urem-seteq-vec-nonzero.ll
4.04 KB
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
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-unknown-linux-gnu < %s | FileCheck %s
define <4 x i1> @t32_3(<4 x i32> %X) nounwind {
; CHECK-LABEL: t32_3:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI0_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI0_0]
; CHECK-NEXT: adrp x9, .LCPI0_1
; CHECK-NEXT: mov w8, #43691
; CHECK-NEXT: ldr q2, [x9, :lo12:.LCPI0_1]
; CHECK-NEXT: movk w8, #43690, lsl #16
; CHECK-NEXT: sub v0.4s, v0.4s, v1.4s
; CHECK-NEXT: dup v1.4s, w8
; CHECK-NEXT: mul v0.4s, v0.4s, v1.4s
; CHECK-NEXT: cmhs v0.4s, v2.4s, v0.4s
; CHECK-NEXT: xtn v0.4h, v0.4s
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 3, i32 3, i32 3, i32 3>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 1, i32 2, i32 2>
ret <4 x i1> %cmp
}
define <4 x i1> @t32_5(<4 x i32> %X) nounwind {
; CHECK-LABEL: t32_5:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI1_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI1_0]
; CHECK-NEXT: mov w8, #52429
; CHECK-NEXT: movk w8, #52428, lsl #16
; CHECK-NEXT: mov w9, #13106
; CHECK-NEXT: movk w9, #13107, lsl #16
; CHECK-NEXT: dup v2.4s, w8
; CHECK-NEXT: sub v0.4s, v0.4s, v1.4s
; CHECK-NEXT: mul v0.4s, v0.4s, v2.4s
; CHECK-NEXT: dup v1.4s, w9
; CHECK-NEXT: cmhs v0.4s, v1.4s, v0.4s
; CHECK-NEXT: xtn v0.4h, v0.4s
; 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 1, i32 2, i32 3, i32 4>
ret <4 x i1> %cmp
}
define <4 x i1> @t32_6_part0(<4 x i32> %X) nounwind {
; CHECK-LABEL: t32_6_part0:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #43691
; CHECK-NEXT: movk w8, #43690, lsl #16
; CHECK-NEXT: adrp x9, .LCPI2_0
; CHECK-NEXT: dup v1.4s, w8
; CHECK-NEXT: ldr q2, [x9, :lo12:.LCPI2_0]
; 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: movi v3.4s, #6
; CHECK-NEXT: mls v0.4s, v1.4s, v3.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, v2.4s
; CHECK-NEXT: xtn v0.4h, v0.4s
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 6, i32 6, i32 6, i32 6>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 1, i32 2, i32 3>
ret <4 x i1> %cmp
}
define <4 x i1> @t32_6_part1(<4 x i32> %X) nounwind {
; CHECK-LABEL: t32_6_part1:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #43691
; CHECK-NEXT: movk w8, #43690, lsl #16
; CHECK-NEXT: adrp x9, .LCPI3_0
; CHECK-NEXT: dup v1.4s, w8
; CHECK-NEXT: ldr q2, [x9, :lo12:.LCPI3_0]
; 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: movi v3.4s, #6
; CHECK-NEXT: mls v0.4s, v1.4s, v3.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, v2.4s
; CHECK-NEXT: xtn v0.4h, v0.4s
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 6, i32 6, i32 6, i32 6>
%cmp = icmp eq <4 x i32> %urem, <i32 4, i32 5, i32 0, i32 0>
ret <4 x i1> %cmp
}
define <4 x i1> @t32_tautological(<4 x i32> %X) nounwind {
; CHECK-LABEL: t32_tautological:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI4_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI4_0]
; CHECK-NEXT: adrp x8, .LCPI4_1
; CHECK-NEXT: ldr q2, [x8, :lo12:.LCPI4_1]
; CHECK-NEXT: adrp x8, .LCPI4_2
; CHECK-NEXT: ldr q3, [x8, :lo12:.LCPI4_2]
; CHECK-NEXT: adrp x8, .LCPI4_3
; CHECK-NEXT: ldr q4, [x8, :lo12:.LCPI4_3]
; CHECK-NEXT: adrp x8, .LCPI4_4
; CHECK-NEXT: umull2 v5.2d, v0.4s, v1.4s
; CHECK-NEXT: umull v1.2d, v0.2s, v1.2s
; CHECK-NEXT: neg v2.4s, v2.4s
; CHECK-NEXT: uzp2 v1.4s, v1.4s, v5.4s
; CHECK-NEXT: ldr q5, [x8, :lo12:.LCPI4_4]
; CHECK-NEXT: ushl v1.4s, v1.4s, v2.4s
; CHECK-NEXT: bsl v3.16b, v0.16b, v1.16b
; CHECK-NEXT: mls v0.4s, v3.4s, v4.4s
; CHECK-NEXT: cmeq v0.4s, v0.4s, v5.4s
; CHECK-NEXT: xtn v0.4h, v0.4s
; CHECK-NEXT: ret
%urem = urem <4 x i32> %X, <i32 1, i32 1, i32 2, i32 3>
%cmp = icmp eq <4 x i32> %urem, <i32 0, i32 1, i32 2, i32 2>
ret <4 x i1> %cmp
}