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
248
249
250
251
252
253
254
255
256
257
258
259
260
261
|
; 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
; Check that dependence analysis correctly handles flip-flop of base addresses.
; Bug 41488 - https://github.com/llvm/llvm-project/issues/41488
define float @bug41488_test1(float %f) {
; CHECK-LABEL: 'bug41488_test1'
; CHECK-NEXT: Src: %0 = load float, ptr %p, align 4 --> Dst: %0 = load float, ptr %p, align 4
; CHECK-NEXT: da analyze - input [*]!
; CHECK-NEXT: Src: %0 = load float, ptr %p, align 4 --> Dst: store float %f, ptr %q, align 4
; CHECK-NEXT: da analyze - confused!
; CHECK-NEXT: Src: store float %f, ptr %q, align 4 --> Dst: store float %f, ptr %q, align 4
; CHECK-NEXT: da analyze - output [*]!
;
entry:
%g = alloca float, align 4
%h = alloca float, align 4
br label %for.body
for.body:
%p = phi float* [ %g, %entry ], [ %q, %for.body ]
%q = phi float* [ %h, %entry ], [ %p, %for.body ]
%0 = load float, float* %p, align 4
store float %f, float* %q, align 4
%branch_cond = fcmp ugt float %0, 0.0
br i1 %branch_cond, label %for.cond.cleanup, label %for.body
for.cond.cleanup:
ret float %f
}
define void @bug41488_test2(i32 %n) {
; CHECK-LABEL: 'bug41488_test2'
; CHECK-NEXT: Src: %0 = load float, ptr %p, align 4 --> Dst: %0 = load float, ptr %p, align 4
; CHECK-NEXT: da analyze - input [*]!
; CHECK-NEXT: Src: %0 = load float, ptr %p, align 4 --> Dst: store float 0.000000e+00, ptr %q, align 4
; CHECK-NEXT: da analyze - confused!
; CHECK-NEXT: Src: store float 0.000000e+00, ptr %q, align 4 --> Dst: store float 0.000000e+00, ptr %q, align 4
; CHECK-NEXT: da analyze - output [*]!
;
entry:
%g = alloca float, align 4
%h = alloca float, align 4
br label %for.body
for.body:
%i = phi i32 [0, %entry ], [ %inc, %for.body ]
%p = phi float* [ %g, %entry ], [ %q, %for.body ]
%q = phi float* [ %h, %entry ], [ %p, %for.body ]
%0 = load float, float* %p, align 4
store float 0.0, float* %q, align 4
%inc = add nuw i32 %i, 1
%branch_cond = icmp ult i32 %i, %n
br i1 %branch_cond, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
ret void
}
; Bug 53942 - https://github.com/llvm/llvm-project/issues/53942
define void @bug53942_foo(i32 noundef %n, ptr noalias nocapture noundef writeonly %A, ptr noalias nocapture noundef %B) {
; CHECK-LABEL: 'bug53942_foo'
; CHECK-NEXT: Src: %.pre = load double, ptr %B, align 8 --> Dst: %.pre = load double, ptr %B, align 8
; CHECK-NEXT: da analyze - consistent input [S]!
; CHECK-NEXT: Src: %.pre = load double, ptr %B, align 8 --> Dst: store double %.pre, ptr %arrayidx2, align 8
; CHECK-NEXT: da analyze - confused!
; CHECK-NEXT: Src: store double %.pre, ptr %arrayidx2, align 8 --> Dst: store double %.pre, ptr %arrayidx2, align 8
; CHECK-NEXT: da analyze - output [*]!
;
entry:
%cmp8 = icmp sgt i32 %n, 1
br i1 %cmp8, label %for.body.preheader, label %for.cond.cleanup
for.body.preheader: ; preds = %entry
%wide.trip.count = zext nneg i32 %n to i64
br label %for.body
for.cond.cleanup: ; preds = %for.body, %entry
ret void
for.body: ; preds = %for.body.preheader, %for.body
%indvars.iv = phi i64 [ 1, %for.body.preheader ], [ %indvars.iv.next, %for.body ]
%ptr1.011 = phi ptr [ %A, %for.body.preheader ], [ %ptr2.09, %for.body ]
%ptr2.09 = phi ptr [ %B, %for.body.preheader ], [ %ptr1.011, %for.body ]
%.pre = load double, ptr %B, align 8
%arrayidx2 = getelementptr inbounds double, ptr %ptr1.011, i64 %indvars.iv
store double %.pre, ptr %arrayidx2, align 8
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, %wide.trip.count
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
}
; Bug 53942 - https://github.com/llvm/llvm-project/issues/53942
define void @bug53942_bar(i32 noundef %n, ptr noalias noundef %A, ptr noalias noundef %B) {
; CHECK-LABEL: 'bug53942_bar'
; CHECK-NEXT: Src: %0 = load double, ptr %arrayidx, align 8 --> Dst: %0 = load double, ptr %arrayidx, align 8
; CHECK-NEXT: da analyze - input [*]!
; CHECK-NEXT: Src: %0 = load double, ptr %arrayidx, align 8 --> Dst: store double %0, ptr %arrayidx8, align 8
; CHECK-NEXT: da analyze - confused!
; CHECK-NEXT: Src: store double %0, ptr %arrayidx8, align 8 --> Dst: store double %0, ptr %arrayidx8, align 8
; CHECK-NEXT: da analyze - output [*]!
