Index: llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
+++ llvm/trunk/lib/Target/X86/X86ISelLowering.cpp
@@ -3011,7 +3011,11 @@
   }
 
   // This is an argument in memory. We might be able to perform copy elision.
-  if (Flags.isCopyElisionCandidate()) {
+  // If the argument is passed directly in memory without any extension, then we
+  // can perform copy elision. Large vector types, for example, may be passed
+  // indirectly by pointer.
+  if (Flags.isCopyElisionCandidate() &&
+      VA.getLocInfo() != CCValAssign::Indirect && !ExtendedInMem) {
     EVT ArgVT = Ins[i].ArgVT;
     SDValue PartAddr;
     if (Ins[i].PartOffset == 0) {
Index: llvm/trunk/test/CodeGen/X86/arg-copy-elide-win64.ll
===================================================================
--- llvm/trunk/test/CodeGen/X86/arg-copy-elide-win64.ll
+++ llvm/trunk/test/CodeGen/X86/arg-copy-elide-win64.ll
@@ -13,12 +13,12 @@
 ; CHECK-NEXT:    vmovaps %xmm6, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
 ; CHECK-NEXT:    andq $-128, %rsp
 ; CHECK-NEXT:    movq 288(%rbp), %rax
-; CHECK-NEXT:    movq 320(%rbp), %r10
 ; CHECK-NEXT:    vmovaps (%rax), %ymm0
-; CHECK-NEXT:    vmovaps (%r10), %ymm1
-; CHECK-NEXT:    movq 352(%rbp), %rax
+; CHECK-NEXT:    movq 296(%rbp), %rax
+; CHECK-NEXT:    vmovaps (%rax), %ymm1
+; CHECK-NEXT:    movq 304(%rbp), %rax
 ; CHECK-NEXT:    vmovaps (%rax), %ymm2
-; CHECK-NEXT:    movq 384(%rbp), %rax
+; CHECK-NEXT:    movq 312(%rbp), %rax
 ; CHECK-NEXT:    vmovaps (%rax), %ymm3
 ; CHECK-NEXT:    vmovaps (%rcx), %ymm4
 ; CHECK-NEXT:    vmovaps (%rdx), %ymm5