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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64 < %s | FileCheck %s
define <16 x i8> @fn1_vector(<16 x i8> %arg) {
; CHECK-LABEL: fn1_vector:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI0_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI0_0]
; CHECK-NEXT: mul v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
entry:
%shl = shl <16 x i8> %arg, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
%mul = mul <16 x i8> %shl, <i8 0, i8 1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>
ret <16 x i8> %mul
}
define <16 x i8> @fn2_vector(<16 x i8> %arg) {
; CHECK-LABEL: fn2_vector:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI1_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI1_0]
; CHECK-NEXT: mul v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
entry:
%mul = mul <16 x i8> %arg, <i8 0, i8 1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>
%shl = shl <16 x i8> %mul, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
ret <16 x i8> %shl
}
define <16 x i8> @fn1_vector_undef(<16 x i8> %arg) {
; CHECK-LABEL: fn1_vector_undef:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI2_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI2_0]
; CHECK-NEXT: mul v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
entry:
%shl = shl <16 x i8> %arg, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
%mul = mul <16 x i8> %shl, <i8 undef, i8 1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>
ret <16 x i8> %mul
}
define <16 x i8> @fn2_vector_undef(<16 x i8> %arg) {
; CHECK-LABEL: fn2_vector_undef:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: adrp x8, .LCPI3_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI3_0]
; CHECK-NEXT: mul v0.16b, v0.16b, v1.16b
; CHECK-NEXT: ret
entry:
%mul = mul <16 x i8> %arg, <i8 undef, i8 1, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>
%shl = shl <16 x i8> %mul, <i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7, i8 7>
ret <16 x i8> %shl
}
define i32 @fn1_scalar(i32 %arg) {
; CHECK-LABEL: fn1_scalar:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov w8, #1664
; CHECK-NEXT: mul w0, w0, w8
; CHECK-NEXT: ret
entry:
%shl = shl i32 %arg, 7
%mul = mul i32 %shl, 13
ret i32 %mul
}
define i32 @fn2_scalar(i32 %arg) {
; CHECK-LABEL: fn2_scalar:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov w8, #1664
; CHECK-NEXT: mul w0, w0, w8
; CHECK-NEXT: ret
entry:
%mul = mul i32 %arg, 13
%shl = shl i32 %mul, 7
ret i32 %shl
}
define i32 @fn1_scalar_undef(i32 %arg) {
; CHECK-LABEL: fn1_scalar_undef:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
entry:
%shl = shl i32 %arg, 7
%mul = mul i32 %shl, undef
ret i32 %mul
}
define i32 @fn2_scalar_undef(i32 %arg) {
; CHECK-LABEL: fn2_scalar_undef:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov w0, wzr
; CHECK-NEXT: ret
entry:
%mul = mul i32 %arg, undef
%shl = shl i32 %mul, 7
ret i32 %shl
}
define i32 @fn1_scalar_opaque(i32 %arg) {
; CHECK-LABEL: fn1_scalar_opaque:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov w8, #13
; CHECK-NEXT: mul w8, w0, w8
; CHECK-NEXT: lsl w0, w8, #7
; CHECK-NEXT: ret
entry:
%bitcast = bitcast i32 13 to i32
%shl = shl i32 %arg, 7
%mul = mul i32 %shl, %bitcast
ret i32 %mul
}
define i32 @fn2_scalar_opaque(i32 %arg) {
; CHECK-LABEL: fn2_scalar_opaque:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: mov w8, #13
; CHECK-NEXT: mul w8, w0, w8
; CHECK-NEXT: lsl w0, w8, #7
; CHECK-NEXT: ret
entry:
%bitcast = bitcast i32 13 to i32
%mul = mul i32 %arg, %bitcast
%shl = shl i32 %mul, 7
ret i32 %shl
}
|
