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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
|
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
; RUN: opt < %s -disable-output -passes="print<da>" 2>&1 | FileCheck %s
; Note: exact results can be achieved even if
; "-da-disable-delinearization-checks" is not used
;; #define N 1024
;; #define M 2048
;; void t1(int a[N][M]) {
;; for (int i = 0; i < N-1; ++i)
;; for (int j = 2; j < M; ++j)
;; a[i][j] = a[i+1][j-2];
;; }
;;
;; Note that there is a getelementptr with index 0, make sure we can analyze this case.
define void @t1(ptr %a) {
; CHECK-LABEL: 't1'
; CHECK-NEXT: Src: %2 = load i32, ptr %arrayidx6, align 4 --> Dst: %2 = load i32, ptr %arrayidx6, align 4
; CHECK-NEXT: da analyze - none!
; CHECK-NEXT: Src: %2 = load i32, ptr %arrayidx6, align 4 --> Dst: store i32 %2, ptr %arrayidx10, align 4
; CHECK-NEXT: da analyze - consistent anti [1 -2]!
; CHECK-NEXT: Src: store i32 %2, ptr %arrayidx10, align 4 --> Dst: store i32 %2, ptr %arrayidx10, align 4
; CHECK-NEXT: da analyze - none!
;
entry:
br label %for.body
for.body: ; preds = %entry, %for.inc11
%indvars.iv4 = phi i64 [ 0, %entry ], [ %indvars.iv.next5, %for.inc11 ]
br label %for.body4
for.body4: ; preds = %for.body, %for.body4
%indvars.iv = phi i64 [ 2, %for.body ], [ %indvars.iv.next, %for.body4 ]
%0 = add nuw nsw i64 %indvars.iv4, 1
%1 = add nsw i64 %indvars.iv, -2
%arrayidx6 = getelementptr inbounds [2048 x i32], ptr %a, i64 %0, i64 %1
%2 = load i32, ptr %arrayidx6, align 4
%arrayidx10 = getelementptr inbounds [2048 x i32], ptr %a, i64 %indvars.iv4, i64 %indvars.iv
store i32 %2, ptr %arrayidx10, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp ne i64 %indvars.iv.next, 2048
br i1 %exitcond, label %for.body4, label %for.inc11
for.inc11: ; preds = %for.body4
%indvars.iv.next5 = add nuw nsw i64 %indvars.iv4, 1
%exitcond7 = icmp ne i64 %indvars.iv.next5, 1023
br i1 %exitcond7, label %for.body, label %for.end13
for.end13: ; preds = %for.inc11
ret void
}
;; Similar to @t1 but includes a call with a "returned" arg, make sure we can analyze
;; this case.
define void @t2(ptr %a) {
; CHECK-LABEL: 't2'
; CHECK-NEXT: Src: %2 = load i32, ptr %arrayidx6, align 4 --> Dst: %2 = load i32, ptr %arrayidx6, align 4
; CHECK-NEXT: da analyze - none!
; CHECK-NEXT: Src: %2 = load i32, ptr %arrayidx6, align 4 --> Dst: %call = call ptr @func_with_returned_arg(ptr returned %a)
; CHECK-NEXT: da analyze - confused!
; CHECK-NEXT: Src: %2 = load i32, ptr %arrayidx6, align 4 --> Dst: store i32 %2, ptr %arrayidx10, align 4
; CHECK-NEXT: da analyze - consistent anti [1 -2]!
; CHECK-NEXT: Src: %call = call ptr @func_with_returned_arg(ptr returned %a) --> Dst: %call = call ptr @func_with_returned_arg(ptr returned %a)
; CHECK-NEXT: da analyze - confused!
; CHECK-NEXT: Src: %call = call ptr @func_with_returned_arg(ptr returned %a) --> Dst: store i32 %2, ptr %arrayidx10, align 4
; CHECK-NEXT: da analyze - confused!
; CHECK-NEXT: Src: store i32 %2, ptr %arrayidx10, align 4 --> Dst: store i32 %2, ptr %arrayidx10, align 4
; CHECK-NEXT: da analyze - none!
