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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s --check-prefix=CHECK
declare i1 @llvm.vector.reduce.umax.v1i1(<1 x i1> %a)
declare i8 @llvm.vector.reduce.umax.v1i8(<1 x i8> %a)
declare i16 @llvm.vector.reduce.umax.v1i16(<1 x i16> %a)
declare i24 @llvm.vector.reduce.umax.v1i24(<1 x i24> %a)
declare i32 @llvm.vector.reduce.umax.v1i32(<1 x i32> %a)
declare i64 @llvm.vector.reduce.umax.v1i64(<1 x i64> %a)
declare i128 @llvm.vector.reduce.umax.v1i128(<1 x i128> %a)
declare i64 @llvm.vector.reduce.umax.v2i64(<2 x i64> %a)
declare i8 @llvm.vector.reduce.umax.v3i8(<3 x i8> %a)
declare i8 @llvm.vector.reduce.umax.v9i8(<9 x i8> %a)
declare i32 @llvm.vector.reduce.umax.v3i32(<3 x i32> %a)
declare i1 @llvm.vector.reduce.umax.v4i1(<4 x i1> %a)
declare i24 @llvm.vector.reduce.umax.v4i24(<4 x i24> %a)
declare i128 @llvm.vector.reduce.umax.v2i128(<2 x i128> %a)
declare i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> %a)
define i1 @test_v1i1(<1 x i1> %a) nounwind {
; CHECK-LABEL: test_v1i1:
; CHECK: // %bb.0:
; CHECK-NEXT: and w0, w0, #0x1
; CHECK-NEXT: ret
%b = call i1 @llvm.vector.reduce.umax.v1i1(<1 x i1> %a)
ret i1 %b
}
define i8 @test_v1i8(<1 x i8> %a) nounwind {
; CHECK-LABEL: test_v1i8:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: umov w0, v0.b[0]
; CHECK-NEXT: ret
%b = call i8 @llvm.vector.reduce.umax.v1i8(<1 x i8> %a)
ret i8 %b
}
define i16 @test_v1i16(<1 x i16> %a) nounwind {
; CHECK-LABEL: test_v1i16:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: umov w0, v0.h[0]
; CHECK-NEXT: ret
%b = call i16 @llvm.vector.reduce.umax.v1i16(<1 x i16> %a)
ret i16 %b
}
define i24 @test_v1i24(<1 x i24> %a) nounwind {
; CHECK-LABEL: test_v1i24:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%b = call i24 @llvm.vector.reduce.umax.v1i24(<1 x i24> %a)
ret i24 %b
}
define i32 @test_v1i32(<1 x i32> %a) nounwind {
; CHECK-LABEL: test_v1i32:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%b = call i32 @llvm.vector.reduce.umax.v1i32(<1 x i32> %a)
ret i32 %b
}
define i64 @test_v1i64(<1 x i64> %a) nounwind {
; CHECK-LABEL: test_v1i64:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: ret
%b = call i64 @llvm.vector.reduce.umax.v1i64(<1 x i64> %a)
ret i64 %b
}
define i128 @test_v1i128(<1 x i128> %a) nounwind {
; CHECK-LABEL: test_v1i128:
; CHECK: // %bb.0:
; CHECK-NEXT: ret
%b = call i128 @llvm.vector.reduce.umax.v1i128(<1 x i128> %a)
ret i128 %b
}
; No i64 vector support for UMAX.
