diff --git a/clang/test/CodeGen/arm_neon_intrinsics.c b/clang/test/CodeGen/arm_neon_intrinsics.c
--- a/clang/test/CodeGen/arm_neon_intrinsics.c
+++ b/clang/test/CodeGen/arm_neon_intrinsics.c
@@ -20227,10 +20227,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.int8x8x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-// CHECK:   store <8 x i8> [[VTRN_I]], <8 x i8>* [[TMP1]], !alias.scope !3
+// CHECK:   store <8 x i8> [[VTRN_I]], <8 x i8>* [[TMP1]], align 4, !alias.scope !3
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <8 x i8>, <8 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
-// CHECK:   store <8 x i8> [[VTRN1_I]], <8 x i8>* [[TMP2]], !alias.scope !3
+// CHECK:   store <8 x i8> [[VTRN1_I]], <8 x i8>* [[TMP2]], align 4, !alias.scope !3
 // CHECK:   ret void
 int8x8x2_t test_vtrn_s8(int8x8_t a, int8x8_t b) {
   return vtrn_s8(a, b);
@@ -20242,10 +20242,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i16> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-// CHECK:   store <4 x i16> [[VTRN_I]], <4 x i16>* [[TMP3]], !alias.scope !6
+// CHECK:   store <4 x i16> [[VTRN_I]], <4 x i16>* [[TMP3]], align 4, !alias.scope !6
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i16>, <4 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
-// CHECK:   store <4 x i16> [[VTRN1_I]], <4 x i16>* [[TMP4]], !alias.scope !6
+// CHECK:   store <4 x i16> [[VTRN1_I]], <4 x i16>* [[TMP4]], align 4, !alias.scope !6
 // CHECK:   ret void
 int16x4x2_t test_vtrn_s16(int16x4_t a, int16x4_t b) {
   return vtrn_s16(a, b);
@@ -20257,10 +20257,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <2 x i32> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <2 x i32>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 0, i32 2>
-// CHECK:   store <2 x i32> [[VTRN_I]], <2 x i32>* [[TMP3]], !alias.scope !9
+// CHECK:   store <2 x i32> [[VTRN_I]], <2 x i32>* [[TMP3]], align 4, !alias.scope !9
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <2 x i32>, <2 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 1, i32 3>
-// CHECK:   store <2 x i32> [[VTRN1_I]], <2 x i32>* [[TMP4]], !alias.scope !9
+// CHECK:   store <2 x i32> [[VTRN1_I]], <2 x i32>* [[TMP4]], align 4, !alias.scope !9
 // CHECK:   ret void
 int32x2x2_t test_vtrn_s32(int32x2_t a, int32x2_t b) {
   return vtrn_s32(a, b);
@@ -20270,10 +20270,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.uint8x8x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-// CHECK:   store <8 x i8> [[VTRN_I]], <8 x i8>* [[TMP1]], !alias.scope !12
+// CHECK:   store <8 x i8> [[VTRN_I]], <8 x i8>* [[TMP1]], align 4, !alias.scope !12
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <8 x i8>, <8 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
-// CHECK:   store <8 x i8> [[VTRN1_I]], <8 x i8>* [[TMP2]], !alias.scope !12
+// CHECK:   store <8 x i8> [[VTRN1_I]], <8 x i8>* [[TMP2]], align 4, !alias.scope !12
 // CHECK:   ret void
 uint8x8x2_t test_vtrn_u8(uint8x8_t a, uint8x8_t b) {
   return vtrn_u8(a, b);
@@ -20285,10 +20285,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i16> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-// CHECK:   store <4 x i16> [[VTRN_I]], <4 x i16>* [[TMP3]], !alias.scope !15
+// CHECK:   store <4 x i16> [[VTRN_I]], <4 x i16>* [[TMP3]], align 4, !alias.scope !15
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i16>, <4 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
-// CHECK:   store <4 x i16> [[VTRN1_I]], <4 x i16>* [[TMP4]], !alias.scope !15
+// CHECK:   store <4 x i16> [[VTRN1_I]], <4 x i16>* [[TMP4]], align 4, !alias.scope !15
 // CHECK:   ret void
 uint16x4x2_t test_vtrn_u16(uint16x4_t a, uint16x4_t b) {
   return vtrn_u16(a, b);
@@ -20300,10 +20300,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <2 x i32> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <2 x i32>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 0, i32 2>
-// CHECK:   store <2 x i32> [[VTRN_I]], <2 x i32>* [[TMP3]], !alias.scope !18
+// CHECK:   store <2 x i32> [[VTRN_I]], <2 x i32>* [[TMP3]], align 4, !alias.scope !18
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <2 x i32>, <2 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 1, i32 3>
-// CHECK:   store <2 x i32> [[VTRN1_I]], <2 x i32>* [[TMP4]], !alias.scope !18
+// CHECK:   store <2 x i32> [[VTRN1_I]], <2 x i32>* [[TMP4]], align 4, !alias.scope !18
 // CHECK:   ret void
 uint32x2x2_t test_vtrn_u32(uint32x2_t a, uint32x2_t b) {
   return vtrn_u32(a, b);
@@ -20315,10 +20315,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <2 x float> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <2 x float>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <2 x float> %a, <2 x float> %b, <2 x i32> <i32 0, i32 2>
-// CHECK:   store <2 x float> [[VTRN_I]], <2 x float>* [[TMP3]], !alias.scope !21
+// CHECK:   store <2 x float> [[VTRN_I]], <2 x float>* [[TMP3]], align 4, !alias.scope !21
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <2 x float>, <2 x float>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <2 x float> %a, <2 x float> %b, <2 x i32> <i32 1, i32 3>
-// CHECK:   store <2 x float> [[VTRN1_I]], <2 x float>* [[TMP4]], !alias.scope !21
+// CHECK:   store <2 x float> [[VTRN1_I]], <2 x float>* [[TMP4]], align 4, !alias.scope !21
 // CHECK:   ret void
 float32x2x2_t test_vtrn_f32(float32x2_t a, float32x2_t b) {
   return vtrn_f32(a, b);
@@ -20328,10 +20328,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.poly8x8x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-// CHECK:   store <8 x i8> [[VTRN_I]], <8 x i8>* [[TMP1]], !alias.scope !24
+// CHECK:   store <8 x i8> [[VTRN_I]], <8 x i8>* [[TMP1]], align 4, !alias.scope !24
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <8 x i8>, <8 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
-// CHECK:   store <8 x i8> [[VTRN1_I]], <8 x i8>* [[TMP2]], !alias.scope !24
+// CHECK:   store <8 x i8> [[VTRN1_I]], <8 x i8>* [[TMP2]], align 4, !alias.scope !24
 // CHECK:   ret void
 poly8x8x2_t test_vtrn_p8(poly8x8_t a, poly8x8_t b) {
   return vtrn_p8(a, b);
@@ -20343,10 +20343,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i16> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-// CHECK:   store <4 x i16> [[VTRN_I]], <4 x i16>* [[TMP3]], !alias.scope !27
+// CHECK:   store <4 x i16> [[VTRN_I]], <4 x i16>* [[TMP3]], align 4, !alias.scope !27
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i16>, <4 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
-// CHECK:   store <4 x i16> [[VTRN1_I]], <4 x i16>* [[TMP4]], !alias.scope !27
+// CHECK:   store <4 x i16> [[VTRN1_I]], <4 x i16>* [[TMP4]], align 4, !alias.scope !27
 // CHECK:   ret void
 poly16x4x2_t test_vtrn_p16(poly16x4_t a, poly16x4_t b) {
   return vtrn_p16(a, b);
@@ -20356,10 +20356,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.int8x16x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-// CHECK:   store <16 x i8> [[VTRN_I]], <16 x i8>* [[TMP1]], !alias.scope !30
+// CHECK:   store <16 x i8> [[VTRN_I]], <16 x i8>* [[TMP1]], align 4, !alias.scope !30
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 1, i32 17, i32 3, i32 19, i32 5, i32 21, i32 7, i32 23, i32 9, i32 25, i32 11, i32 27, i32 13, i32 29, i32 15, i32 31>
-// CHECK:   store <16 x i8> [[VTRN1_I]], <16 x i8>* [[TMP2]], !alias.scope !30
+// CHECK:   store <16 x i8> [[VTRN1_I]], <16 x i8>* [[TMP2]], align 4, !alias.scope !30
 // CHECK:   ret void
 int8x16x2_t test_vtrnq_s8(int8x16_t a, int8x16_t b) {
   return vtrnq_s8(a, b);
@@ -20371,10 +20371,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <8 x i16> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-// CHECK:   store <8 x i16> [[VTRN_I]], <8 x i16>* [[TMP3]], !alias.scope !33
+// CHECK:   store <8 x i16> [[VTRN_I]], <8 x i16>* [[TMP3]], align 4, !alias.scope !33
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
-// CHECK:   store <8 x i16> [[VTRN1_I]], <8 x i16>* [[TMP4]], !alias.scope !33
+// CHECK:   store <8 x i16> [[VTRN1_I]], <8 x i16>* [[TMP4]], align 4, !alias.scope !33
 // CHECK:   ret void
 int16x8x2_t test_vtrnq_s16(int16x8_t a, int16x8_t b) {
   return vtrnq_s16(a, b);
@@ -20386,10 +20386,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i32> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i32>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-// CHECK:   store <4 x i32> [[VTRN_I]], <4 x i32>* [[TMP3]], !alias.scope !36
+// CHECK:   store <4 x i32> [[VTRN_I]], <4 x i32>* [[TMP3]], align 4, !alias.scope !36
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
-// CHECK:   store <4 x i32> [[VTRN1_I]], <4 x i32>* [[TMP4]], !alias.scope !36
+// CHECK:   store <4 x i32> [[VTRN1_I]], <4 x i32>* [[TMP4]], align 4, !alias.scope !36
 // CHECK:   ret void
 int32x4x2_t test_vtrnq_s32(int32x4_t a, int32x4_t b) {
   return vtrnq_s32(a, b);
@@ -20399,10 +20399,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.uint8x16x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-// CHECK:   store <16 x i8> [[VTRN_I]], <16 x i8>* [[TMP1]], !alias.scope !39
+// CHECK:   store <16 x i8> [[VTRN_I]], <16 x i8>* [[TMP1]], align 4, !alias.scope !39
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 1, i32 17, i32 3, i32 19, i32 5, i32 21, i32 7, i32 23, i32 9, i32 25, i32 11, i32 27, i32 13, i32 29, i32 15, i32 31>
-// CHECK:   store <16 x i8> [[VTRN1_I]], <16 x i8>* [[TMP2]], !alias.scope !39
+// CHECK:   store <16 x i8> [[VTRN1_I]], <16 x i8>* [[TMP2]], align 4, !alias.scope !39
 // CHECK:   ret void
 uint8x16x2_t test_vtrnq_u8(uint8x16_t a, uint8x16_t b) {
   return vtrnq_u8(a, b);
@@ -20414,10 +20414,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <8 x i16> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-// CHECK:   store <8 x i16> [[VTRN_I]], <8 x i16>* [[TMP3]], !alias.scope !42
+// CHECK:   store <8 x i16> [[VTRN_I]], <8 x i16>* [[TMP3]], align 4, !alias.scope !42
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
-// CHECK:   store <8 x i16> [[VTRN1_I]], <8 x i16>* [[TMP4]], !alias.scope !42
