Specialize more cases to improve EmbeddingSpMDMNBitBenchmark #5245
+86
−15
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: X-link: facebookresearch/FBGEMM#2236 `EmbeddingSpMDMNBitBenchmark` uses the `scale_bias_last == true && has_weight == true` variant which wasn't previously specialized in the code because we did not see it in the bigger test suites. However it does not cost too much code size to add it and makes this benchmark look better... Also added block_size==576, block_size==36 and block_size==72 specialization seen in some other models. This adds ~50K in code size (compared to currently ~150K for the existing specializations) which seems acceptable. Differential Revision: D87289832
Contributor
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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/2236
EmbeddingSpMDMNBitBenchmarkuses thescale_bias_last == true && has_weight == truevariant which wasn't previously specialized in the code because we did not see it in the bigger test suites. However it does not cost too much code size to add it and makes this benchmark look better... Also added block_size==576, block_size==36 and block_size==72 specialization seen in some other models.This adds ~50K in code size (compared to currently ~150K for the existing specializations) which seems acceptable.
Differential Revision: D87289832