EliasFano.Build: less iterations in upperBits loop#19556
Merged
Giulio2002 merged 4 commits intomainfrom Mar 2, 2026
Merged
Conversation
AskAlexSharov
changed the title
JkLondon
approved these changes
Mar 2, 2026
sudeepdino008
pushed a commit
that referenced
this pull request
Mar 4, 2026
Idea: instead of iterating over bits, iterate over words and get first-non-zero bit in word Details: all Build() functions use naive O(64) bit scanning per word. Replace with `bits.TrailingZeros64 + word &= word-1` to iterate only over set bits directly. This compiles to a single `TZCNT` instruction and eliminates all the skipped-zero-bit iterations. Result: `2.75x` speedup. Also speedup scales with sparsity of upperBits — at ~34% density, the inner loop runs ~3x fewer iterations ``` cpu: AMD EPYC 4344P 8-Core Processor 100 elements sequence: 233.0 ns/op -> 81.98 ns/op 1M elements sequence: 2344235 ns/op -> 824938 ns/op ```
sudeepdino008
pushed a commit
that referenced
this pull request
Mar 4, 2026
Idea: instead of iterating over bits, iterate over words and get first-non-zero bit in word Details: all Build() functions use naive O(64) bit scanning per word. Replace with `bits.TrailingZeros64 + word &= word-1` to iterate only over set bits directly. This compiles to a single `TZCNT` instruction and eliminates all the skipped-zero-bit iterations. Result: `2.75x` speedup. Also speedup scales with sparsity of upperBits — at ~34% density, the inner loop runs ~3x fewer iterations ``` cpu: AMD EPYC 4344P 8-Core Processor 100 elements sequence: 233.0 ns/op -> 81.98 ns/op 1M elements sequence: 2344235 ns/op -> 824938 ns/op ```
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.
Idea: instead of iterating over bits, iterate over words and get first-non-zero bit in word
Details: all Build() functions use naive O(64) bit scanning per word. Replace with
bits.TrailingZeros64 + word &= word-1to iterate only over set bits directly. This compiles to a singleTZCNTinstruction and eliminates all the skipped-zero-bit iterations.Result:
2.75xspeedup. Also speedup scales with sparsity of upperBits — at ~34% density, the inner loop runs ~3x fewer iterations