aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm14/lib/Transforms/Scalar/DeadStoreElimination.cpp
blob: c5c8e880eb3d5a16392ff514290c8f76af74d0e6 (plain) (blame)
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
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
//===- DeadStoreElimination.cpp - MemorySSA Backed Dead Store Elimination -===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// The code below implements dead store elimination using MemorySSA. It uses
// the following general approach: given a MemoryDef, walk upwards to find
// clobbering MemoryDefs that may be killed by the starting def. Then check
// that there are no uses that may read the location of the original MemoryDef
// in between both MemoryDefs. A bit more concretely:
//
// For all MemoryDefs StartDef:
// 1. Get the next dominating clobbering MemoryDef (MaybeDeadAccess) by walking
//    upwards.
// 2. Check that there are no reads between MaybeDeadAccess and the StartDef by
//    checking all uses starting at MaybeDeadAccess and walking until we see
//    StartDef.
// 3. For each found CurrentDef, check that:
//   1. There are no barrier instructions between CurrentDef and StartDef (like
//       throws or stores with ordering constraints).
//   2. StartDef is executed whenever CurrentDef is executed.
//   3. StartDef completely overwrites CurrentDef.
// 4. Erase CurrentDef from the function and MemorySSA.
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar/DeadStoreElimination.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/MapVector.h"
#include "llvm/ADT/PostOrderIterator.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/CaptureTracking.h"
#include "llvm/Analysis/GlobalsModRef.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/MemoryBuiltins.h"
#include "llvm/Analysis/MemoryLocation.h"
#include "llvm/Analysis/MemorySSA.h"
#include "llvm/Analysis/MemorySSAUpdater.h"
#include "llvm/Analysis/MustExecute.h"
#include "llvm/Analysis/PostDominators.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/Argument.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/IntrinsicInst.h"
#include "llvm/IR/Intrinsics.h"
#include "llvm/IR/LLVMContext.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/PassManager.h"
#include "llvm/IR/PatternMatch.h"
#include "llvm/IR/Value.h"
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/DebugCounter.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/MathExtras.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/AssumeBundleBuilder.h"
#include "llvm/Transforms/Utils/BuildLibCalls.h"
#include "llvm/Transforms/Utils/Local.h"
#include <algorithm>
#include <cassert>
#include <cstddef>
#include <cstdint>
#include <iterator>
#include <map>
#include <utility>

using namespace llvm;
using namespace PatternMatch;

#define DEBUG_TYPE "dse"

STATISTIC(NumRemainingStores, "Number of stores remaining after DSE");
STATISTIC(NumRedundantStores, "Number of redundant stores deleted");
STATISTIC(NumFastStores, "Number of stores deleted");
STATISTIC(NumFastOther, "Number of other instrs removed");
STATISTIC(NumCompletePartials, "Number of stores dead by later partials");
STATISTIC(NumModifiedStores, "Number of stores modified");
STATISTIC(NumCFGChecks, "Number of stores modified");
STATISTIC(NumCFGTries, "Number of stores modified");
STATISTIC(NumCFGSuccess, "Number of stores modified");
STATISTIC(NumGetDomMemoryDefPassed,
          "Number of times a valid candidate is returned from getDomMemoryDef");
STATISTIC(NumDomMemDefChecks,
          "Number iterations check for reads in getDomMemoryDef");

DEBUG_COUNTER(MemorySSACounter, "dse-memoryssa",
              "Controls which MemoryDefs are eliminated.");

static cl::opt<bool>
EnablePartialOverwriteTracking("enable-dse-partial-overwrite-tracking",
  cl::init(true), cl::Hidden,
  cl::desc("Enable partial-overwrite tracking in DSE"));

static cl::opt<bool>
EnablePartialStoreMerging("enable-dse-partial-store-merging",
  cl::init(true), cl::Hidden,
  cl::desc("Enable partial store merging in DSE"));

static cl::opt<unsigned>
    MemorySSAScanLimit("dse-memoryssa-scanlimit", cl::init(150), cl::Hidden,
                       cl::desc("The number of memory instructions to scan for "
                                "dead store elimination (default = 150)"));
static cl::opt<unsigned> MemorySSAUpwardsStepLimit(
    "dse-memoryssa-walklimit", cl::init(90), cl::Hidden,
    cl::desc("The maximum number of steps while walking upwards to find "
             "MemoryDefs that may be killed (default = 90)"));

static cl::opt<unsigned> MemorySSAPartialStoreLimit(
    "dse-memoryssa-partial-store-limit", cl::init(5), cl::Hidden,
    cl::desc("The maximum number candidates that only partially overwrite the "
             "killing MemoryDef to consider"
             " (default = 5)"));

static cl::opt<unsigned> MemorySSADefsPerBlockLimit(
    "dse-memoryssa-defs-per-block-limit", cl::init(5000), cl::Hidden,
    cl::desc("The number of MemoryDefs we consider as candidates to eliminated "
             "other stores per basic block (default = 5000)"));

static cl::opt<unsigned> MemorySSASameBBStepCost(
    "dse-memoryssa-samebb-cost", cl::init(1), cl::Hidden,
    cl::desc(
        "The cost of a step in the same basic block as the killing MemoryDef"
        "(default = 1)"));

static cl::opt<unsigned>
    MemorySSAOtherBBStepCost("dse-memoryssa-otherbb-cost", cl::init(5),
                             cl::Hidden,
                             cl::desc("The cost of a step in a different basic "
                                      "block than the killing MemoryDef"
                                      "(default = 5)"));

static cl::opt<unsigned> MemorySSAPathCheckLimit(
    "dse-memoryssa-path-check-limit", cl::init(50), cl::Hidden,
    cl::desc("The maximum number of blocks to check when trying to prove that "
             "all paths to an exit go through a killing block (default = 50)"));

// This flags allows or disallows DSE to optimize MemorySSA during its
// traversal. Note that DSE optimizing MemorySSA may impact other passes
// downstream of the DSE invocation and can lead to issues not being
// reproducible in isolation (i.e. when MemorySSA is built from scratch). In
// those cases, the flag can be used to check if DSE's MemorySSA optimizations
// impact follow-up passes.
static cl::opt<bool>
    OptimizeMemorySSA("dse-optimize-memoryssa", cl::init(true), cl::Hidden,
                      cl::desc("Allow DSE to optimize memory accesses."));

//===----------------------------------------------------------------------===//
// Helper functions
//===----------------------------------------------------------------------===//
using OverlapIntervalsTy = std::map<int64_t, int64_t>;
using InstOverlapIntervalsTy = DenseMap<Instruction *, OverlapIntervalsTy>;

/// Returns true if the end of this instruction can be safely shortened in
/// length.
static bool isShortenableAtTheEnd(Instruction *I) {
  // Don't shorten stores for now
  if (isa<StoreInst>(I))
    return false;

  if (IntrinsicInst *II = dyn_cast<IntrinsicInst>(I)) {
    switch (II->getIntrinsicID()) {
      default: return false;
      case Intrinsic::memset:
      case Intrinsic::memcpy:
      case Intrinsic::memcpy_element_unordered_atomic:
      case Intrinsic::memset_element_unordered_atomic:
        // Do shorten memory intrinsics.
        // FIXME: Add memmove if it's also safe to transform.
        return true;
    }
  }

  // Don't shorten libcalls calls for now.

  return false;
}

/// Returns true if the beginning of this instruction can be safely shortened
/// in length.
static bool isShortenableAtTheBeginning(Instruction *I) {
  // FIXME: Handle only memset for now. Supporting memcpy/memmove should be
  // easily done by offsetting the source address.
  return isa<AnyMemSetInst>(I);
}

static uint64_t getPointerSize(const Value *V, const DataLayout &DL,
                               const TargetLibraryInfo &TLI,
                               const Function *F) {
  uint64_t Size;
  ObjectSizeOpts Opts;
  Opts.NullIsUnknownSize = NullPointerIsDefined(F);

  if (getObjectSize(V, Size, DL, &TLI, Opts))
    return Size;
  return MemoryLocation::UnknownSize;
}

namespace {

enum OverwriteResult {
  OW_Begin,
  OW_Complete,
  OW_End,
  OW_PartialEarlierWithFullLater,
  OW_MaybePartial,
  OW_None,
  OW_Unknown
};

} // end anonymous namespace

/// Check if two instruction are masked stores that completely
/// overwrite one another. More specifically, \p KillingI has to
/// overwrite \p DeadI.
static OverwriteResult isMaskedStoreOverwrite(const Instruction *KillingI,
                                              const Instruction *DeadI,
                                              BatchAAResults &AA) {
  const auto *KillingII = dyn_cast<IntrinsicInst>(KillingI);
  const auto *DeadII = dyn_cast<IntrinsicInst>(DeadI);
  if (KillingII == nullptr || DeadII == nullptr)
    return OW_Unknown;
  if (KillingII->getIntrinsicID() != Intrinsic::masked_store ||
      DeadII->getIntrinsicID() != Intrinsic::masked_store)
    return OW_Unknown;
  // Pointers.
  Value *KillingPtr = KillingII->getArgOperand(1)->stripPointerCasts();
  Value *DeadPtr = DeadII->getArgOperand(1)->stripPointerCasts();
  if (KillingPtr != DeadPtr && !AA.isMustAlias(KillingPtr, DeadPtr))
    return OW_Unknown;
  // Masks.
  // TODO: check that KillingII's mask is a superset of the DeadII's mask.
  if (KillingII->getArgOperand(3) != DeadII->getArgOperand(3))
    return OW_Unknown;
  return OW_Complete;
}

/// Return 'OW_Complete' if a store to the 'KillingLoc' location completely
/// overwrites a store to the 'DeadLoc' location, 'OW_End' if the end of the
/// 'DeadLoc' location is completely overwritten by 'KillingLoc', 'OW_Begin'
/// if the beginning of the 'DeadLoc' location is overwritten by 'KillingLoc'.
/// 'OW_PartialEarlierWithFullLater' means that a dead (big) store was
/// overwritten by a killing (smaller) store which doesn't write outside the big
/// store's memory locations. Returns 'OW_Unknown' if nothing can be determined.
/// NOTE: This function must only be called if both \p KillingLoc and \p
/// DeadLoc belong to the same underlying object with valid \p KillingOff and
/// \p DeadOff.
static OverwriteResult isPartialOverwrite(const MemoryLocation &KillingLoc,
                                          const MemoryLocation &DeadLoc,
                                          int64_t KillingOff, int64_t DeadOff,
                                          Instruction *DeadI,
                                          InstOverlapIntervalsTy &IOL) {
  const uint64_t KillingSize = KillingLoc.Size.getValue();
  const uint64_t DeadSize = DeadLoc.Size.getValue();
  // We may now overlap, although the overlap is not complete. There might also
  // be other incomplete overlaps, and together, they might cover the complete
  // dead store.
  // Note: The correctness of this logic depends on the fact that this function
  // is not even called providing DepWrite when there are any intervening reads.
  if (EnablePartialOverwriteTracking &&
      KillingOff < int64_t(DeadOff + DeadSize) &&
      int64_t(KillingOff + KillingSize) >= DeadOff) {

    // Insert our part of the overlap into the map.
    auto &IM = IOL[DeadI];
    LLVM_DEBUG(dbgs() << "DSE: Partial overwrite: DeadLoc [" << DeadOff << ", "
                      << int64_t(DeadOff + DeadSize) << ") KillingLoc ["
                      << KillingOff << ", " << int64_t(KillingOff + KillingSize)
                      << ")\n");

    // Make sure that we only insert non-overlapping intervals and combine
    // adjacent intervals. The intervals are stored in the map with the ending
    // offset as the key (in the half-open sense) and the starting offset as
    // the value.
    int64_t KillingIntStart = KillingOff;
    int64_t KillingIntEnd = KillingOff + KillingSize;

