Avatar for the OpenMathLib user
OpenMathLib
OpenBLAS
BlogDocsChangelog

Fix incorrect leading dimension check for SME SGEMM direct kernel path

#5805Merged
Comparing
quic:fix/sgemm-direct-leading-dim-check
(
c32eefd
) with
develop
(
3da0ff7
)
CodSpeed Performance Gauge
0%
Untouched
62

Benchmarks

62 total
test_daxpy[100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
-1%
24.3 µs24.5 µs
test_daxpy[100-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
-1%
25.3 µs25.5 µs
test_dgbmv[1-100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
-1%
38 µs38.3 µs
test_dot[1000]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
-1%
28.4 µs28.6 µs
test_nrm2[1000-dz]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
-1%
35.5 µs35.7 µs
test_daxpy[1000-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
32.9 µs33.1 µs
test_dgbmv[1-100-c]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
40.4 µs40.6 µs
test_daxpy[100-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
26 µs26.2 µs
test_nrm2[100-dz]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
28.9 µs29 µs
test_dgbmv[1-100-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
42.3 µs42.5 µs
test_daxpy[1000-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
27.7 µs27.8 µs
test_daxpy[1000-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
40.7 µs40.9 µs
test_dot[100]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
22.5 µs22.5 µs
test_dgbmv[1-100-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
37.4 µs37.5 µs
test_daxpy[100-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
24.2 µs24.3 µs
test_dgbmv[1-1000-z]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
118.9 µs119.2 µs
test_dgbmv[1-1000-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
75.2 µs75.4 µs
test_gesdd[mn0-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
122.6 µs122.4 µs
test_gesdd[mn0-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
111.3 µs111.5 µs
test_daxpy[1000-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
32.6 µs32.7 µs
test_nrm2[1000-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
30.6 µs30.6 µs
test_dgemv[100-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
104.2 µs104.3 µs
test_nrm2[100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
37.7 µs37.7 µs
test_dgemv[100-d]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
141.7 µs141.6 µs
test_gemm[100-s]
benchmark/pybench/benchmarks/bench_blas.py
CodSpeed Performance Gauge
0%
273.5 µs273.6 µs

Commits

Click on a commit to change the comparison range
Base
develop
3da0ff7
-0.12%
Fix incorrect leading dimension check for SME SGEMM direct kernel path
c32eefd
3 months ago
by matcraje
© 2026 CodSpeed Technology
Home Terms Privacy Docs