From 1af53a91c0ed7ac03de1e04f3e0ccd586b0a4a44 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault@amd.com>
Date: Mon, 9 May 2016 16:57:08 +0000
Subject: [PATCH] DivergenceAnalysis: Fix crash with no return blocks

The post dominator tree does not have a root node in this case.

llvm-svn: 268933
---
 llvm/lib/Analysis/DivergenceAnalysis.cpp      |  8 ++++-
 .../AMDGPU/no-return-blocks.ll                | 30 +++++++++++++++++++
 2 files changed, 37 insertions(+), 1 deletion(-)
 create mode 100644 llvm/test/Analysis/DivergenceAnalysis/AMDGPU/no-return-blocks.ll

diff --git a/llvm/lib/Analysis/DivergenceAnalysis.cpp b/llvm/lib/Analysis/DivergenceAnalysis.cpp
index d38725ff0acc..1b36569f7a07 100644
--- a/llvm/lib/Analysis/DivergenceAnalysis.cpp
+++ b/llvm/lib/Analysis/DivergenceAnalysis.cpp
@@ -143,7 +143,13 @@ void DivergencePropagator::exploreSyncDependency(TerminatorInst *TI) {
   if (!DT.isReachableFromEntry(ThisBB))
     return;
 
-  BasicBlock *IPostDom = PDT.getNode(ThisBB)->getIDom()->getBlock();
+  // If the function has no exit blocks or doesn't reach any exit blocks, the
+  // post dominator may be null.
+  DomTreeNode *ThisNode = PDT.getNode(ThisBB);
+  if (!ThisNode)
+    return;
+
+  BasicBlock *IPostDom = ThisNode->getIDom()->getBlock();
   if (IPostDom == nullptr)
     return;
 
diff --git a/llvm/test/Analysis/DivergenceAnalysis/AMDGPU/no-return-blocks.ll b/llvm/test/Analysis/DivergenceAnalysis/AMDGPU/no-return-blocks.ll
new file mode 100644
index 000000000000..b4fa79a6ba9f
--- /dev/null
+++ b/llvm/test/Analysis/DivergenceAnalysis/AMDGPU/no-return-blocks.ll
@@ -0,0 +1,30 @@
+; RUN: opt %s -mtriple amdgcn-- -analyze -divergence | FileCheck %s
+
+; CHECK: DIVERGENT:  %tmp5 = getelementptr inbounds float, float addrspace(1)* %arg, i64 %tmp2
+; CHECK: DIVERGENT:  %tmp10 = load volatile float, float addrspace(1)* %tmp5, align 4
+; CHECK: DIVERGENT:  %tmp11 = load volatile float, float addrspace(1)* %tmp5, align 4
+
+; The post dominator tree does not have a root node in this case
+define void @no_return_blocks(float addrspace(1)* noalias nocapture readonly %arg, float addrspace(1)* noalias nocapture readonly %arg1) #0 {
+bb0:
+  %tmp = tail call i32 @llvm.amdgcn.workitem.id.x() #0
+  %tmp2 = sext i32 %tmp to i64
+  %tmp5 = getelementptr inbounds float, float addrspace(1)* %arg, i64 %tmp2
+  %tmp6 = load volatile float, float addrspace(1)* %tmp5, align 4
+  %tmp8 = fcmp olt float %tmp6, 0.000000e+00
+  br i1 %tmp8, label %bb1, label %bb2
+
+bb1:
+  %tmp10 = load volatile float, float addrspace(1)* %tmp5, align 4
+  br label %bb2
+
+bb2:
+  %tmp11 = load volatile float, float addrspace(1)* %tmp5, align 4
+  br label %bb1
+}
+
+; Function Attrs: nounwind readnone
+declare i32 @llvm.amdgcn.workitem.id.x() #1
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind readnone }