Revert "[SYCL] Fix performance regression in parallel_for with using id class (#5385)" #6013
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
…id class (intel#5385)" This reverts commit a5760aa. Test is kept to check that id is converted from item within kernel.
steffenlarsen
approved these changes
Apr 14, 2022
cperkinsintel
approved these changes
Apr 14, 2022
Contributor
Author
|
@steffenlarsen @cperkinsintel could you please merge this PR? thanks |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
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Outdated suggestions cannot be applied.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 reverts commit a5760aa.
Test is kept to check that id is converted from item within kernel.
#5385 intends to fix a perf regression of a workload on cpu device. An alternative fix for the regression is to fix two pre- and post-vectorizer passes which have not handled llvm.assume properly, which I think is a better approach.
#5385 causes regression on another vectorizer workload due to missing fsycl-id-queries-fit-in-int support for sycl::id that is used for querying global_id within a kernel. fsycl-id-queries-fit-in-int support is very important for vectorizer performance, so it is necessary to have the support for sycl::id.