Skip to content
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

[SYCL] Enable Dead Kernel Argument Elimination for non-SPIR target #2359

Closed
bader opened this issue Aug 22, 2020 · 1 comment · Fixed by #4617
Closed

[SYCL] Enable Dead Kernel Argument Elimination for non-SPIR target #2359

bader opened this issue Aug 22, 2020 · 1 comment · Fixed by #4617
Labels
cuda CUDA back-end enhancement New feature or request performance Performance related issues

Comments

@bader
Copy link
Contributor

bader commented Aug 22, 2020

The optimization is disabled for NVPTX target.

Relevant patches: #2226, #2258, #2303, #2340, #2358.
@bader bader added enhancement New feature or request performance Performance related issues cuda CUDA back-end labels Aug 22, 2020
@bader bader mentioned this issue Mar 16, 2021
Merged
@joeatodd
Copy link
Contributor

#2315 too, I think

@joeatodd joeatodd mentioned this issue Sep 22, 2021
Merged
@bader bader linked a pull request Oct 3, 2021 that will close this issue
[SYCL] Enable Dead Argument Elimination for NVPTX backend #4617
Merged
bader pushed a commit that referenced this issue Oct 5, 2021
@joeatodd
[SYCL] Enable Dead Argument Elimination for NVPTX backend (#4617)
6b3c20f 
This addresses #2359 for NVPTX backend only. Changes are to:
- Detect NVPTX kernels for DAE (using `nvvm.annotations` metadata)
- Update the metadata with new function signatures as required
- Renaming some metadata, variables & files to reflect the fact that SYCL DAE is no longer SPIR specific
- Updating tests to reflect the expectation that -fenable-sycl-dae flag should be passed through for nvptx targets
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
cuda CUDA back-end enhancement New feature or request performance Performance related issues
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

[SYCL] Enable Dead Argument Elimination for NVPTX backend joeatodd/llvm
2 participants
@bader @joeatodd