llvm.org GIT mirror llvm / stable lib / Analysis / ConstantFolding.cpp
stable

Tree @stable (Download .tar.gz)

ConstantFolding.cpp @stableraw · 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
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
//===-- ConstantFolding.cpp - Fold instructions into constants ------------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file defines routines for folding instructions into constants.
//
// Also, to supplement the basic IR ConstantExpr simplifications,
// this file defines some additional folding routines that can make use of
// DataLayout information. These functions cannot go in IR due to library
// dependency issues.
//
//===----------------------------------------------------------------------===//

#include "llvm/Analysis/ConstantFolding.h"
#include "llvm/ADT/APFloat.h"
#include "llvm/ADT/APInt.h"
#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/ValueTracking.h"
#include "llvm/Config/config.h"
#include "llvm/IR/Constant.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Function.h"
#include "llvm/IR/GlobalValue.h"
#include "llvm/IR/GlobalVariable.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instruction.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Operator.h"
#include "llvm/IR/Type.h"
#include "llvm/IR/Value.h"
#include "llvm/Support/Casting.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/KnownBits.h"
#include "llvm/Support/MathExtras.h"
#include <cassert>
#include <cerrno>
#include <cfenv>
#include <cmath>
#include <cstddef>
#include <cstdint>

using namespace llvm;

namespace {

//===----------------------------------------------------------------------===//
// Constant Folding internal helper functions
//===----------------------------------------------------------------------===//

static Constant *foldConstVectorToAPInt(APInt &Result, Type *DestTy,
                                        Constant *C, Type *SrcEltTy,
                                        unsigned NumSrcElts,
                                        const DataLayout &DL) {
  // Now that we know that the input value is a vector of integers, just shift
  // and insert them into our result.
  unsigned BitShift = DL.getTypeSizeInBits(SrcEltTy);
  for (unsigned i = 0; i != NumSrcElts; ++i) {
    Constant *Element;
    if (DL.isLittleEndian())
      Element = C->getAggregateElement(NumSrcElts - i - 1);
    else
      Element = C->getAggregateElement(i);

    if (Element && isa<UndefValue>(Element)) {
      Result <<= BitShift;
      continue;
    }

    auto *ElementCI = dyn_cast_or_null<ConstantInt>(Element);
    if (!ElementCI)
      return ConstantExpr::getBitCast(C, DestTy);

    Result <<= BitShift;
    Result |= ElementCI->getValue().zextOrSelf(Result.getBitWidth());
  }

  return nullptr;
}

/// Constant fold bitcast, symbolically evaluating it with DataLayout.
/// This always returns a non-null constant, but it may be a
/// ConstantExpr if unfoldable.
Constant *FoldBitCast(Constant *C, Type *DestTy, const DataLayout &DL) {
  // Catch the obvious splat cases.
  if (C->isNullValue() && !DestTy->isX86_MMXTy())
    return Constant::getNullValue(DestTy);
  if (C->isAllOnesValue() && !DestTy->isX86_MMXTy() &&
      !DestTy->isPtrOrPtrVectorTy()) // Don't get ones for ptr types!
    return Constant::getAllOnesValue(DestTy);

  if (auto *VTy = dyn_cast<VectorType>(C->getType())) {
    // Handle a vector->scalar integer/fp cast.
    if (isa<IntegerType>(DestTy) || DestTy->isFloatingPointTy()) {
      unsigned NumSrcElts = VTy->getNumElements();
      Type *SrcEltTy = VTy->getElementType();

      // If the vector is a vector of floating point, convert it to vector of int
      // to simplify things.
      if (SrcEltTy->isFloatingPointTy()) {
        unsigned FPWidth = SrcEltTy->getPrimitiveSizeInBits();
        Type *SrcIVTy =
          VectorType::get(IntegerType::get(C->getContext(), FPWidth), NumSrcElts);
        // Ask IR to do the conversion now that #elts line up.
        C = ConstantExpr::getBitCast(C, SrcIVTy);
      }

      APInt Result(DL.getTypeSizeInBits(DestTy), 0);
      if (Constant *CE = foldConstVectorToAPInt(Result, DestTy, C,
                                                SrcEltTy, NumSrcElts, DL))
        return CE;

      if (isa<IntegerType>(DestTy))
        return ConstantInt::get(DestTy, Result);

      APFloat FP(DestTy->getFltSemantics(), Result);
      return ConstantFP::get(DestTy->getContext(), FP);
    }
  }

  // The code below only handles casts to vectors currently.
  auto *DestVTy = dyn_cast<VectorType>(DestTy);
  if (!DestVTy)
    return ConstantExpr::getBitCast(C, DestTy);

  // If this is a scalar -> vector cast, convert the input into a <1 x scalar>
  // vector so the code below can handle it uniformly.
  if (isa<ConstantFP>(C) || isa<ConstantInt>(C)) {
    Constant *Ops = C; // don't take the address of C!
    return FoldBitCast(ConstantVector::get(Ops), DestTy, DL);
  }

  // If this is a bitcast from constant vector -> vector, fold it.
  if (!isa<ConstantDataVector>(C) && !isa<ConstantVector>(C))
    return ConstantExpr::getBitCast(C, DestTy);

  // If the element types match, IR can fold it.
  unsigned NumDstElt = DestVTy->getNumElements();
  unsigned NumSrcElt = C->getType()->getVectorNumElements();
  if (NumDstElt == NumSrcElt)
    return ConstantExpr::getBitCast(C, DestTy);

  Type *SrcEltTy = C->getType()->getVectorElementType();
  Type *DstEltTy = DestVTy->getElementType();

  // Otherwise, we're changing the number of elements in a vector, which
  // requires endianness information to do the right thing.  For example,
  //    bitcast (<2 x i64> <i64 0, i64 1> to <4 x i32>)
  // folds to (little endian):
  //    <4 x i32> <i32 0, i32 0, i32 1, i32 0>
  // and to (big endian):
  //    <4 x i32> <i32 0, i32 0, i32 0, i32 1>

  // First thing is first.  We only want to think about integer here, so if
  // we have something in FP form, recast it as integer.
  if (DstEltTy->isFloatingPointTy()) {
    // Fold to an vector of integers with same size as our FP type.
    unsigned FPWidth = DstEltTy->getPrimitiveSizeInBits();
    Type *DestIVTy =
      VectorType::get(IntegerType::get(C->getContext(), FPWidth), NumDstElt);
    // Recursively handle this integer conversion, if possible.
    C = FoldBitCast(C, DestIVTy, DL);

    // Finally, IR can handle this now that #elts line up.
    return ConstantExpr::getBitCast(C, DestTy);
  }

  // Okay, we know the destination is integer, if the input is FP, convert
  // it to integer first.
  if (SrcEltTy->isFloatingPointTy()) {
    unsigned FPWidth = SrcEltTy->getPrimitiveSizeInBits();
    Type *SrcIVTy =
      VectorType::get(IntegerType::get(C->getContext(), FPWidth), NumSrcElt);
    // Ask IR to do the conversion now that #elts line up.
    C = ConstantExpr::getBitCast(C, SrcIVTy);
    // If IR wasn't able to fold it, bail out.
    if (!isa<ConstantVector>(C) &&  // FIXME: Remove ConstantVector.
        !isa<ConstantDataVector>(C))
      return C;
  }

  // Now we know that the input and output vectors are both integer vectors
  // of the same size, and that their #elements is not the same.  Do the
  // conversion here, which depends on whether the input or output has
  // more elements.
  bool isLittleEndian = DL.isLittleEndian();

  SmallVector<Constant*, 32> Result;
  if (NumDstElt < NumSrcElt) {
    // Handle: bitcast (<4 x i32> <i32 0, i32 1, i32 2, i32 3> to <2 x i64>)
    Constant *Zero = Constant::getNullValue(DstEltTy);
    unsigned Ratio = NumSrcElt/NumDstElt;
    unsigned SrcBitSize = SrcEltTy->getPrimitiveSizeInBits();
    unsigned SrcElt = 0;
    for (unsigned i = 0; i != NumDstElt; ++i) {
      // Build each element of the result.
      Constant *Elt = Zero;
      unsigned ShiftAmt = isLittleEndian ? 0 : SrcBitSize*(Ratio-1);
      for (unsigned j = 0; j != Ratio; ++j) {
        Constant *Src = C->getAggregateElement(SrcElt++);
        if (Src && isa<UndefValue>(Src))
          Src = Constant::getNullValue(C->getType()->getVectorElementType());
        else
          Src = dyn_cast_or_null<ConstantInt>(Src);
        if (!Src)  // Reject constantexpr elements.
          return ConstantExpr::getBitCast(C, DestTy);

        // Zero extend the element to the right size.
        Src = ConstantExpr::getZExt(Src, Elt->getType());

        // Shift it to the right place, depending on endianness.
        Src = ConstantExpr::getShl(Src,
                                   ConstantInt::get(Src->getType(), ShiftAmt));
        ShiftAmt += isLittleEndian ? SrcBitSize : -SrcBitSize;

        // Mix it in.
        Elt = ConstantExpr::getOr(Elt, Src);
      }
      Result.push_back(Elt);
    }
    return ConstantVector::get(Result);
  }

  // Handle: bitcast (<2 x i64> <i64 0, i64 1> to <4 x i32>)
  unsigned Ratio = NumDstElt/NumSrcElt;
  unsigned DstBitSize = DL.getTypeSizeInBits(DstEltTy);

  // Loop over each source value, expanding into multiple results.
  for (unsigned i = 0; i != NumSrcElt; ++i) {
    auto *Element = C->getAggregateElement(i);

    if (!Element) // Reject constantexpr elements.
      return ConstantExpr::getBitCast(C, DestTy);

    if (isa<UndefValue>(Element)) {
      // Correctly Propagate undef values.
      Result.append(Ratio, UndefValue::get(DstEltTy));
      continue;
    }

    auto *Src = dyn_cast<ConstantInt>(Element);
    if (!Src)
      return ConstantExpr::getBitCast(C, DestTy);

    unsigned ShiftAmt = isLittleEndian ? 0 : DstBitSize*(Ratio-1);
    for (unsigned j = 0; j != Ratio; ++j) {
      // Shift the piece of the value into the right place, depending on
      // endianness.
      Constant *Elt = ConstantExpr::getLShr(Src,
                                  ConstantInt::get(Src->getType(), ShiftAmt));
      ShiftAmt += isLittleEndian ? DstBitSize : -DstBitSize;

      // Truncate the element to an integer with the same pointer size and
      // convert the element back to a pointer using a inttoptr.
      if (DstEltTy->isPointerTy()) {
        IntegerType *DstIntTy = Type::getIntNTy(C->getContext(), DstBitSize);
        Constant *CE = ConstantExpr::getTrunc(Elt, DstIntTy);
        Result.push_back(ConstantExpr::getIntToPtr(CE, DstEltTy));
        continue;
      }

      // Truncate and remember this piece.
      Result.push_back(ConstantExpr::getTrunc(Elt, DstEltTy));
    }
  }

  return ConstantVector::get(Result);
}

} // end anonymous namespace

/// If this constant is a constant offset from a global, return the global and
/// the constant. Because of constantexprs, this function is recursive.
bool llvm::IsConstantOffsetFromGlobal(Constant *C, GlobalValue *&GV,
                                      APInt &Offset, const DataLayout &DL) {
  // Trivial case, constant is the global.
  if ((GV = dyn_cast<GlobalValue>(C))) {
    unsigned BitWidth = DL.getIndexTypeSizeInBits(GV->getType());
    Offset = APInt(BitWidth, 0);
    return true;
  }

  // Otherwise, if this isn't a constant expr, bail out.
  auto *CE = dyn_cast<ConstantExpr>(C);
  if (!CE) return false;

  // Look through ptr->int and ptr->ptr casts.
  if (CE->getOpcode() == Instruction::PtrToInt ||
      CE->getOpcode() == Instruction::BitCast)
    return IsConstantOffsetFromGlobal(CE->getOperand(0), GV, Offset, DL);

  // i32* getelementptr ([5 x i32]* @a, i32 0, i32 5)
  auto *GEP = dyn_cast<GEPOperator>(CE);
  if (!GEP)
    return false;

  unsigned BitWidth = DL.getIndexTypeSizeInBits(GEP->getType());
  APInt TmpOffset(BitWidth, 0);

  // If the base isn't a global+constant, we aren't either.
  if (!IsConstantOffsetFromGlobal(CE->getOperand(0), GV, TmpOffset, DL))
    return false;

  // Otherwise, add any offset that our operands provide.
  if (!GEP->accumulateConstantOffset(DL, TmpOffset))
    return false;

