chore: avoid redundant IndexDocument construction in heap emplace#152
Open
longway-code wants to merge 1 commit intoalibaba:mainfrom
Open
chore: avoid redundant IndexDocument construction in heap emplace#152longway-code wants to merge 1 commit intoalibaba:mainfrom
longway-code wants to merge 1 commit intoalibaba:mainfrom
Conversation
…e cannot improve top-k In IndexDocumentHeap::emplace, the parent ailego::Heap::emplace constructs the IndexDocument object before checking whether the candidate score beats the current heap front. For rejected candidates this construction is wasted. Add an early-exit guard: when the heap is full, skip the emplace call entirely if score >= front().score(). The short-circuit evaluation of || ensures front() is only accessed when the heap is non-empty. Benchmark (N=100k, dim=128, topk=10, 200 queries): ~14% latency reduction.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
IndexDocumentHeap::emplacenow checksscore < front().score()before calling intoailego::Heap, avoiding unnecessary object construction for candidates that would be rejected anyway.Performance
Tested locally, decreased ~15% end-to-end latency of
FlatSearcher::search_impl(N=100k, dim=128, topk=10, FP32 SquaredEuclidean, 200 queries averaged).All Tests Passsed