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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
define i8 @uaddv_zexti8_nxv16i1(<vscale x 16 x i1> %v) {
; CHECK-LABEL: uaddv_zexti8_nxv16i1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cntp x0, p0, p0.b
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
entry:
%3 = zext <vscale x 16 x i1> %v to <vscale x 16 x i8>
%4 = tail call i8 @llvm.vector.reduce.add.nxv16i8(<vscale x 16 x i8> %3)
ret i8 %4
}
define i8 @uaddv_zexti8_nxv8i1(<vscale x 8 x i1> %v) {
; CHECK-LABEL: uaddv_zexti8_nxv8i1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cntp x0, p0, p0.h
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
entry:
%3 = zext <vscale x 8 x i1> %v to <vscale x 8 x i8>
%4 = tail call i8 @llvm.vector.reduce.add.nxv8i8(<vscale x 8 x i8> %3)
ret i8 %4
}
define i16 @uaddv_zexti16_nxv8i1(<vscale x 8 x i1> %v) {
; CHECK-LABEL: uaddv_zexti16_nxv8i1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cntp x0, p0, p0.h
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
entry:
%3 = zext <vscale x 8 x i1> %v to <vscale x 8 x i16>
%4 = tail call i16 @llvm.vector.reduce.add.nxv8i16(<vscale x 8 x i16> %3)
ret i16 %4
}
define i8 @uaddv_zexti8_nxv4i1(<vscale x 4 x i1> %v) {
; CHECK-LABEL: uaddv_zexti8_nxv4i1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cntp x0, p0, p0.s
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
entry:
%3 = zext <vscale x 4 x i1> %v to <vscale x 4 x i8>
%4 = tail call i8 @llvm.vector.reduce.add.nxv4i8(<vscale x 4 x i8> %3)
ret i8 %4
}
define i16 @uaddv_zexti16_nxv4i1(<vscale x 4 x i1> %v) {
; CHECK-LABEL: uaddv_zexti16_nxv4i1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cntp x0, p0, p0.s
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
entry:
%3 = zext <vscale x 4 x i1> %v to <vscale x 4 x i16>
%4 = tail call i16 @llvm.vector.reduce.add.nxv4i16(<vscale x 4 x i16> %3)
ret i16 %4
}
define i32 @uaddv_zexti32_nxv4i1(<vscale x 4 x i1> %v) {
; CHECK-LABEL: uaddv_zexti32_nxv4i1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cntp x0, p0, p0.s
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
entry:
%3 = zext <vscale x 4 x i1> %v to <vscale x 4 x i32>
%4 = tail call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %3)
ret i32 %4
}
define i8 @uaddv_zexti8_nxv2i1(<vscale x 2 x i1> %v) {
; CHECK-LABEL: uaddv_zexti8_nxv2i1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cntp x0, p0, p0.d
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
entry:
%3 = zext <vscale x 2 x i1> %v to <vscale x 2 x i8>
%4 = tail call i8 @llvm.vector.reduce.add.nxv2i8(<vscale x 2 x i8> %3)
ret i8 %4
}
define i16 @uaddv_zexti16_nxv2i1(<vscale x 2 x i1> %v) {
; CHECK-LABEL: uaddv_zexti16_nxv2i1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cntp x0, p0, p0.d
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
entry:
%3 = zext <vscale x 2 x i1> %v to <vscale x 2 x i16>
%4 = tail call i16 @llvm.vector.reduce.add.nxv2i16(<vscale x 2 x i16> %3)
ret i16 %4
}
define i32 @uaddv_zexti32_nxv2i1(<vscale x 2 x i1> %v) {
; CHECK-LABEL: uaddv_zexti32_nxv2i1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cntp x0, p0, p0.d
; CHECK-NEXT: // kill: def $w0 killed $w0 killed $x0
; CHECK-NEXT: ret
entry:
%3 = zext <vscale x 2 x i1> %v to <vscale x 2 x i32>
%4 = tail call i32 @llvm.vector.reduce.add.nxv2i32(<vscale x 2 x i32> %3)
ret i32 %4
}
define i64 @uaddv_zexti64_nxv2i1(<vscale x 2 x i1> %v) {
; CHECK-LABEL: uaddv_zexti64_nxv2i1:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: cntp x0, p0, p0.d
; CHECK-NEXT: ret
entry:
%3 = zext <vscale x 2 x i1> %v to <vscale x 2 x i64>
%4 = tail call i64 @llvm.vector.reduce.add.nxv2i64(<vscale x 2 x i64> %3)
ret i64 %4
}
declare i8 @llvm.vector.reduce.add.nxv16i8(<vscale x 16 x i8>)
declare i8 @llvm.vector.reduce.add.nxv8i8(<vscale x 8 x i8>)
declare i16 @llvm.vector.reduce.add.nxv8i16(<vscale x 8 x i16>)
declare i8 @llvm.vector.reduce.add.nxv4i8(<vscale x 4 x i8>)
declare i16 @llvm.vector.reduce.add.nxv4i16(<vscale x 4 x i16>)
declare i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32>)
declare i8 @llvm.vector.reduce.add.nxv2i8(<vscale x 2 x i8>)
declare i16 @llvm.vector.reduce.add.nxv2i16(<vscale x 2 x i16>)
declare i32 @llvm.vector.reduce.add.nxv2i32(<vscale x 2 x i32>)
declare i64 @llvm.vector.reduce.add.nxv2i64(<vscale x 2 x i64>)
|
