llvm.org GIT mirror llvm / 210c690 lib / CodeGen / MachineBlockPlacement.cpp
210c690

Tree @210c690 (Download .tar.gz)

MachineBlockPlacement.cpp @210c690raw · history · 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
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
//===-- MachineBlockPlacement.cpp - Basic Block Code Layout optimization --===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file implements basic block placement transformations using the CFG
// structure and branch probability estimates.
//
// The pass strives to preserve the structure of the CFG (that is, retain
// a topological ordering of basic blocks) in the absence of a *strong* signal
// to the contrary from probabilities. However, within the CFG structure, it
// attempts to choose an ordering which favors placing more likely sequences of
// blocks adjacent to each other.
//
// The algorithm works from the inner-most loop within a function outward, and
// at each stage walks through the basic blocks, trying to coalesce them into
// sequential chains where allowed by the CFG (or demanded by heavy
// probabilities). Finally, it walks the blocks in topological order, and the
// first time it reaches a chain of basic blocks, it schedules them in the
// function in-order.
//
//===----------------------------------------------------------------------===//

#include "llvm/CodeGen/Passes.h"
#include "llvm/CodeGen/TargetPassConfig.h"
#include "BranchFolding.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/SmallPtrSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/Analysis/BlockFrequencyInfoImpl.h"
#include "llvm/CodeGen/MachineBasicBlock.h"
#include "llvm/CodeGen/MachineBlockFrequencyInfo.h"
#include "llvm/CodeGen/MachineBranchProbabilityInfo.h"
#include "llvm/CodeGen/MachineDominators.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineFunctionPass.h"
#include "llvm/CodeGen/MachineLoopInfo.h"
#include "llvm/CodeGen/MachineModuleInfo.h"
#include "llvm/CodeGen/MachinePostDominators.h"
#include "llvm/CodeGen/TailDuplicator.h"
#include "llvm/Support/Allocator.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetInstrInfo.h"
#include "llvm/Target/TargetLowering.h"
#include "llvm/Target/TargetSubtargetInfo.h"
#include <algorithm>
#include <functional>
#include <utility>
using namespace llvm;

#define DEBUG_TYPE "block-placement"

STATISTIC(NumCondBranches, "Number of conditional branches");
STATISTIC(NumUncondBranches, "Number of unconditional branches");
STATISTIC(CondBranchTakenFreq,
          "Potential frequency of taking conditional branches");
STATISTIC(UncondBranchTakenFreq,
          "Potential frequency of taking unconditional branches");

static cl::opt<unsigned> AlignAllBlock("align-all-blocks",
                                       cl::desc("Force the alignment of all "
                                                "blocks in the function."),
                                       cl::init(0), cl::Hidden);

static cl::opt<unsigned> AlignAllNonFallThruBlocks(
    "align-all-nofallthru-blocks",
    cl::desc("Force the alignment of all "
             "blocks that have no fall-through predecessors (i.e. don't add "
             "nops that are executed)."),
    cl::init(0), cl::Hidden);

// FIXME: Find a good default for this flag and remove the flag.
static cl::opt<unsigned> ExitBlockBias(
    "block-placement-exit-block-bias",
    cl::desc("Block frequency percentage a loop exit block needs "
             "over the original exit to be considered the new exit."),
    cl::init(0), cl::Hidden);

// Definition:
// - Outlining: placement of a basic block outside the chain or hot path.

static cl::opt<bool> OutlineOptionalBranches(
    "outline-optional-branches",
    cl::desc("Outlining optional branches will place blocks that are optional "
              "branches, i.e. branches with a common post dominator, outside "
              "the hot path or chain"),
    cl::init(false), cl::Hidden);

static cl::opt<unsigned> OutlineOptionalThreshold(
    "outline-optional-threshold",
    cl::desc("Don't outline optional branches that are a single block with an "
             "instruction count below this threshold"),
    cl::init(4), cl::Hidden);

static cl::opt<unsigned> LoopToColdBlockRatio(
    "loop-to-cold-block-ratio",
    cl::desc("Outline loop blocks from loop chain if (frequency of loop) / "
             "(frequency of block) is greater than this ratio"),
    cl::init(5), cl::Hidden);

static cl::opt<bool>
    PreciseRotationCost("precise-rotation-cost",
                        cl::desc("Model the cost of loop rotation more "
                                 "precisely by using profile data."),
                        cl::init(false), cl::Hidden);
static cl::opt<bool>
    ForcePreciseRotationCost("force-precise-rotation-cost",
                             cl::desc("Force the use of precise cost "
                                      "loop rotation strategy."),
                             cl::init(false), cl::Hidden);

static cl::opt<unsigned> MisfetchCost(
    "misfetch-cost",
    cl::desc("Cost that models the probabilistic risk of an instruction "
             "misfetch due to a jump comparing to falling through, whose cost "
             "is zero."),
    cl::init(1), cl::Hidden);

static cl::opt<unsigned> JumpInstCost("jump-inst-cost",
                                      cl::desc("Cost of jump instructions."),
                                      cl::init(1), cl::Hidden);
static cl::opt<bool>
TailDupPlacement("tail-dup-placement",
              cl::desc("Perform tail duplication during placement. "
                       "Creates more fallthrough opportunites in "
                       "outline branches."),
              cl::init(true), cl::Hidden);

static cl::opt<bool>
BranchFoldPlacement("branch-fold-placement",
              cl::desc("Perform branch folding during placement. "
                       "Reduces code size."),
              cl::init(true), cl::Hidden);

// Heuristic for tail duplication.
static cl::opt<unsigned> TailDupPlacementThreshold(
    "tail-dup-placement-threshold",
    cl::desc("Instruction cutoff for tail duplication during layout. "
             "Tail merging during layout is forced to have a threshold "
             "that won't conflict."), cl::init(2),
    cl::Hidden);

// Heuristic for tail duplication.
static cl::opt<unsigned> TailDupPlacementPenalty(
    "tail-dup-placement-penalty",
    cl::desc("Cost penalty for blocks that can avoid breaking CFG by copying. "
             "Copying can increase fallthrough, but it also increases icache "
             "pressure. This parameter controls the penalty to account for that. "
             "Percent as integer."),
    cl::init(2),
    cl::Hidden);

extern cl::opt<unsigned> StaticLikelyProb;
extern cl::opt<unsigned> ProfileLikelyProb;

// Internal option used to control BFI display only after MBP pass.
// Defined in CodeGen/MachineBlockFrequencyInfo.cpp:
// -view-block-layout-with-bfi=
extern cl::opt<GVDAGType> ViewBlockLayoutWithBFI;

// Command line option to specify the name of the function for CFG dump
// Defined in Analysis/BlockFrequencyInfo.cpp:  -view-bfi-func-name=
extern cl::opt<std::string> ViewBlockFreqFuncName;

namespace {
class BlockChain;
/// \brief Type for our function-wide basic block -> block chain mapping.
typedef DenseMap<const MachineBasicBlock *, BlockChain *> BlockToChainMapType;
}

namespace {
/// \brief A chain of blocks which will be laid out contiguously.
///
/// This is the datastructure representing a chain of consecutive blocks that
/// are profitable to layout together in order to maximize fallthrough
/// probabilities and code locality. We also can use a block chain to represent
/// a sequence of basic blocks which have some external (correctness)
/// requirement for sequential layout.
///
/// Chains can be built around a single basic block and can be merged to grow
/// them. They participate in a block-to-chain mapping, which is updated
/// automatically as chains are merged together.
class BlockChain {
  /// \brief The sequence of blocks belonging to this chain.
  ///
  /// This is the sequence of blocks for a particular chain. These will be laid
  /// out in-order within the function.
  SmallVector<MachineBasicBlock *, 4> Blocks;

  /// \brief A handle to the function-wide basic block to block chain mapping.
  ///
  /// This is retained in each block chain to simplify the computation of child
  /// block chains for SCC-formation and iteration. We store the edges to child
  /// basic blocks, and map them back to their associated chains using this
  /// structure.
  BlockToChainMapType &BlockToChain;

public:
  /// \brief Construct a new BlockChain.
  ///
  /// This builds a new block chain representing a single basic block in the
  /// function. It also registers itself as the chain that block participates
  /// in with the BlockToChain mapping.
  BlockChain(BlockToChainMapType &BlockToChain, MachineBasicBlock *BB)
      : Blocks(1, BB), BlockToChain(BlockToChain), UnscheduledPredecessors(0) {
    assert(BB && "Cannot create a chain with a null basic block");
    BlockToChain[BB] = this;
  }

  /// \brief Iterator over blocks within the chain.
  typedef SmallVectorImpl<MachineBasicBlock *>::iterator iterator;
  typedef SmallVectorImpl<MachineBasicBlock *>::const_iterator const_iterator;

  /// \brief Beginning of blocks within the chain.
  iterator begin() { return Blocks.begin(); }
  const_iterator begin() const { return Blocks.begin(); }

  /// \brief End of blocks within the chain.
  iterator end() { return Blocks.end(); }
  const_iterator end() const { return Blocks.end(); }

  bool remove(MachineBasicBlock* BB) {
    for(iterator i = begin(); i != end(); ++i) {
      if (*i == BB) {
        Blocks.erase(i);
        return true;
      }
    }
    return false;
  }

  /// \brief Merge a block chain into this one.
  ///
  /// This routine merges a block chain into this one. It takes care of forming
  /// a contiguous sequence of basic blocks, updating the edge list, and
  /// updating the block -> chain mapping. It does not free or tear down the
  /// old chain, but the old chain's block list is no longer valid.
  void merge(MachineBasicBlock *BB, BlockChain *Chain) {
    assert(BB);
    assert(!Blocks.empty());

    // Fast path in case we don't have a chain already.
    if (!Chain) {
      assert(!BlockToChain[BB]);
      Blocks.push_back(BB);
      BlockToChain[BB] = this;
      return;
    }

    assert(BB == *Chain->begin());
    assert(Chain->begin() != Chain->end());

    // Update the incoming blocks to point to this chain, and add them to the
    // chain structure.
    for (MachineBasicBlock *ChainBB : *Chain) {
      Blocks.push_back(ChainBB);
      assert(BlockToChain[ChainBB] == Chain && "Incoming blocks not in chain");
      BlockToChain[ChainBB] = this;
    }
  }

#ifndef NDEBUG
  /// \brief Dump the blocks in this chain.
  LLVM_DUMP_METHOD void dump() {
    for (MachineBasicBlock *MBB : *this)
      MBB->dump();
  }
#endif // NDEBUG

  /// \brief Count of predecessors of any block within the chain which have not
  /// yet been scheduled.  In general, we will delay scheduling this chain
  /// until those predecessors are scheduled (or we find a sufficiently good
  /// reason to override this heuristic.)  Note that when forming loop chains,
  /// blocks outside the loop are ignored and treated as if they were already
  /// scheduled.
  ///
  /// Note: This field is reinitialized multiple times - once for each loop,
  /// and then once for the function as a whole.
  unsigned UnscheduledPredecessors;
};
}

namespace {
class MachineBlockPlacement : public MachineFunctionPass {
  /// \brief A typedef for a block filter set.
  typedef SmallSetVector<const MachineBasicBlock *, 16> BlockFilterSet;

  /// Pair struct containing basic block and taildup profitiability
  struct BlockAndTailDupResult {
    MachineBasicBlock * BB;
    bool ShouldTailDup;
  };

  /// \brief work lists of blocks that are ready to be laid out
  SmallVector<MachineBasicBlock *, 16> BlockWorkList;
  SmallVector<MachineBasicBlock *, 16> EHPadWorkList;

  /// \brief Machine Function
  MachineFunction *F;

  /// \brief A handle to the branch probability pass.
  const MachineBranchProbabilityInfo *MBPI;

  /// \brief A handle to the function-wide block frequency pass.
  std::unique_ptr<BranchFolder::MBFIWrapper> MBFI;

  /// \brief A handle to the loop info.
  MachineLoopInfo *MLI;

  /// \brief Preferred loop exit.
  /// Member variable for convenience. It may be removed by duplication deep
  /// in the call stack.
  MachineBasicBlock *PreferredLoopExit;

  /// \brief A handle to the target's instruction info.
  const TargetInstrInfo *TII;

  /// \brief A handle to the target's lowering info.
  const TargetLoweringBase *TLI;

  /// \brief A handle to the dominator tree.
  MachineDominatorTree *MDT;

  /// \brief A handle to the post dominator tree.
  MachinePostDominatorTree *MPDT;

  /// \brief Duplicator used to duplicate tails during placement.
  ///
  /// Placement decisions can open up new tail duplication opportunities, but
  /// since tail duplication affects placement decisions of later blocks, it
  /// must be done inline.
  TailDuplicator TailDup;

  /// \brief A set of blocks that are unavoidably execute, i.e. they dominate
  /// all terminators of the MachineFunction.
  SmallPtrSet<const MachineBasicBlock *, 4> UnavoidableBlocks;

  /// \brief Allocator and owner of BlockChain structures.
  ///
  /// We build BlockChains lazily while processing the loop structure of
  /// a function. To reduce malloc traffic, we allocate them using this
  /// slab-like allocator, and destroy them after the pass completes. An
  /// important guarantee is that this allocator produces stable pointers to
  /// the chains.
  SpecificBumpPtrAllocator<BlockChain> ChainAllocator;

