loop-unrolling.ll
10.6 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
234
235
236
237
238
239
240
241
242
243
244
245
246
247
; RUN: opt -mtriple=armv7 -mcpu=cortex-a57 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A
; RUN: opt -mtriple=thumbv7 -mcpu=cortex-a57 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A
; RUN: opt -mtriple=thumbv7 -mcpu=cortex-a72 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-A
; RUN: opt -mtriple=thumbv8m -mcpu=cortex-m23 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T1
; RUN: opt -mtriple=thumbv8m.main -mcpu=cortex-m33 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T2
; RUN: opt -mtriple=thumbv7em -mcpu=cortex-m7 -loop-unroll -S %s -o - | FileCheck %s --check-prefix=CHECK-UNROLL-T2
; CHECK-LABEL: partial
define arm_aapcs_vfpcc void @partial(i32* nocapture %C, i32* nocapture readonly %A, i32* nocapture readonly %B) local_unnamed_addr #0 {
entry:
br label %for.body
; CHECK-LABEL: for.body
for.body:
; CHECK-UNROLL-A: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, %entry ], [ [[IV2:%[a-z.0-9]+]], %for.body ]
; CHECK-UNROLL-A: [[IV1:%[a-z.0-9]+]] = add nuw nsw i32 [[IV0]], 1
; CHECK-UNROLL-A: [[IV2]] = add nuw nsw i32 [[IV1]], 1
; CHECK-UNROLL-A: [[CMP:%[a-z.0-9]+]] = icmp eq i32 [[IV2]], 1024
; CHECK-UNROLL-A: br i1 [[CMP]], label [[END:%[a-z.]+]], label %for.body
; CHECK-UNROLL-T1: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, %entry ], [ [[IV1:%[a-z.0-9]+]], %for.body ]
; CHECK-UNROLL-T1: [[IV1]] = add nuw nsw i32 [[IV0]], 1
; CHECK-UNROLL-T1: [[CMP:%[a-z.0-9]+]] = icmp eq i32 [[IV1]], 1024
; CHECK-UNROLL-T1: br i1 [[CMP]], label [[END:%[a-z.]+]], label %for.body
; CHECK-UNROLL-T2: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, %entry ], [ [[IV16:%[a-z.0-9]+]], %for.body ]
; CHECK-UNROLL-T2: [[IV1:%[a-z.0-9]+]] = add nuw nsw i32 [[IV0]], 1
; CHECK-UNROLL-T2: [[IV2:%[a-z.0-9]+]] = add nuw nsw i32 [[IV1]], 1
; CHECK-UNROLL-T2: [[IV3:%[a-z.0-9]+]] = add nuw nsw i32 [[IV2]], 1
; CHECK-UNROLL-T2: [[IV4:%[a-z.0-9]+]] = add nuw nsw i32 [[IV3]], 1
; CHECK-UNROLL-T2: [[IV5:%[a-z.0-9]+]] = add nuw nsw i32 [[IV4]], 1
; CHECK-UNROLL-T2: [[IV6:%[a-z.0-9]+]] = add nuw nsw i32 [[IV5]], 1
; CHECK-UNROLL-T2: [[IV7:%[a-z.0-9]+]] = add nuw nsw i32 [[IV6]], 1
; CHECK-UNROLL-T2: [[IV8:%[a-z.0-9]+]] = add nuw nsw i32 [[IV7]], 1
; CHECK-UNROLL-T2: [[IV9:%[a-z.0-9]+]] = add nuw nsw i32 [[IV8]], 1
; CHECK-UNROLL-T2: [[IV10:%[a-z.0-9]+]] = add nuw nsw i32 [[IV9]], 1
; CHECK-UNROLL-T2: [[IV11:%[a-z.0-9]+]] = add nuw nsw i32 [[IV10]], 1
; CHECK-UNROLL-T2: [[IV12:%[a-z.0-9]+]] = add nuw nsw i32 [[IV11]], 1
; CHECK-UNROLL-T2: [[IV13:%[a-z.0-9]+]] = add nuw nsw i32 [[IV12]], 1
