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
|
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
; RUN: opt -passes='print<access-info><allow-partial>' -disable-output %s 2>&1 | FileCheck %s
define void @dependency_check_and_runtime_checks_needed_select_of_invariant_ptrs(ptr %a, ptr %b, ptr %c, i64 %offset, i64 %n) {
; CHECK-LABEL: 'dependency_check_and_runtime_checks_needed_select_of_invariant_ptrs'
; CHECK-NEXT: loop:
; CHECK-NEXT: Memory dependences are safe with run-time checks
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Check 0:
; CHECK-NEXT: Comparing group GRP0:
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
; CHECK-NEXT: Against group GRP1:
; CHECK-NEXT: %select = select i1 %cmp, ptr %b, ptr %c
; CHECK-NEXT: Check 1:
; CHECK-NEXT: Comparing group GRP0:
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
; CHECK-NEXT: Against group GRP2:
; CHECK-NEXT: %select = select i1 %cmp, ptr %b, ptr %c
; CHECK-NEXT: Check 2:
; CHECK-NEXT: Comparing group GRP0:
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
; CHECK-NEXT: Against group GRP3:
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
; CHECK-NEXT: Check 3:
; CHECK-NEXT: Comparing group GRP1:
; CHECK-NEXT: %select = select i1 %cmp, ptr %b, ptr %c
; CHECK-NEXT: Against group GRP2:
; CHECK-NEXT: %select = select i1 %cmp, ptr %b, ptr %c
; CHECK-NEXT: Check 4:
; CHECK-NEXT: Comparing group GRP1:
; CHECK-NEXT: %select = select i1 %cmp, ptr %b, ptr %c
; CHECK-NEXT: Against group GRP3:
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
; CHECK-NEXT: Check 5:
; CHECK-NEXT: Comparing group GRP2:
; CHECK-NEXT: %select = select i1 %cmp, ptr %b, ptr %c
; CHECK-NEXT: Against group GRP3:
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
; CHECK-NEXT: Grouped accesses:
; CHECK-NEXT: Group GRP0:
; CHECK-NEXT: (Low: %a High: ((4 * %n) + %a))
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
; CHECK-NEXT: Group GRP1:
; CHECK-NEXT: (Low: %b High: (4 + %b))
; CHECK-NEXT: Member: %b
; CHECK-NEXT: Group GRP2:
; CHECK-NEXT: (Low: %c High: (4 + %c))
; CHECK-NEXT: Member: %c
; CHECK-NEXT: Group GRP3:
; CHECK-NEXT: (Low: ((4 * %offset) + %a) High: ((4 * %offset) + (4 * %n) + %a))
; CHECK-NEXT: Member: {((4 * %offset) + %a),+,4}<%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
; CHECK-EMPTY:
; CHECK-NEXT: Expressions re-written:
;
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
%l1 = load float, ptr %gep.a.iv, align 4
%iv.offset = add i64 %iv, %offset
%gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
%l2 = load float, ptr %gep.a.iv.off, align 4
%ad = fadd fast float %l1, %l2
store float %ad, ptr %gep.a.iv, align 4
%cmp = fcmp ult float %l1, 10.0
%select = select i1 %cmp, ptr %b, ptr %c
store float 0.0, ptr %select
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, %n
br i1 %exitcond, label %exit, label %loop
exit:
ret void
}
define void @dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs(ptr %a, ptr %b, ptr %c, i64 %offset, i64 %n) {
; CHECK-LABEL: 'dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs'
; CHECK-NEXT: loop:
; CHECK-NEXT: Memory dependences are safe with run-time checks
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Check 0:
; CHECK-NEXT: Comparing group GRP0:
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
; CHECK-NEXT: Against group GRP1:
; CHECK-NEXT: %select = select i1 %cmp, ptr %gep.b, ptr %gep.c
; CHECK-NEXT: Check 1:
; CHECK-NEXT: Comparing group GRP0:
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
; CHECK-NEXT: Against group GRP2:
; CHECK-NEXT: %select = select i1 %cmp, ptr %gep.b, ptr %gep.c
; CHECK-NEXT: Check 2:
; CHECK-NEXT: Comparing group GRP0:
; CHECK-NEXT: %gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
; CHECK-NEXT: Against group GRP3:
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
; CHECK-NEXT: Check 3:
; CHECK-NEXT: Comparing group GRP1:
; CHECK-NEXT: %select = select i1 %cmp, ptr %gep.b, ptr %gep.c
; CHECK-NEXT: Against group GRP2:
; CHECK-NEXT: %select = select i1 %cmp, ptr %gep.b, ptr %gep.c
; CHECK-NEXT: Check 4:
; CHECK-NEXT: Comparing group GRP1:
; CHECK-NEXT: %select = select i1 %cmp, ptr %gep.b, ptr %gep.c
; CHECK-NEXT: Against group GRP3:
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
; CHECK-NEXT: Check 5:
; CHECK-NEXT: Comparing group GRP2:
; CHECK-NEXT: %select = select i1 %cmp, ptr %gep.b, ptr %gep.c
; CHECK-NEXT: Against group GRP3:
; CHECK-NEXT: %gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
; CHECK-NEXT: Grouped accesses:
; CHECK-NEXT: Group GRP0:
