performance: skip over any zero diagonal rows in a 2-D conv#2460
Merged
copybara-service[bot] merged 1 commit intomainfrom Dec 9, 2025
Merged
performance: skip over any zero diagonal rows in a 2-D conv#2460copybara-service[bot] merged 1 commit intomainfrom
copybara-service[bot] merged 1 commit intomainfrom
Conversation
a 2-D convolution is transformed into a large matrix vector product. when we diagonalize this filter matrix to evaluate this with halevi-shoup, we find many zero diagonals. this calculates the zero diagonals from the layout relation of the expanded diagonalized filter matrix and skips over the corresponding summands in the halevi-shoup implementation. Adds * fuzz testing, comparing both the diagonal skipping implementation and no skipping, and the naive impl * e2e test testing that only a restricted # of diagonals are multiplied * unit tests verifying that the calculation of the zero diagonals in right PiperOrigin-RevId: 842382620
copybara-service
bot
force-pushed
the
test_842323494
branch
from
177c310 to
7338398
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
performance: skip over any zero diagonal rows in a 2-D conv
a 2-D convolution is transformed into a large matrix vector product. when we diagonalize this filter matrix to evaluate this with halevi-shoup, we find many zero diagonals. this calculates the zero diagonals from the layout relation of the expanded diagonalized filter matrix and skips over the corresponding summands in the halevi-shoup implementation.
Adds