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
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
| ; RUN: opt < %s -indvars -S | FileCheck %s
target triple = "aarch64--linux-gnu"
; Provide legal integer types.
target datalayout = "n8:16:32:64"
; Check the loop exit i32 compare instruction and operand are widened to i64
; instead of truncating IV before its use in the i32 compare instruction.
@idx = common global i32 0, align 4
@e = common global i32 0, align 4
@ptr = common global i32* null, align 8
; CHECK-LABEL: @test1
; CHECK: for.body.lr.ph:
; CHECK: sext i32
; CHECK: for.cond:
; CHECK: icmp slt i64
; CHECK: for.body:
; CHECK: phi i64
define i32 @test1() {
entry:
store i32 -1, i32* @idx, align 4
%0 = load i32, i32* @e, align 4
%cmp4 = icmp slt i32 %0, 0
br i1 %cmp4, label %for.end.loopexit, label %for.body.lr.ph
for.body.lr.ph:
%1 = load i32*, i32** @ptr, align 8
%2 = load i32, i32* @e, align 4
br label %for.body
for.cond:
%inc = add nsw i32 %i.05, 1
%cmp = icmp slt i32 %i.05, %2
br i1 %cmp, label %for.body, label %for.cond.for.end.loopexit_crit_edge
for.body:
%i.05 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.cond ]
%idxprom = sext i32 %i.05 to i64
%arrayidx = getelementptr inbounds i32, i32* %1, i64 %idxprom
%3 = load i32, i32* %arrayidx, align 4
%tobool = icmp eq i32 %3, 0
br i1 %tobool, label %if.then, label %for.cond
if.then:
%i.05.lcssa = phi i32 [ %i.05, %for.body ]
store i32 %i.05.lcssa, i32* @idx, align 4
br label %for.end
for.cond.for.end.loopexit_crit_edge:
br label %for.end.loopexit
for.end.loopexit:
br label %for.end
for.end:
%4 = load i32, i32* @idx, align 4
ret i32 %4
}
; CHECK-LABEL: @test2
; CHECK: for.body4.us
; CHECK: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK: %cmp2.us = icmp ult i64
; CHECK-NOT: %2 = trunc i64 %indvars.iv.next to i32
; CHECK-NOT: %cmp2.us = icmp slt i32
define void @test2([8 x i8]* %a, i8* %b, i8 %limit) {
entry:
%conv = zext i8 %limit to i32
br i1 undef, label %for.cond1.preheader, label %for.cond1.preheader.us
for.cond1.preheader.us:
%storemerge5.us = phi i32 [ 0, %entry ], [ %inc14.us, %for.inc13.us ]
br i1 true, label %for.body4.lr.ph.us, label %for.inc13.us
for.inc13.us:
%inc14.us = add nsw i32 %storemerge5.us, 1
%cmp.us = icmp slt i32 %inc14.us, 4
br i1 %cmp.us, label %for.cond1.preheader.us, label %for.end
for.body4.us:
%storemerge14.us = phi i32 [ 0, %for.body4.lr.ph.us ], [ %inc.us, %for.body4.us ]
%idxprom.us = sext i32 %storemerge14.us to i64
%arrayidx6.us = getelementptr inbounds [8 x i8], [8 x i8]* %a, i64 %idxprom5.us, i64 %idxprom.us
%0 = load i8, i8* %arrayidx6.us, align 1
%idxprom7.us = zext i8 %0 to i64
%arrayidx8.us = getelementptr inbounds i8, i8* %b, i64 %idxprom7.us
%1 = load i8, i8* %arrayidx8.us, align 1
store i8 %1, i8* %arrayidx6.us, align 1
%inc.us = add nsw i32 %storemerge14.us, 1
%cmp2.us = icmp slt i32 %inc.us, %conv
br i1 %cmp2.us, label %for.body4.us, label %for.inc13.us
for.body4.lr.ph.us:
%idxprom5.us = sext i32 %storemerge5.us to i64
br label %for.body4.us
for.cond1.preheader:
%storemerge5 = phi i32 [ 0, %entry ], [ %inc14, %for.inc13 ]
br i1 false, label %for.inc13, label %for.inc13
for.inc13:
%inc14 = add nsw i32 %storemerge5, 1
%cmp = icmp slt i32 %inc14, 4
br i1 %cmp, label %for.cond1.preheader, label %for.end
for.end:
ret void
}
; CHECK-LABEL: @test3
; CHECK: sext i32 %b
; CHECK: for.cond:
; CHECK: phi i64
; CHECK: icmp slt i64
define i32 @test3(i32* %a, i32 %b) {
entry:
br label %for.cond
for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%cmp = icmp slt i32 %i.0, %b
br i1 %cmp, label %for.body, label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %sum.0, %0
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret i32 %sum.0
}
declare i32 @fn1(i8 signext)
; PR21030
; CHECK-LABEL: @test4
; CHECK: for.body:
; CHECK: phi i32
; CHECK: icmp sgt i8
define i32 @test4(i32 %a) {
entry:
br label %for.body
for.body:
%c.07 = phi i8 [ -3, %entry ], [ %dec, %for.body ]
%conv6 = zext i8 %c.07 to i32
%or = or i32 %a, %conv6
%conv3 = trunc i32 %or to i8
%call = call i32 @fn1(i8 signext %conv3)
%dec = add i8 %c.07, -1
%cmp = icmp sgt i8 %dec, -14
br i1 %cmp, label %for.body, label %for.end
for.end:
