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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s
; At the moment, BuildUREMEqFold does not handle nonsplat vectors.
define <4 x i32> @test_urem_odd_div(<4 x i32> %X) nounwind readnone {
; CHECK-LABEL: test_urem_odd_div:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI0_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI0_0]
; CHECK-NEXT: adrp x8, .LCPI0_1
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI0_1]
; CHECK-NEXT: adrp x8, .LCPI0_2
; CHECK-NEXT: umull2 v3.2d, v0.4s, v1.4s
; CHECK-NEXT: umull v1.2d, v0.2s, v1.2s
; CHECK-NEXT: uzp2 v1.4s, v1.4s, v3.4s
; CHECK-NEXT: sub v3.4s, v0.4s, v1.4s
; CHECK-NEXT: umull2 v4.2d, v3.4s, v2.4s
; CHECK-NEXT: umull v2.2d, v3.2s, v2.2s
; CHECK-NEXT: ldr q3, [x8, :lo12:.LCPI0_2]
; CHECK-NEXT: adrp x8, .LCPI0_3
; CHECK-NEXT: uzp2 v2.4s, v2.4s, v4.4s
; CHECK-NEXT: ldr q4, [x8, :lo12:.LCPI0_3]
; CHECK-NEXT: neg v3.4s, v3.4s
; CHECK-NEXT: add v1.4s, v2.4s, v1.4s
; CHECK-NEXT: ushl v1.4s, v1.4s, v3.4s
; CHECK-NEXT: mls v0.4s, v1.4s, v4.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 3, i32 5, i32 7, i32 9>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 0, i32 0, i32 0>
%ret = zext <4 x i1> %cmp to <4 x i32>
ret <4 x i32> %ret
}
define <4 x i32> @test_urem_even_div(<4 x i32> %X) nounwind readnone {
; CHECK-LABEL: test_urem_even_div:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI1_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI1_0]
; CHECK-NEXT: adrp x8, .LCPI1_1
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI1_1]
; CHECK-NEXT: adrp x8, .LCPI1_2
; CHECK-NEXT: ldr q3, [x8, :lo12:.LCPI1_2]
; CHECK-NEXT: neg v1.4s, v1.4s
; CHECK-NEXT: adrp x8, .LCPI1_3
; CHECK-NEXT: ushl v1.4s, v0.4s, v1.4s
; CHECK-NEXT: umull2 v4.2d, v1.4s, v2.4s
; CHECK-NEXT: umull v1.2d, v1.2s, v2.2s
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI1_3]
; CHECK-NEXT: uzp2 v1.4s, v1.4s, v4.4s
; CHECK-NEXT: neg v3.4s, v3.4s
; CHECK-NEXT: ushl v1.4s, v1.4s, v3.4s
; CHECK-NEXT: mls v0.4s, v1.4s, v2.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 6, i32 10, i32 12, i32 14>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 0, i32 0, i32 0>
%ret = zext <4 x i1> %cmp to <4 x i32>
ret <4 x i32> %ret
}
define <4 x i32> @test_urem_pow2(<4 x i32> %X) nounwind readnone {
; CHECK-LABEL: test_urem_pow2:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI2_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI2_0]
; CHECK-NEXT: adrp x8, .LCPI2_1
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI2_1]
; CHECK-NEXT: adrp x8, .LCPI2_2
; CHECK-NEXT: ldr q3, [x8, :lo12:.LCPI2_2]
; CHECK-NEXT: umull2 v4.2d, v0.4s, v1.4s
; CHECK-NEXT: umull v1.2d, v0.2s, v1.2s
; CHECK-NEXT: uzp2 v1.4s, v1.4s, v4.4s
; CHECK-NEXT: neg v2.4s, v2.4s
; CHECK-NEXT: ushl v1.4s, v1.4s, v2.4s
; CHECK-NEXT: mls v0.4s, v1.4s, v3.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 6, i32 10, i32 12, i32 16>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 0, i32 0, i32 0>
%ret = zext <4 x i1> %cmp to <4 x i32>
ret <4 x i32> %ret
}
define <4 x i32> @test_urem_one(<4 x i32> %X) nounwind readnone {
; CHECK-LABEL: test_urem_one:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI3_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI3_0]
; CHECK-NEXT: adrp x8, .LCPI3_1
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI3_1]
; CHECK-NEXT: adrp x8, .LCPI3_2
; CHECK-NEXT: ldr q3, [x8, :lo12:.LCPI3_2]
; CHECK-NEXT: neg v1.4s, v1.4s
; CHECK-NEXT: adrp x8, .LCPI3_3
; CHECK-NEXT: ushl v1.4s, v0.4s, v1.4s
; CHECK-NEXT: umull2 v4.2d, v1.4s, v2.4s
; CHECK-NEXT: umull v1.2d, v1.2s, v2.2s
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI3_3]
; CHECK-NEXT: adrp x8, .LCPI3_4
; CHECK-NEXT: uzp2 v1.4s, v1.4s, v4.4s
; CHECK-NEXT: ldr q4, [x8, :lo12:.LCPI3_4]
; CHECK-NEXT: neg v3.4s, v3.4s
; CHECK-NEXT: ushl v1.4s, v1.4s, v3.4s
; CHECK-NEXT: bsl v2.16b, v0.16b, v1.16b
