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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s | FileCheck %s
target triple = "aarch64-unknown-linux-gnu"
; INCP
define i64 @cntp_add_nxv16i1(i64 %x, <vscale x 16 x i1> %pg) #0 {
; CHECK-LABEL: cntp_add_nxv16i1:
; CHECK: // %bb.0:
; CHECK-NEXT: incp x0, p0.b
; CHECK-NEXT: ret
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = tail call i64 @llvm.aarch64.sve.cntp.nxv16i1(<vscale x 16 x i1> %1, <vscale x 16 x i1> %pg)
%add = add i64 %2, %x
ret i64 %add
}
define i64 @cntp_add_nxv8i1(i64 %x, <vscale x 8 x i1> %pg) #0 {
; CHECK-LABEL: cntp_add_nxv8i1:
; CHECK: // %bb.0:
; CHECK-NEXT: incp x0, p0.h
; CHECK-NEXT: ret
%1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
%2 = tail call i64 @llvm.aarch64.sve.cntp.nxv8i1(<vscale x 8 x i1> %1, <vscale x 8 x i1> %pg)
%add = add i64 %2, %x
ret i64 %add
}
define i64 @cntp_add_nxv4i1(i64 %x, <vscale x 4 x i1> %pg) #0 {
; CHECK-LABEL: cntp_add_nxv4i1:
; CHECK: // %bb.0:
; CHECK-NEXT: incp x0, p0.s
; CHECK-NEXT: ret
%1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = tail call i64 @llvm.aarch64.sve.cntp.nxv4i1(<vscale x 4 x i1> %1, <vscale x 4 x i1> %pg)
%add = add i64 %2, %x
ret i64 %add
}
define i64 @cntp_add_nxv2i1(i64 %x, <vscale x 2 x i1> %pg) #0 {
; CHECK-LABEL: cntp_add_nxv2i1:
; CHECK: // %bb.0:
; CHECK-NEXT: incp x0, p0.d
; CHECK-NEXT: ret
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call i64 @llvm.aarch64.sve.cntp.nxv2i1(<vscale x 2 x i1> %1, <vscale x 2 x i1> %pg)
%add = add i64 %2, %x
ret i64 %add
}
define i64 @cntp_add_all_active_nxv8i1(i64 %x, <vscale x 8 x i1> %pg) #0 {
; CHECK-LABEL: cntp_add_all_active_nxv8i1:
; CHECK: // %bb.0:
; CHECK-NEXT: incp x0, p0.h
; CHECK-NEXT: ret
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %1)
%3 = tail call i64 @llvm.aarch64.sve.cntp.nxv8i1(<vscale x 8 x i1> %2, <vscale x 8 x i1> %pg)
%add = add i64 %3, %x
ret i64 %add
}
define i64 @cntp_add_nxv2i1_oneuse(i64 %x, <vscale x 2 x i1> %pg) #0 {
; CHECK-LABEL: cntp_add_nxv2i1_oneuse:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p1.d
; CHECK-NEXT: cntp x8, p1, p0.d
; CHECK-NEXT: add x9, x8, x0
; CHECK-NEXT: madd x0, x8, x0, x9
; CHECK-NEXT: ret
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call i64 @llvm.aarch64.sve.cntp.nxv2i1(<vscale x 2 x i1> %1, <vscale x 2 x i1> %pg)
%add = add i64 %2, %x
%mul = mul i64 %2, %x
%res = add i64 %add, %mul
ret i64 %res
}
; DECP
define i64 @cntp_sub_nxv16i1(i64 %x, <vscale x 16 x i1> %pg) #0 {
; CHECK-LABEL: cntp_sub_nxv16i1:
; CHECK: // %bb.0:
; CHECK-NEXT: decp x0, p0.b
; CHECK-NEXT: ret
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = tail call i64 @llvm.aarch64.sve.cntp.nxv16i1(<vscale x 16 x i1> %1, <vscale x 16 x i1> %pg)
%sub = sub i64 %x, %2
ret i64 %sub
}
define i64 @cntp_sub_nxv8i1(i64 %x, <vscale x 8 x i1> %pg) #0 {
; CHECK-LABEL: cntp_sub_nxv8i1:
; CHECK: // %bb.0:
; CHECK-NEXT: decp x0, p0.h
; CHECK-NEXT: ret
%1 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32 31)
%2 = tail call i64 @llvm.aarch64.sve.cntp.nxv8i1(<vscale x 8 x i1> %1, <vscale x 8 x i1> %pg)
%sub = sub i64 %x, %2
ret i64 %sub
}
define i64 @cntp_sub_nxv4i1(i64 %x, <vscale x 4 x i1> %pg) #0 {
; CHECK-LABEL: cntp_sub_nxv4i1:
; CHECK: // %bb.0:
; CHECK-NEXT: decp x0, p0.s
; CHECK-NEXT: ret
%1 = tail call <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32 31)
%2 = tail call i64 @llvm.aarch64.sve.cntp.nxv4i1(<vscale x 4 x i1> %1, <vscale x 4 x i1> %pg)
%sub = sub i64 %x, %2
ret i64 %sub
}
define i64 @cntp_sub_nxv2i1(i64 %x, <vscale x 2 x i1> %pg) #0 {
; CHECK-LABEL: cntp_sub_nxv2i1:
; CHECK: // %bb.0:
; CHECK-NEXT: decp x0, p0.d
; CHECK-NEXT: ret
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call i64 @llvm.aarch64.sve.cntp.nxv2i1(<vscale x 2 x i1> %1, <vscale x 2 x i1> %pg)
%sub = sub i64 %x, %2
ret i64 %sub
}
define i64 @cntp_sub_all_active_nxv8i1(i64 %x, <vscale x 8 x i1> %pg) #0 {
; CHECK-LABEL: cntp_sub_all_active_nxv8i1:
; CHECK: // %bb.0:
; CHECK-NEXT: decp x0, p0.h
; CHECK-NEXT: ret
%1 = tail call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
%2 = tail call <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1> %1)
%3 = tail call i64 @llvm.aarch64.sve.cntp.nxv8i1(<vscale x 8 x i1> %2, <vscale x 8 x i1> %pg)
%sub = sub i64 %x, %3
ret i64 %sub
}
define i64 @cntp_sub_nxv2i1_multiuse(i64 %x, <vscale x 2 x i1> %pg) #0 {
; CHECK-LABEL: cntp_sub_nxv2i1_multiuse:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p1.d
; CHECK-NEXT: cntp x8, p1, p0.d
; CHECK-NEXT: sub x9, x8, x0
; CHECK-NEXT: madd x0, x8, x0, x9
; CHECK-NEXT: ret
%1 = tail call <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32 31)
%2 = tail call i64 @llvm.aarch64.sve.cntp.nxv2i1(<vscale x 2 x i1> %1, <vscale x 2 x i1> %pg)
%add = sub i64 %2, %x
%mul = mul i64 %2, %x
%res = add i64 %add, %mul
ret i64 %res
}
declare <vscale x 8 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv8i1(<vscale x 16 x i1>)
declare <vscale x 4 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv4i1(<vscale x 16 x i1>)
declare <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1>)
declare <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32)
declare <vscale x 8 x i1> @llvm.aarch64.sve.ptrue.nxv8i1(i32)
declare <vscale x 4 x i1> @llvm.aarch64.sve.ptrue.nxv4i1(i32)
declare <vscale x 2 x i1> @llvm.aarch64.sve.ptrue.nxv2i1(i32)
declare i64 @llvm.aarch64.sve.cntp.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>)
declare i64 @llvm.aarch64.sve.cntp.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>)
declare i64 @llvm.aarch64.sve.cntp.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>)
declare i64 @llvm.aarch64.sve.cntp.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>)
attributes #0 = { "target-features"="+sve" }
|
