diff --git a/lib/Target/X86/X86InstrInfo.cpp b/lib/Target/X86/X86InstrInfo.cpp
index 8a6684cef0c..263b8f13f72 100644
--- a/lib/Target/X86/X86InstrInfo.cpp
+++ b/lib/Target/X86/X86InstrInfo.cpp
@@ -572,8 +572,8 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI)
     { X86::VMOVDI2PDIrr,    X86::VMOVDI2PDIrm,        0 },
     { X86::VMOVDI2SSrr,     X86::VMOVDI2SSrm,         0 },
     { X86::VMOVDQArr,       X86::VMOVDQArm,           TB_ALIGN_16 },
-    { X86::VMOVSLDUPrr,     X86::VMOVSLDUPrm,         TB_ALIGN_16 },
-    { X86::VMOVSHDUPrr,     X86::VMOVSHDUPrm,         TB_ALIGN_16 },
+    { X86::VMOVSLDUPrr,     X86::VMOVSLDUPrm,         0 },
+    { X86::VMOVSHDUPrr,     X86::VMOVSHDUPrm,         0 },
     { X86::VMOVUPDrr,       X86::VMOVUPDrm,           0 },
     { X86::VMOVUPSrr,       X86::VMOVUPSrm,           0 },
     { X86::VMOVZQI2PQIrr,   X86::VMOVZQI2PQIrm,       0 },
@@ -629,7 +629,10 @@ X86InstrInfo::X86InstrInfo(X86Subtarget &STI)
     { X86::VCVTTPS2DQYrr,   X86::VCVTTPS2DQYrm,       0 },
     { X86::VMOVAPDYrr,      X86::VMOVAPDYrm,          TB_ALIGN_32 },
     { X86::VMOVAPSYrr,      X86::VMOVAPSYrm,          TB_ALIGN_32 },
+    { X86::VMOVDDUPYrr,     X86::VMOVDDUPYrm,         0 },
     { X86::VMOVDQAYrr,      X86::VMOVDQAYrm,          TB_ALIGN_32 },
+    { X86::VMOVSLDUPYrr,    X86::VMOVSLDUPYrm,        0 },
+    { X86::VMOVSHDUPYrr,    X86::VMOVSHDUPYrm,        0 },
     { X86::VMOVUPDYrr,      X86::VMOVUPDYrm,          0 },
     { X86::VMOVUPSYrr,      X86::VMOVUPSYrm,          0 },
     { X86::VPERMILPDYri,    X86::VPERMILPDYmi,        0 },
diff --git a/test/CodeGen/X86/stack-folding-fp-avx1.ll b/test/CodeGen/X86/stack-folding-fp-avx1.ll
index 2a026159f71..0f8dfd5eac6 100644
--- a/test/CodeGen/X86/stack-folding-fp-avx1.ll
+++ b/test/CodeGen/X86/stack-folding-fp-avx1.ll
@@ -1085,11 +1085,21 @@ define <4 x float> @stack_fold_minss_int(<4 x float> %a0, <4 x float> %a1) {
 }
 declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>) nounwind readnone
 
-; TODO stack_fold_movd (load / store)
-; TODO stack_fold_movq (load / store)
+define <2 x double> @stack_fold_movddup(<2 x double> %a0) {
+  ;CHECK-LABEL: stack_fold_movddup
+  ;CHECK:   vmovddup {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
+  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
+  %2 = shufflevector <2 x double> %a0, <2 x double> undef, <2 x i32> <i32 0, i32 0>
+  ret <2 x double> %2
+}
 
-; TODO stack_fold_movddup
-; TODO stack_fold_movddup_ymm
+define <4 x double> @stack_fold_movddup_ymm(<4 x double> %a0) {
+  ;CHECK-LABEL: stack_fold_movddup_ymm
+  ;CHECK:   vmovddup {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
+  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
+  %2 = shufflevector <4 x double> %a0, <4 x double> undef, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
+  ret <4 x double> %2
+}
 
