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
| ; RUN: opt -basicaa -loop-accesses -analyze < %s | FileCheck %s
; RUN: opt -passes='require<aa>,require<scalar-evolution>,require<aa>,loop(print-access-info)' -aa-pipeline='basic-aa' -disable-output < %s 2>&1 | FileCheck %s
; If the arrays don't alias this loop is safe with no memchecks:
; for (i = 0; i < n; i++)
; A[i] = A[i+1] * B[i] * C[i];
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.10.0"
; Check the loop-carried forward anti-dep between the load of A[i+1] and the
; store of A[i];
; CHECK: Memory dependences are safe{{$}}
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Forward:
; CHECK-NEXT: %loadA_plus_2 = load i16, i16* %arrayidxA_plus_2, align 2 ->
; CHECK-NEXT: store i16 %mul1, i16* %arrayidxA, align 2
define void @f(i16* noalias %a,
i16* noalias %b,
i16* noalias %c) {
entry:
br label %for.body
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%add = add nuw nsw i64 %ind, 1
%arrayidxA_plus_2 = getelementptr inbounds i16, i16* %a, i64 %add
%loadA_plus_2 = load i16, i16* %arrayidxA_plus_2, align 2
%arrayidxB = getelementptr inbounds i16, i16* %b, i64 %ind
%loadB = load i16, i16* %arrayidxB, align 2
%arrayidxC = getelementptr inbounds i16, i16* %c, i64 %ind
%loadC = load i16, i16* %arrayidxC, align 2
%mul = mul i16 %loadB, %loadA_plus_2
%mul1 = mul i16 %mul, %loadC
%arrayidxA = getelementptr inbounds i16, i16* %a, i64 %ind
store i16 %mul1, i16* %arrayidxA, align 2
%exitcond = icmp eq i64 %add, 20
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
|