Index: lib/Target/X86/X86InstrInfo.cpp
===================================================================
--- lib/Target/X86/X86InstrInfo.cpp
+++ lib/Target/X86/X86InstrInfo.cpp
@@ -1615,8 +1615,11 @@
   case X86::VMOVAPSrm:
   case X86::VMOVAPDrm:
   case X86::VMOVDQArm:
+  case X86::VMOVUPSYrm:
   case X86::VMOVAPSYrm:
+  case X86::VMOVUPDYrm:
   case X86::VMOVAPDYrm:
+  case X86::VMOVDQUYrm:
   case X86::VMOVDQAYrm:
   case X86::MMX_MOVD64rm:
   case X86::MMX_MOVQ64rm:
@@ -1644,8 +1647,11 @@
   case X86::VMOVAPSmr:
   case X86::VMOVAPDmr:
   case X86::VMOVDQAmr:
+  case X86::VMOVUPSYmr:
   case X86::VMOVAPSYmr:
+  case X86::VMOVUPDYmr:
   case X86::VMOVAPDYmr:
+  case X86::VMOVDQUYmr:
   case X86::VMOVDQAYmr:
   case X86::VMOVUPSZmr:
   case X86::VMOVAPSZmr:
Index: test/CodeGen/X86/avx-intel-ocl.ll
===================================================================
--- test/CodeGen/X86/avx-intel-ocl.ll
+++ test/CodeGen/X86/avx-intel-ocl.ll
@@ -89,23 +89,23 @@
 ; WIN64: vmovaps {{.*(%rbp).*}}, {{%ymm([6-9]|1[0-5])}}     # 32-byte Reload
 
 ; X64-LABEL: test_prolog_epilog
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
-; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Folded Spill
-; X64: call
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
-; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Folded Reload
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Spill
+; X64: vmovups {{%ymm([8-9]|1[0-5])}}, {{.*}}(%rsp)  ## 32-byte Spill
+; X64: call
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
+; X64: vmovups {{.*}}(%rsp), {{%ymm([8-9]|1[0-5])}} ## 32-byte Reload
 define intel_ocl_bicc <16 x float> @test_prolog_epilog(<16 x float> %a, <16 x float> %b) nounwind {
    %c = call <16 x float> @func_float16(<16 x float> %a, <16 x float> %b)
    ret <16 x float> %c