perf: optimize round in datafusion-functions#23471
Open
andygrove wants to merge 1 commit into
Open
Conversation
Jefffrey
reviewed
Jul 12, 2026
Comment on lines
+877
to
+880
| /// compiler can autovectorize. Requiring no null slots keeps the output | ||
| /// bit-identical to the fallible kernel: `unary` writes a computed value into | ||
| /// every slot while `try_unary` leaves null slots zeroed, so the two only agree | ||
| /// when there are no null slots. Returns `Ok(None)` when the fast path does not |
Contributor
There was a problem hiding this comment.
i feel we dont need to aim for this bit-identical approach? we can still apply this fast path even if there are nulls since the nulls should be masked anyway
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Which issue does this PR close?
N/A
Rationale for this change
Optimize an existing function
What changes are included in this PR?
round() over a no-null float column with scalar decimal_places now hoists the 10^dp factor out of the loop and uses the vectorizable infallible
unarykernel instead of per-elementtry_unary+powi, with a fallback preserving bit-identical output for null/array cases.Are these changes tested?
Existing tests
Benchmark (criterion):
Are there any user-facing changes?
No