; CHECK-NEXT: mls v0.4s, v2.4s, v4.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 6, i32 1, i32 12, i32 14>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 0, i32 0, i32 0>
%ret = zext <4 x i1> %cmp to <4 x i32>
ret <4 x i32> %ret
}
define <4 x i32> @test_urem_comp(<4 x i32> %X) nounwind readnone {
; CHECK-LABEL: test_urem_comp:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #52429
; CHECK-NEXT: movk w8, #52428, lsl #16
; CHECK-NEXT: adrp x9, .LCPI4_0
; CHECK-NEXT: dup v2.4s, w8
; CHECK-NEXT: ldr q3, [x9, :lo12:.LCPI4_0]
; CHECK-NEXT: umull2 v4.2d, v0.4s, v2.4s
; CHECK-NEXT: umull v2.2d, v0.2s, v2.2s
; CHECK-NEXT: uzp2 v2.4s, v2.4s, v4.4s
; CHECK-NEXT: movi v1.4s, #5
; CHECK-NEXT: ushr v2.4s, v2.4s, #2
; CHECK-NEXT: mls v0.4s, v2.4s, v1.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, v3.4s
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 5, i32 5, i32 5, i32 5>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 0, i32 1, i32 0>
%ret = zext <4 x i1> %cmp to <4 x i32>
ret <4 x i32> %ret
}
define <4 x i32> @test_urem_both(<4 x i32> %X) nounwind readnone {
; CHECK-LABEL: test_urem_both:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI5_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI5_0]
; CHECK-NEXT: adrp x8, .LCPI5_1
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI5_1]
; CHECK-NEXT: adrp x8, .LCPI5_2
; CHECK-NEXT: ldr q3, [x8, :lo12:.LCPI5_2]
; CHECK-NEXT: umull2 v4.2d, v0.4s, v1.4s
; CHECK-NEXT: umull v1.2d, v0.2s, v1.2s
; CHECK-NEXT: uzp2 v1.4s, v1.4s, v4.4s
; CHECK-NEXT: ushr v1.4s, v1.4s, #2
; CHECK-NEXT: mls v0.4s, v1.4s, v2.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, v3.4s
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 6, i32 5, i32 6, i32 5>
%cmp = icmp eq <4 x i32> %urem, <i32 1, i32 0, i32 1, i32 0>
%ret = zext <4 x i1> %cmp to <4 x i32>
ret <4 x i32> %ret
}
define <4 x i32> @test_urem_div_undef(<4 x i32> %X) nounwind readnone {
; CHECK-LABEL: test_urem_div_undef:
; CHECK: // %bb.0:
; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 5, i32 5, i32 undef, i32 5>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 0, i32 0, i32 0>
%ret = zext <4 x i1> %cmp to <4 x i32>
ret <4 x i32> %ret
}
define <4 x i32> @test_urem_comp_undef(<4 x i32> %X) nounwind readnone {
; CHECK-LABEL: test_urem_comp_undef:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #52429
; CHECK-NEXT: movk w8, #52428, lsl #16
; CHECK-NEXT: dup v2.4s, w8
; CHECK-NEXT: umull2 v3.2d, v0.4s, v2.4s
; CHECK-NEXT: umull v2.2d, v0.2s, v2.2s
; CHECK-NEXT: uzp2 v2.4s, v2.4s, v3.4s
; CHECK-NEXT: movi v1.4s, #5
; CHECK-NEXT: ushr v2.4s, v2.4s, #2
; CHECK-NEXT: mls v0.4s, v2.4s, v1.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 5, i32 5, i32 5, i32 5>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 undef, i32 0, i32 0>
%ret = zext <4 x i1> %cmp to <4 x i32>
ret <4 x i32> %ret
}
define <4 x i32> @test_urem_both_undef(<4 x i32> %X) nounwind readnone {
; CHECK-LABEL: test_urem_both_undef:
; CHECK: // %bb.0:
; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 5, i32 5, i32 undef, i32 5>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 undef, i32 0, i32 0>
%ret = zext <4 x i1> %cmp to <4 x i32>
ret <4 x i32> %ret
}
define <4 x i32> @test_urem_div_even_odd(<4 x i32> %X) nounwind readnone {
; CHECK-LABEL: test_urem_div_even_odd:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI9_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI9_0]
; CHECK-NEXT: adrp x8, .LCPI9_1
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI9_1]
; CHECK-NEXT: umull2 v3.2d, v0.4s, v1.4s
; CHECK-NEXT: umull v1.2d, v0.2s, v1.2s
; CHECK-NEXT: uzp2 v1.4s, v1.4s, v3.4s
; CHECK-NEXT: ushr v1.4s, v1.4s, #2
; CHECK-NEXT: mls v0.4s, v1.4s, v2.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, #0
; CHECK-NEXT: movi v1.4s, #1
; CHECK-NEXT: and v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 5, i32 5, i32 6, i32 6>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 0, i32 0, i32 0>
%ret = zext <4 x i1> %cmp to <4 x i32>
ret <4 x i32> %ret
}
|
