Skip to content

Conversation

@shalinib-ibm
Copy link
Contributor

This patch moves calls from packing routines from inside MMA kernel to one step behind.
Current call stack :
matmul->mnpack->gemm->kernel->PackTanspose+MMA instructions
Changed call stack:
matmul->mnpack->gemm->PackTranspose->kernel->MMA instrutcions

Not seeing much perf difference with this change

Make sure to read the contributing guidelines before submitting a PR

This patch moves calls from packing routines from inside
MMA kernel to one step behind.
Current call stack :
matmul->mnpack->gemm->kernel->PackTanspose+MMA instructions
Changed call stack:
matmul->mnpack->gemm->PackTranspose->kernel->MMA instrutcions

Not seeing much perf difference with this change

Signed-off-by: Shalini Salomi Bodapati <[email protected]>
@github-actions github-actions bot added the ggml changes relating to the ggml tensor library for machine learning label Jun 9, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ggml changes relating to the ggml tensor library for machine learning

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant