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-- | FileCheck %s
; First, check the generic pattern for any 2 vector constants. Then, check special cases where
; the constants are all off-by-one. Finally, check the extra special cases where the constants
; include 0 or -1.
; Each minimal select test is repeated with a more typical pattern that includes a compare to
; generate the condition value.
define <4 x i32> @sel_C1_or_C2_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_C1_or_C2_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI0_0
; CHECK-NEXT: adrp x9, .LCPI0_1
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI0_0]
; CHECK-NEXT: ldr q2, [x9, :lo12:.LCPI0_1]
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
; CHECK-NEXT: shl v0.4s, v0.4s, #31
; CHECK-NEXT: sshr v0.4s, v0.4s, #31
; CHECK-NEXT: bsl v0.16b, v2.16b, v1.16b
; CHECK-NEXT: ret
%add = select <4 x i1> %cond, <4 x i32> <i32 3000, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_C1_or_C2_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_C1_or_C2_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI1_0
; CHECK-NEXT: adrp x9, .LCPI1_1
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI1_0]
; CHECK-NEXT: ldr q3, [x9, :lo12:.LCPI1_1]
; CHECK-NEXT: cmeq v0.4s, v0.4s, v1.4s
; CHECK-NEXT: bsl v0.16b, v3.16b, v2.16b
; CHECK-NEXT: ret
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 3000, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @sel_Cplus1_or_C_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_Cplus1_or_C_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI2_0
; CHECK-NEXT: adrp x9, .LCPI2_1
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI2_0]
; CHECK-NEXT: ldr q2, [x9, :lo12:.LCPI2_1]
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
; CHECK-NEXT: shl v0.4s, v0.4s, #31
; CHECK-NEXT: sshr v0.4s, v0.4s, #31
; CHECK-NEXT: bsl v0.16b, v2.16b, v1.16b
; CHECK-NEXT: ret
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_Cplus1_or_C_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_Cplus1_or_C_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI3_0
; CHECK-NEXT: adrp x9, .LCPI3_1
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI3_0]
; CHECK-NEXT: ldr q3, [x9, :lo12:.LCPI3_1]
; CHECK-NEXT: cmeq v0.4s, v0.4s, v1.4s
; CHECK-NEXT: bsl v0.16b, v3.16b, v2.16b
; CHECK-NEXT: ret
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 42, i32 0, i32 -2, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @sel_Cminus1_or_C_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_Cminus1_or_C_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI4_0
; CHECK-NEXT: adrp x9, .LCPI4_1
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI4_0]
; CHECK-NEXT: ldr q2, [x9, :lo12:.LCPI4_1]
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
; CHECK-NEXT: shl v0.4s, v0.4s, #31
; CHECK-NEXT: sshr v0.4s, v0.4s, #31
; CHECK-NEXT: bsl v0.16b, v2.16b, v1.16b
; CHECK-NEXT: ret
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 44, i32 2, i32 0, i32 1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_Cminus1_or_C_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_Cminus1_or_C_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI5_0
; CHECK-NEXT: adrp x9, .LCPI5_1
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI5_0]
; CHECK-NEXT: ldr q3, [x9, :lo12:.LCPI5_1]
; CHECK-NEXT: cmeq v0.4s, v0.4s, v1.4s
; CHECK-NEXT: bsl v0.16b, v3.16b, v2.16b
; CHECK-NEXT: ret
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 43, i32 1, i32 -1, i32 0>, <4 x i32> <i32 44, i32 2, i32 0, i32 1>
ret <4 x i32> %add
}
define <4 x i32> @sel_minus1_or_0_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_minus1_or_0_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
; CHECK-NEXT: shl v0.4s, v0.4s, #31
; CHECK-NEXT: sshr v0.4s, v0.4s, #31
; CHECK-NEXT: ret
%add = select <4 x i1> %cond, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_minus1_or_0_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_minus1_or_0_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: cmeq v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @sel_0_or_minus1_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_0_or_minus1_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
; CHECK-NEXT: shl v0.4s, v0.4s, #31
; CHECK-NEXT: cmge v0.4s, v0.4s, #0
; CHECK-NEXT: ret
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_0_or_minus1_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_0_or_minus1_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: cmeq v0.4s, v0.4s, v1.4s
; CHECK-NEXT: mvn v0.16b, v0.16b
; CHECK-NEXT: ret
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %add
}
define <4 x i32> @sel_1_or_0_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_1_or_0_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
; CHECK-NEXT: shl v0.4s, v0.4s, #31
; CHECK-NEXT: sshr v0.4s, v0.4s, #31
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%add = select <4 x i1> %cond, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_1_or_0_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_1_or_0_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: cmeq v0.4s, v0.4s, v1.4s
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
ret <4 x i32> %add
}
define <4 x i32> @sel_0_or_1_vec(<4 x i1> %cond) {
; CHECK-LABEL: sel_0_or_1_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: ushll v0.4s, v0.4h, #0
; CHECK-NEXT: shl v0.4s, v0.4s, #31
; CHECK-NEXT: cmge v0.4s, v0.4s, #0
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
ret <4 x i32> %add
}
define <4 x i32> @cmp_sel_0_or_1_vec(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: cmp_sel_0_or_1_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: cmeq v0.4s, v0.4s, v1.4s
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: bic v0.16b, v1.16b, v0.16b
; CHECK-NEXT: ret
%cond = icmp eq <4 x i32> %x, %y
%add = select <4 x i1> %cond, <4 x i32> <i32 0, i32 0, i32 0, i32 0>, <4 x i32> <i32 1, i32 1, i32 1, i32 1>
ret <4 x i32> %add
}
|