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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve2p1 < %s | FileCheck %s
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sme2p1 -force-streaming < %s | FileCheck %s
;
; FMAXNMQV
;
define <8 x half> @fmaxnmqv_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) {
; CHECK-LABEL: fmaxnmqv_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: fmaxnmqv v0.8h, p0, z0.h
; CHECK-NEXT: ret
%res = call <8 x half> @llvm.aarch64.sve.fmaxnmqv.v8f16.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a)
ret <8 x half> %res
}
define <4 x float> @fmaxnmqv_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a) {
; CHECK-LABEL: fmaxnmqv_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: fmaxnmqv v0.4s, p0, z0.s
; CHECK-NEXT: ret
%res = call <4 x float> @llvm.aarch64.sve.fmaxnmqv.v4f32.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a)
ret <4 x float> %res
}
define <2 x double> @fmaxnmqv_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) {
; CHECK-LABEL: fmaxnmqv_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: fmaxnmqv v0.2d, p0, z0.d
; CHECK-NEXT: ret
%res = call <2 x double> @llvm.aarch64.sve.fmaxnmqv.v2f64.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a)
ret <2 x double> %res
}
;
; FMINNMQV
;
define <8 x half> @fminnmqv_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) {
; CHECK-LABEL: fminnmqv_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: fminnmqv v0.8h, p0, z0.h
; CHECK-NEXT: ret
%res = call <8 x half> @llvm.aarch64.sve.fminnmqv.v8f16.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a)
ret <8 x half> %res
}
define <4 x float> @fminnmqv_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a) {
; CHECK-LABEL: fminnmqv_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: fminnmqv v0.4s, p0, z0.s
; CHECK-NEXT: ret
%res = call <4 x float> @llvm.aarch64.sve.fminnmqv.v4f32.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a)
ret <4 x float> %res
}
define <2 x double> @fminnmqv_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) {
; CHECK-LABEL: fminnmqv_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: fminnmqv v0.2d, p0, z0.d
; CHECK-NEXT: ret
%res = call <2 x double> @llvm.aarch64.sve.fminnmqv.v2f64.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a)
ret <2 x double> %res
}
;
; FADDQV
;
define <8 x half> @faddqv_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) {
; CHECK-LABEL: faddqv_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: faddqv v0.8h, p0, z0.h
; CHECK-NEXT: ret
%res = call <8 x half> @llvm.aarch64.sve.addqv.v8f16.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a)
ret <8 x half> %res
}
define <4 x float> @faddqv_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a) {
; CHECK-LABEL: faddqv_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: faddqv v0.4s, p0, z0.s
; CHECK-NEXT: ret
%res = call <4 x float> @llvm.aarch64.sve.addqv.v4f32.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a)
ret <4 x float> %res
}
define <2 x double> @faddqv_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) {
; CHECK-LABEL: faddqv_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: faddqv v0.2d, p0, z0.d
; CHECK-NEXT: ret
%res = call <2 x double> @llvm.aarch64.sve.addqv.v2f64.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a)
ret <2 x double> %res
}
;
; FMINQV
;
define <8 x half> @fminqv_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) {
; CHECK-LABEL: fminqv_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: fminqv v0.8h, p0, z0.h
; CHECK-NEXT: ret
%res = call <8 x half> @llvm.aarch64.sve.fminqv.v8f16.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a)
ret <8 x half> %res
}
define <4 x float> @fminqv_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a) {
; CHECK-LABEL: fminqv_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: fminqv v0.4s, p0, z0.s
; CHECK-NEXT: ret
%res = call <4 x float> @llvm.aarch64.sve.fminqv.v4f32.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a)
ret <4 x float> %res
}
define <2 x double> @fminqv_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) {
; CHECK-LABEL: fminqv_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: fminqv v0.2d, p0, z0.d
; CHECK-NEXT: ret
%res = call <2 x double> @llvm.aarch64.sve.fminqv.v2f64.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a)
ret <2 x double> %res
}
;
; FMAXQV
;
define <8 x half> @fmaxqv_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) {
; CHECK-LABEL: fmaxqv_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: fmaxqv v0.8h, p0, z0.h
; CHECK-NEXT: ret
%res = call <8 x half> @llvm.aarch64.sve.fmaxqv.v8f16.nxv8f16(<vscale x 8 x i1> %pg,
<vscale x 8 x half> %a)
ret <8 x half> %res
}
define <4 x float> @fmaxqv_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a) {
; CHECK-LABEL: fmaxqv_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: fmaxqv v0.4s, p0, z0.s
; CHECK-NEXT: ret
%res = call <4 x float> @llvm.aarch64.sve.fmaxqv.v4f32.nxv4f32(<vscale x 4 x i1> %pg,
<vscale x 4 x float> %a)
ret <4 x float> %res
}
define <2 x double> @fmaxqv_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) {
; CHECK-LABEL: fmaxqv_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: fmaxqv v0.2d, p0, z0.d
; CHECK-NEXT: ret
%res = call <2 x double> @llvm.aarch64.sve.fmaxqv.v2f64.nxv2f64(<vscale x 2 x i1> %pg,
<vscale x 2 x double> %a)
ret <2 x double> %res
}
declare <8 x half> @llvm.aarch64.sve.fmaxnmqv.v8f16.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>)
declare <4 x float> @llvm.aarch64.sve.fmaxnmqv.v4f32.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>)
declare <2 x double> @llvm.aarch64.sve.fmaxnmqv.v2f64.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>)
declare <8 x half> @llvm.aarch64.sve.fminnmqv.v8f16.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>)
declare <4 x float> @llvm.aarch64.sve.fminnmqv.v4f32.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>)
declare <2 x double> @llvm.aarch64.sve.fminnmqv.v2f64.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>)
declare <8 x half> @llvm.aarch64.sve.addqv.v8f16.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>)
declare <4 x float> @llvm.aarch64.sve.addqv.v4f32.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>)
declare <2 x double> @llvm.aarch64.sve.addqv.v2f64.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>)
declare <8 x half> @llvm.aarch64.sve.fminqv.v8f16.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>)
declare <4 x float> @llvm.aarch64.sve.fminqv.v4f32.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>)
declare <2 x double> @llvm.aarch64.sve.fminqv.v2f64.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>)
declare <8 x half> @llvm.aarch64.sve.fmaxqv.v8f16.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>)
declare <4 x float> @llvm.aarch64.sve.fmaxqv.v4f32.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>)
declare <2 x double> @llvm.aarch64.sve.fmaxqv.v2f64.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>)
|
