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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
|
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
; RUN: opt < %s -disable-output "-passes=print<da>" -aa-pipeline=basic-aa 2>&1 \
; RUN: | FileCheck %s
; The dependence test does not handle array accesses with difference between array accesses
; is not a multiple of the array element size.
; In this test, the element size is i32 = 4 bytes and the difference between the
; load and the store is 2 bytes.
define i32 @alias_with_different_offsets(ptr nocapture %A) {
; CHECK-LABEL: 'alias_with_different_offsets'
; CHECK-NEXT: Src: store i32 2, ptr %arrayidx, align 1 --> Dst: store i32 2, ptr %arrayidx, align 1
; CHECK-NEXT: da analyze - confused!
; CHECK-NEXT: Src: store i32 2, ptr %arrayidx, align 1 --> Dst: %0 = load i32, ptr %A, align 1
; CHECK-NEXT: da analyze - confused!
; CHECK-NEXT: Src: %0 = load i32, ptr %A, align 1 --> Dst: %0 = load i32, ptr %A, align 1
; CHECK-NEXT: da analyze - none!
;
entry:
%arrayidx = getelementptr inbounds i8, ptr %A, i64 2
store i32 2, ptr %arrayidx, align 1
%0 = load i32, ptr %A, align 1
ret i32 %0
}
define i32 @alias_with_parametric_offset(ptr nocapture %A, i64 %n) {
; CHECK-LABEL: 'alias_with_parametric_offset'
; CHECK-NEXT: Src: store i32 2, ptr %arrayidx, align 1 --> Dst: store i32 2, ptr %arrayidx, align 1
; CHECK-NEXT: da analyze - none!
; CHECK-NEXT: Src: store i32 2, ptr %arrayidx, align 1 --> Dst: %0 = load i32, ptr %A, align 1
; CHECK-NEXT: da analyze - flow [|<]!
; CHECK-NEXT: Runtime Assumptions:
; CHECK-NEXT: Equal predicate: (zext i2 (trunc i64 %n to i2) to i64) == 0
; CHECK-NEXT: Src: %0 = load i32, ptr %A, align 1 --> Dst: %0 = load i32, ptr %A, align 1
; CHECK-NEXT: da analyze - none!
; CHECK-NEXT: Runtime Assumptions:
; CHECK-NEXT: Equal predicate: (zext i2 (trunc i64 %n to i2) to i64) == 0
;
entry:
%arrayidx = getelementptr inbounds i8, ptr %A, i64 %n
store i32 2, ptr %arrayidx, align 1
%0 = load i32, ptr %A, align 1
ret i32 %0
}
define i32 @alias_with_parametric_expr(ptr nocapture %A, i64 %n, i64 %m) {
; CHECK-LABEL: 'alias_with_parametric_expr'
; CHECK-NEXT: Src: store i32 2, ptr %arrayidx, align 1 --> Dst: store i32 2, ptr %arrayidx, align 1
; CHECK-NEXT: da analyze - none!
; CHECK-NEXT: Src: store i32 2, ptr %arrayidx, align 1 --> Dst: %0 = load i32, ptr %arrayidx1, align 1
; CHECK-NEXT: da analyze - flow [|<]!
; CHECK-NEXT: Runtime Assumptions:
; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 %m to i2) + (-2 * (trunc i64 %n to i2))) to i64) == 0
; CHECK-NEXT: Equal predicate: (zext i2 (-2 + (trunc i64 %m to i2)) to i64) == 0
; CHECK-NEXT: Src: %0 = load i32, ptr %arrayidx1, align 1 --> Dst: %0 = load i32, ptr %arrayidx1, align 1
; CHECK-NEXT: da analyze - none!
