builtin-assume-aligned.c
6.63 KB
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_cc_test_checks.py
// RUN: %clang_cc1 -triple x86_64-unknown-unknown -emit-llvm -o - %s | FileCheck %s
// CHECK-LABEL: define {{[^@]+}}@test1
// CHECK-SAME: (i32* [[A:%.*]]) #0
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 8
// CHECK-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK-NEXT: [[PTRINT:%.*]] = ptrtoint i8* [[TMP1]] to i64
// CHECK-NEXT: [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 31
// CHECK-NEXT: [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[MASKCOND]])
// CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to i32*
// CHECK-NEXT: store i32* [[TMP2]], i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP3]], i64 0
// CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK-NEXT: ret i32 [[TMP4]]
//
int test1(int *a) {
a = __builtin_assume_aligned(a, 32, 0ull);
return a[0];
}
// CHECK-LABEL: define {{[^@]+}}@test2
// CHECK-SAME: (i32* [[A:%.*]]) #0
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 8
// CHECK-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK-NEXT: [[PTRINT:%.*]] = ptrtoint i8* [[TMP1]] to i64
// CHECK-NEXT: [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 31
// CHECK-NEXT: [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[MASKCOND]])
// CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to i32*
// CHECK-NEXT: store i32* [[TMP2]], i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP3]], i64 0
// CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK-NEXT: ret i32 [[TMP4]]
//
int test2(int *a) {
a = __builtin_assume_aligned(a, 32, 0);
return a[0];
}
// CHECK-LABEL: define {{[^@]+}}@test3
// CHECK-SAME: (i32* [[A:%.*]]) #0
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 8
// CHECK-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK-NEXT: [[PTRINT:%.*]] = ptrtoint i8* [[TMP1]] to i64
// CHECK-NEXT: [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 31
// CHECK-NEXT: [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[MASKCOND]])
// CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to i32*
// CHECK-NEXT: store i32* [[TMP2]], i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP3]], i64 0
// CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK-NEXT: ret i32 [[TMP4]]
//
int test3(int *a) {
a = __builtin_assume_aligned(a, 32);
return a[0];
}
// CHECK-LABEL: define {{[^@]+}}@test4
// CHECK-SAME: (i32* [[A:%.*]], i32 [[B:%.*]]) #0
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 8
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 8
// CHECK-NEXT: store i32 [[B]], i32* [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK-NEXT: [[TMP2:%.*]] = load i32, i32* [[B_ADDR]], align 4
// CHECK-NEXT: [[CONV:%.*]] = sext i32 [[TMP2]] to i64
// CHECK-NEXT: [[PTRINT:%.*]] = ptrtoint i8* [[TMP1]] to i64
// CHECK-NEXT: [[OFFSETPTR:%.*]] = sub i64 [[PTRINT]], [[CONV]]
// CHECK-NEXT: [[MASKEDPTR:%.*]] = and i64 [[OFFSETPTR]], 31
// CHECK-NEXT: [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[MASKCOND]])
// CHECK-NEXT: [[TMP3:%.*]] = bitcast i8* [[TMP1]] to i32*
// CHECK-NEXT: store i32* [[TMP3]], i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP4:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP4]], i64 0
// CHECK-NEXT: [[TMP5:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK-NEXT: ret i32 [[TMP5]]
//
int test4(int *a, int b) {
a = __builtin_assume_aligned(a, 32, b);
return a[0];
}
int *m1() __attribute__((assume_aligned(64)));
// CHECK-LABEL: define {{[^@]+}}@test5() #0
// CHECK-NEXT: entry:
// CHECK-NEXT: [[CALL:%.*]] = call align 64 i32* (...) @m1()
// CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[CALL]], align 4
// CHECK-NEXT: ret i32 [[TMP0]]
//
int test5() {
return *m1();
}
int *m2() __attribute__((assume_aligned(64, 12)));
// CHECK-LABEL: define {{[^@]+}}@test6() #0
// CHECK-NEXT: entry:
// CHECK-NEXT: [[CALL:%.*]] = call i32* (...) @m2()
// CHECK-NEXT: [[PTRINT:%.*]] = ptrtoint i32* [[CALL]] to i64
// CHECK-NEXT: [[OFFSETPTR:%.*]] = sub i64 [[PTRINT]], 12
// CHECK-NEXT: [[MASKEDPTR:%.*]] = and i64 [[OFFSETPTR]], 63
// CHECK-NEXT: [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[MASKCOND]])
// CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[CALL]], align 4
// CHECK-NEXT: ret i32 [[TMP0]]
//
int test6() {
return *m2();
}
// CHECK-LABEL: define {{[^@]+}}@pr43638
// CHECK-SAME: (i32* [[A:%.*]]) #0
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 8
// CHECK-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = bitcast i32* [[TMP0]] to i8*
// CHECK-NEXT: [[PTRINT:%.*]] = ptrtoint i8* [[TMP1]] to i64
// CHECK-NEXT: [[MASKEDPTR:%.*]] = and i64 [[PTRINT]], 536870911
// CHECK-NEXT: [[MASKCOND:%.*]] = icmp eq i64 [[MASKEDPTR]], 0
// CHECK-NEXT: call void @llvm.assume(i1 [[MASKCOND]])
// CHECK-NEXT: [[TMP2:%.*]] = bitcast i8* [[TMP1]] to i32*
// CHECK-NEXT: store i32* [[TMP2]], i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[TMP3:%.*]] = load i32*, i32** [[A_ADDR]], align 8
// CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[TMP3]], i64 0
// CHECK-NEXT: [[TMP4:%.*]] = load i32, i32* [[ARRAYIDX]], align 4
// CHECK-NEXT: ret i32 [[TMP4]]
//
int pr43638(int *a) {
a = __builtin_assume_aligned(a, 4294967296);
return a[0];
}