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
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -instcombine -S < %s | FileCheck %s
@gp = global i32* null, align 8
declare i8* @malloc(i64) #1
define i1 @compare_global_trivialeq() {
; CHECK-LABEL: @compare_global_trivialeq(
; CHECK-NEXT: ret i1 false
;
%m = call i8* @malloc(i64 4)
%bc = bitcast i8* %m to i32*
%lgp = load i32*, i32** @gp, align 8
%cmp = icmp eq i32* %bc, %lgp
ret i1 %cmp
}
define i1 @compare_global_trivialne() {
; CHECK-LABEL: @compare_global_trivialne(
; CHECK-NEXT: ret i1 true
;
%m = call i8* @malloc(i64 4)
%bc = bitcast i8* %m to i32*
%lgp = load i32*, i32** @gp, align 8
%cmp = icmp ne i32* %bc, %lgp
ret i1 %cmp
}
; Although the %m is marked nocapture in the deopt operand in call to function f,
; we cannot remove the alloc site: call to malloc
; The comparison should fold to false irrespective of whether the call to malloc can be elided or not
declare void @f()
define i1 @compare_and_call_with_deopt() {
; CHECK-LABEL: @compare_and_call_with_deopt(
; CHECK-NEXT: [[M:%.*]] = call dereferenceable_or_null(24) i8* @malloc(i64 24)
; CHECK-NEXT: tail call void @f() [ "deopt"(i8* [[M]]) ]
; CHECK-NEXT: ret i1 false
;
%m = call i8* @malloc(i64 24)
%bc = bitcast i8* %m to i32*
%lgp = load i32*, i32** @gp, align 8, !nonnull !0
%cmp = icmp eq i32* %lgp, %bc
tail call void @f() [ "deopt"(i8* %m) ]
ret i1 %cmp
}
; Same functon as above with deopt operand in function f, but comparison is NE
define i1 @compare_ne_and_call_with_deopt() {
; CHECK-LABEL: @compare_ne_and_call_with_deopt(
; CHECK-NEXT: [[M:%.*]] = call dereferenceable_or_null(24) i8* @malloc(i64 24)
; CHECK-NEXT: tail call void @f() [ "deopt"(i8* [[M]]) ]
; CHECK-NEXT: ret i1 true
;
%m = call i8* @malloc(i64 24)
%bc = bitcast i8* %m to i32*
%lgp = load i32*, i32** @gp, align 8, !nonnull !0
%cmp = icmp ne i32* %lgp, %bc
tail call void @f() [ "deopt"(i8* %m) ]
ret i1 %cmp
}
; Same function as above, but global not marked nonnull, and we cannot fold the comparison
define i1 @compare_ne_global_maybe_null() {
; CHECK-LABEL: @compare_ne_global_maybe_null(
; CHECK-NEXT: [[M:%.*]] = call dereferenceable_or_null(24) i8* @malloc(i64 24)
; CHECK-NEXT: [[BC:%.*]] = bitcast i8* [[M]] to i32*
; CHECK-NEXT: [[LGP:%.*]] = load i32*, i32** @gp, align 8
; CHECK-NEXT: [[CMP:%.*]] = icmp ne i32* [[LGP]], [[BC]]
; CHECK-NEXT: tail call void @f() [ "deopt"(i8* [[M]]) ]
; CHECK-NEXT: ret i1 [[CMP]]
;
%m = call i8* @malloc(i64 24)
%bc = bitcast i8* %m to i32*
%lgp = load i32*, i32** @gp
%cmp = icmp ne i32* %lgp, %bc
tail call void @f() [ "deopt"(i8* %m) ]
ret i1 %cmp
}
; FIXME: The comparison should fold to false since %m escapes (call to function escape)
; after the comparison.
declare void @escape(i8*)
define i1 @compare_and_call_after() {
; CHECK-LABEL: @compare_and_call_after(
; CHECK-NEXT: [[M:%.*]] = call dereferenceable_or_null(24) i8* @malloc(i64 24)
; CHECK-NEXT: [[BC:%.*]] = bitcast i8* [[M]] to i32*
; CHECK-NEXT: [[LGP:%.*]] = load i32*, i32** @gp, align 8, !nonnull !0
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i32* [[LGP]], [[BC]]
; CHECK-NEXT: br i1 [[CMP]], label [[ESCAPE_CALL:%.*]], label [[JUST_RETURN:%.*]]
; CHECK: escape_call:
; CHECK-NEXT: call void @escape(i8* [[M]])
; CHECK-NEXT: ret i1 true
; CHECK: just_return:
; CHECK-NEXT: ret i1 [[CMP]]
;
%m = call i8* @malloc(i64 24)
%bc = bitcast i8* %m to i32*
%lgp = load i32*, i32** @gp, align 8, !nonnull !0
%cmp = icmp eq i32* %bc, %lgp
br i1 %cmp, label %escape_call, label %just_return
escape_call:
call void @escape(i8* %m)
ret i1 true
just_return:
ret i1 %cmp
}
define i1 @compare_distinct_mallocs() {
; CHECK-LABEL: @compare_distinct_mallocs(
; CHECK-NEXT: ret i1 false
;
%m = call i8* @malloc(i64 4)
%n = call i8* @malloc(i64 4)
%cmp = icmp eq i8* %m, %n
ret i1 %cmp
}
; the compare is folded to true since the folding compare looks through bitcasts.
