Fix tests for Neon load/store intrinsics to match the i8* types expected by

the intrinsics.  The reason for those i8* types is that the intrinsics are
overloaded on the vector type and we don't have a way to declare an intrinsic
where one argument is an overloaded vector type and another argument is a
pointer to the vector element type.  The bitcasts added here will match what
the frontend will typically generate when these intrinsics are used.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@101840 91177308-0d34-0410-b5e6-96231b3b80d8

10 files changed, 188 insertions, 94 deletions

diff --git a/test/CodeGen/ARM/vld1.ll b/test/CodeGen/ARM/vld1.ll
index f5383aafb2..c61ea8c9a7 100644
--- a/test/CodeGen/ARM/vld1.ll
+++ b/test/CodeGen/ARM/vld1.ll
@@ -10,28 +10,32 @@ define <8 x i8> @vld1i8(i8* %A) nounwind {
 define <4 x i16> @vld1i16(i16* %A) nounwind {
 ;CHECK: vld1i16:
 ;CHECK: vld1.16
-	%tmp1 = call <4 x i16> @llvm.arm.neon.vld1.v4i16(i16* %A)
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = call <4 x i16> @llvm.arm.neon.vld1.v4i16(i8* %tmp0)
 	ret <4 x i16> %tmp1
 }
 
 define <2 x i32> @vld1i32(i32* %A) nounwind {
 ;CHECK: vld1i32:
 ;CHECK: vld1.32
-	%tmp1 = call <2 x i32> @llvm.arm.neon.vld1.v2i32(i32* %A)
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = call <2 x i32> @llvm.arm.neon.vld1.v2i32(i8* %tmp0)
 	ret <2 x i32> %tmp1
 }
 
 define <2 x float> @vld1f(float* %A) nounwind {
 ;CHECK: vld1f:
 ;CHECK: vld1.32
-	%tmp1 = call <2 x float> @llvm.arm.neon.vld1.v2f32(float* %A)
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = call <2 x float> @llvm.arm.neon.vld1.v2f32(i8* %tmp0)
 	ret <2 x float> %tmp1
 }
 
 define <1 x i64> @vld1i64(i64* %A) nounwind {
 ;CHECK: vld1i64:
 ;CHECK: vld1.64
-	%tmp1 = call <1 x i64> @llvm.arm.neon.vld1.v1i64(i64* %A)
+	%tmp0 = bitcast i64* %A to i8*
+	%tmp1 = call <1 x i64> @llvm.arm.neon.vld1.v1i64(i8* %tmp0)
 	ret <1 x i64> %tmp1
 }
 
@@ -45,28 +49,32 @@ define <16 x i8> @vld1Qi8(i8* %A) nounwind {
 define <8 x i16> @vld1Qi16(i16* %A) nounwind {
 ;CHECK: vld1Qi16:
 ;CHECK: vld1.16
-	%tmp1 = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i16* %A)
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = call <8 x i16> @llvm.arm.neon.vld1.v8i16(i8* %tmp0)
 	ret <8 x i16> %tmp1
 }
 
 define <4 x i32> @vld1Qi32(i32* %A) nounwind {
 ;CHECK: vld1Qi32:
 ;CHECK: vld1.32
-	%tmp1 = call <4 x i32> @llvm.arm.neon.vld1.v4i32(i32* %A)
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = call <4 x i32> @llvm.arm.neon.vld1.v4i32(i8* %tmp0)
 	ret <4 x i32> %tmp1
 }
 
 define <4 x float> @vld1Qf(float* %A) nounwind {
 ;CHECK: vld1Qf:
 ;CHECK: vld1.32
-	%tmp1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(float* %A)
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* %tmp0)
 	ret <4 x float> %tmp1
 }
 
 define <2 x i64> @vld1Qi64(i64* %A) nounwind {
 ;CHECK: vld1Qi64:
 ;CHECK: vld1.64
-	%tmp1 = call <2 x i64> @llvm.arm.neon.vld1.v2i64(i64* %A)
+	%tmp0 = bitcast i64* %A to i8*
+	%tmp1 = call <2 x i64> @llvm.arm.neon.vld1.v2i64(i8* %tmp0)
 	ret <2 x i64> %tmp1
 }
 
