[PATCH] D158750: New intrinsic void llvm.amdgcn.s.nop(i16)

Tue Sep 5 02:01:01 PDT 2023

foad added a comment.

In D158750#4637940 <https://reviews.llvm.org/D158750#4637940>, @dstuttard wrote:

> In D158750#4637244 <https://reviews.llvm.org/D158750#4637244>, @foad wrote:
>
>> Depending on the use case, you might also have to mark it as a scheduling barrier, not just having side effects.
>
> It is possible that might be required, but the behaviour is modelled on s_sleep which only tags "hasSideEffects" and doesn't attempt to make it a scheduling barrier as well.
> I propose to leave the implementation as-is and it can be re-visited if a scheduling barrier needs to be enforced.

That's fine with me.

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D158750/new/

https://reviews.llvm.org/D158750