1 ; RUN: llc < %s -march=arm -mattr=+neon -O0 | FileCheck %s
3 define void @vst3i8(i8* %A, <8 x i8>* %B) nounwind {
5 ;Check the alignment value. Max for this instruction is 64 bits:
6 ;This test runs at -O0 so do not check for specific register numbers.
7 ;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}, :64]
8 %tmp1 = load <8 x i8>* %B
9 call void @llvm.arm.neon.vst3.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 32)
13 define void @vst3i16(i16* %A, <4 x i16>* %B) nounwind {
16 %tmp0 = bitcast i16* %A to i8*
17 %tmp1 = load <4 x i16>* %B
18 call void @llvm.arm.neon.vst3.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
22 define void @vst3i32(i32* %A, <2 x i32>* %B) nounwind {
25 %tmp0 = bitcast i32* %A to i8*
26 %tmp1 = load <2 x i32>* %B
27 call void @llvm.arm.neon.vst3.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
31 define void @vst3f(float* %A, <2 x float>* %B) nounwind {
34 %tmp0 = bitcast float* %A to i8*
35 %tmp1 = load <2 x float>* %B
36 call void @llvm.arm.neon.vst3.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
40 define void @vst3i64(i64* %A, <1 x i64>* %B) nounwind {
42 ;Check the alignment value. Max for this instruction is 64 bits:
43 ;This test runs at -O0 so do not check for specific register numbers.
44 ;CHECK: vst1.64 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}, :64]
45 %tmp0 = bitcast i64* %A to i8*
46 %tmp1 = load <1 x i64>* %B
47 call void @llvm.arm.neon.vst3.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 16)
51 define void @vst3Qi8(i8* %A, <16 x i8>* %B) nounwind {
53 ;Check the alignment value. Max for this instruction is 64 bits:
54 ;This test runs at -O0 so do not check for specific register numbers.
55 ;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}, :64]!
56 ;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}, :64]
57 %tmp1 = load <16 x i8>* %B
58 call void @llvm.arm.neon.vst3.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 32)
62 define void @vst3Qi16(i16* %A, <8 x i16>* %B) nounwind {
66 %tmp0 = bitcast i16* %A to i8*
67 %tmp1 = load <8 x i16>* %B
68 call void @llvm.arm.neon.vst3.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
72 define void @vst3Qi32(i32* %A, <4 x i32>* %B) nounwind {
76 %tmp0 = bitcast i32* %A to i8*
77 %tmp1 = load <4 x i32>* %B
78 call void @llvm.arm.neon.vst3.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1)
82 define void @vst3Qf(float* %A, <4 x float>* %B) nounwind {
86 %tmp0 = bitcast float* %A to i8*
87 %tmp1 = load <4 x float>* %B
88 call void @llvm.arm.neon.vst3.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
92 declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind
93 declare void @llvm.arm.neon.vst3.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind
94 declare void @llvm.arm.neon.vst3.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind
95 declare void @llvm.arm.neon.vst3.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32) nounwind
96 declare void @llvm.arm.neon.vst3.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>, i32) nounwind
98 declare void @llvm.arm.neon.vst3.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>, i32) nounwind
99 declare void @llvm.arm.neon.vst3.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind
100 declare void @llvm.arm.neon.vst3.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind
101 declare void @llvm.arm.neon.vst3.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32) nounwind