quic:fix-sgemmdirect-sme1 - Branch - OpenMathLib/OpenBLAS - CodSpeed

Blog Docs Changelog

Add vector registers to clobber list to prevent compiler optimization.

#5203Merged

Comparing

quic:fix-sgemmdirect-sme1

(

04915be

) with

develop

(

3e961c2

)

0%

Untouched: 62

Benchmarks

62 total

test_dgemv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

+1%

147.6 µs146.8 µs

test_dgemv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

+1%

149.3 µs148.5 µs

test_daxpy[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

40.1 µs40 µs

test_dgemv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

110.2 µs109.8 µs

test_daxpy[100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

25.3 µs25.3 µs

test_dgbmv[1-100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

41.5 µs41.4 µs

test_nrm2[1000-dz]

benchmark/pybench/benchmarks/bench_blas.py

0%

34.9 µs34.8 µs

test_daxpy[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

31.9 µs31.8 µs

test_daxpy[100-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

24.6 µs24.6 µs

test_daxpy[100-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

23.6 µs23.5 µs

test_dot[1000]

benchmark/pybench/benchmarks/bench_blas.py

0%

27.9 µs27.8 µs

test_daxpy[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

26.9 µs26.9 µs

test_gesv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

693.8 µs693.1 µs

test_dgbmv[1-100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

36.6 µs36.6 µs

test_syev[50-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

1.4 ms1.4 ms

test_syrk[100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

213 µs212.9 µs

test_gemm[100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

272.7 µs272.6 µs

test_daxpy[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

32.2 µs32.2 µs

test_syrk[100-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

339.3 µs339.1 µs

test_dgemv[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

14.7 ms14.7 ms

test_dgemv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

230.5 µs230.5 µs

test_syrk[100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

855.5 µs855.4 µs

test_nrm2[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

29.8 µs29.8 µs

test_gesdd[mn1-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

93.9 ms93.9 ms

test_gemm[100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

1.2 ms1.2 ms

Commits

Click on a commit to change the comparison range

Base

develop

3e961c2

+0.04%

Add vector registers to clobber list to prevent compiler optimization.

04915be

10 months ago

by vaiskv

© 2026 CodSpeed Technology

Home Terms Privacy Docs