  /// \brief Function wide BasicBlock to BlockChain mapping.
  ///
  /// This mapping allows efficiently moving from any given basic block to the
  /// BlockChain it participates in, if any. We use it to, among other things,
  /// allow implicitly defining edges between chains as the existing edges
  /// between basic blocks.
  DenseMap<const MachineBasicBlock *, BlockChain *> BlockToChain;

#ifndef NDEBUG
  /// The set of basic blocks that have terminators that cannot be fully
  /// analyzed.  These basic blocks cannot be re-ordered safely by
  /// MachineBlockPlacement, and we must preserve physical layout of these
  /// blocks and their successors through the pass.
  SmallPtrSet<MachineBasicBlock *, 4> BlocksWithUnanalyzableExits;
#endif

  /// Decrease the UnscheduledPredecessors count for all blocks in chain, and
  /// if the count goes to 0, add them to the appropriate work list.
  void markChainSuccessors(
      const BlockChain &Chain, const MachineBasicBlock *LoopHeaderBB,
      const BlockFilterSet *BlockFilter = nullptr);

  /// Decrease the UnscheduledPredecessors count for a single block, and
  /// if the count goes to 0, add them to the appropriate work list.
  void markBlockSuccessors(
      const BlockChain &Chain, const MachineBasicBlock *BB,
      const MachineBasicBlock *LoopHeaderBB,
      const BlockFilterSet *BlockFilter = nullptr);

  BranchProbability
  collectViableSuccessors(
      const MachineBasicBlock *BB, const BlockChain &Chain,
      const BlockFilterSet *BlockFilter,
      SmallVector<MachineBasicBlock *, 4> &Successors);
  bool shouldPredBlockBeOutlined(
      const MachineBasicBlock *BB, const MachineBasicBlock *Succ,
      const BlockChain &Chain, const BlockFilterSet *BlockFilter,
      BranchProbability SuccProb, BranchProbability HotProb);
  bool repeatedlyTailDuplicateBlock(
      MachineBasicBlock *BB, MachineBasicBlock *&LPred,
      const MachineBasicBlock *LoopHeaderBB,
      BlockChain &Chain, BlockFilterSet *BlockFilter,
      MachineFunction::iterator &PrevUnplacedBlockIt);
  bool maybeTailDuplicateBlock(
      MachineBasicBlock *BB, MachineBasicBlock *LPred,
      BlockChain &Chain, BlockFilterSet *BlockFilter,
      MachineFunction::iterator &PrevUnplacedBlockIt,
      bool &DuplicatedToPred);
  bool hasBetterLayoutPredecessor(
      const MachineBasicBlock *BB, const MachineBasicBlock *Succ,
      const BlockChain &SuccChain, BranchProbability SuccProb,
      BranchProbability RealSuccProb, const BlockChain &Chain,
      const BlockFilterSet *BlockFilter);
  BlockAndTailDupResult selectBestSuccessor(
      const MachineBasicBlock *BB, const BlockChain &Chain,
      const BlockFilterSet *BlockFilter);
  MachineBasicBlock *selectBestCandidateBlock(
      const BlockChain &Chain, SmallVectorImpl<MachineBasicBlock *> &WorkList);
  MachineBasicBlock *getFirstUnplacedBlock(
      const BlockChain &PlacedChain,
      MachineFunction::iterator &PrevUnplacedBlockIt,
      const BlockFilterSet *BlockFilter);

  /// \brief Add a basic block to the work list if it is appropriate.
  ///
  /// If the optional parameter BlockFilter is provided, only MBB
  /// present in the set will be added to the worklist. If nullptr
  /// is provided, no filtering occurs.
  void fillWorkLists(const MachineBasicBlock *MBB,
                     SmallPtrSetImpl<BlockChain *> &UpdatedPreds,
                     const BlockFilterSet *BlockFilter);
  void buildChain(const MachineBasicBlock *BB, BlockChain &Chain,
                  BlockFilterSet *BlockFilter = nullptr);
  MachineBasicBlock *findBestLoopTop(
      const MachineLoop &L, const BlockFilterSet &LoopBlockSet);
  MachineBasicBlock *findBestLoopExit(
      const MachineLoop &L, const BlockFilterSet &LoopBlockSet);
  BlockFilterSet collectLoopBlockSet(const MachineLoop &L);
  void buildLoopChains(const MachineLoop &L);
  void rotateLoop(
      BlockChain &LoopChain, const MachineBasicBlock *ExitingBB,
      const BlockFilterSet &LoopBlockSet);
  void rotateLoopWithProfile(
      BlockChain &LoopChain, const MachineLoop &L,
      const BlockFilterSet &LoopBlockSet);
  void collectMustExecuteBBs();
  void buildCFGChains();
  void optimizeBranches();
  void alignBlocks();
  bool shouldTailDuplicate(MachineBasicBlock *BB);
  /// Check the edge frequencies to see if tail duplication will increase
  /// fallthroughs.
  bool isProfitableToTailDup(
    const MachineBasicBlock *BB, const MachineBasicBlock *Succ,
    BranchProbability AdjustedSumProb,
    const BlockChain &Chain, const BlockFilterSet *BlockFilter);
  /// Returns true if a block can tail duplicate into all unplaced
  /// predecessors. Filters based on loop.
  bool canTailDuplicateUnplacedPreds(
      const MachineBasicBlock *BB, MachineBasicBlock *Succ,
      const BlockChain &Chain, const BlockFilterSet *BlockFilter);

public:
  static char ID; // Pass identification, replacement for typeid
  MachineBlockPlacement() : MachineFunctionPass(ID) {
    initializeMachineBlockPlacementPass(*PassRegistry::getPassRegistry());
  }

  bool runOnMachineFunction(MachineFunction &F) override;

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.addRequired<MachineBranchProbabilityInfo>();
    AU.addRequired<MachineBlockFrequencyInfo>();
    AU.addRequired<MachineDominatorTree>();
    if (TailDupPlacement)
      AU.addRequired<MachinePostDominatorTree>();
    AU.addRequired<MachineLoopInfo>();
    AU.addRequired<TargetPassConfig>();
    MachineFunctionPass::getAnalysisUsage(AU);
  }
};
}

char MachineBlockPlacement::ID = 0;
char &llvm::MachineBlockPlacementID = MachineBlockPlacement::ID;
INITIALIZE_PASS_BEGIN(MachineBlockPlacement, "block-placement",
                      "Branch Probability Basic Block Placement", false, false)
INITIALIZE_PASS_DEPENDENCY(MachineBranchProbabilityInfo)
INITIALIZE_PASS_DEPENDENCY(MachineBlockFrequencyInfo)
INITIALIZE_PASS_DEPENDENCY(MachineDominatorTree)
INITIALIZE_PASS_DEPENDENCY(MachinePostDominatorTree)
INITIALIZE_PASS_DEPENDENCY(MachineLoopInfo)
INITIALIZE_PASS_END(MachineBlockPlacement, "block-placement",
                    "Branch Probability Basic Block Placement", false, false)

#ifndef NDEBUG
/// \brief Helper to print the name of a MBB.
///
/// Only used by debug logging.
static std::string getBlockName(const MachineBasicBlock *BB) {
  std::string Result;
  raw_string_ostream OS(Result);
  OS << "BB#" << BB->getNumber();
  OS << " ('" << BB->getName() << "')";
  OS.flush();
  return Result;
}
#endif

/// \brief Mark a chain's successors as having one fewer preds.
///
/// When a chain is being merged into the "placed" chain, this routine will
/// quickly walk the successors of each block in the chain and mark them as
/// having one fewer active predecessor. It also adds any successors of this
/// chain which reach the zero-predecessor state to the appropriate worklist.
void MachineBlockPlacement::markChainSuccessors(
    const BlockChain &Chain, const MachineBasicBlock *LoopHeaderBB,
    const BlockFilterSet *BlockFilter) {
  // Walk all the blocks in this chain, marking their successors as having
  // a predecessor placed.
  for (MachineBasicBlock *MBB : Chain) {
    markBlockSuccessors(Chain, MBB, LoopHeaderBB, BlockFilter);
  }
}

/// \brief Mark a single block's successors as having one fewer preds.
///
/// Under normal circumstances, this is only called by markChainSuccessors,
/// but if a block that was to be placed is completely tail-duplicated away,
/// and was duplicated into the chain end, we need to redo markBlockSuccessors
/// for just that block.
void MachineBlockPlacement::markBlockSuccessors(
    const BlockChain &Chain, const MachineBasicBlock *MBB,
    const MachineBasicBlock *LoopHeaderBB, const BlockFilterSet *BlockFilter) {
  // Add any successors for which this is the only un-placed in-loop
  // predecessor to the worklist as a viable candidate for CFG-neutral
  // placement. No subsequent placement of this block will violate the CFG
  // shape, so we get to use heuristics to choose a favorable placement.
  for (MachineBasicBlock *Succ : MBB->successors()) {
    if (BlockFilter && !BlockFilter->count(Succ))
      continue;
    BlockChain &SuccChain = *BlockToChain[Succ];
    // Disregard edges within a fixed chain, or edges to the loop header.
    if (&Chain == &SuccChain || Succ == LoopHeaderBB)
      continue;

    // This is a cross-chain edge that is within the loop, so decrement the
    // loop predecessor count of the destination chain.
    if (SuccChain.UnscheduledPredecessors == 0 ||
        --SuccChain.UnscheduledPredecessors > 0)
      continue;

    auto *NewBB = *SuccChain.begin();
    if (NewBB->isEHPad())
      EHPadWorkList.push_back(NewBB);
    else
      BlockWorkList.push_back(NewBB);
  }
}

/// This helper function collects the set of successors of block
/// \p BB that are allowed to be its layout successors, and return
/// the total branch probability of edges from \p BB to those
/// blocks.
BranchProbability MachineBlockPlacement::collectViableSuccessors(
    const MachineBasicBlock *BB, const BlockChain &Chain,
    const BlockFilterSet *BlockFilter,
    SmallVector<MachineBasicBlock *, 4> &Successors) {
  // Adjust edge probabilities by excluding edges pointing to blocks that is
  // either not in BlockFilter or is already in the current chain. Consider the
  // following CFG:
  //
  //     --->A
  //     |  / \
  //     | B   C
  //     |  \ / \
  //     ----D   E
  //
  // Assume A->C is very hot (>90%), and C->D has a 50% probability, then after
  // A->C is chosen as a fall-through, D won't be selected as a successor of C
  // due to CFG constraint (the probability of C->D is not greater than
  // HotProb to break top-order). If we exclude E that is not in BlockFilter
  // when calculating the  probability of C->D, D will be selected and we
  // will get A C D B as the layout of this loop.
  auto AdjustedSumProb = BranchProbability::getOne();
  for (MachineBasicBlock *Succ : BB->successors()) {
    bool SkipSucc = false;
    if (Succ->isEHPad() || (BlockFilter && !BlockFilter->count(Succ))) {
      SkipSucc = true;
    } else {
      BlockChain *SuccChain = BlockToChain[Succ];
      if (SuccChain == &Chain) {
        SkipSucc = true;
      } else if (Succ != *SuccChain->begin()) {
        DEBUG(dbgs() << "    " << getBlockName(Succ) << " -> Mid chain!\n");
        continue;
      }
    }
    if (SkipSucc)
      AdjustedSumProb -= MBPI->getEdgeProbability(BB, Succ);
    else
      Successors.push_back(Succ);
  }

  return AdjustedSumProb;
}

/// The helper function returns the branch probability that is adjusted
/// or normalized over the new total \p AdjustedSumProb.
static BranchProbability
getAdjustedProbability(BranchProbability OrigProb,
                       BranchProbability AdjustedSumProb) {
  BranchProbability SuccProb;
  uint32_t SuccProbN = OrigProb.getNumerator();
  uint32_t SuccProbD = AdjustedSumProb.getNumerator();
  if (SuccProbN >= SuccProbD)
    SuccProb = BranchProbability::getOne();
  else
    SuccProb = BranchProbability(SuccProbN, SuccProbD);

  return SuccProb;
}

/// Check if a block should be tail duplicated.
/// \p BB Block to check.
bool MachineBlockPlacement::shouldTailDuplicate(MachineBasicBlock *BB) {
  // Blocks with single successors don't create additional fallthrough
  // opportunities. Don't duplicate them. TODO: When conditional exits are
  // analyzable, allow them to be duplicated.
  bool IsSimple = TailDup.isSimpleBB(BB);

  if (BB->succ_size() == 1)
    return false;
  return TailDup.shouldTailDuplicate(IsSimple, *BB);
}

/// Compare 2 BlockFrequency's with a small penalty for \p A.
/// In order to be conservative, we apply a X% penalty to account for
/// increased icache pressure and static heuristics. For small frequencies
/// we use only the numerators to improve accuracy. For simplicity, we assume the
/// penalty is less than 100%
/// TODO(iteratee): Use 64-bit fixed point edge frequencies everywhere.
static bool greaterWithBias(BlockFrequency A, BlockFrequency B,
                            uint64_t EntryFreq) {
  BranchProbability ThresholdProb(TailDupPlacementPenalty, 100);
  BlockFrequency Gain = A - B;
  return (Gain / ThresholdProb).getFrequency() >= EntryFreq;
}

/// Check the edge frequencies to see if tail duplication will increase
/// fallthroughs. It only makes sense to call this function when
/// \p Succ would not be chosen otherwise. Tail duplication of \p Succ is
/// always locally profitable if we would have picked \p Succ without
/// considering duplication.
bool MachineBlockPlacement::isProfitableToTailDup(
    const MachineBasicBlock *BB, const MachineBasicBlock *Succ,
    BranchProbability QProb,
    const BlockChain &Chain, const BlockFilterSet *BlockFilter) {
  // We need to do a probability calculation to make sure this is profitable.
  // First: does succ have a successor that post-dominates? This affects the
  // calculation. The 2 relevant cases are:
  //    BB         BB
  //    | \Qout    | \Qout
  //   P|  C       |P C
  //    =   C'     =   C'
  //    |  /Qin    |  /Qin
  //    | /        | /
  //    Succ       Succ
  //    / \        | \  V
  //  U/   =V      |U \
  //  /     \      =   D
  //  D      E     |  /
  //               | /
  //               |/
  //               PDom
  //  '=' : Branch taken for that CFG edge
  // In the second case, Placing Succ while duplicating it into C prevents the
  // fallthrough of Succ into either D or PDom, because they now have C as an
  // unplaced predecessor

  // Start by figuring out which case we fall into
  MachineBasicBlock *PDom = nullptr;
  SmallVector<MachineBasicBlock *, 4> SuccSuccs;
  // Only scan the relevant successors
  auto AdjustedSuccSumProb =
      collectViableSuccessors(Succ, Chain, BlockFilter, SuccSuccs);
  BranchProbability PProb = MBPI->getEdgeProbability(BB, Succ);
  auto BBFreq = MBFI->getBlockFreq(BB);
  auto SuccFreq = MBFI->getBlockFreq(Succ);
  BlockFrequency P = BBFreq * PProb;
  BlockFrequency Qout = BBFreq * QProb;
  uint64_t EntryFreq = MBFI->getEntryFreq();
  // If there are no more successors, it is profitable to copy, as it strictly
  // increases fallthrough.
  if (SuccSuccs.size() == 0)
    return greaterWithBias(P, Qout, EntryFreq);

  auto BestSuccSucc = BranchProbability::getZero();
  // Find the PDom or the best Succ if no PDom exists.
  for (MachineBasicBlock *SuccSucc : SuccSuccs) {
    auto Prob = MBPI->getEdgeProbability(Succ, SuccSucc);
    if (Prob > BestSuccSucc)
      BestSuccSucc = Prob;
    if (PDom == nullptr)
      if (MPDT->dominates(SuccSucc, Succ)) {
        PDom = SuccSucc;
        break;
      }
  }
  // For the comparisons, we need to know Succ's best incoming edge that isn't
  // from BB.
  auto SuccBestPred = BlockFrequency(0);
  for (MachineBasicBlock *SuccPred : Succ->predecessors()) {
    if (SuccPred == Succ || SuccPred == BB
        || BlockToChain[SuccPred] == &Chain
        || (BlockFilter && !BlockFilter->count(SuccPred)))
      continue;
    auto Freq = MBFI->getBlockFreq(SuccPred)
        * MBPI->getEdgeProbability(SuccPred, Succ);
    if (Freq > SuccBestPred)
      SuccBestPred = Freq;
  }
  // Qin is Succ's best unplaced incoming edge that isn't BB
  BlockFrequency Qin = SuccBestPred;
  // If it doesn't have a post-dominating successor, here is the calculation:
  //    BB        BB
  //    | \Qout   |  \
  //   P|  C      |   =
  //    =   C'    |    C
  //    |  /Qin   |     |
  //    | /       |     C' (+Succ)
  //    Succ      Succ /|
  //    / \       |  \/ |
  //  U/   =V     =  /= =
  //  /     \     | /  \|
  //  D      E    D     E
  //  '=' : Branch taken for that CFG edge
  //  Cost in the first case is: P + V
  //  For this calculation, we always assume P > Qout. If Qout > P
  //  The result of this function will be ignored at the caller.
  //  Cost in the second case is: Qout + Qin * V + P * U + P * V
  //  TODO(iteratee): If we lay out D after Succ, the P * U term
  //  goes away. This logic is coming in D28522.

  if (PDom == nullptr || !Succ->isSuccessor(PDom)) {
    BranchProbability UProb = BestSuccSucc;
    BranchProbability VProb = AdjustedSuccSumProb - UProb;
    BlockFrequency V = SuccFreq * VProb;
    BlockFrequency QinV = Qin * VProb;
    BlockFrequency BaseCost = P + V;
    BlockFrequency DupCost = Qout + QinV + P * AdjustedSuccSumProb;
    return greaterWithBias(BaseCost, DupCost, EntryFreq);
  }
  BranchProbability UProb = MBPI->getEdgeProbability(Succ, PDom);
  BranchProbability VProb = AdjustedSuccSumProb - UProb;
  BlockFrequency U = SuccFreq * UProb;
  BlockFrequency V = SuccFreq * VProb;
  // If there is a post-dominating successor, here is the calculation:
  // BB         BB                 BB          BB
  // | \Qout    |  \               | \Qout     |  \
  // |P C       |   =              |P C        |   =
  // =   C'     |P   C             =   C'      |P   C
  // |  /Qin    |     |            |  /Qin     |     |
  // | /        |     C' (+Succ)   | /         |     C' (+Succ)
  // Succ       Succ /|            Succ        Succ /|
  // | \  V     |  \/ |            | \  V      |  \/ |
  // |U \       |U /\ |            |U =        |U /\ |
  // =   D      = =  =|            |   D       | =  =|
  // |  /       |/    D            |  /        |/    D
  // | /        |    /             | =         |    /
  // |/         |   /              |/          |   =
  // Dom        Dom                Dom         Dom
  //  '=' : Branch taken for that CFG edge
  // The cost for taken branches in the first case is P + U
  // The cost in the second case (assuming independence), given the layout:
  // BB, Succ, (C+Succ), D, Dom
  // is Qout + P * V + Qin * U
  // compare P + U vs Qout + P + Qin * U.
  //
  // The 3rd and 4th cases cover when Dom would be chosen to follow Succ.
  //
  // For the 3rd case, the cost is P + 2 * V
  // For the 4th case, the cost is Qout + Qin * U + P * V + V
  // We choose 4 over 3 when (P + V) > Qout + Qin * U + P * V
  if (UProb > AdjustedSuccSumProb / 2
      && !hasBetterLayoutPredecessor(Succ, PDom, *BlockToChain[PDom],
                                     UProb, UProb, Chain, BlockFilter)) {
    // Cases 3 & 4
    return greaterWithBias((P + V), (Qout + Qin * UProb + P * VProb),
                           EntryFreq);
  }
  // Cases 1 & 2
  return greaterWithBias(
      (P + U), (Qout + Qin * UProb + P * AdjustedSuccSumProb), EntryFreq);
}


/// When the option TailDupPlacement is on, this method checks if the
/// fallthrough candidate block \p Succ (of block \p BB) can be tail-duplicated
/// into all of its unplaced, unfiltered predecessors, that are not BB.
bool MachineBlockPlacement::canTailDuplicateUnplacedPreds(
    const MachineBasicBlock *BB, MachineBasicBlock *Succ,
    const BlockChain &Chain, const BlockFilterSet *BlockFilter) {
  if (!shouldTailDuplicate(Succ))
    return false;

  for (MachineBasicBlock *Pred : Succ->predecessors()) {
    // Make sure all unplaced and unfiltered predecessors can be
    // tail-duplicated into.
    // Skip any blocks that are already placed or not in this loop.
    if (Pred == BB || (BlockFilter && !BlockFilter->count(Pred))
        || BlockToChain[Pred] == &Chain)
      continue;
    if (!TailDup.canTailDuplicate(Succ, Pred))
      return false;
  }
  return true;
}

/// When the option OutlineOptionalBranches is on, this method
/// checks if the fallthrough candidate block \p Succ (of block
/// \p BB) also has other unscheduled predecessor blocks which
/// are also successors of \p BB (forming triangular shape CFG).
/// If none of such predecessors are small, it returns true.
/// The caller can choose to select \p Succ as the layout successors
/// so that \p Succ's predecessors (optional branches) can be
/// outlined.
/// FIXME: fold this with more general layout cost analysis.
bool MachineBlockPlacement::shouldPredBlockBeOutlined(
    const MachineBasicBlock *BB, const MachineBasicBlock *Succ,
    const BlockChain &Chain, const BlockFilterSet *BlockFilter,
    BranchProbability SuccProb, BranchProbability HotProb) {
  if (!OutlineOptionalBranches)
    return false;
  // If we outline optional branches, look whether Succ is unavoidable, i.e.
  // dominates all terminators of the MachineFunction. If it does, other
  // successors must be optional. Don't do this for cold branches.
  if (SuccProb > HotProb.getCompl() && UnavoidableBlocks.count(Succ) > 0) {
    for (MachineBasicBlock *Pred : Succ->predecessors()) {
      // Check whether there is an unplaced optional branch.
      if (Pred == Succ || (BlockFilter && !BlockFilter->count(Pred)) ||
          BlockToChain[Pred] == &Chain)
        continue;
      // Check whether the optional branch has exactly one BB.
      if (Pred->pred_size() > 1 || *Pred->pred_begin() != BB)
        continue;
      // Check whether the optional branch is small.
      if (Pred->size() < OutlineOptionalThreshold)
        return false;
    }
    return true;
  } else
    return false;
}

// When profile is not present, return the StaticLikelyProb.
// When profile is available, we need to handle the triangle-shape CFG.
static BranchProbability getLayoutSuccessorProbThreshold(
      const MachineBasicBlock *BB) {
  if (!BB->getParent()->getFunction()->getEntryCount())
    return BranchProbability(StaticLikelyProb, 100);
  if (BB->succ_size() == 2) {
    const MachineBasicBlock *Succ1 = *BB->succ_begin();
    const MachineBasicBlock *Succ2 = *(BB->succ_begin() + 1);
    if (Succ1->isSuccessor(Succ2) || Succ2->isSuccessor(Succ1)) {
      /* See case 1 below for the cost analysis. For BB->Succ to
       * be taken with smaller cost, the following needs to hold:
       *   Prob(BB->Succ) > 2 * Prob(BB->Pred)
       *   So the threshold T in the calculation below
       *   (1-T) * Prob(BB->Succ) > T * Prob(BB->Pred)
       *   So T / (1 - T) = 2, Yielding T = 2/3
       * Also adding user specified branch bias, we have
       *   T = (2/3)*(ProfileLikelyProb/50)
       *     = (2*ProfileLikelyProb)/150)
       */
      return BranchProbability(2 * ProfileLikelyProb, 150);
    }
  }
  return BranchProbability(ProfileLikelyProb, 100);
}

/// Checks to see if the layout candidate block \p Succ has a better layout
/// predecessor than \c BB. If yes, returns true.
/// \p SuccProb: The probability adjusted for only remaining blocks.
///   Only used for logging
/// \p RealSuccProb: The un-adjusted probability.
/// \p Chain: The chain that BB belongs to and Succ is being considered for.
/// \p BlockFilter: if non-null, the set of blocks that make up the loop being
///    considered
bool MachineBlockPlacement::hasBetterLayoutPredecessor(
    const MachineBasicBlock *BB, const MachineBasicBlock *Succ,
    const BlockChain &SuccChain, BranchProbability SuccProb,
    BranchProbability RealSuccProb, const BlockChain &Chain,
    const BlockFilterSet *BlockFilter) {

  // There isn't a better layout when there are no unscheduled predecessors.
  if (SuccChain.UnscheduledPredecessors == 0)
    return false;

  // There are two basic scenarios here:
  // -------------------------------------
  // Case 1: triangular shape CFG (if-then):
  //     BB
  //     | \
  //     |  \
  //     |   Pred
  //     |   /
  //     Succ
  // In this case, we are evaluating whether to select edge -> Succ, e.g.
  // set Succ as the layout successor of BB. Picking Succ as BB's
  // successor breaks the CFG constraints (FIXME: define these constraints).
  // With this layout, Pred BB
  // is forced to be outlined, so the overall cost will be cost of the
  // branch taken from BB to Pred, plus the cost of back taken branch
  // from Pred to Succ, as well as the additional cost associated
  // with the needed unconditional jump instruction from Pred To Succ.

  // The cost of the topological order layout is the taken branch cost
  // from BB to Succ, so to make BB->Succ a viable candidate, the following
  // must hold:
  //     2 * freq(BB->Pred) * taken_branch_cost + unconditional_jump_cost
  //      < freq(BB->Succ) *  taken_branch_cost.
  // Ignoring unconditional jump cost, we get
  //    freq(BB->Succ) > 2 * freq(BB->Pred), i.e.,
  //    prob(BB->Succ) > 2 * prob(BB->Pred)
  //
  // When real profile data is available, we can precisely compute the
  // probability threshold that is needed for edge BB->Succ to be considered.
  // Without profile data, the heuristic requires the branch bias to be
  // a lot larger to make sure the signal is very strong (e.g. 80% default).
  // -----------------------------------------------------------------
  // Case 2: diamond like CFG (if-then-else):
  //     S
  //    / \
  //   |   \
  //  BB    Pred
  //   \    /
  //    Succ
  //    ..
  //
  // The current block is BB and edge BB->Succ is now being evaluated.
  // Note that edge S->BB was previously already selected because
  // prob(S->BB) > prob(S->Pred).
  // At this point, 2 blocks can be placed after BB: Pred or Succ. If we
  // choose Pred, we will have a topological ordering as shown on the left
  // in the picture below. If we choose Succ, we have the solution as shown
  // on the right:
  //
  //   topo-order:
  //
  //       S-----                             ---S
  //       |    |                             |  |
  //    ---BB   |                             |  BB
  //    |       |                             |  |
  //    |  pred--                             |  Succ--
  //    |  |                                  |       |
  //    ---succ                               ---pred--
  //
  // cost = freq(S->Pred) + freq(BB->Succ)    cost = 2 * freq (S->Pred)
  //      = freq(S->Pred) + freq(S->BB)
  //
  // If we have profile data (i.e, branch probabilities can be trusted), the
  // cost (number of taken branches) with layout S->BB->Succ->Pred is 2 *
  // freq(S->Pred) while the cost of topo order is freq(S->Pred) + freq(S->BB).
  // We know Prob(S->BB) > Prob(S->Pred), so freq(S->BB) > freq(S->Pred), which
  // means the cost of topological order is greater.
  // When profile data is not available, however, we need to be more
  // conservative. If the branch prediction is wrong, breaking the topo-order
  // will actually yield a layout with large cost. For this reason, we need
  // strong biased branch at block S with Prob(S->BB) in order to select
  // BB->Succ. This is equivalent to looking the CFG backward with backward
  // edge: Prob(Succ->BB) needs to >= HotProb in order to be selected (without
  // profile data).
  // --------------------------------------------------------------------------
  // Case 3: forked diamond
  //       S
  //      / \
  //     /   \
  //   BB    Pred
  //   | \   / |
  //   |  \ /  |
  //   |   X   |
  //   |  / \  |
  //   | /   \ |
  //   S1     S2
  //
  // The current block is BB and edge BB->S1 is now being evaluated.
  // As above S->BB was already selected because
  // prob(S->BB) > prob(S->Pred). Assume that prob(BB->S1) >= prob(BB->S2).
  //
  // topo-order:
  //
  //     S-------|                     ---S
  //     |       |                     |  |
  //  ---BB      |                     |  BB
  //  |          |                     |  |
  //  |  Pred----|                     |  S1----
  //  |  |                             |       |
  //  --(S1 or S2)                     ---Pred--
  //
  // topo-cost = freq(S->Pred) + freq(BB->S1) + freq(BB->S2)
  //    + min(freq(Pred->S1), freq(Pred->S2))
  // Non-topo-order cost:
  // In the worst case, S2 will not get laid out after Pred.
  // non-topo-cost = 2 * freq(S->Pred) + freq(BB->S2).
  // To be conservative, we can assume that min(freq(Pred->S1), freq(Pred->S2))
  // is 0. Then the non topo layout is better when
  // freq(S->Pred) < freq(BB->S1).
  // This is exactly what is checked below.
  // Note there are other shapes that apply (Pred may not be a single block,
  // but they all fit this general pattern.)
  BranchProbability HotProb = getLayoutSuccessorProbThreshold(BB);

  // Make sure that a hot successor doesn't have a globally more
  // important predecessor.
  BlockFrequency CandidateEdgeFreq = MBFI->getBlockFreq(BB) * RealSuccProb;
  bool BadCFGConflict = false;

  for (MachineBasicBlock *Pred : Succ->predecessors()) {
    if (Pred == Succ || BlockToChain[Pred] == &SuccChain ||
        (BlockFilter && !BlockFilter->count(Pred)) ||
        BlockToChain[Pred] == &Chain ||
        // This check is redundant except for look ahead. This function is
        // called for lookahead by isProfitableToTailDup when BB hasn't been
        // placed yet.
        (Pred == BB))
      continue;
    // Do backward checking.
    // For all cases above, we need a backward checking to filter out edges that
    // are not 'strongly' biased.
    // BB  Pred
    //  \ /
    //  Succ
    // We select edge BB->Succ if
    //      freq(BB->Succ) > freq(Succ) * HotProb
    //      i.e. freq(BB->Succ) > freq(BB->Succ) * HotProb + freq(Pred->Succ) *
    //      HotProb
    //      i.e. freq((BB->Succ) * (1 - HotProb) > freq(Pred->Succ) * HotProb
    // Case 1 is covered too, because the first equation reduces to:
    // prob(BB->Succ) > HotProb. (freq(Succ) = freq(BB) for a triangle)
    BlockFrequency PredEdgeFreq =
        MBFI->getBlockFreq(Pred) * MBPI->getEdgeProbability(Pred, Succ);
    if (PredEdgeFreq * HotProb >= CandidateEdgeFreq * HotProb.getCompl()) {
      BadCFGConflict = true;
      break;
    }
  }

  if (BadCFGConflict) {
    DEBUG(dbgs() << "    Not a candidate: " << getBlockName(Succ) << " -> " << SuccProb
                 << " (prob) (non-cold CFG conflict)\n");
    return true;
  }

  return false;
}

/// \brief Select the best successor for a block.
///
/// This looks across all successors of a particular block and attempts to
/// select the "best" one to be the layout successor. It only considers direct
/// successors which also pass the block filter. It will attempt to avoid
/// breaking CFG structure, but cave and break such structures in the case of
/// very hot successor edges.
///
/// \returns The best successor block found, or null if none are viable, along
/// with a boolean indicating if tail duplication is necessary.
MachineBlockPlacement::BlockAndTailDupResult
MachineBlockPlacement::selectBestSuccessor(
    const MachineBasicBlock *BB, const BlockChain &Chain,
    const BlockFilterSet *BlockFilter) {
  const BranchProbability HotProb(StaticLikelyProb, 100);

  BlockAndTailDupResult BestSucc = { nullptr, false };
  auto BestProb = BranchProbability::getZero();

  SmallVector<MachineBasicBlock *, 4> Successors;
  auto AdjustedSumProb =
      collectViableSuccessors(BB, Chain, BlockFilter, Successors);

  DEBUG(dbgs() << "Selecting best successor for: " << getBlockName(BB) << "\n");

  // For blocks with CFG violations, we may be able to lay them out anyway with
  // tail-duplication. We keep this vector so we can perform the probability
  // calculations the minimum number of times.
  SmallVector<std::tuple<BranchProbability, MachineBasicBlock *>, 4>
      DupCandidates;
  for (MachineBasicBlock *Succ : Successors) {
    auto RealSuccProb = MBPI->getEdgeProbability(BB, Succ);
    BranchProbability SuccProb =
        getAdjustedProbability(RealSuccProb, AdjustedSumProb);

    // This heuristic is off by default.
    if (shouldPredBlockBeOutlined(BB, Succ, Chain, BlockFilter, SuccProb,
                                  HotProb)) {
      BestSucc.BB = Succ;
      return BestSucc;
    }

    BlockChain &SuccChain = *BlockToChain[Succ];
    // Skip the edge \c BB->Succ if block \c Succ has a better layout
    // predecessor that yields lower global cost.
    if (hasBetterLayoutPredecessor(BB, Succ, SuccChain, SuccProb, RealSuccProb,
                                   Chain, BlockFilter)) {
      // If tail duplication would make Succ profitable, place it.
      if (TailDupPlacement && shouldTailDuplicate(Succ))
        DupCandidates.push_back(std::make_tuple(SuccProb, Succ));
      continue;
    }

    DEBUG(
        dbgs() << "    Candidate: " << getBlockName(Succ) << ", probability: "
               << SuccProb
               << (SuccChain.UnscheduledPredecessors != 0 ? " (CFG break)" : "")
               << "\n");

    if (BestSucc.BB && BestProb >= SuccProb) {
      DEBUG(dbgs() << "    Not the best candidate, continuing\n");
      continue;
    }

    DEBUG(dbgs() << "    Setting it as best candidate\n");
    BestSucc.BB = Succ;
    BestProb = SuccProb;
  }
  // Handle the tail duplication candidates in order of decreasing probability.
  // Stop at the first one that is profitable. Also stop if they are less
  // profitable than BestSucc. Position is important because we preserve it and
  // prefer first best match. Here we aren't comparing in order, so we capture
  // the position instead.
  if (DupCandidates.size() != 0) {
    auto cmp =
        [](const std::tuple<BranchProbability, MachineBasicBlock *> &a,
           const std::tuple<BranchProbability, MachineBasicBlock *> &b) {
          return std::get<0>(a) > std::get<0>(b);
        };
    std::stable_sort(DupCandidates.begin(), DupCandidates.end(), cmp);
  }
  for(auto &Tup : DupCandidates) {
    BranchProbability DupProb;
    MachineBasicBlock *Succ;
    std::tie(DupProb, Succ) = Tup;
    if (DupProb < BestProb)
      break;
    if (canTailDuplicateUnplacedPreds(BB, Succ, Chain, BlockFilter)
        // If tail duplication gives us fallthrough when we otherwise wouldn't
        // have it, that is a strict gain.
        && (BestSucc.BB == nullptr
            || isProfitableToTailDup(BB, Succ, BestProb, Chain,
                                     BlockFilter))) {
      DEBUG(
          dbgs() << "    Candidate: " << getBlockName(Succ) << ", probability: "
                 << DupProb
                 << " (Tail Duplicate)\n");
      BestSucc.BB = Succ;
      BestSucc.ShouldTailDup = true;
      break;
    }
  }

  if (BestSucc.BB)
    DEBUG(dbgs() << "    Selected: " << getBlockName(BestSucc.BB) << "\n");

  return BestSucc;
}

/// \brief Select the best block from a worklist.
///
/// This looks through the provided worklist as a list of candidate basic
/// blocks and select the most profitable one to place. The definition of
/// profitable only really makes sense in the context of a loop. This returns
/// the most frequently visited block in the worklist, which in the case of
/// a loop, is the one most desirable to be physically close to the rest of the
/// loop body in order to improve i-cache behavior.
///
/// \returns The best block found, or null if none are viable.
MachineBasicBlock *MachineBlockPlacement::selectBestCandidateBlock(
    const BlockChain &Chain, SmallVectorImpl<MachineBasicBlock *> &WorkList) {
  // Once we need to walk the worklist looking for a candidate, cleanup the
  // worklist of already placed entries.
  // FIXME: If this shows up on profiles, it could be folded (at the cost of
  // some code complexity) into the loop below.
  WorkList.erase(remove_if(WorkList,
                           [&](MachineBasicBlock *BB) {
                             return BlockToChain.lookup(BB) == &Chain;
                           }),
                 WorkList.end());

  if (WorkList.empty())
    return nullptr;

  bool IsEHPad = WorkList[0]->isEHPad();

  MachineBasicBlock *BestBlock = nullptr;
  BlockFrequency BestFreq;
  for (MachineBasicBlock *MBB : WorkList) {
    assert(MBB->isEHPad() == IsEHPad);

    BlockChain &SuccChain = *BlockToChain[MBB];
    if (&SuccChain == &Chain)
      continue;

    assert(SuccChain.UnscheduledPredecessors == 0 && "Found CFG-violating block");

    BlockFrequency CandidateFreq = MBFI->getBlockFreq(MBB);
    DEBUG(dbgs() << "    " << getBlockName(MBB) << " -> ";
          MBFI->printBlockFreq(dbgs(), CandidateFreq) << " (freq)\n");

    // For ehpad, we layout the least probable first as to avoid jumping back
    // from least probable landingpads to more probable ones.
    //
    // FIXME: Using probability is probably (!) not the best way to achieve
    // this. We should probably have a more principled approach to layout
    // cleanup code.
    //
    // The goal is to get:
    //
    //                 +--------------------------+
    //                 |                          V
    // InnerLp -> InnerCleanup    OuterLp -> OuterCleanup -> Resume
    //
    // Rather than:
    //
    //                 +-------------------------------------+
    //                 V                                     |
    // OuterLp -> OuterCleanup -> Resume     InnerLp -> InnerCleanup
    if (BestBlock && (IsEHPad ^ (BestFreq >= CandidateFreq)))
      continue;

    BestBlock = MBB;
    BestFreq = CandidateFreq;
  }

  return BestBlock;
}

/// \brief Retrieve the first unplaced basic block.
///
/// This routine is called when we are unable to use the CFG to walk through
/// all of the basic blocks and form a chain due to unnatural loops in the CFG.
/// We walk through the function's blocks in order, starting from the
/// LastUnplacedBlockIt. We update this iterator on each call to avoid
/// re-scanning the entire sequence on repeated calls to this routine.
MachineBasicBlock *MachineBlockPlacement::getFirstUnplacedBlock(
    const BlockChain &PlacedChain,
    MachineFunction::iterator &PrevUnplacedBlockIt,
    const BlockFilterSet *BlockFilter) {
  for (MachineFunction::iterator I = PrevUnplacedBlockIt, E = F->end(); I != E;
       ++I) {
    if (BlockFilter && !BlockFilter->count(&*I))
      continue;
    if (BlockToChain[&*I] != &PlacedChain) {
      PrevUnplacedBlockIt = I;
      // Now select the head of the chain to which the unplaced block belongs
      // as the block to place. This will force the entire chain to be placed,
      // and satisfies the requirements of merging chains.
      return *BlockToChain[&*I]->begin();
    }
  }
  return nullptr;
}

void MachineBlockPlacement::fillWorkLists(
    const MachineBasicBlock *MBB,
    SmallPtrSetImpl<BlockChain *> &UpdatedPreds,
    const BlockFilterSet *BlockFilter = nullptr) {
  BlockChain &Chain = *BlockToChain[MBB];
  if (!UpdatedPreds.insert(&Chain).second)
    return;

  assert(Chain.UnscheduledPredecessors == 0);
  for (MachineBasicBlock *ChainBB : Chain) {
    assert(BlockToChain[ChainBB] == &Chain);
    for (MachineBasicBlock *Pred : ChainBB->predecessors()) {
      if (BlockFilter && !BlockFilter->count(Pred))
        continue;
      if (BlockToChain[Pred] == &Chain)
        continue;
      ++Chain.UnscheduledPredecessors;
    }
  }

  if (Chain.UnscheduledPredecessors != 0)
    return;

  MachineBasicBlock *BB = *Chain.begin();
  if (BB->isEHPad())
    EHPadWorkList.push_back(BB);
  else
    BlockWorkList.push_back(BB);
}

void MachineBlockPlacement::buildChain(
    const MachineBasicBlock *HeadBB, BlockChain &Chain,
    BlockFilterSet *BlockFilter) {
  assert(HeadBB && "BB must not be null.\n");
  assert(BlockToChain[HeadBB] == &Chain && "BlockToChainMap mis-match.\n");
  MachineFunction::iterator PrevUnplacedBlockIt = F->begin();

  const MachineBasicBlock *LoopHeaderBB = HeadBB;
  markChainSuccessors(Chain, LoopHeaderBB, BlockFilter);
  MachineBasicBlock *BB = *std::prev(Chain.end());
  for (;;) {
    assert(BB && "null block found at end of chain in loop.");
    assert(BlockToChain[BB] == &Chain && "BlockToChainMap mis-match in loop.");
    assert(*std::prev(Chain.end()) == BB && "BB Not found at end of chain.");


    // Look for the best viable successor if there is one to place immediately
    // after this block.
    auto Result = selectBestSuccessor(BB, Chain, BlockFilter);
    MachineBasicBlock* BestSucc = Result.BB;
    bool ShouldTailDup = Result.ShouldTailDup;
    if (TailDupPlacement)
      ShouldTailDup |= (BestSucc && shouldTailDuplicate(BestSucc));

    // If an immediate successor isn't available, look for the best viable
    // block among those we've identified as not violating the loop's CFG at
    // this point. This won't be a fallthrough, but it will increase locality.
    if (!BestSucc)
      BestSucc = selectBestCandidateBlock(Chain, BlockWorkList);
    if (!BestSucc)
      BestSucc = selectBestCandidateBlock(Chain, EHPadWorkList);

    if (!BestSucc) {
      BestSucc = getFirstUnplacedBlock(Chain, PrevUnplacedBlockIt, BlockFilter);
      if (!BestSucc)
        break;

      DEBUG(dbgs() << "Unnatural loop CFG detected, forcibly merging the "
                      "layout successor until the CFG reduces\n");
    }

    // Placement may have changed tail duplication opportunities.
    // Check for that now.
    if (TailDupPlacement && BestSucc && ShouldTailDup) {
      // If the chosen successor was duplicated into all its predecessors,
      // don't bother laying it out, just go round the loop again with BB as
      // the chain end.
      if (repeatedlyTailDuplicateBlock(BestSucc, BB, LoopHeaderBB, Chain,
                                       BlockFilter, PrevUnplacedBlockIt))
        continue;
    }

    // Place this block, updating the datastructures to reflect its placement.
    BlockChain &SuccChain = *BlockToChain[BestSucc];
    // Zero out UnscheduledPredecessors for the successor we're about to merge in case
    // we selected a successor that didn't fit naturally into the CFG.
    SuccChain.UnscheduledPredecessors = 0;
    DEBUG(dbgs() << "Merging from " << getBlockName(BB) << " to "
                 << getBlockName(BestSucc) << "\n");
    markChainSuccessors(SuccChain, LoopHeaderBB, BlockFilter);
    Chain.merge(BestSucc, &SuccChain);
    BB = *std::prev(Chain.end());
  }

  DEBUG(dbgs() << "Finished forming chain for header block "
               << getBlockName(*Chain.begin()) << "\n");
}

/// \brief Find the best loop top block for layout.
///
/// Look for a block which is strictly better than the loop header for laying
/// out at the top of the loop. This looks for one and only one pattern:
/// a latch block with no conditional exit. This block will cause a conditional
/// jump around it or will be the bottom of the loop if we lay it out in place,
/// but if it it doesn't end up at the bottom of the loop for any reason,
/// rotation alone won't fix it. Because such a block will always result in an
/// unconditional jump (for the backedge) rotating it in front of the loop
/// header is always profitable.
MachineBasicBlock *
MachineBlockPlacement::findBestLoopTop(const MachineLoop &L,
                                       const BlockFilterSet &LoopBlockSet) {
  // Placing the latch block before the header may introduce an extra branch
  // that skips this block the first time the loop is executed, which we want
  // to avoid when optimising for size.
  // FIXME: in theory there is a case that does not introduce a new branch,
  // i.e. when the layout predecessor does not fallthrough to the loop header.
  // In practice this never happens though: there always seems to be a preheader
  // that can fallthrough and that is also placed before the header.
  if (F->getFunction()->optForSize())
    return L.getHeader();

  // Check that the header hasn't been fused with a preheader block due to
  // crazy branches. If it has, we need to start with the header at the top to
  // prevent pulling the preheader into the loop body.
  BlockChain &HeaderChain = *BlockToChain[L.getHeader()];
  if (!LoopBlockSet.count(*HeaderChain.begin()))
    return L.getHeader();

  DEBUG(dbgs() << "Finding best loop top for: " << getBlockName(L.getHeader())
               << "\n");

  BlockFrequency BestPredFreq;
  MachineBasicBlock *BestPred = nullptr;
  for (MachineBasicBlock *Pred : L.getHeader()->predecessors()) {
    if (!LoopBlockSet.count(Pred))
      continue;
    DEBUG(dbgs() << "    header pred: " << getBlockName(Pred) << ", has "
                 << Pred->succ_size() << " successors, ";
          MBFI->printBlockFreq(dbgs(), Pred) << " freq\n");
    if (Pred->succ_size() > 1)
      continue;

    BlockFrequency PredFreq = MBFI->getBlockFreq(Pred);
    if (!BestPred || PredFreq > BestPredFreq ||
        (!(PredFreq < BestPredFreq) &&
         Pred->isLayoutSuccessor(L.getHeader()))) {
      BestPred = Pred;
      BestPredFreq = PredFreq;
    }
  }

  // If no direct predecessor is fine, just use the loop header.
  if (!BestPred) {
    DEBUG(dbgs() << "    final top unchanged\n");
    return L.getHeader();
  }

  // Walk backwards through any straight line of predecessors.
  while (BestPred->pred_size() == 1 &&
         (*BestPred->pred_begin())->succ_size() == 1 &&
         *BestPred->pred_begin() != L.getHeader())
    BestPred = *BestPred->pred_begin();

  DEBUG(dbgs() << "    final top: " << getBlockName(BestPred) << "\n");
  return BestPred;
}

/// \brief Find the best loop exiting block for layout.
///
/// This routine implements the logic to analyze the loop looking for the best
/// block to layout at the top of the loop. Typically this is done to maximize
/// fallthrough opportunities.
MachineBasicBlock *
MachineBlockPlacement::findBestLoopExit(const MachineLoop &L,
                                        const BlockFilterSet &LoopBlockSet) {
  // We don't want to layout the loop linearly in all cases. If the loop header
  // is just a normal basic block in the loop, we want to look for what block
  // within the loop is the best one to layout at the top. However, if the loop
  // header has be pre-merged into a chain due to predecessors not having
  // analyzable branches, *and* the predecessor it is merged with is *not* part
  // of the loop, rotating the header into the middle of the loop will create
  // a non-contiguous range of blocks which is Very Bad. So start with the
  // header and only rotate if safe.
  BlockChain &HeaderChain = *BlockToChain[L.getHeader()];
  if (!LoopBlockSet.count(*HeaderChain.begin()))
    return nullptr;

  BlockFrequency BestExitEdgeFreq;
  unsigned BestExitLoopDepth = 0;
  MachineBasicBlock *ExitingBB = nullptr;
  // If there are exits to outer loops, loop rotation can severely limit
  // fallthrough opportunities unless it selects such an exit. Keep a set of
  // blocks where rotating to exit with that block will reach an outer loop.
  SmallPtrSet<MachineBasicBlock *, 4> BlocksExitingToOuterLoop;

  DEBUG(dbgs() << "Finding best loop exit for: " << getBlockName(L.getHeader())
               << "\n");
  for (MachineBasicBlock *MBB : L.getBlocks()) {
    BlockChain &Chain = *BlockToChain[MBB];
    // Ensure that this block is at the end of a chain; otherwise it could be
    // mid-way through an inner loop or a successor of an unanalyzable branch.
    if (MBB != *std::prev(Chain.end()))
      continue;

    // Now walk the successors. We need to establish whether this has a viable
    // exiting successor and whether it has a viable non-exiting successor.
    // We store the old exiting state and restore it if a viable looping
    // successor isn't found.
    MachineBasicBlock *OldExitingBB = ExitingBB;
    BlockFrequency OldBestExitEdgeFreq = BestExitEdgeFreq;
    bool HasLoopingSucc = false;
    for (MachineBasicBlock *Succ : MBB->successors()) {
      if (Succ->isEHPad())
        continue;
      if (Succ == MBB)
        continue;
      BlockChain &SuccChain = *BlockToChain[Succ];
      // Don't split chains, either this chain or the successor's chain.
      if (&Chain == &SuccChain) {
        DEBUG(dbgs() << "    exiting: " << getBlockName(MBB) << " -> "
                     << getBlockName(Succ) << " (chain conflict)\n");
        continue;
      }

      auto SuccProb = MBPI->getEdgeProbability(MBB, Succ);
      if (LoopBlockSet.count(Succ)) {
        DEBUG(dbgs() << "    looping: " << getBlockName(MBB) << " -> "
                     << getBlockName(Succ) << " (" << SuccProb << ")\n");
        HasLoopingSucc = true;
        continue;
      }

      unsigned SuccLoopDepth = 0;
      if (MachineLoop *ExitLoop = MLI->getLoopFor(Succ)) {
        SuccLoopDepth = ExitLoop->getLoopDepth();
        if (ExitLoop->contains(&L))
          BlocksExitingToOuterLoop.insert(MBB);
      }

      BlockFrequency ExitEdgeFreq = MBFI->getBlockFreq(MBB) * SuccProb;
      DEBUG(dbgs() << "    exiting: " << getBlockName(MBB) << " -> "
                   << getBlockName(Succ) << " [L:" << SuccLoopDepth << "] (";
            MBFI->printBlockFreq(dbgs(), ExitEdgeFreq) << ")\n");
      // Note that we bias this toward an existing layout successor to retain
      // incoming order in the absence of better information. The exit must have
      // a frequency higher than the current exit before we consider breaking
      // the layout.
      BranchProbability Bias(100 - ExitBlockBias, 100);
      if (!ExitingBB || SuccLoopDepth > BestExitLoopDepth ||
          ExitEdgeFreq > BestExitEdgeFreq ||
          (MBB->isLayoutSuccessor(Succ) &&
           !(ExitEdgeFreq < BestExitEdgeFreq * Bias))) {
        BestExitEdgeFreq = ExitEdgeFreq;
        ExitingBB = MBB;
      }
    }

    if (!HasLoopingSucc) {
      // Restore the old exiting state, no viable looping successor was found.
      ExitingBB = OldExitingBB;
      BestExitEdgeFreq = OldBestExitEdgeFreq;
    }
  }
  // Without a candidate exiting block or with only a single block in the
  // loop, just use the loop header to layout the loop.
  if (!ExitingBB) {
    DEBUG(dbgs() << "    No other candidate exit blocks, using loop header\n");
    return nullptr;
  }
  if (L.getNumBlocks() == 1) {
    DEBUG(dbgs() << "    Loop has 1 block, using loop header as exit\n");
    return nullptr;
  }

  // Also, if we have exit blocks which lead to outer loops but didn't select
  // one of them as the exiting block we are rotating toward, disable loop
  // rotation altogether.
  if (!BlocksExitingToOuterLoop.empty() &&
      !BlocksExitingToOuterLoop.count(ExitingBB))
    return nullptr;

  DEBUG(dbgs() << "  Best exiting block: " << getBlockName(ExitingBB) << "\n");
  return ExitingBB;
}

/// \brief Attempt to rotate an exiting block to the bottom of the loop.
///
/// Once we have built a chain, try to rotate it to line up the hot exit block
/// with fallthrough out of the loop if doing so doesn't introduce unnecessary
/// branches. For example, if the loop has fallthrough into its header and out
/// of its bottom already, don't rotate it.
void MachineBlockPlacement::rotateLoop(BlockChain &LoopChain,
                                       const MachineBasicBlock *ExitingBB,
                                       const BlockFilterSet &LoopBlockSet) {
  if (!ExitingBB)
    return;

