aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/llvm12/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
blob: 8064c02e2b392be2b94cb4a9de291e0dba990ee4 (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
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
//===- LoopIdiomRecognize.cpp - Loop idiom recognition --------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This pass implements an idiom recognizer that transforms simple loops into a
// non-loop form.  In cases that this kicks in, it can be a significant
// performance win.
//
// If compiling for code size we avoid idiom recognition if the resulting
// code could be larger than the code for the original loop. One way this could
// happen is if the loop is not removable after idiom recognition due to the
// presence of non-idiom instructions. The initial implementation of the
// heuristics applies to idioms in multi-block loops.
//
//===----------------------------------------------------------------------===//
//
// TODO List:
//
// Future loop memory idioms to recognize:
//   memcmp, memmove, strlen, etc.
// Future floating point idioms to recognize in -ffast-math mode:
//   fpowi
// Future integer operation idioms to recognize:
//   ctpop
//
// Beware that isel's default lowering for ctpop is highly inefficient for
// i64 and larger types when i64 is legal and the value has few bits set.  It
// would be good to enhance isel to emit a loop for ctpop in this case.
//
// This could recognize common matrix multiplies and dot product idioms and
// replace them with calls to BLAS (if linked in??).
//
//===----------------------------------------------------------------------===//

#include "llvm/Transforms/Scalar/LoopIdiomRecognize.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/MapVector.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/CmpInstAnalysis.h"
#include "llvm/Analysis/LoopAccessAnalysis.h"
#include "llvm/Analysis/LoopInfo.h"
#include "llvm/Analysis/LoopPass.h"
#include "llvm/Analysis/MemoryLocation.h"
#include "llvm/Analysis/MemorySSA.h"
#include "llvm/Analysis/MemorySSAUpdater.h"
#include "llvm/Analysis/MustExecute.h"
#include "llvm/Analysis/OptimizationRemarkEmitter.h"
#include "llvm/Analysis/ScalarEvolution.h"
#include "llvm/Analysis/ScalarEvolutionExpressions.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/IR/Attributes.h"
#include "llvm/IR/BasicBlock.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DebugLoc.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/IRBuilder.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/Type.h"
#include "llvm/IR/User.h"
#include "llvm/IR/Value.h"
#include "llvm/IR/ValueHandle.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/raw_ostream.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/BuildLibCalls.h"
#include "llvm/Transforms/Utils/Local.h"
#include "llvm/Transforms/Utils/LoopUtils.h"
#include "llvm/Transforms/Utils/ScalarEvolutionExpander.h"
#include <algorithm>
#include <cassert>
#include <cstdint>
#include <utility>
#include <vector>

using namespace llvm;

#define DEBUG_TYPE "loop-idiom"

STATISTIC(NumMemSet, "Number of memset's formed from loop stores");
STATISTIC(NumMemCpy, "Number of memcpy's formed from loop load+stores");
STATISTIC(
    NumShiftUntilBitTest,
    "Number of uncountable loops recognized as 'shift until bitttest' idiom");

bool DisableLIRP::All;
static cl::opt<bool, true>
    DisableLIRPAll("disable-" DEBUG_TYPE "-all",
                   cl::desc("Options to disable Loop Idiom Recognize Pass."),
                   cl::location(DisableLIRP::All), cl::init(false),
                   cl::ReallyHidden);

bool DisableLIRP::Memset;
static cl::opt<bool, true>
    DisableLIRPMemset("disable-" DEBUG_TYPE "-memset",
                      cl::desc("Proceed with loop idiom recognize pass, but do "
                               "not convert loop(s) to memset."),
                      cl::location(DisableLIRP::Memset), cl::init(false),
                      cl::ReallyHidden);

bool DisableLIRP::Memcpy;
static cl::opt<bool, true>
    DisableLIRPMemcpy("disable-" DEBUG_TYPE "-memcpy",
                      cl::desc("Proceed with loop idiom recognize pass, but do "
                               "not convert loop(s) to memcpy."),
                      cl::location(DisableLIRP::Memcpy), cl::init(false),
                      cl::ReallyHidden);

static cl::opt<bool> UseLIRCodeSizeHeurs(
    "use-lir-code-size-heurs",
    cl::desc("Use loop idiom recognition code size heuristics when compiling"
             "with -Os/-Oz"),
    cl::init(true), cl::Hidden);

namespace {

class LoopIdiomRecognize {
  Loop *CurLoop = nullptr;
  AliasAnalysis *AA;
  DominatorTree *DT;
  LoopInfo *LI;
  ScalarEvolution *SE;
  TargetLibraryInfo *TLI;
  const TargetTransformInfo *TTI;
  const DataLayout *DL;
  OptimizationRemarkEmitter &ORE;
  bool ApplyCodeSizeHeuristics;
  std::unique_ptr<MemorySSAUpdater> MSSAU;

public:
  explicit LoopIdiomRecognize(AliasAnalysis *AA, DominatorTree *DT,
                              LoopInfo *LI, ScalarEvolution *SE,
                              TargetLibraryInfo *TLI,
                              const TargetTransformInfo *TTI, MemorySSA *MSSA,
                              const DataLayout *DL,
                              OptimizationRemarkEmitter &ORE)
      : AA(AA), DT(DT), LI(LI), SE(SE), TLI(TLI), TTI(TTI), DL(DL), ORE(ORE) {
    if (MSSA)
      MSSAU = std::make_unique<MemorySSAUpdater>(MSSA);
  }

  bool runOnLoop(Loop *L);

private:
  using StoreList = SmallVector<StoreInst *, 8>;
  using StoreListMap = MapVector<Value *, StoreList>;

  StoreListMap StoreRefsForMemset;
  StoreListMap StoreRefsForMemsetPattern;
  StoreList StoreRefsForMemcpy;
  bool HasMemset;
  bool HasMemsetPattern;
  bool HasMemcpy;

  /// Return code for isLegalStore()
  enum LegalStoreKind {
    None = 0,
    Memset,
    MemsetPattern,
    Memcpy,
    UnorderedAtomicMemcpy,
    DontUse // Dummy retval never to be used. Allows catching errors in retval
            // handling.
  };

  /// \name Countable Loop Idiom Handling
  /// @{

  bool runOnCountableLoop();
  bool runOnLoopBlock(BasicBlock *BB, const SCEV *BECount,
                      SmallVectorImpl<BasicBlock *> &ExitBlocks);

  void collectStores(BasicBlock *BB);
  LegalStoreKind isLegalStore(StoreInst *SI);
  enum class ForMemset { No, Yes };
  bool processLoopStores(SmallVectorImpl<StoreInst *> &SL, const SCEV *BECount,
                         ForMemset For);
  bool processLoopMemSet(MemSetInst *MSI, const SCEV *BECount);

  bool processLoopStridedStore(Value *DestPtr, unsigned StoreSize,
                               MaybeAlign StoreAlignment, Value *StoredVal,
                               Instruction *TheStore,
                               SmallPtrSetImpl<Instruction *> &Stores,
                               const SCEVAddRecExpr *Ev, const SCEV *BECount,
                               bool NegStride, bool IsLoopMemset = false);
  bool processLoopStoreOfLoopLoad(StoreInst *SI, const SCEV *BECount);
  bool avoidLIRForMultiBlockLoop(bool IsMemset = false,
                                 bool IsLoopMemset = false);

  /// @}
  /// \name Noncountable Loop Idiom Handling
  /// @{

  bool runOnNoncountableLoop();

  bool recognizePopcount();
  void transformLoopToPopcount(BasicBlock *PreCondBB, Instruction *CntInst,
                               PHINode *CntPhi, Value *Var);
  bool recognizeAndInsertFFS();  /// Find First Set: ctlz or cttz
  void transformLoopToCountable(Intrinsic::ID IntrinID, BasicBlock *PreCondBB,
                                Instruction *CntInst, PHINode *CntPhi,
                                Value *Var, Instruction *DefX,
                                const DebugLoc &DL, bool ZeroCheck,
                                bool IsCntPhiUsedOutsideLoop);

  bool recognizeShiftUntilBitTest();

  /// @}
};

class LoopIdiomRecognizeLegacyPass : public LoopPass {
public:
  static char ID;

  explicit LoopIdiomRecognizeLegacyPass() : LoopPass(ID) {
    initializeLoopIdiomRecognizeLegacyPassPass(
        *PassRegistry::getPassRegistry());
  }

  bool runOnLoop(Loop *L, LPPassManager &LPM) override {
    if (DisableLIRP::All)
      return false;

    if (skipLoop(L))
      return false;

    AliasAnalysis *AA = &getAnalysis<AAResultsWrapperPass>().getAAResults();
    DominatorTree *DT = &getAnalysis<DominatorTreeWrapperPass>().getDomTree();
    LoopInfo *LI = &getAnalysis<LoopInfoWrapperPass>().getLoopInfo();
    ScalarEvolution *SE = &getAnalysis<ScalarEvolutionWrapperPass>().getSE();
    TargetLibraryInfo *TLI =
        &getAnalysis<TargetLibraryInfoWrapperPass>().getTLI(
            *L->getHeader()->getParent());
    const TargetTransformInfo *TTI =
        &getAnalysis<TargetTransformInfoWrapperPass>().getTTI(
            *L->getHeader()->getParent());
    const DataLayout *DL = &L->getHeader()->getModule()->getDataLayout();
    auto *MSSAAnalysis = getAnalysisIfAvailable<MemorySSAWrapperPass>();
    MemorySSA *MSSA = nullptr;
    if (MSSAAnalysis)
      MSSA = &MSSAAnalysis->getMSSA();

    // For the old PM, we can't use OptimizationRemarkEmitter as an analysis
    // pass.  Function analyses need to be preserved across loop transformations
    // but ORE cannot be preserved (see comment before the pass definition).
    OptimizationRemarkEmitter ORE(L->getHeader()->getParent());

    LoopIdiomRecognize LIR(AA, DT, LI, SE, TLI, TTI, MSSA, DL, ORE);
    return LIR.runOnLoop(L);
  }

  /// This transformation requires natural loop information & requires that
  /// loop preheaders be inserted into the CFG.
  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.addRequired<TargetLibraryInfoWrapperPass>();
    AU.addRequired<TargetTransformInfoWrapperPass>();
    AU.addPreserved<MemorySSAWrapperPass>();
    getLoopAnalysisUsage(AU);
  }
};

} // end anonymous namespace

char LoopIdiomRecognizeLegacyPass::ID = 0;

PreservedAnalyses LoopIdiomRecognizePass::run(Loop &L, LoopAnalysisManager &AM,
                                              LoopStandardAnalysisResults &AR,
                                              LPMUpdater &) {
  if (DisableLIRP::All)
    return PreservedAnalyses::all();

  const auto *DL = &L.getHeader()->getModule()->getDataLayout();

  // For the new PM, we also can't use OptimizationRemarkEmitter as an analysis
  // pass.  Function analyses need to be preserved across loop transformations
  // but ORE cannot be preserved (see comment before the pass definition).
  OptimizationRemarkEmitter ORE(L.getHeader()->getParent());

  LoopIdiomRecognize LIR(&AR.AA, &AR.DT, &AR.LI, &AR.SE, &AR.TLI, &AR.TTI,
                         AR.MSSA, DL, ORE);
  if (!LIR.runOnLoop(&L))
    return PreservedAnalyses::all();

  auto PA = getLoopPassPreservedAnalyses();
  if (AR.MSSA)
    PA.preserve<MemorySSAAnalysis>();
  return PA;
}

INITIALIZE_PASS_BEGIN(LoopIdiomRecognizeLegacyPass, "loop-idiom",
                      "Recognize loop idioms", false, false)
INITIALIZE_PASS_DEPENDENCY(LoopPass)
INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
INITIALIZE_PASS_DEPENDENCY(TargetTransformInfoWrapperPass)
INITIALIZE_PASS_END(LoopIdiomRecognizeLegacyPass, "loop-idiom",
                    "Recognize loop idioms", false, false)

