Commit 323bfde2 authored by Connor Abbott's avatar Connor Abbott
Browse files

AMDGPU: Fix AMDGPUUnifyDivergentExitNodes with no normal returns 

Summary:
The code was assuming in a few places that if there was only one exit
from the function that it was a normal return, which is invalid. It
could be an infinite loop, in which case we still need to insert the
usual fake edge so that the null export happens. This fixes shaders that
end with an infinite loop that discards.

Reviewers: arsenm, nhaehnle, critson

Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D71192
parent 0994c485

llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp

+1 −3
Original line number Diff line number Diff line
@@ -195,8 +195,6 @@ static BasicBlock *unifyReturnBlockSet(Function &F, 


bool AMDGPUUnifyDivergentExitNodes::runOnFunction(Function &F) {

  auto &PDT = getAnalysis<PostDominatorTreeWrapperPass>().getPostDomTree();

  if (PDT.getRoots().size() <= 1)

    return false;



  LegacyDivergenceAnalysis &DA = getAnalysis<LegacyDivergenceAnalysis>();
@@ -321,7 +319,7 @@ bool AMDGPUUnifyDivergentExitNodes::runOnFunction(Function &F) { 
  if (ReturningBlocks.empty())

    return false; // No blocks return



  if (ReturningBlocks.size() == 1)

  if (ReturningBlocks.size() == 1 && !InsertExport)

    return false; // Already has a single return block



  const TargetTransformInfo &TTI

llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll

+16 −0
Original line number Diff line number Diff line
@@ -45,6 +45,22 @@ end: 
  ret void

}



; test the case where there's only a kill in an infinite loop

; CHECK-LABEL: only_kill

; CHECK: exp null off, off, off, off done vm

; CHECK-NEXT: s_endpgm

; SIInsertSkips inserts an extra null export here, but it should be harmless.

; CHECK: exp null off, off, off, off done vm

; CHECK-NEXT: s_endpgm

define amdgpu_ps void @only_kill() #0 {

main_body:

  br label %loop



loop:

  call void @llvm.amdgcn.kill(i1 false) #3

  br label %loop

}



; In case there's an epilog, we shouldn't have to do this.

; CHECK-LABEL: return_nonvoid

; CHECK-NOT: exp null off, off, off, off done vm