Skip to content

Update HIP target handling using alias #2099

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.

Sign up for GitHub

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

Jump to bottom
Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open

Update HIP target handling using alias #2099

wants to merge 4 commits into from

Conversation

vlad-perevezentsev
Copy link
Collaborator

This PR suggests simplifying DPCTL_TARGET_HIP handling by using target aliases amd_gpu_<arch> and removing support for amdgcn-amd-amdhsa target.
Also updates docs to clarify how to determine and use the correct AMD GPU architecture.

  • Have you provided a meaningful PR description?
  • Have you added a test, reproducer or referred to an issue with a reproducer?
  • Have you tested your changes locally for CPU and GPU devices?
  • Have you made sure that new changes do not introduce compiler warnings?
  • Have you checked performance impact of proposed changes?
  • Have you added documentation for your changes, if necessary?
  • Have you added your changes to the changelog?
  • If this PR is a work in progress, are you opening the PR as a draft?

@github-actions GitHub Actions
Copy link

github-actions bot commented Jun 6, 2025

View rendered docs @ https://intelpython.github.io/dpctl/pulls/2099/index.html

@github-actions GitHub Actions
Copy link

github-actions bot commented Jun 6, 2025

Array API standard conformance tests for dpctl=0.21.0dev0=py310h93fe807_22 ran successfully.
Passed: 1116
Failed: 5
Skipped: 119

ndgrigorian
ndgrigorian previously approved these changes Jun 9, 2025
View reviewed changes
Copy link
Collaborator

@ndgrigorian ndgrigorian left a comment

Choose a reason for hiding this comment

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

This LGTM overall

After this and the CUDA architecture update are merged, I think allowing setting CUDA and HIP architecture as arguments to scripts/build_locally.py script would be convenient

Base automatically changed from update_cuda_build to master June 19, 2025 21:32
@ndgrigorian ndgrigorian dismissed their stale review June 19, 2025 21:32

The base branch was changed.

@github-actions GitHub Actions
Copy link

Array API standard conformance tests for dpctl=0.21.0dev0=py310h93fe807_41 ran successfully.
Passed: 1115
Failed: 6
Skipped: 119

@coveralls
Copy link
Collaborator

coveralls commented Jun 20, 2025 •
edited
Loading

Coverage Status

coverage: 85.0% (+0.01%) from 84.989%
when pulling 499eeed on update_amd_build
into 775d0d3 on master.

@github-actions GitHub Actions
Copy link

Array API standard conformance tests for dpctl=0.21.0dev0=py310h93fe807_42 ran successfully.
Passed: 1116
Failed: 5
Skipped: 119

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ndgrigorian ndgrigorian ndgrigorian left review comments

@antonwolfy antonwolfy Awaiting requested review from antonwolfy antonwolfy is a code owner

@vtavana vtavana Awaiting requested review from vtavana vtavana is a code owner

At least 1 approving review is required to merge this pull request.

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@vlad-perevezentsev @coveralls @ndgrigorian