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
170
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=armv7 %s -o - | FileCheck %s
; Optimize expanded SRL/SHL used as an input of
; SETCC comparing it with zero by removing rotation.
;
; See https://bugs.llvm.org/show_bug.cgi?id=50197
define i64 @opt_setcc_lt_power_of_2(i64 %a) nounwind {
; CHECK-LABEL: opt_setcc_lt_power_of_2:
; CHECK: @ %bb.0:
; CHECK-NEXT: .LBB0_1: @ %loop
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: adds r0, r0, #1
; CHECK-NEXT: adc r1, r1, #0
; CHECK-NEXT: lsr r2, r0, #16
; CHECK-NEXT: orr r2, r2, r1, lsl #16
; CHECK-NEXT: orr r2, r2, r1, lsr #16
; CHECK-NEXT: cmp r2, #0
; CHECK-NEXT: bne .LBB0_1
; CHECK-NEXT: @ %bb.2: @ %exit
; CHECK-NEXT: bx lr
br label %loop
loop:
%phi.a = phi i64 [ %a, %0 ], [ %inc, %loop ]
%inc = add i64 %phi.a, 1
%cmp = icmp ult i64 %inc, 65536
br i1 %cmp, label %exit, label %loop
exit:
ret i64 %inc
}
define i1 @opt_setcc_srl_eq_zero(i64 %a) nounwind {
; CHECK-LABEL: opt_setcc_srl_eq_zero:
; CHECK: @ %bb.0:
; CHECK-NEXT: lsr r0, r0, #17
; CHECK-NEXT: orr r0, r0, r1, lsl #15
; CHECK-NEXT: orr r0, r0, r1, lsr #17
; CHECK-NEXT: clz r0, r0
; CHECK-NEXT: lsr r0, r0, #5
; CHECK-NEXT: bx lr
%srl = lshr i64 %a, 17
%cmp = icmp eq i64 %srl, 0
ret i1 %cmp
}
define i1 @opt_setcc_srl_ne_zero(i64 %a) nounwind {
; CHECK-LABEL: opt_setcc_srl_ne_zero:
; CHECK: @ %bb.0:
; CHECK-NEXT: lsr r0, r0, #17
; CHECK-NEXT: orr r0, r0, r1, lsl #15
; CHECK-NEXT: orr r0, r0, r1, lsr #17
; CHECK-NEXT: cmp r0, #0
; CHECK-NEXT: movwne r0, #1
; CHECK-NEXT: bx lr
%srl = lshr i64 %a, 17
%cmp = icmp ne i64 %srl, 0
ret i1 %cmp
}
define i1 @opt_setcc_shl_eq_zero(i64 %a) nounwind {
; CHECK-LABEL: opt_setcc_shl_eq_zero:
; CHECK: @ %bb.0:
; CHECK-NEXT: lsl r1, r1, #17
; CHECK-NEXT: orr r1, r1, r0, lsr #15
; CHECK-NEXT: orr r0, r1, r0, lsl #17
; CHECK-NEXT: clz r0, r0
; CHECK-NEXT: lsr r0, r0, #5
; CHECK-NEXT: bx lr
%shl = shl i64 %a, 17
%cmp = icmp eq i64 %shl, 0
ret i1 %cmp
}
define i1 @opt_setcc_shl_ne_zero(i64 %a) nounwind {
; CHECK-LABEL: opt_setcc_shl_ne_zero:
; CHECK: @ %bb.0:
; CHECK-NEXT: lsl r1, r1, #17
; CHECK-NEXT: orr r1, r1, r0, lsr #15
; CHECK-NEXT: orr r0, r1, r0, lsl #17
; CHECK-NEXT: cmp r0, #0
; CHECK-NEXT: movwne r0, #1
; CHECK-NEXT: bx lr
%shl = shl i64 %a, 17
%cmp = icmp ne i64 %shl, 0
ret i1 %cmp
}
; Negative test: optimization should not be applied if shift has multiple users.
define i1 @opt_setcc_shl_eq_zero_multiple_shl_users(i64 %a) nounwind {
; CHECK-LABEL: opt_setcc_shl_eq_zero_multiple_shl_users:
; CHECK: @ %bb.0:
; CHECK-NEXT: push {r4, r5, r11, lr}
; CHECK-NEXT: mov r4, r0
; CHECK-NEXT: lsl r0, r1, #17
; CHECK-NEXT: orr r5, r0, r4, lsr #15
; CHECK-NEXT: lsl r0, r4, #17
; CHECK-NEXT: mov r1, r5
; CHECK-NEXT: bl use
; CHECK-NEXT: orr r0, r5, r4, lsl #17
; CHECK-NEXT: clz r0, r0
; CHECK-NEXT: lsr r0, r0, #5
; CHECK-NEXT: pop {r4, r5, r11, pc}
%shl = shl i64 %a, 17
%cmp = icmp eq i64 %shl, 0
call void @use(i64 %shl)
ret i1 %cmp
}
; Check that optimization is applied to DAG having appropriate shape
; even if there were no actual shift's expansion.
define i1 @opt_setcc_expanded_shl_correct_shifts(i32 %a, i32 %b) nounwind {
; CHECK-LABEL: opt_setcc_expanded_shl_correct_shifts:
; CHECK: @ %bb.0:
; CHECK-NEXT: lsl r0, r0, #17
; CHECK-NEXT: orr r0, r0, r1, lsr #15
; CHECK-NEXT: orr r0, r0, r1, lsl #17
; CHECK-NEXT: clz r0, r0
; CHECK-NEXT: lsr r0, r0, #5
; CHECK-NEXT: bx lr
%shl.a = shl i32 %a, 17
%srl.b = lshr i32 %b, 15
%or.0 = or i32 %shl.a, %srl.b
%shl.b = shl i32 %b, 17
%or.1 = or i32 %or.0, %shl.b
%cmp = icmp eq i32 %or.1, 0
ret i1 %cmp
}
; Negative test: optimization should not be applied as
; constants used in shifts do not match.
define i1 @opt_setcc_expanded_shl_wrong_shifts(i32 %a, i32 %b) nounwind {
; CHECK-LABEL: opt_setcc_expanded_shl_wrong_shifts:
; CHECK: @ %bb.0:
; CHECK-NEXT: lsl r0, r0, #17
; CHECK-NEXT: orr r0, r0, r1, lsr #15
; CHECK-NEXT: orr r0, r0, r1, lsl #18
; CHECK-NEXT: clz r0, r0
; CHECK-NEXT: lsr r0, r0, #5
; CHECK-NEXT: bx lr
%shl.a = shl i32 %a, 17
%srl.b = lshr i32 %b, 15
%or.0 = or i32 %shl.a, %srl.b
%shl.b = shl i32 %b, 18
%or.1 = or i32 %or.0, %shl.b
%cmp = icmp eq i32 %or.1, 0
ret i1 %cmp
}
define i1 @opt_setcc_shl_ne_zero_i128(i128 %a) nounwind {
; CHECK-LABEL: opt_setcc_shl_ne_zero_i128:
; CHECK: @ %bb.0:
; CHECK-NEXT: lsl r3, r3, #17
; CHECK-NEXT: orr r12, r3, r2, lsr #15
; CHECK-NEXT: lsl r3, r1, #17
; CHECK-NEXT: lsl r2, r2, #17
; CHECK-NEXT: orr r3, r3, r0, lsr #15
; CHECK-NEXT: orr r1, r2, r1, lsr #15
; CHECK-NEXT: orr r3, r3, r12
; CHECK-NEXT: orr r0, r1, r0, lsl #17
; CHECK-NEXT: orrs r0, r0, r3
; CHECK-NEXT: movwne r0, #1
; CHECK-NEXT: bx lr
%shl = shl i128 %a, 17
%cmp = icmp ne i128 %shl, 0
ret i1 %cmp
}
declare void @use(i64 %a)
|
