zhangxffff commented on PR #20528: URL: https://github.com/apache/datafusion/pull/20528#issuecomment-3976258235
> ``` > in_list_cols/Int32/list=28/match=0%/nulls=0% 1.00 167.4±4.90µs ? ?/sec 8.64 1446.7±11.10µs ? ?/sec > in_list_cols/Int32/list=28/match=0%/nulls=20% 1.00 191.5±5.05µs ? ?/sec 16.27 3.1±0.04ms ? ?/sec > ``` > > Those are some pretty crazy improvements for Int32/Utf8 -- nice work > > I wonder why the others don't show a similar improvement This patch only optimizes the IN LIST path without static filters, which was benchmarked using `in_list_cols`. For IN LIST with a static filter, it uses a hash set for matching and is unchanged in this patch. Therefore, the `in_list` benchmarks do not show any improvement. -- 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]