diff --git a/test/CodeGen/ARM/vld2.ll b/test/CodeGen/ARM/vld2.ll
index 23f7d2ca0c..f5dc06cb30 100644
--- a/test/CodeGen/ARM/vld2.ll
+++ b/test/CodeGen/ARM/vld2.ll
@@ -24,7 +24,8 @@ define <8 x i8> @vld2i8(i8* %A) nounwind {
 define <4 x i16> @vld2i16(i16* %A) nounwind {
 ;CHECK: vld2i16:
 ;CHECK: vld2.16
-	%tmp1 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i16* %A)
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2.v4i16(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int16x4x2_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int16x4x2_t %tmp1, 1
         %tmp4 = add <4 x i16> %tmp2, %tmp3
@@ -34,7 +35,8 @@ define <4 x i16> @vld2i16(i16* %A) nounwind {
 define <2 x i32> @vld2i32(i32* %A) nounwind {
 ;CHECK: vld2i32:
 ;CHECK: vld2.32
-	%tmp1 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2.v2i32(i32* %A)
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2.v2i32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int32x2x2_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int32x2x2_t %tmp1, 1
         %tmp4 = add <2 x i32> %tmp2, %tmp3
@@ -44,7 +46,8 @@ define <2 x i32> @vld2i32(i32* %A) nounwind {
 define <2 x float> @vld2f(float* %A) nounwind {
 ;CHECK: vld2f:
 ;CHECK: vld2.32
-	%tmp1 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(float* %A)
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2.v2f32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_float32x2x2_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_float32x2x2_t %tmp1, 1
         %tmp4 = add <2 x float> %tmp2, %tmp3
@@ -54,7 +57,8 @@ define <2 x float> @vld2f(float* %A) nounwind {
 define <1 x i64> @vld2i64(i64* %A) nounwind {
 ;CHECK: vld2i64:
 ;CHECK: vld1.64
-	%tmp1 = call %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i64* %A)
+	%tmp0 = bitcast i64* %A to i8*
+	%tmp1 = call %struct.__neon_int64x1x2_t @llvm.arm.neon.vld2.v1i64(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int64x1x2_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int64x1x2_t %tmp1, 1
         %tmp4 = add <1 x i64> %tmp2, %tmp3
@@ -74,7 +78,8 @@ define <16 x i8> @vld2Qi8(i8* %A) nounwind {
 define <8 x i16> @vld2Qi16(i16* %A) nounwind {
 ;CHECK: vld2Qi16:
 ;CHECK: vld2.16
-	%tmp1 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i16* %A)
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2.v8i16(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int16x8x2_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int16x8x2_t %tmp1, 1
         %tmp4 = add <8 x i16> %tmp2, %tmp3
@@ -84,7 +89,8 @@ define <8 x i16> @vld2Qi16(i16* %A) nounwind {
 define <4 x i32> @vld2Qi32(i32* %A) nounwind {
 ;CHECK: vld2Qi32:
 ;CHECK: vld2.32
-	%tmp1 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i32* %A)
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2.v4i32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int32x4x2_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int32x4x2_t %tmp1, 1
         %tmp4 = add <4 x i32> %tmp2, %tmp3
@@ -94,7 +100,8 @@ define <4 x i32> @vld2Qi32(i32* %A) nounwind {
 define <4 x float> @vld2Qf(float* %A) nounwind {
 ;CHECK: vld2Qf:
 ;CHECK: vld2.32
-	%tmp1 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2.v4f32(float* %A)
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2.v4f32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_float32x4x2_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_float32x4x2_t %tmp1, 1
         %tmp4 = add <4 x float> %tmp2, %tmp3
diff --git a/test/CodeGen/ARM/vld3.ll b/test/CodeGen/ARM/vld3.ll
index 207dc6a22e..33c4d37b3e 100644
--- a/test/CodeGen/ARM/vld3.ll
+++ b/test/CodeGen/ARM/vld3.ll
@@ -24,7 +24,8 @@ define <8 x i8> @vld3i8(i8* %A) nounwind {
 define <4 x i16> @vld3i16(i16* %A) nounwind {
 ;CHECK: vld3i16:
 ;CHECK: vld3.16
-	%tmp1 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3.v4i16(i16* %A)
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3.v4i16(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int16x4x3_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int16x4x3_t %tmp1, 2
         %tmp4 = add <4 x i16> %tmp2, %tmp3
@@ -34,7 +35,8 @@ define <4 x i16> @vld3i16(i16* %A) nounwind {
 define <2 x i32> @vld3i32(i32* %A) nounwind {
 ;CHECK: vld3i32:
 ;CHECK: vld3.32
-	%tmp1 = call %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3.v2i32(i32* %A)
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = call %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3.v2i32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int32x2x3_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int32x2x3_t %tmp1, 2
         %tmp4 = add <2 x i32> %tmp2, %tmp3
@@ -44,7 +46,8 @@ define <2 x i32> @vld3i32(i32* %A) nounwind {
 define <2 x float> @vld3f(float* %A) nounwind {
 ;CHECK: vld3f:
 ;CHECK: vld3.32
-	%tmp1 = call %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3.v2f32(float* %A)
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = call %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3.v2f32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_float32x2x3_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_float32x2x3_t %tmp1, 2
         %tmp4 = add <2 x float> %tmp2, %tmp3
@@ -54,7 +57,8 @@ define <2 x float> @vld3f(float* %A) nounwind {
 define <1 x i64> @vld3i64(i64* %A) nounwind {
 ;CHECK: vld3i64:
 ;CHECK: vld1.64
-	%tmp1 = call %struct.__neon_int64x1x3_t @llvm.arm.neon.vld3.v1i64(i64* %A)
+	%tmp0 = bitcast i64* %A to i8*
+	%tmp1 = call %struct.__neon_int64x1x3_t @llvm.arm.neon.vld3.v1i64(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int64x1x3_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int64x1x3_t %tmp1, 2
         %tmp4 = add <1 x i64> %tmp2, %tmp3
@@ -76,7 +80,8 @@ define <8 x i16> @vld3Qi16(i16* %A) nounwind {
 ;CHECK: vld3Qi16:
 ;CHECK: vld3.16
 ;CHECK: vld3.16
-	%tmp1 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3.v8i16(i16* %A)
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3.v8i16(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int16x8x3_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int16x8x3_t %tmp1, 2
         %tmp4 = add <8 x i16> %tmp2, %tmp3
@@ -87,7 +92,8 @@ define <4 x i32> @vld3Qi32(i32* %A) nounwind {
 ;CHECK: vld3Qi32:
 ;CHECK: vld3.32
 ;CHECK: vld3.32
-	%tmp1 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3.v4i32(i32* %A)
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3.v4i32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int32x4x3_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int32x4x3_t %tmp1, 2
         %tmp4 = add <4 x i32> %tmp2, %tmp3
@@ -98,7 +104,8 @@ define <4 x float> @vld3Qf(float* %A) nounwind {
 ;CHECK: vld3Qf:
 ;CHECK: vld3.32
 ;CHECK: vld3.32
-	%tmp1 = call %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3.v4f32(float* %A)
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = call %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3.v4f32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_float32x4x3_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_float32x4x3_t %tmp1, 2
         %tmp4 = add <4 x float> %tmp2, %tmp3
diff --git a/test/CodeGen/ARM/vld4.ll b/test/CodeGen/ARM/vld4.ll
index 0624f2977e..e800cb539a 100644
--- a/test/CodeGen/ARM/vld4.ll
+++ b/test/CodeGen/ARM/vld4.ll
@@ -24,7 +24,8 @@ define <8 x i8> @vld4i8(i8* %A) nounwind {
 define <4 x i16> @vld4i16(i16* %A) nounwind {
 ;CHECK: vld4i16:
 ;CHECK: vld4.16
-	%tmp1 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4.v4i16(i16* %A)
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4.v4i16(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int16x4x4_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int16x4x4_t %tmp1, 2
         %tmp4 = add <4 x i16> %tmp2, %tmp3
@@ -34,7 +35,8 @@ define <4 x i16> @vld4i16(i16* %A) nounwind {
 define <2 x i32> @vld4i32(i32* %A) nounwind {
 ;CHECK: vld4i32:
 ;CHECK: vld4.32
-	%tmp1 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4.v2i32(i32* %A)
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4.v2i32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int32x2x4_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int32x2x4_t %tmp1, 2
         %tmp4 = add <2 x i32> %tmp2, %tmp3
@@ -44,7 +46,8 @@ define <2 x i32> @vld4i32(i32* %A) nounwind {
 define <2 x float> @vld4f(float* %A) nounwind {
 ;CHECK: vld4f:
 ;CHECK: vld4.32
-	%tmp1 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4.v2f32(float* %A)
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4.v2f32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_float32x2x4_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_float32x2x4_t %tmp1, 2
         %tmp4 = add <2 x float> %tmp2, %tmp3
@@ -54,7 +57,8 @@ define <2 x float> @vld4f(float* %A) nounwind {
 define <1 x i64> @vld4i64(i64* %A) nounwind {
 ;CHECK: vld4i64:
 ;CHECK: vld1.64
-	%tmp1 = call %struct.__neon_int64x1x4_t @llvm.arm.neon.vld4.v1i64(i64* %A)
+	%tmp0 = bitcast i64* %A to i8*
+	%tmp1 = call %struct.__neon_int64x1x4_t @llvm.arm.neon.vld4.v1i64(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int64x1x4_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int64x1x4_t %tmp1, 2
         %tmp4 = add <1 x i64> %tmp2, %tmp3
@@ -76,7 +80,8 @@ define <8 x i16> @vld4Qi16(i16* %A) nounwind {
 ;CHECK: vld4Qi16:
 ;CHECK: vld4.16
 ;CHECK: vld4.16
-	%tmp1 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4.v8i16(i16* %A)
+	%tmp0 = bitcast i16* %A to i8*
+	%tmp1 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4.v8i16(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int16x8x4_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int16x8x4_t %tmp1, 2
         %tmp4 = add <8 x i16> %tmp2, %tmp3
@@ -87,7 +92,8 @@ define <4 x i32> @vld4Qi32(i32* %A) nounwind {
 ;CHECK: vld4Qi32:
 ;CHECK: vld4.32
 ;CHECK: vld4.32
-	%tmp1 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4.v4i32(i32* %A)
+	%tmp0 = bitcast i32* %A to i8*
+	%tmp1 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4.v4i32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_int32x4x4_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_int32x4x4_t %tmp1, 2
         %tmp4 = add <4 x i32> %tmp2, %tmp3
@@ -98,7 +104,8 @@ define <4 x float> @vld4Qf(float* %A) nounwind {
 ;CHECK: vld4Qf:
 ;CHECK: vld4.32
 ;CHECK: vld4.32
-	%tmp1 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4.v4f32(float* %A)
+	%tmp0 = bitcast float* %A to i8*
+	%tmp1 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4.v4f32(i8* %tmp0)
         %tmp2 = extractvalue %struct.__neon_float32x4x4_t %tmp1, 0
         %tmp3 = extractvalue %struct.__neon_float32x4x4_t %tmp1, 2
         %tmp4 = add <4 x float> %tmp2, %tmp3
diff --git a/test/CodeGen/ARM/vldlane.ll b/test/CodeGen/ARM/vldlane.ll
index 53881a3f92..46a200220f 100644
--- a/test/CodeGen/ARM/vldlane.ll
+++ b/test/CodeGen/ARM/vldlane.ll
@@ -23,8 +23,9 @@ define <8 x i8> @vld2lanei8(i8* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vld2lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vld2lanei16:
 ;CHECK: vld2.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
-	%tmp2 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_int16x4x2_t @llvm.arm.neon.vld2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_int16x4x2_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int16x4x2_t %tmp2, 1
         %tmp5 = add <4 x i16> %tmp3, %tmp4
@@ -34,8 +35,9 @@ define <4 x i16> @vld2lanei16(i16* %A, <4 x i16>* %B) nounwind {
 define <2 x i32> @vld2lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vld2lanei32:
 ;CHECK: vld2.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
-	%tmp2 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_int32x2x2_t @llvm.arm.neon.vld2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int32x2x2_t %tmp2, 1
         %tmp5 = add <2 x i32> %tmp3, %tmp4
@@ -45,8 +47,9 @@ define <2 x i32> @vld2lanei32(i32* %A, <2 x i32>* %B) nounwind {
 define <2 x float> @vld2lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vld2lanef:
 ;CHECK: vld2.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <2 x float>* %B
-	%tmp2 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_float32x2x2_t @llvm.arm.neon.vld2lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_float32x2x2_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_float32x2x2_t %tmp2, 1
         %tmp5 = add <2 x float> %tmp3, %tmp4
@@ -56,8 +59,9 @@ define <2 x float> @vld2lanef(float* %A, <2 x float>* %B) nounwind {
 define <8 x i16> @vld2laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vld2laneQi16:
 ;CHECK: vld2.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
-	%tmp2 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_int16x8x2_t @llvm.arm.neon.vld2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_int16x8x2_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int16x8x2_t %tmp2, 1
         %tmp5 = add <8 x i16> %tmp3, %tmp4
@@ -67,8 +71,9 @@ define <8 x i16> @vld2laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vld2laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vld2laneQi32:
 ;CHECK: vld2.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
-	%tmp2 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2lane.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2)
+	%tmp2 = call %struct.__neon_int32x4x2_t @llvm.arm.neon.vld2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2)
         %tmp3 = extractvalue %struct.__neon_int32x4x2_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int32x4x2_t %tmp2, 1
         %tmp5 = add <4 x i32> %tmp3, %tmp4
@@ -78,8 +83,9 @@ define <4 x i32> @vld2laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 define <4 x float> @vld2laneQf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vld2laneQf:
 ;CHECK: vld2.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <4 x float>* %B
-	%tmp2 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2lane.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_float32x4x2_t @llvm.arm.neon.vld2lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_float32x4x2_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_float32x4x2_t %tmp2, 1
         %tmp5 = add <4 x float> %tmp3, %tmp4
@@ -120,8 +126,9 @@ define <8 x i8> @vld3lanei8(i8* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vld3lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vld3lanei16:
 ;CHECK: vld3.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
-	%tmp2 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_int16x4x3_t @llvm.arm.neon.vld3lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_int16x4x3_t %tmp2, 2
@@ -133,8 +140,9 @@ define <4 x i16> @vld3lanei16(i16* %A, <4 x i16>* %B) nounwind {
 define <2 x i32> @vld3lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vld3lanei32:
 ;CHECK: vld3.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
-	%tmp2 = call %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_int32x2x3_t @llvm.arm.neon.vld3lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_int32x2x3_t %tmp2, 2
@@ -146,8 +154,9 @@ define <2 x i32> @vld3lanei32(i32* %A, <2 x i32>* %B) nounwind {
 define <2 x float> @vld3lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vld3lanef:
 ;CHECK: vld3.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <2 x float>* %B
-	%tmp2 = call %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_float32x2x3_t @llvm.arm.neon.vld3lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_float32x2x3_t %tmp2, 2
@@ -159,8 +168,9 @@ define <2 x float> @vld3lanef(float* %A, <2 x float>* %B) nounwind {
 define <8 x i16> @vld3laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vld3laneQi16:
 ;CHECK: vld3.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
-	%tmp2 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_int16x8x3_t @llvm.arm.neon.vld3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_int16x8x3_t %tmp2, 2
@@ -172,8 +182,9 @@ define <8 x i16> @vld3laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vld3laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vld3laneQi32:
 ;CHECK: vld3.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
-	%tmp2 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3lane.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 3)
+	%tmp2 = call %struct.__neon_int32x4x3_t @llvm.arm.neon.vld3lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 3)
         %tmp3 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_int32x4x3_t %tmp2, 2
@@ -185,8 +196,9 @@ define <4 x i32> @vld3laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 define <4 x float> @vld3laneQf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vld3laneQf:
 ;CHECK: vld3.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <4 x float>* %B
-	%tmp2 = call %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3lane.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_float32x4x3_t @llvm.arm.neon.vld3lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_float32x4x3_t %tmp2, 2
@@ -231,8 +243,9 @@ define <8 x i8> @vld4lanei8(i8* %A, <8 x i8>* %B) nounwind {
 define <4 x i16> @vld4lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vld4lanei16:
 ;CHECK: vld4.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
-	%tmp2 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_int16x4x4_t @llvm.arm.neon.vld4lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_int16x4x4_t %tmp2, 2
@@ -246,8 +259,9 @@ define <4 x i16> @vld4lanei16(i16* %A, <4 x i16>* %B) nounwind {
 define <2 x i32> @vld4lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vld4lanei32:
 ;CHECK: vld4.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
-	%tmp2 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_int32x2x4_t @llvm.arm.neon.vld4lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_int32x2x4_t %tmp2, 2
@@ -261,8 +275,9 @@ define <2 x i32> @vld4lanei32(i32* %A, <2 x i32>* %B) nounwind {
 define <2 x float> @vld4lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vld4lanef:
 ;CHECK: vld4.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <2 x float>* %B
-	%tmp2 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_float32x2x4_t @llvm.arm.neon.vld4lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_float32x2x4_t %tmp2, 2
@@ -276,8 +291,9 @@ define <2 x float> @vld4lanef(float* %A, <2 x float>* %B) nounwind {
 define <8 x i16> @vld4laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vld4laneQi16:
 ;CHECK: vld4.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
-	%tmp2 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4lane.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_int16x8x4_t @llvm.arm.neon.vld4lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_int16x8x4_t %tmp2, 2
@@ -291,8 +307,9 @@ define <8 x i16> @vld4laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 define <4 x i32> @vld4laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vld4laneQi32:
 ;CHECK: vld4.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
-	%tmp2 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4lane.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_int32x4x4_t @llvm.arm.neon.vld4lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_int32x4x4_t %tmp2, 2
@@ -306,8 +323,9 @@ define <4 x i32> @vld4laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 define <4 x float> @vld4laneQf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vld4laneQf:
 ;CHECK: vld4.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <4 x float>* %B
-	%tmp2 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4lane.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
+	%tmp2 = call %struct.__neon_float32x4x4_t @llvm.arm.neon.vld4lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
         %tmp3 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 0
         %tmp4 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 1
         %tmp5 = extractvalue %struct.__neon_float32x4x4_t %tmp2, 2
diff --git a/test/CodeGen/ARM/vst1.ll b/test/CodeGen/ARM/vst1.ll
index 602b124ffa..95414c3089 100644
--- a/test/CodeGen/ARM/vst1.ll
+++ b/test/CodeGen/ARM/vst1.ll
@@ -11,32 +11,36 @@ define void @vst1i8(i8* %A, <8 x i8>* %B) nounwind {
 define void @vst1i16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst1i16:
 ;CHECK: vst1.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
-	call void @llvm.arm.neon.vst1.v4i16(i16* %A, <4 x i16> %tmp1)
+	call void @llvm.arm.neon.vst1.v4i16(i8* %tmp0, <4 x i16> %tmp1)
 	ret void
 }
 
 define void @vst1i32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst1i32:
 ;CHECK: vst1.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
-	call void @llvm.arm.neon.vst1.v2i32(i32* %A, <2 x i32> %tmp1)
+	call void @llvm.arm.neon.vst1.v2i32(i8* %tmp0, <2 x i32> %tmp1)
 	ret void
 }
 
 define void @vst1f(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst1f:
 ;CHECK: vst1.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <2 x float>* %B
-	call void @llvm.arm.neon.vst1.v2f32(float* %A, <2 x float> %tmp1)
+	call void @llvm.arm.neon.vst1.v2f32(i8* %tmp0, <2 x float> %tmp1)
 	ret void
 }
 
 define void @vst1i64(i64* %A, <1 x i64>* %B) nounwind {
 ;CHECK: vst1i64:
 ;CHECK: vst1.64
+	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = load <1 x i64>* %B
-	call void @llvm.arm.neon.vst1.v1i64(i64* %A, <1 x i64> %tmp1)
+	call void @llvm.arm.neon.vst1.v1i64(i8* %tmp0, <1 x i64> %tmp1)
 	ret void
 }
 
@@ -51,32 +55,36 @@ define void @vst1Qi8(i8* %A, <16 x i8>* %B) nounwind {
 define void @vst1Qi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst1Qi16:
 ;CHECK: vst1.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
-	call void @llvm.arm.neon.vst1.v8i16(i16* %A, <8 x i16> %tmp1)
+	call void @llvm.arm.neon.vst1.v8i16(i8* %tmp0, <8 x i16> %tmp1)
 	ret void
 }
 
 define void @vst1Qi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst1Qi32:
 ;CHECK: vst1.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
-	call void @llvm.arm.neon.vst1.v4i32(i32* %A, <4 x i32> %tmp1)
+	call void @llvm.arm.neon.vst1.v4i32(i8* %tmp0, <4 x i32> %tmp1)
 	ret void
 }
 
 define void @vst1Qf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vst1Qf:
 ;CHECK: vst1.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <4 x float>* %B
-	call void @llvm.arm.neon.vst1.v4f32(float* %A, <4 x float> %tmp1)
+	call void @llvm.arm.neon.vst1.v4f32(i8* %tmp0, <4 x float> %tmp1)
 	ret void
 }
 
 define void @vst1Qi64(i64* %A, <2 x i64>* %B) nounwind {
 ;CHECK: vst1Qi64:
 ;CHECK: vst1.64
+	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = load <2 x i64>* %B
-	call void @llvm.arm.neon.vst1.v2i64(i64* %A, <2 x i64> %tmp1)
+	call void @llvm.arm.neon.vst1.v2i64(i8* %tmp0, <2 x i64> %tmp1)
 	ret void
 }
 
diff --git a/test/CodeGen/ARM/vst2.ll b/test/CodeGen/ARM/vst2.ll
index 17d6bee0f5..3c98a2cbe6 100644
--- a/test/CodeGen/ARM/vst2.ll
+++ b/test/CodeGen/ARM/vst2.ll
@@ -11,32 +11,36 @@ define void @vst2i8(i8* %A, <8 x i8>* %B) nounwind {
 define void @vst2i16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst2i16:
 ;CHECK: vst2.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
-	call void @llvm.arm.neon.vst2.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1)
+	call void @llvm.arm.neon.vst2.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1)
 	ret void
 }
 
 define void @vst2i32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst2i32:
 ;CHECK: vst2.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
-	call void @llvm.arm.neon.vst2.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1)
+	call void @llvm.arm.neon.vst2.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1)
 	ret void
 }
 
 define void @vst2f(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst2f:
 ;CHECK: vst2.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <2 x float>* %B
-	call void @llvm.arm.neon.vst2.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1)
+	call void @llvm.arm.neon.vst2.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1)
 	ret void
 }
 
 define void @vst2i64(i64* %A, <1 x i64>* %B) nounwind {
 ;CHECK: vst2i64:
 ;CHECK: vst1.64
+	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = load <1 x i64>* %B
-	call void @llvm.arm.neon.vst2.v1i64(i64* %A, <1 x i64> %tmp1, <1 x i64> %tmp1)
+	call void @llvm.arm.neon.vst2.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1)
 	ret void
 }
 
@@ -51,24 +55,27 @@ define void @vst2Qi8(i8* %A, <16 x i8>* %B) nounwind {
 define void @vst2Qi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst2Qi16:
 ;CHECK: vst2.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
-	call void @llvm.arm.neon.vst2.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1)
+	call void @llvm.arm.neon.vst2.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1)
 	ret void
 }
 
 define void @vst2Qi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst2Qi32:
 ;CHECK: vst2.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
-	call void @llvm.arm.neon.vst2.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1)
+	call void @llvm.arm.neon.vst2.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1)
 	ret void
 }
 
 define void @vst2Qf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vst2Qf:
 ;CHECK: vst2.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <4 x float>* %B
-	call void @llvm.arm.neon.vst2.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1)
+	call void @llvm.arm.neon.vst2.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1)
 	ret void
 }
 
diff --git a/test/CodeGen/ARM/vst3.ll b/test/CodeGen/ARM/vst3.ll
index a831a0c08c..2599bc0db9 100644
--- a/test/CodeGen/ARM/vst3.ll
+++ b/test/CodeGen/ARM/vst3.ll
@@ -11,32 +11,36 @@ define void @vst3i8(i8* %A, <8 x i8>* %B) nounwind {
 define void @vst3i16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst3i16:
 ;CHECK: vst3.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
-	call void @llvm.arm.neon.vst3.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
+	call void @llvm.arm.neon.vst3.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
 	ret void
 }
 
 define void @vst3i32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst3i32:
 ;CHECK: vst3.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
-	call void @llvm.arm.neon.vst3.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
+	call void @llvm.arm.neon.vst3.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
 	ret void
 }
 
 define void @vst3f(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst3f:
 ;CHECK: vst3.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <2 x float>* %B
-	call void @llvm.arm.neon.vst3.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
+	call void @llvm.arm.neon.vst3.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
 	ret void
 }
 
 define void @vst3i64(i64* %A, <1 x i64>* %B) nounwind {
 ;CHECK: vst3i64:
 ;CHECK: vst1.64
+	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = load <1 x i64>* %B
-	call void @llvm.arm.neon.vst3.v1i64(i64* %A, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1)
+	call void @llvm.arm.neon.vst3.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1)
 	ret void
 }
 
@@ -53,8 +57,9 @@ define void @vst3Qi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst3Qi16:
 ;CHECK: vst3.16
 ;CHECK: vst3.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
-	call void @llvm.arm.neon.vst3.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1)
+	call void @llvm.arm.neon.vst3.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1)
 	ret void
 }
 
@@ -62,8 +67,9 @@ define void @vst3Qi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst3Qi32:
 ;CHECK: vst3.32
 ;CHECK: vst3.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
-	call void @llvm.arm.neon.vst3.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1)
+	call void @llvm.arm.neon.vst3.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1)
 	ret void
 }
 
@@ -71,8 +77,9 @@ define void @vst3Qf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vst3Qf:
 ;CHECK: vst3.32
 ;CHECK: vst3.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <4 x float>* %B
-	call void @llvm.arm.neon.vst3.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1)
+	call void @llvm.arm.neon.vst3.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1)
 	ret void
 }
 
diff --git a/test/CodeGen/ARM/vst4.ll b/test/CodeGen/ARM/vst4.ll
index d92c017c30..878f0efaa4 100644
--- a/test/CodeGen/ARM/vst4.ll
+++ b/test/CodeGen/ARM/vst4.ll
@@ -11,32 +11,36 @@ define void @vst4i8(i8* %A, <8 x i8>* %B) nounwind {
 define void @vst4i16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst4i16:
 ;CHECK: vst4.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
-	call void @llvm.arm.neon.vst4.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
+	call void @llvm.arm.neon.vst4.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1)
 	ret void
 }
 
 define void @vst4i32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst4i32:
 ;CHECK: vst4.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
-	call void @llvm.arm.neon.vst4.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
+	call void @llvm.arm.neon.vst4.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1)
 	ret void
 }
 
 define void @vst4f(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst4f:
 ;CHECK: vst4.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <2 x float>* %B
-	call void @llvm.arm.neon.vst4.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
+	call void @llvm.arm.neon.vst4.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1)
 	ret void
 }
 
 define void @vst4i64(i64* %A, <1 x i64>* %B) nounwind {
 ;CHECK: vst4i64:
 ;CHECK: vst1.64
+	%tmp0 = bitcast i64* %A to i8*
 	%tmp1 = load <1 x i64>* %B
-	call void @llvm.arm.neon.vst4.v1i64(i64* %A, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1)
+	call void @llvm.arm.neon.vst4.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1)
 	ret void
 }
 
@@ -53,8 +57,9 @@ define void @vst4Qi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst4Qi16:
 ;CHECK: vst4.16
 ;CHECK: vst4.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
-	call void @llvm.arm.neon.vst4.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1)
+	call void @llvm.arm.neon.vst4.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1)
 	ret void
 }
 
@@ -62,8 +67,9 @@ define void @vst4Qi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst4Qi32:
 ;CHECK: vst4.32
 ;CHECK: vst4.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
-	call void @llvm.arm.neon.vst4.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1)
+	call void @llvm.arm.neon.vst4.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1)
 	ret void
 }
 
@@ -71,8 +77,9 @@ define void @vst4Qf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vst4Qf:
 ;CHECK: vst4.32
 ;CHECK: vst4.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <4 x float>* %B
-	call void @llvm.arm.neon.vst4.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1)
+	call void @llvm.arm.neon.vst4.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1)
 	ret void
 }
 
diff --git a/test/CodeGen/ARM/vstlane.ll b/test/CodeGen/ARM/vstlane.ll
index 3bfb14f17b..cf50756d46 100644
--- a/test/CodeGen/ARM/vstlane.ll
+++ b/test/CodeGen/ARM/vstlane.ll
@@ -11,48 +11,54 @@ define void @vst2lanei8(i8* %A, <8 x i8>* %B) nounwind {
 define void @vst2lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst2lanei16:
 ;CHECK: vst2.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
-	call void @llvm.arm.neon.vst2lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst2lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
 	ret void
 }
 
