Use less thread blocks for find_uncached kernel #3101
Closed
Conversation
This file contains 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
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
|
This pull request was exported from Phabricator. Differential Revision: D62401630 |
Summary: Pull Request resolved: pytorch#3101 X-link: facebookresearch/FBGEMM#190 Find uncached takes quite long time and this often overalap with the main stream in prefetch mode. We do want it to be overlapped with other kernels so it has minimal effect on the main stream. This will likely make cache prefetch taking slightly longer (not significantly as prefetch spent longest time in data transfer), but will make overlapping main stream kernels faster. Differential Revision: D62401630
|
This pull request was exported from Phabricator. Differential Revision: D62401630 |
levythu
force-pushed
the
export-D62401630
branch
from
2d24e5e
to
fb6eb24
Compare
|
This pull request has been merged in 20cb987. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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:
Find uncached takes quite long time and this often overalap with the main stream in prefetch mode. We do want it to be overlapped with other kernels so it has minimal effect on the main stream.
This will likely make cache prefetch taking slightly longer (not significantly as prefetch spent longest time in data transfer), but will make overlapping main stream kernels faster.
Differential Revision: D62401630