Reuse per-thread query buffers in IVFRaBitQFastScan compute_LUT#5123
Open
lyang24 wants to merge 1 commit intofacebookresearch:mainfrom
Open
Reuse per-thread query buffers in IVFRaBitQFastScan compute_LUT#5123lyang24 wants to merge 1 commit intofacebookresearch:mainfrom
lyang24 wants to merge 1 commit intofacebookresearch:mainfrom
Conversation
This updates the rebased branch to match the current main implementation. Instead of carrying the old residual-buffer overload forward, compute_LUT now reuses per-thread rotated_q and centroid_buf scratch space while keeping the newer compute_residual_LUT and compute_LUT_uint8 paths from main unchanged. The goal is to remove per-(query, probe) vector allocations from the float LUT path without changing distance math or the newer mainline interfaces.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The goal is to remove per-(query, probe) vector allocations from the float LUT path without changing distance math or the newer mainline interfaces.