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
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-- | FileCheck %s
declare i4 @llvm.sadd.sat.i4(i4, i4)
declare i8 @llvm.sadd.sat.i8(i8, i8)
declare i16 @llvm.sadd.sat.i16(i16, i16)
declare i32 @llvm.sadd.sat.i32(i32, i32)
declare i64 @llvm.sadd.sat.i64(i64, i64)
declare <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32>, <4 x i32>)
define i32 @func(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: func:
; CHECK: // %bb.0:
; CHECK-NEXT: adds w8, w0, w1
; CHECK-NEXT: mov w9, #2147483647
; CHECK-NEXT: cmp w8, #0 // =0
; CHECK-NEXT: cinv w8, w9, ge
; CHECK-NEXT: adds w9, w0, w1
; CHECK-NEXT: csel w0, w8, w9, vs
; CHECK-NEXT: ret
%tmp = call i32 @llvm.sadd.sat.i32(i32 %x, i32 %y);
ret i32 %tmp;
}
define i64 @func2(i64 %x, i64 %y) nounwind {
; CHECK-LABEL: func2:
; CHECK: // %bb.0:
; CHECK-NEXT: adds x8, x0, x1
; CHECK-NEXT: mov x9, #9223372036854775807
; CHECK-NEXT: cmp x8, #0 // =0
; CHECK-NEXT: cinv x8, x9, ge
; CHECK-NEXT: adds x9, x0, x1
; CHECK-NEXT: csel x0, x8, x9, vs
; CHECK-NEXT: ret
%tmp = call i64 @llvm.sadd.sat.i64(i64 %x, i64 %y);
ret i64 %tmp;
}
define i16 @func16(i16 %x, i16 %y) nounwind {
; CHECK-LABEL: func16:
; CHECK: // %bb.0:
; CHECK-NEXT: sxth w8, w0
; CHECK-NEXT: mov w9, #32767
; CHECK-NEXT: add w8, w8, w1, sxth
; CHECK-NEXT: cmp w8, w9
; CHECK-NEXT: csel w8, w8, w9, lt
; CHECK-NEXT: cmn w8, #8, lsl #12 // =32768
; CHECK-NEXT: mov w9, #-32768
; CHECK-NEXT: csel w0, w8, w9, gt
; CHECK-NEXT: ret
%tmp = call i16 @llvm.sadd.sat.i16(i16 %x, i16 %y);
ret i16 %tmp;
}
define i8 @func8(i8 %x, i8 %y) nounwind {
; CHECK-LABEL: func8:
; CHECK: // %bb.0:
; CHECK-NEXT: sxtb w8, w0
; CHECK-NEXT: add w8, w8, w1, sxtb
; CHECK-NEXT: mov w9, #127
; CHECK-NEXT: cmp w8, #127 // =127
; CHECK-NEXT: csel w8, w8, w9, lt
; CHECK-NEXT: cmn w8, #128 // =128
; CHECK-NEXT: mov w9, #-128
; CHECK-NEXT: csel w0, w8, w9, gt
; CHECK-NEXT: ret
%tmp = call i8 @llvm.sadd.sat.i8(i8 %x, i8 %y);
ret i8 %tmp;
}
define i4 @func3(i4 %x, i4 %y) nounwind {
; CHECK-LABEL: func3:
; CHECK: // %bb.0:
; CHECK-NEXT: lsl w8, w1, #28
; CHECK-NEXT: sbfx w9, w0, #0, #4
; CHECK-NEXT: add w8, w9, w8, asr #28
; CHECK-NEXT: mov w10, #7
; CHECK-NEXT: cmp w8, #7 // =7
; CHECK-NEXT: csel w8, w8, w10, lt
; CHECK-NEXT: cmn w8, #8 // =8
; CHECK-NEXT: mov w9, #-8
; CHECK-NEXT: csel w0, w8, w9, gt
; CHECK-NEXT: ret
%tmp = call i4 @llvm.sadd.sat.i4(i4 %x, i4 %y);
ret i4 %tmp;
}
define <4 x i32> @vec(<4 x i32> %x, <4 x i32> %y) nounwind {
; CHECK-LABEL: vec:
; CHECK: // %bb.0:
; CHECK-NEXT: add v2.4s, v0.4s, v1.4s
; CHECK-NEXT: cmlt v4.4s, v2.4s, #0
; CHECK-NEXT: mvni v3.4s, #128, lsl #24
; CHECK-NEXT: cmlt v1.4s, v1.4s, #0
; CHECK-NEXT: cmgt v0.4s, v0.4s, v2.4s
; CHECK-NEXT: mvn v5.16b, v4.16b
; CHECK-NEXT: bsl v3.16b, v4.16b, v5.16b
; CHECK-NEXT: eor v0.16b, v1.16b, v0.16b
; CHECK-NEXT: bsl v0.16b, v3.16b, v2.16b
; CHECK-NEXT: ret
%tmp = call <4 x i32> @llvm.sadd.sat.v4i32(<4 x i32> %x, <4 x i32> %y);
ret <4 x i32> %tmp;
}
|