llvm icon indicating copy to clipboard operation
llvm copied to clipboard

[Driver][SYCL][NewOffload] Fix arch settings for nvptx and amd

Open mdtoguchi opened this issue 1 year ago • 2 comments

When compiling for -fsycl-targets values of nvptx64-nvidia-cuda and amdgcn-amd-gpu, the default arch behaviors were not applied to the compilation. Updates to do the following:

  • Add default of sm_50 for nvptx64 if not provided
  • Emit diagnostic if no arch provided for amd
  • Parse -Xsycl-backend-target for offload-arch values

mdtoguchi avatar Jun 28 '24 00:06 mdtoguchi

@intel/llvm-gatekeepers, This should be ready for merge - please take a look.

mdtoguchi avatar Jun 28 '24 22:06 mdtoguchi

We should really be not running CI testing for comment updates...:-(

asudarsa avatar Jun 28 '24 23:06 asudarsa

@mdtoguchi this is awaiting approval from @srividya-sundaram

martygrant avatar Jul 01 '24 07:07 martygrant

We have approval from a driver team reviewer, This change unblocks development by fixing a large number of test failures. So, I ill merge it now. @srividya-sundaram, please feel free to reach out to me or @mdtoguchi for any post-commit changes if required.

Thanks Sincerely

asudarsa avatar Jul 01 '24 18:07 asudarsa

Sorry, I missed the notification for approval request.

srividya-sundaram avatar Jul 01 '24 18:07 srividya-sundaram