reduce compilation size and time #886
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
Summary: This patch does refactoring for FBGEMM to slightly reduce compilation size and time associated with `cub`. 1. Moved an inline function `asynchronous_complete_cumsum()` from `embedding_backward_template_helpers.cuh` to `split_embeddings_utils.cu`, which is the only code that uses this function. 2. Instead of calling a template function `cub::DeviceRadixSort::SortPairs`, call a non-static function in FBGEMM to avoid expanding a template function in every `gen_embedding_backward_*` code. Reviewed By: jspark1105 Differential Revision: D33801456 fbshipit-source-id: 6188def8808c9f73a630f1ccdd71c45674f2d255
Contributor
|
This pull request was exported from Phabricator. Differential Revision: D33801456 |
q10
added a commit
to q10/FBGEMM
that referenced
this pull request
Apr 10, 2025
Summary: Pull Request resolved: facebookresearch/FBGEMM#886 - Limit the number of ROCm hardware targets to reduce Nova ROCm build times X-link: pytorch#3797 Reviewed By: sryap Differential Revision: D70949678 Pulled By: q10 fbshipit-source-id: a14cc0f12c7988aa3e9b68549bad9d109f1d7ca6
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Outdated suggestions cannot be applied.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.
Summary:
This patch does refactoring for FBGEMM to slightly reduce compilation size and time associated with
cub.asynchronous_complete_cumsum()fromembedding_backward_template_helpers.cuhtosplit_embeddings_utils.cu, which is the only code that uses this function.cub::DeviceRadixSort::SortPairs, call a non-static function in FBGEMM to avoid expanding a template function in everygen_embedding_backward_*code.Reviewed By: jspark1105
Differential Revision: D33801456