; CHECK-UNROLL-T2: [[IV14:%[a-z.0-9]+]] = add nuw nsw i32 [[IV13]], 1
; CHECK-UNROLL-T2: [[IV15:%[a-z.0-9]+]] = add nuw nsw i32 [[IV14]], 1
; CHECK-UNROLL-T2: [[IV16]] = add nuw nsw i32 [[IV15]], 1
; CHECK-UNROLL-T2: [[CMP:%[a-z.0-9]+]] = icmp eq i32 [[IV16]], 1024
; CHECK-UNROLL-T2: br i1 [[CMP]], label [[END:%[a-z.]+]], label %for.body
%i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.08
%0 = load i32, i32* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %B, i32 %i.08
%1 = load i32, i32* %arrayidx1, align 4
%mul = mul nsw i32 %1, %0
%arrayidx2 = getelementptr inbounds i32, i32* %C, i32 %i.08
store i32 %mul, i32* %arrayidx2, align 4
%inc = add nuw nsw i32 %i.08, 1
%exitcond = icmp eq i32 %inc, 1024
br i1 %exitcond, label %for.cond.cleanup, label %for.body
for.cond.cleanup:
ret void
}
; CHECK-LABEL: runtime
define arm_aapcs_vfpcc void @runtime(i32* nocapture %C, i32* nocapture readonly %A, i32* nocapture readonly %B, i32 %N) local_unnamed_addr #0 {
entry:
%cmp8 = icmp eq i32 %N, 0
br i1 %cmp8, label %for.cond.cleanup, label %for.body
; CHECK-LABEL: for.body
for.body:
; CHECK-UNROLL-A: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, [[PRE:%[a-z.0-9]+]] ], [ [[IV2:%[a-z.0-9]+]], %for.body ]
; CHECK-UNROLL-A: [[IV1:%[a-z.0-9]+]] = add nuw nsw i32 [[IV0]], 1
; CHECK-UNROLL-A: [[IV2]] = add nuw i32 [[IV1]], 1
; CHECK-UNROLL-A: br
; CHECK-UNROLL-T1: %i.09 = phi i32 [ %inc, %for.body ], [ 0
; CHECK-UNROLL-T1: %inc = add nuw i32 %i.09, 1
; CHECK-UNROLL-T1: %exitcond = icmp eq i32 %inc, %N
; CHECK-UNROLL-T1: br
; CHECK-UNROLL-T2: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, [[PRE:%[a-z.0-9]+]] ], [ [[IV4:%[a-z.0-9]+]], %for.body ]
; CHECK-UNROLL-T2: [[IV1:%[a-z.0-9]+]] = add nuw nsw i32 [[IV0]], 1
; CHECK-UNROLL-T2: [[IV2:%[a-z.0-9]+]] = add nuw nsw i32 [[IV1]], 1
; CHECK-UNROLL-T2: [[IV3:%[a-z.0-9]+]] = add nuw nsw i32 [[IV2]], 1
; CHECK-UNROLL-T2: [[IV4]] = add nuw i32 [[IV3]], 1
; CHECK-UNROLL-T2: br
; CHECK-UNROLL-T2: for.body.epil:
; CHECK-UNROLL-T2: for.body.epil.1:
; CHECK-UNROLL-T2: for.body.epil.2:
%i.09 = phi i32 [ %inc, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.09
%0 = load i32, i32* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %B, i32 %i.09
%1 = load i32, i32* %arrayidx1, align 4
%mul = mul nsw i32 %1, %0
%arrayidx2 = getelementptr inbounds i32, i32* %C, i32 %i.09
store i32 %mul, i32* %arrayidx2, align 4
%inc = add nuw i32 %i.09, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.cond.cleanup, label %for.body
for.cond.cleanup:
ret void
}
; CHECK-LABEL: nested_runtime
define arm_aapcs_vfpcc void @nested_runtime(i32* nocapture %C, i16* nocapture readonly %A, i16* nocapture readonly %B, i32 %N) local_unnamed_addr #0 {