; CHECK-NEXT: (Low: %a High: ((4 * %n) + %a))
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
; CHECK-NEXT: Group GRP1:
; CHECK-NEXT: (Low: %b High: ((4 * %n) + %b))
; CHECK-NEXT: Member: {%b,+,4}<%loop>
; CHECK-NEXT: Group GRP2:
; CHECK-NEXT: (Low: %c High: ((4 * %n) + %c))
; CHECK-NEXT: Member: {%c,+,4}<%loop>
; CHECK-NEXT: Group GRP3:
; CHECK-NEXT: (Low: ((4 * %offset) + %a) High: ((4 * %offset) + (4 * %n) + %a))
; CHECK-NEXT: Member: {((4 * %offset) + %a),+,4}<%loop>
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
; CHECK-EMPTY:
; CHECK-NEXT: Expressions re-written:
;
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
%l1 = load float, ptr %gep.a.iv, align 4
%iv.offset = add i64 %iv, %offset
%gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
%l2 = load float, ptr %gep.a.iv.off, align 4
%ad = fadd fast float %l1, %l2
store float %ad, ptr %gep.a.iv, align 4
%gep.b = getelementptr inbounds float, ptr %b, i64 %iv
%gep.c = getelementptr inbounds float, ptr %c, i64 %iv
%cmp = fcmp ult float %l1, 10.0
%select = select i1 %cmp, ptr %gep.b, ptr %gep.c
store float 0.0, ptr %select
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, %n
br i1 %exitcond, label %exit, label %loop
exit:
ret void
}
define void @dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs_may_wrap_1(ptr %a, ptr %b, ptr %c, i64 %offset, i64 %n) {
; CHECK-LABEL: 'dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs_may_wrap_1'
; CHECK-NEXT: loop:
; CHECK-NEXT: Report: cannot identify array bounds
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
; CHECK-NEXT: Group GRP0:
; CHECK-NEXT: (Low: ((4 * %offset) + %a) High: ((4 * %offset) + (4 * %n) + %a))
; CHECK-NEXT: Member: {((4 * %offset) + %a),+,4}<%loop>
; CHECK-NEXT: Group GRP1:
; CHECK-NEXT: (Low: %a High: ((4 * %n) + %a))
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
; CHECK-NEXT: Generated run-time checks are incomplete
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
; CHECK-EMPTY:
; CHECK-NEXT: Expressions re-written:
;
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%iv2 = phi i64 [ 0, %entry ], [ %iv2.next, %loop ]
%gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
%l1 = load float, ptr %gep.a.iv, align 4
%iv.offset = add i64 %iv, %offset
%gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
%l2 = load float, ptr %gep.a.iv.off, align 4
%ad = fadd fast float %l1, %l2
store float %ad, ptr %gep.a.iv, align 4
%gep.b = getelementptr float, ptr %b, i64 %iv2
%gep.c = getelementptr inbounds float, ptr %c, i64 %iv
%cmp = fcmp ult float %l1, 10.0
%select = select i1 %cmp, ptr %gep.b, ptr %gep.c
store float 0.0, ptr %select
%iv.next = add nuw nsw i64 %iv, 1
%iv2.next = add i64 %iv2, 2
%exitcond = icmp eq i64 %iv.next, %n
br i1 %exitcond, label %exit, label %loop
exit:
ret void
}
define void @dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs_may_wrap_2(ptr %a, ptr %b, ptr %c, i64 %offset, i64 %n) {
; CHECK-LABEL: 'dependency_check_and_runtime_checks_needed_select_of_ptr_add_recs_may_wrap_2'
; CHECK-NEXT: loop:
; CHECK-NEXT: Report: cannot identify array bounds
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
; CHECK-NEXT: Group GRP0:
; CHECK-NEXT: (Low: ((4 * %offset) + %a) High: ((4 * %offset) + (4 * %n) + %a))
; CHECK-NEXT: Member: {((4 * %offset) + %a),+,4}<%loop>
; CHECK-NEXT: Group GRP1:
; CHECK-NEXT: (Low: %a High: ((4 * %n) + %a))
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
; CHECK-NEXT: Member: {%a,+,4}<nuw><%loop>
; CHECK-NEXT: Generated run-time checks are incomplete
; CHECK-EMPTY:
; CHECK-NEXT: Non vectorizable stores to invariant address were not found in loop.
; CHECK-NEXT: SCEV assumptions:
; CHECK-EMPTY:
; CHECK-NEXT: Expressions re-written:
;
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%iv2 = phi i64 [ 0, %entry ], [ %iv2.next, %loop ]
%gep.a.iv = getelementptr inbounds float, ptr %a, i64 %iv
%l1 = load float, ptr %gep.a.iv, align 4
%iv.offset = add i64 %iv, %offset
%gep.a.iv.off = getelementptr inbounds float, ptr %a, i64 %iv.offset
%l2 = load float, ptr %gep.a.iv.off, align 4
%ad = fadd fast float %l1, %l2
store float %ad, ptr %gep.a.iv, align 4
%gep.b = getelementptr inbounds float, ptr %b, i64 %iv
%gep.c = getelementptr inbounds float, ptr %c, i64 %iv2
%cmp = fcmp ult float %l1, 10.0
%select = select i1 %cmp, ptr %gep.b, ptr %gep.c
store float 0.0, ptr %select
%iv.next = add nuw nsw i64 %iv, 1
%iv2.next = add i64 %iv2, 2
%exitcond = icmp eq i64 %iv.next, %n
br i1 %exitcond, label %exit, label %loop
exit:
ret void
}
|
