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
|
; RUN: opt -passes=called-value-propagation -S < %s | FileCheck %s
target triple = "aarch64-unknown-linux-gnueabi"
@global_function = internal unnamed_addr global ptr null, align 8
@global_array = common unnamed_addr global ptr null, align 8
; This test checks that we propagate the functions through an internal global
; variable, and attach !callees metadata to the call. Such metadata can enable
; optimizations of this code sequence.
;
; For example, since both of the targeted functions have the "nounwind" and
; "readnone" function attributes, LICM can be made to move the call and the
; function pointer load outside the loop. This would then enable the loop
; vectorizer to vectorize the sum reduction.
;
; CHECK: call void %tmp0(), !callees ![[MD:[0-9]+]]
; CHECK: ![[MD]] = !{ptr @invariant_1, ptr @invariant_2}
;
define i64 @test_memory_entry(i64 %n, i1 %flag) {
entry:
br i1 %flag, label %then, label %else
then:
store ptr @invariant_1, ptr @global_function
br label %merge
else:
store ptr @invariant_2, ptr @global_function
br label %merge
merge:
%tmp1 = call i64 @test_memory(i64 %n)
ret i64 %tmp1
}
define internal i64 @test_memory(i64 %n) {
entry:
%array = load ptr, ptr @global_array
br label %for.body
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
%r = phi i64 [ 0, %entry ], [ %tmp3, %for.body ]
%tmp0 = load ptr, ptr @global_function
call void %tmp0()
%tmp1 = getelementptr inbounds i64, ptr %array, i64 %i
%tmp2 = load i64, ptr %tmp1
%tmp3 = add i64 %tmp2, %r
%i.next = add nuw nsw i64 %i, 1
%cond = icmp slt i64 %i.next, %n
br i1 %cond, label %for.body, label %for.end
for.end:
%tmp4 = phi i64 [ %tmp3, %for.body ]
ret i64 %tmp4
}
declare void @invariant_1() #0
declare void @invariant_2() #0
attributes #0 = { nounwind readnone }
|
