CK BF16 Gemm #2617
Closed
CK BF16 Gemm #2617
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
|
This pull request was exported from Phabricator. Differential Revision: D57292145 |
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
jwfromm
added a commit
to jwfromm/FBGEMM
that referenced
this pull request
May 21, 2024
Summary: Implementation of BF16 Gemm using the latest features from CK. Performance is comparable with hipblas but often a little worse. Detailed benchmarking can be found [here](https://docs.google.com/spreadsheets/d/10b9mRM6xCi1Iv-mRGkPjk37DfYQEDx3zU-EmV9t7f0s/edit?usp=sharing). We see that for llama shapes, there likely isnt much benefit to this kernel. However, it may be useful for less common shapes that hipblas struggles with. We even see a few cases here where the ck kernel is slightly faster. Reviewed By: jianyuh Differential Revision: D57292145
|
This pull request was exported from Phabricator. Differential Revision: D57292145 |
jwfromm
added a commit
to jwfromm/FBGEMM
that referenced
this pull request
May 21, 2024
Summary: Implementation of BF16 Gemm using the latest features from CK. Performance is comparable with hipblas but often a little worse. Detailed benchmarking can be found [here](https://docs.google.com/spreadsheets/d/10b9mRM6xCi1Iv-mRGkPjk37DfYQEDx3zU-EmV9t7f0s/edit?usp=sharing). We see that for llama shapes, there likely isnt much benefit to this kernel. However, it may be useful for less common shapes that hipblas struggles with. We even see a few cases here where the ck kernel is slightly faster. Reviewed By: jianyuh Differential Revision: D57292145
|
This pull request was exported from Phabricator. Differential Revision: D57292145 |
Summary: Implementation of BF16 Gemm using the latest features from CK. Performance is comparable with hipblas but often a little worse. Detailed benchmarking can be found [here](https://docs.google.com/spreadsheets/d/10b9mRM6xCi1Iv-mRGkPjk37DfYQEDx3zU-EmV9t7f0s/edit?usp=sharing). We see that for llama shapes, there likely isnt much benefit to this kernel. However, it may be useful for less common shapes that hipblas struggles with. We even see a few cases here where the ck kernel is slightly faster. Reviewed By: jianyuh Differential Revision: D57292145
|
This pull request was exported from Phabricator. Differential Revision: D57292145 |
|
This pull request has been merged in 7930859. |
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: Implementation of BF16 Gemm using the latest features from CK. Performance is comparable with hipblas but often a little worse. Detailed benchmarking can be found here. We see that for llama shapes, there likely isnt much benefit to this kernel. However, it may be useful for less common shapes that hipblas struggles with. We even see a few cases here where the ck kernel is slightly faster.
Reviewed By: jianyuh
Differential Revision: D57292145