  Offset = TmpOffset;
  return true;
}

Constant *llvm::ConstantFoldLoadThroughBitcast(Constant *C, Type *DestTy,
                                         const DataLayout &DL) {
  do {
    Type *SrcTy = C->getType();

    // If the type sizes are the same and a cast is legal, just directly
    // cast the constant.
    if (DL.getTypeSizeInBits(DestTy) == DL.getTypeSizeInBits(SrcTy)) {
      Instruction::CastOps Cast = Instruction::BitCast;
      // If we are going from a pointer to int or vice versa, we spell the cast
      // differently.
      if (SrcTy->isIntegerTy() && DestTy->isPointerTy())
        Cast = Instruction::IntToPtr;
      else if (SrcTy->isPointerTy() && DestTy->isIntegerTy())
        Cast = Instruction::PtrToInt;

      if (CastInst::castIsValid(Cast, C, DestTy))
        return ConstantExpr::getCast(Cast, C, DestTy);
    }

    // If this isn't an aggregate type, there is nothing we can do to drill down
    // and find a bitcastable constant.
    if (!SrcTy->isAggregateType())
      return nullptr;

    // We're simulating a load through a pointer that was bitcast to point to
    // a different type, so we can try to walk down through the initial
    // elements of an aggregate to see if some part of the aggregate is
    // castable to implement the "load" semantic model.
    if (SrcTy->isStructTy()) {
      // Struct types might have leading zero-length elements like [0 x i32],
      // which are certainly not what we are looking for, so skip them.
      unsigned Elem = 0;
      Constant *ElemC;
      do {
        ElemC = C->getAggregateElement(Elem++);
      } while (ElemC && DL.getTypeSizeInBits(ElemC->getType()) == 0);
      C = ElemC;
    } else {
      C = C->getAggregateElement(0u);
    }
  } while (C);

  return nullptr;
}

namespace {

/// Recursive helper to read bits out of global. C is the constant being copied
/// out of. ByteOffset is an offset into C. CurPtr is the pointer to copy
/// results into and BytesLeft is the number of bytes left in
/// the CurPtr buffer. DL is the DataLayout.
bool ReadDataFromGlobal(Constant *C, uint64_t ByteOffset, unsigned char *CurPtr,
                        unsigned BytesLeft, const DataLayout &DL) {
  assert(ByteOffset <= DL.getTypeAllocSize(C->getType()) &&
         "Out of range access");

  // If this element is zero or undefined, we can just return since *CurPtr is
  // zero initialized.
  if (isa<ConstantAggregateZero>(C) || isa<UndefValue>(C))
    return true;

  if (auto *CI = dyn_cast<ConstantInt>(C)) {
    if (CI->getBitWidth() > 64 ||
        (CI->getBitWidth() & 7) != 0)
      return false;

    uint64_t Val = CI->getZExtValue();
    unsigned IntBytes = unsigned(CI->getBitWidth()/8);

    for (unsigned i = 0; i != BytesLeft && ByteOffset != IntBytes; ++i) {
      int n = ByteOffset;
      if (!DL.isLittleEndian())
        n = IntBytes - n - 1;
      CurPtr[i] = (unsigned char)(Val >> (n * 8));
      ++ByteOffset;
    }
    return true;
  }

  if (auto *CFP = dyn_cast<ConstantFP>(C)) {
    if (CFP->getType()->isDoubleTy()) {
      C = FoldBitCast(C, Type::getInt64Ty(C->getContext()), DL);
      return ReadDataFromGlobal(C, ByteOffset, CurPtr, BytesLeft, DL);
    }
    if (CFP->getType()->isFloatTy()){
      C = FoldBitCast(C, Type::getInt32Ty(C->getContext()), DL);
      return ReadDataFromGlobal(C, ByteOffset, CurPtr, BytesLeft, DL);
    }
    if (CFP->getType()->isHalfTy()){
      C = FoldBitCast(C, Type::getInt16Ty(C->getContext()), DL);
      return ReadDataFromGlobal(C, ByteOffset, CurPtr, BytesLeft, DL);
    }
    return false;
  }

  if (auto *CS = dyn_cast<ConstantStruct>(C)) {
    const StructLayout *SL = DL.getStructLayout(CS->getType());
    unsigned Index = SL->getElementContainingOffset(ByteOffset);
    uint64_t CurEltOffset = SL->getElementOffset(Index);
    ByteOffset -= CurEltOffset;

    while (true) {
      // If the element access is to the element itself and not to tail padding,
      // read the bytes from the element.
      uint64_t EltSize = DL.getTypeAllocSize(CS->getOperand(Index)->getType());

      if (ByteOffset < EltSize &&
          !ReadDataFromGlobal(CS->getOperand(Index), ByteOffset, CurPtr,
                              BytesLeft, DL))
        return false;

      ++Index;

      // Check to see if we read from the last struct element, if so we're done.
      if (Index == CS->getType()->getNumElements())
        return true;

      // If we read all of the bytes we needed from this element we're done.
      uint64_t NextEltOffset = SL->getElementOffset(Index);

      if (BytesLeft <= NextEltOffset - CurEltOffset - ByteOffset)
        return true;

      // Move to the next element of the struct.
      CurPtr += NextEltOffset - CurEltOffset - ByteOffset;
      BytesLeft -= NextEltOffset - CurEltOffset - ByteOffset;
      ByteOffset = 0;
      CurEltOffset = NextEltOffset;
    }
    // not reached.
  }

  if (isa<ConstantArray>(C) || isa<ConstantVector>(C) ||
      isa<ConstantDataSequential>(C)) {
    Type *EltTy = C->getType()->getSequentialElementType();
    uint64_t EltSize = DL.getTypeAllocSize(EltTy);
    uint64_t Index = ByteOffset / EltSize;
    uint64_t Offset = ByteOffset - Index * EltSize;
    uint64_t NumElts;
    if (auto *AT = dyn_cast<ArrayType>(C->getType()))
      NumElts = AT->getNumElements();
    else
      NumElts = C->getType()->getVectorNumElements();

    for (; Index != NumElts; ++Index) {
      if (!ReadDataFromGlobal(C->getAggregateElement(Index), Offset, CurPtr,
                              BytesLeft, DL))
        return false;

      uint64_t BytesWritten = EltSize - Offset;
      assert(BytesWritten <= EltSize && "Not indexing into this element?");
      if (BytesWritten >= BytesLeft)
        return true;

      Offset = 0;
      BytesLeft -= BytesWritten;
      CurPtr += BytesWritten;
    }
    return true;
  }

  if (auto *CE = dyn_cast<ConstantExpr>(C)) {
    if (CE->getOpcode() == Instruction::IntToPtr &&
        CE->getOperand(0)->getType() == DL.getIntPtrType(CE->getType())) {
      return ReadDataFromGlobal(CE->getOperand(0), ByteOffset, CurPtr,
                                BytesLeft, DL);
    }
  }

  // Otherwise, unknown initializer type.
  return false;
}

Constant *FoldReinterpretLoadFromConstPtr(Constant *C, Type *LoadTy,
                                          const DataLayout &DL) {
  auto *PTy = cast<PointerType>(C->getType());
  auto *IntType = dyn_cast<IntegerType>(LoadTy);

  // If this isn't an integer load we can't fold it directly.
  if (!IntType) {
    unsigned AS = PTy->getAddressSpace();

    // If this is a float/double load, we can try folding it as an int32/64 load
    // and then bitcast the result.  This can be useful for union cases.  Note
    // that address spaces don't matter here since we're not going to result in
    // an actual new load.
    Type *MapTy;
    if (LoadTy->isHalfTy())
      MapTy = Type::getInt16Ty(C->getContext());
    else if (LoadTy->isFloatTy())
      MapTy = Type::getInt32Ty(C->getContext());
    else if (LoadTy->isDoubleTy())
      MapTy = Type::getInt64Ty(C->getContext());
    else if (LoadTy->isVectorTy()) {
      MapTy = PointerType::getIntNTy(C->getContext(),
                                     DL.getTypeAllocSizeInBits(LoadTy));
    } else
      return nullptr;

    C = FoldBitCast(C, MapTy->getPointerTo(AS), DL);
    if (Constant *Res = FoldReinterpretLoadFromConstPtr(C, MapTy, DL))
      return FoldBitCast(Res, LoadTy, DL);
    return nullptr;
  }

  unsigned BytesLoaded = (IntType->getBitWidth() + 7) / 8;
  if (BytesLoaded > 32 || BytesLoaded == 0)
    return nullptr;

  GlobalValue *GVal;
  APInt OffsetAI;
  if (!IsConstantOffsetFromGlobal(C, GVal, OffsetAI, DL))
    return nullptr;

  auto *GV = dyn_cast<GlobalVariable>(GVal);
  if (!GV || !GV->isConstant() || !GV->hasDefinitiveInitializer() ||
      !GV->getInitializer()->getType()->isSized())
    return nullptr;

  int64_t Offset = OffsetAI.getSExtValue();
  int64_t InitializerSize = DL.getTypeAllocSize(GV->getInitializer()->getType());

  // If we're not accessing anything in this constant, the result is undefined.
  if (Offset + BytesLoaded <= 0)
    return UndefValue::get(IntType);

  // If we're not accessing anything in this constant, the result is undefined.
  if (Offset >= InitializerSize)
    return UndefValue::get(IntType);

  unsigned char RawBytes[32] = {0};
  unsigned char *CurPtr = RawBytes;
  unsigned BytesLeft = BytesLoaded;

  // If we're loading off the beginning of the global, some bytes may be valid.
  if (Offset < 0) {
    CurPtr += -Offset;
    BytesLeft += Offset;
    Offset = 0;
  }

  if (!ReadDataFromGlobal(GV->getInitializer(), Offset, CurPtr, BytesLeft, DL))
    return nullptr;

  APInt ResultVal = APInt(IntType->getBitWidth(), 0);
  if (DL.isLittleEndian()) {
    ResultVal = RawBytes[BytesLoaded - 1];
    for (unsigned i = 1; i != BytesLoaded; ++i) {
      ResultVal <<= 8;
      ResultVal |= RawBytes[BytesLoaded - 1 - i];
    }
  } else {
    ResultVal = RawBytes[0];
    for (unsigned i = 1; i != BytesLoaded; ++i) {
      ResultVal <<= 8;
      ResultVal |= RawBytes[i];
    }
  }

  return ConstantInt::get(IntType->getContext(), ResultVal);
}

Constant *ConstantFoldLoadThroughBitcastExpr(ConstantExpr *CE, Type *DestTy,
                                             const DataLayout &DL) {
  auto *SrcPtr = CE->getOperand(0);
  auto *SrcPtrTy = dyn_cast<PointerType>(SrcPtr->getType());
  if (!SrcPtrTy)
    return nullptr;
  Type *SrcTy = SrcPtrTy->getPointerElementType();

  Constant *C = ConstantFoldLoadFromConstPtr(SrcPtr, SrcTy, DL);
  if (!C)
    return nullptr;

  return llvm::ConstantFoldLoadThroughBitcast(C, DestTy, DL);
}

} // end anonymous namespace

Constant *llvm::ConstantFoldLoadFromConstPtr(Constant *C, Type *Ty,
                                             const DataLayout &DL) {
  // First, try the easy cases:
  if (auto *GV = dyn_cast<GlobalVariable>(C))
    if (GV->isConstant() && GV->hasDefinitiveInitializer())
      return GV->getInitializer();

  if (auto *GA = dyn_cast<GlobalAlias>(C))
    if (GA->getAliasee() && !GA->isInterposable())
      return ConstantFoldLoadFromConstPtr(GA->getAliasee(), Ty, DL);

  // If the loaded value isn't a constant expr, we can't handle it.
  auto *CE = dyn_cast<ConstantExpr>(C);
  if (!CE)
    return nullptr;

  if (CE->getOpcode() == Instruction::GetElementPtr) {
    if (auto *GV = dyn_cast<GlobalVariable>(CE->getOperand(0))) {
      if (GV->isConstant() && GV->hasDefinitiveInitializer()) {
        if (Constant *V =
             ConstantFoldLoadThroughGEPConstantExpr(GV->getInitializer(), CE))
          return V;
      }
    }
  }

  if (CE->getOpcode() == Instruction::BitCast)
    if (Constant *LoadedC = ConstantFoldLoadThroughBitcastExpr(CE, Ty, DL))
      return LoadedC;