    // Find any intervals ending at, or after, KillingIntStart which start
    // before KillingIntEnd.
    auto ILI = IM.lower_bound(KillingIntStart);
    if (ILI != IM.end() && ILI->second <= KillingIntEnd) {
      // This existing interval is overlapped with the current store somewhere
      // in [KillingIntStart, KillingIntEnd]. Merge them by erasing the existing
      // intervals and adjusting our start and end.
      KillingIntStart = std::min(KillingIntStart, ILI->second);
      KillingIntEnd = std::max(KillingIntEnd, ILI->first);
      ILI = IM.erase(ILI);

      // Continue erasing and adjusting our end in case other previous
      // intervals are also overlapped with the current store.
      //
      // |--- dead 1 ---|  |--- dead 2 ---|
      //     |------- killing---------|
      //
      while (ILI != IM.end() && ILI->second <= KillingIntEnd) {
        assert(ILI->second > KillingIntStart && "Unexpected interval");
        KillingIntEnd = std::max(KillingIntEnd, ILI->first);
        ILI = IM.erase(ILI);
      }
    }

    IM[KillingIntEnd] = KillingIntStart;

    ILI = IM.begin();
    if (ILI->second <= DeadOff && ILI->first >= int64_t(DeadOff + DeadSize)) {
      LLVM_DEBUG(dbgs() << "DSE: Full overwrite from partials: DeadLoc ["
                        << DeadOff << ", " << int64_t(DeadOff + DeadSize)
                        << ") Composite KillingLoc [" << ILI->second << ", "
                        << ILI->first << ")\n");
      ++NumCompletePartials;
      return OW_Complete;
    }
  }

  // Check for a dead store which writes to all the memory locations that
  // the killing store writes to.
  if (EnablePartialStoreMerging && KillingOff >= DeadOff &&
      int64_t(DeadOff + DeadSize) > KillingOff &&
      uint64_t(KillingOff - DeadOff) + KillingSize <= DeadSize) {
    LLVM_DEBUG(dbgs() << "DSE: Partial overwrite a dead load [" << DeadOff
                      << ", " << int64_t(DeadOff + DeadSize)
                      << ") by a killing store [" << KillingOff << ", "
                      << int64_t(KillingOff + KillingSize) << ")\n");
    // TODO: Maybe come up with a better name?
    return OW_PartialEarlierWithFullLater;
  }

  // Another interesting case is if the killing store overwrites the end of the
  // dead store.
  //
  //      |--dead--|
  //                |--   killing   --|
  //
  // In this case we may want to trim the size of dead store to avoid
  // generating stores to addresses which will definitely be overwritten killing
  // store.
  if (!EnablePartialOverwriteTracking &&
      (KillingOff > DeadOff && KillingOff < int64_t(DeadOff + DeadSize) &&
       int64_t(KillingOff + KillingSize) >= int64_t(DeadOff + DeadSize)))
    return OW_End;

  // Finally, we also need to check if the killing store overwrites the
  // beginning of the dead store.
  //
  //                |--dead--|
  //      |--  killing  --|
  //
  // In this case we may want to move the destination address and trim the size
  // of dead store to avoid generating stores to addresses which will definitely
  // be overwritten killing store.
  if (!EnablePartialOverwriteTracking &&
      (KillingOff <= DeadOff && int64_t(KillingOff + KillingSize) > DeadOff)) {
    assert(int64_t(KillingOff + KillingSize) < int64_t(DeadOff + DeadSize) &&
           "Expect to be handled as OW_Complete");
    return OW_Begin;
  }
  // Otherwise, they don't completely overlap.
  return OW_Unknown;
}

/// Returns true if the memory which is accessed by the second instruction is not
/// modified between the first and the second instruction.
/// Precondition: Second instruction must be dominated by the first
/// instruction.
static bool
memoryIsNotModifiedBetween(Instruction *FirstI, Instruction *SecondI,
                           BatchAAResults &AA, const DataLayout &DL,
                           DominatorTree *DT) {
  // Do a backwards scan through the CFG from SecondI to FirstI. Look for
  // instructions which can modify the memory location accessed by SecondI.
  //
  // While doing the walk keep track of the address to check. It might be
  // different in different basic blocks due to PHI translation.
  using BlockAddressPair = std::pair<BasicBlock *, PHITransAddr>;
  SmallVector<BlockAddressPair, 16> WorkList;
  // Keep track of the address we visited each block with. Bail out if we
  // visit a block with different addresses.
  DenseMap<BasicBlock *, Value *> Visited;

  BasicBlock::iterator FirstBBI(FirstI);
  ++FirstBBI;
  BasicBlock::iterator SecondBBI(SecondI);
  BasicBlock *FirstBB = FirstI->getParent();
  BasicBlock *SecondBB = SecondI->getParent();
  MemoryLocation MemLoc;
  if (auto *MemSet = dyn_cast<MemSetInst>(SecondI))
    MemLoc = MemoryLocation::getForDest(MemSet);
  else
    MemLoc = MemoryLocation::get(SecondI);

  auto *MemLocPtr = const_cast<Value *>(MemLoc.Ptr);

  // Start checking the SecondBB.
  WorkList.push_back(
      std::make_pair(SecondBB, PHITransAddr(MemLocPtr, DL, nullptr)));
  bool isFirstBlock = true;

  // Check all blocks going backward until we reach the FirstBB.
  while (!WorkList.empty()) {
    BlockAddressPair Current = WorkList.pop_back_val();
    BasicBlock *B = Current.first;
    PHITransAddr &Addr = Current.second;
    Value *Ptr = Addr.getAddr();

    // Ignore instructions before FirstI if this is the FirstBB.
    BasicBlock::iterator BI = (B == FirstBB ? FirstBBI : B->begin());

    BasicBlock::iterator EI;
    if (isFirstBlock) {
      // Ignore instructions after SecondI if this is the first visit of SecondBB.
      assert(B == SecondBB && "first block is not the store block");
      EI = SecondBBI;
      isFirstBlock = false;
    } else {
      // It's not SecondBB or (in case of a loop) the second visit of SecondBB.
      // In this case we also have to look at instructions after SecondI.
      EI = B->end();
    }
    for (; BI != EI; ++BI) {
      Instruction *I = &*BI;
      if (I->mayWriteToMemory() && I != SecondI)
        if (isModSet(AA.getModRefInfo(I, MemLoc.getWithNewPtr(Ptr))))
          return false;
    }
    if (B != FirstBB) {
      assert(B != &FirstBB->getParent()->getEntryBlock() &&
          "Should not hit the entry block because SI must be dominated by LI");
      for (BasicBlock *Pred : predecessors(B)) {
        PHITransAddr PredAddr = Addr;
        if (PredAddr.NeedsPHITranslationFromBlock(B)) {
          if (!PredAddr.IsPotentiallyPHITranslatable())
            return false;
          if (PredAddr.PHITranslateValue(B, Pred, DT, false))
            return false;
        }
        Value *TranslatedPtr = PredAddr.getAddr();
        auto Inserted = Visited.insert(std::make_pair(Pred, TranslatedPtr));
        if (!Inserted.second) {
          // We already visited this block before. If it was with a different
          // address - bail out!
          if (TranslatedPtr != Inserted.first->second)
            return false;
          // ... otherwise just skip it.
          continue;
        }
        WorkList.push_back(std::make_pair(Pred, PredAddr));
      }
    }
  }
  return true;
}

static bool tryToShorten(Instruction *DeadI, int64_t &DeadStart,
                         uint64_t &DeadSize, int64_t KillingStart,
                         uint64_t KillingSize, bool IsOverwriteEnd) {
  auto *DeadIntrinsic = cast<AnyMemIntrinsic>(DeadI);
  Align PrefAlign = DeadIntrinsic->getDestAlign().valueOrOne();

  // We assume that memet/memcpy operates in chunks of the "largest" native
  // type size and aligned on the same value. That means optimal start and size
  // of memset/memcpy should be modulo of preferred alignment of that type. That
  // is it there is no any sense in trying to reduce store size any further
  // since any "extra" stores comes for free anyway.
  // On the other hand, maximum alignment we can achieve is limited by alignment
  // of initial store.

  // TODO: Limit maximum alignment by preferred (or abi?) alignment of the
  // "largest" native type.
  // Note: What is the proper way to get that value?
  // Should TargetTransformInfo::getRegisterBitWidth be used or anything else?
  // PrefAlign = std::min(DL.getPrefTypeAlign(LargestType), PrefAlign);

  int64_t ToRemoveStart = 0;
  uint64_t ToRemoveSize = 0;
  // Compute start and size of the region to remove. Make sure 'PrefAlign' is
  // maintained on the remaining store.
  if (IsOverwriteEnd) {
    // Calculate required adjustment for 'KillingStart' in order to keep
    // remaining store size aligned on 'PerfAlign'.
    uint64_t Off =
        offsetToAlignment(uint64_t(KillingStart - DeadStart), PrefAlign);
    ToRemoveStart = KillingStart + Off;
    if (DeadSize <= uint64_t(ToRemoveStart - DeadStart))
      return false;
    ToRemoveSize = DeadSize - uint64_t(ToRemoveStart - DeadStart);
  } else {
    ToRemoveStart = DeadStart;
    assert(KillingSize >= uint64_t(DeadStart - KillingStart) &&
           "Not overlapping accesses?");
    ToRemoveSize = KillingSize - uint64_t(DeadStart - KillingStart);
    // Calculate required adjustment for 'ToRemoveSize'in order to keep
    // start of the remaining store aligned on 'PerfAlign'.
    uint64_t Off = offsetToAlignment(ToRemoveSize, PrefAlign);
    if (Off != 0) {
      if (ToRemoveSize <= (PrefAlign.value() - Off))
        return false;
      ToRemoveSize -= PrefAlign.value() - Off;
    }
    assert(isAligned(PrefAlign, ToRemoveSize) &&
           "Should preserve selected alignment");
  }

  assert(ToRemoveSize > 0 && "Shouldn't reach here if nothing to remove");
  assert(DeadSize > ToRemoveSize && "Can't remove more than original size");

  uint64_t NewSize = DeadSize - ToRemoveSize;
  if (auto *AMI = dyn_cast<AtomicMemIntrinsic>(DeadI)) {
    // When shortening an atomic memory intrinsic, the newly shortened
    // length must remain an integer multiple of the element size.
    const uint32_t ElementSize = AMI->getElementSizeInBytes();
    if (0 != NewSize % ElementSize)
      return false;
  }

  LLVM_DEBUG(dbgs() << "DSE: Remove Dead Store:\n  OW "
                    << (IsOverwriteEnd ? "END" : "BEGIN") << ": " << *DeadI
                    << "\n  KILLER [" << ToRemoveStart << ", "
                    << int64_t(ToRemoveStart + ToRemoveSize) << ")\n");

  Value *DeadWriteLength = DeadIntrinsic->getLength();
  Value *TrimmedLength = ConstantInt::get(DeadWriteLength->getType(), NewSize);
  DeadIntrinsic->setLength(TrimmedLength);
  DeadIntrinsic->setDestAlignment(PrefAlign);

  if (!IsOverwriteEnd) {
    Value *OrigDest = DeadIntrinsic->getRawDest();
    Type *Int8PtrTy =
        Type::getInt8PtrTy(DeadIntrinsic->getContext(),
                           OrigDest->getType()->getPointerAddressSpace());
    Value *Dest = OrigDest;
    if (OrigDest->getType() != Int8PtrTy)
      Dest = CastInst::CreatePointerCast(OrigDest, Int8PtrTy, "", DeadI);
    Value *Indices[1] = {
        ConstantInt::get(DeadWriteLength->getType(), ToRemoveSize)};
    Instruction *NewDestGEP = GetElementPtrInst::CreateInBounds(
        Type::getInt8Ty(DeadIntrinsic->getContext()), Dest, Indices, "", DeadI);
    NewDestGEP->setDebugLoc(DeadIntrinsic->getDebugLoc());
    if (NewDestGEP->getType() != OrigDest->getType())
      NewDestGEP = CastInst::CreatePointerCast(NewDestGEP, OrigDest->getType(),
                                               "", DeadI);
    DeadIntrinsic->setDest(NewDestGEP);
  }

