NVIDIA / NVIDIA/cutlass

[QST]Why sm90 mma has prologue and mainloop?

Open
#1,725 2 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 is your question?
Here prologue is not only for initialize, it also has cute::gemm. Why? What is the benefit and meaning here? Overlap? How?

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 SM90 MMA implementation and trace how its prologue and mainloop invoke cute::gemm. Compare the responsibilities and execution order of both entry points, then document the intended benefit, including whether and how work overlaps. Done means the explanation answers why GEMM appears in the prologue and clarifies the overlap model.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
hpc
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.