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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64 < %s | FileCheck %s
; Check that we optimize out AND instructions and ADD/SUB instructions
; modulo the shift size to take advantage of the implicit mod done on
; the shift amount value by the variable shift/rotate instructions.
define i32 @test1(i32 %x, i64 %y) {
; CHECK-LABEL: test1:
; CHECK: // %bb.0:
; CHECK-NEXT: lsr w0, w0, w1
; CHECK-NEXT: ret
%sh_prom = trunc i64 %y to i32
%shr = lshr i32 %x, %sh_prom
ret i32 %shr
}
define i64 @test2(i32 %x, i64 %y) {
; CHECK-LABEL: test2:
; CHECK: // %bb.0:
; CHECK-NEXT: neg w8, w0
; CHECK-NEXT: asr x0, x1, x8
; CHECK-NEXT: ret
%sub9 = sub nsw i32 64, %x
%sh_prom12.i = zext i32 %sub9 to i64
%shr.i = ashr i64 %y, %sh_prom12.i
ret i64 %shr.i
}
define i64 @test3(i64 %x, i64 %y) {
; CHECK-LABEL: test3:
; CHECK: // %bb.0:
; CHECK-NEXT: lsl x0, x1, x0
; CHECK-NEXT: ret
%add = add nsw i64 64, %x
%shl = shl i64 %y, %add
ret i64 %shl
}
define i64 @test4(i64 %y, i32 %s) {
; CHECK-LABEL: test4:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $w1 killed $w1 def $x1
; CHECK-NEXT: asr x0, x0, x1
; CHECK-NEXT: ret
entry:
%sh_prom = zext i32 %s to i64
%shr = ashr i64 %y, %sh_prom
ret i64 %shr
}
define i64 @test5(i64 %y, i32 %s) {
; CHECK-LABEL: test5:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $w1 killed $w1 def $x1
; CHECK-NEXT: asr x0, x0, x1
; CHECK-NEXT: ret
entry:
%sh_prom = sext i32 %s to i64
%shr = ashr i64 %y, %sh_prom
ret i64 %shr
}
define i64 @test6(i64 %y, i32 %s) {
; CHECK-LABEL: test6:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: // kill: def $w1 killed $w1 def $x1
; CHECK-NEXT: lsl x0, x0, x1
; CHECK-NEXT: ret
entry:
%sh_prom = sext i32 %s to i64
%shr = shl i64 %y, %sh_prom
ret i64 %shr
}
; PR42644 - https://bugs.llvm.org/show_bug.cgi?id=42644
define i64 @ashr_add_shl_i32(i64 %r) {
; CHECK-LABEL: ashr_add_shl_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: add w8, w0, #1
; CHECK-NEXT: sxtw x0, w8
; CHECK-NEXT: ret
%conv = shl i64 %r, 32
%sext = add i64 %conv, 4294967296
%conv1 = ashr i64 %sext, 32
ret i64 %conv1
}
define i64 @ashr_add_shl_i8(i64 %r) {
; CHECK-LABEL: ashr_add_shl_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: add w8, w0, #1
; CHECK-NEXT: sxtb x0, w8
; CHECK-NEXT: ret
%conv = shl i64 %r, 56
%sext = add i64 %conv, 72057594037927936
%conv1 = ashr i64 %sext, 56
ret i64 %conv1
}
define <4 x i32> @ashr_add_shl_v4i8(<4 x i32> %r) {
; CHECK-LABEL: ashr_add_shl_v4i8:
; CHECK: // %bb.0:
; CHECK-NEXT: movi v1.4s, #1, lsl #24
; CHECK-NEXT: shl v0.4s, v0.4s, #24
; CHECK-NEXT: add v0.4s, v0.4s, v1.4s
; CHECK-NEXT: sshr v0.4s, v0.4s, #24
; CHECK-NEXT: ret
%conv = shl <4 x i32> %r, <i32 24, i32 24, i32 24, i32 24>
%sext = add <4 x i32> %conv, <i32 16777216, i32 16777216, i32 16777216, i32 16777216>
%conv1 = ashr <4 x i32> %sext, <i32 24, i32 24, i32 24, i32 24>
ret <4 x i32> %conv1
}
define i64 @ashr_add_shl_i36(i64 %r) {
; CHECK-LABEL: ashr_add_shl_i36:
; CHECK: // %bb.0:
; CHECK-NEXT: sbfx x0, x0, #0, #28
; CHECK-NEXT: ret
%conv = shl i64 %r, 36
%sext = add i64 %conv, 4294967296
%conv1 = ashr i64 %sext, 36
ret i64 %conv1
}
define i64 @ashr_add_shl_mismatch_shifts1(i64 %r) {
; CHECK-LABEL: ashr_add_shl_mismatch_shifts1:
; CHECK: // %bb.0:
; CHECK-NEXT: mov x8, #4294967296
; CHECK-NEXT: add x8, x8, x0, lsl #8
; CHECK-NEXT: asr x0, x8, #32
; CHECK-NEXT: ret
%conv = shl i64 %r, 8
%sext = add i64 %conv, 4294967296
%conv1 = ashr i64 %sext, 32
ret i64 %conv1
}
define i64 @ashr_add_shl_mismatch_shifts2(i64 %r) {
; CHECK-LABEL: ashr_add_shl_mismatch_shifts2:
; CHECK: // %bb.0:
; CHECK-NEXT: mov x8, #4294967296
; CHECK-NEXT: add x8, x8, x0, lsr #8
; CHECK-NEXT: lsr x0, x8, #8
; CHECK-NEXT: ret
%conv = lshr i64 %r, 8
%sext = add i64 %conv, 4294967296
%conv1 = ashr i64 %sext, 8
ret i64 %conv1
}
|
