NVIDIA / NVIDIA/cutlass

[QST] How local_partition works?

Open
#1,244 5 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

auto tC = make_layout(make_shape(Int<16>{}, Int<16>{}));
auto tCsA = local_partition(sA, tC, threadIdx.x, Step<_1, X>{});

But I get (_8,_8) as tCsA's shape, why???

I am learning code: https://github.com/NVIDIA/cutlass/blob/main/examples/cute/tutorial/sgemm_nt_1.cu

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 examples/cute/tutorial/sgemm_nt_1.cu and trace the local_partition call using the provided layout and thread index. Read the relevant CuTe layout and partitioning documentation or implementation to determine why tCsA has shape (_8,_8). Done means providing a clear explanation grounded in the example.

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
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.