; CHECK-NEXT: Runtime Assumptions:
; CHECK-NEXT: Equal predicate: (zext i2 ((trunc i64 %m to i2) + (-2 * (trunc i64 %n to i2))) to i64) == 0
; CHECK-NEXT: Equal predicate: (zext i2 (-2 + (trunc i64 %m to i2)) to i64) == 0
;
entry:
%mul = mul nsw i64 %n, 10
%add = add nsw i64 %mul, %m
%arrayidx = getelementptr inbounds i8, ptr %A, i64 %add
store i32 2, ptr %arrayidx, align 1
%add1 = add nsw i64 %m, 42
%arrayidx1 = getelementptr inbounds i8, ptr %A, i64 %add1
%0 = load i32, ptr %arrayidx1, align 1
ret i32 %0
}
define i32 @gep_i8_vs_i32(ptr nocapture %A, i64 %n, i64 %m) {
; CHECK-LABEL: 'gep_i8_vs_i32'
; CHECK-NEXT: Src: store i32 42, ptr %arrayidx0, align 1 --> Dst: store i32 42, ptr %arrayidx0, align 1
; CHECK-NEXT: da analyze - none!
; CHECK-NEXT: Src: store i32 42, ptr %arrayidx0, align 1 --> Dst: store i32 42, ptr %arrayidx1, align 4
; CHECK-NEXT: da analyze - output [|<]!
; CHECK-NEXT: Runtime Assumptions:
; CHECK-NEXT: Equal predicate: (zext i2 (trunc i64 %n to i2) to i64) == 0
; CHECK-NEXT: Src: store i32 42, ptr %arrayidx1, align 4 --> Dst: store i32 42, ptr %arrayidx1, align 4
; CHECK-NEXT: da analyze - none!
; CHECK-NEXT: Runtime Assumptions:
; CHECK-NEXT: Equal predicate: (zext i2 (trunc i64 %n to i2) to i64) == 0
;
entry:
%arrayidx0 = getelementptr inbounds i8, ptr %A, i64 %n
store i32 42, ptr %arrayidx0, align 1
%arrayidx1 = getelementptr inbounds i32, ptr %A, i64 %m
store i32 42, ptr %arrayidx1, align 4
ret i32 0
}
define void @linearized_accesses(i64 %n, i64 %m, i64 %o, ptr %A) {
; CHECK-LABEL: 'linearized_accesses'
; CHECK-NEXT: Src: store i32 1, ptr %idx0, align 4 --> Dst: store i32 1, ptr %idx0, align 4
; CHECK-NEXT: da analyze - output [* * *]!
; CHECK-NEXT: Src: store i32 1, ptr %idx0, align 4 --> Dst: store i32 1, ptr %idx1, align 4
; CHECK-NEXT: da analyze - output [* * *|<]!
; CHECK-NEXT: Src: store i32 1, ptr %idx1, align 4 --> Dst: store i32 1, ptr %idx1, align 4
; CHECK-NEXT: da analyze - none!
;
entry:
br label %for.i
for.i:
%i = phi i64 [ 0, %entry ], [ %i.inc, %for.i.inc ]
br label %for.j
for.j:
%j = phi i64 [ 0, %for.i ], [ %j.inc, %for.j.inc ]
br label %for.k
for.k:
%k = phi i64 [ 0, %for.j ], [ %k.inc, %for.k.inc ]
%subscript0 = mul i64 %i, %m
%subscript1 = add i64 %j, %subscript0
%subscript2 = mul i64 %subscript1, %o
%subscript3 = add i64 %subscript2, %k
%idx0 = getelementptr inbounds i64, ptr %A, i64 %subscript3 ; (i64*)(A) + i*m*o + j*o + k
store i32 1, ptr %idx0
%idx1 = getelementptr inbounds i32, ptr %A, i64 %subscript3 ; (i32*)(A) + i*m*o + j*o + k
store i32 1, ptr %idx1
br label %for.k.inc
for.k.inc:
%k.inc = add nsw i64 %k, 1
%k.exitcond = icmp eq i64 %k.inc, %o
br i1 %k.exitcond, label %for.j.inc, label %for.k
for.j.inc:
%j.inc = add nsw i64 %j, 1
%j.exitcond = icmp eq i64 %j.inc, %m
br i1 %j.exitcond, label %for.i.inc, label %for.j
for.i.inc:
%i.inc = add nsw i64 %i, 1
%i.exitcond = icmp eq i64 %i.inc, %n
br i1 %i.exitcond, label %end, label %for.i
end:
ret void
}
define void @multidim_accesses(ptr %A) {
; CHECK-LABEL: 'multidim_accesses'
; CHECK-NEXT: Src: store i32 1, ptr %idx0, align 4 --> Dst: store i32 1, ptr %idx0, align 4
; CHECK-NEXT: da analyze - none!
