-
Notifications
You must be signed in to change notification settings - Fork 232
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Implement build-side rules for shuffle hash join #342
Implement build-side rules for shuffle hash join #342
Conversation
build |
overall this makes sense. At the time I implemented this I think all we supported was left and inner joins and I probably should have tagged it better to ensure that. |
condition.map(_.convertToGpu()), | ||
childPlans(0).convertIfNeeded(), | ||
childPlans(1).convertIfNeeded()) | ||
} | ||
|
||
private def canBuildRight(joinType: JoinType): Boolean = joinType match { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
might be nice to add comment about these must match the spark join selection critera for ShuffledHashJoinExec
build |
Signed-off-by: spark-rapids automation <70000568+nvauto@users.noreply.github.com>
This PR implements the same logic that Spark uses to determine whether the left or right side of a shuffle hash join can safely be used as the build side.
This fixed one test failure in the AQE proof-of-concept work (hash right join).