+// CHECK:   store <8 x i16> [[VTRN1_I]], <8 x i16>* [[TMP4]], align 4, !alias.scope !42
 // CHECK:   ret void
 uint16x8x2_t test_vtrnq_u16(uint16x8_t a, uint16x8_t b) {
   return vtrnq_u16(a, b);
@@ -20429,10 +20429,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i32> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i32>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-// CHECK:   store <4 x i32> [[VTRN_I]], <4 x i32>* [[TMP3]], !alias.scope !45
+// CHECK:   store <4 x i32> [[VTRN_I]], <4 x i32>* [[TMP3]], align 4, !alias.scope !45
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
-// CHECK:   store <4 x i32> [[VTRN1_I]], <4 x i32>* [[TMP4]], !alias.scope !45
+// CHECK:   store <4 x i32> [[VTRN1_I]], <4 x i32>* [[TMP4]], align 4, !alias.scope !45
 // CHECK:   ret void
 uint32x4x2_t test_vtrnq_u32(uint32x4_t a, uint32x4_t b) {
   return vtrnq_u32(a, b);
@@ -20444,10 +20444,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x float> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x float>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
-// CHECK:   store <4 x float> [[VTRN_I]], <4 x float>* [[TMP3]], !alias.scope !48
+// CHECK:   store <4 x float> [[VTRN_I]], <4 x float>* [[TMP3]], align 4, !alias.scope !48
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x float>, <4 x float>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
-// CHECK:   store <4 x float> [[VTRN1_I]], <4 x float>* [[TMP4]], !alias.scope !48
+// CHECK:   store <4 x float> [[VTRN1_I]], <4 x float>* [[TMP4]], align 4, !alias.scope !48
 // CHECK:   ret void
 float32x4x2_t test_vtrnq_f32(float32x4_t a, float32x4_t b) {
   return vtrnq_f32(a, b);
@@ -20457,10 +20457,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.poly8x16x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 16, i32 2, i32 18, i32 4, i32 20, i32 6, i32 22, i32 8, i32 24, i32 10, i32 26, i32 12, i32 28, i32 14, i32 30>
-// CHECK:   store <16 x i8> [[VTRN_I]], <16 x i8>* [[TMP1]], !alias.scope !51
+// CHECK:   store <16 x i8> [[VTRN_I]], <16 x i8>* [[TMP1]], align 4, !alias.scope !51
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 1, i32 17, i32 3, i32 19, i32 5, i32 21, i32 7, i32 23, i32 9, i32 25, i32 11, i32 27, i32 13, i32 29, i32 15, i32 31>
-// CHECK:   store <16 x i8> [[VTRN1_I]], <16 x i8>* [[TMP2]], !alias.scope !51
+// CHECK:   store <16 x i8> [[VTRN1_I]], <16 x i8>* [[TMP2]], align 4, !alias.scope !51
 // CHECK:   ret void
 poly8x16x2_t test_vtrnq_p8(poly8x16_t a, poly8x16_t b) {
   return vtrnq_p8(a, b);
@@ -20472,10 +20472,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <8 x i16> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
 // CHECK:   [[VTRN_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 8, i32 2, i32 10, i32 4, i32 12, i32 6, i32 14>
-// CHECK:   store <8 x i16> [[VTRN_I]], <8 x i16>* [[TMP3]], !alias.scope !54
+// CHECK:   store <8 x i16> [[VTRN_I]], <8 x i16>* [[TMP3]], align 4, !alias.scope !54
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VTRN1_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 1, i32 9, i32 3, i32 11, i32 5, i32 13, i32 7, i32 15>
-// CHECK:   store <8 x i16> [[VTRN1_I]], <8 x i16>* [[TMP4]], !alias.scope !54
+// CHECK:   store <8 x i16> [[VTRN1_I]], <8 x i16>* [[TMP4]], align 4, !alias.scope !54
 // CHECK:   ret void
 poly16x8x2_t test_vtrnq_p16(poly16x8_t a, poly16x8_t b) {
   return vtrnq_p16(a, b);
@@ -20649,10 +20649,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.int8x8x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
-// CHECK:   store <8 x i8> [[VUZP_I]], <8 x i8>* [[TMP1]], !alias.scope !57
+// CHECK:   store <8 x i8> [[VUZP_I]], <8 x i8>* [[TMP1]], align 4, !alias.scope !57
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <8 x i8>, <8 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
-// CHECK:   store <8 x i8> [[VUZP1_I]], <8 x i8>* [[TMP2]], !alias.scope !57
+// CHECK:   store <8 x i8> [[VUZP1_I]], <8 x i8>* [[TMP2]], align 4, !alias.scope !57
 // CHECK:   ret void
 int8x8x2_t test_vuzp_s8(int8x8_t a, int8x8_t b) {
   return vuzp_s8(a, b);
@@ -20664,10 +20664,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i16> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-// CHECK:   store <4 x i16> [[VUZP_I]], <4 x i16>* [[TMP3]], !alias.scope !60
+// CHECK:   store <4 x i16> [[VUZP_I]], <4 x i16>* [[TMP3]], align 4, !alias.scope !60
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i16>, <4 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
-// CHECK:   store <4 x i16> [[VUZP1_I]], <4 x i16>* [[TMP4]], !alias.scope !60
+// CHECK:   store <4 x i16> [[VUZP1_I]], <4 x i16>* [[TMP4]], align 4, !alias.scope !60
 // CHECK:   ret void
 int16x4x2_t test_vuzp_s16(int16x4_t a, int16x4_t b) {
   return vuzp_s16(a, b);
@@ -20679,10 +20679,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <2 x i32> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <2 x i32>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 0, i32 2>
-// CHECK:   store <2 x i32> [[VUZP_I]], <2 x i32>* [[TMP3]], !alias.scope !63
+// CHECK:   store <2 x i32> [[VUZP_I]], <2 x i32>* [[TMP3]], align 4, !alias.scope !63
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <2 x i32>, <2 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 1, i32 3>
-// CHECK:   store <2 x i32> [[VUZP1_I]], <2 x i32>* [[TMP4]], !alias.scope !63
+// CHECK:   store <2 x i32> [[VUZP1_I]], <2 x i32>* [[TMP4]], align 4, !alias.scope !63
 // CHECK:   ret void
 int32x2x2_t test_vuzp_s32(int32x2_t a, int32x2_t b) {
   return vuzp_s32(a, b);
@@ -20692,10 +20692,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.uint8x8x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
-// CHECK:   store <8 x i8> [[VUZP_I]], <8 x i8>* [[TMP1]], !alias.scope !66
+// CHECK:   store <8 x i8> [[VUZP_I]], <8 x i8>* [[TMP1]], align 4, !alias.scope !66
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <8 x i8>, <8 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
-// CHECK:   store <8 x i8> [[VUZP1_I]], <8 x i8>* [[TMP2]], !alias.scope !66
+// CHECK:   store <8 x i8> [[VUZP1_I]], <8 x i8>* [[TMP2]], align 4, !alias.scope !66
 // CHECK:   ret void
 uint8x8x2_t test_vuzp_u8(uint8x8_t a, uint8x8_t b) {
   return vuzp_u8(a, b);
@@ -20707,10 +20707,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i16> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-// CHECK:   store <4 x i16> [[VUZP_I]], <4 x i16>* [[TMP3]], !alias.scope !69
+// CHECK:   store <4 x i16> [[VUZP_I]], <4 x i16>* [[TMP3]], align 4, !alias.scope !69
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i16>, <4 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
-// CHECK:   store <4 x i16> [[VUZP1_I]], <4 x i16>* [[TMP4]], !alias.scope !69
+// CHECK:   store <4 x i16> [[VUZP1_I]], <4 x i16>* [[TMP4]], align 4, !alias.scope !69
 // CHECK:   ret void
 uint16x4x2_t test_vuzp_u16(uint16x4_t a, uint16x4_t b) {
   return vuzp_u16(a, b);
@@ -20722,10 +20722,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <2 x i32> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <2 x i32>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 0, i32 2>
-// CHECK:   store <2 x i32> [[VUZP_I]], <2 x i32>* [[TMP3]], !alias.scope !72
+// CHECK:   store <2 x i32> [[VUZP_I]], <2 x i32>* [[TMP3]], align 4, !alias.scope !72
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <2 x i32>, <2 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 1, i32 3>
-// CHECK:   store <2 x i32> [[VUZP1_I]], <2 x i32>* [[TMP4]], !alias.scope !72
+// CHECK:   store <2 x i32> [[VUZP1_I]], <2 x i32>* [[TMP4]], align 4, !alias.scope !72
 // CHECK:   ret void
 uint32x2x2_t test_vuzp_u32(uint32x2_t a, uint32x2_t b) {
   return vuzp_u32(a, b);
@@ -20737,10 +20737,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <2 x float> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <2 x float>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <2 x float> %a, <2 x float> %b, <2 x i32> <i32 0, i32 2>
-// CHECK:   store <2 x float> [[VUZP_I]], <2 x float>* [[TMP3]], !alias.scope !75
+// CHECK:   store <2 x float> [[VUZP_I]], <2 x float>* [[TMP3]], align 4, !alias.scope !75
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <2 x float>, <2 x float>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <2 x float> %a, <2 x float> %b, <2 x i32> <i32 1, i32 3>
-// CHECK:   store <2 x float> [[VUZP1_I]], <2 x float>* [[TMP4]], !alias.scope !75
+// CHECK:   store <2 x float> [[VUZP1_I]], <2 x float>* [[TMP4]], align 4, !alias.scope !75
 // CHECK:   ret void
 float32x2x2_t test_vuzp_f32(float32x2_t a, float32x2_t b) {
   return vuzp_f32(a, b);
@@ -20750,10 +20750,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.poly8x8x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
-// CHECK:   store <8 x i8> [[VUZP_I]], <8 x i8>* [[TMP1]], !alias.scope !78
+// CHECK:   store <8 x i8> [[VUZP_I]], <8 x i8>* [[TMP1]], align 4, !alias.scope !78
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <8 x i8>, <8 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
-// CHECK:   store <8 x i8> [[VUZP1_I]], <8 x i8>* [[TMP2]], !alias.scope !78
+// CHECK:   store <8 x i8> [[VUZP1_I]], <8 x i8>* [[TMP2]], align 4, !alias.scope !78
 // CHECK:   ret void
 poly8x8x2_t test_vuzp_p8(poly8x8_t a, poly8x8_t b) {
   return vuzp_p8(a, b);
@@ -20765,10 +20765,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i16> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-// CHECK:   store <4 x i16> [[VUZP_I]], <4 x i16>* [[TMP3]], !alias.scope !81
+// CHECK:   store <4 x i16> [[VUZP_I]], <4 x i16>* [[TMP3]], align 4, !alias.scope !81
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i16>, <4 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
-// CHECK:   store <4 x i16> [[VUZP1_I]], <4 x i16>* [[TMP4]], !alias.scope !81
+// CHECK:   store <4 x i16> [[VUZP1_I]], <4 x i16>* [[TMP4]], align 4, !alias.scope !81
 // CHECK:   ret void
 poly16x4x2_t test_vuzp_p16(poly16x4_t a, poly16x4_t b) {
