[PATCH] D64333: AMDGPU: Move waitcnt intrinsic to instruction definition pattern

Matt Arsenault via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Thu Jul 11 15:29:17 PDT 2019


arsenm added a comment.

In D64333#1581728 <https://reviews.llvm.org/D64333#1581728>, @hakzsam wrote:

> Hi,
>
> Is this expected that a bunch of tests with Mesa now crash because amdgcn.s.waitcnt is not found?
>
> $ ./deqp-vk --deqp-case=dEQP-VK.compute.basic.shared_atomic_op_multiple_groups
>  Writing test log into TestResults.qpa
>  dEQP Core git-38d72fc212ba3084b4f4ddca8cd48ba77754c219 (0x38d72fc2) starting..
>
>   target implementation = 'Default'
>   
>
> Test case 'dEQP-VK.compute.basic.shared_atomic_op_multiple_groups'..
>  LLVM ERROR: Cannot select: intrinsic %llvm.amdgcn.s.waitcnt
>
> Thanks Matt!


No. Do you have example IR? My initial guess is something is violating immarg


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D64333/new/

https://reviews.llvm.org/D64333





More information about the llvm-commits mailing list