Pass *llvm::createLoopIdiomPass() { return new LoopIdiomRecognizeLegacyPass(); }

static void deleteDeadInstruction(Instruction *I) {
  I->replaceAllUsesWith(UndefValue::get(I->getType()));
  I->eraseFromParent();
}

//===----------------------------------------------------------------------===//
//
//          Implementation of LoopIdiomRecognize
//
//===----------------------------------------------------------------------===//

bool LoopIdiomRecognize::runOnLoop(Loop *L) {
  CurLoop = L;
  // If the loop could not be converted to canonical form, it must have an
  // indirectbr in it, just give up.
  if (!L->getLoopPreheader())
    return false;

  // Disable loop idiom recognition if the function's name is a common idiom.
  StringRef Name = L->getHeader()->getParent()->getName();
  if (Name == "memset" || Name == "memcpy")
    return false;

  // Determine if code size heuristics need to be applied.
  ApplyCodeSizeHeuristics =
      L->getHeader()->getParent()->hasOptSize() && UseLIRCodeSizeHeurs;

  HasMemset = TLI->has(LibFunc_memset);
  HasMemsetPattern = TLI->has(LibFunc_memset_pattern16);
  HasMemcpy = TLI->has(LibFunc_memcpy);

  if (HasMemset || HasMemsetPattern || HasMemcpy)
    if (SE->hasLoopInvariantBackedgeTakenCount(L))
      return runOnCountableLoop();

  return runOnNoncountableLoop();
}

bool LoopIdiomRecognize::runOnCountableLoop() {
  const SCEV *BECount = SE->getBackedgeTakenCount(CurLoop);
  assert(!isa<SCEVCouldNotCompute>(BECount) &&
         "runOnCountableLoop() called on a loop without a predictable"
         "backedge-taken count");

  // If this loop executes exactly one time, then it should be peeled, not
  // optimized by this pass.
  if (const SCEVConstant *BECst = dyn_cast<SCEVConstant>(BECount))
    if (BECst->getAPInt() == 0)
      return false;

  SmallVector<BasicBlock *, 8> ExitBlocks;
  CurLoop->getUniqueExitBlocks(ExitBlocks);

  LLVM_DEBUG(dbgs() << DEBUG_TYPE " Scanning: F["
                    << CurLoop->getHeader()->getParent()->getName()
                    << "] Countable Loop %" << CurLoop->getHeader()->getName()
                    << "\n");

  // The following transforms hoist stores/memsets into the loop pre-header.
  // Give up if the loop has instructions that may throw.
  SimpleLoopSafetyInfo SafetyInfo;
  SafetyInfo.computeLoopSafetyInfo(CurLoop);
  if (SafetyInfo.anyBlockMayThrow())
    return false;

  bool MadeChange = false;

  // Scan all the blocks in the loop that are not in subloops.
  for (auto *BB : CurLoop->getBlocks()) {
    // Ignore blocks in subloops.
    if (LI->getLoopFor(BB) != CurLoop)
      continue;

    MadeChange |= runOnLoopBlock(BB, BECount, ExitBlocks);
  }
  return MadeChange;
}

static APInt getStoreStride(const SCEVAddRecExpr *StoreEv) {
  const SCEVConstant *ConstStride = cast<SCEVConstant>(StoreEv->getOperand(1));
  return ConstStride->getAPInt();
}

/// getMemSetPatternValue - If a strided store of the specified value is safe to
/// turn into a memset_pattern16, return a ConstantArray of 16 bytes that should
/// be passed in.  Otherwise, return null.
///
/// Note that we don't ever attempt to use memset_pattern8 or 4, because these
/// just replicate their input array and then pass on to memset_pattern16.
static Constant *getMemSetPatternValue(Value *V, const DataLayout *DL) {
  // FIXME: This could check for UndefValue because it can be merged into any
  // other valid pattern.

  // If the value isn't a constant, we can't promote it to being in a constant
  // array.  We could theoretically do a store to an alloca or something, but
  // that doesn't seem worthwhile.
  Constant *C = dyn_cast<Constant>(V);
  if (!C)
    return nullptr;

  // Only handle simple values that are a power of two bytes in size.
  uint64_t Size = DL->getTypeSizeInBits(V->getType());
  if (Size == 0 || (Size & 7) || (Size & (Size - 1)))
    return nullptr;

  // Don't care enough about darwin/ppc to implement this.
  if (DL->isBigEndian())
    return nullptr;

  // Convert to size in bytes.
  Size /= 8;

  // TODO: If CI is larger than 16-bytes, we can try slicing it in half to see
  // if the top and bottom are the same (e.g. for vectors and large integers).
  if (Size > 16)
    return nullptr;

  // If the constant is exactly 16 bytes, just use it.
  if (Size == 16)
    return C;

  // Otherwise, we'll use an array of the constants.
  unsigned ArraySize = 16 / Size;
  ArrayType *AT = ArrayType::get(V->getType(), ArraySize);
  return ConstantArray::get(AT, std::vector<Constant *>(ArraySize, C));
}

LoopIdiomRecognize::LegalStoreKind
LoopIdiomRecognize::isLegalStore(StoreInst *SI) {
  // Don't touch volatile stores.
  if (SI->isVolatile())
    return LegalStoreKind::None;
  // We only want simple or unordered-atomic stores.
  if (!SI->isUnordered())
    return LegalStoreKind::None;

  // Avoid merging nontemporal stores.
  if (SI->getMetadata(LLVMContext::MD_nontemporal))
    return LegalStoreKind::None;

  Value *StoredVal = SI->getValueOperand();
  Value *StorePtr = SI->getPointerOperand();

  // Don't convert stores of non-integral pointer types to memsets (which stores
  // integers).
  if (DL->isNonIntegralPointerType(StoredVal->getType()->getScalarType()))
    return LegalStoreKind::None;

  // Reject stores that are so large that they overflow an unsigned.
  // When storing out scalable vectors we bail out for now, since the code
  // below currently only works for constant strides.
  TypeSize SizeInBits = DL->getTypeSizeInBits(StoredVal->getType());
  if (SizeInBits.isScalable() || (SizeInBits.getFixedSize() & 7) ||
      (SizeInBits.getFixedSize() >> 32) != 0)
    return LegalStoreKind::None;

  // See if the pointer expression is an AddRec like {base,+,1} on the current
  // loop, which indicates a strided store.  If we have something else, it's a
  // random store we can't handle.
  const SCEVAddRecExpr *StoreEv =
      dyn_cast<SCEVAddRecExpr>(SE->getSCEV(StorePtr));
  if (!StoreEv || StoreEv->getLoop() != CurLoop || !StoreEv->isAffine())
    return LegalStoreKind::None;

  // Check to see if we have a constant stride.
  if (!isa<SCEVConstant>(StoreEv->getOperand(1)))
    return LegalStoreKind::None;

  // See if the store can be turned into a memset.

  // If the stored value is a byte-wise value (like i32 -1), then it may be
  // turned into a memset of i8 -1, assuming that all the consecutive bytes
  // are stored.  A store of i32 0x01020304 can never be turned into a memset,
  // but it can be turned into memset_pattern if the target supports it.
  Value *SplatValue = isBytewiseValue(StoredVal, *DL);
  Constant *PatternValue = nullptr;

  // Note: memset and memset_pattern on unordered-atomic is yet not supported
  bool UnorderedAtomic = SI->isUnordered() && !SI->isSimple();

  // If we're allowed to form a memset, and the stored value would be
  // acceptable for memset, use it.
  if (!UnorderedAtomic && HasMemset && SplatValue && !DisableLIRP::Memset &&
      // Verify that the stored value is loop invariant.  If not, we can't
      // promote the memset.
      CurLoop->isLoopInvariant(SplatValue)) {
    // It looks like we can use SplatValue.
    return LegalStoreKind::Memset;
  } else if (!UnorderedAtomic && HasMemsetPattern && !DisableLIRP::Memset &&
             // Don't create memset_pattern16s with address spaces.
             StorePtr->getType()->getPointerAddressSpace() == 0 &&
             (PatternValue = getMemSetPatternValue(StoredVal, DL))) {
    // It looks like we can use PatternValue!
    return LegalStoreKind::MemsetPattern;
  }

  // Otherwise, see if the store can be turned into a memcpy.
  if (HasMemcpy && !DisableLIRP::Memcpy) {
    // Check to see if the stride matches the size of the store.  If so, then we
    // know that every byte is touched in the loop.
    APInt Stride = getStoreStride(StoreEv);
    unsigned StoreSize = DL->getTypeStoreSize(SI->getValueOperand()->getType());
    if (StoreSize != Stride && StoreSize != -Stride)
      return LegalStoreKind::None;

    // The store must be feeding a non-volatile load.
    LoadInst *LI = dyn_cast<LoadInst>(SI->getValueOperand());

    // Only allow non-volatile loads
    if (!LI || LI->isVolatile())
      return LegalStoreKind::None;
    // Only allow simple or unordered-atomic loads
    if (!LI->isUnordered())
      return LegalStoreKind::None;

    // See if the pointer expression is an AddRec like {base,+,1} on the current
    // loop, which indicates a strided load.  If we have something else, it's a
    // random load we can't handle.
    const SCEVAddRecExpr *LoadEv =
        dyn_cast<SCEVAddRecExpr>(SE->getSCEV(LI->getPointerOperand()));
    if (!LoadEv || LoadEv->getLoop() != CurLoop || !LoadEv->isAffine())
      return LegalStoreKind::None;

    // The store and load must share the same stride.
    if (StoreEv->getOperand(1) != LoadEv->getOperand(1))
      return LegalStoreKind::None;

    // Success.  This store can be converted into a memcpy.
    UnorderedAtomic = UnorderedAtomic || LI->isAtomic();
    return UnorderedAtomic ? LegalStoreKind::UnorderedAtomicMemcpy
                           : LegalStoreKind::Memcpy;
  }
  // This store can't be transformed into a memset/memcpy.
  return LegalStoreKind::None;
}

void LoopIdiomRecognize::collectStores(BasicBlock *BB) {
  StoreRefsForMemset.clear();
  StoreRefsForMemsetPattern.clear();
  StoreRefsForMemcpy.clear();
  for (Instruction &I : *BB) {
    StoreInst *SI = dyn_cast<StoreInst>(&I);
    if (!SI)
      continue;

    // Make sure this is a strided store with a constant stride.
    switch (isLegalStore(SI)) {
    case LegalStoreKind::None:
      // Nothing to do
      break;
    case LegalStoreKind::Memset: {
      // Find the base pointer.
      Value *Ptr = getUnderlyingObject(SI->getPointerOperand());
      StoreRefsForMemset[Ptr].push_back(SI);
    } break;
    case LegalStoreKind::MemsetPattern: {
      // Find the base pointer.
      Value *Ptr = getUnderlyingObject(SI->getPointerOperand());
      StoreRefsForMemsetPattern[Ptr].push_back(SI);
    } break;
    case LegalStoreKind::Memcpy:
    case LegalStoreKind::UnorderedAtomicMemcpy:
      StoreRefsForMemcpy.push_back(SI);
      break;
    default:
      assert(false && "unhandled return value");
      break;
    }
  }
}

/// runOnLoopBlock - Process the specified block, which lives in a counted loop
/// with the specified backedge count.  This block is known to be in the current
/// loop and not in any subloops.
bool LoopIdiomRecognize::runOnLoopBlock(
    BasicBlock *BB, const SCEV *BECount,
    SmallVectorImpl<BasicBlock *> &ExitBlocks) {
  // We can only promote stores in this block if they are unconditionally
  // executed in the loop.  For a block to be unconditionally executed, it has
  // to dominate all the exit blocks of the loop.  Verify this now.
  for (unsigned i = 0, e = ExitBlocks.size(); i != e; ++i)
    if (!DT->dominates(BB, ExitBlocks[i]))
      return false;

  bool MadeChange = false;
  // Look for store instructions, which may be optimized to memset/memcpy.
  collectStores(BB);