  // Instead of loading constant c string, use corresponding integer value
  // directly if string length is small enough.
  StringRef Str;
  if (getConstantStringInfo(CE, Str) && !Str.empty()) {
    size_t StrLen = Str.size();
    unsigned NumBits = Ty->getPrimitiveSizeInBits();
    // Replace load with immediate integer if the result is an integer or fp
    // value.
    if ((NumBits >> 3) == StrLen + 1 && (NumBits & 7) == 0 &&
        (isa<IntegerType>(Ty) || Ty->isFloatingPointTy())) {
      APInt StrVal(NumBits, 0);
      APInt SingleChar(NumBits, 0);
      if (DL.isLittleEndian()) {
        for (unsigned char C : reverse(Str.bytes())) {
          SingleChar = static_cast<uint64_t>(C);
          StrVal = (StrVal << 8) | SingleChar;
        }
      } else {
        for (unsigned char C : Str.bytes()) {
          SingleChar = static_cast<uint64_t>(C);
          StrVal = (StrVal << 8) | SingleChar;
        }
        // Append NULL at the end.
        SingleChar = 0;
        StrVal = (StrVal << 8) | SingleChar;
      }

      Constant *Res = ConstantInt::get(CE->getContext(), StrVal);
      if (Ty->isFloatingPointTy())
        Res = ConstantExpr::getBitCast(Res, Ty);
      return Res;
    }
  }

  // If this load comes from anywhere in a constant global, and if the global
  // is all undef or zero, we know what it loads.
  if (auto *GV = dyn_cast<GlobalVariable>(GetUnderlyingObject(CE, DL))) {
    if (GV->isConstant() && GV->hasDefinitiveInitializer()) {
      if (GV->getInitializer()->isNullValue())
        return Constant::getNullValue(Ty);
      if (isa<UndefValue>(GV->getInitializer()))
        return UndefValue::get(Ty);
    }
  }

  // Try hard to fold loads from bitcasted strange and non-type-safe things.
  return FoldReinterpretLoadFromConstPtr(CE, Ty, DL);
}

namespace {

Constant *ConstantFoldLoadInst(const LoadInst *LI, const DataLayout &DL) {
  if (LI->isVolatile()) return nullptr;

  if (auto *C = dyn_cast<Constant>(LI->getOperand(0)))
    return ConstantFoldLoadFromConstPtr(C, LI->getType(), DL);

  return nullptr;
}

/// One of Op0/Op1 is a constant expression.
/// Attempt to symbolically evaluate the result of a binary operator merging
/// these together.  If target data info is available, it is provided as DL,
/// otherwise DL is null.
Constant *SymbolicallyEvaluateBinop(unsigned Opc, Constant *Op0, Constant *Op1,
                                    const DataLayout &DL) {
  // SROA

  // Fold (and 0xffffffff00000000, (shl x, 32)) -> shl.
  // Fold (lshr (or X, Y), 32) -> (lshr [X/Y], 32) if one doesn't contribute
  // bits.

  if (Opc == Instruction::And) {
    KnownBits Known0 = computeKnownBits(Op0, DL);
    KnownBits Known1 = computeKnownBits(Op1, DL);
    if ((Known1.One | Known0.Zero).isAllOnesValue()) {
      // All the bits of Op0 that the 'and' could be masking are already zero.
      return Op0;
    }
    if ((Known0.One | Known1.Zero).isAllOnesValue()) {
      // All the bits of Op1 that the 'and' could be masking are already zero.
      return Op1;
    }

    Known0.Zero |= Known1.Zero;
    Known0.One &= Known1.One;
    if (Known0.isConstant())
      return ConstantInt::get(Op0->getType(), Known0.getConstant());
  }

  // If the constant expr is something like &A[123] - &A[4].f, fold this into a
  // constant.  This happens frequently when iterating over a global array.
  if (Opc == Instruction::Sub) {
    GlobalValue *GV1, *GV2;
    APInt Offs1, Offs2;

    if (IsConstantOffsetFromGlobal(Op0, GV1, Offs1, DL))
      if (IsConstantOffsetFromGlobal(Op1, GV2, Offs2, DL) && GV1 == GV2) {
        unsigned OpSize = DL.getTypeSizeInBits(Op0->getType());

        // (&GV+C1) - (&GV+C2) -> C1-C2, pointer arithmetic cannot overflow.
        // PtrToInt may change the bitwidth so we have convert to the right size
        // first.
        return ConstantInt::get(Op0->getType(), Offs1.zextOrTrunc(OpSize) -
                                                Offs2.zextOrTrunc(OpSize));
      }
  }

  return nullptr;
}

/// If array indices are not pointer-sized integers, explicitly cast them so
/// that they aren't implicitly casted by the getelementptr.
Constant *CastGEPIndices(Type *SrcElemTy, ArrayRef<Constant *> Ops,
                         Type *ResultTy, Optional<unsigned> InRangeIndex,
                         const DataLayout &DL, const TargetLibraryInfo *TLI) {
  Type *IntPtrTy = DL.getIntPtrType(ResultTy);
  Type *IntPtrScalarTy = IntPtrTy->getScalarType();

  bool Any = false;
  SmallVector<Constant*, 32> NewIdxs;
  for (unsigned i = 1, e = Ops.size(); i != e; ++i) {
    if ((i == 1 ||
         !isa<StructType>(GetElementPtrInst::getIndexedType(
             SrcElemTy, Ops.slice(1, i - 1)))) &&
        Ops[i]->getType()->getScalarType() != IntPtrScalarTy) {
      Any = true;
      Type *NewType = Ops[i]->getType()->isVectorTy()
                          ? IntPtrTy
                          : IntPtrTy->getScalarType();
      NewIdxs.push_back(ConstantExpr::getCast(CastInst::getCastOpcode(Ops[i],
                                                                      true,
                                                                      NewType,
                                                                      true),
                                              Ops[i], NewType));
    } else
      NewIdxs.push_back(Ops[i]);
  }

  if (!Any)
    return nullptr;

  Constant *C = ConstantExpr::getGetElementPtr(
      SrcElemTy, Ops[0], NewIdxs, /*InBounds=*/false, InRangeIndex);
  if (Constant *Folded = ConstantFoldConstant(C, DL, TLI))
    C = Folded;

  return C;
}

/// Strip the pointer casts, but preserve the address space information.
Constant* StripPtrCastKeepAS(Constant* Ptr, Type *&ElemTy) {
  assert(Ptr->getType()->isPointerTy() && "Not a pointer type");
  auto *OldPtrTy = cast<PointerType>(Ptr->getType());
  Ptr = Ptr->stripPointerCasts();
  auto *NewPtrTy = cast<PointerType>(Ptr->getType());

  ElemTy = NewPtrTy->getPointerElementType();

  // Preserve the address space number of the pointer.
  if (NewPtrTy->getAddressSpace() != OldPtrTy->getAddressSpace()) {
    NewPtrTy = ElemTy->getPointerTo(OldPtrTy->getAddressSpace());
    Ptr = ConstantExpr::getPointerCast(Ptr, NewPtrTy);
  }
  return Ptr;
}

/// If we can symbolically evaluate the GEP constant expression, do so.
Constant *SymbolicallyEvaluateGEP(const GEPOperator *GEP,
                                  ArrayRef<Constant *> Ops,
                                  const DataLayout &DL,
                                  const TargetLibraryInfo *TLI) {
  const GEPOperator *InnermostGEP = GEP;
  bool InBounds = GEP->isInBounds();

  Type *SrcElemTy = GEP->getSourceElementType();
  Type *ResElemTy = GEP->getResultElementType();
  Type *ResTy = GEP->getType();
  if (!SrcElemTy->isSized())
    return nullptr;

  if (Constant *C = CastGEPIndices(SrcElemTy, Ops, ResTy,
                                   GEP->getInRangeIndex(), DL, TLI))
    return C;

  Constant *Ptr = Ops[0];
  if (!Ptr->getType()->isPointerTy())
    return nullptr;

  Type *IntPtrTy = DL.getIntPtrType(Ptr->getType());

  // If this is a constant expr gep that is effectively computing an
  // "offsetof", fold it into 'cast int Size to T*' instead of 'gep 0, 0, 12'
  for (unsigned i = 1, e = Ops.size(); i != e; ++i)
      if (!isa<ConstantInt>(Ops[i])) {

        // If this is "gep i8* Ptr, (sub 0, V)", fold this as:
        // "inttoptr (sub (ptrtoint Ptr), V)"
        if (Ops.size() == 2 && ResElemTy->isIntegerTy(8)) {
          auto *CE = dyn_cast<ConstantExpr>(Ops[1]);
          assert((!CE || CE->getType() == IntPtrTy) &&
                 "CastGEPIndices didn't canonicalize index types!");
          if (CE && CE->getOpcode() == Instruction::Sub &&
              CE->getOperand(0)->isNullValue()) {
            Constant *Res = ConstantExpr::getPtrToInt(Ptr, CE->getType());
            Res = ConstantExpr::getSub(Res, CE->getOperand(1));
            Res = ConstantExpr::getIntToPtr(Res, ResTy);
            if (auto *FoldedRes = ConstantFoldConstant(Res, DL, TLI))
              Res = FoldedRes;
            return Res;
          }
        }
        return nullptr;
      }

  unsigned BitWidth = DL.getTypeSizeInBits(IntPtrTy);
  APInt Offset =
      APInt(BitWidth,
            DL.getIndexedOffsetInType(
                SrcElemTy,
                makeArrayRef((Value * const *)Ops.data() + 1, Ops.size() - 1)));
  Ptr = StripPtrCastKeepAS(Ptr, SrcElemTy);

  // If this is a GEP of a GEP, fold it all into a single GEP.
  while (auto *GEP = dyn_cast<GEPOperator>(Ptr)) {
    InnermostGEP = GEP;
    InBounds &= GEP->isInBounds();

    SmallVector<Value *, 4> NestedOps(GEP->op_begin() + 1, GEP->op_end());

    // Do not try the incorporate the sub-GEP if some index is not a number.
    bool AllConstantInt = true;
    for (Value *NestedOp : NestedOps)
      if (!isa<ConstantInt>(NestedOp)) {
        AllConstantInt = false;
        break;
      }
    if (!AllConstantInt)
      break;

    Ptr = cast<Constant>(GEP->getOperand(0));
    SrcElemTy = GEP->getSourceElementType();
    Offset += APInt(BitWidth, DL.getIndexedOffsetInType(SrcElemTy, NestedOps));
    Ptr = StripPtrCastKeepAS(Ptr, SrcElemTy);
  }

  // If the base value for this address is a literal integer value, fold the
  // getelementptr to the resulting integer value casted to the pointer type.
  APInt BasePtr(BitWidth, 0);
  if (auto *CE = dyn_cast<ConstantExpr>(Ptr)) {
    if (CE->getOpcode() == Instruction::IntToPtr) {
      if (auto *Base = dyn_cast<ConstantInt>(CE->getOperand(0)))
        BasePtr = Base->getValue().zextOrTrunc(BitWidth);
    }
  }

  auto *PTy = cast<PointerType>(Ptr->getType());
  if ((Ptr->isNullValue() || BasePtr != 0) &&
      !DL.isNonIntegralPointerType(PTy)) {
    Constant *C = ConstantInt::get(Ptr->getContext(), Offset + BasePtr);
    return ConstantExpr::getIntToPtr(C, ResTy);
  }

  // Otherwise form a regular getelementptr. Recompute the indices so that
  // we eliminate over-indexing of the notional static type array bounds.
  // This makes it easy to determine if the getelementptr is "inbounds".
  // Also, this helps GlobalOpt do SROA on GlobalVariables.
  Type *Ty = PTy;
  SmallVector<Constant *, 32> NewIdxs;

  do {
    if (!Ty->isStructTy()) {
      if (Ty->isPointerTy()) {
        // The only pointer indexing we'll do is on the first index of the GEP.
        if (!NewIdxs.empty())
          break;

        Ty = SrcElemTy;

        // Only handle pointers to sized types, not pointers to functions.
        if (!Ty->isSized())
          return nullptr;
      } else if (auto *ATy = dyn_cast<SequentialType>(Ty)) {
        Ty = ATy->getElementType();
      } else {
        // We've reached some non-indexable type.
        break;
      }

      // Determine which element of the array the offset points into.
      APInt ElemSize(BitWidth, DL.getTypeAllocSize(Ty));
      if (ElemSize == 0) {
        // The element size is 0. This may be [0 x Ty]*, so just use a zero
        // index for this level and proceed to the next level to see if it can
        // accommodate the offset.
        NewIdxs.push_back(ConstantInt::get(IntPtrTy, 0));
      } else {
        // The element size is non-zero divide the offset by the element
        // size (rounding down), to compute the index at this level.
        bool Overflow;
        APInt NewIdx = Offset.sdiv_ov(ElemSize, Overflow);
        if (Overflow)
          break;
        Offset -= NewIdx * ElemSize;
        NewIdxs.push_back(ConstantInt::get(IntPtrTy, NewIdx));
      }
    } else {
      auto *STy = cast<StructType>(Ty);
      // If we end up with an offset that isn't valid for this struct type, we
      // can't re-form this GEP in a regular form, so bail out. The pointer
      // operand likely went through casts that are necessary to make the GEP
      // sensible.
      const StructLayout &SL = *DL.getStructLayout(STy);
      if (Offset.isNegative() || Offset.uge(SL.getSizeInBytes()))
        break;

