Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

cblas_cgemm does not use avx512 #28

Open
dkfirsov opened this issue Jan 21, 2025 · 1 comment
Open

cblas_cgemm does not use avx512 #28

dkfirsov opened this issue Jan 21, 2025 · 1 comment

Comments

@dkfirsov
Copy link

I discovered that compiling library for target zen4 with gcc version 11.3.1 20221121 (Red Hat 11.3.1-4) (GCC) does not enable avx512 acceleration for cblas_cgemm, The performance remains the same as for target zen3. There I used: ./configure CFLAGS="-O3" --enable-cblas --blas-int-size=64 zen4
The same issue I observed in blis-4.0.0. Moreover the performance was a little bit degraded. My code went up in time to 151s. (blis-5.0.0) from (blis-4.0.0) 146s.

@kvaragan
Copy link
Collaborator

Hi,
We haven't written AVX512 kernels for cgemm yet. Right now, they still use avx2 kernels. Around 5.2 they will be available.
--blas-int-size=64 just builds ILP64.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants