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
129
130
131
132
133
134
135
136
137
|
; RUN: llc < %s -march=arm -mattr=+neon | FileCheck %s
define <8 x i8> @vabas8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
;CHECK: vabas8:
;CHECK: vaba.s8
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = load <8 x i8>* %C
%tmp4 = call <8 x i8> @llvm.arm.neon.vabas.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
ret <8 x i8> %tmp4
}
define <4 x i16> @vabas16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
;CHECK: vabas16:
;CHECK: vaba.s16
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = load <4 x i16>* %C
%tmp4 = call <4 x i16> @llvm.arm.neon.vabas.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
ret <4 x i16> %tmp4
}
define <2 x i32> @vabas32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
;CHECK: vabas32:
;CHECK: vaba.s32
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = load <2 x i32>* %C
%tmp4 = call <2 x i32> @llvm.arm.neon.vabas.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
ret <2 x i32> %tmp4
}
define <8 x i8> @vabau8(<8 x i8>* %A, <8 x i8>* %B, <8 x i8>* %C) nounwind {
;CHECK: vabau8:
;CHECK: vaba.u8
%tmp1 = load <8 x i8>* %A
%tmp2 = load <8 x i8>* %B
%tmp3 = load <8 x i8>* %C
%tmp4 = call <8 x i8> @llvm.arm.neon.vabau.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2, <8 x i8> %tmp3)
ret <8 x i8> %tmp4
}
define <4 x i16> @vabau16(<4 x i16>* %A, <4 x i16>* %B, <4 x i16>* %C) nounwind {
;CHECK: vabau16:
;CHECK: vaba.u16
%tmp1 = load <4 x i16>* %A
%tmp2 = load <4 x i16>* %B
%tmp3 = load <4 x i16>* %C
%tmp4 = call <4 x i16> @llvm.arm.neon.vabau.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2, <4 x i16> %tmp3)
ret <4 x i16> %tmp4
}
define <2 x i32> @vabau32(<2 x i32>* %A, <2 x i32>* %B, <2 x i32>* %C) nounwind {
;CHECK: vabau32:
;CHECK: vaba.u32
%tmp1 = load <2 x i32>* %A
%tmp2 = load <2 x i32>* %B
%tmp3 = load <2 x i32>* %C
%tmp4 = call <2 x i32> @llvm.arm.neon.vabau.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2, <2 x i32> %tmp3)
ret <2 x i32> %tmp4
}
define <16 x i8> @vabaQs8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8>* %C) nounwind {
;CHECK: vabaQs8:
;CHECK: vaba.s8
%tmp1 = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = load <16 x i8>* %C
%tmp4 = call <16 x i8> @llvm.arm.neon.vabas.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i8> %tmp3)
ret <16 x i8> %tmp4
}
define <8 x i16> @vabaQs16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind {
;CHECK: vabaQs16:
;CHECK: vaba.s16
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i16>* %B
%tmp3 = load <8 x i16>* %C
%tmp4 = call <8 x i16> @llvm.arm.neon.vabas.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i16> %tmp3)
ret <8 x i16> %tmp4
}
define <4 x i32> @vabaQs32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind {
;CHECK: vabaQs32:
;CHECK: vaba.s32
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i32>* %B
%tmp3 = load <4 x i32>* %C
%tmp4 = call <4 x i32> @llvm.arm.neon.vabas.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> %tmp3)
ret <4 x i32> %tmp4
}
define <16 x i8> @vabaQu8(<16 x i8>* %A, <16 x i8>* %B, <16 x i8>* %C) nounwind {
;CHECK: vabaQu8:
;CHECK: vaba.u8
%tmp1 = load <16 x i8>* %A
%tmp2 = load <16 x i8>* %B
%tmp3 = load <16 x i8>* %C
%tmp4 = call <16 x i8> @llvm.arm.neon.vabau.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2, <16 x i8> %tmp3)
ret <16 x i8> %tmp4
}
define <8 x i16> @vabaQu16(<8 x i16>* %A, <8 x i16>* %B, <8 x i16>* %C) nounwind {
;CHECK: vabaQu16:
;CHECK: vaba.u16
%tmp1 = load <8 x i16>* %A
%tmp2 = load <8 x i16>* %B
%tmp3 = load <8 x i16>* %C
%tmp4 = call <8 x i16> @llvm.arm.neon.vabau.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2, <8 x i16> %tmp3)
ret <8 x i16> %tmp4
}
define <4 x i32> @vabaQu32(<4 x i32>* %A, <4 x i32>* %B, <4 x i32>* %C) nounwind {
;CHECK: vabaQu32:
;CHECK: vaba.u32
%tmp1 = load <4 x i32>* %A
%tmp2 = load <4 x i32>* %B
%tmp3 = load <4 x i32>* %C
%tmp4 = call <4 x i32> @llvm.arm.neon.vabau.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2, <4 x i32> %tmp3)
ret <4 x i32> %tmp4
}
declare <8 x i8> @llvm.arm.neon.vabas.v8i8(<8 x i8>, <8 x i8>, <8 x i8>) nounwind readnone
declare <4 x i16> @llvm.arm.neon.vabas.v4i16(<4 x i16>, <4 x i16>, <4 x i16>) nounwind readnone
declare <2 x i32> @llvm.arm.neon.vabas.v2i32(<2 x i32>, <2 x i32>, <2 x i32>) nounwind readnone
declare <8 x i8> @llvm.arm.neon.vabau.v8i8(<8 x i8>, <8 x i8>, <8 x i8>) nounwind readnone
declare <4 x i16> @llvm.arm.neon.vabau.v4i16(<4 x i16>, <4 x i16>, <4 x i16>) nounwind readnone
declare <2 x i32> @llvm.arm.neon.vabau.v2i32(<2 x i32>, <2 x i32>, <2 x i32>) nounwind readnone
declare <16 x i8> @llvm.arm.neon.vabas.v16i8(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
declare <8 x i16> @llvm.arm.neon.vabas.v8i16(<8 x i16>, <8 x i16>, <8 x i16>) nounwind readnone
declare <4 x i32> @llvm.arm.neon.vabas.v4i32(<4 x i32>, <4 x i32>, <4 x i32>) nounwind readnone
declare <16 x i8> @llvm.arm.neon.vabau.v16i8(<16 x i8>, <16 x i8>, <16 x i8>) nounwind readnone
declare <8 x i16> @llvm.arm.neon.vabau.v8i16(<8 x i16>, <8 x i16>, <8 x i16>) nounwind readnone
declare <4 x i32> @llvm.arm.neon.vabau.v4i32(<4 x i32>, <4 x i32>, <4 x i32>) nounwind readnone
|
