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
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -asm-verbose=0 < %s | FileCheck %s
; FADD
define half @fadda_nxv2f16(half %init, <vscale x 2 x half> %a) {
; CHECK-LABEL: fadda_nxv2f16:
; CHECK: ptrue p0.d
; CHECK-NEXT: fadda h0, p0, h0, z1.h
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fadd.nxv2f16(half %init, <vscale x 2 x half> %a)
ret half %res
}
define half @fadda_nxv4f16(half %init, <vscale x 4 x half> %a) {
; CHECK-LABEL: fadda_nxv4f16:
; CHECK: ptrue p0.s
; CHECK-NEXT: fadda h0, p0, h0, z1.h
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fadd.nxv4f16(half %init, <vscale x 4 x half> %a)
ret half %res
}
define half @fadda_nxv8f16(half %init, <vscale x 8 x half> %a) {
; CHECK-LABEL: fadda_nxv8f16:
; CHECK: ptrue p0.h
; CHECK-NEXT: fadda h0, p0, h0, z1.h
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fadd.nxv8f16(half %init, <vscale x 8 x half> %a)
ret half %res
}
define float @fadda_nxv2f32(float %init, <vscale x 2 x float> %a) {
; CHECK-LABEL: fadda_nxv2f32:
; CHECK: ptrue p0.d
; CHECK-NEXT: fadda s0, p0, s0, z1.s
; CHECK-NEXT: ret
%res = call float @llvm.vector.reduce.fadd.nxv2f32(float %init, <vscale x 2 x float> %a)
ret float %res
}
define float @fadda_nxv4f32(float %init, <vscale x 4 x float> %a) {
; CHECK-LABEL: fadda_nxv4f32:
; CHECK: ptrue p0.s
; CHECK-NEXT: fadda s0, p0, s0, z1.s
; CHECK-NEXT: ret
%res = call float @llvm.vector.reduce.fadd.nxv4f32(float %init, <vscale x 4 x float> %a)
ret float %res
}
define double @fadda_nxv2f64(double %init, <vscale x 2 x double> %a) {
; CHECK-LABEL: fadda_nxv2f64:
; CHECK: ptrue p0.d
; CHECK-NEXT: fadda d0, p0, d0, z1.d
; CHECK-NEXT: ret
%res = call double @llvm.vector.reduce.fadd.nxv2f64(double %init, <vscale x 2 x double> %a)
ret double %res
}
; FADDV
define half @faddv_nxv2f16(half %init, <vscale x 2 x half> %a) {
; CHECK-LABEL: faddv_nxv2f16:
; CHECK: ptrue p0.d
; CHECK-NEXT: faddv h1, p0, z1.h
; CHECK-NEXT: fadd h0, h0, h1
; CHECK-NEXT: ret
%res = call fast half @llvm.vector.reduce.fadd.nxv2f16(half %init, <vscale x 2 x half> %a)
ret half %res
}
define half @faddv_nxv4f16(half %init, <vscale x 4 x half> %a) {
; CHECK-LABEL: faddv_nxv4f16:
; CHECK: ptrue p0.s
; CHECK-NEXT: faddv h1, p0, z1.h
; CHECK-NEXT: fadd h0, h0, h1
; CHECK-NEXT: ret
%res = call fast half @llvm.vector.reduce.fadd.nxv4f16(half %init, <vscale x 4 x half> %a)
ret half %res
}
define half @faddv_nxv8f16(half %init, <vscale x 8 x half> %a) {
; CHECK-LABEL: faddv_nxv8f16:
; CHECK: ptrue p0.h
; CHECK-NEXT: faddv h1, p0, z1.h
; CHECK-NEXT: fadd h0, h0, h1
; CHECK-NEXT: ret
%res = call fast half @llvm.vector.reduce.fadd.nxv8f16(half %init, <vscale x 8 x half> %a)
ret half %res
}
define float @faddv_nxv2f32(float %init, <vscale x 2 x float> %a) {
; CHECK-LABEL: faddv_nxv2f32:
; CHECK: ptrue p0.d
; CHECK-NEXT: faddv s1, p0, z1.s
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: ret
%res = call fast float @llvm.vector.reduce.fadd.nxv2f32(float %init, <vscale x 2 x float> %a)
ret float %res
}
define float @faddv_nxv4f32(float %init, <vscale x 4 x float> %a) {
; CHECK-LABEL: faddv_nxv4f32:
; CHECK: ptrue p0.s
; CHECK-NEXT: faddv s1, p0, z1.s
; CHECK-NEXT: fadd s0, s0, s1
; CHECK-NEXT: ret
%res = call fast float @llvm.vector.reduce.fadd.nxv4f32(float %init, <vscale x 4 x float> %a)
ret float %res
}
define double @faddv_nxv2f64(double %init, <vscale x 2 x double> %a) {
; CHECK-LABEL: faddv_nxv2f64:
; CHECK: ptrue p0.d
; CHECK-NEXT: faddv d1, p0, z1.d
; CHECK-NEXT: fadd d0, d0, d1
; CHECK-NEXT: ret
%res = call fast double @llvm.vector.reduce.fadd.nxv2f64(double %init, <vscale x 2 x double> %a)
ret double %res
}
; FMAXV
define half @fmaxv_nxv2f16(<vscale x 2 x half> %a) {
; CHECK-LABEL: fmaxv_nxv2f16:
; CHECK: ptrue p0.d
; CHECK-NEXT: fmaxnmv h0, p0, z0.h
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fmax.nxv2f16(<vscale x 2 x half> %a)
ret half %res
}
define half @fmaxv_nxv4f16(<vscale x 4 x half> %a) {
