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
|
; 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 i1 @andv_nxv32i1(<vscale x 32 x i1> %a) {
; CHECK-LABEL: andv_nxv32i1:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p2.b
; CHECK-NEXT: and p0.b, p0/z, p0.b, p1.b
; CHECK-NEXT: nots p0.b, p2/z, p0.b
; CHECK-NEXT: cset w0, eq
; CHECK-NEXT: ret
%res = call i1 @llvm.vector.reduce.and.nxv32i1(<vscale x 32 x i1> %a)
ret i1 %res
}
define i1 @andv_nxv64i1(<vscale x 64 x i1> %a) {
; CHECK-LABEL: andv_nxv64i1:
; CHECK: // %bb.0:
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w29, -16
; CHECK-NEXT: addvl sp, sp, #-1
; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
; CHECK-NEXT: and p1.b, p1/z, p1.b, p3.b
; CHECK-NEXT: and p0.b, p0/z, p0.b, p2.b
; CHECK-NEXT: str p4, [sp, #7, mul vl] // 2-byte Folded Spill
; CHECK-NEXT: ptrue p4.b
; CHECK-NEXT: and p0.b, p0/z, p0.b, p1.b
; CHECK-NEXT: nots p0.b, p4/z, p0.b
; CHECK-NEXT: ldr p4, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT: cset w0, eq
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%res = call i1 @llvm.vector.reduce.and.nxv64i1(<vscale x 64 x i1> %a)
ret i1 %res
}
; ORV
define i1 @orv_nxv32i1(<vscale x 32 x i1> %a) {
; CHECK-LABEL: orv_nxv32i1:
; CHECK: // %bb.0:
; CHECK-NEXT: sel p0.b, p0, p0.b, p1.b
; CHECK-NEXT: ptest p0, p0.b
; CHECK-NEXT: cset w0, ne
; CHECK-NEXT: ret
%res = call i1 @llvm.vector.reduce.or.nxv32i1(<vscale x 32 x i1> %a)
ret i1 %res
}
; XORV
define i1 @xorv_nxv32i1(<vscale x 32 x i1> %a) {
; CHECK-LABEL: xorv_nxv32i1:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p2.b
; CHECK-NEXT: eor p0.b, p2/z, p0.b, p1.b
; CHECK-NEXT: cntp x8, p2, p0.b
; CHECK-NEXT: and w0, w8, #0x1
; CHECK-NEXT: ret
%res = call i1 @llvm.vector.reduce.xor.nxv32i1(<vscale x 32 x i1> %a)
ret i1 %res
}
; SMAXV
define i1 @smaxv_nxv32i1(<vscale x 32 x i1> %a) {
; CHECK-LABEL: smaxv_nxv32i1:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p2.b
; CHECK-NEXT: and p0.b, p0/z, p0.b, p1.b
; CHECK-NEXT: nots p0.b, p2/z, p0.b
; CHECK-NEXT: cset w0, eq
; CHECK-NEXT: ret
%res = call i1 @llvm.vector.reduce.smax.nxv32i1(<vscale x 32 x i1> %a)
ret i1 %res
}
; SMINV
define i1 @sminv_nxv32i1(<vscale x 32 x i1> %a) {
; CHECK-LABEL: sminv_nxv32i1:
; CHECK: // %bb.0:
; CHECK-NEXT: sel p0.b, p0, p0.b, p1.b
; CHECK-NEXT: ptest p0, p0.b
; CHECK-NEXT: cset w0, ne
; CHECK-NEXT: ret
%res = call i1 @llvm.vector.reduce.smin.nxv32i1(<vscale x 32 x i1> %a)
ret i1 %res
}
; UMAXV
define i1 @umaxv_nxv32i1(<vscale x 32 x i1> %a) {
; CHECK-LABEL: umaxv_nxv32i1:
; CHECK: // %bb.0:
; CHECK-NEXT: sel p0.b, p0, p0.b, p1.b
; CHECK-NEXT: ptest p0, p0.b
; CHECK-NEXT: cset w0, ne
; CHECK-NEXT: ret
%res = call i1 @llvm.vector.reduce.umax.nxv32i1(<vscale x 32 x i1> %a)
ret i1 %res
}
; UMINV
define i1 @uminv_nxv32i1(<vscale x 32 x i1> %a) {
; CHECK-LABEL: uminv_nxv32i1:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p2.b
; CHECK-NEXT: and p0.b, p0/z, p0.b, p1.b
; CHECK-NEXT: nots p0.b, p2/z, p0.b
; CHECK-NEXT: cset w0, eq
; CHECK-NEXT: ret
%res = call i1 @llvm.vector.reduce.umin.nxv32i1(<vscale x 32 x i1> %a)
ret i1 %res
}
declare i1 @llvm.vector.reduce.and.nxv32i1(<vscale x 32 x i1>)
declare i1 @llvm.vector.reduce.and.nxv64i1(<vscale x 64 x i1>)
declare i1 @llvm.vector.reduce.or.nxv32i1(<vscale x 32 x i1>)
declare i1 @llvm.vector.reduce.xor.nxv32i1(<vscale x 32 x i1>)
declare i1 @llvm.vector.reduce.smax.nxv32i1(<vscale x 32 x i1>)
declare i1 @llvm.vector.reduce.smin.nxv32i1(<vscale x 32 x i1>)
declare i1 @llvm.vector.reduce.umax.nxv32i1(<vscale x 32 x i1>)
declare i1 @llvm.vector.reduce.umin.nxv32i1(<vscale x 32 x i1>)
|