  // Finally update start and size of dead access.
  if (!IsOverwriteEnd)
    DeadStart += ToRemoveSize;
  DeadSize = NewSize;

  return true;
}

static bool tryToShortenEnd(Instruction *DeadI, OverlapIntervalsTy &IntervalMap,
                            int64_t &DeadStart, uint64_t &DeadSize) {
  if (IntervalMap.empty() || !isShortenableAtTheEnd(DeadI))
    return false;

  OverlapIntervalsTy::iterator OII = --IntervalMap.end();
  int64_t KillingStart = OII->second;
  uint64_t KillingSize = OII->first - KillingStart;

  assert(OII->first - KillingStart >= 0 && "Size expected to be positive");

  if (KillingStart > DeadStart &&
      // Note: "KillingStart - KillingStart" is known to be positive due to
      // preceding check.
      (uint64_t)(KillingStart - DeadStart) < DeadSize &&
      // Note: "DeadSize - (uint64_t)(KillingStart - DeadStart)" is known to
      // be non negative due to preceding checks.
      KillingSize >= DeadSize - (uint64_t)(KillingStart - DeadStart)) {
    if (tryToShorten(DeadI, DeadStart, DeadSize, KillingStart, KillingSize,
                     true)) {
      IntervalMap.erase(OII);
      return true;
    }
  }
  return false;
}

static bool tryToShortenBegin(Instruction *DeadI,
                              OverlapIntervalsTy &IntervalMap,
                              int64_t &DeadStart, uint64_t &DeadSize) {
  if (IntervalMap.empty() || !isShortenableAtTheBeginning(DeadI))
    return false;

  OverlapIntervalsTy::iterator OII = IntervalMap.begin();
  int64_t KillingStart = OII->second;
  uint64_t KillingSize = OII->first - KillingStart;

  assert(OII->first - KillingStart >= 0 && "Size expected to be positive");

  if (KillingStart <= DeadStart &&
      // Note: "DeadStart - KillingStart" is known to be non negative due to
      // preceding check.
      KillingSize > (uint64_t)(DeadStart - KillingStart)) {
    // Note: "KillingSize - (uint64_t)(DeadStart - DeadStart)" is known to
    // be positive due to preceding checks.
    assert(KillingSize - (uint64_t)(DeadStart - KillingStart) < DeadSize &&
           "Should have been handled as OW_Complete");
    if (tryToShorten(DeadI, DeadStart, DeadSize, KillingStart, KillingSize,
                     false)) {
      IntervalMap.erase(OII);
      return true;
    }
  }
  return false;
}

static Constant *
tryToMergePartialOverlappingStores(StoreInst *KillingI, StoreInst *DeadI,
                                   int64_t KillingOffset, int64_t DeadOffset,
                                   const DataLayout &DL, BatchAAResults &AA,
                                   DominatorTree *DT) {

  if (DeadI && isa<ConstantInt>(DeadI->getValueOperand()) &&
      DL.typeSizeEqualsStoreSize(DeadI->getValueOperand()->getType()) &&
      KillingI && isa<ConstantInt>(KillingI->getValueOperand()) &&
      DL.typeSizeEqualsStoreSize(KillingI->getValueOperand()->getType()) &&
      memoryIsNotModifiedBetween(DeadI, KillingI, AA, DL, DT)) {
    // If the store we find is:
    //   a) partially overwritten by the store to 'Loc'
    //   b) the killing store is fully contained in the dead one and
    //   c) they both have a constant value
    //   d) none of the two stores need padding
    // Merge the two stores, replacing the dead store's value with a
    // merge of both values.
    // TODO: Deal with other constant types (vectors, etc), and probably
    // some mem intrinsics (if needed)

    APInt DeadValue = cast<ConstantInt>(DeadI->getValueOperand())->getValue();
    APInt KillingValue =
        cast<ConstantInt>(KillingI->getValueOperand())->getValue();
    unsigned KillingBits = KillingValue.getBitWidth();
    assert(DeadValue.getBitWidth() > KillingValue.getBitWidth());
    KillingValue = KillingValue.zext(DeadValue.getBitWidth());

    // Offset of the smaller store inside the larger store
    unsigned BitOffsetDiff = (KillingOffset - DeadOffset) * 8;
    unsigned LShiftAmount =
        DL.isBigEndian() ? DeadValue.getBitWidth() - BitOffsetDiff - KillingBits
                         : BitOffsetDiff;
    APInt Mask = APInt::getBitsSet(DeadValue.getBitWidth(), LShiftAmount,
                                   LShiftAmount + KillingBits);
    // Clear the bits we'll be replacing, then OR with the smaller
    // store, shifted appropriately.
    APInt Merged = (DeadValue & ~Mask) | (KillingValue << LShiftAmount);
    LLVM_DEBUG(dbgs() << "DSE: Merge Stores:\n  Dead: " << *DeadI
                      << "\n  Killing: " << *KillingI
                      << "\n  Merged Value: " << Merged << '\n');
    return ConstantInt::get(DeadI->getValueOperand()->getType(), Merged);
  }
  return nullptr;
}

namespace {
// Returns true if \p I is an intrisnic that does not read or write memory.
bool isNoopIntrinsic(Instruction *I) {
  if (const IntrinsicInst *II = dyn_cast<IntrinsicInst>(I)) {
    switch (II->getIntrinsicID()) {
    case Intrinsic::lifetime_start:
    case Intrinsic::lifetime_end:
    case Intrinsic::invariant_end:
    case Intrinsic::launder_invariant_group:
    case Intrinsic::assume:
      return true;
    case Intrinsic::dbg_addr:
    case Intrinsic::dbg_declare:
    case Intrinsic::dbg_label:
    case Intrinsic::dbg_value:
      llvm_unreachable("Intrinsic should not be modeled in MemorySSA");
    default:
      return false;
    }
  }
  return false;
}

// Check if we can ignore \p D for DSE.
bool canSkipDef(MemoryDef *D, bool DefVisibleToCaller) {
  Instruction *DI = D->getMemoryInst();
  // Calls that only access inaccessible memory cannot read or write any memory
  // locations we consider for elimination.
  if (auto *CB = dyn_cast<CallBase>(DI))
    if (CB->onlyAccessesInaccessibleMemory())
      return true;

  // We can eliminate stores to locations not visible to the caller across
  // throwing instructions.
  if (DI->mayThrow() && !DefVisibleToCaller)
    return true;

  // We can remove the dead stores, irrespective of the fence and its ordering
  // (release/acquire/seq_cst). Fences only constraints the ordering of
  // already visible stores, it does not make a store visible to other
  // threads. So, skipping over a fence does not change a store from being
  // dead.
  if (isa<FenceInst>(DI))
    return true;

  // Skip intrinsics that do not really read or modify memory.
  if (isNoopIntrinsic(DI))
    return true;

  return false;
}

struct DSEState {
  Function &F;
  AliasAnalysis &AA;
  EarliestEscapeInfo EI;

  /// The single BatchAA instance that is used to cache AA queries. It will
  /// not be invalidated over the whole run. This is safe, because:
  /// 1. Only memory writes are removed, so the alias cache for memory
  ///    locations remains valid.
  /// 2. No new instructions are added (only instructions removed), so cached
  ///    information for a deleted value cannot be accessed by a re-used new
  ///    value pointer.
  BatchAAResults BatchAA;

  MemorySSA &MSSA;
  DominatorTree &DT;
  PostDominatorTree &PDT;
  const TargetLibraryInfo &TLI;
  const DataLayout &DL;
  const LoopInfo &LI;

  // Whether the function contains any irreducible control flow, useful for
  // being accurately able to detect loops.
  bool ContainsIrreducibleLoops;

  // All MemoryDefs that potentially could kill other MemDefs.
  SmallVector<MemoryDef *, 64> MemDefs;
  // Any that should be skipped as they are already deleted
  SmallPtrSet<MemoryAccess *, 4> SkipStores;
  // Keep track whether a given object is captured before return or not.
  DenseMap<const Value *, bool> CapturedBeforeReturn;
  // Keep track of all of the objects that are invisible to the caller after
  // the function returns.
  DenseMap<const Value *, bool> InvisibleToCallerAfterRet;
  // Keep track of blocks with throwing instructions not modeled in MemorySSA.
  SmallPtrSet<BasicBlock *, 16> ThrowingBlocks;
  // Post-order numbers for each basic block. Used to figure out if memory
  // accesses are executed before another access.
  DenseMap<BasicBlock *, unsigned> PostOrderNumbers;

  /// Keep track of instructions (partly) overlapping with killing MemoryDefs per
  /// basic block.
  MapVector<BasicBlock *, InstOverlapIntervalsTy> IOLs;
  // Check if there are root nodes that are terminated by UnreachableInst.
  // Those roots pessimize post-dominance queries. If there are such roots,
  // fall back to CFG scan starting from all non-unreachable roots.
  bool AnyUnreachableExit;

  // Class contains self-reference, make sure it's not copied/moved.
  DSEState(const DSEState &) = delete;
  DSEState &operator=(const DSEState &) = delete;

  DSEState(Function &F, AliasAnalysis &AA, MemorySSA &MSSA, DominatorTree &DT,
           PostDominatorTree &PDT, const TargetLibraryInfo &TLI,
           const LoopInfo &LI)
      : F(F), AA(AA), EI(DT, LI), BatchAA(AA, &EI), MSSA(MSSA), DT(DT),
        PDT(PDT), TLI(TLI), DL(F.getParent()->getDataLayout()), LI(LI) {
    // Collect blocks with throwing instructions not modeled in MemorySSA and
    // alloc-like objects.
    unsigned PO = 0;
    for (BasicBlock *BB : post_order(&F)) {
      PostOrderNumbers[BB] = PO++;
      for (Instruction &I : *BB) {
        MemoryAccess *MA = MSSA.getMemoryAccess(&I);
        if (I.mayThrow() && !MA)
          ThrowingBlocks.insert(I.getParent());

        auto *MD = dyn_cast_or_null<MemoryDef>(MA);
        if (MD && MemDefs.size() < MemorySSADefsPerBlockLimit &&
            (getLocForWrite(&I) || isMemTerminatorInst(&I)))
          MemDefs.push_back(MD);
      }
    }

    // Treat byval or inalloca arguments the same as Allocas, stores to them are
    // dead at the end of the function.
    for (Argument &AI : F.args())
      if (AI.hasPassPointeeByValueCopyAttr())
        InvisibleToCallerAfterRet.insert({&AI, true});

    // Collect whether there is any irreducible control flow in the function.
    ContainsIrreducibleLoops = mayContainIrreducibleControl(F, &LI);

    AnyUnreachableExit = any_of(PDT.roots(), [](const BasicBlock *E) {
      return isa<UnreachableInst>(E->getTerminator());
    });
  }

