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

llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp

@@ -195,7 +195,12 @@ static BasicBlock *unifyReturnBlockSet(Function &F,
 
 bool AMDGPUUnifyDivergentExitNodes::runOnFunction(Function &F) {
   auto &PDT = getAnalysis<PostDominatorTreeWrapperPass>().getPostDomTree();
-  if (PDT.getRoots().size() <= 1)
+
+  // If there's only one exit, we don't need to do anything, unless this is a
+  // pixel shader and that exit is an infinite loop, since we still have to
+  // insert an export in that case.
+  if (PDT.getRoots().size() <= 1 &&
+      F.getCallingConv() != CallingConv::AMDGPU_PS)
     return false;
 
   LegacyDivergenceAnalysis &DA = getAnalysis<LegacyDivergenceAnalysis>();
@@ -321,7 +326,7 @@ 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

@@ -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

llvm/test/CodeGen/AMDGPU/update-phi.ll

@@ -14,12 +14,13 @@ define amdgpu_ps void @_amdgpu_ps_main() local_unnamed_addr #3 {
 ; IR-NEXT:    [[DOT01:%.*]] = phi float [ 0.000000e+00, [[DOTLOOPEXIT]] ], [ [[N29:%.*]], [[TRANSITIONBLOCK:%.*]] ]
 ; IR-NEXT:    [[N29]] = fadd float [[DOT01]], 1.000000e+00
 ; IR-NEXT:    [[N30:%.*]] = fcmp ogt float [[N29]], 4.000000e+00
-; IR-NEXT:    br i1 true, label [[TRANSITIONBLOCK]], label [[DUMMYRETURNBLOCK:%.*]]
+; IR-NEXT:    br i1 true, label [[TRANSITIONBLOCK]], label [[UNIFIEDRETURNBLOCK:%.*]]
 ; IR:       TransitionBlock:
 ; IR-NEXT:    br i1 [[N30]], label [[DOTLOOPEXIT]], label [[N28]]
 ; IR:       n31:
 ; IR-NEXT:    ret void
-; IR:       DummyReturnBlock:
+; IR:       UnifiedReturnBlock:
+; IR-NEXT:    call void @llvm.amdgcn.exp.f32(i32 9, i32 0, float undef, float undef, float undef, float undef, i1 true, i1 true)
 ; IR-NEXT:    ret void
 ;
 .entry: