Open
Conversation
We go over all the bits and pieces necessary to write a multiCTA kernels in Gluon. We finalise with a recipe to get SOTA perf on a dense matmul. We also change the bench tool used in tutorial 8 (as cudagraph bench does not zero out the L2) and the numbers from cublas as I was not able to repro the numbers there (probably they have optimised cublas in a newer version).
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 32682077d6
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Jokeren
reviewed
Mar 6, 2026
|
|
||
|
|
||
| if __name__ == "__main__" and not is_blackwell(): | ||
| raise RuntimeError("This tutorial requires a Blackwell NVIDIA GPU") |
Contributor
There was a problem hiding this comment.
hmm, why you still have the is_hopper_or_newer function then?
| # `two_ctas=True`, because only the lead CTA waits before issuing the MMA. | ||
| # | ||
| # Once one `tcgen05_mma` in a kernel uses 2CTA mode, all of the `tcgen05_mma` | ||
| # instructions in that kernel must use 2CTA mode. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
We go over all the bits and pieces necessary to write a multiCTA kernels
in Gluon. We finalise with a recipe to get SOTA perf on a dense matmul.
We also change the bench tool used in tutorial 8 (as cudagraph bench
does not zero out the L2) and the numbers from cublas as I was not
able to repro the numbers there (probably they have optimised cublas
in a newer version).