  /// Return 'OW_Complete' if a store to the 'KillingLoc' location (by \p
  /// KillingI instruction) completely overwrites a store to the 'DeadLoc'
  /// location (by \p DeadI instruction).
  /// Return OW_MaybePartial if \p KillingI does not completely overwrite
  /// \p DeadI, but they both write to the same underlying object. In that
  /// case, use isPartialOverwrite to check if \p KillingI partially overwrites
  /// \p DeadI. Returns 'OR_None' if \p KillingI is known to not overwrite the
  /// \p DeadI. Returns 'OW_Unknown' if nothing can be determined.
  OverwriteResult isOverwrite(const Instruction *KillingI,
                              const Instruction *DeadI,
                              const MemoryLocation &KillingLoc,
                              const MemoryLocation &DeadLoc,
                              int64_t &KillingOff, int64_t &DeadOff) {
    // AliasAnalysis does not always account for loops. Limit overwrite checks
    // to dependencies for which we can guarantee they are independent of any
    // loops they are in.
    if (!isGuaranteedLoopIndependent(DeadI, KillingI, DeadLoc))
      return OW_Unknown;

    const Value *DeadPtr = DeadLoc.Ptr->stripPointerCasts();
    const Value *KillingPtr = KillingLoc.Ptr->stripPointerCasts();
    const Value *DeadUndObj = getUnderlyingObject(DeadPtr);
    const Value *KillingUndObj = getUnderlyingObject(KillingPtr);

    // Check whether the killing store overwrites the whole object, in which
    // case the size/offset of the dead store does not matter.
    if (DeadUndObj == KillingUndObj && KillingLoc.Size.isPrecise()) {
      uint64_t KillingUndObjSize = getPointerSize(KillingUndObj, DL, TLI, &F);
      if (KillingUndObjSize != MemoryLocation::UnknownSize &&
          KillingUndObjSize == KillingLoc.Size.getValue())
        return OW_Complete;
    }

    // FIXME: Vet that this works for size upper-bounds. Seems unlikely that we'll
    // get imprecise values here, though (except for unknown sizes).
    if (!KillingLoc.Size.isPrecise() || !DeadLoc.Size.isPrecise()) {
      // In case no constant size is known, try to an IR values for the number
      // of bytes written and check if they match.
      const auto *KillingMemI = dyn_cast<MemIntrinsic>(KillingI);
      const auto *DeadMemI = dyn_cast<MemIntrinsic>(DeadI);
      if (KillingMemI && DeadMemI) {
        const Value *KillingV = KillingMemI->getLength();
        const Value *DeadV = DeadMemI->getLength();
        if (KillingV == DeadV && BatchAA.isMustAlias(DeadLoc, KillingLoc))
          return OW_Complete;
      }

      // Masked stores have imprecise locations, but we can reason about them
      // to some extent.
      return isMaskedStoreOverwrite(KillingI, DeadI, BatchAA);
    }

    const uint64_t KillingSize = KillingLoc.Size.getValue();
    const uint64_t DeadSize = DeadLoc.Size.getValue();

    // Query the alias information
    AliasResult AAR = BatchAA.alias(KillingLoc, DeadLoc);

    // If the start pointers are the same, we just have to compare sizes to see if
    // the killing store was larger than the dead store.
    if (AAR == AliasResult::MustAlias) {
      // Make sure that the KillingSize size is >= the DeadSize size.
      if (KillingSize >= DeadSize)
        return OW_Complete;
    }

    // If we hit a partial alias we may have a full overwrite
    if (AAR == AliasResult::PartialAlias && AAR.hasOffset()) {
      int32_t Off = AAR.getOffset();
      if (Off >= 0 && (uint64_t)Off + DeadSize <= KillingSize)
        return OW_Complete;
    }

    // If we can't resolve the same pointers to the same object, then we can't
    // analyze them at all.
    if (DeadUndObj != KillingUndObj) {
      // Non aliasing stores to different objects don't overlap. Note that
      // if the killing store is known to overwrite whole object (out of
      // bounds access overwrites whole object as well) then it is assumed to
      // completely overwrite any store to the same object even if they don't
      // actually alias (see next check).
      if (AAR == AliasResult::NoAlias)
        return OW_None;
      return OW_Unknown;
    }

    // Okay, we have stores to two completely different pointers.  Try to
    // decompose the pointer into a "base + constant_offset" form.  If the base
    // pointers are equal, then we can reason about the two stores.
    DeadOff = 0;
    KillingOff = 0;
    const Value *DeadBasePtr =
        GetPointerBaseWithConstantOffset(DeadPtr, DeadOff, DL);
    const Value *KillingBasePtr =
        GetPointerBaseWithConstantOffset(KillingPtr, KillingOff, DL);

    // If the base pointers still differ, we have two completely different
    // stores.
    if (DeadBasePtr != KillingBasePtr)
      return OW_Unknown;

    // The killing access completely overlaps the dead store if and only if
    // both start and end of the dead one is "inside" the killing one:
    //    |<->|--dead--|<->|
    //    |-----killing------|
    // Accesses may overlap if and only if start of one of them is "inside"
    // another one:
    //    |<->|--dead--|<-------->|
    //    |-------killing--------|
    //           OR
    //    |-------dead-------|
    //    |<->|---killing---|<----->|
    //
    // We have to be careful here as *Off is signed while *.Size is unsigned.

    // Check if the dead access starts "not before" the killing one.
    if (DeadOff >= KillingOff) {
      // If the dead access ends "not after" the killing access then the
      // dead one is completely overwritten by the killing one.
      if (uint64_t(DeadOff - KillingOff) + DeadSize <= KillingSize)
        return OW_Complete;
      // If start of the dead access is "before" end of the killing access
      // then accesses overlap.
      else if ((uint64_t)(DeadOff - KillingOff) < KillingSize)
        return OW_MaybePartial;
    }
    // If start of the killing access is "before" end of the dead access then
    // accesses overlap.
    else if ((uint64_t)(KillingOff - DeadOff) < DeadSize) {
      return OW_MaybePartial;
    }

    // Can reach here only if accesses are known not to overlap.
    return OW_None;
  }

  bool isInvisibleToCallerAfterRet(const Value *V) {
    if (isa<AllocaInst>(V))
      return true;
    auto I = InvisibleToCallerAfterRet.insert({V, false});
    if (I.second) {
      if (!isInvisibleToCallerOnUnwind(V)) {
        I.first->second = false;
      } else if (isNoAliasCall(V)) {
        I.first->second = !PointerMayBeCaptured(V, true, false);
      }
    }
    return I.first->second;
  }

  bool isInvisibleToCallerOnUnwind(const Value *V) {
    bool RequiresNoCaptureBeforeUnwind;
    if (!isNotVisibleOnUnwind(V, RequiresNoCaptureBeforeUnwind))
      return false;
    if (!RequiresNoCaptureBeforeUnwind)
      return true;

    auto I = CapturedBeforeReturn.insert({V, true});
    if (I.second)
      // NOTE: This could be made more precise by PointerMayBeCapturedBefore
      // with the killing MemoryDef. But we refrain from doing so for now to
      // limit compile-time and this does not cause any changes to the number
      // of stores removed on a large test set in practice.
      I.first->second = PointerMayBeCaptured(V, false, true);
    return !I.first->second;
  }

  Optional<MemoryLocation> getLocForWrite(Instruction *I) const {
    if (!I->mayWriteToMemory())
      return None;

    if (auto *CB = dyn_cast<CallBase>(I))
      return MemoryLocation::getForDest(CB, TLI);

    return MemoryLocation::getOrNone(I);
  }

  /// Assuming this instruction has a dead analyzable write, can we delete
  /// this instruction?
  bool isRemovable(Instruction *I) {
    assert(getLocForWrite(I) && "Must have analyzable write");

    // Don't remove volatile/atomic stores.
    if (StoreInst *SI = dyn_cast<StoreInst>(I))
      return SI->isUnordered();

    if (auto *CB = dyn_cast<CallBase>(I)) {
      // Don't remove volatile memory intrinsics.
      if (auto *MI = dyn_cast<MemIntrinsic>(CB))
        return !MI->isVolatile();

      // Never remove dead lifetime intrinsics, e.g. because they are followed
      // by a free.
      if (CB->isLifetimeStartOrEnd())
        return false;

      return CB->use_empty() && CB->willReturn() && CB->doesNotThrow();
    }

    return false;
  }

  /// Returns true if \p UseInst completely overwrites \p DefLoc
  /// (stored by \p DefInst).
  bool isCompleteOverwrite(const MemoryLocation &DefLoc, Instruction *DefInst,
                           Instruction *UseInst) {
    // UseInst has a MemoryDef associated in MemorySSA. It's possible for a
    // MemoryDef to not write to memory, e.g. a volatile load is modeled as a
    // MemoryDef.
    if (!UseInst->mayWriteToMemory())
      return false;

    if (auto *CB = dyn_cast<CallBase>(UseInst))
      if (CB->onlyAccessesInaccessibleMemory())
        return false;

    int64_t InstWriteOffset, DepWriteOffset;
    if (auto CC = getLocForWrite(UseInst))
      return isOverwrite(UseInst, DefInst, *CC, DefLoc, InstWriteOffset,
                         DepWriteOffset) == OW_Complete;
    return false;
  }

  /// Returns true if \p Def is not read before returning from the function.
  bool isWriteAtEndOfFunction(MemoryDef *Def) {
    LLVM_DEBUG(dbgs() << "  Check if def " << *Def << " ("
                      << *Def->getMemoryInst()
                      << ") is at the end the function \n");

    auto MaybeLoc = getLocForWrite(Def->getMemoryInst());
    if (!MaybeLoc) {
      LLVM_DEBUG(dbgs() << "  ... could not get location for write.\n");
      return false;
    }

    SmallVector<MemoryAccess *, 4> WorkList;
    SmallPtrSet<MemoryAccess *, 8> Visited;
    auto PushMemUses = [&WorkList, &Visited](MemoryAccess *Acc) {
      if (!Visited.insert(Acc).second)
        return;
      for (Use &U : Acc->uses())
        WorkList.push_back(cast<MemoryAccess>(U.getUser()));
    };
    PushMemUses(Def);
    for (unsigned I = 0; I < WorkList.size(); I++) {
      if (WorkList.size() >= MemorySSAScanLimit) {
        LLVM_DEBUG(dbgs() << "  ... hit exploration limit.\n");
        return false;
      }

      MemoryAccess *UseAccess = WorkList[I];
      // Simply adding the users of MemoryPhi to the worklist is not enough,
      // because we might miss read clobbers in different iterations of a loop,
      // for example.
      // TODO: Add support for phi translation to handle the loop case.
      if (isa<MemoryPhi>(UseAccess))
        return false;

      // TODO: Checking for aliasing is expensive. Consider reducing the amount
      // of times this is called and/or caching it.
      Instruction *UseInst = cast<MemoryUseOrDef>(UseAccess)->getMemoryInst();
      if (isReadClobber(*MaybeLoc, UseInst)) {
        LLVM_DEBUG(dbgs() << "  ... hit read clobber " << *UseInst << ".\n");
        return false;
      }

      if (MemoryDef *UseDef = dyn_cast<MemoryDef>(UseAccess))
        PushMemUses(UseDef);
    }
    return true;
  }

  /// If \p I is a memory  terminator like llvm.lifetime.end or free, return a
  /// pair with the MemoryLocation terminated by \p I and a boolean flag
  /// indicating whether \p I is a free-like call.
  Optional<std::pair<MemoryLocation, bool>>
  getLocForTerminator(Instruction *I) const {
    uint64_t Len;
    Value *Ptr;
    if (match(I, m_Intrinsic<Intrinsic::lifetime_end>(m_ConstantInt(Len),
                                                      m_Value(Ptr))))
      return {std::make_pair(MemoryLocation(Ptr, Len), false)};

    if (auto *CB = dyn_cast<CallBase>(I)) {
      if (isFreeCall(I, &TLI))
        return {std::make_pair(MemoryLocation::getAfter(CB->getArgOperand(0)),
                               true)};
    }

    return None;
  }

  /// Returns true if \p I is a memory terminator instruction like
  /// llvm.lifetime.end or free.
  bool isMemTerminatorInst(Instruction *I) const {
    IntrinsicInst *II = dyn_cast<IntrinsicInst>(I);
    return (II && II->getIntrinsicID() == Intrinsic::lifetime_end) ||
           isFreeCall(I, &TLI);
  }