entry:
%cmp25 = icmp eq i32 %N, 0
br i1 %cmp25, label %for.cond.cleanup, label %for.body4.lr.ph
for.body4.lr.ph:
%h.026 = phi i32 [ %inc11, %for.cond.cleanup3 ], [ 0, %entry ]
%mul = mul i32 %h.026, %N
br label %for.body4
for.cond.cleanup:
ret void
for.cond.cleanup3:
%inc11 = add nuw i32 %h.026, 1
%exitcond27 = icmp eq i32 %inc11, %N
br i1 %exitcond27, label %for.cond.cleanup, label %for.body4.lr.ph
; CHECK-LABEL: for.body4
for.body4:
; CHECK-UNROLL-T1: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, [[PRE:%[a-z0-9.]+]] ], [ [[IV1:%[a-z.0-9]+]], %for.body4 ]
; CHECK-UNROLL-T1: [[IV1]] = add nuw i32 [[IV0]], 1
; CHECK-UNROLL-T1: br
; CHECK-UNROLL-T2: for.body4.epil:
; CHECK-UNROLL-T2: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, [[PRE:%[a-z0-9.]+]] ], [ [[IV4:%[a-z.0-9]+]], %for.body4 ]
; CHECK-UNROLL-T2: [[IV1:%[a-z.0-9]+]] = add nuw nsw i32 [[IV0]], 1
; CHECK-UNROLL-T2: [[IV2:%[a-z.0-9]+]] = add nuw nsw i32 [[IV1]], 1
; CHECK-UNROLL-T2: [[IV3:%[a-z.0-9]+]] = add nuw nsw i32 [[IV2]], 1
; CHECK-UNROLL-T2: [[IV4]] = add nuw i32 [[IV3]], 1
; CHECK-UNROLL-T2: br
; CHECK-UNROLL-T2: for.body4.epil.1:
; CHECK-UNROLL-T2: for.body4.epil.2:
%w.024 = phi i32 [ 0, %for.body4.lr.ph ], [ %inc, %for.body4 ]
%add = add i32 %w.024, %mul
%arrayidx = getelementptr inbounds i16, i16* %A, i32 %add
%0 = load i16, i16* %arrayidx, align 2
%conv = sext i16 %0 to i32
%arrayidx5 = getelementptr inbounds i16, i16* %B, i32 %w.024
%1 = load i16, i16* %arrayidx5, align 2
%conv6 = sext i16 %1 to i32
%mul7 = mul nsw i32 %conv6, %conv
%arrayidx8 = getelementptr inbounds i32, i32* %C, i32 %w.024
%2 = load i32, i32* %arrayidx8, align 4
%add9 = add nsw i32 %mul7, %2
store i32 %add9, i32* %arrayidx8, align 4
%inc = add nuw i32 %w.024, 1
%exitcond = icmp eq i32 %inc, %N
br i1 %exitcond, label %for.cond.cleanup3, label %for.body4
}
; CHECK-LABEL: loop_call
define arm_aapcs_vfpcc void @loop_call(i32* nocapture %C, i32* nocapture readonly %A, i32* nocapture readonly %B) local_unnamed_addr #1 {
entry:
br label %for.body
for.cond.cleanup:
ret void
; CHECK-LABEL: for.body
for.body:
; CHECK-UNROLL-A: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, %entry ], [ [[IV1:%[a-z.0-9]+]], %for.body ]
; CHECK-UNROLL-A: [[IV1]] = add nuw nsw i32 [[IV0]], 1
; CHECK-UNROLL-A: icmp eq i32 [[IV1]], 1024
; CHECK-UNROLL-A: br
; CHECK-UNROLL-T1: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, %entry ], [ [[IV1:%[a-z.0-9]+]], %for.body ]
; CHECK-UNROLL-T1: [[IV1]] = add nuw nsw i32 [[IV0]], 1
; CHECK-UNROLL-T1: icmp eq i32 [[IV1]], 1024
; CHECK-UNROLL-T1: br
; CHECK-UNROLL-T2: [[IV0:%[a-z.0-9]+]] = phi i32 [ 0, %entry ], [ [[IV1:%[a-z.0-9]+]], %for.body ]
