improve write performance by ~10x #4277
Closed
Conversation
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
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
This pull request was exported from Phabricator. Differential Revision: D76073692 |
steven1327
force-pushed
the
export-D76073692
branch
from
f68b118 to
ddc9181
Compare
steven1327
pushed a commit
to steven1327/FBGEMM-1
that referenced
this pull request
Jun 6, 2025
Summary: X-link: facebookresearch/FBGEMM#1354 we used [] to get a pointer to ith entry in weights. This is very slow. In this diff, we use raw pointer access to get the ith pointer. This improve the write performance by 10x and bring write performance on the same scale as read performance. Reviewed By: q10 Differential Revision: D76073692
steven1327
force-pushed
the
export-D76073692
branch
from
ddc9181 to
4f7b07a
Compare
steven1327
pushed a commit
to steven1327/FBGEMM-1
that referenced
this pull request
Jun 6, 2025
Summary: X-link: facebookresearch/FBGEMM#1354 we used [] to get a pointer to ith entry in weights. This is very slow. In this diff, we use raw pointer access to get the ith pointer. This improve the write performance by 10x and bring write performance on the same scale as read performance. Reviewed By: q10 Differential Revision: D76073692
|
This pull request was exported from Phabricator. Differential Revision: D76073692 |
steven1327
pushed a commit
to steven1327/FBGEMM-1
that referenced
this pull request
Jun 6, 2025
Summary: Pull Request resolved: pytorch#4277 X-link: facebookresearch/FBGEMM#1354 we used [] to get a pointer to ith entry in weights. This is very slow. In this diff, we use raw pointer access to get the ith pointer. This improve the write performance by 10x and bring write performance on the same scale as read performance. Reviewed By: q10 Differential Revision: D76073692
steven1327
force-pushed
the
export-D76073692
branch
from
4f7b07a to
615080b
Compare
Summary: Pull Request resolved: pytorch#4277 X-link: facebookresearch/FBGEMM#1354 we used [] to get a pointer to ith entry in weights. This is very slow. In this diff, we use raw pointer access to get the ith pointer. This improve the write performance by 10x and bring write performance on the same scale as read performance. Reviewed By: q10 Differential Revision: D76073692
|
This pull request was exported from Phabricator. Differential Revision: D76073692 |
steven1327
force-pushed
the
export-D76073692
branch
from
615080b to
a344996
Compare
|
This pull request has been merged in 7a913d5. |
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: we used [] to get a pointer to ith entry in weights. This is very slow. In this diff, we use raw pointer access to get the ith pointer. This improve the write performance by 10x and bring write performance on the same scale as read performance.
Reviewed By: q10
Differential Revision: D76073692