Index: lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
===================================================================
--- lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
+++ lib/Target/AMDGPU/SIAnnotateControlFlow.cpp
@@ -331,6 +331,10 @@
 
   BasicBlock *BB = Term->getParent();
   llvm::Loop *L = LI->getLoopFor(BB);
+  if (!L) {
+    return;
+  }
+
   BasicBlock *Target = Term->getSuccessor(1);
   PHINode *Broken = PHINode::Create(Int64, 0, "", &Target->front());
 
Index: test/CodeGen/AMDGPU/si-annotate-cf-no-loop.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/si-annotate-cf-no-loop.ll
@@ -0,0 +1,35 @@
+; RUN: llc < %s -march=amdgcn -mcpu=fiji -verify-machineinstrs | FileCheck %s
+
+; FIXME: should emit s_endpgm
+; CHECK-LABEL: {{^}}annotate_crash:
+; CHECK: s_cbranch_vccnz
+; CHECK-NOT: s_endpgm
+; CHECK: .Lfunc_end0
+define void @annotate_crash(<4 x float> addrspace(1)* noalias nocapture readonly %arg) #0 {
+bb:
+  %tmp = tail call i32 @llvm.amdgcn.workitem.id.x()
+  br label %bb1
+
+bb1:                                              ; preds = %bb
+  %tmp2 = sext i32 %tmp to i64
+  %tmp3 = getelementptr inbounds <4 x float>, <4 x float> addrspace(1)* %arg, i64 %tmp2
+  %tmp4 = load <4 x float>, <4 x float> addrspace(1)* %tmp3, align 16
+  br i1 undef, label %bb5, label %bb3
+
+bb3:                                              ; preds = %bb1
+  %tmp6 = extractelement <4 x float> %tmp4, i32 2
+  %tmp7 = fcmp olt float %tmp6, 0.000000e+00
+  br i1 %tmp7, label %bb4, label %bb5 ; crash goes away if these are swapped
+
+bb4:                                              ; preds = %bb3
+  unreachable
+
+bb5:                                              ; preds = %bb3, %bb1
+  unreachable
+}
+
+
+declare i32 @llvm.amdgcn.workitem.id.x() #1
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind readnone }