basic-b.ll
8.05 KB
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
; RUN: opt < %s -disable-output "-passes=print<ddg>" 2>&1 | FileCheck %s
; CHECK-LABEL: 'DDG' for loop 'test1.for.body':
; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:pi-block
; CHECK-NEXT:--- start of nodes in pi-block ---
; CHECK: Node Address:[[N2:0x[0-9a-f]*]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %i.02 = phi i64 [ %inc, %test1.for.body ], [ 1, %test1.for.body.preheader ]
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N3:0x[0-9a-f]*]]
; CHECK: Node Address:[[N3]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %inc = add i64 %i.02, 1
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N2]]
; CHECK-NEXT:--- end of nodes in pi-block ---
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N4:0x[0-9a-f]*]]
; CHECK-NEXT: [def-use] to [[N5:0x[0-9a-f]*]]
; CHECK-NEXT: [def-use] to [[N6:0x[0-9a-f]*]]
; CHECK-NEXT: [def-use] to [[N7:0x[0-9a-f]*]]
; CHECK: Node Address:[[N7]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %cmp = icmp ult i64 %inc, %sub
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N8:0x[0-9a-f]*]]
; CHECK: Node Address:[[N8]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: br i1 %cmp, label %test1.for.body, label %for.end.loopexit
; CHECK-NEXT: Edges:none!
; CHECK: Node Address:[[N6]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N9:0x[0-9a-f]*]]
; CHECK: Node Address:[[N5]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %sub1 = add i64 %i.02, -1
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N10:0x[0-9a-f]*]]
; CHECK: Node Address:[[N10]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %arrayidx2 = getelementptr inbounds float, float* %a, i64 %sub1
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N9]]
; CHECK: Node Address:[[N4]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N11:0x[0-9a-f]*]]
; CHECK: Node Address:[[N11]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %0 = load float, float* %arrayidx, align 4
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N9]]
; CHECK: Node Address:[[N9]]:pi-block
; CHECK-NEXT: --- start of nodes in pi-block ---
; CHECK: Node Address:[[N12:0x[0-9a-f]*]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %1 = load float, float* %arrayidx2, align 4
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N13:0x[0-9a-f]*]]
; CHECK: Node Address:[[N13]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %add = fadd float %0, %1
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N14:0x[0-9a-f]*]]
; CHECK: Node Address:[[N14]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: store float %add, float* %arrayidx3, align 4
; CHECK-NEXT: Edges:
; CHECK-NEXT: [memory] to [[N12]]
; CHECK-NEXT:--- end of nodes in pi-block ---
; CHECK-NEXT: Edges:none!
;; Loop-carried dependence requiring edge-reversal to expose a cycle
;; in the graph.
;; void test(unsigned long n, float * restrict a, float * restrict b) {
;; for (unsigned long i = 1; i < n-1; i++)
;; a[i] = b[i] + a[i-1];
;; }
define void @test1(i64 %n, float* noalias %a, float* noalias %b) {
entry:
%sub = add i64 %n, -1
%cmp1 = icmp ult i64 1, %sub
br i1 %cmp1, label %test1.for.body, label %for.end
test1.for.body: ; preds = %entry, %test1.for.body
%i.02 = phi i64 [ %inc, %test1.for.body ], [ 1, %entry ]
%arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
%0 = load float, float* %arrayidx, align 4
%sub1 = add i64 %i.02, -1
%arrayidx2 = getelementptr inbounds float, float* %a, i64 %sub1
%1 = load float, float* %arrayidx2, align 4
%add = fadd float %0, %1
%arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
store float %add, float* %arrayidx3, align 4
%inc = add i64 %i.02, 1
%cmp = icmp ult i64 %inc, %sub
br i1 %cmp, label %test1.for.body, label %for.end
for.end: ; preds = %test1.for.body, %entry
ret void
}
; CHECK-LABEL: 'DDG' for loop 'test2.for.body':
; CHECK: Node Address:[[N1:0x[0-9a-f]*]]:pi-block
; CHECK-NEXT:--- start of nodes in pi-block ---
; CHECK: Node Address:[[N2:0x[0-9a-f]*]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %i.02 = phi i64 [ %inc, %test2.for.body ], [ 1, %test2.for.body.preheader ]
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N3:0x[0-9a-f]*]]
; CHECK: Node Address:[[N3]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %inc = add i64 %i.02, 1
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N2]]
; CHECK-NEXT:--- end of nodes in pi-block ---
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N4:0x[0-9a-f]*]]
; CHECK-NEXT: [def-use] to [[N5:0x[0-9a-f]*]]
; CHECK-NEXT: [def-use] to [[N6:0x[0-9a-f]*]]
; CHECK-NEXT: [def-use] to [[N7:0x[0-9a-f]*]]
; CHECK: Node Address:[[N7]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %cmp = icmp ult i64 %inc, %sub
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N8:0x[0-9a-f]*]]
; CHECK: Node Address:[[N8]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: br i1 %cmp, label %test2.for.body, label %for.end.loopexit
; CHECK-NEXT: Edges:none!
; CHECK: Node Address:[[N6]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N9:0x[0-9a-f]*]]
; CHECK: Node Address:[[N5]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %add1 = add i64 %i.02, 1
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N10:0x[0-9a-f]*]]
; CHECK: Node Address:[[N10]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %arrayidx2 = getelementptr inbounds float, float* %a, i64 %add1
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N11:0x[0-9a-f]*]]
; CHECK: Node Address:[[N11]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %1 = load float, float* %arrayidx2, align 4
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N12:0x[0-9a-f]*]]
; CHECK-NEXT: [memory] to [[N9]]
; CHECK: Node Address:[[N4]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N13:0x[0-9a-f]*]]
; CHECK: Node Address:[[N13]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %0 = load float, float* %arrayidx, align 4
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N12]]
; CHECK: Node Address:[[N12]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: %add = fadd float %0, %1
; CHECK-NEXT: Edges:
; CHECK-NEXT: [def-use] to [[N9]]
; CHECK: Node Address:[[N9]]:single-instruction
; CHECK-NEXT: Instructions:
; CHECK-NEXT: store float %add, float* %arrayidx3, align 4
; CHECK-NEXT: Edges:none!
;; Forward loop-carried dependence *not* causing a cycle.
;; void test2(unsigned long n, float * restrict a, float * restrict b) {
;; for (unsigned long i = 1; i < n-1; i++)
;; a[i] = b[i] + a[i+1];
;; }
define void @test2(i64 %n, float* noalias %a, float* noalias %b) {
entry:
%sub = add i64 %n, -1
%cmp1 = icmp ult i64 1, %sub
br i1 %cmp1, label %test2.for.body, label %for.end
test2.for.body: ; preds = %entry, %test2.for.body
%i.02 = phi i64 [ %inc, %test2.for.body ], [ 1, %entry ]
%arrayidx = getelementptr inbounds float, float* %b, i64 %i.02
%0 = load float, float* %arrayidx, align 4
%add1 = add i64 %i.02, 1
%arrayidx2 = getelementptr inbounds float, float* %a, i64 %add1
%1 = load float, float* %arrayidx2, align 4
%add = fadd float %0, %1
%arrayidx3 = getelementptr inbounds float, float* %a, i64 %i.02
store float %add, float* %arrayidx3, align 4
%inc = add i64 %i.02, 1
%cmp = icmp ult i64 %inc, %sub
br i1 %cmp, label %test2.for.body, label %for.end
for.end: ; preds = %test2.for.body, %entry
ret void
}