;
entry:
br label %for.cond
for.cond: ; preds = %for.inc, %entry
%i.0 = phi i32 [ 1, %entry ], [ %inc, %for.inc ]
%cmp = icmp slt i32 %i.0, %n
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %for.cond
br label %for.end
for.body: ; preds = %for.cond
%and = and i32 %i.0, 2
%tobool.not = icmp eq i32 %and, 0
br i1 %tobool.not, label %cond.false, label %cond.true
cond.true: ; preds = %for.body
br label %cond.end
cond.false: ; preds = %for.body
br label %cond.end
cond.end: ; preds = %cond.false, %cond.true
%cond = phi ptr [ %A, %cond.true ], [ %B, %cond.false ]
%and1 = and i32 %i.0, 2
%tobool2.not = icmp eq i32 %and1, 0
br i1 %tobool2.not, label %cond.false4, label %cond.true3
cond.true3: ; preds = %cond.end
br label %cond.end5
cond.false4: ; preds = %cond.end
br label %cond.end5
cond.end5: ; preds = %cond.false4, %cond.true3
%cond6 = phi ptr [ %B, %cond.true3 ], [ %A, %cond.false4 ]
%sub = add nsw i32 %i.0, -1
%idxprom = sext i32 %sub to i64
%arrayidx = getelementptr inbounds double, ptr %cond6, i64 %idxprom
%0 = load double, ptr %arrayidx, align 8
%idxprom7 = zext nneg i32 %i.0 to i64
%arrayidx8 = getelementptr inbounds double, ptr %cond, i64 %idxprom7
store double %0, ptr %arrayidx8, align 8
br label %for.inc
for.inc: ; preds = %cond.end5
%inc = add nuw nsw i32 %i.0, 1
br label %for.cond
for.end: ; preds = %for.cond.cleanup
ret void
}
; Pseudo-code for the following IR:
;
; void f(int A[][42]) {
; for (int i = 0; i < 100; i++)
; for (int j = 0; j < 41; j++)
; (j % 2 == 0 ? A[i][j] : A[i][j+1]) = 1;
; }
;
; FIXME: There are loop-carried dependencies between the store instruction. For
; example, the value of %ptr0 when (i, j) = (0, 1) is %A+8, which is the same
; as when (i, j) = (0, 2).
define void @non_invariant_baseptr_with_identical_obj(ptr %A) {
; CHECK-LABEL: 'non_invariant_baseptr_with_identical_obj'
; CHECK-NEXT: Src: store i32 1, ptr %idx, align 4 --> Dst: store i32 1, ptr %idx, align 4
; CHECK-NEXT: da analyze - none!
;
entry:
br label %loop.i.header
loop.i.header:
%i = phi i32 [ 0, %entry ], [ %i.inc, %loop.i.latch ]
%A1 = getelementptr i32, ptr %A, i32 1
br label %loop.j
loop.j:
%j = phi i32 [ 0, %loop.i.header ], [ %j.inc, %loop.j ]
%ptr0 = phi ptr [ %A, %loop.i.header ], [ %ptr1, %loop.j ]
%ptr1 = phi ptr [ %A1, %loop.i.header ], [ %ptr0, %loop.j ]
%idx = getelementptr [42 x i32], ptr %ptr0, i32 %i, i32 %j
store i32 1, ptr %idx
%j.inc = add i32 %j, 1
%cmp.j = icmp slt i32 %j.inc, 41
br i1 %cmp.j, label %loop.j, label %loop.i.latch
loop.i.latch:
%i.inc = add i32 %i, 1
%cmp.i = icmp slt i32 %i.inc, 100
br i1 %cmp.i, label %loop.i.header, label %exit
exit:
ret void
}
; Pseudo-code for the following IR:
;
; void f(int A[][42][42]) {
; for (int i = 0; i < 100; i++)
; for (int j = 0; j < 41; j++) {
; int *ptr0 = (j % 2 == 0 ? A[i][j] : A[i][j+1]);
; for (int k = 0; k < 42; k++)
; ptr0[k] = 1;
; }
; }
;
; Similar to the above case, but ptr0 is loop-invariant with respsect to the
; k-loop.
;
; FIXME: Same as the above case, there are loop-carried dependencies between
; the store.
define void @non_invariant_baseptr_with_identical_obj2(ptr %A) {
; CHECK-LABEL: 'non_invariant_baseptr_with_identical_obj2'
; CHECK-NEXT: Src: store i32 1, ptr %idx, align 4 --> Dst: store i32 1, ptr %idx, align 4
; CHECK-NEXT: da analyze - none!
;
entry:
br label %loop.i.header
loop.i.header:
%i = phi i32 [ 0, %entry ], [ %i.inc, %loop.i.latch ]
%A1 = getelementptr i32, ptr %A, i32 1
br label %loop.j.header
loop.j.header:
%j = phi i32 [ 0, %loop.i.header ], [ %j.inc, %loop.j.latch ]
%ptr0 = phi ptr [ %A, %loop.i.header ], [ %ptr1, %loop.j.latch ]
%ptr1 = phi ptr [ %A1, %loop.i.header ], [ %ptr0, %loop.j.latch ]
br label %loop.k
loop.k:
%k = phi i32 [ 0, %loop.j.header ], [ %k.inc, %loop.k ]
%idx = getelementptr [42 x [42 x i32]], ptr %ptr0, i32 %i, i32 %k, i32 %j
store i32 1, ptr %idx
%k.inc = add i32 %k, 1
%cmp.k = icmp slt i32 %k.inc, 42
br i1 %cmp.k, label %loop.k, label %loop.j.latch
loop.j.latch:
%j.inc = add i32 %j, 1
%cmp.j = icmp slt i32 %j.inc, 41
br i1 %cmp.j, label %loop.j.header, label %loop.i.latch
loop.i.latch:
%i.inc = add i32 %i, 1
%cmp.i = icmp slt i32 %i.inc, 100
br i1 %cmp.i, label %loop.i.header, label %exit
exit:
ret void
}
|