 ; TODO stack_fold_movhpd (load / store)
 ; TODO stack_fold_movhps (load / store)
@@ -1097,9 +1107,6 @@ declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>) nounwind read
 ; TODO stack_fold_movlpd (load / store)
 ; TODO stack_fold_movlps (load / store)
 
-; TODO stack_fold_movsd (load / store)
-; TODO stack_fold_movss (load / store)
-
 define <4 x float> @stack_fold_movshdup(<4 x float> %a0) {
   ;CHECK-LABEL: stack_fold_movshdup
   ;CHECK:   vmovshdup {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
@@ -1108,7 +1115,13 @@ define <4 x float> @stack_fold_movshdup(<4 x float> %a0) {
   ret <4 x float> %2
 }
 
-; TODO stack_fold_movshdup_ymm
+define <8 x float> @stack_fold_movshdup_ymm(<8 x float> %a0) {
+  ;CHECK-LABEL: stack_fold_movshdup_ymm
+  ;CHECK:   vmovshdup {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
+  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
+  %2 = shufflevector <8 x float> %a0, <8 x float> undef, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7>
+  ret <8 x float> %2
+}
 
 define <4 x float> @stack_fold_movsldup(<4 x float> %a0) {
   ;CHECK-LABEL: stack_fold_movsldup
@@ -1118,7 +1131,13 @@ define <4 x float> @stack_fold_movsldup(<4 x float> %a0) {
   ret <4 x float> %2
 }
 
-; TODO stack_fold_movshdup_ymm
+define <8 x float> @stack_fold_movsldup_ymm(<8 x float> %a0) {
+  ;CHECK-LABEL: stack_fold_movsldup_ymm
+  ;CHECK:   vmovsldup {{-?[0-9]*}}(%rsp), {{%ymm[0-9][0-9]*}} {{.*#+}} 32-byte Folded Reload
+  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
+  %2 = shufflevector <8 x float> %a0, <8 x float> undef, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
+  ret <8 x float> %2
+}
 
 define <2 x double> @stack_fold_mulpd(<2 x double> %a0, <2 x double> %a1) {
   ;CHECK-LABEL: stack_fold_mulpd
diff --git a/test/CodeGen/X86/stack-folding-fp-sse42.ll b/test/CodeGen/X86/stack-folding-fp-sse42.ll
index 4010907854d..ed365538879 100644
--- a/test/CodeGen/X86/stack-folding-fp-sse42.ll
+++ b/test/CodeGen/X86/stack-folding-fp-sse42.ll
@@ -737,20 +737,19 @@ define <4 x float> @stack_fold_minss_int(<4 x float> %a0, <4 x float> %a1) {
 }
 declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>) nounwind readnone
 
-; TODO stack_fold_movd (load / store)
-; TODO stack_fold_movq (load / store)
-
-; TODO stack_fold_movddup
-
+define <2 x double> @stack_fold_movddup(<2 x double> %a0) {
+  ;CHECK-LABEL: stack_fold_movddup
+  ;CHECK:   movddup {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload
+  %1 = tail call <2 x i64> asm sideeffect "nop", "=x,~{xmm1},~{xmm2},~{xmm3},~{xmm4},~{xmm5},~{xmm6},~{xmm7},~{xmm8},~{xmm9},~{xmm10},~{xmm11},~{xmm12},~{xmm13},~{xmm14},~{xmm15},~{flags}"()
+  %2 = shufflevector <2 x double> %a0, <2 x double> undef, <2 x i32> <i32 0, i32 0>
+  ret <2 x double> %2
+}
 ; TODO stack_fold_movhpd (load / store)
 ; TODO stack_fold_movhps (load / store)
 
 ; TODO stack_fold_movlpd (load / store)
 ; TODO stack_fold_movlps (load / store)
 
-; TODO stack_fold_movsd (load / store)
-; TODO stack_fold_movss (load / store)
-
 define <4 x float> @stack_fold_movshdup(<4 x float> %a0) {
   ;CHECK-LABEL: stack_fold_movshdup
   ;CHECK:       movshdup {{-?[0-9]*}}(%rsp), {{%xmm[0-9][0-9]*}} {{.*#+}} 16-byte Folded Reload