  MachineBasicBlock *Top = *LoopChain.begin();
  bool ViableTopFallthrough = false;
  for (MachineBasicBlock *Pred : Top->predecessors()) {
    BlockChain *PredChain = BlockToChain[Pred];
    if (!LoopBlockSet.count(Pred) &&
        (!PredChain || Pred == *std::prev(PredChain->end()))) {
      ViableTopFallthrough = true;
      break;
    }
  }

  // If the header has viable fallthrough, check whether the current loop
  // bottom is a viable exiting block. If so, bail out as rotating will
  // introduce an unnecessary branch.
  if (ViableTopFallthrough) {
    MachineBasicBlock *Bottom = *std::prev(LoopChain.end());
    for (MachineBasicBlock *Succ : Bottom->successors()) {
      BlockChain *SuccChain = BlockToChain[Succ];
      if (!LoopBlockSet.count(Succ) &&
          (!SuccChain || Succ == *SuccChain->begin()))
        return;
    }
  }

  BlockChain::iterator ExitIt = find(LoopChain, ExitingBB);
  if (ExitIt == LoopChain.end())
    return;

  std::rotate(LoopChain.begin(), std::next(ExitIt), LoopChain.end());
}

/// \brief Attempt to rotate a loop based on profile data to reduce branch cost.
///
/// With profile data, we can determine the cost in terms of missed fall through
/// opportunities when rotating a loop chain and select the best rotation.
/// Basically, there are three kinds of cost to consider for each rotation:
///    1. The possibly missed fall through edge (if it exists) from BB out of
///    the loop to the loop header.
///    2. The possibly missed fall through edges (if they exist) from the loop
///    exits to BB out of the loop.
///    3. The missed fall through edge (if it exists) from the last BB to the
///    first BB in the loop chain.
///  Therefore, the cost for a given rotation is the sum of costs listed above.
///  We select the best rotation with the smallest cost.
void MachineBlockPlacement::rotateLoopWithProfile(
    BlockChain &LoopChain, const MachineLoop &L,
    const BlockFilterSet &LoopBlockSet) {
  auto HeaderBB = L.getHeader();
  auto HeaderIter = find(LoopChain, HeaderBB);
  auto RotationPos = LoopChain.end();

  BlockFrequency SmallestRotationCost = BlockFrequency::getMaxFrequency();

  // A utility lambda that scales up a block frequency by dividing it by a
  // branch probability which is the reciprocal of the scale.
  auto ScaleBlockFrequency = [](BlockFrequency Freq,
                                unsigned Scale) -> BlockFrequency {
    if (Scale == 0)
      return 0;
    // Use operator / between BlockFrequency and BranchProbability to implement
    // saturating multiplication.
    return Freq / BranchProbability(1, Scale);
  };

  // Compute the cost of the missed fall-through edge to the loop header if the
  // chain head is not the loop header. As we only consider natural loops with
  // single header, this computation can be done only once.
  BlockFrequency HeaderFallThroughCost(0);
  for (auto *Pred : HeaderBB->predecessors()) {
    BlockChain *PredChain = BlockToChain[Pred];
    if (!LoopBlockSet.count(Pred) &&
        (!PredChain || Pred == *std::prev(PredChain->end()))) {
      auto EdgeFreq =
          MBFI->getBlockFreq(Pred) * MBPI->getEdgeProbability(Pred, HeaderBB);
      auto FallThruCost = ScaleBlockFrequency(EdgeFreq, MisfetchCost);
      // If the predecessor has only an unconditional jump to the header, we
      // need to consider the cost of this jump.
      if (Pred->succ_size() == 1)
        FallThruCost += ScaleBlockFrequency(EdgeFreq, JumpInstCost);
      HeaderFallThroughCost = std::max(HeaderFallThroughCost, FallThruCost);
    }
  }

  // Here we collect all exit blocks in the loop, and for each exit we find out
  // its hottest exit edge. For each loop rotation, we define the loop exit cost
  // as the sum of frequencies of exit edges we collect here, excluding the exit
  // edge from the tail of the loop chain.
  SmallVector<std::pair<MachineBasicBlock *, BlockFrequency>, 4> ExitsWithFreq;
  for (auto BB : LoopChain) {
    auto LargestExitEdgeProb = BranchProbability::getZero();
    for (auto *Succ : BB->successors()) {
      BlockChain *SuccChain = BlockToChain[Succ];
      if (!LoopBlockSet.count(Succ) &&
          (!SuccChain || Succ == *SuccChain->begin())) {
        auto SuccProb = MBPI->getEdgeProbability(BB, Succ);
        LargestExitEdgeProb = std::max(LargestExitEdgeProb, SuccProb);
      }
    }
    if (LargestExitEdgeProb > BranchProbability::getZero()) {
      auto ExitFreq = MBFI->getBlockFreq(BB) * LargestExitEdgeProb;
      ExitsWithFreq.emplace_back(BB, ExitFreq);
    }
  }

  // In this loop we iterate every block in the loop chain and calculate the
  // cost assuming the block is the head of the loop chain. When the loop ends,
  // we should have found the best candidate as the loop chain's head.
  for (auto Iter = LoopChain.begin(), TailIter = std::prev(LoopChain.end()),
            EndIter = LoopChain.end();
       Iter != EndIter; Iter++, TailIter++) {
    // TailIter is used to track the tail of the loop chain if the block we are
    // checking (pointed by Iter) is the head of the chain.
    if (TailIter == LoopChain.end())
      TailIter = LoopChain.begin();

    auto TailBB = *TailIter;

    // Calculate the cost by putting this BB to the top.
    BlockFrequency Cost = 0;

    // If the current BB is the loop header, we need to take into account the
    // cost of the missed fall through edge from outside of the loop to the
    // header.
    if (Iter != HeaderIter)
      Cost += HeaderFallThroughCost;

    // Collect the loop exit cost by summing up frequencies of all exit edges
    // except the one from the chain tail.
    for (auto &ExitWithFreq : ExitsWithFreq)
      if (TailBB != ExitWithFreq.first)
        Cost += ExitWithFreq.second;

    // The cost of breaking the once fall-through edge from the tail to the top
    // of the loop chain. Here we need to consider three cases:
    // 1. If the tail node has only one successor, then we will get an
    //    additional jmp instruction. So the cost here is (MisfetchCost +
    //    JumpInstCost) * tail node frequency.
    // 2. If the tail node has two successors, then we may still get an
    //    additional jmp instruction if the layout successor after the loop
    //    chain is not its CFG successor. Note that the more frequently executed
    //    jmp instruction will be put ahead of the other one. Assume the
    //    frequency of those two branches are x and y, where x is the frequency
    //    of the edge to the chain head, then the cost will be
    //    (x * MisfetechCost + min(x, y) * JumpInstCost) * tail node frequency.
    // 3. If the tail node has more than two successors (this rarely happens),
    //    we won't consider any additional cost.
    if (TailBB->isSuccessor(*Iter)) {
      auto TailBBFreq = MBFI->getBlockFreq(TailBB);
      if (TailBB->succ_size() == 1)
        Cost += ScaleBlockFrequency(TailBBFreq.getFrequency(),
                                    MisfetchCost + JumpInstCost);
      else if (TailBB->succ_size() == 2) {
        auto TailToHeadProb = MBPI->getEdgeProbability(TailBB, *Iter);
        auto TailToHeadFreq = TailBBFreq * TailToHeadProb;
        auto ColderEdgeFreq = TailToHeadProb > BranchProbability(1, 2)
                                  ? TailBBFreq * TailToHeadProb.getCompl()
                                  : TailToHeadFreq;
        Cost += ScaleBlockFrequency(TailToHeadFreq, MisfetchCost) +
                ScaleBlockFrequency(ColderEdgeFreq, JumpInstCost);
      }
    }

    DEBUG(dbgs() << "The cost of loop rotation by making " << getBlockName(*Iter)
                 << " to the top: " << Cost.getFrequency() << "\n");

    if (Cost < SmallestRotationCost) {
      SmallestRotationCost = Cost;
      RotationPos = Iter;
    }
  }

  if (RotationPos != LoopChain.end()) {
    DEBUG(dbgs() << "Rotate loop by making " << getBlockName(*RotationPos)
                 << " to the top\n");
    std::rotate(LoopChain.begin(), RotationPos, LoopChain.end());
  }
}

/// \brief Collect blocks in the given loop that are to be placed.
///
/// When profile data is available, exclude cold blocks from the returned set;
/// otherwise, collect all blocks in the loop.
MachineBlockPlacement::BlockFilterSet
MachineBlockPlacement::collectLoopBlockSet(const MachineLoop &L) {
  BlockFilterSet LoopBlockSet;

  // Filter cold blocks off from LoopBlockSet when profile data is available.
  // Collect the sum of frequencies of incoming edges to the loop header from
  // outside. If we treat the loop as a super block, this is the frequency of
  // the loop. Then for each block in the loop, we calculate the ratio between
  // its frequency and the frequency of the loop block. When it is too small,
  // don't add it to the loop chain. If there are outer loops, then this block
  // will be merged into the first outer loop chain for which this block is not
  // cold anymore. This needs precise profile data and we only do this when
  // profile data is available.
  if (F->getFunction()->getEntryCount()) {
    BlockFrequency LoopFreq(0);
    for (auto LoopPred : L.getHeader()->predecessors())
      if (!L.contains(LoopPred))
        LoopFreq += MBFI->getBlockFreq(LoopPred) *
                    MBPI->getEdgeProbability(LoopPred, L.getHeader());

    for (MachineBasicBlock *LoopBB : L.getBlocks()) {
      auto Freq = MBFI->getBlockFreq(LoopBB).getFrequency();
      if (Freq == 0 || LoopFreq.getFrequency() / Freq > LoopToColdBlockRatio)
        continue;
      LoopBlockSet.insert(LoopBB);
    }
  } else
    LoopBlockSet.insert(L.block_begin(), L.block_end());

  return LoopBlockSet;
}

/// \brief Forms basic block chains from the natural loop structures.
///
/// These chains are designed to preserve the existing *structure* of the code
/// as much as possible. We can then stitch the chains together in a way which
/// both preserves the topological structure and minimizes taken conditional
/// branches.
void MachineBlockPlacement::buildLoopChains(const MachineLoop &L) {
  // First recurse through any nested loops, building chains for those inner
  // loops.
  for (const MachineLoop *InnerLoop : L)
    buildLoopChains(*InnerLoop);

  assert(BlockWorkList.empty());
  assert(EHPadWorkList.empty());
  BlockFilterSet LoopBlockSet = collectLoopBlockSet(L);

  // Check if we have profile data for this function. If yes, we will rotate
  // this loop by modeling costs more precisely which requires the profile data
  // for better layout.
  bool RotateLoopWithProfile =
      ForcePreciseRotationCost ||
      (PreciseRotationCost && F->getFunction()->getEntryCount());

  // First check to see if there is an obviously preferable top block for the
  // loop. This will default to the header, but may end up as one of the
  // predecessors to the header if there is one which will result in strictly
  // fewer branches in the loop body.
  // When we use profile data to rotate the loop, this is unnecessary.
  MachineBasicBlock *LoopTop =
      RotateLoopWithProfile ? L.getHeader() : findBestLoopTop(L, LoopBlockSet);

  // If we selected just the header for the loop top, look for a potentially
  // profitable exit block in the event that rotating the loop can eliminate
  // branches by placing an exit edge at the bottom.
  if (!RotateLoopWithProfile && LoopTop == L.getHeader())
    PreferredLoopExit = findBestLoopExit(L, LoopBlockSet);

  BlockChain &LoopChain = *BlockToChain[LoopTop];

  // FIXME: This is a really lame way of walking the chains in the loop: we
  // walk the blocks, and use a set to prevent visiting a particular chain
  // twice.
  SmallPtrSet<BlockChain *, 4> UpdatedPreds;
  assert(LoopChain.UnscheduledPredecessors == 0);
  UpdatedPreds.insert(&LoopChain);

  for (const MachineBasicBlock *LoopBB : LoopBlockSet)
    fillWorkLists(LoopBB, UpdatedPreds, &LoopBlockSet);

  buildChain(LoopTop, LoopChain, &LoopBlockSet);

  if (RotateLoopWithProfile)
    rotateLoopWithProfile(LoopChain, L, LoopBlockSet);
  else
    rotateLoop(LoopChain, PreferredLoopExit, LoopBlockSet);

