[PATCH] D117544: [AMDGPU] Fix missing waitcnt issue

[Piotr Sobczak via Phabricator via llvm-commits]

piotr added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp:1428
 
-    if (RegStrictDom && !OldOutOfOrder)
       StrictDom = true;
----------------
foad wrote:
> foad wrote:
> > As an experiment, would changing the condition to `RegStrictDom && !OldOutOfOrder && MyPending != 0` also fix the bug?
> > As an experiment, would changing the condition to `RegStrictDom && !OldOutOfOrder && MyPending != 0` also fix the bug?
> 
> Sorry I meant `RegStrictDom && !(OldOutOfOrder && MyPending != 0)`.
> > As an experiment, would changing the condition to `RegStrictDom && !OldOutOfOrder && MyPending != 0` also fix the bug?
> 
> Sorry I meant `RegStrictDom && !(OldOutOfOrder && MyPending != 0)`.

Do you mean this:

if (RegStrictDom && !(OldOutOfOrder && MyPending == 0))

I think that would also fix the bug in the test, but I wasn't convinced that was a complete fix, so I went for a safer and simpler approach.


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D117544/new/

https://reviews.llvm.org/D117544