martin-frbg:woa_sum - Branch - OpenMathLib/OpenBLAS - CodSpeed

Blog Docs Changelog

Provide optimized ?SUM kernels for NeoverseN1 and related

#5621Merged

Comparing

martin-frbg:woa_sum

(

861b3db

) with

develop

(

413e609

)

0%

Untouched: 62

Benchmarks

62 total

test_nrm2[100-d]

benchmark/pybench/benchmarks/bench_blas.py

-2%

37.4 µs38 µs

test_daxpy[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

+1%

32.5 µs32.3 µs

test_daxpy[100-s]

benchmark/pybench/benchmarks/bench_blas.py

+1%

24.1 µs24 µs

test_daxpy[100-z]

benchmark/pybench/benchmarks/bench_blas.py

+1%

26 µs25.8 µs

test_syrk[100-z]

benchmark/pybench/benchmarks/bench_blas.py

-1%

852.2 µs856.6 µs

test_dgemv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

140.7 µs141.4 µs

test_daxpy[100-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

25.2 µs25.1 µs

test_daxpy[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

32.8 µs32.6 µs

test_nrm2[1000-dz]

benchmark/pybench/benchmarks/bench_blas.py

0%

35.2 µs35.4 µs

test_dgemv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

149.5 µs150 µs

test_nrm2[100-dz]

benchmark/pybench/benchmarks/bench_blas.py

0%

28.8 µs28.9 µs

test_syrk[100-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

472.5 µs473.9 µs

test_gesv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

256.9 µs257.6 µs

test_dot[100]

benchmark/pybench/benchmarks/bench_blas.py

0%

22.5 µs22.4 µs

test_daxpy[100-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

24.2 µs24.1 µs

test_dgbmv[1-100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

42.2 µs42.3 µs

test_dgbmv[1-100-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

40.3 µs40.4 µs

test_daxpy[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

40.7 µs40.6 µs

test_dgbmv[1-100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

37.2 µs37.3 µs

test_gesdd[mn0-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

109.3 µs109.1 µs

test_dgbmv[1-1000-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

119 µs118.8 µs

test_dgbmv[1-1000-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

74.9 µs75 µs

test_dgemv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

231.3 µs231 µs

test_dot[1000]

benchmark/pybench/benchmarks/bench_blas.py

0%

28.5 µs28.5 µs

test_nrm2[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

30.4 µs30.4 µs

Commits

Click on a commit to change the comparison range

Base

develop

413e609

-0.02%

Reuse ?SUM kernels from ThunderX2T99

861b3db

6 months ago

by martin-frbg

© 2026 CodSpeed Technology

Home Terms Privacy Docs