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
|
; RUN: opt < %s -inline -S | FileCheck %s
; RUN: opt < %s -passes='cgscc(inline)' -S | FileCheck %s
; Inlining a byval struct should cause an explicit copy into an alloca.
%struct.ss = type { i32, i64 }
@.str = internal constant [10 x i8] c"%d, %lld\0A\00" ; <[10 x i8]*> [#uses=1]
define internal void @f(%struct.ss* byval %b) nounwind {
entry:
%tmp = getelementptr %struct.ss, %struct.ss* %b, i32 0, i32 0 ; <i32*> [#uses=2]
%tmp1 = load i32, i32* %tmp, align 4 ; <i32> [#uses=1]
%tmp2 = add i32 %tmp1, 1 ; <i32> [#uses=1]
store i32 %tmp2, i32* %tmp, align 4
ret void
}
declare i32 @printf(i8*, ...) nounwind
define i32 @test1() nounwind {
entry:
%S = alloca %struct.ss ; <%struct.ss*> [#uses=4]
%tmp1 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 0 ; <i32*> [#uses=1]
store i32 1, i32* %tmp1, align 8
%tmp4 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 1 ; <i64*> [#uses=1]
store i64 2, i64* %tmp4, align 4
call void @f( %struct.ss* byval %S ) nounwind
ret i32 0
; CHECK: @test1()
; CHECK: %S1 = alloca %struct.ss
; CHECK: %S = alloca %struct.ss
; CHECK: call void @llvm.memcpy
; CHECK: ret i32 0
}
; Inlining a byval struct should NOT cause an explicit copy
; into an alloca if the function is readonly
define internal i32 @f2(%struct.ss* byval %b) nounwind readonly {
entry:
%tmp = getelementptr %struct.ss, %struct.ss* %b, i32 0, i32 0 ; <i32*> [#uses=2]
%tmp1 = load i32, i32* %tmp, align 4 ; <i32> [#uses=1]
%tmp2 = add i32 %tmp1, 1 ; <i32> [#uses=1]
ret i32 %tmp2
}
define i32 @test2() nounwind {
entry:
%S = alloca %struct.ss ; <%struct.ss*> [#uses=4]
%tmp1 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 0 ; <i32*> [#uses=1]
store i32 1, i32* %tmp1, align 8
%tmp4 = getelementptr %struct.ss, %struct.ss* %S, i32 0, i32 1 ; <i64*> [#uses=1]
store i64 2, i64* %tmp4, align 4
%X = call i32 @f2( %struct.ss* byval %S ) nounwind
ret i32 %X
; CHECK: @test2()
; CHECK: %S = alloca %struct.ss
; CHECK-NOT: call void @llvm.memcpy
; CHECK: ret i32
}
; Inlining a byval with an explicit alignment needs to use *at least* that
; alignment on the generated alloca.
; PR8769
declare void @g3(%struct.ss* %p)
define internal void @f3(%struct.ss* byval align 64 %b) nounwind {
call void @g3(%struct.ss* %b) ;; Could make alignment assumptions!
ret void
}
define void @test3() nounwind {
entry:
%S = alloca %struct.ss, align 1 ;; May not be aligned.
call void @f3( %struct.ss* byval align 64 %S) nounwind
ret void
; CHECK: @test3()
; CHECK: %S1 = alloca %struct.ss, align 64
; CHECK: %S = alloca %struct.ss
; CHECK: call void @llvm.memcpy
; CHECK: call void @g3(%struct.ss* %S1)
; CHECK: ret void
}
; Inlining a byval struct should NOT cause an explicit copy
; into an alloca if the function is readonly, but should increase an alloca's
; alignment to satisfy an explicit alignment request.
define internal i32 @f4(%struct.ss* byval align 64 %b) nounwind readonly {
call void @g3(%struct.ss* %b)
ret i32 4
}
define i32 @test4() nounwind {
entry:
%S = alloca %struct.ss, align 2 ; <%struct.ss*> [#uses=4]
%X = call i32 @f4( %struct.ss* byval align 64 %S ) nounwind
ret i32 %X
; CHECK: @test4()
; CHECK: %S = alloca %struct.ss, align 64
; CHECK-NOT: call void @llvm.memcpy
; CHECK: call void @g3
; CHECK: ret i32 4
}
%struct.S0 = type { i32 }
@b = global %struct.S0 { i32 1 }, align 4
@a = common global i32 0, align 4
define internal void @f5(%struct.S0* byval nocapture readonly align 4 %p) {
entry:
store i32 0, i32* getelementptr inbounds (%struct.S0, %struct.S0* @b, i64 0, i32 0), align 4
%f2 = getelementptr inbounds %struct.S0, %struct.S0* %p, i64 0, i32 0
%0 = load i32, i32* %f2, align 4
store i32 %0, i32* @a, align 4
ret void
}
define i32 @test5() {
entry:
tail call void @f5(%struct.S0* byval align 4 @b)
%0 = load i32, i32* @a, align 4
ret i32 %0
; CHECK: @test5()
; CHECK: store i32 0, i32* getelementptr inbounds (%struct.S0, %struct.S0* @b, i64 0, i32 0), align 4
; CHECK-NOT: load i32, i32* getelementptr inbounds (%struct.S0, %struct.S0* @b, i64 0, i32 0), align 4
}
|
