[QST] why use AutoVectoringCopy rather LDSM in hopper mixed gemm?
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 10.5k
- Forks
- 2.1k
- Avg merge
- 3d 11h
- Merged PRs (30d)
- 7
Description
What is your question?
Hello folks,
I observe the SmemCopyAtomA in SM90_WS_RS collective builder is set to AutoVectorizingCopy. In 55_hopper_mixed_gemm example, narrower dtype (int8,int4....) will be operand A, my question is why we use AutoVectorizingCopyhere rather LDSM here?
https://github.com/NVIDIA/cutlass/blob/main/include/cutlass/gemm/collective/builders/sm90_gmma_builder.inl#L468
Thanks
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the SM90_WS_RS collective builder at include/cutlass/gemm/collective/builders/sm90_gmma_builder.inl around line 468, then inspect the 55_hopper_mixed_gemm example. Compare the roles of AutoVectorizingCopy and LDSM for operand A and document the reason for the selected copy atom, including the narrower dtypes mentioned in the question.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- performance
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100