;
entry:
br label %for.body
for.body: ; preds = %entry, %for.inc11
%indvars.iv4 = phi i64 [ 0, %entry ], [ %indvars.iv.next5, %for.inc11 ]
br label %for.body4
for.body4: ; preds = %for.body, %for.body4
%indvars.iv = phi i64 [ 2, %for.body ], [ %indvars.iv.next, %for.body4 ]
%0 = add nuw nsw i64 %indvars.iv4, 1
%1 = add nsw i64 %indvars.iv, -2
%arrayidx6 = getelementptr inbounds [2048 x i32], ptr %a, i64 %0, i64 %1
%2 = load i32, ptr %arrayidx6, align 4
%call = call ptr @func_with_returned_arg(ptr returned %a)
%arrayidx10 = getelementptr inbounds [2048 x i32], ptr %call, i64 %indvars.iv4, i64 %indvars.iv
store i32 %2, ptr %arrayidx10, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp ne i64 %indvars.iv.next, 2048
br i1 %exitcond, label %for.body4, label %for.inc11
for.inc11: ; preds = %for.body4
%indvars.iv.next5 = add nuw nsw i64 %indvars.iv4, 1
%exitcond7 = icmp ne i64 %indvars.iv.next5, 1023
br i1 %exitcond7, label %for.body, label %for.end13
for.end13: ; preds = %for.inc11
ret void
}
declare ptr @func_with_returned_arg(ptr returned %arg)
;; #define N 1024
;; #define M 2048
;; void t2(int a[][N][N][N][M]) {
;; for (int i1 = 0; i1 < N-1; ++i1)
;; for (int i2 = 2; i2 < N; ++i2)
;; for (int i3 = 0; i3 < N; ++i3)
;; for (int i4 = 3; i4 < N; ++i4)
;; for (int i5 = 0; i5 < M-2; ++i5)
;; a[i1][i2][i3][i4][i5] = a[i1+1][i2-2][i3][i4-3][i5+2];
;; }
define void @t3(ptr %a) {
; CHECK-LABEL: 't3'
; CHECK-NEXT: Src: %4 = load i32, ptr %arrayidx26, align 4 --> Dst: %4 = load i32, ptr %arrayidx26, align 4
; CHECK-NEXT: da analyze - none!
; CHECK-NEXT: Src: %4 = load i32, ptr %arrayidx26, align 4 --> Dst: store i32 %4, ptr %arrayidx36, align 4
; CHECK-NEXT: da analyze - consistent anti [1 -2 0 -3 2]!
; CHECK-NEXT: Src: store i32 %4, ptr %arrayidx36, align 4 --> Dst: store i32 %4, ptr %arrayidx36, align 4
; CHECK-NEXT: da analyze - none!
;
entry:
br label %for.body
for.body: ; preds = %entry, %for.inc46
%indvars.iv18 = phi i64 [ 0, %entry ], [ %indvars.iv.next19, %for.inc46 ]
br label %for.body4
for.body4: ; preds = %for.body, %for.inc43
%indvars.iv14 = phi i64 [ 2, %for.body ], [ %indvars.iv.next15, %for.inc43 ]
br label %for.body8
for.body8: ; preds = %for.body4, %for.inc40
%indvars.iv11 = phi i64 [ 0, %for.body4 ], [ %indvars.iv.next12, %for.inc40 ]
br label %for.body12
for.body12: ; preds = %for.body8, %for.inc37
%indvars.iv7 = phi i64 [ 3, %for.body8 ], [ %indvars.iv.next8, %for.inc37 ]
br label %for.body16
for.body16: ; preds = %for.body12, %for.body16
%indvars.iv = phi i64 [ 0, %for.body12 ], [ %indvars.iv.next, %for.body16 ]
%0 = add nuw nsw i64 %indvars.iv18, 1
%1 = add nsw i64 %indvars.iv14, -2
%2 = add nsw i64 %indvars.iv7, -3
%3 = add nuw nsw i64 %indvars.iv, 2
%arrayidx26 = getelementptr inbounds [1024 x [1024 x [1024 x [2048 x i32]]]], ptr %a, i64 %0, i64 %1, i64 %indvars.iv11, i64 %2, i64 %3
%4 = load i32, ptr %arrayidx26, align 4
%arrayidx36 = getelementptr inbounds [1024 x [1024 x [1024 x [2048 x i32]]]], ptr %a, i64 %indvars.iv18, i64 %indvars.iv14, i64 %indvars.iv11, i64 %indvars.iv7, i64 %indvars.iv
store i32 %4, ptr %arrayidx36, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp ne i64 %indvars.iv.next, 2046
br i1 %exitcond, label %for.body16, label %for.inc37
for.inc37: ; preds = %for.body16
%indvars.iv.next8 = add nuw nsw i64 %indvars.iv7, 1
%exitcond10 = icmp ne i64 %indvars.iv.next8, 1024
br i1 %exitcond10, label %for.body12, label %for.inc40
for.inc40: ; preds = %for.inc37
%indvars.iv.next12 = add nuw nsw i64 %indvars.iv11, 1
%exitcond13 = icmp ne i64 %indvars.iv.next12, 1024
br i1 %exitcond13, label %for.body8, label %for.inc43
for.inc43: ; preds = %for.inc40
%indvars.iv.next15 = add nuw nsw i64 %indvars.iv14, 1
%exitcond17 = icmp ne i64 %indvars.iv.next15, 1024
br i1 %exitcond17, label %for.body4, label %for.inc46
for.inc46: ; preds = %for.inc43
%indvars.iv.next19 = add nuw nsw i64 %indvars.iv18, 1
%exitcond21 = icmp ne i64 %indvars.iv.next19, 1023
br i1 %exitcond21, label %for.body, label %for.end48
for.end48: ; preds = %for.inc46
ret void
}
|