  /// Returns true if \p MaybeTerm is a memory terminator for \p Loc from
  /// instruction \p AccessI.
  bool isMemTerminator(const MemoryLocation &Loc, Instruction *AccessI,
                       Instruction *MaybeTerm) {
    Optional<std::pair<MemoryLocation, bool>> MaybeTermLoc =
        getLocForTerminator(MaybeTerm);

    if (!MaybeTermLoc)
      return false;

    // If the terminator is a free-like call, all accesses to the underlying
    // object can be considered terminated.
    if (getUnderlyingObject(Loc.Ptr) !=
        getUnderlyingObject(MaybeTermLoc->first.Ptr))
      return false;

    auto TermLoc = MaybeTermLoc->first;
    if (MaybeTermLoc->second) {
      const Value *LocUO = getUnderlyingObject(Loc.Ptr);
      return BatchAA.isMustAlias(TermLoc.Ptr, LocUO);
    }
    int64_t InstWriteOffset = 0;
    int64_t DepWriteOffset = 0;
    return isOverwrite(MaybeTerm, AccessI, TermLoc, Loc, InstWriteOffset,
                       DepWriteOffset) == OW_Complete;
  }

  // Returns true if \p Use may read from \p DefLoc.
  bool isReadClobber(const MemoryLocation &DefLoc, Instruction *UseInst) {
    if (isNoopIntrinsic(UseInst))
      return false;

    // Monotonic or weaker atomic stores can be re-ordered and do not need to be
    // treated as read clobber.
    if (auto SI = dyn_cast<StoreInst>(UseInst))
      return isStrongerThan(SI->getOrdering(), AtomicOrdering::Monotonic);

    if (!UseInst->mayReadFromMemory())
      return false;

    if (auto *CB = dyn_cast<CallBase>(UseInst))
      if (CB->onlyAccessesInaccessibleMemory())
        return false;

    return isRefSet(BatchAA.getModRefInfo(UseInst, DefLoc));
  }

  /// Returns true if a dependency between \p Current and \p KillingDef is
  /// guaranteed to be loop invariant for the loops that they are in. Either
  /// because they are known to be in the same block, in the same loop level or
  /// by guaranteeing that \p CurrentLoc only references a single MemoryLocation
  /// during execution of the containing function.
  bool isGuaranteedLoopIndependent(const Instruction *Current,
                                   const Instruction *KillingDef,
                                   const MemoryLocation &CurrentLoc) {
    // If the dependency is within the same block or loop level (being careful
    // of irreducible loops), we know that AA will return a valid result for the
    // memory dependency. (Both at the function level, outside of any loop,
    // would also be valid but we currently disable that to limit compile time).
    if (Current->getParent() == KillingDef->getParent())
      return true;
    const Loop *CurrentLI = LI.getLoopFor(Current->getParent());
    if (!ContainsIrreducibleLoops && CurrentLI &&
        CurrentLI == LI.getLoopFor(KillingDef->getParent()))
      return true;
    // Otherwise check the memory location is invariant to any loops.
    return isGuaranteedLoopInvariant(CurrentLoc.Ptr);
  }

  /// Returns true if \p Ptr is guaranteed to be loop invariant for any possible
  /// loop. In particular, this guarantees that it only references a single
  /// MemoryLocation during execution of the containing function.
  bool isGuaranteedLoopInvariant(const Value *Ptr) {
    Ptr = Ptr->stripPointerCasts();
    if (auto *GEP = dyn_cast<GEPOperator>(Ptr))
      if (GEP->hasAllConstantIndices())
        Ptr = GEP->getPointerOperand()->stripPointerCasts();

    if (auto *I = dyn_cast<Instruction>(Ptr))
      return I->getParent()->isEntryBlock();
    return true;
  }

  // Find a MemoryDef writing to \p KillingLoc and dominating \p StartAccess,
  // with no read access between them or on any other path to a function exit
  // block if \p KillingLoc is not accessible after the function returns. If
  // there is no such MemoryDef, return None. The returned value may not
  // (completely) overwrite \p KillingLoc. Currently we bail out when we
  // encounter an aliasing MemoryUse (read).
  Optional<MemoryAccess *>
  getDomMemoryDef(MemoryDef *KillingDef, MemoryAccess *StartAccess,
                  const MemoryLocation &KillingLoc, const Value *KillingUndObj,
                  unsigned &ScanLimit, unsigned &WalkerStepLimit,
                  bool IsMemTerm, unsigned &PartialLimit) {
    if (ScanLimit == 0 || WalkerStepLimit == 0) {
      LLVM_DEBUG(dbgs() << "\n    ...  hit scan limit\n");
      return None;
    }

    MemoryAccess *Current = StartAccess;
    Instruction *KillingI = KillingDef->getMemoryInst();
    LLVM_DEBUG(dbgs() << "  trying to get dominating access\n");

    // Only optimize defining access of KillingDef when directly starting at its
    // defining access. The defining access also must only access KillingLoc. At
    // the moment we only support instructions with a single write location, so
    // it should be sufficient to disable optimizations for instructions that
    // also read from memory.
    bool CanOptimize = OptimizeMemorySSA &&
                       KillingDef->getDefiningAccess() == StartAccess &&
                       !KillingI->mayReadFromMemory();

    // Find the next clobbering Mod access for DefLoc, starting at StartAccess.
    Optional<MemoryLocation> CurrentLoc;
    for (;; Current = cast<MemoryDef>(Current)->getDefiningAccess()) {
      LLVM_DEBUG({
        dbgs() << "   visiting " << *Current;
        if (!MSSA.isLiveOnEntryDef(Current) && isa<MemoryUseOrDef>(Current))
          dbgs() << " (" << *cast<MemoryUseOrDef>(Current)->getMemoryInst()
                 << ")";
        dbgs() << "\n";
      });

      // Reached TOP.
      if (MSSA.isLiveOnEntryDef(Current)) {
        LLVM_DEBUG(dbgs() << "   ...  found LiveOnEntryDef\n");
        return None;
      }

      // Cost of a step. Accesses in the same block are more likely to be valid
      // candidates for elimination, hence consider them cheaper.
      unsigned StepCost = KillingDef->getBlock() == Current->getBlock()
                              ? MemorySSASameBBStepCost
                              : MemorySSAOtherBBStepCost;
      if (WalkerStepLimit <= StepCost) {
        LLVM_DEBUG(dbgs() << "   ...  hit walker step limit\n");
        return None;
      }
      WalkerStepLimit -= StepCost;

      // Return for MemoryPhis. They cannot be eliminated directly and the
      // caller is responsible for traversing them.
      if (isa<MemoryPhi>(Current)) {
        LLVM_DEBUG(dbgs() << "   ...  found MemoryPhi\n");
        return Current;
      }

      // Below, check if CurrentDef is a valid candidate to be eliminated by
      // KillingDef. If it is not, check the next candidate.
      MemoryDef *CurrentDef = cast<MemoryDef>(Current);
      Instruction *CurrentI = CurrentDef->getMemoryInst();

      if (canSkipDef(CurrentDef, !isInvisibleToCallerOnUnwind(KillingUndObj))) {
        CanOptimize = false;
        continue;
      }

      // Before we try to remove anything, check for any extra throwing
      // instructions that block us from DSEing
      if (mayThrowBetween(KillingI, CurrentI, KillingUndObj)) {
        LLVM_DEBUG(dbgs() << "  ... skip, may throw!\n");
        return None;
      }

      // Check for anything that looks like it will be a barrier to further
      // removal
      if (isDSEBarrier(KillingUndObj, CurrentI)) {
        LLVM_DEBUG(dbgs() << "  ... skip, barrier\n");
        return None;
      }

      // If Current is known to be on path that reads DefLoc or is a read
      // clobber, bail out, as the path is not profitable. We skip this check
      // for intrinsic calls, because the code knows how to handle memcpy
      // intrinsics.
      if (!isa<IntrinsicInst>(CurrentI) && isReadClobber(KillingLoc, CurrentI))
        return None;

      // Quick check if there are direct uses that are read-clobbers.
      if (any_of(Current->uses(), [this, &KillingLoc, StartAccess](Use &U) {
            if (auto *UseOrDef = dyn_cast<MemoryUseOrDef>(U.getUser()))
              return !MSSA.dominates(StartAccess, UseOrDef) &&
                     isReadClobber(KillingLoc, UseOrDef->getMemoryInst());
            return false;
          })) {
        LLVM_DEBUG(dbgs() << "   ...  found a read clobber\n");
        return None;
      }

      // If Current does not have an analyzable write location or is not
      // removable, skip it.
      CurrentLoc = getLocForWrite(CurrentI);
      if (!CurrentLoc || !isRemovable(CurrentI)) {
        CanOptimize = false;
        continue;
      }

      // AliasAnalysis does not account for loops. Limit elimination to
      // candidates for which we can guarantee they always store to the same
      // memory location and not located in different loops.
      if (!isGuaranteedLoopIndependent(CurrentI, KillingI, *CurrentLoc)) {
        LLVM_DEBUG(dbgs() << "  ... not guaranteed loop independent\n");
        WalkerStepLimit -= 1;
        CanOptimize = false;
        continue;
      }

      if (IsMemTerm) {
        // If the killing def is a memory terminator (e.g. lifetime.end), check
        // the next candidate if the current Current does not write the same
        // underlying object as the terminator.
        if (!isMemTerminator(*CurrentLoc, CurrentI, KillingI)) {
          CanOptimize = false;
          continue;
        }
      } else {
        int64_t KillingOffset = 0;
        int64_t DeadOffset = 0;
        auto OR = isOverwrite(KillingI, CurrentI, KillingLoc, *CurrentLoc,
                              KillingOffset, DeadOffset);
        if (CanOptimize) {
          // CurrentDef is the earliest write clobber of KillingDef. Use it as
          // optimized access. Do not optimize if CurrentDef is already the
          // defining access of KillingDef.
          if (CurrentDef != KillingDef->getDefiningAccess() &&
              (OR == OW_Complete || OR == OW_MaybePartial))
            KillingDef->setOptimized(CurrentDef);

          // Once a may-aliasing def is encountered do not set an optimized
          // access.
          if (OR != OW_None)
            CanOptimize = false;
        }

        // If Current does not write to the same object as KillingDef, check
        // the next candidate.
        if (OR == OW_Unknown || OR == OW_None)
          continue;
        else if (OR == OW_MaybePartial) {
          // If KillingDef only partially overwrites Current, check the next
          // candidate if the partial step limit is exceeded. This aggressively
          // limits the number of candidates for partial store elimination,
          // which are less likely to be removable in the end.
          if (PartialLimit <= 1) {
            WalkerStepLimit -= 1;
            LLVM_DEBUG(dbgs() << "   ... reached partial limit ... continue with next access\n");
            continue;
          }
          PartialLimit -= 1;
        }
      }
      break;
    };

    // Accesses to objects accessible after the function returns can only be
    // eliminated if the access is dead along all paths to the exit. Collect
    // the blocks with killing (=completely overwriting MemoryDefs) and check if
    // they cover all paths from MaybeDeadAccess to any function exit.
    SmallPtrSet<Instruction *, 16> KillingDefs;
    KillingDefs.insert(KillingDef->getMemoryInst());
    MemoryAccess *MaybeDeadAccess = Current;
    MemoryLocation MaybeDeadLoc = *CurrentLoc;
    Instruction *MaybeDeadI = cast<MemoryDef>(MaybeDeadAccess)->getMemoryInst();
    LLVM_DEBUG(dbgs() << "  Checking for reads of " << *MaybeDeadAccess << " ("
                      << *MaybeDeadI << ")\n");

