NVIDIA / NVIDIA/cutlass

[QST] Terminology question on GMMA::ScaleOut::One

Open
#2,046 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

? - Needs Triage inactive-30d inactive-90d question
Dominant language
C++
Stars
10.5k
Forks
2.1k
Avg merge
3d 11h
Merged PRs (30d)
7

Description

What does this code do?

tiled_mma.accumulate_ = GMMA::ScaleOut::One;

For example, in "cutlass/include/cutlass/gemm/collective/sm90_mma_tma_gmma_rs_warpspecialized.hpp"

I have no idea when it is set two 1 or 0, it seems random.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the assignment to tiled_mma.accumulate_ in cutlass/include/cutlass/gemm/collective/sm90_mma_tma_gmma_rs_warpspecialized.hpp. Trace the definition and uses of GMMA::ScaleOut::One, including where the value is set to 0 or 1. Done means the terminology and the conditions for each value are clearly documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
hpc
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.