  // Look for a single store or sets of stores with a common base, which can be
  // optimized into a memset (memset_pattern).  The latter most commonly happens
  // with structs and handunrolled loops.
  for (auto &SL : StoreRefsForMemset)
    MadeChange |= processLoopStores(SL.second, BECount, ForMemset::Yes);

  for (auto &SL : StoreRefsForMemsetPattern)
    MadeChange |= processLoopStores(SL.second, BECount, ForMemset::No);

  // Optimize the store into a memcpy, if it feeds an similarly strided load.
  for (auto &SI : StoreRefsForMemcpy)
    MadeChange |= processLoopStoreOfLoopLoad(SI, BECount);

  for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E;) {
    Instruction *Inst = &*I++;
    // Look for memset instructions, which may be optimized to a larger memset.
    if (MemSetInst *MSI = dyn_cast<MemSetInst>(Inst)) {
      WeakTrackingVH InstPtr(&*I);
      if (!processLoopMemSet(MSI, BECount))
        continue;
      MadeChange = true;

      // If processing the memset invalidated our iterator, start over from the
      // top of the block.
      if (!InstPtr)
        I = BB->begin();
      continue;
    }
  }

  return MadeChange;
}

/// See if this store(s) can be promoted to a memset.
bool LoopIdiomRecognize::processLoopStores(SmallVectorImpl<StoreInst *> &SL,
                                           const SCEV *BECount, ForMemset For) {
  // Try to find consecutive stores that can be transformed into memsets.
  SetVector<StoreInst *> Heads, Tails;
  SmallDenseMap<StoreInst *, StoreInst *> ConsecutiveChain;

  // Do a quadratic search on all of the given stores and find
  // all of the pairs of stores that follow each other.
  SmallVector<unsigned, 16> IndexQueue;
  for (unsigned i = 0, e = SL.size(); i < e; ++i) {
    assert(SL[i]->isSimple() && "Expected only non-volatile stores.");

    Value *FirstStoredVal = SL[i]->getValueOperand();
    Value *FirstStorePtr = SL[i]->getPointerOperand();
    const SCEVAddRecExpr *FirstStoreEv =
        cast<SCEVAddRecExpr>(SE->getSCEV(FirstStorePtr));
    APInt FirstStride = getStoreStride(FirstStoreEv);
    unsigned FirstStoreSize = DL->getTypeStoreSize(SL[i]->getValueOperand()->getType());

    // See if we can optimize just this store in isolation.
    if (FirstStride == FirstStoreSize || -FirstStride == FirstStoreSize) {
      Heads.insert(SL[i]);
      continue;
    }

    Value *FirstSplatValue = nullptr;
    Constant *FirstPatternValue = nullptr;

    if (For == ForMemset::Yes)
      FirstSplatValue = isBytewiseValue(FirstStoredVal, *DL);
    else
      FirstPatternValue = getMemSetPatternValue(FirstStoredVal, DL);

    assert((FirstSplatValue || FirstPatternValue) &&
           "Expected either splat value or pattern value.");

    IndexQueue.clear();
    // If a store has multiple consecutive store candidates, search Stores
    // array according to the sequence: from i+1 to e, then from i-1 to 0.
    // This is because usually pairing with immediate succeeding or preceding
    // candidate create the best chance to find memset opportunity.
    unsigned j = 0;
    for (j = i + 1; j < e; ++j)
      IndexQueue.push_back(j);
    for (j = i; j > 0; --j)
      IndexQueue.push_back(j - 1);

    for (auto &k : IndexQueue) {
      assert(SL[k]->isSimple() && "Expected only non-volatile stores.");
      Value *SecondStorePtr = SL[k]->getPointerOperand();
      const SCEVAddRecExpr *SecondStoreEv =
          cast<SCEVAddRecExpr>(SE->getSCEV(SecondStorePtr));
      APInt SecondStride = getStoreStride(SecondStoreEv);

      if (FirstStride != SecondStride)
        continue;

      Value *SecondStoredVal = SL[k]->getValueOperand();
      Value *SecondSplatValue = nullptr;
      Constant *SecondPatternValue = nullptr;

      if (For == ForMemset::Yes)
        SecondSplatValue = isBytewiseValue(SecondStoredVal, *DL);
      else
        SecondPatternValue = getMemSetPatternValue(SecondStoredVal, DL);

      assert((SecondSplatValue || SecondPatternValue) &&
             "Expected either splat value or pattern value.");

      if (isConsecutiveAccess(SL[i], SL[k], *DL, *SE, false)) {
        if (For == ForMemset::Yes) {
          if (isa<UndefValue>(FirstSplatValue))
            FirstSplatValue = SecondSplatValue;
          if (FirstSplatValue != SecondSplatValue)
            continue;
        } else {
          if (isa<UndefValue>(FirstPatternValue))
            FirstPatternValue = SecondPatternValue;
          if (FirstPatternValue != SecondPatternValue)
            continue;
        }
        Tails.insert(SL[k]);
        Heads.insert(SL[i]);
        ConsecutiveChain[SL[i]] = SL[k];
        break;
      }
    }
  }

  // We may run into multiple chains that merge into a single chain. We mark the
  // stores that we transformed so that we don't visit the same store twice.
  SmallPtrSet<Value *, 16> TransformedStores;
  bool Changed = false;

  // For stores that start but don't end a link in the chain:
  for (SetVector<StoreInst *>::iterator it = Heads.begin(), e = Heads.end();
       it != e; ++it) {
    if (Tails.count(*it))
      continue;

    // We found a store instr that starts a chain. Now follow the chain and try
    // to transform it.
    SmallPtrSet<Instruction *, 8> AdjacentStores;
    StoreInst *I = *it;

    StoreInst *HeadStore = I;
    unsigned StoreSize = 0;

    // Collect the chain into a list.
    while (Tails.count(I) || Heads.count(I)) {
      if (TransformedStores.count(I))
        break;
      AdjacentStores.insert(I);

      StoreSize += DL->getTypeStoreSize(I->getValueOperand()->getType());
      // Move to the next value in the chain.
      I = ConsecutiveChain[I];
    }

    Value *StoredVal = HeadStore->getValueOperand();
    Value *StorePtr = HeadStore->getPointerOperand();
    const SCEVAddRecExpr *StoreEv = cast<SCEVAddRecExpr>(SE->getSCEV(StorePtr));
    APInt Stride = getStoreStride(StoreEv);

    // Check to see if the stride matches the size of the stores.  If so, then
    // we know that every byte is touched in the loop.
    if (StoreSize != Stride && StoreSize != -Stride)
      continue;

    bool NegStride = StoreSize == -Stride;

    if (processLoopStridedStore(StorePtr, StoreSize,
                                MaybeAlign(HeadStore->getAlignment()),
                                StoredVal, HeadStore, AdjacentStores, StoreEv,
                                BECount, NegStride)) {
      TransformedStores.insert(AdjacentStores.begin(), AdjacentStores.end());
      Changed = true;
    }
  }

  return Changed;
}

/// processLoopMemSet - See if this memset can be promoted to a large memset.
bool LoopIdiomRecognize::processLoopMemSet(MemSetInst *MSI,
                                           const SCEV *BECount) {
  // We can only handle non-volatile memsets with a constant size.
  if (MSI->isVolatile() || !isa<ConstantInt>(MSI->getLength()))
    return false;

  // If we're not allowed to hack on memset, we fail.
  if (!HasMemset)
    return false;

  Value *Pointer = MSI->getDest();

  // See if the pointer expression is an AddRec like {base,+,1} on the current
  // loop, which indicates a strided store.  If we have something else, it's a
  // random store we can't handle.
  const SCEVAddRecExpr *Ev = dyn_cast<SCEVAddRecExpr>(SE->getSCEV(Pointer));
  if (!Ev || Ev->getLoop() != CurLoop || !Ev->isAffine())
    return false;

  // Reject memsets that are so large that they overflow an unsigned.
  uint64_t SizeInBytes = cast<ConstantInt>(MSI->getLength())->getZExtValue();
  if ((SizeInBytes >> 32) != 0)
    return false;

  // Check to see if the stride matches the size of the memset.  If so, then we
  // know that every byte is touched in the loop.
  const SCEVConstant *ConstStride = dyn_cast<SCEVConstant>(Ev->getOperand(1));
  if (!ConstStride)
    return false;

  APInt Stride = ConstStride->getAPInt();
  if (SizeInBytes != Stride && SizeInBytes != -Stride)
    return false;

  // Verify that the memset value is loop invariant.  If not, we can't promote
  // the memset.
  Value *SplatValue = MSI->getValue();
  if (!SplatValue || !CurLoop->isLoopInvariant(SplatValue))
    return false;

  SmallPtrSet<Instruction *, 1> MSIs;
  MSIs.insert(MSI);
  bool NegStride = SizeInBytes == -Stride;
  return processLoopStridedStore(
      Pointer, (unsigned)SizeInBytes, MaybeAlign(MSI->getDestAlignment()),
      SplatValue, MSI, MSIs, Ev, BECount, NegStride, /*IsLoopMemset=*/true);
}

/// mayLoopAccessLocation - Return true if the specified loop might access the
/// specified pointer location, which is a loop-strided access.  The 'Access'
/// argument specifies what the verboten forms of access are (read or write).
static bool
mayLoopAccessLocation(Value *Ptr, ModRefInfo Access, Loop *L,
                      const SCEV *BECount, unsigned StoreSize,
                      AliasAnalysis &AA,
                      SmallPtrSetImpl<Instruction *> &IgnoredStores) {
  // Get the location that may be stored across the loop.  Since the access is
  // strided positively through memory, we say that the modified location starts
  // at the pointer and has infinite size.
  LocationSize AccessSize = LocationSize::afterPointer();

  // If the loop iterates a fixed number of times, we can refine the access size
  // to be exactly the size of the memset, which is (BECount+1)*StoreSize
  if (const SCEVConstant *BECst = dyn_cast<SCEVConstant>(BECount))
    AccessSize = LocationSize::precise((BECst->getValue()->getZExtValue() + 1) *
                                       StoreSize);

  // TODO: For this to be really effective, we have to dive into the pointer
  // operand in the store.  Store to &A[i] of 100 will always return may alias
  // with store of &A[100], we need to StoreLoc to be "A" with size of 100,
  // which will then no-alias a store to &A[100].
  MemoryLocation StoreLoc(Ptr, AccessSize);

  for (Loop::block_iterator BI = L->block_begin(), E = L->block_end(); BI != E;
       ++BI)
    for (Instruction &I : **BI)
      if (IgnoredStores.count(&I) == 0 &&
          isModOrRefSet(
              intersectModRef(AA.getModRefInfo(&I, StoreLoc), Access)))
        return true;

  return false;
}

// If we have a negative stride, Start refers to the end of the memory location
// we're trying to memset.  Therefore, we need to recompute the base pointer,
// which is just Start - BECount*Size.
static const SCEV *getStartForNegStride(const SCEV *Start, const SCEV *BECount,
                                        Type *IntPtr, unsigned StoreSize,
                                        ScalarEvolution *SE) {
  const SCEV *Index = SE->getTruncateOrZeroExtend(BECount, IntPtr);
  if (StoreSize != 1)
    Index = SE->getMulExpr(Index, SE->getConstant(IntPtr, StoreSize),
                           SCEV::FlagNUW);
  return SE->getMinusSCEV(Start, Index);
}