   return vuzp_p16(a, b);
@@ -20778,10 +20778,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.int8x16x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
-// CHECK:   store <16 x i8> [[VUZP_I]], <16 x i8>* [[TMP1]], !alias.scope !84
+// CHECK:   store <16 x i8> [[VUZP_I]], <16 x i8>* [[TMP1]], align 4, !alias.scope !84
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
-// CHECK:   store <16 x i8> [[VUZP1_I]], <16 x i8>* [[TMP2]], !alias.scope !84
+// CHECK:   store <16 x i8> [[VUZP1_I]], <16 x i8>* [[TMP2]], align 4, !alias.scope !84
 // CHECK:   ret void
 int8x16x2_t test_vuzpq_s8(int8x16_t a, int8x16_t b) {
   return vuzpq_s8(a, b);
@@ -20793,10 +20793,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <8 x i16> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
-// CHECK:   store <8 x i16> [[VUZP_I]], <8 x i16>* [[TMP3]], !alias.scope !87
+// CHECK:   store <8 x i16> [[VUZP_I]], <8 x i16>* [[TMP3]], align 4, !alias.scope !87
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
-// CHECK:   store <8 x i16> [[VUZP1_I]], <8 x i16>* [[TMP4]], !alias.scope !87
+// CHECK:   store <8 x i16> [[VUZP1_I]], <8 x i16>* [[TMP4]], align 4, !alias.scope !87
 // CHECK:   ret void
 int16x8x2_t test_vuzpq_s16(int16x8_t a, int16x8_t b) {
   return vuzpq_s16(a, b);
@@ -20808,10 +20808,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i32> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i32>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-// CHECK:   store <4 x i32> [[VUZP_I]], <4 x i32>* [[TMP3]], !alias.scope !90
+// CHECK:   store <4 x i32> [[VUZP_I]], <4 x i32>* [[TMP3]], align 4, !alias.scope !90
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
-// CHECK:   store <4 x i32> [[VUZP1_I]], <4 x i32>* [[TMP4]], !alias.scope !90
+// CHECK:   store <4 x i32> [[VUZP1_I]], <4 x i32>* [[TMP4]], align 4, !alias.scope !90
 // CHECK:   ret void
 int32x4x2_t test_vuzpq_s32(int32x4_t a, int32x4_t b) {
   return vuzpq_s32(a, b);
@@ -20821,10 +20821,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.uint8x16x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
-// CHECK:   store <16 x i8> [[VUZP_I]], <16 x i8>* [[TMP1]], !alias.scope !93
+// CHECK:   store <16 x i8> [[VUZP_I]], <16 x i8>* [[TMP1]], align 4, !alias.scope !93
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
-// CHECK:   store <16 x i8> [[VUZP1_I]], <16 x i8>* [[TMP2]], !alias.scope !93
+// CHECK:   store <16 x i8> [[VUZP1_I]], <16 x i8>* [[TMP2]], align 4, !alias.scope !93
 // CHECK:   ret void
 uint8x16x2_t test_vuzpq_u8(uint8x16_t a, uint8x16_t b) {
   return vuzpq_u8(a, b);
@@ -20836,10 +20836,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <8 x i16> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
-// CHECK:   store <8 x i16> [[VUZP_I]], <8 x i16>* [[TMP3]], !alias.scope !96
+// CHECK:   store <8 x i16> [[VUZP_I]], <8 x i16>* [[TMP3]], align 4, !alias.scope !96
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
-// CHECK:   store <8 x i16> [[VUZP1_I]], <8 x i16>* [[TMP4]], !alias.scope !96
+// CHECK:   store <8 x i16> [[VUZP1_I]], <8 x i16>* [[TMP4]], align 4, !alias.scope !96
 // CHECK:   ret void
 uint16x8x2_t test_vuzpq_u16(uint16x8_t a, uint16x8_t b) {
   return vuzpq_u16(a, b);
@@ -20851,10 +20851,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i32> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i32>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-// CHECK:   store <4 x i32> [[VUZP_I]], <4 x i32>* [[TMP3]], !alias.scope !99
+// CHECK:   store <4 x i32> [[VUZP_I]], <4 x i32>* [[TMP3]], align 4, !alias.scope !99
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
-// CHECK:   store <4 x i32> [[VUZP1_I]], <4 x i32>* [[TMP4]], !alias.scope !99
+// CHECK:   store <4 x i32> [[VUZP1_I]], <4 x i32>* [[TMP4]], align 4, !alias.scope !99
 // CHECK:   ret void
 uint32x4x2_t test_vuzpq_u32(uint32x4_t a, uint32x4_t b) {
   return vuzpq_u32(a, b);
@@ -20866,10 +20866,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x float> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x float>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 2, i32 4, i32 6>
-// CHECK:   store <4 x float> [[VUZP_I]], <4 x float>* [[TMP3]], !alias.scope !102
+// CHECK:   store <4 x float> [[VUZP_I]], <4 x float>* [[TMP3]], align 4, !alias.scope !102
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x float>, <4 x float>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 1, i32 3, i32 5, i32 7>
-// CHECK:   store <4 x float> [[VUZP1_I]], <4 x float>* [[TMP4]], !alias.scope !102
+// CHECK:   store <4 x float> [[VUZP1_I]], <4 x float>* [[TMP4]], align 4, !alias.scope !102
 // CHECK:   ret void
 float32x4x2_t test_vuzpq_f32(float32x4_t a, float32x4_t b) {
   return vuzpq_f32(a, b);
@@ -20879,10 +20879,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.poly8x16x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14, i32 16, i32 18, i32 20, i32 22, i32 24, i32 26, i32 28, i32 30>
-// CHECK:   store <16 x i8> [[VUZP_I]], <16 x i8>* [[TMP1]], !alias.scope !105
+// CHECK:   store <16 x i8> [[VUZP_I]], <16 x i8>* [[TMP1]], align 4, !alias.scope !105
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15, i32 17, i32 19, i32 21, i32 23, i32 25, i32 27, i32 29, i32 31>
-// CHECK:   store <16 x i8> [[VUZP1_I]], <16 x i8>* [[TMP2]], !alias.scope !105
+// CHECK:   store <16 x i8> [[VUZP1_I]], <16 x i8>* [[TMP2]], align 4, !alias.scope !105
 // CHECK:   ret void
 poly8x16x2_t test_vuzpq_p8(poly8x16_t a, poly8x16_t b) {
   return vuzpq_p8(a, b);
@@ -20894,10 +20894,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <8 x i16> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
 // CHECK:   [[VUZP_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 14>
-// CHECK:   store <8 x i16> [[VUZP_I]], <8 x i16>* [[TMP3]], !alias.scope !108
+// CHECK:   store <8 x i16> [[VUZP_I]], <8 x i16>* [[TMP3]], align 4, !alias.scope !108
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VUZP1_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
-// CHECK:   store <8 x i16> [[VUZP1_I]], <8 x i16>* [[TMP4]], !alias.scope !108
+// CHECK:   store <8 x i16> [[VUZP1_I]], <8 x i16>* [[TMP4]], align 4, !alias.scope !108
 // CHECK:   ret void
 poly16x8x2_t test_vuzpq_p16(poly16x8_t a, poly16x8_t b) {
   return vuzpq_p16(a, b);
@@ -20907,10 +20907,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.int8x8x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-// CHECK:   store <8 x i8> [[VZIP_I]], <8 x i8>* [[TMP1]], !alias.scope !111
+// CHECK:   store <8 x i8> [[VZIP_I]], <8 x i8>* [[TMP1]], align 4, !alias.scope !111
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <8 x i8>, <8 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
-// CHECK:   store <8 x i8> [[VZIP1_I]], <8 x i8>* [[TMP2]], !alias.scope !111
+// CHECK:   store <8 x i8> [[VZIP1_I]], <8 x i8>* [[TMP2]], align 4, !alias.scope !111
 // CHECK:   ret void
 int8x8x2_t test_vzip_s8(int8x8_t a, int8x8_t b) {
   return vzip_s8(a, b);
@@ -20922,10 +20922,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i16> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
-// CHECK:   store <4 x i16> [[VZIP_I]], <4 x i16>* [[TMP3]], !alias.scope !114
+// CHECK:   store <4 x i16> [[VZIP_I]], <4 x i16>* [[TMP3]], align 4, !alias.scope !114
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i16>, <4 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-// CHECK:   store <4 x i16> [[VZIP1_I]], <4 x i16>* [[TMP4]], !alias.scope !114
+// CHECK:   store <4 x i16> [[VZIP1_I]], <4 x i16>* [[TMP4]], align 4, !alias.scope !114
 // CHECK:   ret void
 int16x4x2_t test_vzip_s16(int16x4_t a, int16x4_t b) {
   return vzip_s16(a, b);
@@ -20937,10 +20937,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <2 x i32> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <2 x i32>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 0, i32 2>
-// CHECK:   store <2 x i32> [[VZIP_I]], <2 x i32>* [[TMP3]], !alias.scope !117
+// CHECK:   store <2 x i32> [[VZIP_I]], <2 x i32>* [[TMP3]], align 4, !alias.scope !117
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <2 x i32>, <2 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 1, i32 3>
-// CHECK:   store <2 x i32> [[VZIP1_I]], <2 x i32>* [[TMP4]], !alias.scope !117
+// CHECK:   store <2 x i32> [[VZIP1_I]], <2 x i32>* [[TMP4]], align 4, !alias.scope !117
 // CHECK:   ret void
 int32x2x2_t test_vzip_s32(int32x2_t a, int32x2_t b) {
   return vzip_s32(a, b);
@@ -20950,10 +20950,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.uint8x8x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-// CHECK:   store <8 x i8> [[VZIP_I]], <8 x i8>* [[TMP1]], !alias.scope !120
+// CHECK:   store <8 x i8> [[VZIP_I]], <8 x i8>* [[TMP1]], align 4, !alias.scope !120
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <8 x i8>, <8 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
-// CHECK:   store <8 x i8> [[VZIP1_I]], <8 x i8>* [[TMP2]], !alias.scope !120
+// CHECK:   store <8 x i8> [[VZIP1_I]], <8 x i8>* [[TMP2]], align 4, !alias.scope !120
 // CHECK:   ret void
 uint8x8x2_t test_vzip_u8(uint8x8_t a, uint8x8_t b) {
   return vzip_u8(a, b);
@@ -20965,10 +20965,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i16> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
-// CHECK:   store <4 x i16> [[VZIP_I]], <4 x i16>* [[TMP3]], !alias.scope !123
+// CHECK:   store <4 x i16> [[VZIP_I]], <4 x i16>* [[TMP3]], align 4, !alias.scope !123
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i16>, <4 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-// CHECK:   store <4 x i16> [[VZIP1_I]], <4 x i16>* [[TMP4]], !alias.scope !123
+// CHECK:   store <4 x i16> [[VZIP1_I]], <4 x i16>* [[TMP4]], align 4, !alias.scope !123
 // CHECK:   ret void
 uint16x4x2_t test_vzip_u16(uint16x4_t a, uint16x4_t b) {
   return vzip_u16(a, b);
@@ -20980,10 +20980,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <2 x i32> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <2 x i32>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 0, i32 2>
