perf/sorter: use custom binary encoding for binary-collated keys#4895
Open
jussisaurio wants to merge 1 commit intomainfrom
Open
perf/sorter: use custom binary encoding for binary-collated keys#4895jussisaurio wants to merge 1 commit intomainfrom
jussisaurio wants to merge 1 commit intomainfrom
Conversation
This comment has been minimized.
This comment has been minimized.
Merging this PR will degrade performance by 32.44%
Performance Changes
Comparing |
94389c5 to
954ddd3
Compare
LeMikaelF
approved these changes
Jan 27, 2026
Collaborator
Author
|
I'll do a self-review pass of this at some pt and then merge |
954ddd3 to
a5eb97a
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
we can get 2x performance for binary-collated in-memory sorter workloads by encoding the sort keys into binary, so sorting becomes a simple lexicographic byte comparison. keys are constructed one time (
O(n)) and stored in bump arenaimplementation fully written by Codex 5.2. interestingly enough I was originally attempting to implement the sorting algorithm from this expired oracle patent but accidentally discovered during benchmarking that using binary-encoded keys for binary-collation was at least twice as fast as our current ValueRef::cmp based implementation, so decided to pivot to that.
Note: this implementation diverges from
ValueRefin thatValueRefactually panics onNaNsince it assumes total order - this implementation sorts `NaN´ first without panicing.