      // Determine which field of the struct the offset points into. The
      // getZExtValue is fine as we've already ensured that the offset is
      // within the range representable by the StructLayout API.
      unsigned ElIdx = SL.getElementContainingOffset(Offset.getZExtValue());
      NewIdxs.push_back(ConstantInt::get(Type::getInt32Ty(Ty->getContext()),
                                         ElIdx));
      Offset -= APInt(BitWidth, SL.getElementOffset(ElIdx));
      Ty = STy->getTypeAtIndex(ElIdx);
    }
  } while (Ty != ResElemTy);

  // If we haven't used up the entire offset by descending the static
  // type, then the offset is pointing into the middle of an indivisible
  // member, so we can't simplify it.
  if (Offset != 0)
    return nullptr;

  // Preserve the inrange index from the innermost GEP if possible. We must
  // have calculated the same indices up to and including the inrange index.
  Optional<unsigned> InRangeIndex;
  if (Optional<unsigned> LastIRIndex = InnermostGEP->getInRangeIndex())
    if (SrcElemTy == InnermostGEP->getSourceElementType() &&
        NewIdxs.size() > *LastIRIndex) {
      InRangeIndex = LastIRIndex;
      for (unsigned I = 0; I <= *LastIRIndex; ++I)
        if (NewIdxs[I] != InnermostGEP->getOperand(I + 1))
          return nullptr;
    }

  // Create a GEP.
  Constant *C = ConstantExpr::getGetElementPtr(SrcElemTy, Ptr, NewIdxs,
                                               InBounds, InRangeIndex);
  assert(C->getType()->getPointerElementType() == Ty &&
         "Computed GetElementPtr has unexpected type!");

  // If we ended up indexing a member with a type that doesn't match
  // the type of what the original indices indexed, add a cast.
  if (Ty != ResElemTy)
    C = FoldBitCast(C, ResTy, DL);

  return C;
}

/// Attempt to constant fold an instruction with the
/// specified opcode and operands.  If successful, the constant result is
/// returned, if not, null is returned.  Note that this function can fail when
/// attempting to fold instructions like loads and stores, which have no
/// constant expression form.
Constant *ConstantFoldInstOperandsImpl(const Value *InstOrCE, unsigned Opcode,
                                       ArrayRef<Constant *> Ops,
                                       const DataLayout &DL,
                                       const TargetLibraryInfo *TLI) {
  Type *DestTy = InstOrCE->getType();

  if (Instruction::isUnaryOp(Opcode))
    return ConstantFoldUnaryOpOperand(Opcode, Ops[0], DL);

  if (Instruction::isBinaryOp(Opcode))
    return ConstantFoldBinaryOpOperands(Opcode, Ops[0], Ops[1], DL);

  if (Instruction::isCast(Opcode))
    return ConstantFoldCastOperand(Opcode, Ops[0], DestTy, DL);

  if (auto *GEP = dyn_cast<GEPOperator>(InstOrCE)) {
    if (Constant *C = SymbolicallyEvaluateGEP(GEP, Ops, DL, TLI))
      return C;

    return ConstantExpr::getGetElementPtr(GEP->getSourceElementType(), Ops[0],
                                          Ops.slice(1), GEP->isInBounds(),
                                          GEP->getInRangeIndex());
  }

  if (auto *CE = dyn_cast<ConstantExpr>(InstOrCE))
    return CE->getWithOperands(Ops);

  switch (Opcode) {
  default: return nullptr;
  case Instruction::ICmp:
  case Instruction::FCmp: llvm_unreachable("Invalid for compares");
  case Instruction::Call:
    if (auto *F = dyn_cast<Function>(Ops.back())) {
      const auto *Call = cast<CallBase>(InstOrCE);
      if (canConstantFoldCallTo(Call, F))
        return ConstantFoldCall(Call, F, Ops.slice(0, Ops.size() - 1), TLI);
    }
    return nullptr;
  case Instruction::Select:
    return ConstantExpr::getSelect(Ops[0], Ops[1], Ops[2]);
  case Instruction::ExtractElement:
    return ConstantExpr::getExtractElement(Ops[0], Ops[1]);
  case Instruction::InsertElement:
    return ConstantExpr::getInsertElement(Ops[0], Ops[1], Ops[2]);
  case Instruction::ShuffleVector:
    return ConstantExpr::getShuffleVector(Ops[0], Ops[1], Ops[2]);
  }
}

} // end anonymous namespace

//===----------------------------------------------------------------------===//
// Constant Folding public APIs
//===----------------------------------------------------------------------===//

namespace {

Constant *
ConstantFoldConstantImpl(const Constant *C, const DataLayout &DL,
                         const TargetLibraryInfo *TLI,
                         SmallDenseMap<Constant *, Constant *> &FoldedOps) {
  if (!isa<ConstantVector>(C) && !isa<ConstantExpr>(C))
    return nullptr;

  SmallVector<Constant *, 8> Ops;
  for (const Use &NewU : C->operands()) {
    auto *NewC = cast<Constant>(&NewU);
    // Recursively fold the ConstantExpr's operands. If we have already folded
    // a ConstantExpr, we don't have to process it again.
    if (isa<ConstantVector>(NewC) || isa<ConstantExpr>(NewC)) {
      auto It = FoldedOps.find(NewC);
      if (It == FoldedOps.end()) {
        if (auto *FoldedC =
                ConstantFoldConstantImpl(NewC, DL, TLI, FoldedOps)) {
          FoldedOps.insert({NewC, FoldedC});
          NewC = FoldedC;
        } else {
          FoldedOps.insert({NewC, NewC});
        }
      } else {
        NewC = It->second;
      }
    }
    Ops.push_back(NewC);
  }

  if (auto *CE = dyn_cast<ConstantExpr>(C)) {
    if (CE->isCompare())
      return ConstantFoldCompareInstOperands(CE->getPredicate(), Ops[0], Ops[1],
                                             DL, TLI);

    return ConstantFoldInstOperandsImpl(CE, CE->getOpcode(), Ops, DL, TLI);
  }

  assert(isa<ConstantVector>(C));
  return ConstantVector::get(Ops);
}

} // end anonymous namespace

Constant *llvm::ConstantFoldInstruction(Instruction *I, const DataLayout &DL,
                                        const TargetLibraryInfo *TLI) {
  // Handle PHI nodes quickly here...
  if (auto *PN = dyn_cast<PHINode>(I)) {
    Constant *CommonValue = nullptr;

    SmallDenseMap<Constant *, Constant *> FoldedOps;
    for (Value *Incoming : PN->incoming_values()) {
      // If the incoming value is undef then skip it.  Note that while we could
      // skip the value if it is equal to the phi node itself we choose not to
      // because that would break the rule that constant folding only applies if
      // all operands are constants.
      if (isa<UndefValue>(Incoming))
        continue;
      // If the incoming value is not a constant, then give up.
      auto *C = dyn_cast<Constant>(Incoming);
      if (!C)
        return nullptr;
      // Fold the PHI's operands.
      if (auto *FoldedC = ConstantFoldConstantImpl(C, DL, TLI, FoldedOps))
        C = FoldedC;
      // If the incoming value is a different constant to
      // the one we saw previously, then give up.
      if (CommonValue && C != CommonValue)
        return nullptr;
      CommonValue = C;
    }

    // If we reach here, all incoming values are the same constant or undef.
    return CommonValue ? CommonValue : UndefValue::get(PN->getType());
  }

  // Scan the operand list, checking to see if they are all constants, if so,
  // hand off to ConstantFoldInstOperandsImpl.
  if (!all_of(I->operands(), [](Use &U) { return isa<Constant>(U); }))
    return nullptr;

  SmallDenseMap<Constant *, Constant *> FoldedOps;
  SmallVector<Constant *, 8> Ops;
  for (const Use &OpU : I->operands()) {
    auto *Op = cast<Constant>(&OpU);
    // Fold the Instruction's operands.
    if (auto *FoldedOp = ConstantFoldConstantImpl(Op, DL, TLI, FoldedOps))
      Op = FoldedOp;

    Ops.push_back(Op);
  }

  if (const auto *CI = dyn_cast<CmpInst>(I))
    return ConstantFoldCompareInstOperands(CI->getPredicate(), Ops[0], Ops[1],
                                           DL, TLI);

  if (const auto *LI = dyn_cast<LoadInst>(I))
    return ConstantFoldLoadInst(LI, DL);

  if (auto *IVI = dyn_cast<InsertValueInst>(I)) {
    return ConstantExpr::getInsertValue(
                                cast<Constant>(IVI->getAggregateOperand()),
                                cast<Constant>(IVI->getInsertedValueOperand()),
                                IVI->getIndices());
  }

  if (auto *EVI = dyn_cast<ExtractValueInst>(I)) {
    return ConstantExpr::getExtractValue(
                                    cast<Constant>(EVI->getAggregateOperand()),
                                    EVI->getIndices());
  }

  return ConstantFoldInstOperands(I, Ops, DL, TLI);
}

Constant *llvm::ConstantFoldConstant(const Constant *C, const DataLayout &DL,
                                     const TargetLibraryInfo *TLI) {
  SmallDenseMap<Constant *, Constant *> FoldedOps;
  return ConstantFoldConstantImpl(C, DL, TLI, FoldedOps);
}

Constant *llvm::ConstantFoldInstOperands(Instruction *I,
                                         ArrayRef<Constant *> Ops,
                                         const DataLayout &DL,
                                         const TargetLibraryInfo *TLI) {
  return ConstantFoldInstOperandsImpl(I, I->getOpcode(), Ops, DL, TLI);
}

Constant *llvm::ConstantFoldCompareInstOperands(unsigned Predicate,
                                                Constant *Ops0, Constant *Ops1,
                                                const DataLayout &DL,
                                                const TargetLibraryInfo *TLI) {
  // fold: icmp (inttoptr x), null         -> icmp x, 0
  // fold: icmp null, (inttoptr x)         -> icmp 0, x
  // fold: icmp (ptrtoint x), 0            -> icmp x, null
  // fold: icmp 0, (ptrtoint x)            -> icmp null, x
  // fold: icmp (inttoptr x), (inttoptr y) -> icmp trunc/zext x, trunc/zext y
  // fold: icmp (ptrtoint x), (ptrtoint y) -> icmp x, y
  //
  // FIXME: The following comment is out of data and the DataLayout is here now.
  // ConstantExpr::getCompare cannot do this, because it doesn't have DL
  // around to know if bit truncation is happening.
  if (auto *CE0 = dyn_cast<ConstantExpr>(Ops0)) {
    if (Ops1->isNullValue()) {
      if (CE0->getOpcode() == Instruction::IntToPtr) {
        Type *IntPtrTy = DL.getIntPtrType(CE0->getType());
        // Convert the integer value to the right size to ensure we get the
        // proper extension or truncation.
        Constant *C = ConstantExpr::getIntegerCast(CE0->getOperand(0),
                                                   IntPtrTy, false);
        Constant *Null = Constant::getNullValue(C->getType());
        return ConstantFoldCompareInstOperands(Predicate, C, Null, DL, TLI);
      }

      // Only do this transformation if the int is intptrty in size, otherwise
      // there is a truncation or extension that we aren't modeling.
      if (CE0->getOpcode() == Instruction::PtrToInt) {
        Type *IntPtrTy = DL.getIntPtrType(CE0->getOperand(0)->getType());
        if (CE0->getType() == IntPtrTy) {
          Constant *C = CE0->getOperand(0);
          Constant *Null = Constant::getNullValue(C->getType());
          return ConstantFoldCompareInstOperands(Predicate, C, Null, DL, TLI);
        }
      }
    }

    if (auto *CE1 = dyn_cast<ConstantExpr>(Ops1)) {
      if (CE0->getOpcode() == CE1->getOpcode()) {
        if (CE0->getOpcode() == Instruction::IntToPtr) {
          Type *IntPtrTy = DL.getIntPtrType(CE0->getType());

          // Convert the integer value to the right size to ensure we get the
          // proper extension or truncation.
          Constant *C0 = ConstantExpr::getIntegerCast(CE0->getOperand(0),
                                                      IntPtrTy, false);
          Constant *C1 = ConstantExpr::getIntegerCast(CE1->getOperand(0),
                                                      IntPtrTy, false);
          return ConstantFoldCompareInstOperands(Predicate, C0, C1, DL, TLI);
        }

        // Only do this transformation if the int is intptrty in size, otherwise
        // there is a truncation or extension that we aren't modeling.
        if (CE0->getOpcode() == Instruction::PtrToInt) {
          Type *IntPtrTy = DL.getIntPtrType(CE0->getOperand(0)->getType());
          if (CE0->getType() == IntPtrTy &&
              CE0->getOperand(0)->getType() == CE1->getOperand(0)->getType()) {
            return ConstantFoldCompareInstOperands(
                Predicate, CE0->getOperand(0), CE1->getOperand(0), DL, TLI);
          }
        }
      }
    }

    // icmp eq (or x, y), 0 -> (icmp eq x, 0) & (icmp eq y, 0)
    // icmp ne (or x, y), 0 -> (icmp ne x, 0) | (icmp ne y, 0)
    if ((Predicate == ICmpInst::ICMP_EQ || Predicate == ICmpInst::ICMP_NE) &&
        CE0->getOpcode() == Instruction::Or && Ops1->isNullValue()) {
      Constant *LHS = ConstantFoldCompareInstOperands(
          Predicate, CE0->getOperand(0), Ops1, DL, TLI);
      Constant *RHS = ConstantFoldCompareInstOperands(
          Predicate, CE0->getOperand(1), Ops1, DL, TLI);
      unsigned OpC =
        Predicate == ICmpInst::ICMP_EQ ? Instruction::And : Instruction::Or;
      return ConstantFoldBinaryOpOperands(OpC, LHS, RHS, DL);
    }
  } else if (isa<ConstantExpr>(Ops1)) {
    // If RHS is a constant expression, but the left side isn't, swap the
    // operands and try again.
    Predicate = ICmpInst::getSwappedPredicate((ICmpInst::Predicate)Predicate);
    return ConstantFoldCompareInstOperands(Predicate, Ops1, Ops0, DL, TLI);
  }

  return ConstantExpr::getCompare(Predicate, Ops0, Ops1);
}

Constant *llvm::ConstantFoldUnaryOpOperand(unsigned Opcode, Constant *Op,
                                           const DataLayout &DL) {
  assert(Instruction::isUnaryOp(Opcode));

  return ConstantExpr::get(Opcode, Op);
}

Constant *llvm::ConstantFoldBinaryOpOperands(unsigned Opcode, Constant *LHS,
                                             Constant *RHS,
                                             const DataLayout &DL) {
  assert(Instruction::isBinaryOp(Opcode));
  if (isa<ConstantExpr>(LHS) || isa<ConstantExpr>(RHS))
    if (Constant *C = SymbolicallyEvaluateBinop(Opcode, LHS, RHS, DL))
      return C;

  return ConstantExpr::get(Opcode, LHS, RHS);
}

Constant *llvm::ConstantFoldCastOperand(unsigned Opcode, Constant *C,
                                        Type *DestTy, const DataLayout &DL) {
  assert(Instruction::isCast(Opcode));
  switch (Opcode) {
  default:
    llvm_unreachable("Missing case");
  case Instruction::PtrToInt:
    // If the input is a inttoptr, eliminate the pair.  This requires knowing
    // the width of a pointer, so it can't be done in ConstantExpr::getCast.
    if (auto *CE = dyn_cast<ConstantExpr>(C)) {
      if (CE->getOpcode() == Instruction::IntToPtr) {
        Constant *Input = CE->getOperand(0);
        unsigned InWidth = Input->getType()->getScalarSizeInBits();
        unsigned PtrWidth = DL.getPointerTypeSizeInBits(CE->getType());
        if (PtrWidth < InWidth) {
          Constant *Mask =
            ConstantInt::get(CE->getContext(),
                             APInt::getLowBitsSet(InWidth, PtrWidth));
          Input = ConstantExpr::getAnd(Input, Mask);
        }
        // Do a zext or trunc to get to the dest size.
        return ConstantExpr::getIntegerCast(Input, DestTy, false);
      }
    }
    return ConstantExpr::getCast(Opcode, C, DestTy);
  case Instruction::IntToPtr:
    // If the input is a ptrtoint, turn the pair into a ptr to ptr bitcast if
    // the int size is >= the ptr size and the address spaces are the same.
    // This requires knowing the width of a pointer, so it can't be done in
    // ConstantExpr::getCast.
    if (auto *CE = dyn_cast<ConstantExpr>(C)) {
      if (CE->getOpcode() == Instruction::PtrToInt) {
        Constant *SrcPtr = CE->getOperand(0);
        unsigned SrcPtrSize = DL.getPointerTypeSizeInBits(SrcPtr->getType());
        unsigned MidIntSize = CE->getType()->getScalarSizeInBits();

        if (MidIntSize >= SrcPtrSize) {
          unsigned SrcAS = SrcPtr->getType()->getPointerAddressSpace();
          if (SrcAS == DestTy->getPointerAddressSpace())
            return FoldBitCast(CE->getOperand(0), DestTy, DL);
        }
      }
    }

    return ConstantExpr::getCast(Opcode, C, DestTy);
  case Instruction::Trunc:
  case Instruction::ZExt:
  case Instruction::SExt:
  case Instruction::FPTrunc:
  case Instruction::FPExt:
  case Instruction::UIToFP:
  case Instruction::SIToFP:
  case Instruction::FPToUI:
  case Instruction::FPToSI:
  case Instruction::AddrSpaceCast:
      return ConstantExpr::getCast(Opcode, C, DestTy);
  case Instruction::BitCast:
    return FoldBitCast(C, DestTy, DL);
  }
}

Constant *llvm::ConstantFoldLoadThroughGEPConstantExpr(Constant *C,
                                                       ConstantExpr *CE) {
  if (!CE->getOperand(1)->isNullValue())
    return nullptr;  // Do not allow stepping over the value!

  // Loop over all of the operands, tracking down which value we are
  // addressing.
  for (unsigned i = 2, e = CE->getNumOperands(); i != e; ++i) {
    C = C->getAggregateElement(CE->getOperand(i));
    if (!C)
      return nullptr;
  }
  return C;
}

Constant *
llvm::ConstantFoldLoadThroughGEPIndices(Constant *C,
                                        ArrayRef<Constant *> Indices) {
  // Loop over all of the operands, tracking down which value we are
  // addressing.
  for (Constant *Index : Indices) {
    C = C->getAggregateElement(Index);
    if (!C)
      return nullptr;
  }
  return C;
}

//===----------------------------------------------------------------------===//
//  Constant Folding for Calls
//

bool llvm::canConstantFoldCallTo(const CallBase *Call, const Function *F) {
  if (Call->isNoBuiltin() || Call->isStrictFP())
    return false;
  switch (F->getIntrinsicID()) {
  case Intrinsic::fabs:
  case Intrinsic::minnum:
  case Intrinsic::maxnum:
  case Intrinsic::minimum:
  case Intrinsic::maximum:
  case Intrinsic::log:
  case Intrinsic::log2:
  case Intrinsic::log10:
  case Intrinsic::exp:
  case Intrinsic::exp2:
  case Intrinsic::floor:
  case Intrinsic::ceil:
  case Intrinsic::sqrt:
  case Intrinsic::sin:
  case Intrinsic::cos:
  case Intrinsic::trunc:
  case Intrinsic::rint:
  case Intrinsic::nearbyint:
  case Intrinsic::pow:
  case Intrinsic::powi:
  case Intrinsic::bswap:
  case Intrinsic::ctpop:
  case Intrinsic::ctlz:
  case Intrinsic::cttz:
  case Intrinsic::fshl:
  case Intrinsic::fshr:
  case Intrinsic::fma:
  case Intrinsic::fmuladd:
  case Intrinsic::copysign:
  case Intrinsic::launder_invariant_group:
  case Intrinsic::strip_invariant_group:
  case Intrinsic::round:
  case Intrinsic::masked_load:
  case Intrinsic::sadd_with_overflow:
  case Intrinsic::uadd_with_overflow:
  case Intrinsic::ssub_with_overflow:
  case Intrinsic::usub_with_overflow:
  case Intrinsic::smul_with_overflow:
  case Intrinsic::umul_with_overflow:
  case Intrinsic::sadd_sat:
  case Intrinsic::uadd_sat:
  case Intrinsic::ssub_sat:
  case Intrinsic::usub_sat:
  case Intrinsic::convert_from_fp16:
  case Intrinsic::convert_to_fp16:
  case Intrinsic::bitreverse:
  case Intrinsic::x86_sse_cvtss2si:
  case Intrinsic::x86_sse_cvtss2si64:
  case Intrinsic::x86_sse_cvttss2si:
  case Intrinsic::x86_sse_cvttss2si64:
  case Intrinsic::x86_sse2_cvtsd2si:
  case Intrinsic::x86_sse2_cvtsd2si64:
  case Intrinsic::x86_sse2_cvttsd2si:
  case Intrinsic::x86_sse2_cvttsd2si64:
  case Intrinsic::x86_avx512_vcvtss2si32:
  case Intrinsic::x86_avx512_vcvtss2si64:
  case Intrinsic::x86_avx512_cvttss2si:
  case Intrinsic::x86_avx512_cvttss2si64:
  case Intrinsic::x86_avx512_vcvtsd2si32:
  case Intrinsic::x86_avx512_vcvtsd2si64:
  case Intrinsic::x86_avx512_cvttsd2si:
  case Intrinsic::x86_avx512_cvttsd2si64:
  case Intrinsic::x86_avx512_vcvtss2usi32:
  case Intrinsic::x86_avx512_vcvtss2usi64:
  case Intrinsic::x86_avx512_cvttss2usi:
  case Intrinsic::x86_avx512_cvttss2usi64:
  case Intrinsic::x86_avx512_vcvtsd2usi32:
  case Intrinsic::x86_avx512_vcvtsd2usi64:
  case Intrinsic::x86_avx512_cvttsd2usi:
  case Intrinsic::x86_avx512_cvttsd2usi64:
  case Intrinsic::is_constant:
    return true;
  default:
    return false;
  case Intrinsic::not_intrinsic: break;
  }

  if (!F->hasName())
    return false;
  StringRef Name = F->getName();

  // In these cases, the check of the length is required.  We don't want to
  // return true for a name like "cos\0blah" which strcmp would return equal to
  // "cos", but has length 8.
  switch (Name[0]) {
  default:
    return false;
  case 'a':
    return Name == "acos" || Name == "asin" || Name == "atan" ||
           Name == "atan2" || Name == "acosf" || Name == "asinf" ||
           Name == "atanf" || Name == "atan2f";
  case 'c':
    return Name == "ceil" || Name == "cos" || Name == "cosh" ||
           Name == "ceilf" || Name == "cosf" || Name == "coshf";
  case 'e':
    return Name == "exp" || Name == "exp2" || Name == "expf" || Name == "exp2f";
  case 'f':
    return Name == "fabs" || Name == "floor" || Name == "fmod" ||
           Name == "fabsf" || Name == "floorf" || Name == "fmodf";
  case 'l':
    return Name == "log" || Name == "log10" || Name == "logf" ||
           Name == "log10f";
  case 'p':
    return Name == "pow" || Name == "powf";
  case 'r':
    return Name == "round" || Name == "roundf";
  case 's':
    return Name == "sin" || Name == "sinh" || Name == "sqrt" ||
           Name == "sinf" || Name == "sinhf" || Name == "sqrtf";
  case 't':
    return Name == "tan" || Name == "tanh" || Name == "tanf" || Name == "tanhf";
  case '_':

    // Check for various function names that get used for the math functions
    // when the header files are preprocessed with the macro
    // __FINITE_MATH_ONLY__ enabled.
    // The '12' here is the length of the shortest name that can match.
    // We need to check the size before looking at Name[1] and Name[2]
    // so we may as well check a limit that will eliminate mismatches.
    if (Name.size() < 12 || Name[1] != '_')
      return false;
    switch (Name[2]) {
    default:
      return false;
    case 'a':
      return Name == "__acos_finite" || Name == "__acosf_finite" ||
             Name == "__asin_finite" || Name == "__asinf_finite" ||
             Name == "__atan2_finite" || Name == "__atan2f_finite";
    case 'c':
      return Name == "__cosh_finite" || Name == "__coshf_finite";
    case 'e':
      return Name == "__exp_finite" || Name == "__expf_finite" ||
             Name == "__exp2_finite" || Name == "__exp2f_finite";
    case 'l':
      return Name == "__log_finite" || Name == "__logf_finite" ||
             Name == "__log10_finite" || Name == "__log10f_finite";
    case 'p':
      return Name == "__pow_finite" || Name == "__powf_finite";
    case 's':
      return Name == "__sinh_finite" || Name == "__sinhf_finite";
    }
  }
}

namespace {

Constant *GetConstantFoldFPValue(double V, Type *Ty) {
  if (Ty->isHalfTy() || Ty->isFloatTy()) {
    APFloat APF(V);
    bool unused;
    APF.convert(Ty->getFltSemantics(), APFloat::rmNearestTiesToEven, &unused);
    return ConstantFP::get(Ty->getContext(), APF);
  }
  if (Ty->isDoubleTy())
    return ConstantFP::get(Ty->getContext(), APFloat(V));
  llvm_unreachable("Can only constant fold half/float/double");
}

