Add reverse! and reverse#102
Open
shreyas-omkar wants to merge 1 commit into
Open
Conversation
Reverse a vector in-place by swapping symmetric pairs, so only length ÷ 2 threads are launched and no temporary array is allocated. Odd-length arrays keep their middle element in place. Also provides a two-argument reverse!(dst, src) writing into a caller-supplied buffer, and an allocating reverse(v). Measured against CUDA.jl and torch.flip on an RTX 3060 and an RTX 5080: at large n all three converge on device-to-device copy bandwidth (within 1-2% of copyto!, 92% of peak on the 3060), since reverse reads n and writes n with no reuse to exploit. Below 100M elements this is 2.4-2.8x faster than torch.flip, which carries a flat ~70us dispatch floor. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
shreyas-omkar
marked this pull request as ready for review
July 22, 2026 06:32
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Reverse a vector in-place by swapping symmetric pairs, so only length ÷ 2 threads are launched and no temporary array is allocated. Odd-length arrays keep their middle element in place.
Also provides a two-argument reverse!(dst, src) writing into a caller-supplied buffer, and an allocating reverse(v).
Measured against CUDA.jl and torch.flip on an RTX 3060 and an RTX 5080: at large n all three converge on device-to-device copy bandwidth (within 1-2% of copyto!, 92% of peak on the 3060), since reverse reads n and writes n with no reuse to exploit. Below 100M elements this is 2.4-2.8x faster than torch.flip, which carries a flat ~70us dispatch floor.