    SmallSetVector<MemoryAccess *, 32> WorkList;
    auto PushMemUses = [&WorkList](MemoryAccess *Acc) {
      for (Use &U : Acc->uses())
        WorkList.insert(cast<MemoryAccess>(U.getUser()));
    };
    PushMemUses(MaybeDeadAccess);

    // Check if DeadDef may be read.
    for (unsigned I = 0; I < WorkList.size(); I++) {
      MemoryAccess *UseAccess = WorkList[I];

      LLVM_DEBUG(dbgs() << "   " << *UseAccess);
      // Bail out if the number of accesses to check exceeds the scan limit.
      if (ScanLimit < (WorkList.size() - I)) {
        LLVM_DEBUG(dbgs() << "\n    ...  hit scan limit\n");
        return None;
      }
      --ScanLimit;
      NumDomMemDefChecks++;

      if (isa<MemoryPhi>(UseAccess)) {
        if (any_of(KillingDefs, [this, UseAccess](Instruction *KI) {
              return DT.properlyDominates(KI->getParent(),
                                          UseAccess->getBlock());
            })) {
          LLVM_DEBUG(dbgs() << " ... skipping, dominated by killing block\n");
          continue;
        }
        LLVM_DEBUG(dbgs() << "\n    ... adding PHI uses\n");
        PushMemUses(UseAccess);
        continue;
      }

      Instruction *UseInst = cast<MemoryUseOrDef>(UseAccess)->getMemoryInst();
      LLVM_DEBUG(dbgs() << " (" << *UseInst << ")\n");

      if (any_of(KillingDefs, [this, UseInst](Instruction *KI) {
            return DT.dominates(KI, UseInst);
          })) {
        LLVM_DEBUG(dbgs() << " ... skipping, dominated by killing def\n");
        continue;
      }

      // A memory terminator kills all preceeding MemoryDefs and all succeeding
      // MemoryAccesses. We do not have to check it's users.
      if (isMemTerminator(MaybeDeadLoc, MaybeDeadI, UseInst)) {
        LLVM_DEBUG(
            dbgs()
            << " ... skipping, memterminator invalidates following accesses\n");
        continue;
      }

      if (isNoopIntrinsic(cast<MemoryUseOrDef>(UseAccess)->getMemoryInst())) {
        LLVM_DEBUG(dbgs() << "    ... adding uses of intrinsic\n");
        PushMemUses(UseAccess);
        continue;
      }

      if (UseInst->mayThrow() && !isInvisibleToCallerOnUnwind(KillingUndObj)) {
        LLVM_DEBUG(dbgs() << "  ... found throwing instruction\n");
        return None;
      }

      // Uses which may read the original MemoryDef mean we cannot eliminate the
      // original MD. Stop walk.
      if (isReadClobber(MaybeDeadLoc, UseInst)) {
        LLVM_DEBUG(dbgs() << "    ... found read clobber\n");
        return None;
      }

      // If this worklist walks back to the original memory access (and the
      // pointer is not guarenteed loop invariant) then we cannot assume that a
      // store kills itself.
      if (MaybeDeadAccess == UseAccess &&
          !isGuaranteedLoopInvariant(MaybeDeadLoc.Ptr)) {
        LLVM_DEBUG(dbgs() << "    ... found not loop invariant self access\n");
        return None;
      }
      // Otherwise, for the KillingDef and MaybeDeadAccess we only have to check
      // if it reads the memory location.
      // TODO: It would probably be better to check for self-reads before
      // calling the function.
      if (KillingDef == UseAccess || MaybeDeadAccess == UseAccess) {
        LLVM_DEBUG(dbgs() << "    ... skipping killing def/dom access\n");
        continue;
      }

      // Check all uses for MemoryDefs, except for defs completely overwriting
      // the original location. Otherwise we have to check uses of *all*
      // MemoryDefs we discover, including non-aliasing ones. Otherwise we might
      // miss cases like the following
      //   1 = Def(LoE) ; <----- DeadDef stores [0,1]
      //   2 = Def(1)   ; (2, 1) = NoAlias,   stores [2,3]
      //   Use(2)       ; MayAlias 2 *and* 1, loads [0, 3].
      //                  (The Use points to the *first* Def it may alias)
      //   3 = Def(1)   ; <---- Current  (3, 2) = NoAlias, (3,1) = MayAlias,
      //                  stores [0,1]
      if (MemoryDef *UseDef = dyn_cast<MemoryDef>(UseAccess)) {
        if (isCompleteOverwrite(MaybeDeadLoc, MaybeDeadI, UseInst)) {
          BasicBlock *MaybeKillingBlock = UseInst->getParent();
          if (PostOrderNumbers.find(MaybeKillingBlock)->second <
              PostOrderNumbers.find(MaybeDeadAccess->getBlock())->second) {
            if (!isInvisibleToCallerAfterRet(KillingUndObj)) {
              LLVM_DEBUG(dbgs()
                         << "    ... found killing def " << *UseInst << "\n");
              KillingDefs.insert(UseInst);
            }
          } else {
            LLVM_DEBUG(dbgs()
                       << "    ... found preceeding def " << *UseInst << "\n");
            return None;
          }
        } else
          PushMemUses(UseDef);
      }
    }

    // For accesses to locations visible after the function returns, make sure
    // that the location is dead (=overwritten) along all paths from
    // MaybeDeadAccess to the exit.
    if (!isInvisibleToCallerAfterRet(KillingUndObj)) {
      SmallPtrSet<BasicBlock *, 16> KillingBlocks;
      for (Instruction *KD : KillingDefs)
        KillingBlocks.insert(KD->getParent());
      assert(!KillingBlocks.empty() &&
             "Expected at least a single killing block");

      // Find the common post-dominator of all killing blocks.
      BasicBlock *CommonPred = *KillingBlocks.begin();
      for (BasicBlock *BB : llvm::drop_begin(KillingBlocks)) {
        if (!CommonPred)
          break;
        CommonPred = PDT.findNearestCommonDominator(CommonPred, BB);
      }

      // If the common post-dominator does not post-dominate MaybeDeadAccess,
      // there is a path from MaybeDeadAccess to an exit not going through a
      // killing block.
      if (!PDT.dominates(CommonPred, MaybeDeadAccess->getBlock())) {
        if (!AnyUnreachableExit)
          return None;

        // Fall back to CFG scan starting at all non-unreachable roots if not
        // all paths to the exit go through CommonPred.
        CommonPred = nullptr;
      }

      // If CommonPred itself is in the set of killing blocks, we're done.
      if (KillingBlocks.count(CommonPred))
        return {MaybeDeadAccess};

      SetVector<BasicBlock *> WorkList;
      // If CommonPred is null, there are multiple exits from the function.
      // They all have to be added to the worklist.
      if (CommonPred)
        WorkList.insert(CommonPred);
      else
        for (BasicBlock *R : PDT.roots()) {
          if (!isa<UnreachableInst>(R->getTerminator()))
            WorkList.insert(R);
        }

      NumCFGTries++;
      // Check if all paths starting from an exit node go through one of the
      // killing blocks before reaching MaybeDeadAccess.
      for (unsigned I = 0; I < WorkList.size(); I++) {
        NumCFGChecks++;
        BasicBlock *Current = WorkList[I];
        if (KillingBlocks.count(Current))
          continue;
        if (Current == MaybeDeadAccess->getBlock())
          return None;

        // MaybeDeadAccess is reachable from the entry, so we don't have to
        // explore unreachable blocks further.
        if (!DT.isReachableFromEntry(Current))
          continue;

        for (BasicBlock *Pred : predecessors(Current))
          WorkList.insert(Pred);

        if (WorkList.size() >= MemorySSAPathCheckLimit)
          return None;
      }
      NumCFGSuccess++;
    }

    // No aliasing MemoryUses of MaybeDeadAccess found, MaybeDeadAccess is
    // potentially dead.
    return {MaybeDeadAccess};
  }

  // Delete dead memory defs
  void deleteDeadInstruction(Instruction *SI) {
    MemorySSAUpdater Updater(&MSSA);
    SmallVector<Instruction *, 32> NowDeadInsts;
    NowDeadInsts.push_back(SI);
    --NumFastOther;

    while (!NowDeadInsts.empty()) {
      Instruction *DeadInst = NowDeadInsts.pop_back_val();
      ++NumFastOther;

      // Try to preserve debug information attached to the dead instruction.
      salvageDebugInfo(*DeadInst);
      salvageKnowledge(DeadInst);

      // Remove the Instruction from MSSA.
      if (MemoryAccess *MA = MSSA.getMemoryAccess(DeadInst)) {
        if (MemoryDef *MD = dyn_cast<MemoryDef>(MA)) {
          SkipStores.insert(MD);
        }

        Updater.removeMemoryAccess(MA);
      }

      auto I = IOLs.find(DeadInst->getParent());
      if (I != IOLs.end())
        I->second.erase(DeadInst);
      // Remove its operands
      for (Use &O : DeadInst->operands())
        if (Instruction *OpI = dyn_cast<Instruction>(O)) {
          O = nullptr;
          if (isInstructionTriviallyDead(OpI, &TLI))
            NowDeadInsts.push_back(OpI);
        }

      EI.removeInstruction(DeadInst);
      DeadInst->eraseFromParent();
    }
  }

  // Check for any extra throws between \p KillingI and \p DeadI that block
  // DSE.  This only checks extra maythrows (those that aren't MemoryDef's).
  // MemoryDef that may throw are handled during the walk from one def to the
  // next.
  bool mayThrowBetween(Instruction *KillingI, Instruction *DeadI,
                       const Value *KillingUndObj) {
    // First see if we can ignore it by using the fact that KillingI is an
    // alloca/alloca like object that is not visible to the caller during
    // execution of the function.
    if (KillingUndObj && isInvisibleToCallerOnUnwind(KillingUndObj))
      return false;

    if (KillingI->getParent() == DeadI->getParent())
      return ThrowingBlocks.count(KillingI->getParent());
    return !ThrowingBlocks.empty();
  }

  // Check if \p DeadI acts as a DSE barrier for \p KillingI. The following
  // instructions act as barriers:
  //  * A memory instruction that may throw and \p KillingI accesses a non-stack
  //  object.
  //  * Atomic stores stronger that monotonic.
  bool isDSEBarrier(const Value *KillingUndObj, Instruction *DeadI) {
    // If DeadI may throw it acts as a barrier, unless we are to an
    // alloca/alloca like object that does not escape.
    if (DeadI->mayThrow() && !isInvisibleToCallerOnUnwind(KillingUndObj))
      return true;

    // If DeadI is an atomic load/store stronger than monotonic, do not try to
    // eliminate/reorder it.
    if (DeadI->isAtomic()) {
      if (auto *LI = dyn_cast<LoadInst>(DeadI))
        return isStrongerThanMonotonic(LI->getOrdering());
      if (auto *SI = dyn_cast<StoreInst>(DeadI))
        return isStrongerThanMonotonic(SI->getOrdering());
      if (auto *ARMW = dyn_cast<AtomicRMWInst>(DeadI))
        return isStrongerThanMonotonic(ARMW->getOrdering());
      if (auto *CmpXchg = dyn_cast<AtomicCmpXchgInst>(DeadI))
        return isStrongerThanMonotonic(CmpXchg->getSuccessOrdering()) ||
               isStrongerThanMonotonic(CmpXchg->getFailureOrdering());
      llvm_unreachable("other instructions should be skipped in MemorySSA");
    }
    return false;
  }

