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 -opaque-pointers=0 -passes=loop-versioning -S < %s | FileCheck %s
; RUN: opt -opaque-pointers=0 -aa-pipeline=basic-aa -passes=loop-versioning -S < %s | FileCheck %s
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
; Version this loop with overlap checks between a, c and b, c.
define void @f(i32* %a, i32* %b, i32* %c) {
entry:
br label %for.body
; CHECK: for.body.lver.check:
; CHECK: icmp
; CHECK: icmp
; CHECK: icmp
; CHECK: icmp
; CHECK-NOT: icmp
; CHECK: br i1 %conflict.rdx, label %for.body.ph.lver.orig, label %for.body.ph
; CHECK: for.body.ph.lver.orig:
; CHECK: for.body.lver.orig:
; CHECK: br i1 %exitcond.lver.orig, label %for.end.loopexit, label %for.body.lver.orig
; CHECK: for.body.ph:
; CHECK: for.body:
; CHECK: br i1 %exitcond, label %for.end.loopexit12, label %for.body
; CHECK: for.end.loopexit:
; CHECK: br label %for.end
; CHECK: for.end.loopexit12:
; CHECK: br label %for.end
; CHECK: for.end:
for.body: ; preds = %for.body, %entry
%ind = phi i64 [ 0, %entry ], [ %add, %for.body ]
%arrayidxA = getelementptr inbounds i32, i32* %a, i64 %ind
%loadA = load i32, i32* %arrayidxA, align 4
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %ind
%loadB = load i32, i32* %arrayidxB, align 4
%mulC = mul i32 %loadA, %loadB
%arrayidxC = getelementptr inbounds i32, i32* %c, i64 %ind
store i32 %mulC, i32* %arrayidxC, align 4
%add = add nuw nsw i64 %ind, 1
%exitcond = icmp eq i64 %add, 20
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
|
