[PATCH] D144162: [AMDGPU] Replace LegacyDA with Uniformity Analysis in AnnotateUniformValues

[Anshil Gandhi via Phabricator via llvm-commits]

gandhi21299 added inline comments.


================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUAnnotateUniformValues.cpp:81
 void AMDGPUAnnotateUniformValues::visitBranchInst(BranchInst &I) {
-  if (DA->isUniform(&I))
+  if (!UA->hasDivergentTerminator(*I.getParent()))
     setUniformMetadata(&I);
----------------
foad wrote:
> sameerds wrote:
> > sameerds wrote:
> > > I am not sure we should be doing this. Smells like a bug in the UA!
> > D144699 allows the original "isUniform()" call to work as expected on a BranchInst.
> Did you mean to change this back to `isUniform`? (I don't really mind either way.)
Yea I meant to change this back, great catch!


================
Comment at: llvm/test/CodeGen/AMDGPU/i1-copy-from-loop.ll:28
 ; SI-NEXT:    s_cmp_gt_u32 s14, 3
-; SI-NEXT:    s_cbranch_scc1 .LBB0_1
+; SI-NEXT:    s_cselect_b64 s[12:13], -1, 0
+; SI-NEXT:    s_and_b64 vcc, exec, s[12:13]
----------------
foad wrote:
> This is a regression.
Should I handle all the regressions in a seperate patch?


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D144162/new/

https://reviews.llvm.org/D144162