reduce overhead for f8f8bf16_rowwise_grouped_dynamic on amd#3742
Closed
mxz297 wants to merge 1 commit into
Closed
Conversation
Summary: X-link: facebookresearch/FBGEMM#823 When there is no need to zeroing output tensor, the argument setup kernel currently will launch many wasted thread blocks, and that can cause significant overhead. So we separate argument setup kernels into two kernels based on whether we need zeroing or not. Differential Revision: D70327636
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D70327636 |
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
Contributor
|
This pull request has been merged in eee973c. |
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary:
X-link: https://github.com/facebookresearch/FBGEMM/pull/823
When there is no need to zeroing output tensor, the argument setup kernel currently will launch many wasted thread blocks, and that can cause significant overhead. So we separate argument setup kernels into two kernels based on whether we need zeroing or not.
Differential Revision: D70327636