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
253
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mattr=+sve -mtriple=aarch64 %s -o - | FileCheck %s --check-prefixes=CHECK
; These tests just check that the plumbing is in place for @llvm.smax, @llvm.umax,
; @llvm.smin, @llvm.umin.
; tests for smax:
define <vscale x 16 x i8> @smax_select_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: smax_select_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: smax z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT: ret
%sel = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
%out = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %sel, <vscale x 16 x i8> %a
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @smax_select_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: smax_select_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: smax z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%sel = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
%out = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %sel, <vscale x 8 x i16> %a
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @smax_select_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: smax_select_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: smax z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%sel = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
%out = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %sel, <vscale x 4 x i32> %a
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @smax_select_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: smax_select_i64:
; CHECK: // %bb.0:
; CHECK-NEXT: smax z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%sel = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
%out = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %sel, <vscale x 2 x i64> %a
ret <vscale x 2 x i64> %out
}
; tests for umax:
define <vscale x 16 x i8> @umax_select_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: umax_select_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: umax z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT: ret
%sel = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
%out = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %sel, <vscale x 16 x i8> %a
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @umax_select_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: umax_select_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: umax z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%sel = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
%out = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %sel, <vscale x 8 x i16> %a
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @umax_select_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: umax_select_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: umax z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%sel = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
%out = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %sel, <vscale x 4 x i32> %a
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @umax_select_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: umax_select_i64:
; CHECK: // %bb.0:
; CHECK-NEXT: umax z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%sel = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
%out = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %sel, <vscale x 2 x i64> %a
ret <vscale x 2 x i64> %out
}
; tests for smin:
define <vscale x 16 x i8> @smin_select_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: smin_select_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: smin z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT: ret
%sel = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
%out = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %sel, <vscale x 16 x i8> %a
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @smin_select_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: smin_select_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: smin z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%sel = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
%out = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %sel, <vscale x 8 x i16> %a
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @smin_select_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: smin_select_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: smin z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%sel = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
%out = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %sel, <vscale x 4 x i32> %a
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @smin_select_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: smin_select_i64:
; CHECK: // %bb.0:
; CHECK-NEXT: smin z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%sel = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
%out = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %sel, <vscale x 2 x i64> %a
ret <vscale x 2 x i64> %out
}
; tests for umin:
define <vscale x 16 x i8> @umin_select_i8(<vscale x 16 x i1> %pg, <vscale x 16 x i8> %a, <vscale x 16 x i8> %b) {
; CHECK-LABEL: umin_select_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: umin z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT: ret
%sel = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b)
%out = select <vscale x 16 x i1> %pg, <vscale x 16 x i8> %sel, <vscale x 16 x i8> %a
ret <vscale x 16 x i8> %out
}
define <vscale x 8 x i16> @umin_select_i16(<vscale x 8 x i1> %pg, <vscale x 8 x i16> %a, <vscale x 8 x i16> %b) {
; CHECK-LABEL: umin_select_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: umin z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%sel = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b)
%out = select <vscale x 8 x i1> %pg, <vscale x 8 x i16> %sel, <vscale x 8 x i16> %a
ret <vscale x 8 x i16> %out
}
define <vscale x 4 x i32> @umin_select_i32(<vscale x 4 x i1> %pg, <vscale x 4 x i32> %a, <vscale x 4 x i32> %b) {
; CHECK-LABEL: umin_select_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: umin z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%sel = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b)
%out = select <vscale x 4 x i1> %pg, <vscale x 4 x i32> %sel, <vscale x 4 x i32> %a
ret <vscale x 4 x i32> %out
}
define <vscale x 2 x i64> @umin_select_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: umin_select_i64:
; CHECK: // %bb.0:
; CHECK-NEXT: umin z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%sel = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
%out = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %sel, <vscale x 2 x i64> %a
ret <vscale x 2 x i64> %out
}
define <vscale x 2 x i64> @umin_select_i64_multiuse(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b, ptr %p) {
; CHECK-LABEL: umin_select_i64_multiuse:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p1.d
; CHECK-NEXT: umin z1.d, p1/m, z1.d, z0.d
; CHECK-NEXT: mov z0.d, p0/m, z1.d
; CHECK-NEXT: st1d { z1.d }, p1, [x0]
; CHECK-NEXT: ret
%sel = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
store <vscale x 2 x i64> %sel, ptr %p
%out = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %sel, <vscale x 2 x i64> %a
ret <vscale x 2 x i64> %out
}
define <vscale x 2 x i64> @smin_select_i64_c(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: smin_select_i64_c:
; CHECK: // %bb.0:
; CHECK-NEXT: smin z1.d, p0/m, z1.d, z0.d
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
%sel = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
%out = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %sel, <vscale x 2 x i64> %b
ret <vscale x 2 x i64> %out
}
define <vscale x 2 x i64> @smax_select_i64_c(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: smax_select_i64_c:
; CHECK: // %bb.0:
; CHECK-NEXT: smax z1.d, p0/m, z1.d, z0.d
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
%sel = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
%out = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %sel, <vscale x 2 x i64> %b
ret <vscale x 2 x i64> %out
}
define <vscale x 2 x i64> @umin_select_i64_c(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: umin_select_i64_c:
; CHECK: // %bb.0:
; CHECK-NEXT: umin z1.d, p0/m, z1.d, z0.d
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
%sel = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
%out = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %sel, <vscale x 2 x i64> %b
ret <vscale x 2 x i64> %out
}
define <vscale x 2 x i64> @umax_select_i64_c(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a, <vscale x 2 x i64> %b) {
; CHECK-LABEL: umax_select_i64_c:
; CHECK: // %bb.0:
; CHECK-NEXT: umax z1.d, p0/m, z1.d, z0.d
; CHECK-NEXT: mov z0.d, z1.d
; CHECK-NEXT: ret
%sel = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b)
%out = select <vscale x 2 x i1> %pg, <vscale x 2 x i64> %sel, <vscale x 2 x i64> %b
ret <vscale x 2 x i64> %out
}
declare <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
|
