[PATCH] D87674: [AMDGPU] Insert waitcnt after returning from call

Wed Sep 23 09:53:45 PDT 2020

madhur13490 added a comment.

In D87674#2290419 <https://reviews.llvm.org/D87674#2290419>, @arsenm wrote:

> In D87674#2290418 <https://reviews.llvm.org/D87674#2290418>, @madhur13490 wrote:
>
>> In D87674#2290396 <https://reviews.llvm.org/D87674#2290396>, @mareko wrote:
>>
>>> Yes, this commit is incorrect. It completely breaks code linking in Mesa OpenGL. s_waitcnt is required at the end of all global functions that return values.
>>>
>>> Please revert. @nhaehnle
>>
>> I don't understand why would it fail. This patch just moves s_waitcnt to the caller so they would be executed anyway. I think I am missing something. It would be helpful to root cause if we can isolate to a small test case.
>
> Shader returns aren't real returns and the "caller" doesn't wait

I see. So how should this be implemented? May be we conditionalize this patch just for compute?

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D87674/new/

https://reviews.llvm.org/D87674