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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
define <vscale x 16 x i8> @mad_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
; CHECK-LABEL: mad_i8:
; CHECK: mad z0.b, p0/m, z1.b, z2.b
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1> %pg,
<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
<vscale x 16 x i8> %c)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @mad_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
; CHECK-LABEL: mad_i16:
; CHECK: mad z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
<vscale x 8 x i16> %c)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @mad_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) {
; CHECK-LABEL: mad_i32:
; CHECK: mad z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
<vscale x 4 x i32> %c)
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @mad_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) {
; CHECK-LABEL: mad_i64:
; CHECK: mad z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
<vscale x 2 x i64> %c)
ret <vscale x 2 x i64> %out
}
define <vscale x 16 x i8> @msb_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
; CHECK-LABEL: msb_i8:
; CHECK: msb z0.b, p0/m, z1.b, z2.b
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1> %pg,
<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
<vscale x 16 x i8> %c)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @msb_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
; CHECK-LABEL: msb_i16:
; CHECK: msb z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
<vscale x 8 x i16> %c)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @msb_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) {
; CHECK-LABEL: msb_i32:
; CHECK: msb z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
<vscale x 4 x i32> %c)
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @msb_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) {
; CHECK-LABEL: msb_i64:
; CHECK: msb z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
<vscale x 2 x i64> %c)
ret <vscale x 2 x i64> %out
}
define <vscale x 16 x i8> @mla_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
; CHECK-LABEL: mla_i8:
; CHECK: mla z0.b, p0/m, z1.b, z2.b
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1> %pg,
<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
<vscale x 16 x i8> %c)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @mla_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
; CHECK-LABEL: mla_i16:
; CHECK: mla z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
<vscale x 8 x i16> %c)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @mla_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) {
; CHECK-LABEL: mla_i32:
; CHECK: mla z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
<vscale x 4 x i32> %c)
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @mla_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) {
; CHECK-LABEL: mla_i64:
; CHECK: mla z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
<vscale x 2 x i64> %c)
ret <vscale x 2 x i64> %out
}
define <vscale x 16 x i8> @mls_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b, <vscale x 16 x i8> %c) {
; CHECK-LABEL: mls_i8:
; CHECK: mls z0.b, p0/m, z1.b, z2.b
; CHECK-NEXT: ret
%out = call <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1> %pg,
<vscale x 16 x i8> %a,
<vscale x 16 x i8> %b,
<vscale x 16 x i8> %c)
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @mls_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b, <vscale x 8 x i16> %c) {
; CHECK-LABEL: mls_i16:
; CHECK: mls z0.h, p0/m, z1.h, z2.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1> %pg,
<vscale x 8 x i16> %a,
<vscale x 8 x i16> %b,
<vscale x 8 x i16> %c)
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @mls_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b, <vscale x 4 x i32> %c) {
; CHECK-LABEL: mls_i32:
; CHECK: mls z0.s, p0/m, z1.s, z2.s
; CHECK-NEXT: ret
%out = call <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1> %pg,
<vscale x 4 x i32> %a,
<vscale x 4 x i32> %b,
<vscale x 4 x i32> %c)
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @mls_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, <vscale x 2 x i64> %c) {
; CHECK-LABEL: mls_i64:
; CHECK: mls z0.d, p0/m, z1.d, z2.d
; CHECK-NEXT: ret
%out = call <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1> %pg,
<vscale x 2 x i64> %a,
<vscale x 2 x i64> %b,
<vscale x 2 x i64> %c)
ret <vscale x 2 x i64> %out
}
declare <vscale x 16 x i8> @llvm.aarch64.sve.mad.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>,<vscale x 16 x i8>,<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.mad.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>,<vscale x 8 x i16>,<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.mad.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>,<vscale x 4 x i32>,<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.mad.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>,<vscale x 2 x i64>,<vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.msb.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>,<vscale x 16 x i8>,<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.msb.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>,<vscale x 8 x i16>,<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.msb.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>,<vscale x 4 x i32>,<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.msb.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>,<vscale x 2 x i64>,<vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.mla.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>,<vscale x 16 x i8>,<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.mla.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>,<vscale x 8 x i16>,<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.mla.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>,<vscale x 4 x i32>,<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.mla.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>,<vscale x 2 x i64>,<vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.mls.nxv16i8(<vscale x 16 x i1>, <vscale x 16 x i8>,<vscale x 16 x i8>,<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.mls.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>,<vscale x 8 x i16>,<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.mls.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>,<vscale x 4 x i32>,<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.mls.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>,<vscale x 2 x i64>,<vscale x 2 x i64>)
|
