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.

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

[SYCL] Add support for optional kernel features in AOT x86_64 compilation #14590

Merged
merged 8 commits into from
Jul 24, 2024

Conversation

jzc
Copy link
Contributor

@jzc jzc commented Jul 16, 2024

No description provided.

@jzc jzc requested review from a team as code owners July 16, 2024 18:59
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_tgllp -o %t.tgllp.out %s
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_cfl -o %t.cfl.out %s
// RUN: %clangxx -fsycl -fsycl-targets=spir64_x86_64 -o %t.x86.out %s
Copy link
Contributor

Choose a reason for hiding this comment

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

i think we need a REQUIRES for any-device-is-cpu, i think we can only compile for spir64_x86_64 if the OCL CPU RT is installed as per this, i just fixed an issue related to that for another test here.

Copy link
Contributor

Choose a reason for hiding this comment

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

Also REQUIRES: opencl-aot

Copy link
Contributor Author

Choose a reason for hiding this comment

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


// REQUIRES: ocloc, opencl-aot
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_tgllp -o %t.tgllp.out %s
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_cfl -o %t.cfl.out %s
Copy link
Contributor

Choose a reason for hiding this comment

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

Can you please apply a similar fix that I have proposed in #14588, as written this will fail on Windows once I enable windows aot.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_tgllp -o %t.tgllp.out %s
// RUN: %clangxx -fsycl -fsycl-targets=intel_gpu_cfl -o %t.cfl.out %s
// RUN: %clangxx -fsycl -fsycl-targets=spir64_x86_64 -o %t.x86.out %s
Copy link
Contributor

Choose a reason for hiding this comment

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

same question about REQUIRES

Copy link
Contributor

@sarnex sarnex left a comment

Choose a reason for hiding this comment

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

my flags are resolved, thanks!

@sarnex
Copy link
Contributor

sarnex commented Jul 18, 2024

BTW I finally enabled Windows AOT in our CI, if you want to have the best testing I recommend merging sycl/HEAD and letting tests run, in the Windows Gen12 logs you should see

lit.py: D:\github\_work\llvm\llvm\llvm\sycl\test-e2e\lit.cfg.py:632: note: Found pre-installed AOT device compiler ocloc

and that means it's working

Thanks and sorry for the trouble

@AlexeySachkov AlexeySachkov merged commit 73be194 into intel:sycl Jul 24, 2024
14 checks passed
hdelan pushed a commit to hdelan/llvm that referenced this pull request Jul 26, 2024
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.

None yet

4 participants