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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
; ANDV
define i8 @andv_nxv8i8(<vscale x 8 x i8> %a) {
; CHECK-LABEL: andv_nxv8i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: andv h0, p0, z0.h
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%res = call i8 @llvm.vector.reduce.and.nxv8i8(<vscale x 8 x i8> %a)
ret i8 %res
}
define i32 @andv_nxv8i32(<vscale x 8 x i32> %a) {
; CHECK-LABEL: andv_nxv8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: and z0.d, z0.d, z1.d
; CHECK-NEXT: andv s0, p0, z0.s
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%res = call i32 @llvm.vector.reduce.and.nxv8i32(<vscale x 8 x i32> %a)
ret i32 %res
}
; ORV
define i32 @orv_nxv2i32(<vscale x 2 x i32> %a) {
; CHECK-LABEL: orv_nxv2i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: orv d0, p0, z0.d
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
%res = call i32 @llvm.vector.reduce.or.nxv2i32(<vscale x 2 x i32> %a)
ret i32 %res
}
define i64 @orv_nxv8i64(<vscale x 8 x i64> %a) {
; CHECK-LABEL: orv_nxv8i64:
; CHECK: // %bb.0:
; CHECK-NEXT: orr z1.d, z1.d, z3.d
; CHECK-NEXT: orr z0.d, z0.d, z2.d
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: orr z0.d, z0.d, z1.d
; CHECK-NEXT: orv d0, p0, z0.d
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: ret
%res = call i64 @llvm.vector.reduce.or.nxv8i64(<vscale x 8 x i64> %a)
ret i64 %res
}
; XORV
define i16 @xorv_nxv2i16(<vscale x 2 x i16> %a) {
; CHECK-LABEL: xorv_nxv2i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: eorv d0, p0, z0.d
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
%res = call i16 @llvm.vector.reduce.xor.nxv2i16(<vscale x 2 x i16> %a)
ret i16 %res
}
define i32 @xorv_nxv8i32(<vscale x 8 x i32> %a) {
; CHECK-LABEL: xorv_nxv8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: eor z0.d, z0.d, z1.d
; CHECK-NEXT: eorv s0, p0, z0.s
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%res = call i32 @llvm.vector.reduce.xor.nxv8i32(<vscale x 8 x i32> %a)
ret i32 %res
}
; UADDV
define i16 @uaddv_nxv4i16(<vscale x 4 x i16> %a) {
; CHECK-LABEL: uaddv_nxv4i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: uaddv d0, p0, z0.s
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
%res = call i16 @llvm.vector.reduce.add.nxv4i16(<vscale x 4 x i16> %a)
ret i16 %res
}
define i16 @uaddv_nxv16i16(<vscale x 16 x i16> %a) {
; CHECK-LABEL: uaddv_nxv16i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: add z0.h, z0.h, z1.h
; CHECK-NEXT: uaddv d0, p0, z0.h
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
%res = call i16 @llvm.vector.reduce.add.nxv16i16(<vscale x 16 x i16> %a)
ret i16 %res
}
define i32 @uaddv_nxv16i32(<vscale x 16 x i32> %a) {
; CHECK-LABEL: uaddv_nxv16i32:
; CHECK: // %bb.0:
; CHECK-NEXT: add z1.s, z1.s, z3.s
; CHECK-NEXT: add z0.s, z0.s, z2.s
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: add z0.s, z0.s, z1.s
; CHECK-NEXT: uaddv d0, p0, z0.s
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
%res = call i32 @llvm.vector.reduce.add.nxv16i32(<vscale x 16 x i32> %a)
ret i32 %res
}
; UMINV
define i32 @umin_nxv2i32(<vscale x 2 x i32> %a) {
; CHECK-LABEL: umin_nxv2i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: and z0.d, z0.d, #0xffffffff
; CHECK-NEXT: uminv d0, p0, z0.d
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
%res = call i32 @llvm.vector.reduce.umin.nxv2i32(<vscale x 2 x i32> %a)
ret i32 %res
}
define i64 @umin_nxv4i64(<vscale x 4 x i64> %a) {
; CHECK-LABEL: umin_nxv4i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: umin z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: uminv d0, p0, z0.d
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: ret
%res = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %a)
ret i64 %res
}
; SMINV
define i8 @smin_nxv4i8(<vscale x 4 x i8> %a) {
; CHECK-LABEL: smin_nxv4i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: sxtb z0.s, p0/m, z0.s
; CHECK-NEXT: sminv s0, p0, z0.s
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%res = call i8 @llvm.vector.reduce.smin.nxv4i8(<vscale x 4 x i8> %a)
ret i8 %res
}
define i32 @smin_nxv8i32(<vscale x 8 x i32> %a) {
; CHECK-LABEL: smin_nxv8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: smin z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: sminv s0, p0, z0.s
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%res = call i32 @llvm.vector.reduce.smin.nxv8i32(<vscale x 8 x i32> %a)
ret i32 %res
}
; UMAXV
define i16 @smin_nxv16i16(<vscale x 16 x i16> %a) {
; CHECK-LABEL: smin_nxv16i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: umax z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: umaxv h0, p0, z0.h
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%res = call i16 @llvm.vector.reduce.umax.nxv16i16(<vscale x 16 x i16> %a)
ret i16 %res
}
; SMAXV
define i64 @smin_nxv8i64(<vscale x 8 x i64> %a) {
; CHECK-LABEL: smin_nxv8i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: smax z1.d, p0/m, z1.d, z3.d
; CHECK-NEXT: smax z0.d, p0/m, z0.d, z2.d
; CHECK-NEXT: smax z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: smaxv d0, p0, z0.d
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: ret
%res = call i64 @llvm.vector.reduce.smax.nxv8i64(<vscale x 8 x i64> %a)
ret i64 %res
}
declare i8 @llvm.vector.reduce.and.nxv8i8(<vscale x 8 x i8>)
declare i32 @llvm.vector.reduce.and.nxv8i32(<vscale x 8 x i32>)
declare i32 @llvm.vector.reduce.or.nxv2i32(<vscale x 2 x i32>)
declare i64 @llvm.vector.reduce.or.nxv8i64(<vscale x 8 x i64>)
declare i16 @llvm.vector.reduce.xor.nxv2i16(<vscale x 2 x i16>)
declare i32 @llvm.vector.reduce.xor.nxv8i32(<vscale x 8 x i32>)
declare i16 @llvm.vector.reduce.add.nxv4i16(<vscale x 4 x i16>)
declare i16 @llvm.vector.reduce.add.nxv16i16(<vscale x 16 x i16>)
declare i32 @llvm.vector.reduce.add.nxv16i32(<vscale x 16 x i32>)
declare i32 @llvm.vector.reduce.umin.nxv2i32(<vscale x 2 x i32>)
declare i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64>)
declare i8 @llvm.vector.reduce.smin.nxv4i8(<vscale x 4 x i8>)
declare i32 @llvm.vector.reduce.smin.nxv8i32(<vscale x 8 x i32>)
declare i16 @llvm.vector.reduce.umax.nxv16i16(<vscale x 16 x i16>)
declare i64 @llvm.vector.reduce.smax.nxv8i64(<vscale x 8 x i64>)
|
