Skip to content

Conversation

hideaki-motoki
Copy link
Contributor

Resolves #5343.
This change improves the overall performance of [SD]GEMM, [SDCZ]SYMM, and [CZ]HEMM. The graphs below show the 12-thread performance improvement of [SD]GEMM on A64FX.
level3 sgemm nn
level3 dgemm nn

@hideaki-motoki hideaki-motoki marked this pull request as ready for review June 27, 2025 10:52
@martin-frbg martin-frbg added this to the 0.3.31 milestone Jun 27, 2025
@martin-frbg martin-frbg merged commit 334cd24 into OpenMathLib:develop Jun 27, 2025
84 of 87 checks passed
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

Successfully merging this pull request may close these issues.

Setting GEMM_PREFERED_SIZE parameter for A64FX
2 participants