  /// Eliminate writes to objects that are not visible in the caller and are not
  /// accessed before returning from the function.
  bool eliminateDeadWritesAtEndOfFunction() {
    bool MadeChange = false;
    LLVM_DEBUG(
        dbgs()
        << "Trying to eliminate MemoryDefs at the end of the function\n");
    for (MemoryDef *Def : llvm::reverse(MemDefs)) {
      if (SkipStores.contains(Def))
        continue;

      Instruction *DefI = Def->getMemoryInst();
      auto DefLoc = getLocForWrite(DefI);
      if (!DefLoc || !isRemovable(DefI))
        continue;

      // NOTE: Currently eliminating writes at the end of a function is limited
      // to MemoryDefs with a single underlying object, to save compile-time. In
      // practice it appears the case with multiple underlying objects is very
      // uncommon. If it turns out to be important, we can use
      // getUnderlyingObjects here instead.
      const Value *UO = getUnderlyingObject(DefLoc->Ptr);
      if (!isInvisibleToCallerAfterRet(UO))
        continue;

      if (isWriteAtEndOfFunction(Def)) {
        // See through pointer-to-pointer bitcasts
        LLVM_DEBUG(dbgs() << "   ... MemoryDef is not accessed until the end "
                             "of the function\n");
        deleteDeadInstruction(DefI);
        ++NumFastStores;
        MadeChange = true;
      }
    }
    return MadeChange;
  }

  /// If we have a zero initializing memset following a call to malloc,
  /// try folding it into a call to calloc.
  bool tryFoldIntoCalloc(MemoryDef *Def, const Value *DefUO) {
    Instruction *DefI = Def->getMemoryInst();
    MemSetInst *MemSet = dyn_cast<MemSetInst>(DefI);
    if (!MemSet)
      // TODO: Could handle zero store to small allocation as well.
      return false;
    Constant *StoredConstant = dyn_cast<Constant>(MemSet->getValue());
    if (!StoredConstant || !StoredConstant->isNullValue())
      return false;

    if (!isRemovable(DefI))
      // The memset might be volatile..
      return false;

    if (F.hasFnAttribute(Attribute::SanitizeMemory) ||
        F.hasFnAttribute(Attribute::SanitizeAddress) ||
        F.hasFnAttribute(Attribute::SanitizeHWAddress) ||
        F.getName() == "calloc")
      return false;
    auto *Malloc = const_cast<CallInst *>(dyn_cast<CallInst>(DefUO));
    if (!Malloc)
      return false;
    auto *InnerCallee = Malloc->getCalledFunction();
    if (!InnerCallee)
      return false;
    LibFunc Func;
    if (!TLI.getLibFunc(*InnerCallee, Func) || !TLI.has(Func) ||
        Func != LibFunc_malloc)
      return false;

    auto shouldCreateCalloc = [](CallInst *Malloc, CallInst *Memset) {
      // Check for br(icmp ptr, null), truebb, falsebb) pattern at the end
      // of malloc block
      auto *MallocBB = Malloc->getParent(),
        *MemsetBB = Memset->getParent();
      if (MallocBB == MemsetBB)
        return true;
      auto *Ptr = Memset->getArgOperand(0);
      auto *TI = MallocBB->getTerminator();
      ICmpInst::Predicate Pred;
      BasicBlock *TrueBB, *FalseBB;
      if (!match(TI, m_Br(m_ICmp(Pred, m_Specific(Ptr), m_Zero()), TrueBB,
                          FalseBB)))
        return false;
      if (Pred != ICmpInst::ICMP_EQ || MemsetBB != FalseBB)
        return false;
      return true;
    };

    if (Malloc->getOperand(0) != MemSet->getLength())
      return false;
    if (!shouldCreateCalloc(Malloc, MemSet) ||
        !DT.dominates(Malloc, MemSet) ||
        !memoryIsNotModifiedBetween(Malloc, MemSet, BatchAA, DL, &DT))
      return false;
    IRBuilder<> IRB(Malloc);
    const auto &DL = Malloc->getModule()->getDataLayout();
    auto *Calloc =
      emitCalloc(ConstantInt::get(IRB.getIntPtrTy(DL), 1),
                 Malloc->getArgOperand(0), IRB, TLI);
    if (!Calloc)
      return false;
    MemorySSAUpdater Updater(&MSSA);
    auto *LastDef =
      cast<MemoryDef>(Updater.getMemorySSA()->getMemoryAccess(Malloc));
    auto *NewAccess =
      Updater.createMemoryAccessAfter(cast<Instruction>(Calloc), LastDef,
                                      LastDef);
    auto *NewAccessMD = cast<MemoryDef>(NewAccess);
    Updater.insertDef(NewAccessMD, /*RenameUses=*/true);
    Updater.removeMemoryAccess(Malloc);
    Malloc->replaceAllUsesWith(Calloc);
    Malloc->eraseFromParent();
    return true;
  }

  /// \returns true if \p Def is a no-op store, either because it
  /// directly stores back a loaded value or stores zero to a calloced object.
  bool storeIsNoop(MemoryDef *Def, const Value *DefUO) {
    Instruction *DefI = Def->getMemoryInst();
    StoreInst *Store = dyn_cast<StoreInst>(DefI);
    MemSetInst *MemSet = dyn_cast<MemSetInst>(DefI);
    Constant *StoredConstant = nullptr;
    if (Store)
      StoredConstant = dyn_cast<Constant>(Store->getOperand(0));
    else if (MemSet)
      StoredConstant = dyn_cast<Constant>(MemSet->getValue());
    else
      return false;

    if (!isRemovable(DefI))
      return false;

    if (StoredConstant && isAllocationFn(DefUO, &TLI)) {
      auto *CB = cast<CallBase>(DefUO);
      auto *InitC = getInitialValueOfAllocation(CB, &TLI,
                                                StoredConstant->getType());
      // If the clobbering access is LiveOnEntry, no instructions between them
      // can modify the memory location.
      if (InitC && InitC == StoredConstant)
        return MSSA.isLiveOnEntryDef(
            MSSA.getSkipSelfWalker()->getClobberingMemoryAccess(Def));
    }

    if (!Store)
      return false;

    if (auto *LoadI = dyn_cast<LoadInst>(Store->getOperand(0))) {
      if (LoadI->getPointerOperand() == Store->getOperand(1)) {
        // Get the defining access for the load.
        auto *LoadAccess = MSSA.getMemoryAccess(LoadI)->getDefiningAccess();
        // Fast path: the defining accesses are the same.
        if (LoadAccess == Def->getDefiningAccess())
          return true;

        // Look through phi accesses. Recursively scan all phi accesses by
        // adding them to a worklist. Bail when we run into a memory def that
        // does not match LoadAccess.
        SetVector<MemoryAccess *> ToCheck;
        MemoryAccess *Current =
            MSSA.getWalker()->getClobberingMemoryAccess(Def);
        // We don't want to bail when we run into the store memory def. But,
        // the phi access may point to it. So, pretend like we've already
        // checked it.
        ToCheck.insert(Def);
        ToCheck.insert(Current);
        // Start at current (1) to simulate already having checked Def.
        for (unsigned I = 1; I < ToCheck.size(); ++I) {
          Current = ToCheck[I];
          if (auto PhiAccess = dyn_cast<MemoryPhi>(Current)) {
            // Check all the operands.
            for (auto &Use : PhiAccess->incoming_values())
              ToCheck.insert(cast<MemoryAccess>(&Use));
            continue;
          }

          // If we found a memory def, bail. This happens when we have an
          // unrelated write in between an otherwise noop store.
          assert(isa<MemoryDef>(Current) &&
                 "Only MemoryDefs should reach here.");
          // TODO: Skip no alias MemoryDefs that have no aliasing reads.
          // We are searching for the definition of the store's destination.
          // So, if that is the same definition as the load, then this is a
          // noop. Otherwise, fail.
          if (LoadAccess != Current)
            return false;
        }
        return true;
      }
    }

    return false;
  }

  bool removePartiallyOverlappedStores(InstOverlapIntervalsTy &IOL) {
    bool Changed = false;
    for (auto OI : IOL) {
      Instruction *DeadI = OI.first;
      MemoryLocation Loc = *getLocForWrite(DeadI);
      assert(isRemovable(DeadI) && "Expect only removable instruction");

      const Value *Ptr = Loc.Ptr->stripPointerCasts();
      int64_t DeadStart = 0;
      uint64_t DeadSize = Loc.Size.getValue();
      GetPointerBaseWithConstantOffset(Ptr, DeadStart, DL);
      OverlapIntervalsTy &IntervalMap = OI.second;
      Changed |= tryToShortenEnd(DeadI, IntervalMap, DeadStart, DeadSize);
      if (IntervalMap.empty())
        continue;
      Changed |= tryToShortenBegin(DeadI, IntervalMap, DeadStart, DeadSize);
    }
    return Changed;
  }

  /// Eliminates writes to locations where the value that is being written
  /// is already stored at the same location.
  bool eliminateRedundantStoresOfExistingValues() {
    bool MadeChange = false;
    LLVM_DEBUG(dbgs() << "Trying to eliminate MemoryDefs that write the "
                         "already existing value\n");
    for (auto *Def : MemDefs) {
      if (SkipStores.contains(Def) || MSSA.isLiveOnEntryDef(Def))
        continue;

      Instruction *DefInst = Def->getMemoryInst();
      auto MaybeDefLoc = getLocForWrite(DefInst);
      if (!MaybeDefLoc || !isRemovable(DefInst))
        continue;

      MemoryDef *UpperDef;
      // To conserve compile-time, we avoid walking to the next clobbering def.
      // Instead, we just try to get the optimized access, if it exists. DSE
      // will try to optimize defs during the earlier traversal.
      if (Def->isOptimized())
        UpperDef = dyn_cast<MemoryDef>(Def->getOptimized());
      else
        UpperDef = dyn_cast<MemoryDef>(Def->getDefiningAccess());
      if (!UpperDef || MSSA.isLiveOnEntryDef(UpperDef))
        continue;

      Instruction *UpperInst = UpperDef->getMemoryInst();
      auto IsRedundantStore = [&]() {
        if (DefInst->isIdenticalTo(UpperInst))
          return true;
        if (auto *MemSetI = dyn_cast<MemSetInst>(UpperInst)) {
          if (auto *SI = dyn_cast<StoreInst>(DefInst)) {
            // MemSetInst must have a write location.
            MemoryLocation UpperLoc = *getLocForWrite(UpperInst);
            int64_t InstWriteOffset = 0;
            int64_t DepWriteOffset = 0;
            auto OR = isOverwrite(UpperInst, DefInst, UpperLoc, *MaybeDefLoc,
                                  InstWriteOffset, DepWriteOffset);
            Value *StoredByte = isBytewiseValue(SI->getValueOperand(), DL);
            return StoredByte && StoredByte == MemSetI->getOperand(1) &&
                   OR == OW_Complete;
          }
        }
        return false;
      };

      if (!IsRedundantStore() || isReadClobber(*MaybeDefLoc, DefInst))
        continue;
      LLVM_DEBUG(dbgs() << "DSE: Remove No-Op Store:\n  DEAD: " << *DefInst
                        << '\n');
      deleteDeadInstruction(DefInst);
      NumRedundantStores++;
      MadeChange = true;
    }
    return MadeChange;
  }
};

static bool eliminateDeadStores(Function &F, AliasAnalysis &AA, MemorySSA &MSSA,
                                DominatorTree &DT, PostDominatorTree &PDT,
                                const TargetLibraryInfo &TLI,
                                const LoopInfo &LI) {
  bool MadeChange = false;