-// CHECK:   store <2 x i32> [[VZIP_I]], <2 x i32>* [[TMP3]], !alias.scope !126
+// CHECK:   store <2 x i32> [[VZIP_I]], <2 x i32>* [[TMP3]], align 4, !alias.scope !126
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <2 x i32>, <2 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <2 x i32> %a, <2 x i32> %b, <2 x i32> <i32 1, i32 3>
-// CHECK:   store <2 x i32> [[VZIP1_I]], <2 x i32>* [[TMP4]], !alias.scope !126
+// CHECK:   store <2 x i32> [[VZIP1_I]], <2 x i32>* [[TMP4]], align 4, !alias.scope !126
 // CHECK:   ret void
 uint32x2x2_t test_vzip_u32(uint32x2_t a, uint32x2_t b) {
   return vzip_u32(a, b);
@@ -20995,10 +20995,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <2 x float> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <2 x float>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <2 x float> %a, <2 x float> %b, <2 x i32> <i32 0, i32 2>
-// CHECK:   store <2 x float> [[VZIP_I]], <2 x float>* [[TMP3]], !alias.scope !129
+// CHECK:   store <2 x float> [[VZIP_I]], <2 x float>* [[TMP3]], align 4, !alias.scope !129
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <2 x float>, <2 x float>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <2 x float> %a, <2 x float> %b, <2 x i32> <i32 1, i32 3>
-// CHECK:   store <2 x float> [[VZIP1_I]], <2 x float>* [[TMP4]], !alias.scope !129
+// CHECK:   store <2 x float> [[VZIP1_I]], <2 x float>* [[TMP4]], align 4, !alias.scope !129
 // CHECK:   ret void
 float32x2x2_t test_vzip_f32(float32x2_t a, float32x2_t b) {
   return vzip_f32(a, b);
@@ -21008,10 +21008,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.poly8x8x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <8 x i8>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-// CHECK:   store <8 x i8> [[VZIP_I]], <8 x i8>* [[TMP1]], !alias.scope !132
+// CHECK:   store <8 x i8> [[VZIP_I]], <8 x i8>* [[TMP1]], align 4, !alias.scope !132
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <8 x i8>, <8 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <8 x i8> %a, <8 x i8> %b, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
-// CHECK:   store <8 x i8> [[VZIP1_I]], <8 x i8>* [[TMP2]], !alias.scope !132
+// CHECK:   store <8 x i8> [[VZIP1_I]], <8 x i8>* [[TMP2]], align 4, !alias.scope !132
 // CHECK:   ret void
 poly8x8x2_t test_vzip_p8(poly8x8_t a, poly8x8_t b) {
   return vzip_p8(a, b);
@@ -21023,10 +21023,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i16> %b to <8 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i16>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
-// CHECK:   store <4 x i16> [[VZIP_I]], <4 x i16>* [[TMP3]], !alias.scope !135
+// CHECK:   store <4 x i16> [[VZIP_I]], <4 x i16>* [[TMP3]], align 4, !alias.scope !135
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i16>, <4 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <4 x i16> %a, <4 x i16> %b, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-// CHECK:   store <4 x i16> [[VZIP1_I]], <4 x i16>* [[TMP4]], !alias.scope !135
+// CHECK:   store <4 x i16> [[VZIP1_I]], <4 x i16>* [[TMP4]], align 4, !alias.scope !135
 // CHECK:   ret void
 poly16x4x2_t test_vzip_p16(poly16x4_t a, poly16x4_t b) {
   return vzip_p16(a, b);
@@ -21036,10 +21036,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.int8x16x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
-// CHECK:   store <16 x i8> [[VZIP_I]], <16 x i8>* [[TMP1]], !alias.scope !138
+// CHECK:   store <16 x i8> [[VZIP_I]], <16 x i8>* [[TMP1]], align 4, !alias.scope !138
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
-// CHECK:   store <16 x i8> [[VZIP1_I]], <16 x i8>* [[TMP2]], !alias.scope !138
+// CHECK:   store <16 x i8> [[VZIP1_I]], <16 x i8>* [[TMP2]], align 4, !alias.scope !138
 // CHECK:   ret void
 int8x16x2_t test_vzipq_s8(int8x16_t a, int8x16_t b) {
   return vzipq_s8(a, b);
@@ -21051,10 +21051,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <8 x i16> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-// CHECK:   store <8 x i16> [[VZIP_I]], <8 x i16>* [[TMP3]], !alias.scope !141
+// CHECK:   store <8 x i16> [[VZIP_I]], <8 x i16>* [[TMP3]], align 4, !alias.scope !141
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
-// CHECK:   store <8 x i16> [[VZIP1_I]], <8 x i16>* [[TMP4]], !alias.scope !141
+// CHECK:   store <8 x i16> [[VZIP1_I]], <8 x i16>* [[TMP4]], align 4, !alias.scope !141
 // CHECK:   ret void
 int16x8x2_t test_vzipq_s16(int16x8_t a, int16x8_t b) {
   return vzipq_s16(a, b);
@@ -21066,10 +21066,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i32> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i32>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
-// CHECK:   store <4 x i32> [[VZIP_I]], <4 x i32>* [[TMP3]], !alias.scope !144
+// CHECK:   store <4 x i32> [[VZIP_I]], <4 x i32>* [[TMP3]], align 4, !alias.scope !144
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-// CHECK:   store <4 x i32> [[VZIP1_I]], <4 x i32>* [[TMP4]], !alias.scope !144
+// CHECK:   store <4 x i32> [[VZIP1_I]], <4 x i32>* [[TMP4]], align 4, !alias.scope !144
 // CHECK:   ret void
 int32x4x2_t test_vzipq_s32(int32x4_t a, int32x4_t b) {
   return vzipq_s32(a, b);
@@ -21079,10 +21079,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.uint8x16x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
-// CHECK:   store <16 x i8> [[VZIP_I]], <16 x i8>* [[TMP1]], !alias.scope !147
+// CHECK:   store <16 x i8> [[VZIP_I]], <16 x i8>* [[TMP1]], align 4, !alias.scope !147
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
-// CHECK:   store <16 x i8> [[VZIP1_I]], <16 x i8>* [[TMP2]], !alias.scope !147
+// CHECK:   store <16 x i8> [[VZIP1_I]], <16 x i8>* [[TMP2]], align 4, !alias.scope !147
 // CHECK:   ret void
 uint8x16x2_t test_vzipq_u8(uint8x16_t a, uint8x16_t b) {
   return vzipq_u8(a, b);
@@ -21094,10 +21094,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <8 x i16> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-// CHECK:   store <8 x i16> [[VZIP_I]], <8 x i16>* [[TMP3]], !alias.scope !150
+// CHECK:   store <8 x i16> [[VZIP_I]], <8 x i16>* [[TMP3]], align 4, !alias.scope !150
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
-// CHECK:   store <8 x i16> [[VZIP1_I]], <8 x i16>* [[TMP4]], !alias.scope !150
+// CHECK:   store <8 x i16> [[VZIP1_I]], <8 x i16>* [[TMP4]], align 4, !alias.scope !150
 // CHECK:   ret void
 uint16x8x2_t test_vzipq_u16(uint16x8_t a, uint16x8_t b) {
   return vzipq_u16(a, b);
@@ -21109,10 +21109,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x i32> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x i32>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
-// CHECK:   store <4 x i32> [[VZIP_I]], <4 x i32>* [[TMP3]], !alias.scope !153
+// CHECK:   store <4 x i32> [[VZIP_I]], <4 x i32>* [[TMP3]], align 4, !alias.scope !153
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <4 x i32> %a, <4 x i32> %b, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-// CHECK:   store <4 x i32> [[VZIP1_I]], <4 x i32>* [[TMP4]], !alias.scope !153
+// CHECK:   store <4 x i32> [[VZIP1_I]], <4 x i32>* [[TMP4]], align 4, !alias.scope !153
 // CHECK:   ret void
 uint32x4x2_t test_vzipq_u32(uint32x4_t a, uint32x4_t b) {
   return vzipq_u32(a, b);
@@ -21124,10 +21124,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <4 x float> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <4 x float>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 4, i32 1, i32 5>
-// CHECK:   store <4 x float> [[VZIP_I]], <4 x float>* [[TMP3]], !alias.scope !156
+// CHECK:   store <4 x float> [[VZIP_I]], <4 x float>* [[TMP3]], align 4, !alias.scope !156
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <4 x float>, <4 x float>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 2, i32 6, i32 3, i32 7>
-// CHECK:   store <4 x float> [[VZIP1_I]], <4 x float>* [[TMP4]], !alias.scope !156
+// CHECK:   store <4 x float> [[VZIP1_I]], <4 x float>* [[TMP4]], align 4, !alias.scope !156
 // CHECK:   ret void
 float32x4x2_t test_vzipq_f32(float32x4_t a, float32x4_t b) {
   return vzipq_f32(a, b);
@@ -21137,10 +21137,10 @@
 // CHECK:   [[TMP0:%.*]] = bitcast %struct.poly8x16x2_t* [[AGG_RESULT]] to i8*
 // CHECK:   [[TMP1:%.*]] = bitcast i8* [[TMP0]] to <16 x i8>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
-// CHECK:   store <16 x i8> [[VZIP_I]], <16 x i8>* [[TMP1]], !alias.scope !159
+// CHECK:   store <16 x i8> [[VZIP_I]], <16 x i8>* [[TMP1]], align 4, !alias.scope !159
 // CHECK:   [[TMP2:%.*]] = getelementptr inbounds <16 x i8>, <16 x i8>* [[TMP1]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
-// CHECK:   store <16 x i8> [[VZIP1_I]], <16 x i8>* [[TMP2]], !alias.scope !159
+// CHECK:   store <16 x i8> [[VZIP1_I]], <16 x i8>* [[TMP2]], align 4, !alias.scope !159
 // CHECK:   ret void
 poly8x16x2_t test_vzipq_p8(poly8x16_t a, poly8x16_t b) {
   return vzipq_p8(a, b);
@@ -21152,10 +21152,10 @@
 // CHECK:   [[TMP2:%.*]] = bitcast <8 x i16> %b to <16 x i8>
 // CHECK:   [[TMP3:%.*]] = bitcast i8* [[TMP0]] to <8 x i16>*
 // CHECK:   [[VZIP_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
-// CHECK:   store <8 x i16> [[VZIP_I]], <8 x i16>* [[TMP3]], !alias.scope !162
+// CHECK:   store <8 x i16> [[VZIP_I]], <8 x i16>* [[TMP3]], align 4, !alias.scope !162
 // CHECK:   [[TMP4:%.*]] = getelementptr inbounds <8 x i16>, <8 x i16>* [[TMP3]], i32 1
 // CHECK:   [[VZIP1_I:%.*]] = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
-// CHECK:   store <8 x i16> [[VZIP1_I]], <8 x i16>* [[TMP4]], !alias.scope !162
+// CHECK:   store <8 x i16> [[VZIP1_I]], <8 x i16>* [[TMP4]], align 4, !alias.scope !162
 // CHECK:   ret void
 poly16x8x2_t test_vzipq_p16(poly16x8_t a, poly16x8_t b) {
   return vzipq_p16(a, b);
diff --git a/llvm/include/llvm/IR/IRBuilder.h b/llvm/include/llvm/IR/IRBuilder.h
--- a/llvm/include/llvm/IR/IRBuilder.h
+++ b/llvm/include/llvm/IR/IRBuilder.h
@@ -1568,28 +1568,32 @@
 
