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
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basic-aa -dse -S | FileCheck %s
; RUN: opt < %s -aa-pipeline=basic-aa -passes=dse -S | FileCheck %s
target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
declare i8* @calloc(i64, i64)
declare void @memset_pattern16(i8*, i8*, i64)
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
declare void @llvm.memset.element.unordered.atomic.p0i8.i64(i8* nocapture, i8, i64, i32) nounwind
declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i1) nounwind
declare void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* nocapture, i8* nocapture, i64, i32) nounwind
declare void @llvm.init.trampoline(i8*, i8*, i8*)
; **** Noop load->store tests **************************************************
; We CAN optimize volatile loads.
define void @test_load_volatile(i32* %Q) {
; CHECK-LABEL: @test_load_volatile(
; CHECK-NEXT: [[A:%.*]] = load volatile i32, i32* [[Q:%.*]], align 4
; CHECK-NEXT: ret void
;
%a = load volatile i32, i32* %Q
store i32 %a, i32* %Q
ret void
}
; We can NOT optimize volatile stores.
define void @test_store_volatile(i32* %Q) {
; CHECK-LABEL: @test_store_volatile(
; CHECK-NEXT: [[A:%.*]] = load i32, i32* [[Q:%.*]], align 4
; CHECK-NEXT: store volatile i32 [[A]], i32* [[Q]], align 4
; CHECK-NEXT: ret void
;
%a = load i32, i32* %Q
store volatile i32 %a, i32* %Q
ret void
}
; PR2599 - load -> store to same address.
define void @test12({ i32, i32 }* %x) nounwind {
; CHECK-LABEL: @test12(
; CHECK-NEXT: [[TEMP7:%.*]] = getelementptr { i32, i32 }, { i32, i32 }* [[X:%.*]], i32 0, i32 1
; CHECK-NEXT: [[TEMP8:%.*]] = load i32, i32* [[TEMP7]], align 4
; CHECK-NEXT: [[TEMP17:%.*]] = sub i32 0, [[TEMP8]]
; CHECK-NEXT: store i32 [[TEMP17]], i32* [[TEMP7]], align 4
; CHECK-NEXT: ret void
;
%temp4 = getelementptr { i32, i32 }, { i32, i32 }* %x, i32 0, i32 0
%temp5 = load i32, i32* %temp4, align 4
%temp7 = getelementptr { i32, i32 }, { i32, i32 }* %x, i32 0, i32 1
%temp8 = load i32, i32* %temp7, align 4
%temp17 = sub i32 0, %temp8
store i32 %temp5, i32* %temp4, align 4
store i32 %temp17, i32* %temp7, align 4
ret void
}
; Remove redundant store if loaded value is in another block.
define i32 @test26(i1 %c, i32* %p) {
; CHECK-LABEL: @test26(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 [[C:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br label [[BB3:%.*]]
; CHECK: bb2:
; CHECK-NEXT: br label [[BB3]]
; CHECK: bb3:
; CHECK-NEXT: ret i32 0
;
entry:
%v = load i32, i32* %p, align 4
br i1 %c, label %bb1, label %bb2
bb1:
br label %bb3
bb2:
store i32 %v, i32* %p, align 4
br label %bb3
bb3:
ret i32 0
}
; Remove redundant store if loaded value is in another block.
define i32 @test27(i1 %c, i32* %p) {
; CHECK-LABEL: @test27(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 [[C:%.*]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br label [[BB3:%.*]]
; CHECK: bb2:
; CHECK-NEXT: br label [[BB3]]
; CHECK: bb3:
; CHECK-NEXT: ret i32 0
;
entry:
%v = load i32, i32* %p, align 4
br i1 %c, label %bb1, label %bb2
bb1:
br label %bb3
bb2:
br label %bb3
bb3:
store i32 %v, i32* %p, align 4
ret i32 0
}
; Remove redundant store if loaded value is in another block inside a loop.
