Repository navigation
perf: divide once per row in decimal / and div - #7699
Draft
mbutrovich wants to merge 2 commits into
Draft
mbutrovich wants to merge 2 commits into
mbutrovich wants to merge 2 commits into
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Which issue does this PR close?
Closes #7694.
Rationale for this change
See #7694.
What changes are included in this PR?
spark_decimal_div_internalrescales the operands to the result scale instead of one digit past it, so thei128andBigIntbranches each divide once per row./rounds half away from zero from the remainder, anddivtruncates./anddiv#7694 describes. Both branches compute the same quotient.benches/decimal_div.rsgets cases with Spark's result types:/onDecimal(10, 4)byDecimal(10, 3),divat scale 0, theBigIntbranch, and integerdivonDecimal(19, 0)with small and with full-range values. Arrow's decimaldivis the control, since this PR doesn't touch it.How are these changes tested?
The tests are in
native/spark-expr/src/math_funcs/div.rs.test_decimal_div_matches_exact_quotientcompares every row of/anddivwith an exactBigIntquotient across scale combinations on both branches. It covers both signs, exact halves, and values at the precision bound. It also passes againstmain, so it checks that the rewrite changes no result.test_integral_divide_overflow_through_kernelchecks the ANSI long-overflow error on both branches.Benchmarks
TODO
AI usage disclosure
I wrote this PR with help from Claude but understand and support the core approach, implementation, and test coverage.