   AllocaInst *CreateAlloca(Type *Ty, unsigned AddrSpace,
                            Value *ArraySize = nullptr, const Twine &Name = "") {
-    return Insert(new AllocaInst(Ty, AddrSpace, ArraySize), Name);
+    const DataLayout &DL = BB->getModule()->getDataLayout();
+    Align AllocaAlign = DL.getPrefTypeAlign(Ty);
+    return Insert(new AllocaInst(Ty, AddrSpace, ArraySize, AllocaAlign), Name);
   }
 
   AllocaInst *CreateAlloca(Type *Ty, Value *ArraySize = nullptr,
                            const Twine &Name = "") {
-    const DataLayout &DL = BB->getParent()->getParent()->getDataLayout();
-    return Insert(new AllocaInst(Ty, DL.getAllocaAddrSpace(), ArraySize), Name);
+    const DataLayout &DL = BB->getModule()->getDataLayout();
+    Align AllocaAlign = DL.getPrefTypeAlign(Ty);
+    unsigned AddrSpace = DL.getAllocaAddrSpace();
+    return Insert(new AllocaInst(Ty, AddrSpace, ArraySize, AllocaAlign), Name);
   }
 
   /// Provided to resolve 'CreateLoad(Ty, Ptr, "...")' correctly, instead of
   /// converting the string to 'bool' for the isVolatile parameter.
   LoadInst *CreateLoad(Type *Ty, Value *Ptr, const char *Name) {
-    return Insert(new LoadInst(Ty, Ptr), Name);
+    return CreateAlignedLoad(Ty, Ptr, MaybeAlign(), Name);
   }
 