  DSEState State(F, AA, MSSA, DT, PDT, TLI, LI);
  // For each store:
  for (unsigned I = 0; I < State.MemDefs.size(); I++) {
    MemoryDef *KillingDef = State.MemDefs[I];
    if (State.SkipStores.count(KillingDef))
      continue;
    Instruction *KillingI = KillingDef->getMemoryInst();

    Optional<MemoryLocation> MaybeKillingLoc;
    if (State.isMemTerminatorInst(KillingI))
      MaybeKillingLoc = State.getLocForTerminator(KillingI).map(
          [](const std::pair<MemoryLocation, bool> &P) { return P.first; });
    else
      MaybeKillingLoc = State.getLocForWrite(KillingI);

    if (!MaybeKillingLoc) {
      LLVM_DEBUG(dbgs() << "Failed to find analyzable write location for "
                        << *KillingI << "\n");
      continue;
    }
    MemoryLocation KillingLoc = *MaybeKillingLoc;
    assert(KillingLoc.Ptr && "KillingLoc should not be null");
    const Value *KillingUndObj = getUnderlyingObject(KillingLoc.Ptr);
    LLVM_DEBUG(dbgs() << "Trying to eliminate MemoryDefs killed by "
                      << *KillingDef << " (" << *KillingI << ")\n");

    unsigned ScanLimit = MemorySSAScanLimit;
    unsigned WalkerStepLimit = MemorySSAUpwardsStepLimit;
    unsigned PartialLimit = MemorySSAPartialStoreLimit;
    // Worklist of MemoryAccesses that may be killed by KillingDef.
    SetVector<MemoryAccess *> ToCheck;
    ToCheck.insert(KillingDef->getDefiningAccess());

    bool Shortend = false;
    bool IsMemTerm = State.isMemTerminatorInst(KillingI);
    // Check if MemoryAccesses in the worklist are killed by KillingDef.
    for (unsigned I = 0; I < ToCheck.size(); I++) {
      MemoryAccess *Current = ToCheck[I];
      if (State.SkipStores.count(Current))
        continue;

      Optional<MemoryAccess *> MaybeDeadAccess = State.getDomMemoryDef(
          KillingDef, Current, KillingLoc, KillingUndObj, ScanLimit,
          WalkerStepLimit, IsMemTerm, PartialLimit);

      if (!MaybeDeadAccess) {
        LLVM_DEBUG(dbgs() << "  finished walk\n");
        continue;
      }

      MemoryAccess *DeadAccess = *MaybeDeadAccess;
      LLVM_DEBUG(dbgs() << " Checking if we can kill " << *DeadAccess);
      if (isa<MemoryPhi>(DeadAccess)) {
        LLVM_DEBUG(dbgs() << "\n  ... adding incoming values to worklist\n");
        for (Value *V : cast<MemoryPhi>(DeadAccess)->incoming_values()) {
          MemoryAccess *IncomingAccess = cast<MemoryAccess>(V);
          BasicBlock *IncomingBlock = IncomingAccess->getBlock();
          BasicBlock *PhiBlock = DeadAccess->getBlock();

          // We only consider incoming MemoryAccesses that come before the
          // MemoryPhi. Otherwise we could discover candidates that do not
          // strictly dominate our starting def.
          if (State.PostOrderNumbers[IncomingBlock] >
              State.PostOrderNumbers[PhiBlock])
            ToCheck.insert(IncomingAccess);
        }
        continue;
      }
      auto *DeadDefAccess = cast<MemoryDef>(DeadAccess);
      Instruction *DeadI = DeadDefAccess->getMemoryInst();
      LLVM_DEBUG(dbgs() << " (" << *DeadI << ")\n");
      ToCheck.insert(DeadDefAccess->getDefiningAccess());
      NumGetDomMemoryDefPassed++;

      if (!DebugCounter::shouldExecute(MemorySSACounter))
        continue;

      MemoryLocation DeadLoc = *State.getLocForWrite(DeadI);

      if (IsMemTerm) {
        const Value *DeadUndObj = getUnderlyingObject(DeadLoc.Ptr);
        if (KillingUndObj != DeadUndObj)
          continue;
        LLVM_DEBUG(dbgs() << "DSE: Remove Dead Store:\n  DEAD: " << *DeadI
                          << "\n  KILLER: " << *KillingI << '\n');
        State.deleteDeadInstruction(DeadI);
        ++NumFastStores;
        MadeChange = true;
      } else {
        // Check if DeadI overwrites KillingI.
        int64_t KillingOffset = 0;
        int64_t DeadOffset = 0;
        OverwriteResult OR = State.isOverwrite(
            KillingI, DeadI, KillingLoc, DeadLoc, KillingOffset, DeadOffset);
        if (OR == OW_MaybePartial) {
          auto Iter = State.IOLs.insert(
              std::make_pair<BasicBlock *, InstOverlapIntervalsTy>(
                  DeadI->getParent(), InstOverlapIntervalsTy()));
          auto &IOL = Iter.first->second;
          OR = isPartialOverwrite(KillingLoc, DeadLoc, KillingOffset,
                                  DeadOffset, DeadI, IOL);
        }

        if (EnablePartialStoreMerging && OR == OW_PartialEarlierWithFullLater) {
          auto *DeadSI = dyn_cast<StoreInst>(DeadI);
          auto *KillingSI = dyn_cast<StoreInst>(KillingI);
          // We are re-using tryToMergePartialOverlappingStores, which requires
          // DeadSI to dominate DeadSI.
          // TODO: implement tryToMergeParialOverlappingStores using MemorySSA.
          if (DeadSI && KillingSI && DT.dominates(DeadSI, KillingSI)) {
            if (Constant *Merged = tryToMergePartialOverlappingStores(
                    KillingSI, DeadSI, KillingOffset, DeadOffset, State.DL,
                    State.BatchAA, &DT)) {

              // Update stored value of earlier store to merged constant.
              DeadSI->setOperand(0, Merged);
              ++NumModifiedStores;
              MadeChange = true;

              Shortend = true;
              // Remove killing store and remove any outstanding overlap
              // intervals for the updated store.
              State.deleteDeadInstruction(KillingSI);
              auto I = State.IOLs.find(DeadSI->getParent());
              if (I != State.IOLs.end())
                I->second.erase(DeadSI);
              break;
            }
          }
        }

        if (OR == OW_Complete) {
          LLVM_DEBUG(dbgs() << "DSE: Remove Dead Store:\n  DEAD: " << *DeadI
                            << "\n  KILLER: " << *KillingI << '\n');
          State.deleteDeadInstruction(DeadI);
          ++NumFastStores;
          MadeChange = true;
        }
      }
    }

    // Check if the store is a no-op.
    if (!Shortend && State.storeIsNoop(KillingDef, KillingUndObj)) {
      LLVM_DEBUG(dbgs() << "DSE: Remove No-Op Store:\n  DEAD: " << *KillingI
                        << '\n');
      State.deleteDeadInstruction(KillingI);
      NumRedundantStores++;
      MadeChange = true;
      continue;
    }

    // Can we form a calloc from a memset/malloc pair?
    if (!Shortend && State.tryFoldIntoCalloc(KillingDef, KillingUndObj)) {
      LLVM_DEBUG(dbgs() << "DSE: Remove memset after forming calloc:\n"
                        << "  DEAD: " << *KillingI << '\n');
      State.deleteDeadInstruction(KillingI);
      MadeChange = true;
      continue;
    }
  }

  if (EnablePartialOverwriteTracking)
    for (auto &KV : State.IOLs)
      MadeChange |= State.removePartiallyOverlappedStores(KV.second);

  MadeChange |= State.eliminateRedundantStoresOfExistingValues();
  MadeChange |= State.eliminateDeadWritesAtEndOfFunction();
  return MadeChange;
}
} // end anonymous namespace

//===----------------------------------------------------------------------===//
// DSE Pass
//===----------------------------------------------------------------------===//
PreservedAnalyses DSEPass::run(Function &F, FunctionAnalysisManager &AM) {
  AliasAnalysis &AA = AM.getResult<AAManager>(F);
  const TargetLibraryInfo &TLI = AM.getResult<TargetLibraryAnalysis>(F);
  DominatorTree &DT = AM.getResult<DominatorTreeAnalysis>(F);
  MemorySSA &MSSA = AM.getResult<MemorySSAAnalysis>(F).getMSSA();
  PostDominatorTree &PDT = AM.getResult<PostDominatorTreeAnalysis>(F);
  LoopInfo &LI = AM.getResult<LoopAnalysis>(F);

  bool Changed = eliminateDeadStores(F, AA, MSSA, DT, PDT, TLI, LI);

#ifdef LLVM_ENABLE_STATS
  if (AreStatisticsEnabled())
    for (auto &I : instructions(F))
      NumRemainingStores += isa<StoreInst>(&I);
#endif

  if (!Changed)
    return PreservedAnalyses::all();

  PreservedAnalyses PA;
  PA.preserveSet<CFGAnalyses>();
  PA.preserve<MemorySSAAnalysis>();
  PA.preserve<LoopAnalysis>();
  return PA;
}

namespace {

/// A legacy pass for the legacy pass manager that wraps \c DSEPass.
class DSELegacyPass : public FunctionPass {
public:
  static char ID; // Pass identification, replacement for typeid

  DSELegacyPass() : FunctionPass(ID) {
    initializeDSELegacyPassPass(*PassRegistry::getPassRegistry());
  }

  bool runOnFunction(Function &F) override {
    if (skipFunction(F))
      return false;

    AliasAnalysis &AA = getAnalysis<AAResultsWrapperPass>().getAAResults();
    DominatorTree &DT = getAnalysis<DominatorTreeWrapperPass>().getDomTree();
    const TargetLibraryInfo &TLI =
        getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(F);
    MemorySSA &MSSA = getAnalysis<MemorySSAWrapperPass>().getMSSA();
    PostDominatorTree &PDT =
        getAnalysis<PostDominatorTreeWrapperPass>().getPostDomTree();
    LoopInfo &LI = getAnalysis<LoopInfoWrapperPass>().getLoopInfo();

    bool Changed = eliminateDeadStores(F, AA, MSSA, DT, PDT, TLI, LI);

#ifdef LLVM_ENABLE_STATS
    if (AreStatisticsEnabled())
      for (auto &I : instructions(F))
        NumRemainingStores += isa<StoreInst>(&I);
#endif

    return Changed;
  }

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.setPreservesCFG();
    AU.addRequired<AAResultsWrapperPass>();
    AU.addRequired<TargetLibraryInfoWrapperPass>();
    AU.addPreserved<GlobalsAAWrapperPass>();
    AU.addRequired<DominatorTreeWrapperPass>();
    AU.addPreserved<DominatorTreeWrapperPass>();
    AU.addRequired<PostDominatorTreeWrapperPass>();
    AU.addRequired<MemorySSAWrapperPass>();
    AU.addPreserved<PostDominatorTreeWrapperPass>();
    AU.addPreserved<MemorySSAWrapperPass>();
    AU.addRequired<LoopInfoWrapperPass>();
    AU.addPreserved<LoopInfoWrapperPass>();
  }
};

} // end anonymous namespace

char DSELegacyPass::ID = 0;

INITIALIZE_PASS_BEGIN(DSELegacyPass, "dse", "Dead Store Elimination", false,
                      false)
INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(PostDominatorTreeWrapperPass)
INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
INITIALIZE_PASS_DEPENDENCY(GlobalsAAWrapperPass)
INITIALIZE_PASS_DEPENDENCY(MemorySSAWrapperPass)
INITIALIZE_PASS_DEPENDENCY(MemoryDependenceWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(LoopInfoWrapperPass)
INITIALIZE_PASS_END(DSELegacyPass, "dse", "Dead Store Elimination", false,
                    false)

FunctionPass *llvm::createDeadStoreEliminationPass() {
  return new DSELegacyPass();
}