1 ; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
3 define void @vst4i8(i8* %A, <8 x i8>* %B) nounwind {
5 ;Check the alignment value. Max for this instruction is 256 bits:
6 ;CHECK: vst4.8 {d16, d17, d18, d19}, [r0, :64]
7 %tmp1 = load <8 x i8>* %B
8 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)
12 define void @vst4i16(i16* %A, <4 x i16>* %B) nounwind {
14 ;Check the alignment value. Max for this instruction is 256 bits:
15 ;CHECK: vst4.16 {d16, d17, d18, d19}, [r0, :128]
16 %tmp0 = bitcast i16* %A to i8*
17 %tmp1 = load <4 x i16>* %B
18 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)
22 define void @vst4i32(i32* %A, <2 x i32>* %B) nounwind {
24 ;Check the alignment value. Max for this instruction is 256 bits:
25 ;CHECK: vst4.32 {d16, d17, d18, d19}, [r0, :256]
26 %tmp0 = bitcast i32* %A to i8*
27 %tmp1 = load <2 x i32>* %B
28 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)
32 define void @vst4f(float* %A, <2 x float>* %B) nounwind {
35 %tmp0 = bitcast float* %A to i8*
36 %tmp1 = load <2 x float>* %B
37 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)
41 define void @vst4i64(i64* %A, <1 x i64>* %B) nounwind {
43 ;Check the alignment value. Max for this instruction is 256 bits:
44 ;CHECK: vst1.64 {d16, d17, d18, d19}, [r0, :256]
45 %tmp0 = bitcast i64* %A to i8*
46 %tmp1 = load <1 x i64>* %B
47 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)
51 define void @vst4Qi8(i8* %A, <16 x i8>* %B) nounwind {
53 ;Check the alignment value. Max for this instruction is 256 bits:
54 ;CHECK: vst4.8 {d16, d18, d20, d22}, [r0, :256]!
55 ;CHECK: vst4.8 {d17, d19, d21, d23}, [r0, :256]
56 %tmp1 = load <16 x i8>* %B
57 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)
61 define void @vst4Qi16(i16* %A, <8 x i16>* %B) nounwind {
63 ;Check for no alignment specifier.
64 ;CHECK: vst4.16 {d16, d18, d20, d22}, [r0]!
65 ;CHECK: vst4.16 {d17, d19, d21, d23}, [r0]
66 %tmp0 = bitcast i16* %A to i8*
67 %tmp1 = load <8 x i16>* %B
68 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)
72 define void @vst4Qi32(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.vst4.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1)
82 define void @vst4Qf(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.vst4.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
92 declare void @llvm.arm.neon.vst4.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind
93 declare void @llvm.arm.neon.vst4.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind
94 declare void @llvm.arm.neon.vst4.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind
95 declare void @llvm.arm.neon.vst4.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, <2 x float>, i32) nounwind
96 declare void @llvm.arm.neon.vst4.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>, <1 x i64>, i32) nounwind
98 declare void @llvm.arm.neon.vst4.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>, <16 x i8>, i32) nounwind
99 declare void @llvm.arm.neon.vst4.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind
100 declare void @llvm.arm.neon.vst4.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind
101 declare void @llvm.arm.neon.vst4.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, <4 x float>, i32) nounwind