   LoadInst *CreateLoad(Type *Ty, Value *Ptr, const Twine &Name = "") {
-    return Insert(new LoadInst(Ty, Ptr), Name);
+    return CreateAlignedLoad(Ty, Ptr, MaybeAlign(), Name);
   }
 
   LoadInst *CreateLoad(Type *Ty, Value *Ptr, bool isVolatile,
                        const Twine &Name = "") {
-    return Insert(new LoadInst(Ty, Ptr, Twine(), isVolatile), Name);
+    return CreateAlignedLoad(Ty, Ptr, MaybeAlign(), isVolatile, Name);
   }
 
   // Deprecated [opaque pointer types]
@@ -1609,7 +1613,7 @@
   }
 
   StoreInst *CreateStore(Value *Val, Value *Ptr, bool isVolatile = false) {
-    return Insert(new StoreInst(Val, Ptr, isVolatile));
+    return CreateAlignedStore(Val, Ptr, MaybeAlign(), isVolatile);
   }
 
   LLVM_ATTRIBUTE_DEPRECATED(LoadInst *CreateAlignedLoad(Type *Ty, Value *Ptr,
@@ -1620,9 +1624,7 @@
   }
   LoadInst *CreateAlignedLoad(Type *Ty, Value *Ptr, MaybeAlign Align,
                               const char *Name) {
-    LoadInst *LI = CreateLoad(Ty, Ptr, Name);
-    LI->setAlignment(Align);
-    return LI;
+    return CreateAlignedLoad(Ty, Ptr, Align, /*isVolatile*/false, Name);
   }
 
   LLVM_ATTRIBUTE_DEPRECATED(LoadInst *CreateAlignedLoad(Type *Ty, Value *Ptr,
@@ -1633,9 +1635,7 @@
   }
   LoadInst *CreateAlignedLoad(Type *Ty, Value *Ptr, MaybeAlign Align,
                               const Twine &Name = "") {
-    LoadInst *LI = CreateLoad(Ty, Ptr, Name);
-    LI->setAlignment(Align);
-    return LI;
+    return CreateAlignedLoad(Ty, Ptr, Align, /*isVolatile*/false, Name);
   }
 
   LLVM_ATTRIBUTE_DEPRECATED(LoadInst *CreateAlignedLoad(Type *Ty, Value *Ptr,
@@ -1647,9 +1647,11 @@
   }
   LoadInst *CreateAlignedLoad(Type *Ty, Value *Ptr, MaybeAlign Align,
                               bool isVolatile, const Twine &Name = "") {
-    LoadInst *LI = CreateLoad(Ty, Ptr, isVolatile, Name);
-    LI->setAlignment(Align);
-    return LI;
+    if (!Align) {
+      const DataLayout &DL = BB->getModule()->getDataLayout();
+      Align = DL.getABITypeAlign(Ty);
+    }
+    return Insert(new LoadInst(Ty, Ptr, Twine(), isVolatile, *Align), Name);
   }
 
   // Deprecated [opaque pointer types]
@@ -1703,9 +1705,11 @@
   }
   StoreInst *CreateAlignedStore(Value *Val, Value *Ptr, MaybeAlign Align,
                                 bool isVolatile = false) {
-    StoreInst *SI = CreateStore(Val, Ptr, isVolatile);
-    SI->setAlignment(Align);
-    return SI;
+    if (!Align) {
+      const DataLayout &DL = BB->getModule()->getDataLayout();
+      Align = DL.getABITypeAlign(Val->getType());
+    }
+    return Insert(new StoreInst(Val, Ptr, isVolatile, Align));
   }
   FenceInst *CreateFence(AtomicOrdering Ordering,
                          SyncScope::ID SSID = SyncScope::System,
diff --git a/llvm/test/Bindings/llvm-c/atomics.ll b/llvm/test/Bindings/llvm-c/atomics.ll
--- a/llvm/test/Bindings/llvm-c/atomics.ll
+++ b/llvm/test/Bindings/llvm-c/atomics.ll
@@ -3,7 +3,7 @@
 ; RUN: diff -w %t.orig %t.echo
 
 define i32 @main() {
-  %1 = alloca i32
+  %1 = alloca i32, align 4
   %2 = cmpxchg i32* %1, i32 2, i32 3 seq_cst acquire
   %3 = extractvalue { i32, i1 } %2, 0
   ret i32 %3
diff --git a/llvm/test/Bindings/llvm-c/echo.ll b/llvm/test/Bindings/llvm-c/echo.ll
--- a/llvm/test/Bindings/llvm-c/echo.ll
+++ b/llvm/test/Bindings/llvm-c/echo.ll
@@ -48,18 +48,18 @@
 
 ; TODO: label and metadata types
 define void @types() {
-  %1 = alloca half
-  %2 = alloca float
-  %3 = alloca double
-  %4 = alloca x86_fp80
-  %5 = alloca fp128
-  %6 = alloca ppc_fp128
-  %7 = alloca i7
-  %8 = alloca void (i1)*
-  %9 = alloca [3 x i22]
-  %10 = alloca i328 addrspace(5)*
-  %11 = alloca <5 x i23*>
-  %12 = alloca x86_mmx
+  %1 = alloca half, align 2
+  %2 = alloca float, align 4
+  %3 = alloca double, align 8
+  %4 = alloca x86_fp80, align 16
+  %5 = alloca fp128, align 16
+  %6 = alloca ppc_fp128, align 16
+  %7 = alloca i7, align 1
+  %8 = alloca void (i1)*, align 8
+  %9 = alloca [3 x i22], align 4
+  %10 = alloca i328 addrspace(5)*, align 8
+  %11 = alloca <5 x i23*>, align 64
+  %12 = alloca x86_mmx, align 8
   ret void
 }
 
@@ -203,7 +203,7 @@
 define void @test_intrinsics() {
 entry:
   %sp = call i8* @llvm.stacksave()
-  %x = alloca i32
+  %x = alloca i32, align 4
   %0 = bitcast i32* %x to i8*
   call void @llvm.lifetime.start.p0i8(i64 4, i8* %0)
   call void @llvm.lifetime.end.p0i8(i64 4, i8* %0)
diff --git a/llvm/test/Bindings/llvm-c/memops.ll b/llvm/test/Bindings/llvm-c/memops.ll
--- a/llvm/test/Bindings/llvm-c/memops.ll
+++ b/llvm/test/Bindings/llvm-c/memops.ll
@@ -5,9 +5,9 @@
 %S = type { i32, i32 }
 
 define i32 @method(%S* %this, i32 %arg.a, i32 %arg.b) {
-  %a = alloca i32
+  %a = alloca i32, align 4
   store i32 %arg.a, i32* %a, align 4
-  %b = alloca i32
+  %b = alloca i32, align 4
   store i32 %arg.b, i32* %b
   %1 = load i32, i32* %a, align 4
   %2 = load i32, i32* %b, align 4
@@ -22,7 +22,7 @@
 }
 
 define i32 @main() {
-  %s = alloca %S
+  %s = alloca %S, align 4
   store %S zeroinitializer, %S* %s
   %1 = getelementptr inbounds %S, %S* %s, i32 0, i32 0
   %2 = getelementptr inbounds %S, %S* %s, i32 0, i32 1
diff --git a/llvm/test/CodeGen/AMDGPU/widen_extending_scalar_loads.ll b/llvm/test/CodeGen/AMDGPU/widen_extending_scalar_loads.ll
--- a/llvm/test/CodeGen/AMDGPU/widen_extending_scalar_loads.ll
+++ b/llvm/test/CodeGen/AMDGPU/widen_extending_scalar_loads.ll
@@ -190,7 +190,7 @@
 }
 
 ; OPT-LABEL: @constant_load_i16_align4_range(
-; OPT: load i32, i32 addrspace(4)* %1, !range !0
+; OPT: load i32, i32 addrspace(4)* %1, align 4, !range !0
 define amdgpu_kernel void @constant_load_i16_align4_range(i32 addrspace(1)* %out, i16 addrspace(4)* %in) #0 {
   %ld = load i16, i16 addrspace(4)* %in, align 4, !range !0
   %ext = sext i16 %ld to i32
@@ -199,7 +199,7 @@
 }
 