; CHECK-NEXT: Src: store i32 1, ptr %idx0, align 4 --> Dst: store i32 1, ptr %idx1, align 4
; CHECK-NEXT: da analyze - consistent output [0 0 0|<]!
; CHECK-NEXT: Src: store i32 1, ptr %idx1, align 4 --> Dst: store i32 1, ptr %idx1, align 4
; CHECK-NEXT: da analyze - none!
;
; FIXME: the dependence distance is not constant. Distance vector should be [* * *|<]!
; for (i = 0; i < 256; i++)
; for (j = 0; j < 256; j++)
; for (k = 0; k < 256; k++) {
; int *idx0 = (int *)((long long *)(A) + 256*256*i + 256*j + k);
; *idx0 = 1;
; int *idx1 = (int *)((int *)(A) + 256*256*i + 256*j + k);
; *idx1 = 1;
; }
entry:
br label %for.i
for.i:
%i = phi i64 [ 0, %entry ], [ %i.inc, %for.i.inc ]
br label %for.j
for.j:
%j = phi i64 [ 0, %for.i ], [ %j.inc, %for.j.inc ]
br label %for.k
for.k:
%k = phi i64 [ 0, %for.j ], [ %k.inc, %for.k.inc ]
%idx0 = getelementptr inbounds [256 x [256 x [256 x i64]]], ptr %A, i64 0, i64 %i, i64 %j, i64 %k
store i32 1, ptr %idx0
%idx1 = getelementptr inbounds [256 x [256 x [256 x i32]]], ptr %A, i64 0, i64 %i, i64 %j, i64 %k
store i32 1, ptr %idx1
br label %for.k.inc
for.k.inc:
%k.inc = add nsw i64 %k, 1
%k.exitcond = icmp eq i64 %k.inc, 256
br i1 %k.exitcond, label %for.j.inc, label %for.k
for.j.inc:
%j.inc = add nsw i64 %j, 1
%j.exitcond = icmp eq i64 %j.inc, 256
br i1 %j.exitcond, label %for.i.inc, label %for.j
for.i.inc:
%i.inc = add nsw i64 %i, 1
%i.exitcond = icmp eq i64 %i.inc, 256
br i1 %i.exitcond, label %end, label %for.i
end:
ret void
}
; for (int i = 0; i < 256; i++)
; for (int j = 0; j < 256; j++)
; for (int k = 0; k < 256; k++) {
; int *idx = (int *)((int *)(A) + 256*256*i + 256*j + k);
; *((long long *)idx) = 1;
; }
;
; There are loop-carried dependencies across iterations in the store.
define void @multidim_accesses2(ptr %A) {
; CHECK-LABEL: 'multidim_accesses2'
; CHECK-NEXT: Src: store i64 1, ptr %idx, align 4 --> Dst: store i64 1, ptr %idx, align 4
; CHECK-NEXT: da analyze - confused!
;
entry:
br label %for.i
for.i:
%i = phi i64 [ 0, %entry ], [ %i.inc, %for.i.inc ]
br label %for.j
for.j:
%j = phi i64 [ 0, %for.i ], [ %j.inc, %for.j.inc ]
br label %for.k
for.k:
%k = phi i64 [ 0, %for.j ], [ %k.inc, %for.k ]
%idx = getelementptr inbounds [256 x [256 x [256 x i32]]], ptr %A, i64 0, i64 %i, i64 %j, i64 %k
store i64 1, ptr %idx
%k.inc = add nsw i64 %k, 1
%k.exitcond = icmp eq i64 %k.inc, 256
br i1 %k.exitcond, label %for.j.inc, label %for.k
for.j.inc:
%j.inc = add nsw i64 %j, 1
%j.exitcond = icmp eq i64 %j.inc, 256
br i1 %j.exitcond, label %for.i.inc, label %for.j
for.i.inc:
%i.inc = add nsw i64 %i, 1
%i.exitcond = icmp eq i64 %i.inc, 256
br i1 %i.exitcond, label %end, label %for.i
end:
ret void
}
|
