perf(sql): speed up row counting in filter queries#6580
Merged
bluestreak01 merged 12 commits intomasterfrom Dec 28, 2025
Merged
perf(sql): speed up row counting in filter queries#6580bluestreak01 merged 12 commits intomasterfrom
bluestreak01 merged 12 commits intomasterfrom
Conversation
puzpuzpuz
added
SQL
|
Important Review skippedAuto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the ✨ Finishing touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Contributor
[PR Coverage check]😍 pass : 101 / 106 (95.28%) file detail
|
bluestreak01
approved these changes
Dec 28, 2025
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Implements a fast-path for count-only (
SELECT count(*) FROM table WHERE ...) queries that avoids materializing matching rows, instead just incrementing a counter. This is highly effective when many rows match the filter.Key changes:
- Does not accept
rowslist for filtered row indexes, but only return the number of rows satisfying the filter- 16-bit, 32-bit, and 64-bit SIMD paths have no vector-to-scalar domain crossing while the generic SIMD path uses
popcntinstruction on bitmasks - much faster than scatter-gather- Removed
rows_start_offsetparameter from filter functions as it was always set to0- Functions now work with relative indices directly, reducing arithmetic overhead
countOnlyflag inPageFrameReduceTask- Used only in
calculateSize()implementation inAsync*FilteredfactoriesJIT assembly before/after
Sample query:
AVX2 Loop Comparison
AVX2 loop body before (compacted to instructions only):
AVX2 loop body after:
The count-only optimization eliminates:
pext/pdep/vpermps)This reduces the loop from ~20 instructions to 6 instructions (~70% reduction), with all remaining instructions being simple and fully pipelined.
Benchmarks
Key observations:
testCountOnlyFiltershows 60-92% improvements for NEQ predicatestestFilter) are unchanged - as expected, since they need to materialize rowsBefore:
After: