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
171
172
173
174
175
176
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64 -sink-insts-to-avoid-spills | FileCheck %s
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
@A = external dso_local global [100 x i32], align 4
define i32 @sink_load_and_copy(i32 %n) {
; CHECK-LABEL: sink_load_and_copy:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: stp x30, x21, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w20, -16
; CHECK-NEXT: .cfi_offset w21, -24
; CHECK-NEXT: .cfi_offset w30, -32
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: cmp w0, #1
; CHECK-NEXT: b.lt .LBB0_3
; CHECK-NEXT: // %bb.1: // %for.body.preheader
; CHECK-NEXT: adrp x8, A
; CHECK-NEXT: mov w20, w19
; CHECK-NEXT: ldr w21, [x8, :lo12:A]
; CHECK-NEXT: .LBB0_2: // %for.body
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: mov w0, w21
; CHECK-NEXT: bl _Z3usei
; CHECK-NEXT: sdiv w20, w20, w0
; CHECK-NEXT: subs w19, w19, #1
; CHECK-NEXT: b.ne .LBB0_2
; CHECK-NEXT: b .LBB0_4
; CHECK-NEXT: .LBB0_3:
; CHECK-NEXT: mov w20, w19
; CHECK-NEXT: .LBB0_4: // %for.cond.cleanup
; CHECK-NEXT: mov w0, w20
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldp x30, x21, [sp], #32 // 16-byte Folded Reload
; CHECK-NEXT: ret
entry:
%cmp63 = icmp sgt i32 %n, 0
br i1 %cmp63, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%0 = load i32, i32* getelementptr inbounds ([100 x i32], [100 x i32]* @A, i64 0, i64 0), align 4
br label %for.body
for.cond.cleanup:
%sum.0.lcssa = phi i32 [ %n, %entry ], [ %div, %for.body ]
ret i32 %sum.0.lcssa
for.body:
%lsr.iv = phi i32 [ %n, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
%sum.065 = phi i32 [ %div, %for.body ], [ %n, %for.body.preheader ]
%call = tail call i32 @_Z3usei(i32 %0)
%div = sdiv i32 %sum.065, %call
%lsr.iv.next = add i32 %lsr.iv, -1
%exitcond.not = icmp eq i32 %lsr.iv.next, 0
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
define i32 @cant_sink_successive_call(i32 %n) {
; CHECK-LABEL: cant_sink_successive_call:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: stp x30, x21, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w20, -16
; CHECK-NEXT: .cfi_offset w21, -24
; CHECK-NEXT: .cfi_offset w30, -32
; CHECK-NEXT: mov w19, w0
; CHECK-NEXT: cmp w0, #1
; CHECK-NEXT: b.lt .LBB1_3
; CHECK-NEXT: // %bb.1: // %for.body.preheader
; CHECK-NEXT: adrp x8, A
; CHECK-NEXT: mov w0, w19
; CHECK-NEXT: ldr w20, [x8, :lo12:A]
; CHECK-NEXT: bl _Z3usei
; CHECK-NEXT: mov w21, w19
; CHECK-NEXT: .LBB1_2: // %for.body
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: mov w0, w20
; CHECK-NEXT: bl _Z3usei
; CHECK-NEXT: sdiv w21, w21, w0
; CHECK-NEXT: subs w19, w19, #1
; CHECK-NEXT: b.ne .LBB1_2
; CHECK-NEXT: b .LBB1_4
; CHECK-NEXT: .LBB1_3:
; CHECK-NEXT: mov w21, w19
; CHECK-NEXT: .LBB1_4: // %for.cond.cleanup
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: mov w0, w21
; CHECK-NEXT: ldp x30, x21, [sp], #32 // 16-byte Folded Reload
; CHECK-NEXT: ret
entry:
%cmp63 = icmp sgt i32 %n, 0
br i1 %cmp63, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%0 = load i32, i32* getelementptr inbounds ([100 x i32], [100 x i32]* @A, i64 0, i64 0), align 4
%call0 = tail call i32 @_Z3usei(i32 %n)
br label %for.body
for.cond.cleanup:
%sum.0.lcssa = phi i32 [ %n, %entry ], [ %div, %for.body ]
ret i32 %sum.0.lcssa
for.body:
%lsr.iv = phi i32 [ %n, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
%sum.065 = phi i32 [ %div, %for.body ], [ %n, %for.body.preheader ]
%call = tail call i32 @_Z3usei(i32 %0)
%div = sdiv i32 %sum.065, %call
%lsr.iv.next = add i32 %lsr.iv, -1
%exitcond.not = icmp eq i32 %lsr.iv.next, 0
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
define i32 @cant_sink_successive_store(i32* nocapture readnone %store, i32 %n) {
; CHECK-LABEL: cant_sink_successive_store:
; CHECK: // %bb.0: // %entry
; CHECK-NEXT: stp x30, x21, [sp, #-32]! // 16-byte Folded Spill
; CHECK-NEXT: stp x20, x19, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 32
; CHECK-NEXT: .cfi_offset w19, -8
; CHECK-NEXT: .cfi_offset w20, -16
; CHECK-NEXT: .cfi_offset w21, -24
; CHECK-NEXT: .cfi_offset w30, -32
; CHECK-NEXT: mov w19, w1
; CHECK-NEXT: cmp w1, #1
; CHECK-NEXT: b.lt .LBB2_3
; CHECK-NEXT: // %bb.1: // %for.body.preheader
; CHECK-NEXT: adrp x8, A
; CHECK-NEXT: mov w9, #42
; CHECK-NEXT: mov w20, w19
; CHECK-NEXT: ldr w21, [x8, :lo12:A]
; CHECK-NEXT: str w9, [x0]
; CHECK-NEXT: .LBB2_2: // %for.body
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: mov w0, w21
; CHECK-NEXT: bl _Z3usei
; CHECK-NEXT: sdiv w20, w20, w0
; CHECK-NEXT: subs w19, w19, #1
; CHECK-NEXT: b.ne .LBB2_2
; CHECK-NEXT: b .LBB2_4
; CHECK-NEXT: .LBB2_3:
; CHECK-NEXT: mov w20, w19
; CHECK-NEXT: .LBB2_4: // %for.cond.cleanup
; CHECK-NEXT: mov w0, w20
; CHECK-NEXT: ldp x20, x19, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT: ldp x30, x21, [sp], #32 // 16-byte Folded Reload
; CHECK-NEXT: ret
entry:
%cmp63 = icmp sgt i32 %n, 0
br i1 %cmp63, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader:
%0 = load i32, i32* getelementptr inbounds ([100 x i32], [100 x i32]* @A, i64 0, i64 0), align 4
store i32 42, i32* %store, align 4
br label %for.body
for.cond.cleanup:
%sum.0.lcssa = phi i32 [ %n, %entry ], [ %div, %for.body ]
ret i32 %sum.0.lcssa
for.body:
%lsr.iv = phi i32 [ %n, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
%sum.065 = phi i32 [ %div, %for.body ], [ %n, %for.body.preheader ]
%call = tail call i32 @_Z3usei(i32 %0)
%div = sdiv i32 %sum.065, %call
%lsr.iv.next = add i32 %lsr.iv, -1
%exitcond.not = icmp eq i32 %lsr.iv.next, 0
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
declare i32 @_Z3usei(i32)
|
