amritahs-ibm:use_lxvp_builtins - Branch - OpenMathLib/OpenBLAS - CodSpeed

Blog Docs Changelog

DRAFT PR: Power10: Replace vector pair loads with __builtin_vsx_lxvp

Comparing

amritahs-ibm:use_lxvp_builtins

(

3863a77

) with

develop

(

91f97c6

)

0%

Untouched: 62

Benchmarks

62 total

test_daxpy[1000-s]

benchmark/pybench/benchmarks/bench_blas.py

+1%

24 µs23.7 µs

test_daxpy[100-d]

benchmark/pybench/benchmarks/bench_blas.py

+1%

20.7 µs20.5 µs

test_daxpy[100-c]

benchmark/pybench/benchmarks/bench_blas.py

+1%

21.7 µs21.6 µs

test_daxpy[100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

20.5 µs20.5 µs

test_daxpy[1000-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

29.2 µs29.1 µs

test_daxpy[1000-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

28.4 µs28.3 µs

test_dot[1000]

benchmark/pybench/benchmarks/bench_blas.py

0%

24.6 µs24.5 µs

test_dgbmv[1-100-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

34.6 µs34.5 µs

test_daxpy[1000-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

37.1 µs37 µs

test_dgbmv[1-100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

39 µs38.8 µs

test_dgbmv[1-1000-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

71.4 µs71.2 µs

test_dgbmv[1-1000-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

80.3 µs80.1 µs

test_daxpy[100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

22.4 µs22.3 µs

test_gesv[100-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

391.6 µs390.6 µs

test_gesdd[mn0-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

108.2 µs108 µs

test_dgbmv[1-1000-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

96.3 µs96.2 µs

test_dgbmv[1-100-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

37 µs37 µs

test_dgbmv[1-100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

34 µs34 µs

test_gesv[100-c]

benchmark/pybench/benchmarks/bench_blas.py

0%

693.3 µs692.8 µs

test_gemm[100-d]

benchmark/pybench/benchmarks/bench_blas.py

0%

468.2 µs468 µs

test_dgemv[100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

229.1 µs229 µs

test_syrk[100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

210.3 µs210.2 µs

test_gesv[100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

253.9 µs253.8 µs

test_gemm[100-s]

benchmark/pybench/benchmarks/bench_blas.py

0%

270.1 µs270 µs

test_syrk[100-z]

benchmark/pybench/benchmarks/bench_blas.py

0%

853.4 µs853.2 µs

Commits

Click on a commit to change the comparison range

Base

develop

91f97c6

+0.05%

Power10: Replace vector pair loads with __builtin_vsx_lxvp

3863a77

1 day ago

by amritahs-ibm

© 2026 CodSpeed Technology

Home Terms Privacy Docs