define i32 @test31(i1 %c, i32* %p, i32 %i) {
; CHECK-LABEL: @test31(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[BB1:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br i1 [[C:%.*]], label [[BB1]], label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: ret i32 0
;
entry:
%v = load i32, i32* %p, align 4
br label %bb1
bb1:
store i32 %v, i32* %p, align 4
br i1 %c, label %bb1, label %bb2
bb2:
ret i32 0
}
; Don't remove "redundant" store if %p is possibly stored to.
define i32 @test46(i1 %c, i32* %p, i32* %p2, i32 %i) {
; CHECK-LABEL: @test46(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[V:%.*]] = load i32, i32* [[P:%.*]], align 4
; CHECK-NEXT: br label [[BB1:%.*]]
; CHECK: bb1:
; CHECK-NEXT: store i32 [[V]], i32* [[P]], align 4
; CHECK-NEXT: br i1 [[C:%.*]], label [[BB1]], label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: store i32 0, i32* [[P2:%.*]], align 4
; CHECK-NEXT: br i1 [[C]], label [[BB3:%.*]], label [[BB1]]
; CHECK: bb3:
; CHECK-NEXT: ret i32 0
;
entry:
%v = load i32, i32* %p, align 4
br label %bb1
bb1:
store i32 %v, i32* %p, align 4
br i1 %c, label %bb1, label %bb2
bb2:
store i32 0, i32* %p2, align 4
br i1 %c, label %bb3, label %bb1
bb3:
ret i32 0
}
declare void @unknown_func()
; Remove redundant store, which is in the lame loop as the load.
define i32 @test33(i1 %c, i32* %p, i32 %i) {
; CHECK-LABEL: @test33(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[BB1:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: call void @unknown_func()
; CHECK-NEXT: br i1 [[C:%.*]], label [[BB1]], label [[BB3:%.*]]
; CHECK: bb3:
; CHECK-NEXT: ret i32 0
;
entry:
br label %bb1
bb1:
%v = load i32, i32* %p, align 4
br label %bb2
bb2:
store i32 %v, i32* %p, align 4
; Might read and overwrite value at %p, but doesn't matter.
call void @unknown_func()
br i1 %c, label %bb1, label %bb3
bb3:
ret i32 0
}
declare void @unkown_write(i32*)
; We can't remove the "noop" store around an unkown write.
define void @test43(i32* %Q) {
; CHECK-LABEL: @test43(
; CHECK-NEXT: [[A:%.*]] = load i32, i32* [[Q:%.*]], align 4
; CHECK-NEXT: call void @unkown_write(i32* [[Q]])
; CHECK-NEXT: store i32 [[A]], i32* [[Q]], align 4
; CHECK-NEXT: ret void
;
%a = load i32, i32* %Q
call void @unkown_write(i32* %Q)
store i32 %a, i32* %Q
ret void
}
; We CAN remove it when the unkown write comes AFTER.