  DEBUG({
    // Crash at the end so we get all of the debugging output first.
    bool BadLoop = false;
    if (LoopChain.UnscheduledPredecessors) {
      BadLoop = true;
      dbgs() << "Loop chain contains a block without its preds placed!\n"
             << "  Loop header:  " << getBlockName(*L.block_begin()) << "\n"
             << "  Chain header: " << getBlockName(*LoopChain.begin()) << "\n";
    }
    for (MachineBasicBlock *ChainBB : LoopChain) {
      dbgs() << "          ... " << getBlockName(ChainBB) << "\n";
      if (!LoopBlockSet.remove(ChainBB)) {
        // We don't mark the loop as bad here because there are real situations
        // where this can occur. For example, with an unanalyzable fallthrough
        // from a loop block to a non-loop block or vice versa.
        dbgs() << "Loop chain contains a block not contained by the loop!\n"
               << "  Loop header:  " << getBlockName(*L.block_begin()) << "\n"
               << "  Chain header: " << getBlockName(*LoopChain.begin()) << "\n"
               << "  Bad block:    " << getBlockName(ChainBB) << "\n";
      }
    }

    if (!LoopBlockSet.empty()) {
      BadLoop = true;
      for (const MachineBasicBlock *LoopBB : LoopBlockSet)
        dbgs() << "Loop contains blocks never placed into a chain!\n"
               << "  Loop header:  " << getBlockName(*L.block_begin()) << "\n"
               << "  Chain header: " << getBlockName(*LoopChain.begin()) << "\n"
               << "  Bad block:    " << getBlockName(LoopBB) << "\n";
    }
    assert(!BadLoop && "Detected problems with the placement of this loop.");
  });

  BlockWorkList.clear();
  EHPadWorkList.clear();
}

/// When OutlineOpitonalBranches is on, this method collects BBs that
/// dominates all terminator blocks of the function \p F.
void MachineBlockPlacement::collectMustExecuteBBs() {
  if (OutlineOptionalBranches) {
    // Find the nearest common dominator of all of F's terminators.
    MachineBasicBlock *Terminator = nullptr;
    for (MachineBasicBlock &MBB : *F) {
      if (MBB.succ_size() == 0) {
        if (Terminator == nullptr)
          Terminator = &MBB;
        else
          Terminator = MDT->findNearestCommonDominator(Terminator, &MBB);
      }
    }

    // MBBs dominating this common dominator are unavoidable.
    UnavoidableBlocks.clear();
    for (MachineBasicBlock &MBB : *F) {
      if (MDT->dominates(&MBB, Terminator)) {
        UnavoidableBlocks.insert(&MBB);
      }
    }
  }
}

void MachineBlockPlacement::buildCFGChains() {
  // Ensure that every BB in the function has an associated chain to simplify
  // the assumptions of the remaining algorithm.
  SmallVector<MachineOperand, 4> Cond; // For AnalyzeBranch.
  for (MachineFunction::iterator FI = F->begin(), FE = F->end(); FI != FE;
       ++FI) {
    MachineBasicBlock *BB = &*FI;
    BlockChain *Chain =
        new (ChainAllocator.Allocate()) BlockChain(BlockToChain, BB);
    // Also, merge any blocks which we cannot reason about and must preserve
    // the exact fallthrough behavior for.
    for (;;) {
      Cond.clear();
      MachineBasicBlock *TBB = nullptr, *FBB = nullptr; // For AnalyzeBranch.
      if (!TII->analyzeBranch(*BB, TBB, FBB, Cond) || !FI->canFallThrough())
        break;

      MachineFunction::iterator NextFI = std::next(FI);
      MachineBasicBlock *NextBB = &*NextFI;
      // Ensure that the layout successor is a viable block, as we know that
      // fallthrough is a possibility.
      assert(NextFI != FE && "Can't fallthrough past the last block.");
      DEBUG(dbgs() << "Pre-merging due to unanalyzable fallthrough: "
                   << getBlockName(BB) << " -> " << getBlockName(NextBB)
                   << "\n");
      Chain->merge(NextBB, nullptr);
#ifndef NDEBUG
      BlocksWithUnanalyzableExits.insert(&*BB);
#endif
      FI = NextFI;
      BB = NextBB;
    }
  }

  // Turned on with OutlineOptionalBranches option
  collectMustExecuteBBs();

  // Build any loop-based chains.
  PreferredLoopExit = nullptr;
  for (MachineLoop *L : *MLI)
    buildLoopChains(*L);

  assert(BlockWorkList.empty());
  assert(EHPadWorkList.empty());

  SmallPtrSet<BlockChain *, 4> UpdatedPreds;
  for (MachineBasicBlock &MBB : *F)
    fillWorkLists(&MBB, UpdatedPreds);

  BlockChain &FunctionChain = *BlockToChain[&F->front()];
  buildChain(&F->front(), FunctionChain);

#ifndef NDEBUG
  typedef SmallPtrSet<MachineBasicBlock *, 16> FunctionBlockSetType;
#endif
  DEBUG({
    // Crash at the end so we get all of the debugging output first.
    bool BadFunc = false;
    FunctionBlockSetType FunctionBlockSet;
    for (MachineBasicBlock &MBB : *F)
      FunctionBlockSet.insert(&MBB);

    for (MachineBasicBlock *ChainBB : FunctionChain)
      if (!FunctionBlockSet.erase(ChainBB)) {
        BadFunc = true;
        dbgs() << "Function chain contains a block not in the function!\n"
               << "  Bad block:    " << getBlockName(ChainBB) << "\n";
      }

    if (!FunctionBlockSet.empty()) {
      BadFunc = true;
      for (MachineBasicBlock *RemainingBB : FunctionBlockSet)
        dbgs() << "Function contains blocks never placed into a chain!\n"
               << "  Bad block:    " << getBlockName(RemainingBB) << "\n";
    }
    assert(!BadFunc && "Detected problems with the block placement.");
  });

  // Splice the blocks into place.
  MachineFunction::iterator InsertPos = F->begin();
  DEBUG(dbgs() << "[MBP] Function: "<< F->getName() << "\n");
  for (MachineBasicBlock *ChainBB : FunctionChain) {
    DEBUG(dbgs() << (ChainBB == *FunctionChain.begin() ? "Placing chain "
                                                       : "          ... ")
                 << getBlockName(ChainBB) << "\n");
    if (InsertPos != MachineFunction::iterator(ChainBB))
      F->splice(InsertPos, ChainBB);
    else
      ++InsertPos;

    // Update the terminator of the previous block.
    if (ChainBB == *FunctionChain.begin())
      continue;
    MachineBasicBlock *PrevBB = &*std::prev(MachineFunction::iterator(ChainBB));

    // FIXME: It would be awesome of updateTerminator would just return rather
    // than assert when the branch cannot be analyzed in order to remove this
    // boiler plate.
    Cond.clear();
    MachineBasicBlock *TBB = nullptr, *FBB = nullptr; // For AnalyzeBranch.

#ifndef NDEBUG
    if (!BlocksWithUnanalyzableExits.count(PrevBB)) {
      // Given the exact block placement we chose, we may actually not _need_ to
      // be able to edit PrevBB's terminator sequence, but not being _able_ to
      // do that at this point is a bug.
      assert((!TII->analyzeBranch(*PrevBB, TBB, FBB, Cond) ||
              !PrevBB->canFallThrough()) &&
             "Unexpected block with un-analyzable fallthrough!");
      Cond.clear();
      TBB = FBB = nullptr;
    }
#endif

    // The "PrevBB" is not yet updated to reflect current code layout, so,
    //   o. it may fall-through to a block without explicit "goto" instruction
    //      before layout, and no longer fall-through it after layout; or
    //   o. just opposite.
    //
    // analyzeBranch() may return erroneous value for FBB when these two
    // situations take place. For the first scenario FBB is mistakenly set NULL;
    // for the 2nd scenario, the FBB, which is expected to be NULL, is
    // mistakenly pointing to "*BI".
    // Thus, if the future change needs to use FBB before the layout is set, it
    // has to correct FBB first by using the code similar to the following:
    //
    // if (!Cond.empty() && (!FBB || FBB == ChainBB)) {
    //   PrevBB->updateTerminator();
    //   Cond.clear();
    //   TBB = FBB = nullptr;
    //   if (TII->analyzeBranch(*PrevBB, TBB, FBB, Cond)) {
    //     // FIXME: This should never take place.
    //     TBB = FBB = nullptr;
    //   }
    // }
    if (!TII->analyzeBranch(*PrevBB, TBB, FBB, Cond))
      PrevBB->updateTerminator();
  }

  // Fixup the last block.
  Cond.clear();
  MachineBasicBlock *TBB = nullptr, *FBB = nullptr; // For AnalyzeBranch.
  if (!TII->analyzeBranch(F->back(), TBB, FBB, Cond))
    F->back().updateTerminator();

  BlockWorkList.clear();
  EHPadWorkList.clear();
}

void MachineBlockPlacement::optimizeBranches() {
  BlockChain &FunctionChain = *BlockToChain[&F->front()];
  SmallVector<MachineOperand, 4> Cond; // For AnalyzeBranch.

  // Now that all the basic blocks in the chain have the proper layout,
  // make a final call to AnalyzeBranch with AllowModify set.
  // Indeed, the target may be able to optimize the branches in a way we
  // cannot because all branches may not be analyzable.
  // E.g., the target may be able to remove an unconditional branch to
  // a fallthrough when it occurs after predicated terminators.
  for (MachineBasicBlock *ChainBB : FunctionChain) {
    Cond.clear();
    MachineBasicBlock *TBB = nullptr, *FBB = nullptr; // For AnalyzeBranch.
    if (!TII->analyzeBranch(*ChainBB, TBB, FBB, Cond, /*AllowModify*/ true)) {
      // If PrevBB has a two-way branch, try to re-order the branches
      // such that we branch to the successor with higher probability first.
      if (TBB && !Cond.empty() && FBB &&
          MBPI->getEdgeProbability(ChainBB, FBB) >
              MBPI->getEdgeProbability(ChainBB, TBB) &&
          !TII->reverseBranchCondition(Cond)) {
        DEBUG(dbgs() << "Reverse order of the two branches: "
                     << getBlockName(ChainBB) << "\n");
        DEBUG(dbgs() << "    Edge probability: "
                     << MBPI->getEdgeProbability(ChainBB, FBB) << " vs "
                     << MBPI->getEdgeProbability(ChainBB, TBB) << "\n");
        DebugLoc dl; // FIXME: this is nowhere
        TII->removeBranch(*ChainBB);
        TII->insertBranch(*ChainBB, FBB, TBB, Cond, dl);
        ChainBB->updateTerminator();
      }
    }
  }
}

void MachineBlockPlacement::alignBlocks() {
  // Walk through the backedges of the function now that we have fully laid out
  // the basic blocks and align the destination of each backedge. We don't rely
  // exclusively on the loop info here so that we can align backedges in
  // unnatural CFGs and backedges that were introduced purely because of the
  // loop rotations done during this layout pass.
  if (F->getFunction()->optForSize())
    return;
  BlockChain &FunctionChain = *BlockToChain[&F->front()];
  if (FunctionChain.begin() == FunctionChain.end())
    return; // Empty chain.

  const BranchProbability ColdProb(1, 5); // 20%
  BlockFrequency EntryFreq = MBFI->getBlockFreq(&F->front());
  BlockFrequency WeightedEntryFreq = EntryFreq * ColdProb;
  for (MachineBasicBlock *ChainBB : FunctionChain) {
    if (ChainBB == *FunctionChain.begin())
      continue;

    // Don't align non-looping basic blocks. These are unlikely to execute
    // enough times to matter in practice. Note that we'll still handle
    // unnatural CFGs inside of a natural outer loop (the common case) and
    // rotated loops.
    MachineLoop *L = MLI->getLoopFor(ChainBB);
    if (!L)
      continue;

    unsigned Align = TLI->getPrefLoopAlignment(L);
    if (!Align)
      continue; // Don't care about loop alignment.

    // If the block is cold relative to the function entry don't waste space
    // aligning it.
    BlockFrequency Freq = MBFI->getBlockFreq(ChainBB);
    if (Freq < WeightedEntryFreq)
      continue;

    // If the block is cold relative to its loop header, don't align it
    // regardless of what edges into the block exist.
    MachineBasicBlock *LoopHeader = L->getHeader();
    BlockFrequency LoopHeaderFreq = MBFI->getBlockFreq(LoopHeader);
    if (Freq < (LoopHeaderFreq * ColdProb))
      continue;

    // Check for the existence of a non-layout predecessor which would benefit
    // from aligning this block.
    MachineBasicBlock *LayoutPred =
        &*std::prev(MachineFunction::iterator(ChainBB));

    // Force alignment if all the predecessors are jumps. We already checked
    // that the block isn't cold above.
    if (!LayoutPred->isSuccessor(ChainBB)) {
      ChainBB->setAlignment(Align);
      continue;
    }

    // Align this block if the layout predecessor's edge into this block is
    // cold relative to the block. When this is true, other predecessors make up
    // all of the hot entries into the block and thus alignment is likely to be
    // important.
    BranchProbability LayoutProb =
        MBPI->getEdgeProbability(LayoutPred, ChainBB);
    BlockFrequency LayoutEdgeFreq = MBFI->getBlockFreq(LayoutPred) * LayoutProb;
    if (LayoutEdgeFreq <= (Freq * ColdProb))
      ChainBB->setAlignment(Align);
  }
}

