Skip to content

Fix failure of proj to JIT-compile associated kernel on HW without fp64-support #1276

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
Jul 12, 2023

Conversation

oleksandr-pavlyk
Copy link
Contributor

@oleksandr-pavlyk oleksandr-pavlyk commented Jul 10, 2023

Closes gh-1275

This PR modifies the kernel associated with dpctl.tensor.proj to avoid using literal constants of type double to allow compilation for hardware without fp64 support.

Modified test test_complex.py::test_complex_output to pass on such HW as well.

  • 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?
  • If this PR is a work in progress, are you opening the PR as a draft?

Literal 0.0 is interpreted as double(0) causing kernel build error on devices
without fp64 support.
@github-actions
Copy link

@coveralls
Copy link
Collaborator

Coverage Status

coverage: 83.273%. remained the same when pulling 4dfa3ac on fix-proj into 5ebd6c3 on master.

@github-actions
Copy link

Array API standard conformance tests for dpctl=0.14.5dev1=py310h7bf5fec_3 ran successfully.
Passed: 449
Failed: 551
Skipped: 119

@oleksandr-pavlyk oleksandr-pavlyk merged commit 79f4041 into master Jul 12, 2023
@github-actions
Copy link

Deleted rendered PR docs from intelpython.github.com/dpctl, latest should be updated shortly. 🤞

@oleksandr-pavlyk oleksandr-pavlyk deleted the fix-proj branch July 12, 2023 13:12
@github-actions
Copy link

Array API standard conformance tests for dpctl=0.14.5dev1=py310h7bf5fec_5 ran successfully.
Passed: 447
Failed: 553
Skipped: 119

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.

proj raises on devices without fp64 support
3 participants