define void @test44(i32* %Q) {
; CHECK-LABEL: @test44(
; CHECK-NEXT: call void @unkown_write(i32* [[Q:%.*]])
; CHECK-NEXT: ret void
;
%a = load i32, i32* %Q
store i32 %a, i32* %Q
call void @unkown_write(i32* %Q)
ret void
}
define void @test45(i32* %Q) {
; CHECK-LABEL: @test45(
; CHECK-NEXT: ret void
;
%a = load i32, i32* %Q
store i32 10, i32* %Q
store i32 %a, i32* %Q
ret void
}
define i32 @test48(i1 %c, i32* %p) {
; CHECK-LABEL: @test48(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[V:%.*]] = load i32, i32* [[P:%.*]], align 4
; CHECK-NEXT: br i1 [[C:%.*]], label [[BB0:%.*]], label [[BB0_0:%.*]]
; CHECK: bb0:
; CHECK-NEXT: store i32 0, i32* [[P]], align 4
; CHECK-NEXT: br i1 [[C]], label [[BB1:%.*]], label [[BB2:%.*]]
; CHECK: bb0.0:
; CHECK-NEXT: br label [[BB1]]
; CHECK: bb1:
; CHECK-NEXT: store i32 [[V]], i32* [[P]], align 4
; CHECK-NEXT: br i1 [[C]], label [[BB2]], label [[BB0]]
; CHECK: bb2:
; CHECK-NEXT: ret i32 0
;
entry:
%v = load i32, i32* %p, align 4
br i1 %c, label %bb0, label %bb0.0
bb0:
store i32 0, i32* %p
br i1 %c, label %bb1, label %bb2
bb0.0:
br label %bb1
bb1:
store i32 %v, i32* %p, align 4
br i1 %c, label %bb2, label %bb0
bb2:
ret i32 0
}
define i32 @test47(i1 %c, i32* %p, i32 %i) {
; CHECK-LABEL: @test47(
; CHECK-NEXT: entry:
; CHECK-NEXT: br label [[BB1:%.*]]
; CHECK: bb1:
; CHECK-NEXT: br i1 [[C:%.*]], label [[BB1]], label [[BB2:%.*]]
; CHECK: bb2:
; CHECK-NEXT: br i1 [[C]], label [[BB3:%.*]], label [[BB1]]
; CHECK: bb3:
; CHECK-NEXT: ret i32 0
;
entry:
%v = load i32, i32* %p, align 4
br label %bb1
bb1:
store i32 %v, i32* %p, align 4
br i1 %c, label %bb1, label %bb2
bb2:
store i32 %v, i32* %p, align 4
br i1 %c, label %bb3, label %bb1
bb3:
ret i32 0
}
; Test case from PR47887.
define void @test_noalias_store_between_load_and_store(i32* noalias %x, i32* noalias %y) {
; CHECK-LABEL: @test_noalias_store_between_load_and_store(
; CHECK-NEXT: entry:
; CHECK-NEXT: store i32 0, i32* [[Y:%.*]], align 4
; CHECK-NEXT: ret void
;
entry:
%lv = load i32, i32* %x, align 4
store i32 0, i32* %y, align 4
store i32 %lv, i32* %x, align 4
ret void
}
; Test case from PR47887. Currently we eliminate the dead `store i32 %inc, i32* %x`,
; but not the no-op `store i32 %lv, i32* %x`. That is because no-op stores are
; eliminated before dead stores for the same def.
define void @test_noalias_store_between_load_and_store_elimin_order(i32* noalias %x, i32* noalias %y) {
; CHECK-LABEL: @test_noalias_store_between_load_and_store_elimin_order(
; CHECK-NEXT: entry:
; CHECK-NEXT: store i32 0, i32* [[Y:%.*]], align 4
; CHECK-NEXT: ret void
;
entry:
%lv = load i32, i32* %x, align 4
%inc = add nsw i32 %lv, 1
store i32 %inc, i32* %x, align 4
store i32 0, i32* %y, align 4
store i32 %lv, i32* %x, align 4
ret void
}
; PR50143
define i8* @store_zero_after_calloc_inaccessiblememonly() {
; CHECK-LABEL: @store_zero_after_calloc_inaccessiblememonly(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 1, i64 10) #[[ATTR6:[0-9]+]]
; CHECK-NEXT: store i8 0, i8* [[CALL]], align 1
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 1, i64 10) inaccessiblememonly
store i8 0, i8* %call
ret i8* %call
}
define i8* @zero_memset_after_calloc() {
; CHECK-LABEL: @zero_memset_after_calloc(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4)
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4)
call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 40000, i1 false)
ret i8* %call
}
define i8* @volatile_zero_memset_after_calloc() {
; CHECK-LABEL: @volatile_zero_memset_after_calloc(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4)
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[CALL]], i8 0, i64 40000, i1 true)
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4)
call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 40000, i1 true)
ret i8* %call
}
define i8* @zero_memset_and_store_after_calloc(i8 %v) {
; CHECK-LABEL: @zero_memset_and_store_after_calloc(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4)
