Adam Binford created SPARK-37466: ------------------------------------ Summary: Support subexpression elimination in lambda functions Key: SPARK-37466 URL: https://issues.apache.org/jira/browse/SPARK-37466 Project: Spark Issue Type: Improvement Components: SQL Affects Versions: 3.3.0 Reporter: Adam Binford
https://issues.apache.org/jira/browse/SPARK-37019 will add codegen support for higher order functions. However we can't support subexpression elimination inside of lambda functions because subexpressions are evaluated once per row at the beginning of the codegen. Common expressions inside lambda functions can easily result in performance degradation due to multiple evaluations of the same expression. Subexpression elimination inside of lambda functions needs to be handled specially to be evaluated once per function invocation. -- This message was sent by Atlassian Jira (v8.20.1#820001) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org