/// Clear the floating-point exception state.
inline void llvm_fenv_clearexcept() {
#if defined(HAVE_FENV_H) && HAVE_DECL_FE_ALL_EXCEPT
  feclearexcept(FE_ALL_EXCEPT);
#endif
  errno = 0;
}

/// Test if a floating-point exception was raised.
inline bool llvm_fenv_testexcept() {
  int errno_val = errno;
  if (errno_val == ERANGE || errno_val == EDOM)
    return true;
#if defined(HAVE_FENV_H) && HAVE_DECL_FE_ALL_EXCEPT && HAVE_DECL_FE_INEXACT
  if (fetestexcept(FE_ALL_EXCEPT & ~FE_INEXACT))
    return true;
#endif
  return false;
}

Constant *ConstantFoldFP(double (*NativeFP)(double), double V, Type *Ty) {
  llvm_fenv_clearexcept();
  V = NativeFP(V);
  if (llvm_fenv_testexcept()) {
    llvm_fenv_clearexcept();
    return nullptr;
  }

  return GetConstantFoldFPValue(V, Ty);
}

Constant *ConstantFoldBinaryFP(double (*NativeFP)(double, double), double V,
                               double W, Type *Ty) {
  llvm_fenv_clearexcept();
  V = NativeFP(V, W);
  if (llvm_fenv_testexcept()) {
    llvm_fenv_clearexcept();
    return nullptr;
  }

  return GetConstantFoldFPValue(V, Ty);
}

/// Attempt to fold an SSE floating point to integer conversion of a constant
/// floating point. If roundTowardZero is false, the default IEEE rounding is
/// used (toward nearest, ties to even). This matches the behavior of the
/// non-truncating SSE instructions in the default rounding mode. The desired
/// integer type Ty is used to select how many bits are available for the
/// result. Returns null if the conversion cannot be performed, otherwise
/// returns the Constant value resulting from the conversion.
Constant *ConstantFoldSSEConvertToInt(const APFloat &Val, bool roundTowardZero,
                                      Type *Ty, bool IsSigned) {
  // All of these conversion intrinsics form an integer of at most 64bits.
  unsigned ResultWidth = Ty->getIntegerBitWidth();
  assert(ResultWidth <= 64 &&
         "Can only constant fold conversions to 64 and 32 bit ints");

  uint64_t UIntVal;
  bool isExact = false;
  APFloat::roundingMode mode = roundTowardZero? APFloat::rmTowardZero
                                              : APFloat::rmNearestTiesToEven;
  APFloat::opStatus status =
      Val.convertToInteger(makeMutableArrayRef(UIntVal), ResultWidth,
                           IsSigned, mode, &isExact);
  if (status != APFloat::opOK &&
      (!roundTowardZero || status != APFloat::opInexact))
    return nullptr;
  return ConstantInt::get(Ty, UIntVal, IsSigned);
}

double getValueAsDouble(ConstantFP *Op) {
  Type *Ty = Op->getType();

  if (Ty->isFloatTy())
    return Op->getValueAPF().convertToFloat();

  if (Ty->isDoubleTy())
    return Op->getValueAPF().convertToDouble();

  bool unused;
  APFloat APF = Op->getValueAPF();
  APF.convert(APFloat::IEEEdouble(), APFloat::rmNearestTiesToEven, &unused);
  return APF.convertToDouble();
}

static bool isManifestConstant(const Constant *c) {
  if (isa<ConstantData>(c)) {
    return true;
  } else if (isa<ConstantAggregate>(c) || isa<ConstantExpr>(c)) {
    for (const Value *subc : c->operand_values()) {
      if (!isManifestConstant(cast<Constant>(subc)))
        return false;
    }
    return true;
  }
  return false;
}

static bool getConstIntOrUndef(Value *Op, const APInt *&C) {
  if (auto *CI = dyn_cast<ConstantInt>(Op)) {
    C = &CI->getValue();
    return true;
  }
  if (isa<UndefValue>(Op)) {
    C = nullptr;
    return true;
  }
  return false;
}

Constant *ConstantFoldScalarCall(StringRef Name, unsigned IntrinsicID, Type *Ty,
                                 ArrayRef<Constant *> Operands,
                                 const TargetLibraryInfo *TLI,
                                 const CallBase *Call) {
  if (Operands.size() == 1) {
    if (IntrinsicID == Intrinsic::is_constant) {
      // We know we have a "Constant" argument. But we want to only
      // return true for manifest constants, not those that depend on
      // constants with unknowable values, e.g. GlobalValue or BlockAddress.
      if (isManifestConstant(Operands[0]))
        return ConstantInt::getTrue(Ty->getContext());
      return nullptr;
    }
    if (isa<UndefValue>(Operands[0])) {
      // cosine(arg) is between -1 and 1. cosine(invalid arg) is NaN.
      // ctpop() is between 0 and bitwidth, pick 0 for undef.
      if (IntrinsicID == Intrinsic::cos ||
          IntrinsicID == Intrinsic::ctpop)
        return Constant::getNullValue(Ty);
      if (IntrinsicID == Intrinsic::bswap ||
          IntrinsicID == Intrinsic::bitreverse ||
          IntrinsicID == Intrinsic::launder_invariant_group ||
          IntrinsicID == Intrinsic::strip_invariant_group)
        return Operands[0];
    }

    if (isa<ConstantPointerNull>(Operands[0])) {
      // launder(null) == null == strip(null) iff in addrspace 0
      if (IntrinsicID == Intrinsic::launder_invariant_group ||
          IntrinsicID == Intrinsic::strip_invariant_group) {
        // If instruction is not yet put in a basic block (e.g. when cloning
        // a function during inlining), Call's caller may not be available.
        // So check Call's BB first before querying Call->getCaller.
        const Function *Caller =
            Call->getParent() ? Call->getCaller() : nullptr;
        if (Caller &&
            !NullPointerIsDefined(
                Caller, Operands[0]->getType()->getPointerAddressSpace())) {
          return Operands[0];
        }
        return nullptr;
      }
    }

    if (auto *Op = dyn_cast<ConstantFP>(Operands[0])) {
      if (IntrinsicID == Intrinsic::convert_to_fp16) {
        APFloat Val(Op->getValueAPF());

        bool lost = false;
        Val.convert(APFloat::IEEEhalf(), APFloat::rmNearestTiesToEven, &lost);

        return ConstantInt::get(Ty->getContext(), Val.bitcastToAPInt());
      }

      if (!Ty->isHalfTy() && !Ty->isFloatTy() && !Ty->isDoubleTy())
        return nullptr;

      if (IntrinsicID == Intrinsic::round) {
        APFloat V = Op->getValueAPF();
        V.roundToIntegral(APFloat::rmNearestTiesToAway);
        return ConstantFP::get(Ty->getContext(), V);
      }

      if (IntrinsicID == Intrinsic::floor) {
        APFloat V = Op->getValueAPF();
        V.roundToIntegral(APFloat::rmTowardNegative);
        return ConstantFP::get(Ty->getContext(), V);
      }

      if (IntrinsicID == Intrinsic::ceil) {
        APFloat V = Op->getValueAPF();
        V.roundToIntegral(APFloat::rmTowardPositive);
        return ConstantFP::get(Ty->getContext(), V);
      }

      if (IntrinsicID == Intrinsic::trunc) {
        APFloat V = Op->getValueAPF();
        V.roundToIntegral(APFloat::rmTowardZero);
        return ConstantFP::get(Ty->getContext(), V);
      }

      if (IntrinsicID == Intrinsic::rint) {
        APFloat V = Op->getValueAPF();
        V.roundToIntegral(APFloat::rmNearestTiesToEven);
        return ConstantFP::get(Ty->getContext(), V);
      }

      if (IntrinsicID == Intrinsic::nearbyint) {
        APFloat V = Op->getValueAPF();
        V.roundToIntegral(APFloat::rmNearestTiesToEven);
        return ConstantFP::get(Ty->getContext(), V);
      }

      /// We only fold functions with finite arguments. Folding NaN and inf is
      /// likely to be aborted with an exception anyway, and some host libms
      /// have known errors raising exceptions.
      if (Op->getValueAPF().isNaN() || Op->getValueAPF().isInfinity())
        return nullptr;

      /// Currently APFloat versions of these functions do not exist, so we use
      /// the host native double versions.  Float versions are not called
      /// directly but for all these it is true (float)(f((double)arg)) ==
      /// f(arg).  Long double not supported yet.
      double V = getValueAsDouble(Op);

      switch (IntrinsicID) {
        default: break;
        case Intrinsic::fabs:
          return ConstantFoldFP(fabs, V, Ty);
        case Intrinsic::log2:
          return ConstantFoldFP(Log2, V, Ty);
        case Intrinsic::log:
          return ConstantFoldFP(log, V, Ty);
        case Intrinsic::log10:
          return ConstantFoldFP(log10, V, Ty);
        case Intrinsic::exp:
          return ConstantFoldFP(exp, V, Ty);
        case Intrinsic::exp2:
          return ConstantFoldFP(exp2, V, Ty);
        case Intrinsic::sin:
          return ConstantFoldFP(sin, V, Ty);
        case Intrinsic::cos:
          return ConstantFoldFP(cos, V, Ty);
        case Intrinsic::sqrt:
          return ConstantFoldFP(sqrt, V, Ty);
      }

      if (!TLI)
        return nullptr;

      char NameKeyChar = Name[0];
      if (Name[0] == '_' && Name.size() > 2 && Name[1] == '_')
        NameKeyChar = Name[2];