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4)
store i8 %v, i8* %call
call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 40000, i1 false)
ret i8* %call
}
define i8* @partial_zero_memset_after_calloc() {
; CHECK-LABEL: @partial_zero_memset_after_calloc(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4)
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4)
call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 20, i1 false)
ret i8* %call
}
define i8* @partial_zero_memset_and_store_after_calloc(i8 %v) {
; CHECK-LABEL: @partial_zero_memset_and_store_after_calloc(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4)
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, i8* [[CALL]], i64 30
; CHECK-NEXT: store i8 [[V:%.*]], i8* [[GEP]], align 1
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4)
%gep = getelementptr inbounds i8, i8* %call, i64 30
store i8 %v, i8* %gep
call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 20, i1 false)
ret i8* %call
}
define i8* @zero_memset_and_store_with_dyn_index_after_calloc(i8 %v, i64 %idx) {
; CHECK-LABEL: @zero_memset_and_store_with_dyn_index_after_calloc(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4)
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4)
%gep = getelementptr inbounds i8, i8* %call, i64 %idx
store i8 %v, i8* %gep
call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 40000, i1 false)
ret i8* %call
}
define i8* @partial_zero_memset_and_store_with_dyn_index_after_calloc(i8 %v, i64 %idx) {
; CHECK-LABEL: @partial_zero_memset_and_store_with_dyn_index_after_calloc(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4)
; CHECK-NEXT: [[GEP:%.*]] = getelementptr inbounds i8, i8* [[CALL]], i64 [[IDX:%.*]]
; CHECK-NEXT: store i8 [[V:%.*]], i8* [[GEP]], align 1
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[CALL]], i8 0, i64 20, i1 false)
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4)
%gep = getelementptr inbounds i8, i8* %call, i64 %idx
store i8 %v, i8* %gep
call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 20, i1 false)
ret i8* %call
}
define i8* @zero_memset_after_calloc_inaccessiblememonly() {
; CHECK-LABEL: @zero_memset_after_calloc_inaccessiblememonly(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4) #[[ATTR6]]
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[CALL]], i8 0, i64 40000, i1 false)
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4) inaccessiblememonly
call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 40000, i1 false)
ret i8* %call
}
define i8* @cst_nonzero_memset_after_calloc() {
; CHECK-LABEL: @cst_nonzero_memset_after_calloc(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4)
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[CALL]], i8 1, i64 40000, i1 false)
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4)
call void @llvm.memset.p0i8.i64(i8* %call, i8 1, i64 40000, i1 false)
ret i8* %call
}
define i8* @nonzero_memset_after_calloc(i8 %v) {
; CHECK-LABEL: @nonzero_memset_after_calloc(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4)
; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[CALL]], i8 [[V:%.*]], i64 40000, i1 false)
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4)
call void @llvm.memset.p0i8.i64(i8* %call, i8 %v, i64 40000, i1 false)
ret i8* %call
}
; PR11896
; The first memset is dead, because calloc provides zero-filled memory.
; TODO: This could be replaced with a call to malloc + memset_pattern16.
define i8* @memset_pattern16_after_calloc(i8* %pat) {
; CHECK-LABEL: @memset_pattern16_after_calloc(
; CHECK-NEXT: [[CALL:%.*]] = tail call i8* @calloc(i64 10000, i64 4)
; CHECK-NEXT: call void @memset_pattern16(i8* [[CALL]], i8* [[PAT:%.*]], i64 40000)
; CHECK-NEXT: ret i8* [[CALL]]
;
%call = tail call i8* @calloc(i64 10000, i64 4) #1
call void @llvm.memset.p0i8.i64(i8* align 4 %call, i8 0, i64 40000, i1 false)
call void @memset_pattern16(i8* %call, i8* %pat, i64 40000) #1
ret i8* %call
}
|
