Skip to content

[SYCL] group operations update to use size() #7589

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

Merged
merged 2 commits into from
Dec 2, 2022

Conversation

cperkinsintel
Copy link
Contributor

@cperkinsintel cperkinsintel commented Nov 30, 2022

get_size() returns byte size. it is size() that is wanted in these group operations.

@cperkinsintel cperkinsintel requested a review from a team as a code owner November 30, 2022 00:40
@cperkinsintel cperkinsintel marked this pull request as draft November 30, 2022 00:44
@cperkinsintel cperkinsintel marked this pull request as ready for review November 30, 2022 00:46
Copy link
Contributor

@sergey-semenov sergey-semenov left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's alarming that something like this wasn't caught in our testing, we should close this gap.

@Pennycook
Copy link
Contributor

It's alarming that something like this wasn't caught in our testing, we should close this gap.

Yeah, this is a little scary! I guess the byte size is always bigger than the size, so the loop is always big enough. It might write some extra memory, but nothing in the test checks against that...

Good catch, @cperkinsintel. I agree with Sergey's suggestion to use the non-deprecated functions, but otherwise have nothing to add.

@cperkinsintel cperkinsintel changed the title [SYCL] group operations update to use get_count [SYCL] group operations update to use size() Nov 30, 2022
Copy link
Contributor

@sergey-semenov sergey-semenov left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The fix LGTM, but it'll need to be followed up with a test.

@againull againull merged commit 0fa7542 into intel:sycl Dec 2, 2022
cperkinsintel added a commit to cperkinsintel/llvm-test-suite that referenced this pull request Jan 2, 2023
…ction using sycl::vec<float>. Is sensitive to byte size vs. vector size fix in SYCL headers.
againull pushed a commit to intel/llvm-test-suite that referenced this pull request Jan 4, 2023
…1480)

Test to follow up on recent fix intel/llvm#7589. Test performs a reduction using sycl::vec<float>. Is sensitive to byte size vs. vector size fix in SYCL headers.
aelovikov-intel pushed a commit to aelovikov-intel/llvm that referenced this pull request Mar 27, 2023
…ntel/llvm-test-suite#1480)

Test to follow up on recent fix intel#7589. Test performs a reduction using sycl::vec<float>. Is sensitive to byte size vs. vector size fix in SYCL headers.
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.

4 participants