Repository navigation
Conversation
Dr-Emann
added this pull request to stack #381
October 9, 2026 19:59
Dr-Emann
changed the title
Open
Collapse the branchy loop/break merge in the array-store SIMD union and xor into a single while loop. It picks the next input vector with core::hint::select_unpredictable, which hints the compiler to select without branching, because which side advances is essentially unpredictable. This ports the equivalent change from CRoaring. Split the inputs with `as_chunks::<LANES>()` and load whole chunks with `load_array_ref` instead of indexing slices by `8 * i`. A slice pattern on the chunk lists handles the scalar fallback. `select_unpredictable` now picks the chunk and the index to advance together. This has a nice benefit of removing a fair number of bounds checks
Dr-Emann
force-pushed
the
stable_simd_refactor
branch
from
October 11, 2026 02:53
fec473a to
d626bbb
Compare
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Collapse the branchy loop/break merge in the array-store SIMD union and xor into a single while loop. It picks the next input vector with core::hint::select_unpredictable, which hints the compiler to select without branching, because which side advances is essentially unpredictable. This ports the equivalent change from CRoaring.
Split the inputs with
as_chunks::<LANES>()and load whole chunks withload_array_refinstead of indexing slices by8 * i. A slice pattern on the chunk lists handles the scalar fallback.select_unpredictablenow picks the chunk and the index to advance together.This has a nice benefit of removing a fair number of bounds checks