/// Compute the number of bytes as a SCEV from the backedge taken count.
///
/// This also maps the SCEV into the provided type and tries to handle the
/// computation in a way that will fold cleanly.
static const SCEV *getNumBytes(const SCEV *BECount, Type *IntPtr,
                               unsigned StoreSize, Loop *CurLoop,
                               const DataLayout *DL, ScalarEvolution *SE) {
  const SCEV *NumBytesS;
  // The # stored bytes is (BECount+1)*Size.  Expand the trip count out to
  // pointer size if it isn't already.
  //
  // If we're going to need to zero extend the BE count, check if we can add
  // one to it prior to zero extending without overflow. Provided this is safe,
  // it allows better simplification of the +1.
  if (DL->getTypeSizeInBits(BECount->getType()).getFixedSize() <
          DL->getTypeSizeInBits(IntPtr).getFixedSize() &&
      SE->isLoopEntryGuardedByCond(
          CurLoop, ICmpInst::ICMP_NE, BECount,
          SE->getNegativeSCEV(SE->getOne(BECount->getType())))) {
    NumBytesS = SE->getZeroExtendExpr(
        SE->getAddExpr(BECount, SE->getOne(BECount->getType()), SCEV::FlagNUW),
        IntPtr);
  } else {
    NumBytesS = SE->getAddExpr(SE->getTruncateOrZeroExtend(BECount, IntPtr),
                               SE->getOne(IntPtr), SCEV::FlagNUW);
  }

  // And scale it based on the store size.
  if (StoreSize != 1) {
    NumBytesS = SE->getMulExpr(NumBytesS, SE->getConstant(IntPtr, StoreSize),
                               SCEV::FlagNUW);
  }
  return NumBytesS;
}

/// processLoopStridedStore - We see a strided store of some value.  If we can
/// transform this into a memset or memset_pattern in the loop preheader, do so.
bool LoopIdiomRecognize::processLoopStridedStore(
    Value *DestPtr, unsigned StoreSize, MaybeAlign StoreAlignment,
    Value *StoredVal, Instruction *TheStore,
    SmallPtrSetImpl<Instruction *> &Stores, const SCEVAddRecExpr *Ev,
    const SCEV *BECount, bool NegStride, bool IsLoopMemset) {
  Value *SplatValue = isBytewiseValue(StoredVal, *DL);
  Constant *PatternValue = nullptr;

  if (!SplatValue)
    PatternValue = getMemSetPatternValue(StoredVal, DL);

  assert((SplatValue || PatternValue) &&
         "Expected either splat value or pattern value.");

  // The trip count of the loop and the base pointer of the addrec SCEV is
  // guaranteed to be loop invariant, which means that it should dominate the
  // header.  This allows us to insert code for it in the preheader.
  unsigned DestAS = DestPtr->getType()->getPointerAddressSpace();
  BasicBlock *Preheader = CurLoop->getLoopPreheader();
  IRBuilder<> Builder(Preheader->getTerminator());
  SCEVExpander Expander(*SE, *DL, "loop-idiom");
  SCEVExpanderCleaner ExpCleaner(Expander, *DT);

  Type *DestInt8PtrTy = Builder.getInt8PtrTy(DestAS);
  Type *IntIdxTy = DL->getIndexType(DestPtr->getType());

  bool Changed = false;
  const SCEV *Start = Ev->getStart();
  // Handle negative strided loops.
  if (NegStride)
    Start = getStartForNegStride(Start, BECount, IntIdxTy, StoreSize, SE);

  // TODO: ideally we should still be able to generate memset if SCEV expander
  // is taught to generate the dependencies at the latest point.
  if (!isSafeToExpand(Start, *SE))
    return Changed;

  // Okay, we have a strided store "p[i]" of a splattable value.  We can turn
  // this into a memset in the loop preheader now if we want.  However, this
  // would be unsafe to do if there is anything else in the loop that may read
  // or write to the aliased location.  Check for any overlap by generating the
  // base pointer and checking the region.
  Value *BasePtr =
      Expander.expandCodeFor(Start, DestInt8PtrTy, Preheader->getTerminator());

  // From here on out, conservatively report to the pass manager that we've
  // changed the IR, even if we later clean up these added instructions. There
  // may be structural differences e.g. in the order of use lists not accounted
  // for in just a textual dump of the IR. This is written as a variable, even
  // though statically all the places this dominates could be replaced with
  // 'true', with the hope that anyone trying to be clever / "more precise" with
  // the return value will read this comment, and leave them alone.
  Changed = true;

  if (mayLoopAccessLocation(BasePtr, ModRefInfo::ModRef, CurLoop, BECount,
                            StoreSize, *AA, Stores))
    return Changed;

  if (avoidLIRForMultiBlockLoop(/*IsMemset=*/true, IsLoopMemset))
    return Changed;

  // Okay, everything looks good, insert the memset.

  const SCEV *NumBytesS =
      getNumBytes(BECount, IntIdxTy, StoreSize, CurLoop, DL, SE);

  // TODO: ideally we should still be able to generate memset if SCEV expander
  // is taught to generate the dependencies at the latest point.
  if (!isSafeToExpand(NumBytesS, *SE))
    return Changed;

  Value *NumBytes =
      Expander.expandCodeFor(NumBytesS, IntIdxTy, Preheader->getTerminator());

  CallInst *NewCall;
  if (SplatValue) {
    NewCall = Builder.CreateMemSet(BasePtr, SplatValue, NumBytes,
                                   MaybeAlign(StoreAlignment));
  } else {
    // Everything is emitted in default address space
    Type *Int8PtrTy = DestInt8PtrTy;

    Module *M = TheStore->getModule();
    StringRef FuncName = "memset_pattern16";
    FunctionCallee MSP = M->getOrInsertFunction(FuncName, Builder.getVoidTy(),
                                                Int8PtrTy, Int8PtrTy, IntIdxTy);
    inferLibFuncAttributes(M, FuncName, *TLI);

    // Otherwise we should form a memset_pattern16.  PatternValue is known to be
    // an constant array of 16-bytes.  Plop the value into a mergable global.
    GlobalVariable *GV = new GlobalVariable(*M, PatternValue->getType(), true,
                                            GlobalValue::PrivateLinkage,
                                            PatternValue, ".memset_pattern");
    GV->setUnnamedAddr(GlobalValue::UnnamedAddr::Global); // Ok to merge these.
    GV->setAlignment(Align(16));
    Value *PatternPtr = ConstantExpr::getBitCast(GV, Int8PtrTy);
    NewCall = Builder.CreateCall(MSP, {BasePtr, PatternPtr, NumBytes});
  }
  NewCall->setDebugLoc(TheStore->getDebugLoc());

  if (MSSAU) {
    MemoryAccess *NewMemAcc = MSSAU->createMemoryAccessInBB(
        NewCall, nullptr, NewCall->getParent(), MemorySSA::BeforeTerminator);
    MSSAU->insertDef(cast<MemoryDef>(NewMemAcc), true);
  }

  LLVM_DEBUG(dbgs() << "  Formed memset: " << *NewCall << "\n"
                    << "    from store to: " << *Ev << " at: " << *TheStore
                    << "\n");

  ORE.emit([&]() {
    return OptimizationRemark(DEBUG_TYPE, "ProcessLoopStridedStore",
                              NewCall->getDebugLoc(), Preheader)
           << "Transformed loop-strided store into a call to "
           << ore::NV("NewFunction", NewCall->getCalledFunction())
           << "() function";
  });

  // Okay, the memset has been formed.  Zap the original store and anything that
  // feeds into it.
  for (auto *I : Stores) {
    if (MSSAU)
      MSSAU->removeMemoryAccess(I, true);
    deleteDeadInstruction(I);
  }
  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();
  ++NumMemSet;
  ExpCleaner.markResultUsed();
  return true;
}

/// If the stored value is a strided load in the same loop with the same stride
/// this may be transformable into a memcpy.  This kicks in for stuff like
/// for (i) A[i] = B[i];
bool LoopIdiomRecognize::processLoopStoreOfLoopLoad(StoreInst *SI,
                                                    const SCEV *BECount) {
  assert(SI->isUnordered() && "Expected only non-volatile non-ordered stores.");

  Value *StorePtr = SI->getPointerOperand();
  const SCEVAddRecExpr *StoreEv = cast<SCEVAddRecExpr>(SE->getSCEV(StorePtr));
  APInt Stride = getStoreStride(StoreEv);
  unsigned StoreSize = DL->getTypeStoreSize(SI->getValueOperand()->getType());
  bool NegStride = StoreSize == -Stride;

  // The store must be feeding a non-volatile load.
  LoadInst *LI = cast<LoadInst>(SI->getValueOperand());
  assert(LI->isUnordered() && "Expected only non-volatile non-ordered loads.");

  // See if the pointer expression is an AddRec like {base,+,1} on the current
  // loop, which indicates a strided load.  If we have something else, it's a
  // random load we can't handle.
  const SCEVAddRecExpr *LoadEv =
      cast<SCEVAddRecExpr>(SE->getSCEV(LI->getPointerOperand()));

  // The trip count of the loop and the base pointer of the addrec SCEV is
  // guaranteed to be loop invariant, which means that it should dominate the
  // header.  This allows us to insert code for it in the preheader.
  BasicBlock *Preheader = CurLoop->getLoopPreheader();
  IRBuilder<> Builder(Preheader->getTerminator());
  SCEVExpander Expander(*SE, *DL, "loop-idiom");

  SCEVExpanderCleaner ExpCleaner(Expander, *DT);

  bool Changed = false;
  const SCEV *StrStart = StoreEv->getStart();
  unsigned StrAS = SI->getPointerAddressSpace();
  Type *IntIdxTy = Builder.getIntNTy(DL->getIndexSizeInBits(StrAS));

  // Handle negative strided loops.
  if (NegStride)
    StrStart = getStartForNegStride(StrStart, BECount, IntIdxTy, StoreSize, SE);

  // Okay, we have a strided store "p[i]" of a loaded value.  We can turn
  // this into a memcpy in the loop preheader now if we want.  However, this
  // would be unsafe to do if there is anything else in the loop that may read
  // or write the memory region we're storing to.  This includes the load that
  // feeds the stores.  Check for an alias by generating the base address and
  // checking everything.
  Value *StoreBasePtr = Expander.expandCodeFor(
      StrStart, Builder.getInt8PtrTy(StrAS), Preheader->getTerminator());

  // From here on out, conservatively report to the pass manager that we've
  // changed the IR, even if we later clean up these added instructions. There
  // may be structural differences e.g. in the order of use lists not accounted
  // for in just a textual dump of the IR. This is written as a variable, even
  // though statically all the places this dominates could be replaced with
  // 'true', with the hope that anyone trying to be clever / "more precise" with
  // the return value will read this comment, and leave them alone.
  Changed = true;

  SmallPtrSet<Instruction *, 1> Stores;
  Stores.insert(SI);
  if (mayLoopAccessLocation(StoreBasePtr, ModRefInfo::ModRef, CurLoop, BECount,
                            StoreSize, *AA, Stores))
    return Changed;

  const SCEV *LdStart = LoadEv->getStart();
  unsigned LdAS = LI->getPointerAddressSpace();

  // Handle negative strided loops.
  if (NegStride)
    LdStart = getStartForNegStride(LdStart, BECount, IntIdxTy, StoreSize, SE);

  // For a memcpy, we have to make sure that the input array is not being
  // mutated by the loop.
  Value *LoadBasePtr = Expander.expandCodeFor(
      LdStart, Builder.getInt8PtrTy(LdAS), Preheader->getTerminator());

  if (mayLoopAccessLocation(LoadBasePtr, ModRefInfo::Mod, CurLoop, BECount,
                            StoreSize, *AA, Stores))
    return Changed;

  if (avoidLIRForMultiBlockLoop())
    return Changed;

  // Okay, everything is safe, we can transform this!

  const SCEV *NumBytesS =
      getNumBytes(BECount, IntIdxTy, StoreSize, CurLoop, DL, SE);

  Value *NumBytes =
      Expander.expandCodeFor(NumBytesS, IntIdxTy, Preheader->getTerminator());