 define void @vst2lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst2lanei32:
 ;CHECK: vst2.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
-	call void @llvm.arm.neon.vst2lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst2lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
 	ret void
 }
 
 define void @vst2lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst2lanef:
 ;CHECK: vst2.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <2 x float>* %B
-	call void @llvm.arm.neon.vst2lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst2lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
 	ret void
 }
 
 define void @vst2laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst2laneQi16:
 ;CHECK: vst2.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
-	call void @llvm.arm.neon.vst2lane.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst2lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
 	ret void
 }
 
 define void @vst2laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst2laneQi32:
 ;CHECK: vst2.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
-	call void @llvm.arm.neon.vst2lane.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2)
+	call void @llvm.arm.neon.vst2lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2)
 	ret void
 }
 
 define void @vst2laneQf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vst2laneQf:
 ;CHECK: vst2.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <4 x float>* %B
-	call void @llvm.arm.neon.vst2lane.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, i32 3)
+	call void @llvm.arm.neon.vst2lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, i32 3)
 	ret void
 }
 
@@ -76,48 +82,54 @@ define void @vst3lanei8(i8* %A, <8 x i8>* %B) nounwind {
 define void @vst3lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst3lanei16:
 ;CHECK: vst3.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
-	call void @llvm.arm.neon.vst3lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst3lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
 	ret void
 }
 
 define void @vst3lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst3lanei32:
 ;CHECK: vst3.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
-	call void @llvm.arm.neon.vst3lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst3lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
 	ret void
 }
 
 define void @vst3lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst3lanef:
 ;CHECK: vst3.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <2 x float>* %B
-	call void @llvm.arm.neon.vst3lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst3lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
 	ret void
 }
 
 define void @vst3laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst3laneQi16:
 ;CHECK: vst3.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
-	call void @llvm.arm.neon.vst3lane.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 6)
+	call void @llvm.arm.neon.vst3lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 6)
 	ret void
 }
 
 define void @vst3laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst3laneQi32:
 ;CHECK: vst3.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
-	call void @llvm.arm.neon.vst3lane.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 0)
+	call void @llvm.arm.neon.vst3lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 0)
 	ret void
 }
 
 define void @vst3laneQf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vst3laneQf:
 ;CHECK: vst3.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <4 x float>* %B
-	call void @llvm.arm.neon.vst3lane.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst3lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
 	ret void
 }
 
@@ -142,48 +154,54 @@ define void @vst4lanei8(i8* %A, <8 x i8>* %B) nounwind {
 define void @vst4lanei16(i16* %A, <4 x i16>* %B) nounwind {
 ;CHECK: vst4lanei16:
 ;CHECK: vst4.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <4 x i16>* %B
-	call void @llvm.arm.neon.vst4lane.v4i16(i16* %A, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst4lane.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
 	ret void
 }
 
 define void @vst4lanei32(i32* %A, <2 x i32>* %B) nounwind {
 ;CHECK: vst4lanei32:
 ;CHECK: vst4.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <2 x i32>* %B
-	call void @llvm.arm.neon.vst4lane.v2i32(i32* %A, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst4lane.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
 	ret void
 }
 
 define void @vst4lanef(float* %A, <2 x float>* %B) nounwind {
 ;CHECK: vst4lanef:
 ;CHECK: vst4.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <2 x float>* %B
-	call void @llvm.arm.neon.vst4lane.v2f32(float* %A, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst4lane.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
 	ret void
 }
 
 define void @vst4laneQi16(i16* %A, <8 x i16>* %B) nounwind {
 ;CHECK: vst4laneQi16:
 ;CHECK: vst4.16
+	%tmp0 = bitcast i16* %A to i8*
 	%tmp1 = load <8 x i16>* %B
-	call void @llvm.arm.neon.vst4lane.v8i16(i16* %A, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 7)
+	call void @llvm.arm.neon.vst4lane.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 7)
 	ret void
 }
 
 define void @vst4laneQi32(i32* %A, <4 x i32>* %B) nounwind {
 ;CHECK: vst4laneQi32:
 ;CHECK: vst4.32
+	%tmp0 = bitcast i32* %A to i8*
 	%tmp1 = load <4 x i32>* %B
-	call void @llvm.arm.neon.vst4lane.v4i32(i32* %A, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2)
+	call void @llvm.arm.neon.vst4lane.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 2)
 	ret void
 }
 
 define void @vst4laneQf(float* %A, <4 x float>* %B) nounwind {
 ;CHECK: vst4laneQf:
 ;CHECK: vst4.32
+	%tmp0 = bitcast float* %A to i8*
 	%tmp1 = load <4 x float>* %B
-	call void @llvm.arm.neon.vst4lane.v4f32(float* %A, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
+	call void @llvm.arm.neon.vst4lane.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
 	ret void
 }