 ; OPT-LABEL: @constant_load_i16_align4_range_max(
-; OPT: load i32, i32 addrspace(4)* %1, !range !0
+; OPT: load i32, i32 addrspace(4)* %1, align 4, !range !0
 define amdgpu_kernel void @constant_load_i16_align4_range_max(i32 addrspace(1)* %out, i16 addrspace(4)* %in) #0 {
   %ld = load i16, i16 addrspace(4)* %in, align 4, !range !1
   %ext = sext i16 %ld to i32
@@ -208,7 +208,7 @@
 }
 
 ; OPT-LABEL: @constant_load_i16_align4_complex_range(
-; OPT: load i32, i32 addrspace(4)* %1, !range !1
+; OPT: load i32, i32 addrspace(4)* %1, align 4, !range !1
 define amdgpu_kernel void @constant_load_i16_align4_complex_range(i32 addrspace(1)* %out, i16 addrspace(4)* %in) #0 {
   %ld = load i16, i16 addrspace(4)* %in, align 4, !range !2
   %ext = sext i16 %ld to i32
@@ -217,7 +217,7 @@
 }
 
 ; OPT-LABEL: @constant_load_i16_align4_range_from_0(
-; OPT: load i32, i32 addrspace(4)* %1{{$}}
+; OPT: load i32, i32 addrspace(4)* %1, align 4{{$}}
 define amdgpu_kernel void @constant_load_i16_align4_range_from_0(i32 addrspace(1)* %out, i16 addrspace(4)* %in) #0 {
   %ld = load i16, i16 addrspace(4)* %in, align 4, !range !3
   %ext = sext i16 %ld to i32
@@ -226,7 +226,7 @@
 }
 
 ; OPT-LABEL: @constant_load_i16_align4_range_from_neg(
-; OPT: load i32, i32 addrspace(4)* %1, !range !2
+; OPT: load i32, i32 addrspace(4)* %1, align 4, !range !2
 define amdgpu_kernel void @constant_load_i16_align4_range_from_neg(i32 addrspace(1)* %out, i16 addrspace(4)* %in) #0 {
   %ld = load i16, i16 addrspace(4)* %in, align 4, !range !4
   %ext = sext i16 %ld to i32
@@ -235,7 +235,7 @@
 }
 
 ; OPT-LABEL: @constant_load_i16_align4_range_from_neg_to_0(
-; OPT: load i32, i32 addrspace(4)* %1, !range !2
+; OPT: load i32, i32 addrspace(4)* %1, align 4, !range !2
 define amdgpu_kernel void @constant_load_i16_align4_range_from_neg_to_0(i32 addrspace(1)* %out, i16 addrspace(4)* %in) #0 {
   %ld = load i16, i16 addrspace(4)* %in, align 4, !range !5
   %ext = sext i16 %ld to i32
@@ -244,7 +244,7 @@
 }
 
 ; OPT-LABEL: @constant_load_i16_align4_invariant
-; OPT: load i32, i32 addrspace(4)* %1, !invariant.load !3
+; OPT: load i32, i32 addrspace(4)* %1, align 4, !invariant.load !3
 define amdgpu_kernel void @constant_load_i16_align4_invariant(i32 addrspace(1)* %out, i16 addrspace(4)* %in) #0 {
   %ld = load i16, i16 addrspace(4)* %in, align 4, !invariant.load !6
   %ext = sext i16 %ld to i32
diff --git a/llvm/test/Instrumentation/AddressSanitizer/debug-info-alloca.ll b/llvm/test/Instrumentation/AddressSanitizer/debug-info-alloca.ll
--- a/llvm/test/Instrumentation/AddressSanitizer/debug-info-alloca.ll
+++ b/llvm/test/Instrumentation/AddressSanitizer/debug-info-alloca.ll
@@ -17,7 +17,7 @@
 define dso_local i32 @main(i32 %argc, i8** %argv) #0 !dbg !15 {
 entry:
 ; No suffix like !dbg !123
-; CHECK: %asan_local_stack_base = alloca i64{{$}}
+; CHECK: %asan_local_stack_base = alloca i64, align 8{{$}}
 ; CHECK:     %3 = call i64 @__asan_stack_malloc_0(i64 64){{$}}
   %argc.addr = alloca i32, align 4
   %argv.addr = alloca i8**, align 8
diff --git a/llvm/test/Instrumentation/SanitizerCoverage/inline-8bit-counters.ll b/llvm/test/Instrumentation/SanitizerCoverage/inline-8bit-counters.ll
--- a/llvm/test/Instrumentation/SanitizerCoverage/inline-8bit-counters.ll
+++ b/llvm/test/Instrumentation/SanitizerCoverage/inline-8bit-counters.ll
@@ -7,9 +7,9 @@
 define void @foo() {
 entry:
 ; CHECK: section "__sancov_cntrs", comdat($foo), align 1
-; CHECK:  %0 = load i8, i8* getelementptr inbounds ([1 x i8], [1 x i8]* @__sancov_gen_, i64 0, i64 0), !nosanitize
+; CHECK:  %0 = load i8, i8* getelementptr inbounds ([1 x i8], [1 x i8]* @__sancov_gen_, i64 0, i64 0), align 1, !nosanitize
 ; CHECK:  %1 = add i8 %0, 1
-; CHECK:  store i8 %1, i8* getelementptr inbounds ([1 x i8], [1 x i8]* @__sancov_gen_, i64 0, i64 0), !nosanitize
+; CHECK:  store i8 %1, i8* getelementptr inbounds ([1 x i8], [1 x i8]* @__sancov_gen_, i64 0, i64 0), align 1, !nosanitize
   ret void
 }
 ; CHECK: call void @__sanitizer_cov_8bit_counters_init(i8* bitcast (i8** @__start___sancov_cntrs to i8*), i8* bitcast (i8** @__stop___sancov_cntrs to i8*))
diff --git a/llvm/test/Instrumentation/SanitizerCoverage/inline-bool-flag.ll b/llvm/test/Instrumentation/SanitizerCoverage/inline-bool-flag.ll
--- a/llvm/test/Instrumentation/SanitizerCoverage/inline-bool-flag.ll
+++ b/llvm/test/Instrumentation/SanitizerCoverage/inline-bool-flag.ll
@@ -7,7 +7,7 @@
 define void @foo() {
 entry:
 ; CHECK: @__sancov_gen_ = private global [1 x i1] zeroinitializer, section "__sancov_bool_flag", comdat($foo), align 1, !associated !0
-; CHECK: store i1 true, i1* getelementptr inbounds ([1 x i1], [1 x i1]* @__sancov_gen_, i64 0, i64 0), !nosanitize !1
+; CHECK: store i1 true, i1* getelementptr inbounds ([1 x i1], [1 x i1]* @__sancov_gen_, i64 0, i64 0), align 1, !nosanitize !1
   ret void
 }
 ; CHECK: call void @__sanitizer_cov_bool_flag_init(i1* bitcast (i1** @__start___sancov_bool_flag to i1*), i1* bitcast (i1** @__stop___sancov_bool_flag to i1*))
diff --git a/llvm/test/Transforms/ArgumentPromotion/dbg.ll b/llvm/test/Transforms/ArgumentPromotion/dbg.ll
--- a/llvm/test/Transforms/ArgumentPromotion/dbg.ll
+++ b/llvm/test/Transforms/ArgumentPromotion/dbg.ll
@@ -38,9 +38,9 @@
 ; CHECK-NEXT:    [[Y_VAL_VAL:%.*]] = load i32, i32* [[Y_VAL]], align 8, !dbg !4
 ; CHECK-NEXT:    call void @test(i32 [[Y_VAL_VAL]]), !dbg !4
 ; CHECK-NEXT:    [[P_0:%.*]] = getelementptr [[STRUCT_PAIR:%.*]], %struct.pair* [[P]], i32 0, i32 0, !dbg !5
-; CHECK-NEXT:    [[P_0_VAL:%.*]] = load i32, i32* [[P_0]], !dbg !5
+; CHECK-NEXT:    [[P_0_VAL:%.*]] = load i32, i32* [[P_0]], align 4, !dbg !5
 ; CHECK-NEXT:    [[P_1:%.*]] = getelementptr [[STRUCT_PAIR]], %struct.pair* [[P]], i32 0, i32 1, !dbg !5
-; CHECK-NEXT:    [[P_1_VAL:%.*]] = load i32, i32* [[P_1]], !dbg !5
+; CHECK-NEXT:    [[P_1_VAL:%.*]] = load i32, i32* [[P_1]], align 4, !dbg !5
 ; CHECK-NEXT:    call void @test_byval(i32 [[P_0_VAL]], i32 [[P_1_VAL]]), !dbg !5
 ; CHECK-NEXT:    ret void
 ;
diff --git a/llvm/test/Transforms/SROA/alignment.ll b/llvm/test/Transforms/SROA/alignment.ll
--- a/llvm/test/Transforms/SROA/alignment.ll
+++ b/llvm/test/Transforms/SROA/alignment.ll
@@ -130,11 +130,14 @@
 }
 
 define void @test6() {
-; Test that we promote alignment when the underlying alloca switches to one
-; that innately provides it.
+; We should set the alignment on all load and store operations; make sure
+; we choose an appropriate alignment.
 ; CHECK-LABEL: @test6(
-; CHECK: alloca double
-; CHECK: alloca double
+; CHECK: alloca double{{$}}
+; CHECK: alloca double{{$}}
+; CHECK: store{{.*}}, align 8
+; CHECK: load{{.*}}, align 8
+; CHECK: store{{.*}}, align 8
 ; CHECK-NOT: align
 ; CHECK: ret void
 
