Skip to content

Conversation

@jchlanda
Copy link
Contributor

As the loop count is not statically known and llvm can not guarantee that the target allows remainders, this loop is not unrolled.

Fixes: #9783

As the loop count is not statically known and llvm can not guarantee
that the target allows remainders, this loop is not unrolled.
@jchlanda jchlanda requested a review from a team as a code owner June 22, 2023 09:20
@jchlanda jchlanda requested a review from sergey-semenov June 22, 2023 09:20
@jchlanda jchlanda temporarily deployed to aws June 22, 2023 09:37 — with GitHub Actions Inactive
@jchlanda jchlanda temporarily deployed to aws June 22, 2023 10:14 — with GitHub Actions Inactive
@bader bader merged commit 04eb46e into intel:sycl Jun 22, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[SYCL][CUDA] DPC++ build warning and error related to unrolling, optimization for CUDA plugin

3 participants