You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
The text was updated successfully, but these errors were encountered:
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.
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.
The text was updated successfully, but these errors were encountered: