diff options
Diffstat (limited to 'test/CodeGen/ARM/vld4.ll')
| -rw-r--r-- | test/CodeGen/ARM/vld4.ll | 21 |
1 files changed, 14 insertions, 7 deletions
diff --git a/test/CodeGen/ARM/vld4.ll b/test/CodeGen/ARM/vld4.ll index 0624f29..e800cb5 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 |