Precompute segments offsets and use them as segment's identity#15509
Merged
Conversation
Motivation: Reusing a segment perform a data-dependent multiply to obtain the recycled segment's starting index slowing down segment's allocation Modifications: Store in the segments free-list the precomputed offsets, performing just a lookup Result: Faster segment's allocation
Contributor
Author
|
This is not key but the Whilst a more contained change could be by just changing free list fill to perform the multiplication on the fly using the counter. |
There was a problem hiding this comment.
Pull Request Overview
This PR optimizes segment allocation in the adaptive pooling allocator by precomputing segment offsets and storing them directly in the free list, eliminating the need for runtime multiplication to calculate segment starting positions.
- Precomputes segment offsets at chunk controller factory initialization
- Stores actual offset values in the free list instead of segment IDs
- Removes segment ID tracking by using start index as both adjustment and segment identifier
chrisvest
approved these changes
Aug 5, 2025
Member
|
Thanks! |
normanmaurer
pushed a commit
that referenced
this pull request
Sep 15, 2025
Motivation: Reusing a segment perform a data-dependent multiply to obtain the recycled segment's starting index slowing down segment's allocation Modifications: Store in the segments free-list the precomputed offsets, performing just a lookup Result: Faster segment's allocation Co-authored-by: Chris Vest <christianvest_hansen@apple.com>
normanmaurer
added a commit
that referenced
this pull request
Sep 15, 2025
… (#15656) Motivation: Reusing a segment perform a data-dependent multiply to obtain the recycled segment's starting index slowing down segment's allocation Modifications: Store in the segments free-list the precomputed offsets, performing just a lookup Result: Faster segment's allocation Co-authored-by: Francesco Nigro <nigro.fra@gmail.com> Co-authored-by: Chris Vest <christianvest_hansen@apple.com>
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.
Motivation:
Reusing a segment perform a data-dependent multiply to obtain the recycled segment's starting index slowing down segment's allocation
Modifications:
Store in the segments free-list the precomputed offsets, performing just a lookup
Result:
Faster segment's allocation