NVIDIA / NVIDIA/cutlass

[QST]how to use one threadblock process one matrix multiplication?

Open
#1,617 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

I have a thousand of tasks in parallel, each task has two steps:

  1. matrix multiplication, C[i] = A[i]*B[i], the matrix sizes are non-uniform, and (m, n, k) is in range 10 ~1024.
  2. some operation on C[i], like scatter matrix C[i] to another matrix D[i]

I can use grouped GEMM in cutlass to do step 1 and then use a kernel to complete step 2 on all of the tasks. but it looks not efficient enough. I think it will be better if I use one thread block to do the step 1 and 2 for each task in parallel.

Here is my question: is there any similar example in cutlass? or any suggestion on this problem?

Thanks

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 by reviewing CUTLASS grouped GEMM examples and the existing kernel approach described in the issue. Compare the two-step grouped GEMM plus scatter workflow with a one-threadblock-per-task design for non-uniform matrix sizes. The issue is complete only when a supported example or a concrete, benchmarked design is identified.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.