

3a9da52

+0.01%

Prevent possible conversion from bfloat16 to __bf16.

edf2e59

1 month ago

by ChipKerchner

+0.08%

Missing one gemv conversion.

00a7336

1 month ago

by ChipKerchner

Home Terms Privacy Docs