Avatar for the OpenMathLib user
OpenMathLib
OpenBLAS
BlogDocsChangelog

Work around miscompilation of the AVX512 ?GEMM kernels by Windows LLVM

#5756Merged
Comparing
issue5267
(
c59578f
) with
develop
(
172f41c
)
CodSpeed Performance Gauge
0%
Untouched
62

Benchmarks

62 total
test_nrm2[100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+2%
38.7 µs38 µs
test_dot[100]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
+1%
22.6 µs22.4 µs
test_dot[1000]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
28.6 µs28.5 µs
test_dgbmv[1-100-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
42.6 µs42.4 µs
test_nrm2[1000-dz]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
35.8 µs35.7 µs
test_nrm2[1000-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
30.7 µs30.6 µs
test_nrm2[100-dz]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
29.1 µs29.1 µs
test_dgbmv[1-100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
38.1 µs38.1 µs
test_dgbmv[1-1000-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
83.8 µs83.7 µs
test_dgbmv[1-1000-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
99.9 µs99.8 µs
test_daxpy[100-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
25.4 µs25.4 µs
test_gesv[100-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
258 µs257.8 µs
test_daxpy[100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
24.4 µs24.4 µs
test_syev[50-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
1.4 ms1.4 ms
test_gesv[1000-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
93.3 ms93.3 ms
test_daxpy[1000-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
40.8 µs40.8 µs
test_gesv[100-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
938.4 µs938.4 µs
test_syrk[100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
339.9 µs339.9 µs
test_syrk[1000-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
65.4 ms65.4 ms
test_gesdd[mn1-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
94 ms94 ms
test_gesv[1000-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
52.6 ms52.6 ms
test_gemm[1000-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
426 ms426 ms
test_syrk[1000-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
476.4 ms476.4 ms
test_gemm[1000-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
875.6 ms875.6 ms
test_gemm[100-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
659.9 µs659.9 µs

Commits

Click on a commit to change the comparison range
Base
develop
172f41c
-0.01%
Work around miscompilation of the AVX512 ?GEMM kernels by Windows LLVM
94e053a
4 days ago
by martin-frbg
-0.04%
Quote the respective SUMM file on failure in BLAS2/3 tests
b9da7db
2 days ago
by martin-frbg
-0.01%
fix missing eol
d9786d3
22 hours ago
by martin-frbg
+0.1%
fix conditionals
c59578f
11 hours ago
by martin-frbg
© 2026 CodSpeed Technology
Home Terms Privacy Docs