diff --git a/llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp b/llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
index f7bd478d73e6..01bb60f07f2e 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUUnifyDivergentExitNodes.cpp
@@ -195,6 +195,8 @@ 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>();
 
@@ -319,7 +321,7 @@ bool AMDGPUUnifyDivergentExitNodes::runOnFunction(Function &F) {
   if (ReturningBlocks.empty())
     return false; // No blocks return
 
-  if (ReturningBlocks.size() == 1 && !InsertExport)
+  if (ReturningBlocks.size() == 1)
     return false; // Already has a single return block
 
   const TargetTransformInfo &TTI
diff --git a/llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll b/llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll
index a2358f3a80f4..30280b967ad8 100644
--- a/llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll
+++ b/llvm/test/CodeGen/AMDGPU/kill-infinite-loop.ll
@@ -45,22 +45,6 @@ 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