define i64 @test_v2i64(<2 x i64> %a) nounwind {
; CHECK-LABEL: test_v2i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ext v1.16b, v0.16b, v0.16b, #8
; CHECK-NEXT: cmhi d2, d0, d1
; CHECK-NEXT: bif v0.8b, v1.8b, v2.8b
; CHECK-NEXT: fmov x0, d0
; CHECK-NEXT: ret
%b = call i64 @llvm.vector.reduce.umax.v2i64(<2 x i64> %a)
ret i64 %b
}
define i8 @test_v3i8(<3 x i8> %a) nounwind {
; CHECK-LABEL: test_v3i8:
; CHECK: // %bb.0:
; CHECK-NEXT: movi d0, #0000000000000000
; CHECK-NEXT: mov v0.h[0], w0
; CHECK-NEXT: mov v0.h[1], w1
; CHECK-NEXT: mov v0.h[2], w2
; CHECK-NEXT: bic v0.4h, #255, lsl #8
; CHECK-NEXT: umaxv h0, v0.4h
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%b = call i8 @llvm.vector.reduce.umax.v3i8(<3 x i8> %a)
ret i8 %b
}
define i8 @test_v9i8(<9 x i8> %a) nounwind {
; CHECK-LABEL: test_v9i8:
; CHECK: // %bb.0:
; CHECK-NEXT: mov v0.b[9], wzr
; CHECK-NEXT: mov v0.b[10], wzr
; CHECK-NEXT: mov v0.b[11], wzr
; CHECK-NEXT: mov v0.b[12], wzr
; CHECK-NEXT: mov v0.b[13], wzr
; CHECK-NEXT: mov v0.b[14], wzr
; CHECK-NEXT: mov v0.b[15], wzr
; CHECK-NEXT: umaxv b0, v0.16b
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%b = call i8 @llvm.vector.reduce.umax.v9i8(<9 x i8> %a)
ret i8 %b
}
define i32 @test_v3i32(<3 x i32> %a) nounwind {
; CHECK-LABEL: test_v3i32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov v0.s[3], wzr
; CHECK-NEXT: umaxv s0, v0.4s
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%b = call i32 @llvm.vector.reduce.umax.v3i32(<3 x i32> %a)
ret i32 %b
}
define i1 @test_v4i1(<4 x i1> %a) nounwind {
; CHECK-LABEL: test_v4i1:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: umov w8, v0.h[1]
; CHECK-NEXT: umov w9, v0.h[0]
; CHECK-NEXT: umov w10, v0.h[2]
; CHECK-NEXT: umov w11, v0.h[3]
; CHECK-NEXT: orr w8, w9, w8
; CHECK-NEXT: orr w8, w8, w10
; CHECK-NEXT: orr w8, w8, w11
; CHECK-NEXT: and w0, w8, #0x1
; CHECK-NEXT: ret
%b = call i1 @llvm.vector.reduce.umax.v4i1(<4 x i1> %a)
ret i1 %b
}
define i24 @test_v4i24(<4 x i24> %a) nounwind {
; CHECK-LABEL: test_v4i24:
; CHECK: // %bb.0:
; CHECK-NEXT: bic v0.4s, #255, lsl #24
; CHECK-NEXT: umaxv s0, v0.4s
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%b = call i24 @llvm.vector.reduce.umax.v4i24(<4 x i24> %a)
ret i24 %b
}
define i128 @test_v2i128(<2 x i128> %a) nounwind {
; CHECK-LABEL: test_v2i128:
; CHECK: // %bb.0:
; CHECK-NEXT: cmp x0, x2
; CHECK-NEXT: csel x8, x0, x2, hi
; CHECK-NEXT: cmp x1, x3
; CHECK-NEXT: csel x9, x0, x2, hi
; CHECK-NEXT: csel x1, x1, x3, hi
; CHECK-NEXT: csel x0, x8, x9, eq
; CHECK-NEXT: ret
%b = call i128 @llvm.vector.reduce.umax.v2i128(<2 x i128> %a)
ret i128 %b
}
define i32 @test_v16i32(<16 x i32> %a) nounwind {
; CHECK-LABEL: test_v16i32:
; CHECK: // %bb.0:
; CHECK-NEXT: umax v1.4s, v1.4s, v3.4s
; CHECK-NEXT: umax v0.4s, v0.4s, v2.4s
; CHECK-NEXT: umax v0.4s, v0.4s, v1.4s
; CHECK-NEXT: umaxv s0, v0.4s
; CHECK-NEXT: fmov w0, s0
; CHECK-NEXT: ret
%b = call i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> %a)
ret i32 %b
}
|