      switch (NameKeyChar) {
      case 'a':
        if ((Name == "acos" && TLI->has(LibFunc_acos)) ||
            (Name == "acosf" && TLI->has(LibFunc_acosf)) ||
            (Name == "__acos_finite" && TLI->has(LibFunc_acos_finite)) ||
            (Name == "__acosf_finite" && TLI->has(LibFunc_acosf_finite)))
          return ConstantFoldFP(acos, V, Ty);
        else if ((Name == "asin" && TLI->has(LibFunc_asin)) ||
                 (Name == "asinf" && TLI->has(LibFunc_asinf)) ||
                 (Name == "__asin_finite" && TLI->has(LibFunc_asin_finite)) ||
                 (Name == "__asinf_finite" && TLI->has(LibFunc_asinf_finite)))
          return ConstantFoldFP(asin, V, Ty);
        else if ((Name == "atan" && TLI->has(LibFunc_atan)) ||
                 (Name == "atanf" && TLI->has(LibFunc_atanf)))
          return ConstantFoldFP(atan, V, Ty);
        break;
      case 'c':
        if ((Name == "ceil" && TLI->has(LibFunc_ceil)) ||
            (Name == "ceilf" && TLI->has(LibFunc_ceilf)))
          return ConstantFoldFP(ceil, V, Ty);
        else if ((Name == "cos" && TLI->has(LibFunc_cos)) ||
                 (Name == "cosf" && TLI->has(LibFunc_cosf)))
          return ConstantFoldFP(cos, V, Ty);
        else if ((Name == "cosh" && TLI->has(LibFunc_cosh)) ||
                 (Name == "coshf" && TLI->has(LibFunc_coshf)) ||
                 (Name == "__cosh_finite" && TLI->has(LibFunc_cosh_finite)) ||
                 (Name == "__coshf_finite" && TLI->has(LibFunc_coshf_finite)))
          return ConstantFoldFP(cosh, V, Ty);
        break;
      case 'e':
        if ((Name == "exp" && TLI->has(LibFunc_exp)) ||
            (Name == "expf" && TLI->has(LibFunc_expf)) ||
            (Name == "__exp_finite" && TLI->has(LibFunc_exp_finite)) ||
            (Name == "__expf_finite" && TLI->has(LibFunc_expf_finite)))
          return ConstantFoldFP(exp, V, Ty);
        if ((Name == "exp2" && TLI->has(LibFunc_exp2)) ||
            (Name == "exp2f" && TLI->has(LibFunc_exp2f)) ||
            (Name == "__exp2_finite" && TLI->has(LibFunc_exp2_finite)) ||
            (Name == "__exp2f_finite" && TLI->has(LibFunc_exp2f_finite)))
          // Constant fold exp2(x) as pow(2,x) in case the host doesn't have a
          // C99 library.
          return ConstantFoldBinaryFP(pow, 2.0, V, Ty);
        break;
      case 'f':
        if ((Name == "fabs" && TLI->has(LibFunc_fabs)) ||
            (Name == "fabsf" && TLI->has(LibFunc_fabsf)))
          return ConstantFoldFP(fabs, V, Ty);
        else if ((Name == "floor" && TLI->has(LibFunc_floor)) ||
                 (Name == "floorf" && TLI->has(LibFunc_floorf)))
          return ConstantFoldFP(floor, V, Ty);
        break;
      case 'l':
        if ((Name == "log" && V > 0 && TLI->has(LibFunc_log)) ||
            (Name == "logf" && V > 0 && TLI->has(LibFunc_logf)) ||
            (Name == "__log_finite" && V > 0 &&
              TLI->has(LibFunc_log_finite)) ||
            (Name == "__logf_finite" && V > 0 &&
              TLI->has(LibFunc_logf_finite)))
          return ConstantFoldFP(log, V, Ty);
        else if ((Name == "log10" && V > 0 && TLI->has(LibFunc_log10)) ||
                 (Name == "log10f" && V > 0 && TLI->has(LibFunc_log10f)) ||
                 (Name == "__log10_finite" && V > 0 &&
                   TLI->has(LibFunc_log10_finite)) ||
                 (Name == "__log10f_finite" && V > 0 &&
                   TLI->has(LibFunc_log10f_finite)))
          return ConstantFoldFP(log10, V, Ty);
        break;
      case 'r':
        if ((Name == "round" && TLI->has(LibFunc_round)) ||
            (Name == "roundf" && TLI->has(LibFunc_roundf)))
          return ConstantFoldFP(round, V, Ty);
        break;
      case 's':
        if ((Name == "sin" && TLI->has(LibFunc_sin)) ||
            (Name == "sinf" && TLI->has(LibFunc_sinf)))
          return ConstantFoldFP(sin, V, Ty);
        else if ((Name == "sinh" && TLI->has(LibFunc_sinh)) ||
                 (Name == "sinhf" && TLI->has(LibFunc_sinhf)) ||
                 (Name == "__sinh_finite" && TLI->has(LibFunc_sinh_finite)) ||
                 (Name == "__sinhf_finite" && TLI->has(LibFunc_sinhf_finite)))
          return ConstantFoldFP(sinh, V, Ty);
        else if ((Name == "sqrt" && V >= 0 && TLI->has(LibFunc_sqrt)) ||
                 (Name == "sqrtf" && V >= 0 && TLI->has(LibFunc_sqrtf)))
          return ConstantFoldFP(sqrt, V, Ty);
        break;
      case 't':
        if ((Name == "tan" && TLI->has(LibFunc_tan)) ||
            (Name == "tanf" && TLI->has(LibFunc_tanf)))
          return ConstantFoldFP(tan, V, Ty);
        else if ((Name == "tanh" && TLI->has(LibFunc_tanh)) ||
                 (Name == "tanhf" && TLI->has(LibFunc_tanhf)))
          return ConstantFoldFP(tanh, V, Ty);
        break;
      default:
        break;
      }
      return nullptr;
    }

    if (auto *Op = dyn_cast<ConstantInt>(Operands[0])) {
      switch (IntrinsicID) {
      case Intrinsic::bswap:
        return ConstantInt::get(Ty->getContext(), Op->getValue().byteSwap());
      case Intrinsic::ctpop:
        return ConstantInt::get(Ty, Op->getValue().countPopulation());
      case Intrinsic::bitreverse:
        return ConstantInt::get(Ty->getContext(), Op->getValue().reverseBits());
      case Intrinsic::convert_from_fp16: {
        APFloat Val(APFloat::IEEEhalf(), Op->getValue());

        bool lost = false;
        APFloat::opStatus status = Val.convert(
            Ty->getFltSemantics(), APFloat::rmNearestTiesToEven, &lost);

        // Conversion is always precise.
        (void)status;
        assert(status == APFloat::opOK && !lost &&
               "Precision lost during fp16 constfolding");

        return ConstantFP::get(Ty->getContext(), Val);
      }
      default:
        return nullptr;
      }
    }

    // Support ConstantVector in case we have an Undef in the top.
    if (isa<ConstantVector>(Operands[0]) ||
        isa<ConstantDataVector>(Operands[0])) {
      auto *Op = cast<Constant>(Operands[0]);
      switch (IntrinsicID) {
      default: break;
      case Intrinsic::x86_sse_cvtss2si:
      case Intrinsic::x86_sse_cvtss2si64:
      case Intrinsic::x86_sse2_cvtsd2si:
      case Intrinsic::x86_sse2_cvtsd2si64:
        if (ConstantFP *FPOp =
                dyn_cast_or_null<ConstantFP>(Op->getAggregateElement(0U)))
          return ConstantFoldSSEConvertToInt(FPOp->getValueAPF(),
                                             /*roundTowardZero=*/false, Ty,
                                             /*IsSigned*/true);
        break;
      case Intrinsic::x86_sse_cvttss2si:
      case Intrinsic::x86_sse_cvttss2si64:
      case Intrinsic::x86_sse2_cvttsd2si:
      case Intrinsic::x86_sse2_cvttsd2si64:
        if (ConstantFP *FPOp =
                dyn_cast_or_null<ConstantFP>(Op->getAggregateElement(0U)))
          return ConstantFoldSSEConvertToInt(FPOp->getValueAPF(),
                                             /*roundTowardZero=*/true, Ty,
                                             /*IsSigned*/true);
        break;
      }
    }

    return nullptr;
  }

  if (Operands.size() == 2) {
    if (auto *Op1 = dyn_cast<ConstantFP>(Operands[0])) {
      if (!Ty->isHalfTy() && !Ty->isFloatTy() && !Ty->isDoubleTy())
        return nullptr;
      double Op1V = getValueAsDouble(Op1);

      if (auto *Op2 = dyn_cast<ConstantFP>(Operands[1])) {
        if (Op2->getType() != Op1->getType())
          return nullptr;

        double Op2V = getValueAsDouble(Op2);
        if (IntrinsicID == Intrinsic::pow) {
          return ConstantFoldBinaryFP(pow, Op1V, Op2V, Ty);
        }
        if (IntrinsicID == Intrinsic::copysign) {
          APFloat V1 = Op1->getValueAPF();
          const APFloat &V2 = Op2->getValueAPF();
          V1.copySign(V2);
          return ConstantFP::get(Ty->getContext(), V1);
        }

        if (IntrinsicID == Intrinsic::minnum) {
          const APFloat &C1 = Op1->getValueAPF();
          const APFloat &C2 = Op2->getValueAPF();
          return ConstantFP::get(Ty->getContext(), minnum(C1, C2));
        }

        if (IntrinsicID == Intrinsic::maxnum) {
          const APFloat &C1 = Op1->getValueAPF();
          const APFloat &C2 = Op2->getValueAPF();
          return ConstantFP::get(Ty->getContext(), maxnum(C1, C2));
        }

        if (IntrinsicID == Intrinsic::minimum) {
          const APFloat &C1 = Op1->getValueAPF();
          const APFloat &C2 = Op2->getValueAPF();
          return ConstantFP::get(Ty->getContext(), minimum(C1, C2));
        }

        if (IntrinsicID == Intrinsic::maximum) {
          const APFloat &C1 = Op1->getValueAPF();
          const APFloat &C2 = Op2->getValueAPF();
          return ConstantFP::get(Ty->getContext(), maximum(C1, C2));
        }

        if (!TLI)
          return nullptr;
        if ((Name == "pow" && TLI->has(LibFunc_pow)) ||
            (Name == "powf" && TLI->has(LibFunc_powf)) ||
            (Name == "__pow_finite" && TLI->has(LibFunc_pow_finite)) ||
            (Name == "__powf_finite" && TLI->has(LibFunc_powf_finite)))
          return ConstantFoldBinaryFP(pow, Op1V, Op2V, Ty);
        if ((Name == "fmod" && TLI->has(LibFunc_fmod)) ||
            (Name == "fmodf" && TLI->has(LibFunc_fmodf)))
          return ConstantFoldBinaryFP(fmod, Op1V, Op2V, Ty);
        if ((Name == "atan2" && TLI->has(LibFunc_atan2)) ||
            (Name == "atan2f" && TLI->has(LibFunc_atan2f)) ||
            (Name == "__atan2_finite" && TLI->has(LibFunc_atan2_finite)) ||
            (Name == "__atan2f_finite" && TLI->has(LibFunc_atan2f_finite)))
          return ConstantFoldBinaryFP(atan2, Op1V, Op2V, Ty);
      } else if (auto *Op2C = dyn_cast<ConstantInt>(Operands[1])) {
        if (IntrinsicID == Intrinsic::powi && Ty->isHalfTy())
          return ConstantFP::get(Ty->getContext(),
                                 APFloat((float)std::pow((float)Op1V,
                                                 (int)Op2C->getZExtValue())));
        if (IntrinsicID == Intrinsic::powi && Ty->isFloatTy())
          return ConstantFP::get(Ty->getContext(),
                                 APFloat((float)std::pow((float)Op1V,
                                                 (int)Op2C->getZExtValue())));
        if (IntrinsicID == Intrinsic::powi && Ty->isDoubleTy())
          return ConstantFP::get(Ty->getContext(),
                                 APFloat((double)std::pow((double)Op1V,
                                                   (int)Op2C->getZExtValue())));
      }
      return nullptr;
    }

    if (Operands[0]->getType()->isIntegerTy() &&
        Operands[1]->getType()->isIntegerTy()) {
      const APInt *C0, *C1;
      if (!getConstIntOrUndef(Operands[0], C0) ||
          !getConstIntOrUndef(Operands[1], C1))
        return nullptr;

      switch (IntrinsicID) {
      default: break;
      case Intrinsic::smul_with_overflow:
      case Intrinsic::umul_with_overflow:
        // Even if both operands are undef, we cannot fold muls to undef
        // in the general case. For example, on i2 there are no inputs
        // that would produce { i2 -1, i1 true } as the result.
        if (!C0 || !C1)
          return Constant::getNullValue(Ty);
        LLVM_FALLTHROUGH;
      case Intrinsic::sadd_with_overflow:
      case Intrinsic::uadd_with_overflow:
      case Intrinsic::ssub_with_overflow:
      case Intrinsic::usub_with_overflow: {
        if (!C0 || !C1)
          return UndefValue::get(Ty);

        APInt Res;
        bool Overflow;
        switch (IntrinsicID) {
        default: llvm_unreachable("Invalid case");
        case Intrinsic::sadd_with_overflow:
          Res = C0->sadd_ov(*C1, Overflow);
          break;
        case Intrinsic::uadd_with_overflow:
          Res = C0->uadd_ov(*C1, Overflow);
          break;
        case Intrinsic::ssub_with_overflow:
          Res = C0->ssub_ov(*C1, Overflow);
          break;
        case Intrinsic::usub_with_overflow:
          Res = C0->usub_ov(*C1, Overflow);
          break;
        case Intrinsic::smul_with_overflow:
          Res = C0->smul_ov(*C1, Overflow);
          break;
        case Intrinsic::umul_with_overflow:
          Res = C0->umul_ov(*C1, Overflow);
          break;
        }
        Constant *Ops[] = {
          ConstantInt::get(Ty->getContext(), Res),
          ConstantInt::get(Type::getInt1Ty(Ty->getContext()), Overflow)
        };
        return ConstantStruct::get(cast<StructType>(Ty), Ops);
      }
      case Intrinsic::uadd_sat:
      case Intrinsic::sadd_sat:
        if (!C0 && !C1)
          return UndefValue::get(Ty);
        if (!C0 || !C1)
          return Constant::getAllOnesValue(Ty);
        if (IntrinsicID == Intrinsic::uadd_sat)
          return ConstantInt::get(Ty, C0->uadd_sat(*C1));
        else
          return ConstantInt::get(Ty, C0->sadd_sat(*C1));
      case Intrinsic::usub_sat:
      case Intrinsic::ssub_sat:
        if (!C0 && !C1)
          return UndefValue::get(Ty);
        if (!C0 || !C1)
          return Constant::getNullValue(Ty);
        if (IntrinsicID == Intrinsic::usub_sat)
          return ConstantInt::get(Ty, C0->usub_sat(*C1));
        else
          return ConstantInt::get(Ty, C0->ssub_sat(*C1));
      case Intrinsic::cttz:
      case Intrinsic::ctlz:
        assert(C1 && "Must be constant int");

