Preserve operator order when lifting filter chains above FILTER - #26
Open
jianhongshi123 wants to merge 1 commit into
Open
Preserve operator order when lifting filter chains above FILTER#26jianhongshi123 wants to merge 1 commit into
jianhongshi123 wants to merge 1 commit into
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This is a follow-up to #20 . That PR restored correctness by conservatively stopping
CREATE_FILTERlifting when column bindings changed. However, some of the blocked lifts are semantically valid. The problem was the original rewrite: it moved theFILTERacross operators that could not commute with it and also did not remap the input bindings.This PR lifts the contiguous
CREATE/PROBEchain through the deepestCREATEabove theFILTER, while keeping theFILTERand all operators betweenFILTERand the chain in their original relative order. It also remaps the input bindings of the movedCREATEandPROBEoperators against their new child output.For TPC-H Q18 at SF=100 with 8 threads, relative performance improves from 0.35× baseline with #20 to 1.05× baseline.