adriangb opened a new pull request, #26218: URL: https://github.com/apache/datafusion/pull/26218
Add a PushDownSemiJoin logical optimizer rule (datafusion.optimizer.enable_semi_join_pushdown, default true): - Push LeftSemi/LeftAnti joins below inner joins when all referenced left columns come from one input and the other input is not filtered, so the semi join removes rows before the larger inner join (TPC-H Q18). - For LeftSemi(L, Aggregate(group by k)) joined on L.x = k, semi join the aggregate input with the cheap filtered scan that L.x originates from, so groups that can never match are not computed (TPC-H Q2, Q17) -- 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]
