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_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_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_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_daxpy[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

40.7 µs40.6 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_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_gesv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

695.5 µs694.8 µs

test_dgbmv[1-100-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

38 µs38 µs

test_dgemv[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

7 ms7 ms

test_gemm[100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

273.2 µs273.1 µs

test_dgemv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

104.1 µs104 µs

test_gemm[100-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

471.3 µs471.2 µs

test_gesv[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

93.3 ms93.3 ms

test_dgemv[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

14.8 ms14.8 ms

test_gesdd[mn1-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

65.2 ms65.2 ms

test_gesv[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

353.6 ms353.6 ms

test_gemm[100-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

659.6 µs659.6 µs

test_syev[200-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

49.1 ms49.1 ms

test_syrk[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

130.4 ms130.3 ms

Commits

Click on a commit to change the comparison range

Base

develop

413e609

-0.02%

Reuse ?SUM kernels from ThunderX2T99

861b3db

2 months ago

by martin-frbg

© 2026 CodSpeed Technology

Home Terms Privacy Docs