  CallInst *NewCall = nullptr;
  // Check whether to generate an unordered atomic memcpy:
  //  If the load or store are atomic, then they must necessarily be unordered
  //  by previous checks.
  if (!SI->isAtomic() && !LI->isAtomic())
    NewCall = Builder.CreateMemCpy(StoreBasePtr, SI->getAlign(), LoadBasePtr,
                                   LI->getAlign(), NumBytes);
  else {
    // We cannot allow unaligned ops for unordered load/store, so reject
    // anything where the alignment isn't at least the element size.
    const Align StoreAlign = SI->getAlign();
    const Align LoadAlign = LI->getAlign();
    if (StoreAlign < StoreSize || LoadAlign < StoreSize)
      return Changed;

    // If the element.atomic memcpy is not lowered into explicit
    // loads/stores later, then it will be lowered into an element-size
    // specific lib call. If the lib call doesn't exist for our store size, then
    // we shouldn't generate the memcpy.
    if (StoreSize > TTI->getAtomicMemIntrinsicMaxElementSize())
      return Changed;

    // Create the call.
    // Note that unordered atomic loads/stores are *required* by the spec to
    // have an alignment but non-atomic loads/stores may not.
    NewCall = Builder.CreateElementUnorderedAtomicMemCpy(
        StoreBasePtr, StoreAlign, LoadBasePtr, LoadAlign, NumBytes,
        StoreSize);
  }
  NewCall->setDebugLoc(SI->getDebugLoc());

  if (MSSAU) {
    MemoryAccess *NewMemAcc = MSSAU->createMemoryAccessInBB(
        NewCall, nullptr, NewCall->getParent(), MemorySSA::BeforeTerminator);
    MSSAU->insertDef(cast<MemoryDef>(NewMemAcc), true);
  }

  LLVM_DEBUG(dbgs() << "  Formed memcpy: " << *NewCall << "\n"
                    << "    from load ptr=" << *LoadEv << " at: " << *LI << "\n"
                    << "    from store ptr=" << *StoreEv << " at: " << *SI
                    << "\n");

  ORE.emit([&]() {
    return OptimizationRemark(DEBUG_TYPE, "ProcessLoopStoreOfLoopLoad",
                              NewCall->getDebugLoc(), Preheader)
           << "Formed a call to "
           << ore::NV("NewFunction", NewCall->getCalledFunction())
           << "() function";
  });

  // Okay, the memcpy has been formed.  Zap the original store and anything that
  // feeds into it.
  if (MSSAU)
    MSSAU->removeMemoryAccess(SI, true);
  deleteDeadInstruction(SI);
  if (MSSAU && VerifyMemorySSA)
    MSSAU->getMemorySSA()->verifyMemorySSA();
  ++NumMemCpy;
  ExpCleaner.markResultUsed();
  return true;
}

// When compiling for codesize we avoid idiom recognition for a multi-block loop
// unless it is a loop_memset idiom or a memset/memcpy idiom in a nested loop.
//
bool LoopIdiomRecognize::avoidLIRForMultiBlockLoop(bool IsMemset,
                                                   bool IsLoopMemset) {
  if (ApplyCodeSizeHeuristics && CurLoop->getNumBlocks() > 1) {
    if (CurLoop->isOutermost() && (!IsMemset || !IsLoopMemset)) {
      LLVM_DEBUG(dbgs() << "  " << CurLoop->getHeader()->getParent()->getName()
                        << " : LIR " << (IsMemset ? "Memset" : "Memcpy")
                        << " avoided: multi-block top-level loop\n");
      return true;
    }
  }

  return false;
}

bool LoopIdiomRecognize::runOnNoncountableLoop() {
  LLVM_DEBUG(dbgs() << DEBUG_TYPE " Scanning: F["
                    << CurLoop->getHeader()->getParent()->getName()
                    << "] Noncountable Loop %"
                    << CurLoop->getHeader()->getName() << "\n");

  return recognizePopcount() || recognizeAndInsertFFS() ||
         recognizeShiftUntilBitTest();
}

/// Check if the given conditional branch is based on the comparison between
/// a variable and zero, and if the variable is non-zero or zero (JmpOnZero is
/// true), the control yields to the loop entry. If the branch matches the
/// behavior, the variable involved in the comparison is returned. This function
/// will be called to see if the precondition and postcondition of the loop are
/// in desirable form.
static Value *matchCondition(BranchInst *BI, BasicBlock *LoopEntry,
                             bool JmpOnZero = false) {
  if (!BI || !BI->isConditional())
    return nullptr;

  ICmpInst *Cond = dyn_cast<ICmpInst>(BI->getCondition());
  if (!Cond)
    return nullptr;

  ConstantInt *CmpZero = dyn_cast<ConstantInt>(Cond->getOperand(1));
  if (!CmpZero || !CmpZero->isZero())
    return nullptr;

  BasicBlock *TrueSucc = BI->getSuccessor(0);
  BasicBlock *FalseSucc = BI->getSuccessor(1);
  if (JmpOnZero)
    std::swap(TrueSucc, FalseSucc);

  ICmpInst::Predicate Pred = Cond->getPredicate();
  if ((Pred == ICmpInst::ICMP_NE && TrueSucc == LoopEntry) ||
      (Pred == ICmpInst::ICMP_EQ && FalseSucc == LoopEntry))
    return Cond->getOperand(0);

  return nullptr;
}

// Check if the recurrence variable `VarX` is in the right form to create
// the idiom. Returns the value coerced to a PHINode if so.
static PHINode *getRecurrenceVar(Value *VarX, Instruction *DefX,
                                 BasicBlock *LoopEntry) {
  auto *PhiX = dyn_cast<PHINode>(VarX);
  if (PhiX && PhiX->getParent() == LoopEntry &&
      (PhiX->getOperand(0) == DefX || PhiX->getOperand(1) == DefX))
    return PhiX;
  return nullptr;
}

/// Return true iff the idiom is detected in the loop.
///
/// Additionally:
/// 1) \p CntInst is set to the instruction counting the population bit.
/// 2) \p CntPhi is set to the corresponding phi node.
/// 3) \p Var is set to the value whose population bits are being counted.
///
/// The core idiom we are trying to detect is:
/// \code
///    if (x0 != 0)
///      goto loop-exit // the precondition of the loop
///    cnt0 = init-val;
///    do {
///       x1 = phi (x0, x2);
///       cnt1 = phi(cnt0, cnt2);
///
///       cnt2 = cnt1 + 1;
///        ...
///       x2 = x1 & (x1 - 1);
///        ...
///    } while(x != 0);
///
/// loop-exit:
/// \endcode
static bool detectPopcountIdiom(Loop *CurLoop, BasicBlock *PreCondBB,
                                Instruction *&CntInst, PHINode *&CntPhi,
                                Value *&Var) {
  // step 1: Check to see if the look-back branch match this pattern:
  //    "if (a!=0) goto loop-entry".
  BasicBlock *LoopEntry;
  Instruction *DefX2, *CountInst;
  Value *VarX1, *VarX0;
  PHINode *PhiX, *CountPhi;

  DefX2 = CountInst = nullptr;
  VarX1 = VarX0 = nullptr;
  PhiX = CountPhi = nullptr;
  LoopEntry = *(CurLoop->block_begin());

  // step 1: Check if the loop-back branch is in desirable form.
  {
    if (Value *T = matchCondition(
            dyn_cast<BranchInst>(LoopEntry->getTerminator()), LoopEntry))
      DefX2 = dyn_cast<Instruction>(T);
    else
      return false;
  }

  // step 2: detect instructions corresponding to "x2 = x1 & (x1 - 1)"
  {
    if (!DefX2 || DefX2->getOpcode() != Instruction::And)
      return false;

    BinaryOperator *SubOneOp;

    if ((SubOneOp = dyn_cast<BinaryOperator>(DefX2->getOperand(0))))
      VarX1 = DefX2->getOperand(1);
    else {
      VarX1 = DefX2->getOperand(0);
      SubOneOp = dyn_cast<BinaryOperator>(DefX2->getOperand(1));
    }
    if (!SubOneOp || SubOneOp->getOperand(0) != VarX1)
      return false;

    ConstantInt *Dec = dyn_cast<ConstantInt>(SubOneOp->getOperand(1));
    if (!Dec ||
        !((SubOneOp->getOpcode() == Instruction::Sub && Dec->isOne()) ||
          (SubOneOp->getOpcode() == Instruction::Add &&
           Dec->isMinusOne()))) {
      return false;
    }
  }

  // step 3: Check the recurrence of variable X
  PhiX = getRecurrenceVar(VarX1, DefX2, LoopEntry);
  if (!PhiX)
    return false;

  // step 4: Find the instruction which count the population: cnt2 = cnt1 + 1
  {
    CountInst = nullptr;
    for (BasicBlock::iterator Iter = LoopEntry->getFirstNonPHI()->getIterator(),
                              IterE = LoopEntry->end();
         Iter != IterE; Iter++) {
      Instruction *Inst = &*Iter;
      if (Inst->getOpcode() != Instruction::Add)
        continue;

      ConstantInt *Inc = dyn_cast<ConstantInt>(Inst->getOperand(1));
      if (!Inc || !Inc->isOne())
        continue;

      PHINode *Phi = getRecurrenceVar(Inst->getOperand(0), Inst, LoopEntry);
      if (!Phi)
        continue;

      // Check if the result of the instruction is live of the loop.
      bool LiveOutLoop = false;
      for (User *U : Inst->users()) {
        if ((cast<Instruction>(U))->getParent() != LoopEntry) {
          LiveOutLoop = true;
          break;
        }
      }

      if (LiveOutLoop) {
        CountInst = Inst;
        CountPhi = Phi;
        break;
      }
    }

    if (!CountInst)
      return false;
  }

  // step 5: check if the precondition is in this form:
  //   "if (x != 0) goto loop-head ; else goto somewhere-we-don't-care;"
  {
    auto *PreCondBr = dyn_cast<BranchInst>(PreCondBB->getTerminator());
    Value *T = matchCondition(PreCondBr, CurLoop->getLoopPreheader());
    if (T != PhiX->getOperand(0) && T != PhiX->getOperand(1))
      return false;

    CntInst = CountInst;
    CntPhi = CountPhi;
    Var = T;
  }

  return true;
}

/// Return true if the idiom is detected in the loop.
///
/// Additionally:
/// 1) \p CntInst is set to the instruction Counting Leading Zeros (CTLZ)
///       or nullptr if there is no such.
/// 2) \p CntPhi is set to the corresponding phi node
///       or nullptr if there is no such.
/// 3) \p Var is set to the value whose CTLZ could be used.
/// 4) \p DefX is set to the instruction calculating Loop exit condition.
///
/// The core idiom we are trying to detect is:
/// \code
///    if (x0 == 0)
///      goto loop-exit // the precondition of the loop
///    cnt0 = init-val;
///    do {
///       x = phi (x0, x.next);   //PhiX
///       cnt = phi(cnt0, cnt.next);
///
///       cnt.next = cnt + 1;
///        ...
///       x.next = x >> 1;   // DefX
///        ...
///    } while(x.next != 0);
///
/// loop-exit:
/// \endcode
static bool detectShiftUntilZeroIdiom(Loop *CurLoop, const DataLayout &DL,
                                      Intrinsic::ID &IntrinID, Value *&InitX,
                                      Instruction *&CntInst, PHINode *&CntPhi,
                                      Instruction *&DefX) {
  BasicBlock *LoopEntry;
  Value *VarX = nullptr;

  DefX = nullptr;
  CntInst = nullptr;
  CntPhi = nullptr;
  LoopEntry = *(CurLoop->block_begin());

  // step 1: Check if the loop-back branch is in desirable form.
  if (Value *T = matchCondition(
          dyn_cast<BranchInst>(LoopEntry->getTerminator()), LoopEntry))
    DefX = dyn_cast<Instruction>(T);
  else
    return false;

  // step 2: detect instructions corresponding to "x.next = x >> 1 or x << 1"
  if (!DefX || !DefX->isShift())
    return false;
  IntrinID = DefX->getOpcode() == Instruction::Shl ? Intrinsic::cttz :
                                                     Intrinsic::ctlz;
  ConstantInt *Shft = dyn_cast<ConstantInt>(DefX->getOperand(1));
  if (!Shft || !Shft->isOne())
    return false;
  VarX = DefX->getOperand(0);

