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
|
; RUN: opt -loop-accesses -analyze < %s | FileCheck %s
; The runtime memory check code and the access grouping
; algorithm both assume that the start and end values
; for an access range are ordered (start <= stop).
; When generating checks for accesses with negative stride
; we need to take this into account and swap the interval
; ends.
;
; for (i = 0; i < 10000; i++) {
; B[i] = A[15000 - i] * 3;
; }
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
target triple = "aarch64--linux-gnueabi"
; CHECK: function 'f':
; CHECK: (Low: (20000 + %a) High: (60000 + %a))
@B = common global i32* null, align 8
@A = common global i32* null, align 8
define void @f() {
entry:
%a = load i32*, i32** @A, align 8
%b = load i32*, i32** @B, align 8
br label %for.body
for.body: ; preds = %for.body, %entry
%idx = phi i64 [ 0, %entry ], [ %add, %for.body ]
%negidx = sub i64 15000, %idx
%arrayidxA0 = getelementptr inbounds i32, i32* %a, i64 %negidx
%loadA0 = load i32, i32* %arrayidxA0, align 2
%res = mul i32 %loadA0, 3
%add = add nuw nsw i64 %idx, 1
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %idx
store i32 %res, i32* %arrayidxB, align 2
%exitcond = icmp eq i64 %idx, 10000
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
; CHECK: function 'g':
; When the stride is not constant, we are forced to do umin/umax to get
; the interval limits.
; for (i = 0; i < 10000; i++) {
; B[i] = A[15000 - step * i] * 3;
; }
; Here it is not obvious what the limits are, since 'step' could be negative.
; CHECK: Low: (-1 + (-1 * ((-60001 + (-1 * %a)) umax (-60001 + (40000 * %step) + (-1 * %a)))))
; CHECK: High: ((60000 + %a) umax (60000 + (-40000 * %step) + %a))
define void @g(i64 %step) {
entry:
%a = load i32*, i32** @A, align 8
%b = load i32*, i32** @B, align 8
br label %for.body
for.body: ; preds = %for.body, %entry
%idx = phi i64 [ 0, %entry ], [ %add, %for.body ]
%idx_mul = mul i64 %idx, %step
%negidx = sub i64 15000, %idx_mul
%arrayidxA0 = getelementptr inbounds i32, i32* %a, i64 %negidx
%loadA0 = load i32, i32* %arrayidxA0, align 2
%res = mul i32 %loadA0, 3
%add = add nuw nsw i64 %idx, 1
%arrayidxB = getelementptr inbounds i32, i32* %b, i64 %idx
store i32 %res, i32* %arrayidxB, align 2
%exitcond = icmp eq i64 %idx, 10000
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
|
