geoffreyclaude opened a new pull request, #23015: URL: https://github.com/apache/datafusion/pull/23015
## Which issue does this PR close? - Part of #19241. - Stacked on #23014. - Extracted from #19390. ## Rationale for this change This is one draft PR in the `IN LIST` optimization stack. It reuses commit `c2625de65` verbatim so the existing stack can be reviewed one step at a time. Once primitive lists are larger than the branchless thresholds, a compact open-addressing table avoids the generic hash set path and keeps probes simple. ## What changes are included in this PR? - Adds a direct-probe hash filter for larger primitive `IN` lists. - Uses open addressing with linear probing for membership checks. - Updates strategy selection to use direct probing above the branchless thresholds. ## Are these changes tested? Covered by the existing `IN LIST` test suite from the original stack. ## Are there any user-facing changes? No user-facing API changes. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