  // step 3: Check the recurrence of variable X
  PHINode *PhiX = getRecurrenceVar(VarX, DefX, LoopEntry);
  if (!PhiX)
    return false;

  InitX = PhiX->getIncomingValueForBlock(CurLoop->getLoopPreheader());

  // Make sure the initial value can't be negative otherwise the ashr in the
  // loop might never reach zero which would make the loop infinite.
  if (DefX->getOpcode() == Instruction::AShr && !isKnownNonNegative(InitX, DL))
    return false;

  // step 4: Find the instruction which count the CTLZ: cnt.next = cnt + 1
  //         or cnt.next = cnt + -1.
  // TODO: We can skip the step. If loop trip count is known (CTLZ),
  //       then all uses of "cnt.next" could be optimized to the trip count
  //       plus "cnt0". Currently it is not optimized.
  //       This step could be used to detect POPCNT instruction:
  //       cnt.next = cnt + (x.next & 1)
  for (BasicBlock::iterator Iter = LoopEntry->getFirstNonPHI()->getIterator(),
                            IterE = LoopEntry->end();
       Iter != IterE; Iter++) {
    Instruction *Inst = &*Iter;
    if (Inst->getOpcode() != Instruction::Add)
      continue;

    ConstantInt *Inc = dyn_cast<ConstantInt>(Inst->getOperand(1));
    if (!Inc || (!Inc->isOne() && !Inc->isMinusOne()))
      continue;

    PHINode *Phi = getRecurrenceVar(Inst->getOperand(0), Inst, LoopEntry);
    if (!Phi)
      continue;

    CntInst = Inst;
    CntPhi = Phi;
    break;
  }
  if (!CntInst)
    return false;

  return true;
}

/// Recognize CTLZ or CTTZ idiom in a non-countable loop and convert the loop
/// to countable (with CTLZ / CTTZ trip count). If CTLZ / CTTZ inserted as a new
/// trip count returns true; otherwise, returns false.
bool LoopIdiomRecognize::recognizeAndInsertFFS() {
  // Give up if the loop has multiple blocks or multiple backedges.
  if (CurLoop->getNumBackEdges() != 1 || CurLoop->getNumBlocks() != 1)
    return false;

  Intrinsic::ID IntrinID;
  Value *InitX;
  Instruction *DefX = nullptr;
  PHINode *CntPhi = nullptr;
  Instruction *CntInst = nullptr;
  // Help decide if transformation is profitable. For ShiftUntilZero idiom,
  // this is always 6.
  size_t IdiomCanonicalSize = 6;

  if (!detectShiftUntilZeroIdiom(CurLoop, *DL, IntrinID, InitX,
                                 CntInst, CntPhi, DefX))
    return false;

  bool IsCntPhiUsedOutsideLoop = false;
  for (User *U : CntPhi->users())
    if (!CurLoop->contains(cast<Instruction>(U))) {
      IsCntPhiUsedOutsideLoop = true;
      break;
    }
  bool IsCntInstUsedOutsideLoop = false;
  for (User *U : CntInst->users())
    if (!CurLoop->contains(cast<Instruction>(U))) {
      IsCntInstUsedOutsideLoop = true;
      break;
    }
  // If both CntInst and CntPhi are used outside the loop the profitability
  // is questionable.
  if (IsCntInstUsedOutsideLoop && IsCntPhiUsedOutsideLoop)
    return false;

  // For some CPUs result of CTLZ(X) intrinsic is undefined
  // when X is 0. If we can not guarantee X != 0, we need to check this
  // when expand.
  bool ZeroCheck = false;
  // It is safe to assume Preheader exist as it was checked in
  // parent function RunOnLoop.
  BasicBlock *PH = CurLoop->getLoopPreheader();

  // If we are using the count instruction outside the loop, make sure we
  // have a zero check as a precondition. Without the check the loop would run
  // one iteration for before any check of the input value. This means 0 and 1
  // would have identical behavior in the original loop and thus
  if (!IsCntPhiUsedOutsideLoop) {
    auto *PreCondBB = PH->getSinglePredecessor();
    if (!PreCondBB)
      return false;
    auto *PreCondBI = dyn_cast<BranchInst>(PreCondBB->getTerminator());
    if (!PreCondBI)
      return false;
    if (matchCondition(PreCondBI, PH) != InitX)
      return false;
    ZeroCheck = true;
  }

  // Check if CTLZ / CTTZ intrinsic is profitable. Assume it is always
  // profitable if we delete the loop.

  // the loop has only 6 instructions:
  //  %n.addr.0 = phi [ %n, %entry ], [ %shr, %while.cond ]
  //  %i.0 = phi [ %i0, %entry ], [ %inc, %while.cond ]
  //  %shr = ashr %n.addr.0, 1
  //  %tobool = icmp eq %shr, 0
  //  %inc = add nsw %i.0, 1
  //  br i1 %tobool

  const Value *Args[] = {
      InitX, ZeroCheck ? ConstantInt::getTrue(InitX->getContext())
                       : ConstantInt::getFalse(InitX->getContext())};

  // @llvm.dbg doesn't count as they have no semantic effect.
  auto InstWithoutDebugIt = CurLoop->getHeader()->instructionsWithoutDebug();
  uint32_t HeaderSize =
      std::distance(InstWithoutDebugIt.begin(), InstWithoutDebugIt.end());

  IntrinsicCostAttributes Attrs(IntrinID, InitX->getType(), Args);
  int Cost =
    TTI->getIntrinsicInstrCost(Attrs, TargetTransformInfo::TCK_SizeAndLatency);
  if (HeaderSize != IdiomCanonicalSize &&
      Cost > TargetTransformInfo::TCC_Basic)
    return false;

  transformLoopToCountable(IntrinID, PH, CntInst, CntPhi, InitX, DefX,
                           DefX->getDebugLoc(), ZeroCheck,
                           IsCntPhiUsedOutsideLoop);
  return true;
}

/// Recognizes a population count idiom in a non-countable loop.
///
/// If detected, transforms the relevant code to issue the popcount intrinsic
/// function call, and returns true; otherwise, returns false.
bool LoopIdiomRecognize::recognizePopcount() {
  if (TTI->getPopcntSupport(32) != TargetTransformInfo::PSK_FastHardware)
    return false;

  // Counting population are usually conducted by few arithmetic instructions.
  // Such instructions can be easily "absorbed" by vacant slots in a
  // non-compact loop. Therefore, recognizing popcount idiom only makes sense
  // in a compact loop.

  // Give up if the loop has multiple blocks or multiple backedges.
  if (CurLoop->getNumBackEdges() != 1 || CurLoop->getNumBlocks() != 1)
    return false;

  BasicBlock *LoopBody = *(CurLoop->block_begin());
  if (LoopBody->size() >= 20) {
    // The loop is too big, bail out.
    return false;
  }

  // It should have a preheader containing nothing but an unconditional branch.
  BasicBlock *PH = CurLoop->getLoopPreheader();
  if (!PH || &PH->front() != PH->getTerminator())
    return false;
  auto *EntryBI = dyn_cast<BranchInst>(PH->getTerminator());
  if (!EntryBI || EntryBI->isConditional())
    return false;

  // It should have a precondition block where the generated popcount intrinsic
  // function can be inserted.
  auto *PreCondBB = PH->getSinglePredecessor();
  if (!PreCondBB)
    return false;
  auto *PreCondBI = dyn_cast<BranchInst>(PreCondBB->getTerminator());
  if (!PreCondBI || PreCondBI->isUnconditional())
    return false;

  Instruction *CntInst;
  PHINode *CntPhi;
  Value *Val;
  if (!detectPopcountIdiom(CurLoop, PreCondBB, CntInst, CntPhi, Val))
    return false;

  transformLoopToPopcount(PreCondBB, CntInst, CntPhi, Val);
  return true;
}

static CallInst *createPopcntIntrinsic(IRBuilder<> &IRBuilder, Value *Val,
                                       const DebugLoc &DL) {
  Value *Ops[] = {Val};
  Type *Tys[] = {Val->getType()};

  Module *M = IRBuilder.GetInsertBlock()->getParent()->getParent();
  Function *Func = Intrinsic::getDeclaration(M, Intrinsic::ctpop, Tys);
  CallInst *CI = IRBuilder.CreateCall(Func, Ops);
  CI->setDebugLoc(DL);

  return CI;
}

static CallInst *createFFSIntrinsic(IRBuilder<> &IRBuilder, Value *Val,
                                    const DebugLoc &DL, bool ZeroCheck,
                                    Intrinsic::ID IID) {
  Value *Ops[] = {Val, ZeroCheck ? IRBuilder.getTrue() : IRBuilder.getFalse()};
  Type *Tys[] = {Val->getType()};

  Module *M = IRBuilder.GetInsertBlock()->getParent()->getParent();
  Function *Func = Intrinsic::getDeclaration(M, IID, Tys);
  CallInst *CI = IRBuilder.CreateCall(Func, Ops);
  CI->setDebugLoc(DL);

  return CI;
}

/// Transform the following loop (Using CTLZ, CTTZ is similar):
/// loop:
///   CntPhi = PHI [Cnt0, CntInst]
///   PhiX = PHI [InitX, DefX]
///   CntInst = CntPhi + 1
///   DefX = PhiX >> 1
///   LOOP_BODY
///   Br: loop if (DefX != 0)
/// Use(CntPhi) or Use(CntInst)
///
/// Into:
/// If CntPhi used outside the loop:
///   CountPrev = BitWidth(InitX) - CTLZ(InitX >> 1)
///   Count = CountPrev + 1
/// else
///   Count = BitWidth(InitX) - CTLZ(InitX)
/// loop:
///   CntPhi = PHI [Cnt0, CntInst]
///   PhiX = PHI [InitX, DefX]
///   PhiCount = PHI [Count, Dec]
///   CntInst = CntPhi + 1
///   DefX = PhiX >> 1
///   Dec = PhiCount - 1
///   LOOP_BODY
///   Br: loop if (Dec != 0)
/// Use(CountPrev + Cnt0) // Use(CntPhi)
/// or
/// Use(Count + Cnt0) // Use(CntInst)
///
/// If LOOP_BODY is empty the loop will be deleted.
/// If CntInst and DefX are not used in LOOP_BODY they will be removed.
void LoopIdiomRecognize::transformLoopToCountable(
    Intrinsic::ID IntrinID, BasicBlock *Preheader, Instruction *CntInst,
    PHINode *CntPhi, Value *InitX, Instruction *DefX, const DebugLoc &DL,
    bool ZeroCheck, bool IsCntPhiUsedOutsideLoop) {
  BranchInst *PreheaderBr = cast<BranchInst>(Preheader->getTerminator());

  // Step 1: Insert the CTLZ/CTTZ instruction at the end of the preheader block
  IRBuilder<> Builder(PreheaderBr);
  Builder.SetCurrentDebugLocation(DL);

  //   Count = BitWidth - CTLZ(InitX);
  //   NewCount = Count;
  // If there are uses of CntPhi create:
  //   NewCount = BitWidth - CTLZ(InitX >> 1);
  //   Count = NewCount + 1;
  Value *InitXNext;
  if (IsCntPhiUsedOutsideLoop) {
    if (DefX->getOpcode() == Instruction::AShr)
      InitXNext =
          Builder.CreateAShr(InitX, ConstantInt::get(InitX->getType(), 1));
    else if (DefX->getOpcode() == Instruction::LShr)
      InitXNext =
          Builder.CreateLShr(InitX, ConstantInt::get(InitX->getType(), 1));
    else if (DefX->getOpcode() == Instruction::Shl) // cttz
      InitXNext =
          Builder.CreateShl(InitX, ConstantInt::get(InitX->getType(), 1));
    else
      llvm_unreachable("Unexpected opcode!");
  } else
    InitXNext = InitX;
  Value *FFS = createFFSIntrinsic(Builder, InitXNext, DL, ZeroCheck, IntrinID);
  Value *Count = Builder.CreateSub(
      ConstantInt::get(FFS->getType(), FFS->getType()->getIntegerBitWidth()),
      FFS);
  Value *NewCount = Count;
  if (IsCntPhiUsedOutsideLoop) {
    NewCount = Count;
    Count = Builder.CreateAdd(Count, ConstantInt::get(Count->getType(), 1));
  }

