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
|
; RUN: opt %loadPolly -polly-print-dependences -disable-output < %s | FileCheck %s
;
; CHECK: RAW dependences:
; CHECK-NEXT: { Stmt_S1[i0, i1] -> Stmt_S2[-1 + i0 + i1] : 0 <= i0 <= 1023 and i1 >= 0 and -i0 < i1 <= 1024 - i0 and i1 <= 1023; Stmt_S0[i0] -> Stmt_S1[o0, i0 - o0] : i0 <= 1023 and 0 <= o0 <= i0 }
; CHECK-NEXT: WAR dependences:
; CHECK-NEXT: { Stmt_S1[i0, i1] -> Stmt_S2[i0 + i1] : i0 >= 0 and 0 <= i1 <= 1023 - i0; Stmt_S2[i0] -> Stmt_S2[1 + i0] : 0 <= i0 <= 1022 }
; CHECK-NEXT: WAW dependences:
; CHECK-NEXT: { Stmt_S1[i0, i1] -> Stmt_S2[i0 + i1] : i0 >= 0 and 0 <= i1 <= 1023 - i0; Stmt_S0[i0] -> Stmt_S1[o0, i0 - o0] : i0 <= 1023 and 0 <= o0 <= i0 }
; CHECK-NEXT: Reduction dependences:
; CHECK-NEXT: { Stmt_S1[i0, i1] -> Stmt_S1[1 + i0, -1 + i1] : 0 <= i0 <= 1022 and 0 < i1 <= 1023 }
;
; void f(int *sum) {
; for (int i = 0; i < 1024; i++)
; S0: sum[i] = 0;
; for (int i = 0; i < 1024; i++)
; for (int j = 0; j < 1024; j++)
; S1: sum[i + j] += i;
; for (int i = 0; i < 1024; i++)
; S2: sum[i] = sumptr 3;
; }
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-n32-S64"
define void @f(ptr %sum) {
entry:
br label %for.cond
for.cond: ; preds = %for.inc, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.inc ]
%exitcond3 = icmp ne i32 %i.0, 1024
br i1 %exitcond3, label %for.body, label %for.end
for.body: ; preds = %for.cond
br label %S0
S0: ; preds = %for.body
%arrayidx = getelementptr inbounds i32, ptr %sum, i32 %i.0
store i32 0, ptr %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %S0
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end: ; preds = %for.cond
br label %for.cond2
for.cond2: ; preds = %for.inc13, %for.end
%i1.0 = phi i32 [ 0, %for.end ], [ %inc14, %for.inc13 ]
%exitcond2 = icmp ne i32 %i1.0, 1024
br i1 %exitcond2, label %for.body4, label %for.end15
for.body4: ; preds = %for.cond2
br label %for.cond5
for.cond5: ; preds = %for.inc10, %for.body4
%j.0 = phi i32 [ 0, %for.body4 ], [ %inc11, %for.inc10 ]
%exitcond1 = icmp ne i32 %j.0, 1024
br i1 %exitcond1, label %for.body7, label %for.end12
for.body7: ; preds = %for.cond5
br label %S1
S1: ; preds = %for.body7
%add = add nsw i32 %i1.0, %j.0
%arrayidx8 = getelementptr inbounds i32, ptr %sum, i32 %add
%tmp = load i32, ptr %arrayidx8, align 4
%add9 = add nsw i32 %tmp, %i1.0
store i32 %add9, ptr %arrayidx8, align 4
br label %for.inc10
for.inc10: ; preds = %S1
%inc11 = add nsw i32 %j.0, 1
br label %for.cond5
for.end12: ; preds = %for.cond5
br label %for.inc13
for.inc13: ; preds = %for.end12
%inc14 = add nsw i32 %i1.0, 1
br label %for.cond2
for.end15: ; preds = %for.cond2
br label %for.cond17
for.cond17: ; preds = %for.inc23, %for.end15
%i16.0 = phi i32 [ 0, %for.end15 ], [ %inc24, %for.inc23 ]
%exitcond = icmp ne i32 %i16.0, 1024
br i1 %exitcond, label %for.body19, label %for.end25
for.body19: ; preds = %for.cond17
br label %S2
S2: ; preds = %for.body19
%add20 = add nsw i32 %i16.0, 1
%arrayidx21 = getelementptr inbounds i32, ptr %sum, i32 %add20
%tmp4 = load i32, ptr %arrayidx21, align 4
%mul = mul nsw i32 %tmp4, 3
%arrayidx22 = getelementptr inbounds i32, ptr %sum, i32 %i16.0
store i32 %mul, ptr %arrayidx22, align 4
br label %for.inc23
for.inc23: ; preds = %S2
%inc24 = add nsw i32 %i16.0, 1
br label %for.cond17
for.end25: ; preds = %for.cond17
ret void
}
|
