Index: llvm/trunk/lib/Target/NVPTX/NVPTXLowerKernelArgs.cpp
===================================================================
--- llvm/trunk/lib/Target/NVPTX/NVPTXLowerKernelArgs.cpp
+++ llvm/trunk/lib/Target/NVPTX/NVPTXLowerKernelArgs.cpp
@@ -132,6 +132,10 @@
   assert(!Arg->hasByValAttr() &&
          "byval params should be handled by handleByValParam");
 
+  // Do nothing if the argument already points to the global address space.
+  if (Arg->getType()->getPointerAddressSpace() == ADDRESS_SPACE_GLOBAL)
+    return;
+
   Instruction *FirstInst = Arg->getParent()->getEntryBlock().begin();
   Instruction *ArgInGlobal = new AddrSpaceCastInst(
       Arg, PointerType::get(Arg->getType()->getPointerElementType(),
Index: llvm/trunk/test/CodeGen/NVPTX/lower-kernel-ptr-arg.ll
===================================================================
--- llvm/trunk/test/CodeGen/NVPTX/lower-kernel-ptr-arg.ll
+++ llvm/trunk/test/CodeGen/NVPTX/lower-kernel-ptr-arg.ll
@@ -16,5 +16,16 @@
   ret void
 }
 
-!nvvm.annotations = !{!0}
+define void @kernel2(float addrspace(1)* %input, float addrspace(1)* %output) {
+; CHECK-LABEL: .visible .entry kernel2(
+; CHECK-NOT: cvta.to.global.u64
+  %1 = load float, float addrspace(1)* %input, align 4
+; CHECK: ld.global.f32
+  store float %1, float addrspace(1)* %output, align 4
+; CHECK: st.global.f32
+  ret void
+}
+
+!nvvm.annotations = !{!0, !1}
 !0 = !{void (float*, float*)* @kernel, !"kernel", i32 1}
+!1 = !{void (float addrspace(1)*, float addrspace(1)*)* @kernel2, !"kernel", i32 1}