  NewCount = Builder.CreateZExtOrTrunc(NewCount,
                                       cast<IntegerType>(CntInst->getType()));

  Value *CntInitVal = CntPhi->getIncomingValueForBlock(Preheader);
  if (cast<ConstantInt>(CntInst->getOperand(1))->isOne()) {
    // If the counter was being incremented in the loop, add NewCount to the
    // counter's initial value, but only if the initial value is not zero.
    ConstantInt *InitConst = dyn_cast<ConstantInt>(CntInitVal);
    if (!InitConst || !InitConst->isZero())
      NewCount = Builder.CreateAdd(NewCount, CntInitVal);
  } else {
    // If the count was being decremented in the loop, subtract NewCount from
    // the counter's initial value.
    NewCount = Builder.CreateSub(CntInitVal, NewCount);
  }

  // Step 2: Insert new IV and loop condition:
  // loop:
  //   ...
  //   PhiCount = PHI [Count, Dec]
  //   ...
  //   Dec = PhiCount - 1
  //   ...
  //   Br: loop if (Dec != 0)
  BasicBlock *Body = *(CurLoop->block_begin());
  auto *LbBr = cast<BranchInst>(Body->getTerminator());
  ICmpInst *LbCond = cast<ICmpInst>(LbBr->getCondition());
  Type *Ty = Count->getType();

  PHINode *TcPhi = PHINode::Create(Ty, 2, "tcphi", &Body->front());

  Builder.SetInsertPoint(LbCond);
  Instruction *TcDec = cast<Instruction>(
      Builder.CreateSub(TcPhi, ConstantInt::get(Ty, 1),
                        "tcdec", false, true));

  TcPhi->addIncoming(Count, Preheader);
  TcPhi->addIncoming(TcDec, Body);

  CmpInst::Predicate Pred =
      (LbBr->getSuccessor(0) == Body) ? CmpInst::ICMP_NE : CmpInst::ICMP_EQ;
  LbCond->setPredicate(Pred);
  LbCond->setOperand(0, TcDec);
  LbCond->setOperand(1, ConstantInt::get(Ty, 0));

  // Step 3: All the references to the original counter outside
  //  the loop are replaced with the NewCount
  if (IsCntPhiUsedOutsideLoop)
    CntPhi->replaceUsesOutsideBlock(NewCount, Body);
  else
    CntInst->replaceUsesOutsideBlock(NewCount, Body);

  // step 4: Forget the "non-computable" trip-count SCEV associated with the
  //   loop. The loop would otherwise not be deleted even if it becomes empty.
  SE->forgetLoop(CurLoop);
}

void LoopIdiomRecognize::transformLoopToPopcount(BasicBlock *PreCondBB,
                                                 Instruction *CntInst,
                                                 PHINode *CntPhi, Value *Var) {
  BasicBlock *PreHead = CurLoop->getLoopPreheader();
  auto *PreCondBr = cast<BranchInst>(PreCondBB->getTerminator());
  const DebugLoc &DL = CntInst->getDebugLoc();

  // Assuming before transformation, the loop is following:
  //  if (x) // the precondition
  //     do { cnt++; x &= x - 1; } while(x);

  // Step 1: Insert the ctpop instruction at the end of the precondition block
  IRBuilder<> Builder(PreCondBr);
  Value *PopCnt, *PopCntZext, *NewCount, *TripCnt;
  {
    PopCnt = createPopcntIntrinsic(Builder, Var, DL);
    NewCount = PopCntZext =
        Builder.CreateZExtOrTrunc(PopCnt, cast<IntegerType>(CntPhi->getType()));

    if (NewCount != PopCnt)
      (cast<Instruction>(NewCount))->setDebugLoc(DL);

    // TripCnt is exactly the number of iterations the loop has
    TripCnt = NewCount;

    // If the population counter's initial value is not zero, insert Add Inst.
    Value *CntInitVal = CntPhi->getIncomingValueForBlock(PreHead);
    ConstantInt *InitConst = dyn_cast<ConstantInt>(CntInitVal);
    if (!InitConst || !InitConst->isZero()) {
      NewCount = Builder.CreateAdd(NewCount, CntInitVal);
      (cast<Instruction>(NewCount))->setDebugLoc(DL);
    }
  }

  // Step 2: Replace the precondition from "if (x == 0) goto loop-exit" to
  //   "if (NewCount == 0) loop-exit". Without this change, the intrinsic
  //   function would be partial dead code, and downstream passes will drag
  //   it back from the precondition block to the preheader.
  {
    ICmpInst *PreCond = cast<ICmpInst>(PreCondBr->getCondition());

    Value *Opnd0 = PopCntZext;
    Value *Opnd1 = ConstantInt::get(PopCntZext->getType(), 0);
    if (PreCond->getOperand(0) != Var)
      std::swap(Opnd0, Opnd1);

    ICmpInst *NewPreCond = cast<ICmpInst>(
        Builder.CreateICmp(PreCond->getPredicate(), Opnd0, Opnd1));
    PreCondBr->setCondition(NewPreCond);

    RecursivelyDeleteTriviallyDeadInstructions(PreCond, TLI);
  }

  // Step 3: Note that the population count is exactly the trip count of the
  // loop in question, which enable us to convert the loop from noncountable
  // loop into a countable one. The benefit is twofold:
  //
  //  - If the loop only counts population, the entire loop becomes dead after
  //    the transformation. It is a lot easier to prove a countable loop dead
  //    than to prove a noncountable one. (In some C dialects, an infinite loop
  //    isn't dead even if it computes nothing useful. In general, DCE needs
  //    to prove a noncountable loop finite before safely delete it.)
  //
  //  - If the loop also performs something else, it remains alive.
  //    Since it is transformed to countable form, it can be aggressively
  //    optimized by some optimizations which are in general not applicable
  //    to a noncountable loop.
  //
  // After this step, this loop (conceptually) would look like following:
  //   newcnt = __builtin_ctpop(x);
  //   t = newcnt;
  //   if (x)
  //     do { cnt++; x &= x-1; t--) } while (t > 0);
  BasicBlock *Body = *(CurLoop->block_begin());
  {
    auto *LbBr = cast<BranchInst>(Body->getTerminator());
    ICmpInst *LbCond = cast<ICmpInst>(LbBr->getCondition());
    Type *Ty = TripCnt->getType();

    PHINode *TcPhi = PHINode::Create(Ty, 2, "tcphi", &Body->front());

    Builder.SetInsertPoint(LbCond);
    Instruction *TcDec = cast<Instruction>(
        Builder.CreateSub(TcPhi, ConstantInt::get(Ty, 1),
                          "tcdec", false, true));

    TcPhi->addIncoming(TripCnt, PreHead);
    TcPhi->addIncoming(TcDec, Body);

    CmpInst::Predicate Pred =
        (LbBr->getSuccessor(0) == Body) ? CmpInst::ICMP_UGT : CmpInst::ICMP_SLE;
    LbCond->setPredicate(Pred);
    LbCond->setOperand(0, TcDec);
    LbCond->setOperand(1, ConstantInt::get(Ty, 0));
  }

  // Step 4: All the references to the original population counter outside
  //  the loop are replaced with the NewCount -- the value returned from
  //  __builtin_ctpop().
  CntInst->replaceUsesOutsideBlock(NewCount, Body);

  // step 5: Forget the "non-computable" trip-count SCEV associated with the
  //   loop. The loop would otherwise not be deleted even if it becomes empty.
  SE->forgetLoop(CurLoop);
}

/// Match loop-invariant value.
template <typename SubPattern_t> struct match_LoopInvariant {
  SubPattern_t SubPattern;
  const Loop *L;

  match_LoopInvariant(const SubPattern_t &SP, const Loop *L)
      : SubPattern(SP), L(L) {}

  template <typename ITy> bool match(ITy *V) {
    return L->isLoopInvariant(V) && SubPattern.match(V);
  }
};

/// Matches if the value is loop-invariant.
template <typename Ty>
inline match_LoopInvariant<Ty> m_LoopInvariant(const Ty &M, const Loop *L) {
  return match_LoopInvariant<Ty>(M, L);
}

/// Return true if the idiom is detected in the loop.
///
/// The core idiom we are trying to detect is:
/// \code
///   entry:
///     <...>
///     %bitmask = shl i32 1, %bitpos
///     br label %loop
///
///   loop:
///     %x.curr = phi i32 [ %x, %entry ], [ %x.next, %loop ]
///     %x.curr.bitmasked = and i32 %x.curr, %bitmask
///     %x.curr.isbitunset = icmp eq i32 %x.curr.bitmasked, 0
///     %x.next = shl i32 %x.curr, 1
///     <...>
///     br i1 %x.curr.isbitunset, label %loop, label %end
///
///   end:
///     %x.curr.res = phi i32 [ %x.curr, %loop ] <...>
///     %x.next.res = phi i32 [ %x.next, %loop ] <...>
///     <...>
/// \endcode
static bool detectShiftUntilBitTestIdiom(Loop *CurLoop, Value *&BaseX,
                                         Value *&BitMask, Value *&BitPos,
                                         Value *&CurrX, Instruction *&NextX) {
  LLVM_DEBUG(dbgs() << DEBUG_TYPE
             " Performing shift-until-bittest idiom detection.\n");

  // Give up if the loop has multiple blocks or multiple backedges.
  if (CurLoop->getNumBlocks() != 1 || CurLoop->getNumBackEdges() != 1) {
    LLVM_DEBUG(dbgs() << DEBUG_TYPE " Bad block/backedge count.\n");
    return false;
  }

  BasicBlock *LoopHeaderBB = CurLoop->getHeader();
  BasicBlock *LoopPreheaderBB = CurLoop->getLoopPreheader();
  assert(LoopPreheaderBB && "There is always a loop preheader.");

  using namespace PatternMatch;

  // Step 1: Check if the loop backedge is in desirable form.

