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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-linux-gnu | FileCheck %s
define i32 @func(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: func:
; CHECK: // %bb.0:
; CHECK-NEXT: smull x8, w0, w1
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: extr w0, w9, w8, #2
; CHECK-NEXT: ret
%tmp = call i32 @llvm.smul.fix.i32(i32 %x, i32 %y, i32 2)
ret i32 %tmp
}
define i64 @func2(i64 %x, i64 %y) {
; CHECK-LABEL: func2:
; CHECK: // %bb.0:
; CHECK-NEXT: mul x8, x0, x1
; CHECK-NEXT: smulh x9, x0, x1
; CHECK-NEXT: extr x0, x9, x8, #2
; CHECK-NEXT: ret
%tmp = call i64 @llvm.smul.fix.i64(i64 %x, i64 %y, i32 2)
ret i64 %tmp
}
define i4 @func3(i4 %x, i4 %y) nounwind {
; CHECK-LABEL: func3:
; CHECK: // %bb.0:
; CHECK-NEXT: sbfx w8, w1, #0, #4
; CHECK-NEXT: sbfx w9, w0, #0, #4
; CHECK-NEXT: smull x8, w9, w8
; CHECK-NEXT: lsr x9, x8, #32
; CHECK-NEXT: extr w0, w9, w8, #2
; CHECK-NEXT: ret
%tmp = call i4 @llvm.smul.fix.i4(i4 %x, i4 %y, i32 2)
ret i4 %tmp
}
;; These result in regular integer multiplication
define i32 @func4(i32 %x, i32 %y) nounwind {
; CHECK-LABEL: func4:
; CHECK: // %bb.0:
; CHECK-NEXT: mul w0, w0, w1
; CHECK-NEXT: ret
%tmp = call i32 @llvm.smul.fix.i32(i32 %x, i32 %y, i32 0)
ret i32 %tmp
}
define i64 @func5(i64 %x, i64 %y) {
; CHECK-LABEL: func5:
; CHECK: // %bb.0:
; CHECK-NEXT: mul x0, x0, x1
; CHECK-NEXT: ret
%tmp = call i64 @llvm.smul.fix.i64(i64 %x, i64 %y, i32 0)
ret i64 %tmp
}
define i4 @func6(i4 %x, i4 %y) nounwind {
; CHECK-LABEL: func6:
; CHECK: // %bb.0:
; CHECK-NEXT: sbfx w8, w1, #0, #4
; CHECK-NEXT: sbfx w9, w0, #0, #4
; CHECK-NEXT: mul w0, w9, w8
; CHECK-NEXT: ret
%tmp = call i4 @llvm.smul.fix.i4(i4 %x, i4 %y, i32 0)
ret i4 %tmp
}
define i64 @func7(i64 %x, i64 %y) nounwind {
; CHECK-LABEL: func7:
; CHECK: // %bb.0:
; CHECK-NEXT: mul x8, x0, x1
; CHECK-NEXT: smulh x9, x0, x1
; CHECK-NEXT: extr x0, x9, x8, #32
; CHECK-NEXT: ret
%tmp = call i64 @llvm.smul.fix.i64(i64 %x, i64 %y, i32 32)
ret i64 %tmp
}
define i64 @func8(i64 %x, i64 %y) nounwind {
; CHECK-LABEL: func8:
; CHECK: // %bb.0:
; CHECK-NEXT: mul x8, x0, x1
; CHECK-NEXT: smulh x9, x0, x1
; CHECK-NEXT: extr x0, x9, x8, #63
; CHECK-NEXT: ret
%tmp = call i64 @llvm.smul.fix.i64(i64 %x, i64 %y, i32 63)
ret i64 %tmp
}
define <2 x i32> @vec(<2 x i32> %x, <2 x i32> %y) nounwind {
; CHECK-LABEL: vec:
; CHECK: // %bb.0:
; CHECK-NEXT: mul v0.2s, v0.2s, v1.2s
; CHECK-NEXT: ret
%tmp = call <2 x i32> @llvm.smul.fix.v2i32(<2 x i32> %x, <2 x i32> %y, i32 0)
ret <2 x i32> %tmp
}
define <4 x i32> @vec2(<4 x i32> %x, <4 x i32> %y) nounwind {
; CHECK-LABEL: vec2:
; CHECK: // %bb.0:
; CHECK-NEXT: mul v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
%tmp = call <4 x i32> @llvm.smul.fix.v4i32(<4 x i32> %x, <4 x i32> %y, i32 0)
ret <4 x i32> %tmp
}
define <4 x i64> @vec3(<4 x i64> %x, <4 x i64> %y) nounwind {
; CHECK-LABEL: vec3:
; CHECK: // %bb.0:
; CHECK-NEXT: mov x8, v2.d[1]
; CHECK-NEXT: mov x9, v0.d[1]
; CHECK-NEXT: fmov x10, d2
; CHECK-NEXT: fmov x11, d0
; CHECK-NEXT: mov x14, v3.d[1]
; CHECK-NEXT: mov x15, v1.d[1]
; CHECK-NEXT: mul x12, x11, x10
; CHECK-NEXT: mul x13, x9, x8
; CHECK-NEXT: smulh x8, x9, x8
; CHECK-NEXT: smulh x9, x11, x10
; CHECK-NEXT: fmov x10, d3
; CHECK-NEXT: fmov x11, d1
; CHECK-NEXT: mul x16, x11, x10
; CHECK-NEXT: extr x8, x8, x13, #32
; CHECK-NEXT: smulh x10, x11, x10
; CHECK-NEXT: extr x9, x9, x12, #32
; CHECK-NEXT: mul x11, x15, x14
; CHECK-NEXT: fmov d0, x9
; CHECK-NEXT: smulh x14, x15, x14
; CHECK-NEXT: extr x10, x10, x16, #32
; CHECK-NEXT: mov v0.d[1], x8
; CHECK-NEXT: fmov d1, x10
; CHECK-NEXT: extr x11, x14, x11, #32
; CHECK-NEXT: mov v1.d[1], x11
; CHECK-NEXT: ret
%tmp = call <4 x i64> @llvm.smul.fix.v4i64(<4 x i64> %x, <4 x i64> %y, i32 32)
ret <4 x i64> %tmp
}
|