diff --git a/llvm/test/Transforms/SROA/basictest.ll b/llvm/test/Transforms/SROA/basictest.ll
--- a/llvm/test/Transforms/SROA/basictest.ll
+++ b/llvm/test/Transforms/SROA/basictest.ll
@@ -195,7 +195,7 @@
   %overlap.9.i64 = bitcast i8* %overlap.9.i8 to i64*
   store i8 1, i8* %overlap.1.i8, !tbaa !3
 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [16 x i8], [16 x i8]* %[[test3_a3]], i64 0, i64 0
-; CHECK-NEXT: store i8 1, i8* %[[gep]], !tbaa [[TAG_3:!.*]]
+; CHECK-NEXT: store i8 1, i8* %[[gep]], align 1, !tbaa [[TAG_3:!.*]]
   store i16 1, i16* %overlap.1.i16, !tbaa !5
 ; CHECK-NEXT: %[[bitcast:.*]] = bitcast [16 x i8]* %[[test3_a3]] to i16*
 ; CHECK-NEXT: store i16 1, i16* %[[bitcast]], {{.*}}, !tbaa [[TAG_5:!.*]]
@@ -256,7 +256,7 @@
   %overlap2.1.3.i32 = bitcast i8* %overlap2.1.3.i8 to i32*
   store i8 1,  i8*  %overlap2.1.0.i8, !tbaa !27
 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a5]], i64 0, i64 0
-; CHECK-NEXT: store i8 1, i8* %[[gep]], !tbaa [[TAG_27:!.*]]
+; CHECK-NEXT: store i8 1, i8* %[[gep]], align 1, !tbaa [[TAG_27:!.*]]
   store i16 1, i16* %overlap2.1.0.i16, !tbaa !29
 ; CHECK-NEXT: %[[bitcast:.*]] = bitcast [7 x i8]* %[[test3_a5]] to i16*
 ; CHECK-NEXT: store i16 1, i16* %[[bitcast]], {{.*}}, !tbaa [[TAG_29:!.*]]
@@ -286,7 +286,7 @@
 ; CHECK-NEXT: store i32 1, i32* %[[bitcast]], {{.*}}, !tbaa [[TAG_39:!.*]]
   store i8 1,  i8*  %overlap2.2.1.i8, !tbaa !41
 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 1
-; CHECK-NEXT: store i8 1, i8* %[[gep]], !tbaa [[TAG_41:!.*]]
+; CHECK-NEXT: store i8 1, i8* %[[gep]], align 1, !tbaa [[TAG_41:!.*]]
   store i16 1, i16* %overlap2.2.1.i16, !tbaa !43
 ; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds [7 x i8], [7 x i8]* %[[test3_a6]], i64 0, i64 1
 ; CHECK-NEXT: %[[bitcast:.*]] = bitcast i8* %[[gep]] to i16*
diff --git a/llvm/test/Transforms/SROA/preserve-nonnull.ll b/llvm/test/Transforms/SROA/preserve-nonnull.ll
--- a/llvm/test/Transforms/SROA/preserve-nonnull.ll
+++ b/llvm/test/Transforms/SROA/preserve-nonnull.ll
@@ -12,7 +12,7 @@
 ; CHECK-NEXT:    %[[A:.*]] = alloca i8*
 ; CHECK-NEXT:    %[[V_CAST:.*]] = bitcast i32* %v to i8*
 ; CHECK-NEXT:    store i8* %[[V_CAST]], i8** %[[A]]
-; CHECK-NEXT:    %[[LOAD:.*]] = load volatile i8*, i8** %[[A]], !nonnull !0
+; CHECK-NEXT:    %[[LOAD:.*]] = load volatile i8*, i8** %[[A]], align 8, !nonnull !0
 ; CHECK-NEXT:    ret i8* %[[LOAD]]
 entry:
   %a = alloca [2 x i8*]
diff --git a/llvm/tools/llvm-c-test/echo.cpp b/llvm/tools/llvm-c-test/echo.cpp
--- a/llvm/tools/llvm-c-test/echo.cpp
+++ b/llvm/tools/llvm-c-test/echo.cpp
@@ -577,6 +577,7 @@
       case LLVMAlloca: {
         LLVMTypeRef Ty = CloneType(LLVMGetAllocatedType(Src));
         Dst = LLVMBuildAlloca(Builder, Ty, Name);
+        LLVMSetAlignment(Dst, LLVMGetAlignment(Src));
         break;
       }
       case LLVMLoad: {
diff --git a/polly/test/Isl/CodeGen/invariant_load_alias_metadata.ll b/polly/test/Isl/CodeGen/invariant_load_alias_metadata.ll
--- a/polly/test/Isl/CodeGen/invariant_load_alias_metadata.ll
+++ b/polly/test/Isl/CodeGen/invariant_load_alias_metadata.ll
@@ -4,7 +4,7 @@
 ; This test case checks whether Polly generates alias metadata in case of
 ; the ublas gemm kernel and polly-invariant-load-hoisting.
 ;
-; CHECK: store float 4.200000e+01, float* %polly.access.A.load, !alias.scope !3, !noalias !4
+; CHECK: store float 4.200000e+01, float* %polly.access.A.load, align 4, !alias.scope !3, !noalias !4
 ;
 ; CHECK: !0 = distinct !{!0, !1, !"polly.alias.scope.MemRef_A"}
 ; CHECK-NEXT: !1 = distinct !{!1, !"polly.alias.scope.domain"}
diff --git a/polly/test/Isl/CodeGen/non-affine-phi-node-expansion-2.ll b/polly/test/Isl/CodeGen/non-affine-phi-node-expansion-2.ll
--- a/polly/test/Isl/CodeGen/non-affine-phi-node-expansion-2.ll
+++ b/polly/test/Isl/CodeGen/non-affine-phi-node-expansion-2.ll
@@ -4,7 +4,7 @@
 
 
 ; CHECK: polly.stmt.bb3:                                   ; preds = %polly.stmt.bb3.entry
-; CHECK:   %tmp6_p_scalar_ = load double, double* %arg1{{[0-9]*}}, !alias.scope !0, !noalias !2
+; CHECK:   %tmp6_p_scalar_ = load double, double* %arg1{{[0-9]*}}, align 8, !alias.scope !0, !noalias !2
 ; CHECK:   %p_tmp7 = fadd double 1.000000e+00, %tmp6_p_scalar_
 ; CHECK:   %p_tmp8 = fcmp olt double 1.400000e+01, %p_tmp7
 ; CHECK:   br i1 %p_tmp8, label %polly.stmt.bb9, label %polly.stmt.bb10
diff --git a/polly/test/Isl/CodeGen/partial_write_array.ll b/polly/test/Isl/CodeGen/partial_write_array.ll
--- a/polly/test/Isl/CodeGen/partial_write_array.ll
+++ b/polly/test/Isl/CodeGen/partial_write_array.ll
@@ -38,7 +38,7 @@
 
 ; CHECK:      polly.stmt.body.Stmt_body_Write0.partial:
 ; CHECK-NEXT:   %polly.access.A = getelementptr double, double* %A, i64 0
-; CHECK-NEXT:   store double 4.200000e+01, double* %polly.access.A, !alias.scope !0, !noalias !2
+; CHECK-NEXT:   store double 4.200000e+01, double* %polly.access.A, align 8, !alias.scope !0, !noalias !2
 ; CHECK-NEXT:   br label %polly.stmt.body.cont
 
 ; CHECK:      polly.stmt.body.cont:
diff --git a/polly/test/Isl/CodeGen/partial_write_impossible_restriction.ll b/polly/test/Isl/CodeGen/partial_write_impossible_restriction.ll
--- a/polly/test/Isl/CodeGen/partial_write_impossible_restriction.ll
+++ b/polly/test/Isl/CodeGen/partial_write_impossible_restriction.ll
@@ -50,10 +50,10 @@
 
 ; CHECK-LABEL: polly.stmt.cond.false:
 ; CHECK:         %polly.access..pn2 = getelementptr i32, i32* %.pn, i64 %polly.indvar
-; CHECK:         store i32 %cond.in.sroa.speculate.load.cond.false_p_scalar_, i32* %polly.access..pn2, !alias.scope !0, !noalias !2
+; CHECK:         store i32 %cond.in.sroa.speculate.load.cond.false_p_scalar_, i32* %polly.access..pn2, align 4, !alias.scope !0, !noalias !2
 ; CHECK:         br label %polly.merge
 
 ; CHECK-LABEL: polly.stmt.cond.false11:
 ; CHECK:         %polly.access..pn14 = getelementptr i32, i32* %.pn, i64 0
-; CHECK:         store i32 %cond.in.sroa.speculate.load.cond.false_p_scalar_13, i32* %polly.access..pn14, !alias.scope !0, !noalias !2
+; CHECK:         store i32 %cond.in.sroa.speculate.load.cond.false_p_scalar_13, i32* %polly.access..pn14, align 4, !alias.scope !0, !noalias !2
 ; CHECK:         br label %polly.stmt.cond.end15