-
Notifications
You must be signed in to change notification settings - Fork 787
[SYCL][HIP][libclc] Add group collective functions for HIP #5202
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
Conversation
@intel/llvm-reviewers-runtime, ping. |
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.
Test changes seem fine for SYCL RT.
Should there be any test changes for libclc/amdgcn-amdhsa?
According to the description these changes are covered by intel/llvm-test-suite#656. Are these enough or want to have libclc specific tests? |
Sorry, I missed the question. In my opinion the tests in the test suite should suffice. |
@againull, intel/llvm-test-suite#656 must be merged at the same time, otherwise, pre-commit checks on AMD GPU will be broken. |
Thank you, merged. |
Broadcast has recently been implemented for HIP backend in intel/llvm#5202 and XFAIL for AMD HIP was removed in #656. However on CI machines these tests are still failing, so we need to mark them XFAIL again
Broadcast has recently been implemented for HIP backend in intel#5202 and XFAIL for AMD HIP was removed in intel/llvm-test-suite#656. However on CI machines these tests are still failing, so we need to mark them XFAIL again
Adds group collective functions (reduce, scans, broadcast) for HIP.
Tested by: intel/llvm-test-suite#656