; call to malloc and the bitcast instructions are elided after that since there are no uses of the malloc
define i1 @compare_samepointer_under_bitcast() {
; CHECK-LABEL: @compare_samepointer_under_bitcast(
; CHECK-NEXT: ret i1 true
;
%m = call i8* @malloc(i64 4)
%bc = bitcast i8* %m to i32*
%bcback = bitcast i32* %bc to i8*
%cmp = icmp eq i8* %m, %bcback
ret i1 %cmp
}
; the compare is folded to true since the folding compare looks through bitcasts.
; The malloc call for %m cannot be elided since it is used in the call to function f.
define i1 @compare_samepointer_escaped() {
; CHECK-LABEL: @compare_samepointer_escaped(
; CHECK-NEXT: [[M:%.*]] = call dereferenceable_or_null(4) i8* @malloc(i64 4)
; CHECK-NEXT: call void @f() [ "deopt"(i8* [[M]]) ]
; CHECK-NEXT: ret i1 true
;
%m = call i8* @malloc(i64 4)
%bc = bitcast i8* %m to i32*
%bcback = bitcast i32* %bc to i8*
%cmp = icmp eq i8* %m, %bcback
call void @f() [ "deopt"(i8* %m) ]
ret i1 %cmp
}
; Technically, we can fold the %cmp2 comparison, even though %m escapes through
; the ret statement since `ret` terminates the function and we cannot reach from
; the ret to cmp.
; FIXME: Folding this %cmp2 when %m escapes through ret could be an issue with
; cross-threading data dependencies since we do not make the distinction between
; atomic and non-atomic loads in capture tracking.
define i8* @compare_ret_escape(i8* %c) {
; CHECK-LABEL: @compare_ret_escape(
; CHECK-NEXT: [[M:%.*]] = call dereferenceable_or_null(4) i8* @malloc(i64 4)
; CHECK-NEXT: [[N:%.*]] = call dereferenceable_or_null(4) i8* @malloc(i64 4)
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8* [[N]], [[C:%.*]]
; CHECK-NEXT: br i1 [[CMP]], label [[RETST:%.*]], label [[CHK:%.*]]
; CHECK: retst:
; CHECK-NEXT: ret i8* [[M]]
; CHECK: chk:
; CHECK-NEXT: [[BC:%.*]] = bitcast i8* [[M]] to i32*
; CHECK-NEXT: [[LGP:%.*]] = load i32*, i32** @gp, align 8, !nonnull !0
; CHECK-NEXT: [[CMP2:%.*]] = icmp eq i32* [[LGP]], [[BC]]
; CHECK-NEXT: br i1 [[CMP2]], label [[RETST]], label [[CHK2:%.*]]
; CHECK: chk2:
; CHECK-NEXT: ret i8* [[N]]
;
%m = call i8* @malloc(i64 4)
%n = call i8* @malloc(i64 4)
%cmp = icmp eq i8* %n, %c
br i1 %cmp, label %retst, label %chk
retst:
ret i8* %m
chk:
%bc = bitcast i8* %m to i32*
%lgp = load i32*, i32** @gp, align 8, !nonnull !0
%cmp2 = icmp eq i32* %bc, %lgp
br i1 %cmp2, label %retst, label %chk2
chk2:
ret i8* %n
}
; The malloc call for %m cannot be elided since it is used in the call to function f.
; However, the cmp can be folded to true as %n doesnt escape and %m, %n are distinct allocations
define i1 @compare_distinct_pointer_escape() {
; CHECK-LABEL: @compare_distinct_pointer_escape(
; CHECK-NEXT: [[M:%.*]] = call dereferenceable_or_null(4) i8* @malloc(i64 4)
; CHECK-NEXT: tail call void @f() [ "deopt"(i8* [[M]]) ]
; CHECK-NEXT: ret i1 true
;
%m = call i8* @malloc(i64 4)
%n = call i8* @malloc(i64 4)
tail call void @f() [ "deopt"(i8* %m) ]
%cmp = icmp ne i8* %m, %n
ret i1 %cmp
}
!0 = !{}
|