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
|
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 5
; RUN: opt -passes='print<access-info>' -disable-output %s 2>&1 | FileCheck %s
target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
define void @runtime_checks_with_symbolic_max_btc_neg_1(ptr %P, ptr %S, i32 %x, i32 %y) {
; CHECK-LABEL: 'runtime_checks_with_symbolic_max_btc_neg_1'
; 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.iv = getelementptr inbounds i32, ptr %P, i32 %iv
; CHECK-NEXT: Against group GRP1:
; CHECK-NEXT: ptr %S
; CHECK-NEXT: Grouped accesses:
; CHECK-NEXT: Group GRP0:
; CHECK-NEXT: (Low: ((4 * %y) + %P) High: inttoptr (i32 -1 to ptr))
; CHECK-NEXT: Member: {((4 * %y) + %P),+,4}<%loop>
; CHECK-NEXT: Group GRP1:
; CHECK-NEXT: (Low: %S High: (4 + %S))
; CHECK-NEXT: Member: %S
; 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 i32 [ %y, %entry ], [ %iv.next, %loop ]
%gep.iv = getelementptr inbounds i32, ptr %P, i32 %iv
%l = load i32, ptr %S
store i32 %l, ptr %gep.iv, align 4
%iv.next = add nsw i32 %iv, 1
%c.2 = icmp slt i32 %iv.next, %l
br i1 %c.2, label %loop, label %exit
exit:
ret void
}
define void @runtime_check_with_symbolic_max_btc_neg_2(ptr %P, ptr %S, i32 %x, i32 %y) {
; CHECK-LABEL: 'runtime_check_with_symbolic_max_btc_neg_2'
; 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.iv = getelementptr inbounds i32, ptr %P, i32 %iv
; CHECK-NEXT: Against group GRP1:
; CHECK-NEXT: ptr %S
; CHECK-NEXT: Grouped accesses:
; CHECK-NEXT: Group GRP0:
; CHECK-NEXT: (Low: ((4 * %y) + %P) High: inttoptr (i32 -1 to ptr))
; CHECK-NEXT: Member: {((4 * %y) + %P),+,4}<%loop>
; CHECK-NEXT: Group GRP1:
; CHECK-NEXT: (Low: %S High: (4 + %S))
; CHECK-NEXT: Member: %S
; 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 i32 [ %y, %entry ], [ %iv.next, %loop ]
%gep.iv = getelementptr inbounds i32, ptr %P, i32 %iv
%l = load i32, ptr %S
store i32 %l, ptr %gep.iv, align 4
%iv.next = add nsw i32 %iv, 1
%a = and i32 %l, -2
%c.2 = icmp slt i32 %iv.next, %a
br i1 %c.2, label %loop, label %exit
exit:
ret void
}
define i32 @check_no_dep_via_bounds_compare_symbolic_max_btc_neg_1(ptr %P, i32 %x, i32 %y) {
; CHECK-LABEL: 'check_no_dep_via_bounds_compare_symbolic_max_btc_neg_1'
; CHECK-NEXT: loop:
; CHECK-NEXT: Report: unsafe dependent memory operations in loop. Use #pragma clang loop distribute(enable) to allow loop distribution to attempt to isolate the offending operations into a separate loop
; CHECK-NEXT: Unknown data dependence.
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Unknown:
; CHECK-NEXT: store i64 0, ptr %gep.iv, align 4 ->
; CHECK-NEXT: %l.2 = load i32, ptr %gep.P.4, align 4
; CHECK-EMPTY:
; CHECK-NEXT: Unknown:
; CHECK-NEXT: %l = load i32, ptr %gep.iv, align 4 ->
; CHECK-NEXT: store i64 0, ptr %gep.iv, align 4
; CHECK-EMPTY:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: Grouped accesses:
; 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:
%gep.P.4 = getelementptr inbounds nuw i8, ptr %P, i32 4
%gep.P.8 = getelementptr inbounds nuw i8, ptr %P, i32 8
br label %loop
loop:
%1 = phi i32 [ %x, %entry ], [ %sel, %loop.latch ]
%iv = phi i32 [ %y, %entry ], [ %iv.next, %loop.latch ]
%gep.iv = getelementptr inbounds i64, ptr %gep.P.8, i32 %iv
%l = load i32, ptr %gep.iv, align 4
%c.1 = icmp eq i32 %l, 3
br i1 %c.1, label %loop.latch, label %if.then
if.then: ; preds = %for.body
store i64 0, ptr %gep.iv, align 4
%l.2 = load i32, ptr %gep.P.4
br label %loop.latch
loop.latch:
%sel = phi i32 [ %l.2, %if.then ], [ %1, %loop ]
%iv.next = add nsw i32 %iv, 1
%c.2 = icmp slt i32 %iv.next, %sel
br i1 %c.2, label %loop, label %exit
exit:
%res = phi i32 [ %iv.next, %loop.latch ]
ret i32 %res
}
; Evaluating at symbolic max BTC wraps around to a positive
; offset: (2 + (2 * %y) + %P).
define void @runtime_check_with_symbolic_max_wraps_to_positive_offset(ptr %P, ptr %S, i32 %x, i32 %y) {
; CHECK-LABEL: 'runtime_check_with_symbolic_max_wraps_to_positive_offset'
; 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.iv = getelementptr inbounds i16, ptr %P, i32 %iv
; CHECK-NEXT: Against group GRP1:
; CHECK-NEXT: ptr %S
; CHECK-NEXT: Grouped accesses:
; CHECK-NEXT: Group GRP0:
; CHECK-NEXT: (Low: ((2 * %y) + %P) High: inttoptr (i32 -1 to ptr))
; CHECK-NEXT: Member: {((2 * %y) + %P),+,2}<%loop>
; CHECK-NEXT: Group GRP1:
; CHECK-NEXT: (Low: %S High: (4 + %S))
; CHECK-NEXT: Member: %S
; 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 i32 [ %y, %entry ], [ %iv.next, %loop ]
%gep.iv = getelementptr inbounds i16 , ptr %P, i32 %iv
%l = load i32, ptr %S
store i16 0, ptr %gep.iv, align 4
%iv.next = add nsw i32 %iv, 1
%a = and i32 %l, 2147483648
%c.2 = icmp slt i32 %iv.next, %a
br i1 %c.2, label %loop, label %exit
exit:
ret void
}
|