; CHECK-UNROLL-T2: [[IV1]] = add nuw nsw i32 [[IV0]], 1
; CHECK-UNROLL-T2: icmp eq i32 [[IV1]], 1024
; CHECK-UNROLL-T2: br
%i.08 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.08
%0 = load i32, i32* %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, i32* %B, i32 %i.08
%1 = load i32, i32* %arrayidx1, align 4
%call = tail call arm_aapcs_vfpcc i32 @some_func(i32 %0, i32 %1) #3
%arrayidx2 = getelementptr inbounds i32, i32* %C, i32 %i.08
store i32 %call, i32* %arrayidx2, align 4
%inc = add nuw nsw i32 %i.08, 1
%exitcond = icmp eq i32 %inc, 1024
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
; CHECK-LABEL: iterate_inc
; CHECK-UNROLL-A: %n.addr.04 = phi %struct.Node* [ %1, %while.body ], [ %n, %while.body.preheader ]
; CHECK-UNROLL-A: %tobool = icmp eq %struct.Node* %1, null
; CHECK-UNROLL-A: br i1 %tobool
; CHECK-UNROLL-A-NOT: load
; CHECK-UNROLL-T1: %n.addr.04 = phi %struct.Node* [ %1, %while.body ], [ %n, %while.body.preheader ]
; CHECK-UNROLL-T1: %tobool = icmp eq %struct.Node* %1, null
; CHECK-UNROLL-T1: br i1 %tobool
; CHECK-UNROLL-T1-NOT: load
; CHECK-UNROLL-T2: [[CMP0:%[a-z.0-9]+]] = icmp eq %struct.Node* [[VAR0:%[a-z.0-9]+]], null
; CHECK-UNROLL-T2: br i1 [[CMP0]], label [[END:%[a-z.0-9]+]]
; CHECK-UNROLL-T2: [[CMP1:%[a-z.0-9]+]] = icmp eq %struct.Node* [[VAR1:%[a-z.0-9]+]], null
; CHECK-UNROLL-T2: br i1 [[CMP1]], label [[END]]
; CHECK-UNROLL-T2: [[CMP2:%[a-z.0-9]+]] = icmp eq %struct.Node* [[VAR2:%[a-z.0-9]+]], null
; CHECK-UNROLL-T2: br i1 [[CMP2]], label [[END]]
; CHECK-UNROLL-T2: [[CMP3:%[a-z.0-9]+]] = icmp eq %struct.Node* [[VAR3:%[a-z.0-9]+]], null
; CHECK-UNROLL-T2: br i1 [[CMP3]], label [[END]]
; CHECK-UNROLL-T2: [[CMP4:%[a-z.0-9]+]] = icmp eq %struct.Node* [[VAR4:%[a-z.0-9]+]], null
; CHECK-UNROLL-T2: br i1 [[CMP4]], label [[END]]
; CHECK-UNROLL-T2-NOT: load
%struct.Node = type { %struct.Node*, i32 }
define arm_aapcscc void @iterate_inc(%struct.Node* %n) local_unnamed_addr #0 {
entry:
%tobool3 = icmp eq %struct.Node* %n, null
br i1 %tobool3, label %while.end, label %while.body.preheader
while.body.preheader:
br label %while.body
while.body:
%n.addr.04 = phi %struct.Node* [ %1, %while.body ], [ %n, %while.body.preheader ]
%val = getelementptr inbounds %struct.Node, %struct.Node* %n.addr.04, i32 0, i32 1
%0 = load i32, i32* %val, align 4
%add = add nsw i32 %0, 1
store i32 %add, i32* %val, align 4
%next = getelementptr inbounds %struct.Node, %struct.Node* %n.addr.04, i32 0, i32 0
%1 = load %struct.Node*, %struct.Node** %next, align 4
%tobool = icmp eq %struct.Node* %1, null
br i1 %tobool, label %while.end, label %while.body
while.end:
ret void
}
declare arm_aapcs_vfpcc i32 @some_func(i32, i32) local_unnamed_addr #2