  ICmpInst::Predicate Pred;
  Value *CmpLHS, *CmpRHS;
  BasicBlock *TrueBB, *FalseBB;
  if (!match(LoopHeaderBB->getTerminator(),
             m_Br(m_ICmp(Pred, m_Value(CmpLHS), m_Value(CmpRHS)),
                  m_BasicBlock(TrueBB), m_BasicBlock(FalseBB)))) {
    LLVM_DEBUG(dbgs() << DEBUG_TYPE " Bad backedge structure.\n");
    return false;
  }

  // Step 2: Check if the backedge's condition is in desirable form.

  auto MatchVariableBitMask = [&]() {
    return ICmpInst::isEquality(Pred) && match(CmpRHS, m_Zero()) &&
           match(CmpLHS,
                 m_c_And(m_Value(CurrX),
                         m_CombineAnd(
                             m_Value(BitMask),
                             m_LoopInvariant(m_Shl(m_One(), m_Value(BitPos)),
                                             CurLoop))));
  };
  auto MatchConstantBitMask = [&]() {
    return ICmpInst::isEquality(Pred) && match(CmpRHS, m_Zero()) &&
           match(CmpLHS, m_And(m_Value(CurrX),
                               m_CombineAnd(m_Value(BitMask), m_Power2()))) &&
           (BitPos = ConstantExpr::getExactLogBase2(cast<Constant>(BitMask)));
  };
  auto MatchDecomposableConstantBitMask = [&]() {
    APInt Mask;
    return llvm::decomposeBitTestICmp(CmpLHS, CmpRHS, Pred, CurrX, Mask) &&
           ICmpInst::isEquality(Pred) && Mask.isPowerOf2() &&
           (BitMask = ConstantInt::get(CurrX->getType(), Mask)) &&
           (BitPos = ConstantInt::get(CurrX->getType(), Mask.logBase2()));
  };

  if (!MatchVariableBitMask() && !MatchConstantBitMask() &&
      !MatchDecomposableConstantBitMask()) {
    LLVM_DEBUG(dbgs() << DEBUG_TYPE " Bad backedge comparison.\n");
    return false;
  }

  // Step 3: Check if the recurrence is in desirable form.
  auto *CurrXPN = dyn_cast<PHINode>(CurrX);
  if (!CurrXPN || CurrXPN->getParent() != LoopHeaderBB) {
    LLVM_DEBUG(dbgs() << DEBUG_TYPE " Not an expected PHI node.\n");
    return false;
  }

  BaseX = CurrXPN->getIncomingValueForBlock(LoopPreheaderBB);
  NextX =
      dyn_cast<Instruction>(CurrXPN->getIncomingValueForBlock(LoopHeaderBB));

  if (!NextX || !match(NextX, m_Shl(m_Specific(CurrX), m_One()))) {
    // FIXME: support right-shift?
    LLVM_DEBUG(dbgs() << DEBUG_TYPE " Bad recurrence.\n");
    return false;
  }

  // Step 4: Check if the backedge's destinations are in desirable form.

  assert(ICmpInst::isEquality(Pred) &&
         "Should only get equality predicates here.");

  // cmp-br is commutative, so canonicalize to a single variant.
  if (Pred != ICmpInst::Predicate::ICMP_EQ) {
    Pred = ICmpInst::getInversePredicate(Pred);
    std::swap(TrueBB, FalseBB);
  }

  // We expect to exit loop when comparison yields false,
  // so when it yields true we should branch back to loop header.
  if (TrueBB != LoopHeaderBB) {
    LLVM_DEBUG(dbgs() << DEBUG_TYPE " Bad backedge flow.\n");
    return false;
  }

  // Okay, idiom checks out.
  return true;
}

/// Look for the following loop:
/// \code
///   entry:
///     <...>
///     %bitmask = shl i32 1, %bitpos
///     br label %loop
///
///   loop:
///     %x.curr = phi i32 [ %x, %entry ], [ %x.next, %loop ]
///     %x.curr.bitmasked = and i32 %x.curr, %bitmask
///     %x.curr.isbitunset = icmp eq i32 %x.curr.bitmasked, 0
///     %x.next = shl i32 %x.curr, 1
///     <...>
///     br i1 %x.curr.isbitunset, label %loop, label %end
///
///   end:
///     %x.curr.res = phi i32 [ %x.curr, %loop ] <...>
///     %x.next.res = phi i32 [ %x.next, %loop ] <...>
///     <...>
/// \endcode
///
/// And transform it into:
/// \code
///   entry:
///     %bitmask = shl i32 1, %bitpos
///     %lowbitmask = add i32 %bitmask, -1
///     %mask = or i32 %lowbitmask, %bitmask
///     %x.masked = and i32 %x, %mask
///     %x.masked.numleadingzeros = call i32 @llvm.ctlz.i32(i32 %x.masked,
///                                                         i1 true)
///     %x.masked.numactivebits = sub i32 32, %x.masked.numleadingzeros
///     %x.masked.leadingonepos = add i32 %x.masked.numactivebits, -1
///     %backedgetakencount = sub i32 %bitpos, %x.masked.leadingonepos
///     %tripcount = add i32 %backedgetakencount, 1
///     %x.curr = shl i32 %x, %backedgetakencount
///     %x.next = shl i32 %x, %tripcount
///     br label %loop
///
///   loop:
///     %loop.iv = phi i32 [ 0, %entry ], [ %loop.iv.next, %loop ]
///     %loop.iv.next = add nuw i32 %loop.iv, 1
///     %loop.ivcheck = icmp eq i32 %loop.iv.next, %tripcount
///     <...>
///     br i1 %loop.ivcheck, label %end, label %loop
///
///   end:
///     %x.curr.res = phi i32 [ %x.curr, %loop ] <...>
///     %x.next.res = phi i32 [ %x.next, %loop ] <...>
///     <...>
/// \endcode
bool LoopIdiomRecognize::recognizeShiftUntilBitTest() {
  bool MadeChange = false;

  Value *X, *BitMask, *BitPos, *XCurr;
  Instruction *XNext;
  if (!detectShiftUntilBitTestIdiom(CurLoop, X, BitMask, BitPos, XCurr,
                                    XNext)) {
    LLVM_DEBUG(dbgs() << DEBUG_TYPE
               " shift-until-bittest idiom detection failed.\n");
    return MadeChange;
  }
  LLVM_DEBUG(dbgs() << DEBUG_TYPE " shift-until-bittest idiom detected!\n");

  // Ok, it is the idiom we were looking for, we *could* transform this loop,
  // but is it profitable to transform?

  BasicBlock *LoopHeaderBB = CurLoop->getHeader();
  BasicBlock *LoopPreheaderBB = CurLoop->getLoopPreheader();
  assert(LoopPreheaderBB && "There is always a loop preheader.");

  BasicBlock *SuccessorBB = CurLoop->getExitBlock();
  assert(LoopPreheaderBB && "There is only a single successor.");

  IRBuilder<> Builder(LoopPreheaderBB->getTerminator());
  Builder.SetCurrentDebugLocation(cast<Instruction>(XCurr)->getDebugLoc());

  Intrinsic::ID IntrID = Intrinsic::ctlz;
  Type *Ty = X->getType();

  TargetTransformInfo::TargetCostKind CostKind =
      TargetTransformInfo::TCK_SizeAndLatency;

  // The rewrite is considered to be unprofitable iff and only iff the
  // intrinsic/shift we'll use are not cheap. Note that we are okay with *just*
  // making the loop countable, even if nothing else changes.
  IntrinsicCostAttributes Attrs(
      IntrID, Ty, {UndefValue::get(Ty), /*is_zero_undef=*/Builder.getTrue()});
  int Cost = TTI->getIntrinsicInstrCost(Attrs, CostKind);
  if (Cost > TargetTransformInfo::TCC_Basic) {
    LLVM_DEBUG(dbgs() << DEBUG_TYPE
               " Intrinsic is too costly, not beneficial\n");
    return MadeChange;
  }
  if (TTI->getArithmeticInstrCost(Instruction::Shl, Ty, CostKind) >
      TargetTransformInfo::TCC_Basic) {
    LLVM_DEBUG(dbgs() << DEBUG_TYPE " Shift is too costly, not beneficial\n");
    return MadeChange;
  }

  // Ok, transform appears worthwhile.
  MadeChange = true;

  // Step 1: Compute the loop trip count.

  Value *LowBitMask = Builder.CreateAdd(BitMask, Constant::getAllOnesValue(Ty),
                                        BitPos->getName() + ".lowbitmask");
  Value *Mask =
      Builder.CreateOr(LowBitMask, BitMask, BitPos->getName() + ".mask");
  Value *XMasked = Builder.CreateAnd(X, Mask, X->getName() + ".masked");
  CallInst *XMaskedNumLeadingZeros = Builder.CreateIntrinsic(
      IntrID, Ty, {XMasked, /*is_zero_undef=*/Builder.getTrue()},
      /*FMFSource=*/nullptr, XMasked->getName() + ".numleadingzeros");
  Value *XMaskedNumActiveBits = Builder.CreateSub(
      ConstantInt::get(Ty, Ty->getScalarSizeInBits()), XMaskedNumLeadingZeros,
      XMasked->getName() + ".numactivebits");
  Value *XMaskedLeadingOnePos =
      Builder.CreateAdd(XMaskedNumActiveBits, Constant::getAllOnesValue(Ty),
                        XMasked->getName() + ".leadingonepos");

  Value *LoopBackedgeTakenCount = Builder.CreateSub(
      BitPos, XMaskedLeadingOnePos, CurLoop->getName() + ".backedgetakencount");
  // We know loop's backedge-taken count, but what's loop's trip count?
  // Note that while NUW is always safe, while NSW is only for bitwidths != 2.
  Value *LoopTripCount =
      Builder.CreateNUWAdd(LoopBackedgeTakenCount, ConstantInt::get(Ty, 1),
                           CurLoop->getName() + ".tripcount");

  // Step 2: Compute the recurrence's final value without a loop.

  // NewX is always safe to compute, because `LoopBackedgeTakenCount`
  // will always be smaller than `bitwidth(X)`, i.e. we never get poison.
  Value *NewX = Builder.CreateShl(X, LoopBackedgeTakenCount);
  NewX->takeName(XCurr);
  if (auto *I = dyn_cast<Instruction>(NewX))
    I->copyIRFlags(XNext, /*IncludeWrapFlags=*/true);

  Value *NewXNext;
  // Rewriting XNext is more complicated, however, because `X << LoopTripCount`
  // will be poison iff `LoopTripCount == bitwidth(X)` (which will happen
  // iff `BitPos` is `bitwidth(x) - 1` and `X` is `1`). So unless we know
  // that isn't the case, we'll need to emit an alternative, safe IR.
  if (XNext->hasNoSignedWrap() || XNext->hasNoUnsignedWrap() ||
      PatternMatch::match(
          BitPos, PatternMatch::m_SpecificInt_ICMP(
                      ICmpInst::ICMP_NE, APInt(Ty->getScalarSizeInBits(),
                                               Ty->getScalarSizeInBits() - 1))))
    NewXNext = Builder.CreateShl(X, LoopTripCount);
  else {
    // Otherwise, just additionally shift by one. It's the smallest solution,
    // alternatively, we could check that NewX is INT_MIN (or BitPos is )
    // and select 0 instead.
    NewXNext = Builder.CreateShl(NewX, ConstantInt::get(Ty, 1));
  }

  NewXNext->takeName(XNext);
  if (auto *I = dyn_cast<Instruction>(NewXNext))
    I->copyIRFlags(XNext, /*IncludeWrapFlags=*/true);

  // Step 3: Adjust the successor basic block to recieve the computed
  //         recurrence's final value instead of the recurrence itself.

  XCurr->replaceUsesOutsideBlock(NewX, LoopHeaderBB);
  XNext->replaceUsesOutsideBlock(NewXNext, LoopHeaderBB);

  // Step 4: Rewrite the loop into a countable form, with canonical IV.

  // The new canonical induction variable.
  Builder.SetInsertPoint(&LoopHeaderBB->front());
  auto *IV = Builder.CreatePHI(Ty, 2, CurLoop->getName() + ".iv");

  // The induction itself.
  // Note that while NUW is always safe, while NSW is only for bitwidths != 2.
  Builder.SetInsertPoint(LoopHeaderBB->getTerminator());
  auto *IVNext = Builder.CreateNUWAdd(IV, ConstantInt::get(Ty, 1),
                                      IV->getName() + ".next");

  // The loop trip count check.
  auto *IVCheck = Builder.CreateICmpEQ(IVNext, LoopTripCount,
                                       CurLoop->getName() + ".ivcheck");
  Builder.CreateCondBr(IVCheck, SuccessorBB, LoopHeaderBB);
  LoopHeaderBB->getTerminator()->eraseFromParent();

  // Populate the IV PHI.
  IV->addIncoming(ConstantInt::get(Ty, 0), LoopPreheaderBB);
  IV->addIncoming(IVNext, LoopHeaderBB);

  // Step 5: Forget the "non-computable" trip-count SCEV associated with the
  //   loop. The loop would otherwise not be deleted even if it becomes empty.

  SE->forgetLoop(CurLoop);

  // Other passes will take care of actually deleting the loop if possible.

  LLVM_DEBUG(dbgs() << DEBUG_TYPE " shift-until-bittest idiom optimized!\n");

  ++NumShiftUntilBitTest;
  return MadeChange;
}