; CHECK-LABEL: fmaxv_nxv4f16:
; CHECK: ptrue p0.s
; CHECK-NEXT: fmaxnmv h0, p0, z0.h
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fmax.nxv4f16(<vscale x 4 x half> %a)
ret half %res
}
define half @fmaxv_nxv8f16(<vscale x 8 x half> %a) {
; CHECK-LABEL: fmaxv_nxv8f16:
; CHECK: ptrue p0.h
; CHECK-NEXT: fmaxnmv h0, p0, z0.h
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fmax.nxv8f16(<vscale x 8 x half> %a)
ret half %res
}
define float @fmaxv_nxv2f32(<vscale x 2 x float> %a) {
; CHECK-LABEL: fmaxv_nxv2f32:
; CHECK: ptrue p0.d
; CHECK-NEXT: fmaxnmv s0, p0, z0.s
; CHECK-NEXT: ret
%res = call float @llvm.vector.reduce.fmax.nxv2f32(<vscale x 2 x float> %a)
ret float %res
}
define float @fmaxv_nxv4f32(<vscale x 4 x float> %a) {
; CHECK-LABEL: fmaxv_nxv4f32:
; CHECK: ptrue p0.s
; CHECK-NEXT: fmaxnmv s0, p0, z0.s
; CHECK-NEXT: ret
%res = call float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %a)
ret float %res
}
define double @fmaxv_nxv2f64(<vscale x 2 x double> %a) {
; CHECK-LABEL: fmaxv_nxv2f64:
; CHECK: ptrue p0.d
; CHECK-NEXT: fmaxnmv d0, p0, z0.d
; CHECK-NEXT: ret
%res = call double @llvm.vector.reduce.fmax.nxv2f64(<vscale x 2 x double> %a)
ret double %res
}
; FMINV
define half @fminv_nxv2f16(<vscale x 2 x half> %a) {
; CHECK-LABEL: fminv_nxv2f16:
; CHECK: ptrue p0.d
; CHECK-NEXT: fminnmv h0, p0, z0.h
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fmin.nxv2f16(<vscale x 2 x half> %a)
ret half %res
}
define half @fminv_nxv4f16(<vscale x 4 x half> %a) {
; CHECK-LABEL: fminv_nxv4f16:
; CHECK: ptrue p0.s
; CHECK-NEXT: fminnmv h0, p0, z0.h
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fmin.nxv4f16(<vscale x 4 x half> %a)
ret half %res
}
define half @fminv_nxv8f16(<vscale x 8 x half> %a) {
; CHECK-LABEL: fminv_nxv8f16:
; CHECK: ptrue p0.h
; CHECK-NEXT: fminnmv h0, p0, z0.h
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fmin.nxv8f16(<vscale x 8 x half> %a)
ret half %res
}
define float @fminv_nxv2f32(<vscale x 2 x float> %a) {
; CHECK-LABEL: fminv_nxv2f32:
; CHECK: ptrue p0.d
; CHECK-NEXT: fminnmv s0, p0, z0.s
; CHECK-NEXT: ret
%res = call float @llvm.vector.reduce.fmin.nxv2f32(<vscale x 2 x float> %a)
ret float %res
}
define float @fminv_nxv4f32(<vscale x 4 x float> %a) {
; CHECK-LABEL: fminv_nxv4f32:
; CHECK: ptrue p0.s
; CHECK-NEXT: fminnmv s0, p0, z0.s
; CHECK-NEXT: ret
%res = call float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %a)
ret float %res
}
define double @fminv_nxv2f64(<vscale x 2 x double> %a) {
; CHECK-LABEL: fminv_nxv2f64:
; CHECK: ptrue p0.d
; CHECK-NEXT: fminnmv d0, p0, z0.d
; CHECK-NEXT: ret
%res = call double @llvm.vector.reduce.fmin.nxv2f64(<vscale x 2 x double> %a)
ret double %res
}
declare half @llvm.vector.reduce.fadd.nxv2f16(half, <vscale x 2 x half>)
declare half @llvm.vector.reduce.fadd.nxv4f16(half, <vscale x 4 x half>)
declare half @llvm.vector.reduce.fadd.nxv8f16(half, <vscale x 8 x half>)
declare float @llvm.vector.reduce.fadd.nxv2f32(float, <vscale x 2 x float>)
declare float @llvm.vector.reduce.fadd.nxv4f32(float, <vscale x 4 x float>)
declare double @llvm.vector.reduce.fadd.nxv2f64(double, <vscale x 2 x double>)
declare half @llvm.vector.reduce.fmax.nxv2f16(<vscale x 2 x half>)
declare half @llvm.vector.reduce.fmax.nxv4f16(<vscale x 4 x half>)
declare half @llvm.vector.reduce.fmax.nxv8f16(<vscale x 8 x half>)
declare float @llvm.vector.reduce.fmax.nxv2f32(<vscale x 2 x float>)
declare float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float>)
declare double @llvm.vector.reduce.fmax.nxv2f64(<vscale x 2 x double>)
declare half @llvm.vector.reduce.fmin.nxv2f16(<vscale x 2 x half>)
declare half @llvm.vector.reduce.fmin.nxv4f16(<vscale x 4 x half>)
declare half @llvm.vector.reduce.fmin.nxv8f16(<vscale x 8 x half>)
declare float @llvm.vector.reduce.fmin.nxv2f32(<vscale x 2 x float>)
declare float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float>)
declare double @llvm.vector.reduce.fmin.nxv2f64(<vscale x 2 x double>)
|
