1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
|
; RUN: llc < %s -march=arm -mattr=+neon -fast-isel=0 -O0 | FileCheck %s
define void @vst3i8(i8* %A, <8 x i8>* %B) nounwind {
;CHECK-LABEL: vst3i8:
;Check the alignment value. Max for this instruction is 64 bits:
;This test runs at -O0 so do not check for specific register numbers.
;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}:64]
%tmp1 = load <8 x i8>* %B
call void @llvm.arm.neon.vst3.v8i8(i8* %A, <8 x i8> %tmp1, <8 x i8> %tmp1, <8 x i8> %tmp1, i32 32)
ret void
}
define void @vst3i16(i16* %A, <4 x i16>* %B) nounwind {
;CHECK-LABEL: vst3i16:
;CHECK: vst3.16
%tmp0 = bitcast i16* %A to i8*
%tmp1 = load <4 x i16>* %B
call void @llvm.arm.neon.vst3.v4i16(i8* %tmp0, <4 x i16> %tmp1, <4 x i16> %tmp1, <4 x i16> %tmp1, i32 1)
ret void
}
define void @vst3i32(i32* %A, <2 x i32>* %B) nounwind {
;CHECK-LABEL: vst3i32:
;CHECK: vst3.32
%tmp0 = bitcast i32* %A to i8*
%tmp1 = load <2 x i32>* %B
call void @llvm.arm.neon.vst3.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
ret void
}
;Check for a post-increment updating store.
define void @vst3i32_update(i32** %ptr, <2 x i32>* %B) nounwind {
;CHECK-LABEL: vst3i32_update:
;CHECK: vst3.32 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}]!
%A = load i32** %ptr
%tmp0 = bitcast i32* %A to i8*
%tmp1 = load <2 x i32>* %B
call void @llvm.arm.neon.vst3.v2i32(i8* %tmp0, <2 x i32> %tmp1, <2 x i32> %tmp1, <2 x i32> %tmp1, i32 1)
%tmp2 = getelementptr i32* %A, i32 6
store i32* %tmp2, i32** %ptr
ret void
}
define void @vst3f(float* %A, <2 x float>* %B) nounwind {
;CHECK-LABEL: vst3f:
;CHECK: vst3.32
%tmp0 = bitcast float* %A to i8*
%tmp1 = load <2 x float>* %B
call void @llvm.arm.neon.vst3.v2f32(i8* %tmp0, <2 x float> %tmp1, <2 x float> %tmp1, <2 x float> %tmp1, i32 1)
ret void
}
define void @vst3i64(i64* %A, <1 x i64>* %B) nounwind {
;CHECK-LABEL: vst3i64:
;Check the alignment value. Max for this instruction is 64 bits:
;This test runs at -O0 so do not check for specific register numbers.
;CHECK: vst1.64 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}:64]
%tmp0 = bitcast i64* %A to i8*
%tmp1 = load <1 x i64>* %B
call void @llvm.arm.neon.vst3.v1i64(i8* %tmp0, <1 x i64> %tmp1, <1 x i64> %tmp1, <1 x i64> %tmp1, i32 16)
ret void
}
define void @vst3Qi8(i8* %A, <16 x i8>* %B) nounwind {
;CHECK-LABEL: vst3Qi8:
;Check the alignment value. Max for this instruction is 64 bits:
;This test runs at -O0 so do not check for specific register numbers.
;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}:64]!
;CHECK: vst3.8 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}:64]
%tmp1 = load <16 x i8>* %B
call void @llvm.arm.neon.vst3.v16i8(i8* %A, <16 x i8> %tmp1, <16 x i8> %tmp1, <16 x i8> %tmp1, i32 32)
ret void
}
define void @vst3Qi16(i16* %A, <8 x i16>* %B) nounwind {
;CHECK-LABEL: vst3Qi16:
;CHECK: vst3.16
;CHECK: vst3.16
%tmp0 = bitcast i16* %A to i8*
%tmp1 = load <8 x i16>* %B
call void @llvm.arm.neon.vst3.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
ret void
}
;Check for a post-increment updating store.
define void @vst3Qi16_update(i16** %ptr, <8 x i16>* %B) nounwind {
;CHECK-LABEL: vst3Qi16_update:
;CHECK: vst3.16 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}]!
;CHECK: vst3.16 {d{{.*}}, d{{.*}}, d{{.*}}}, [r{{.*}}]!
%A = load i16** %ptr
%tmp0 = bitcast i16* %A to i8*
%tmp1 = load <8 x i16>* %B
call void @llvm.arm.neon.vst3.v8i16(i8* %tmp0, <8 x i16> %tmp1, <8 x i16> %tmp1, <8 x i16> %tmp1, i32 1)
%tmp2 = getelementptr i16* %A, i32 24
store i16* %tmp2, i16** %ptr
ret void
}
define void @vst3Qi32(i32* %A, <4 x i32>* %B) nounwind {
;CHECK-LABEL: vst3Qi32:
;CHECK: vst3.32
;CHECK: vst3.32
%tmp0 = bitcast i32* %A to i8*
%tmp1 = load <4 x i32>* %B
call void @llvm.arm.neon.vst3.v4i32(i8* %tmp0, <4 x i32> %tmp1, <4 x i32> %tmp1, <4 x i32> %tmp1, i32 1)
ret void
}
define void @vst3Qf(float* %A, <4 x float>* %B) nounwind {
;CHECK-LABEL: vst3Qf:
;CHECK: vst3.32
;CHECK: vst3.32
%tmp0 = bitcast float* %A to i8*
%tmp1 = load <4 x float>* %B
call void @llvm.arm.neon.vst3.v4f32(i8* %tmp0, <4 x float> %tmp1, <4 x float> %tmp1, <4 x float> %tmp1, i32 1)
ret void
}
declare void @llvm.arm.neon.vst3.v8i8(i8*, <8 x i8>, <8 x i8>, <8 x i8>, i32) nounwind
declare void @llvm.arm.neon.vst3.v4i16(i8*, <4 x i16>, <4 x i16>, <4 x i16>, i32) nounwind
declare void @llvm.arm.neon.vst3.v2i32(i8*, <2 x i32>, <2 x i32>, <2 x i32>, i32) nounwind
declare void @llvm.arm.neon.vst3.v2f32(i8*, <2 x float>, <2 x float>, <2 x float>, i32) nounwind
declare void @llvm.arm.neon.vst3.v1i64(i8*, <1 x i64>, <1 x i64>, <1 x i64>, i32) nounwind
declare void @llvm.arm.neon.vst3.v16i8(i8*, <16 x i8>, <16 x i8>, <16 x i8>, i32) nounwind
declare void @llvm.arm.neon.vst3.v8i16(i8*, <8 x i16>, <8 x i16>, <8 x i16>, i32) nounwind
declare void @llvm.arm.neon.vst3.v4i32(i8*, <4 x i32>, <4 x i32>, <4 x i32>, i32) nounwind
declare void @llvm.arm.neon.vst3.v4f32(i8*, <4 x float>, <4 x float>, <4 x float>, i32) nounwind
|