ret i32 0
}
; CHECK-LABEL: @test5
; CHECK: zext i32 %b
; CHECK: for.cond:
; CHECK: phi i64
; CHECK: icmp ule i64
define i32 @test5(i32* %a, i32 %b) {
entry:
br label %for.cond
for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%cmp = icmp ule i32 %i.0, %b
br i1 %cmp, label %for.body, label %for.end
for.body:
%idxprom = zext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %sum.0, %0
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret i32 %sum.0
}
define i32 @test6(i32* %a, i32 %b) {
; CHECK-LABEL: @test6(
; CHECK: [[B_SEXT:%[a-z0-9]+]] = sext i32 %b to i64
; CHECK: for.cond:
; CHECK: icmp sle i64 %indvars.iv, [[B_SEXT]]
entry:
br label %for.cond
for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%cmp = icmp sle i32 %i.0, %b
br i1 %cmp, label %for.body, label %for.end
for.body:
%idxprom = zext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %sum.0, %0
%inc = add nsw i32 %i.0, 1
br label %for.cond
for.end:
ret i32 %sum.0
}
define i32 @test7(i32* %a, i32 %b) {
; CHECK-LABEL: @test7(
; CHECK: [[B_ZEXT:%[a-z0-9]+]] = zext i32 %b to i64
; CHECK: [[B_SEXT:%[a-z0-9]+]] = sext i32 %b to i64
; CHECK: for.cond:
; CHECK: icmp ule i64 %indvars.iv, [[B_ZEXT]]
; CHECK: for.body:
; CHECK: icmp sle i64 %indvars.iv, [[B_SEXT]]
entry:
br label %for.cond
for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%cmp = icmp ule i32 %i.0, %b
br i1 %cmp, label %for.body, label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %sum.0, %0
%inc = add nsw i32 %i.0, 1
%cmp2 = icmp sle i32 %i.0, %b
br i1 %cmp2, label %for.cond, label %for.end
for.end:
ret i32 %sum.0
}
define i32 @test8(i32* %a, i32 %b, i32 %init) {
; CHECK-LABEL: @test8(
; CHECK: [[INIT_SEXT:%[a-z0-9]+]] = sext i32 %init to i64
; CHECK: [[B_ZEXT:%[a-z0-9]+]] = zext i32 %b to i64
; CHECK: for.cond:
; Note: %indvars.iv is the sign extension of %i.0
; CHECK: %indvars.iv = phi i64 [ [[INIT_SEXT]], %for.cond.preheader ], [ %indvars.iv.next, %for.body ]
; CHECK: icmp ule i64 %indvars.iv, [[B_ZEXT]]
entry:
%e = icmp sgt i32 %init, 0
br i1 %e, label %for.cond, label %leave
for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i.0 = phi i32 [ %init, %entry ], [ %inc, %for.body ]
%cmp = icmp ule i32 %i.0, %b
br i1 %cmp, label %for.body, label %for.end
for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %sum.0, %0
%inc = add nsw i32 %i.0, 1
%cmp2 = icmp slt i32 0, %inc
br i1 %cmp2, label %for.cond, label %for.end
for.end:
ret i32 %sum.0
leave:
ret i32 0
}
define i32 @test9(i32* %a, i32 %b, i32 %init) {
; CHECK-LABEL: @test9(
; CHECK: [[INIT_ZEXT:%[a-z0-9]+]] = zext i32 %init to i64
; CHECK: [[B_SEXT:%[a-z0-9]+]] = sext i32 %b to i64
; CHECK: for.cond:
; Note: %indvars.iv is the zero extension of %i.0
; CHECK: %indvars.iv = phi i64 [ [[INIT_ZEXT]], %for.cond.preheader ], [ %indvars.iv.next, %for.body ]
; CHECK: icmp slt i64 %indvars.iv, [[B_SEXT]]
entry:
%e = icmp sgt i32 %init, 0
br i1 %e, label %for.cond, label %leave
for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i.0 = phi i32 [ %init, %entry ], [ %inc, %for.body ]
%cmp = icmp slt i32 %i.0, %b
br i1 %cmp, label %for.body, label %for.end
for.body:
%idxprom = zext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %sum.0, %0
%inc = add nsw i32 %i.0, 1
%cmp2 = icmp slt i32 0, %inc
br i1 %cmp2, label %for.cond, label %for.end
for.end:
ret i32 %sum.0
leave:
ret i32 0
}
declare void @consume.i64(i64)
declare void @consume.i1(i1)
define i32 @test10(i32 %v) {
; CHECK-LABEL: @test10(
entry:
; CHECK-NOT: zext
br label %loop
loop:
; CHECK: [[WIDE_V:%[a-z0-9]+]] = sext i32 %v to i64
; CHECK: loop:
; CHECK: %indvars.iv = phi i64 [ %indvars.iv.next, %loop ], [ 0, %entry ]
; CHECK: %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
; CHECK: [[MUL:%[a-z0-9]+]] = mul nsw i64 %indvars.iv, -1
; CHECK: [[CMP:%[a-z0-9]+]] = icmp eq i64 [[MUL]], [[WIDE_V]]
; CHECK: call void @consume.i1(i1 [[CMP]])
%i = phi i32 [ 0, %entry ], [ %i.inc, %loop ]
%i.inc = add i32 %i, 1
%iv = mul i32 %i, -1
%cmp = icmp eq i32 %iv, %v
call void @consume.i1(i1 %cmp)
%be.cond = icmp slt i32 %i.inc, 11
%ext = sext i32 %iv to i64
call void @consume.i64(i64 %ext)
br i1 %be.cond, label %loop, label %leave
leave:
ret i32 22
}
|