Index: llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
+++ llvm/trunk/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -3046,6 +3046,7 @@
     // special case to check if the atomic has only one extract_subreg use,
     // which itself has no uses.
     if ((Node->hasNUsesOfValue(1, 0) &&
+         Node->use_begin()->isMachineOpcode() &&
          Node->use_begin()->getMachineOpcode() == AMDGPU::EXTRACT_SUBREG &&
          !Node->use_begin()->hasAnyUseOfValue(0))) {
       unsigned Def = MI->getOperand(0).getReg();
Index: llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
===================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
+++ llvm/trunk/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.atomic.ll
@@ -100,6 +100,15 @@
   ret float %out
 }
 
+;CHECK-LABEL: {{^}}test4:
+;CHECK: buffer_atomic_add v0,
+define amdgpu_ps float @test4() {
+main_body:
+  %v = call i32 @llvm.amdgcn.buffer.atomic.add(i32 1, <4 x i32> undef, i32 0, i32 4, i1 false)
+  %v.float = bitcast i32 %v to float
+  ret float %v.float
+}
+
 declare i32 @llvm.amdgcn.buffer.atomic.swap(i32, <4 x i32>, i32, i32, i1) #0
 declare i32 @llvm.amdgcn.buffer.atomic.add(i32, <4 x i32>, i32, i32, i1) #0
 declare i32 @llvm.amdgcn.buffer.atomic.sub(i32, <4 x i32>, i32, i32, i1) #0