diff options
Diffstat (limited to 'llvm/test/CodeGen/ARM/vst4.ll')
| -rw-r--r-- | llvm/test/CodeGen/ARM/vst4.ll | 42 |
1 files changed, 21 insertions, 21 deletions
diff --git a/llvm/test/CodeGen/ARM/vst4.ll b/llvm/test/CodeGen/ARM/vst4.ll index c343c6c8695..18895510229 100644 --- a/llvm/test/CodeGen/ARM/vst4.ll +++ b/llvm/test/CodeGen/ARM/vst4.ll @@ -5,7 +5,7 @@ define void @vst4i8(i8* %A, <8 x i8>* %B) nounwind { ;Check the alignment value. Max for this instruction is 256 bits: ;CHECK: vst4.8 {d16, d17, d18, d19}, [r0:64] %tmp1 = load <8 x i8>, <8 x i8>* %B - call void @llvm.arm.neon.vst4.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 8) + call void @llvm.arm.neon.vst4.p0i8.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 8) ret void } @@ -15,7 +15,7 @@ define void @vst4i8_update(i8** %ptr, <8 x i8>* %B, i32 %inc) nounwind { ;CHECK: vst4.8 {d16, d17, d18, d19}, [r1:128], r2 %A = load i8*, i8** %ptr %tmp1 = load <8 x i8>, <8 x i8>* %B - call void @llvm.arm.neon.vst4.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 16) + call void @llvm.arm.neon.vst4.p0i8.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 16) %tmp2 = getelementptr i8, i8* %A, i32 %inc store i8* %tmp2, i8** %ptr ret void @@ -27,7 +27,7 @@ define void @vst4i16(i16* %A, <4 x i16>* %B) nounwind { ;CHECK: vst4.16 {d16, d17, d18, d19}, [r0:128] %tmp0 = bitcast i16* %A to i8* %tmp1 = load <4 x i16>, <4 x i16>* %B - 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, i32 16) + call void @llvm.arm.neon.vst4.p0i8.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 16) ret void } @@ -37,7 +37,7 @@ define void @vst4i32(i32* %A, <2 x i32>* %B) nounwind { ;CHECK: vst4.32 {d16, d17, d18, d19}, [r0:256] %tmp0 = bitcast i32* %A to i8* %tmp1 = load <2 x i32>, <2 x i32>* %B - 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, i32 32) + call void @llvm.arm.neon.vst4.p0i8.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 32) ret void } @@ -46,7 +46,7 @@ define void @vst4f(float* %A, <2 x float>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <2 x float>, <2 x float>* %B - 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, i32 1) + call void @llvm.arm.neon.vst4.p0i8.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1) ret void } @@ -56,7 +56,7 @@ define void @vst4i64(i64* %A, <1 x i64>* %B) nounwind { ;CHECK: vst1.64 {d16, d17, d18, d19}, [r0:256] %tmp0 = bitcast i64* %A to i8* %tmp1 = load <1 x i64>, <1 x i64>* %B - 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, i32 64) + call void @llvm.arm.neon.vst4.p0i8.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 64) ret void } @@ -66,7 +66,7 @@ define void @vst4i64_update(i64** %ptr, <1 x i64>* %B) nounwind { %A = load i64*, i64** %ptr %tmp0 = bitcast i64* %A to i8* %tmp1 = load <1 x i64>, <1 x i64>* %B - 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, i32 1) + call void @llvm.arm.neon.vst4.p0i8.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 1) %tmp2 = getelementptr i64, i64* %A, i32 4 store i64* %tmp2, i64** %ptr ret void @@ -78,7 +78,7 @@ define void @vst4Qi8(i8* %A, <16 x i8>* %B) nounwind { ;CHECK: vst4.8 {d16, d18, d20, d22}, [r0:256]! ;CHECK: vst4.8 {d17, d19, d21, d23}, [r0:256] %tmp1 = load <16 x i8>, <16 x i8>* %B - call void @llvm.arm.neon.vst4.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 64) + call void @llvm.arm.neon.vst4.p0i8.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 64) ret void } @@ -89,7 +89,7 @@ define void @vst4Qi16(i16* %A, <8 x i16>* %B) nounwind { ;CHECK: vst4.16 {d17, d19, d21, d23}, [r0] %tmp0 = bitcast i16* %A to i8* %tmp1 = load <8 x i16>, <8 x i16>* %B - 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, i32 1) + call void @llvm.arm.neon.vst4.p0i8.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1) ret void } @@ -99,7 +99,7 @@ define void @vst4Qi32(i32* %A, <4 x i32>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast i32* %A to i8* %tmp1 = load <4 x i32>, <4 x i32>* %B - 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, i32 1) + call void @llvm.arm.neon.vst4.p0i8.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1) ret void } @@ -109,7 +109,7 @@ define void @vst4Qf(float* %A, <4 x float>* %B) nounwind { ;CHECK: vst4.32 %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>, <4 x float>* %B - 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, i32 1) + call void @llvm.arm.neon.vst4.p0i8.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) ret void } @@ -121,19 +121,19 @@ define void @vst4Qf_update(float** %ptr, <4 x float>* %B) nounwind { %A = load float*, float** %ptr %tmp0 = bitcast float* %A to i8* %tmp1 = load <4 x float>, <4 x float>* %B - 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, i32 1) + call void @llvm.arm.neon.vst4.p0i8.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1) %tmp2 = getelementptr float, float* %A, i32 16 store float* %tmp2, float** %ptr ret void } -declare void @llvm.arm.neon.vst4.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind -declare void @llvm.arm.neon.vst4.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind -declare void @llvm.arm.neon.vst4.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind -declare void @llvm.arm.neon.vst4.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32) nounwind -declare void @llvm.arm.neon.vst4.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64>, i32) nounwind +declare void @llvm.arm.neon.vst4.p0i8.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind +declare void @llvm.arm.neon.vst4.p0i8.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind +declare void @llvm.arm.neon.vst4.p0i8.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind +declare void @llvm.arm.neon.vst4.p0i8.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32) nounwind +declare void @llvm.arm.neon.vst4.p0i8.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64>, i32) nounwind -declare void @llvm.arm.neon.vst4.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, i32) nounwind -declare void @llvm.arm.neon.vst4.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind -declare void @llvm.arm.neon.vst4.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind -declare void @llvm.arm.neon.vst4.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32) nounwind +declare void @llvm.arm.neon.vst4.p0i8.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, i32) nounwind +declare void @llvm.arm.neon.vst4.p0i8.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind +declare void @llvm.arm.neon.vst4.p0i8.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind +declare void @llvm.arm.neon.vst4.p0i8.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32) nounwind |
