perf improvement - Summary metric - #729
Open
mdebjit wants to merge 2 commits into
Open
Conversation
gjasny
reviewed
Aug 29, 2026
|
|
||
| if (sample_[item].value > v) { | ||
| --idx; | ||
| float value = buffer_[i]; |
Collaborator
There was a problem hiding this comment.
Is there a reason for using float instead of double here and below?
gjasny
force-pushed
the
user/debjit/summary-perf
branch
from
August 29, 2026 19:35
4082a62 to
ace740a
Compare
Collaborator
|
Hello, Thanks for working on this. The original code was written by Jupp and I never had to touch it. I used Claude to review it, create test cases and fixes. Could you please take a look if the commit I pushed on top makes sense at all? Thanks, |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
CKMS Quantiles/Summary Performance Improvements
Optimized insertion: Replaced linear search with binary search in the insertBatch algorithm, improving insertion speed.
Enhanced readability & maintainability: Streamlined index management in both the compress and insertBatch algorithms, resulting in cleaner, more maintainable code.
Prevent undefined behavior: Addressed potential issues in the compress method by eliminating vector element erasure during iteration, preventing iterator invalidation and out-of-bounds errors.
Pre-allocation: Reserved vector capacity upfront when the size is known, eliminating multiple resize operations and significantly enhancing performance.
The observations clearly indicate that for a limited number of quantiles (typically around 8), which represent the most common use case, there are substantial performance gains. However, for a larger number of quantiles (around 64), the performance improvements are either negligible or slightly diminished.