/// Tail duplicate \p BB into (some) predecessors if profitable, repeating if
/// it was duplicated into its chain predecessor and removed.
/// \p BB    - Basic block that may be duplicated.
///
/// \p LPred - Chosen layout predecessor of \p BB.
///            Updated to be the chain end if LPred is removed.
/// \p Chain - Chain to which \p LPred belongs, and \p BB will belong.
/// \p BlockFilter - Set of blocks that belong to the loop being laid out.
///                  Used to identify which blocks to update predecessor
///                  counts.
/// \p PrevUnplacedBlockIt - Iterator pointing to the last block that was
///                          chosen in the given order due to unnatural CFG
///                          only needed if \p BB is removed and
///                          \p PrevUnplacedBlockIt pointed to \p BB.
/// @return true if \p BB was removed.
bool MachineBlockPlacement::repeatedlyTailDuplicateBlock(
    MachineBasicBlock *BB, MachineBasicBlock *&LPred,
    const MachineBasicBlock *LoopHeaderBB,
    BlockChain &Chain, BlockFilterSet *BlockFilter,
    MachineFunction::iterator &PrevUnplacedBlockIt) {
  bool Removed, DuplicatedToLPred;
  bool DuplicatedToOriginalLPred;
  Removed = maybeTailDuplicateBlock(BB, LPred, Chain, BlockFilter,
                                    PrevUnplacedBlockIt,
                                    DuplicatedToLPred);
  if (!Removed)
    return false;
  DuplicatedToOriginalLPred = DuplicatedToLPred;
  // Iteratively try to duplicate again. It can happen that a block that is
  // duplicated into is still small enough to be duplicated again.
  // No need to call markBlockSuccessors in this case, as the blocks being
  // duplicated from here on are already scheduled.
  // Note that DuplicatedToLPred always implies Removed.
  while (DuplicatedToLPred) {
    assert (Removed && "Block must have been removed to be duplicated into its "
            "layout predecessor.");
    MachineBasicBlock *DupBB, *DupPred;
    // The removal callback causes Chain.end() to be updated when a block is
    // removed. On the first pass through the loop, the chain end should be the
    // same as it was on function entry. On subsequent passes, because we are
    // duplicating the block at the end of the chain, if it is removed the
    // chain will have shrunk by one block.
    BlockChain::iterator ChainEnd = Chain.end();
    DupBB = *(--ChainEnd);
    // Now try to duplicate again.
    if (ChainEnd == Chain.begin())
      break;
    DupPred = *std::prev(ChainEnd);
    Removed = maybeTailDuplicateBlock(DupBB, DupPred, Chain, BlockFilter,
                                      PrevUnplacedBlockIt,
                                      DuplicatedToLPred);
  }
  // If BB was duplicated into LPred, it is now scheduled. But because it was
  // removed, markChainSuccessors won't be called for its chain. Instead we
  // call markBlockSuccessors for LPred to achieve the same effect. This must go
  // at the end because repeating the tail duplication can increase the number
  // of unscheduled predecessors.
  LPred = *std::prev(Chain.end());
  if (DuplicatedToOriginalLPred)
    markBlockSuccessors(Chain, LPred, LoopHeaderBB, BlockFilter);
  return true;
}

/// Tail duplicate \p BB into (some) predecessors if profitable.
/// \p BB    - Basic block that may be duplicated
/// \p LPred - Chosen layout predecessor of \p BB
/// \p Chain - Chain to which \p LPred belongs, and \p BB will belong.
/// \p BlockFilter - Set of blocks that belong to the loop being laid out.
///                  Used to identify which blocks to update predecessor
///                  counts.
/// \p PrevUnplacedBlockIt - Iterator pointing to the last block that was
///                          chosen in the given order due to unnatural CFG
///                          only needed if \p BB is removed and
///                          \p PrevUnplacedBlockIt pointed to \p BB.
/// \p DuplicatedToLPred - True if the block was duplicated into LPred. Will
///                        only be true if the block was removed.
/// \return  - True if the block was duplicated into all preds and removed.
bool MachineBlockPlacement::maybeTailDuplicateBlock(
    MachineBasicBlock *BB, MachineBasicBlock *LPred,
    BlockChain &Chain, BlockFilterSet *BlockFilter,
    MachineFunction::iterator &PrevUnplacedBlockIt,
    bool &DuplicatedToLPred) {
  DuplicatedToLPred = false;
  if (!shouldTailDuplicate(BB))
    return false;

  DEBUG(dbgs() << "Redoing tail duplication for Succ#"
        << BB->getNumber() << "\n");

  // This has to be a callback because none of it can be done after
  // BB is deleted.
  bool Removed = false;
  auto RemovalCallback =
      [&](MachineBasicBlock *RemBB) {
        // Signal to outer function
        Removed = true;

        // Conservative default.
        bool InWorkList = true;
        // Remove from the Chain and Chain Map
        if (BlockToChain.count(RemBB)) {
          BlockChain *Chain = BlockToChain[RemBB];
          InWorkList = Chain->UnscheduledPredecessors == 0;
          Chain->remove(RemBB);
          BlockToChain.erase(RemBB);
        }

        // Handle the unplaced block iterator
        if (&(*PrevUnplacedBlockIt) == RemBB) {
          PrevUnplacedBlockIt++;
        }

        // Handle the Work Lists
        if (InWorkList) {
          SmallVectorImpl<MachineBasicBlock *> &RemoveList = BlockWorkList;
          if (RemBB->isEHPad())
            RemoveList = EHPadWorkList;
          RemoveList.erase(
              remove_if(RemoveList,
                        [RemBB](MachineBasicBlock *BB) {return BB == RemBB;}),
              RemoveList.end());
        }

        // Handle the filter set
        if (BlockFilter) {
          BlockFilter->remove(RemBB);
        }

        // Remove the block from loop info.
        MLI->removeBlock(RemBB);
        if (RemBB == PreferredLoopExit)
          PreferredLoopExit = nullptr;

        DEBUG(dbgs() << "TailDuplicator deleted block: "
              << getBlockName(RemBB) << "\n");
      };
  auto RemovalCallbackRef =
      llvm::function_ref<void(MachineBasicBlock*)>(RemovalCallback);

  SmallVector<MachineBasicBlock *, 8> DuplicatedPreds;
  bool IsSimple = TailDup.isSimpleBB(BB);
  TailDup.tailDuplicateAndUpdate(IsSimple, BB, LPred,
                                 &DuplicatedPreds, &RemovalCallbackRef);

  // Update UnscheduledPredecessors to reflect tail-duplication.
  DuplicatedToLPred = false;
  for (MachineBasicBlock *Pred : DuplicatedPreds) {
    // We're only looking for unscheduled predecessors that match the filter.
    BlockChain* PredChain = BlockToChain[Pred];
    if (Pred == LPred)
      DuplicatedToLPred = true;
    if (Pred == LPred || (BlockFilter && !BlockFilter->count(Pred))
        || PredChain == &Chain)
      continue;
    for (MachineBasicBlock *NewSucc : Pred->successors()) {
      if (BlockFilter && !BlockFilter->count(NewSucc))
        continue;
      BlockChain *NewChain = BlockToChain[NewSucc];
      if (NewChain != &Chain && NewChain != PredChain)
        NewChain->UnscheduledPredecessors++;
    }
  }
  return Removed;
}

bool MachineBlockPlacement::runOnMachineFunction(MachineFunction &MF) {
  if (skipFunction(*MF.getFunction()))
    return false;

  // Check for single-block functions and skip them.
  if (std::next(MF.begin()) == MF.end())
    return false;

  F = &MF;
  MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
  MBFI = llvm::make_unique<BranchFolder::MBFIWrapper>(
      getAnalysis<MachineBlockFrequencyInfo>());
  MLI = &getAnalysis<MachineLoopInfo>();
  TII = MF.getSubtarget().getInstrInfo();
  TLI = MF.getSubtarget().getTargetLowering();
  MDT = &getAnalysis<MachineDominatorTree>();
  MPDT = nullptr;

  // Initialize PreferredLoopExit to nullptr here since it may never be set if
  // there are no MachineLoops.
  PreferredLoopExit = nullptr;

  if (TailDupPlacement) {
    MPDT = &getAnalysis<MachinePostDominatorTree>();
    unsigned TailDupSize = TailDupPlacementThreshold;
    if (MF.getFunction()->optForSize())
      TailDupSize = 1;
    TailDup.initMF(MF, MBPI, /* LayoutMode */ true, TailDupSize);
  }

  assert(BlockToChain.empty());

  buildCFGChains();

  // Changing the layout can create new tail merging opportunities.
  TargetPassConfig *PassConfig = &getAnalysis<TargetPassConfig>();
  // TailMerge can create jump into if branches that make CFG irreducible for
  // HW that requires structured CFG.
  bool EnableTailMerge = !MF.getTarget().requiresStructuredCFG() &&
                         PassConfig->getEnableTailMerge() &&
                         BranchFoldPlacement;
  // No tail merging opportunities if the block number is less than four.
  if (MF.size() > 3 && EnableTailMerge) {
    unsigned TailMergeSize = TailDupPlacementThreshold + 1;
    BranchFolder BF(/*EnableTailMerge=*/true, /*CommonHoist=*/false, *MBFI,
                    *MBPI, TailMergeSize);

    if (BF.OptimizeFunction(MF, TII, MF.getSubtarget().getRegisterInfo(),
                            getAnalysisIfAvailable<MachineModuleInfo>(), MLI,
                            /*AfterBlockPlacement=*/true)) {
      // Redo the layout if tail merging creates/removes/moves blocks.
      BlockToChain.clear();
      // Must redo the dominator tree if blocks were changed.
      MDT->runOnMachineFunction(MF);
      if (MPDT)
        MPDT->runOnMachineFunction(MF);
      ChainAllocator.DestroyAll();
      buildCFGChains();
    }
  }

  optimizeBranches();
  alignBlocks();

  BlockToChain.clear();
  ChainAllocator.DestroyAll();

  if (AlignAllBlock)
    // Align all of the blocks in the function to a specific alignment.
    for (MachineBasicBlock &MBB : MF)
      MBB.setAlignment(AlignAllBlock);
  else if (AlignAllNonFallThruBlocks) {
    // Align all of the blocks that have no fall-through predecessors to a
    // specific alignment.
    for (auto MBI = std::next(MF.begin()), MBE = MF.end(); MBI != MBE; ++MBI) {
      auto LayoutPred = std::prev(MBI);
      if (!LayoutPred->isSuccessor(&*MBI))
        MBI->setAlignment(AlignAllNonFallThruBlocks);
    }
  }
  if (ViewBlockLayoutWithBFI != GVDT_None &&
      (ViewBlockFreqFuncName.empty() ||
       F->getFunction()->getName().equals(ViewBlockFreqFuncName))) {
    MBFI->view("MBP." + MF.getName(), false);
  }


  // We always return true as we have no way to track whether the final order
  // differs from the original order.
  return true;
}

namespace {
/// \brief A pass to compute block placement statistics.
///
/// A separate pass to compute interesting statistics for evaluating block
/// placement. This is separate from the actual placement pass so that they can
/// be computed in the absence of any placement transformations or when using
/// alternative placement strategies.
class MachineBlockPlacementStats : public MachineFunctionPass {
  /// \brief A handle to the branch probability pass.
  const MachineBranchProbabilityInfo *MBPI;

  /// \brief A handle to the function-wide block frequency pass.
  const MachineBlockFrequencyInfo *MBFI;

public:
  static char ID; // Pass identification, replacement for typeid
  MachineBlockPlacementStats() : MachineFunctionPass(ID) {
    initializeMachineBlockPlacementStatsPass(*PassRegistry::getPassRegistry());
  }

  bool runOnMachineFunction(MachineFunction &F) override;

  void getAnalysisUsage(AnalysisUsage &AU) const override {
    AU.addRequired<MachineBranchProbabilityInfo>();
    AU.addRequired<MachineBlockFrequencyInfo>();
    AU.setPreservesAll();
    MachineFunctionPass::getAnalysisUsage(AU);
  }
};
}

char MachineBlockPlacementStats::ID = 0;
char &llvm::MachineBlockPlacementStatsID = MachineBlockPlacementStats::ID;
INITIALIZE_PASS_BEGIN(MachineBlockPlacementStats, "block-placement-stats",
                      "Basic Block Placement Stats", false, false)
INITIALIZE_PASS_DEPENDENCY(MachineBranchProbabilityInfo)
INITIALIZE_PASS_DEPENDENCY(MachineBlockFrequencyInfo)
INITIALIZE_PASS_END(MachineBlockPlacementStats, "block-placement-stats",
                    "Basic Block Placement Stats", false, false)

bool MachineBlockPlacementStats::runOnMachineFunction(MachineFunction &F) {
  // Check for single-block functions and skip them.
  if (std::next(F.begin()) == F.end())
    return false;

  MBPI = &getAnalysis<MachineBranchProbabilityInfo>();
  MBFI = &getAnalysis<MachineBlockFrequencyInfo>();

  for (MachineBasicBlock &MBB : F) {
    BlockFrequency BlockFreq = MBFI->getBlockFreq(&MBB);
    Statistic &NumBranches =
        (MBB.succ_size() > 1) ? NumCondBranches : NumUncondBranches;
    Statistic &BranchTakenFreq =
        (MBB.succ_size() > 1) ? CondBranchTakenFreq : UncondBranchTakenFreq;
    for (MachineBasicBlock *Succ : MBB.successors()) {
      // Skip if this successor is a fallthrough.
      if (MBB.isLayoutSuccessor(Succ))
        continue;

      BlockFrequency EdgeFreq =
          BlockFreq * MBPI->getEdgeProbability(&MBB, Succ);
      ++NumBranches;
      BranchTakenFreq += EdgeFreq.getFrequency();
    }
  }

  return false;
}