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.

llvm-svn: 101840

1 files changed, 16 insertions, 8 deletions

diff --git a/llvm/test/CodeGen/ARM/vld1.ll b/llvm/test/CodeGen/ARM/vld1.ll
index f5383aafb2b..c61ea8c9a78 100644
--- a/llvm/test/CodeGen/ARM/vld1.ll
+++ b/llvm/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
 }