        // cttz(0, 1) and ctlz(0, 1) are undef.
        if (C1->isOneValue() && (!C0 || C0->isNullValue()))
          return UndefValue::get(Ty);
        if (!C0)
          return Constant::getNullValue(Ty);
        if (IntrinsicID == Intrinsic::cttz)
          return ConstantInt::get(Ty, C0->countTrailingZeros());
        else
          return ConstantInt::get(Ty, C0->countLeadingZeros());
      }

      return nullptr;
    }

    // Support ConstantVector in case we have an Undef in the top.
    if ((isa<ConstantVector>(Operands[0]) ||
         isa<ConstantDataVector>(Operands[0])) &&
        // Check for default rounding mode.
        // FIXME: Support other rounding modes?
        isa<ConstantInt>(Operands[1]) &&
        cast<ConstantInt>(Operands[1])->getValue() == 4) {
      auto *Op = cast<Constant>(Operands[0]);
      switch (IntrinsicID) {
      default: break;
      case Intrinsic::x86_avx512_vcvtss2si32:
      case Intrinsic::x86_avx512_vcvtss2si64:
      case Intrinsic::x86_avx512_vcvtsd2si32:
      case Intrinsic::x86_avx512_vcvtsd2si64:
        if (ConstantFP *FPOp =
                dyn_cast_or_null<ConstantFP>(Op->getAggregateElement(0U)))
          return ConstantFoldSSEConvertToInt(FPOp->getValueAPF(),
                                             /*roundTowardZero=*/false, Ty,
                                             /*IsSigned*/true);
        break;
      case Intrinsic::x86_avx512_vcvtss2usi32:
      case Intrinsic::x86_avx512_vcvtss2usi64:
      case Intrinsic::x86_avx512_vcvtsd2usi32:
      case Intrinsic::x86_avx512_vcvtsd2usi64:
        if (ConstantFP *FPOp =
                dyn_cast_or_null<ConstantFP>(Op->getAggregateElement(0U)))
          return ConstantFoldSSEConvertToInt(FPOp->getValueAPF(),
                                             /*roundTowardZero=*/false, Ty,
                                             /*IsSigned*/false);
        break;
      case Intrinsic::x86_avx512_cvttss2si:
      case Intrinsic::x86_avx512_cvttss2si64:
      case Intrinsic::x86_avx512_cvttsd2si:
      case Intrinsic::x86_avx512_cvttsd2si64:
        if (ConstantFP *FPOp =
                dyn_cast_or_null<ConstantFP>(Op->getAggregateElement(0U)))
          return ConstantFoldSSEConvertToInt(FPOp->getValueAPF(),
                                             /*roundTowardZero=*/true, Ty,
                                             /*IsSigned*/true);
        break;
      case Intrinsic::x86_avx512_cvttss2usi:
      case Intrinsic::x86_avx512_cvttss2usi64:
      case Intrinsic::x86_avx512_cvttsd2usi:
      case Intrinsic::x86_avx512_cvttsd2usi64:
        if (ConstantFP *FPOp =
                dyn_cast_or_null<ConstantFP>(Op->getAggregateElement(0U)))
          return ConstantFoldSSEConvertToInt(FPOp->getValueAPF(),
                                             /*roundTowardZero=*/true, Ty,
                                             /*IsSigned*/false);
        break;
      }
    }
    return nullptr;
  }

  if (Operands.size() != 3)
    return nullptr;

  if (const auto *Op1 = dyn_cast<ConstantFP>(Operands[0])) {
    if (const auto *Op2 = dyn_cast<ConstantFP>(Operands[1])) {
      if (const auto *Op3 = dyn_cast<ConstantFP>(Operands[2])) {
        switch (IntrinsicID) {
        default: break;
        case Intrinsic::fma:
        case Intrinsic::fmuladd: {
          APFloat V = Op1->getValueAPF();
          APFloat::opStatus s = V.fusedMultiplyAdd(Op2->getValueAPF(),
                                                   Op3->getValueAPF(),
                                                   APFloat::rmNearestTiesToEven);
          if (s != APFloat::opInvalidOp)
            return ConstantFP::get(Ty->getContext(), V);

          return nullptr;
        }
        }
      }
    }
  }

  if (IntrinsicID == Intrinsic::fshl || IntrinsicID == Intrinsic::fshr) {
    const APInt *C0, *C1, *C2;
    if (!getConstIntOrUndef(Operands[0], C0) ||
        !getConstIntOrUndef(Operands[1], C1) ||
        !getConstIntOrUndef(Operands[2], C2))
      return nullptr;

    bool IsRight = IntrinsicID == Intrinsic::fshr;
    if (!C2)
      return Operands[IsRight ? 1 : 0];
    if (!C0 && !C1)
      return UndefValue::get(Ty);

    // The shift amount is interpreted as modulo the bitwidth. If the shift
    // amount is effectively 0, avoid UB due to oversized inverse shift below.
    unsigned BitWidth = C2->getBitWidth();
    unsigned ShAmt = C2->urem(BitWidth);
    if (!ShAmt)
      return Operands[IsRight ? 1 : 0];

    // (C0 << ShlAmt) | (C1 >> LshrAmt)
    unsigned LshrAmt = IsRight ? ShAmt : BitWidth - ShAmt;
    unsigned ShlAmt = !IsRight ? ShAmt : BitWidth - ShAmt;
    if (!C0)
      return ConstantInt::get(Ty, C1->lshr(LshrAmt));
    if (!C1)
      return ConstantInt::get(Ty, C0->shl(ShlAmt));
    return ConstantInt::get(Ty, C0->shl(ShlAmt) | C1->lshr(LshrAmt));
  }

  return nullptr;
}

Constant *ConstantFoldVectorCall(StringRef Name, unsigned IntrinsicID,
                                 VectorType *VTy, ArrayRef<Constant *> Operands,
                                 const DataLayout &DL,
                                 const TargetLibraryInfo *TLI,
                                 const CallBase *Call) {
  SmallVector<Constant *, 4> Result(VTy->getNumElements());
  SmallVector<Constant *, 4> Lane(Operands.size());
  Type *Ty = VTy->getElementType();

  if (IntrinsicID == Intrinsic::masked_load) {
    auto *SrcPtr = Operands[0];
    auto *Mask = Operands[2];
    auto *Passthru = Operands[3];

    Constant *VecData = ConstantFoldLoadFromConstPtr(SrcPtr, VTy, DL);

    SmallVector<Constant *, 32> NewElements;
    for (unsigned I = 0, E = VTy->getNumElements(); I != E; ++I) {
      auto *MaskElt = Mask->getAggregateElement(I);
      if (!MaskElt)
        break;
      auto *PassthruElt = Passthru->getAggregateElement(I);
      auto *VecElt = VecData ? VecData->getAggregateElement(I) : nullptr;
      if (isa<UndefValue>(MaskElt)) {
        if (PassthruElt)
          NewElements.push_back(PassthruElt);
        else if (VecElt)
          NewElements.push_back(VecElt);
        else
          return nullptr;
      }
      if (MaskElt->isNullValue()) {
        if (!PassthruElt)
          return nullptr;
        NewElements.push_back(PassthruElt);
      } else if (MaskElt->isOneValue()) {
        if (!VecElt)
          return nullptr;
        NewElements.push_back(VecElt);
      } else {
        return nullptr;
      }
    }
    if (NewElements.size() != VTy->getNumElements())
      return nullptr;
    return ConstantVector::get(NewElements);
  }

  for (unsigned I = 0, E = VTy->getNumElements(); I != E; ++I) {
    // Gather a column of constants.
    for (unsigned J = 0, JE = Operands.size(); J != JE; ++J) {
      // These intrinsics use a scalar type for their second argument.
      if (J == 1 &&
          (IntrinsicID == Intrinsic::cttz || IntrinsicID == Intrinsic::ctlz ||
           IntrinsicID == Intrinsic::powi)) {
        Lane[J] = Operands[J];
        continue;
      }

      Constant *Agg = Operands[J]->getAggregateElement(I);
      if (!Agg)
        return nullptr;

      Lane[J] = Agg;
    }

    // Use the regular scalar folding to simplify this column.
    Constant *Folded =
        ConstantFoldScalarCall(Name, IntrinsicID, Ty, Lane, TLI, Call);
    if (!Folded)
      return nullptr;
    Result[I] = Folded;
  }

  return ConstantVector::get(Result);
}

} // end anonymous namespace

Constant *llvm::ConstantFoldCall(const CallBase *Call, Function *F,
                                 ArrayRef<Constant *> Operands,
                                 const TargetLibraryInfo *TLI) {
  if (Call->isNoBuiltin() || Call->isStrictFP())
    return nullptr;
  if (!F->hasName())
    return nullptr;
  StringRef Name = F->getName();

  Type *Ty = F->getReturnType();

  if (auto *VTy = dyn_cast<VectorType>(Ty))
    return ConstantFoldVectorCall(Name, F->getIntrinsicID(), VTy, Operands,
                                  F->getParent()->getDataLayout(), TLI, Call);

  return ConstantFoldScalarCall(Name, F->getIntrinsicID(), Ty, Operands, TLI,
                                Call);
}

bool llvm::isMathLibCallNoop(const CallBase *Call,
                             const TargetLibraryInfo *TLI) {
  // FIXME: Refactor this code; this duplicates logic in LibCallsShrinkWrap
  // (and to some extent ConstantFoldScalarCall).
  if (Call->isNoBuiltin() || Call->isStrictFP())
    return false;
  Function *F = Call->getCalledFunction();
  if (!F)
    return false;

  LibFunc Func;
  if (!TLI || !TLI->getLibFunc(*F, Func))
    return false;

  if (Call->getNumArgOperands() == 1) {
    if (ConstantFP *OpC = dyn_cast<ConstantFP>(Call->getArgOperand(0))) {
      const APFloat &Op = OpC->getValueAPF();
      switch (Func) {
      case LibFunc_logl:
      case LibFunc_log:
      case LibFunc_logf:
      case LibFunc_log2l:
      case LibFunc_log2:
      case LibFunc_log2f:
      case LibFunc_log10l:
      case LibFunc_log10:
      case LibFunc_log10f:
        return Op.isNaN() || (!Op.isZero() && !Op.isNegative());

      case LibFunc_expl:
      case LibFunc_exp:
      case LibFunc_expf:
        // FIXME: These boundaries are slightly conservative.
        if (OpC->getType()->isDoubleTy())
          return Op.compare(APFloat(-745.0)) != APFloat::cmpLessThan &&
                 Op.compare(APFloat(709.0)) != APFloat::cmpGreaterThan;
        if (OpC->getType()->isFloatTy())
          return Op.compare(APFloat(-103.0f)) != APFloat::cmpLessThan &&
                 Op.compare(APFloat(88.0f)) != APFloat::cmpGreaterThan;
        break;

      case LibFunc_exp2l:
      case LibFunc_exp2:
      case LibFunc_exp2f:
        // FIXME: These boundaries are slightly conservative.
        if (OpC->getType()->isDoubleTy())
          return Op.compare(APFloat(-1074.0)) != APFloat::cmpLessThan &&
                 Op.compare(APFloat(1023.0)) != APFloat::cmpGreaterThan;
        if (OpC->getType()->isFloatTy())
          return Op.compare(APFloat(-149.0f)) != APFloat::cmpLessThan &&
                 Op.compare(APFloat(127.0f)) != APFloat::cmpGreaterThan;
        break;

      case LibFunc_sinl:
      case LibFunc_sin:
      case LibFunc_sinf:
      case LibFunc_cosl:
      case LibFunc_cos:
      case LibFunc_cosf:
        return !Op.isInfinity();

      case LibFunc_tanl:
      case LibFunc_tan:
      case LibFunc_tanf: {
        // FIXME: Stop using the host math library.
        // FIXME: The computation isn't done in the right precision.
        Type *Ty = OpC->getType();
        if (Ty->isDoubleTy() || Ty->isFloatTy() || Ty->isHalfTy()) {
          double OpV = getValueAsDouble(OpC);
          return ConstantFoldFP(tan, OpV, Ty) != nullptr;
        }
        break;
      }

      case LibFunc_asinl:
      case LibFunc_asin:
      case LibFunc_asinf:
      case LibFunc_acosl:
      case LibFunc_acos:
      case LibFunc_acosf:
        return Op.compare(APFloat(Op.getSemantics(), "-1")) !=
                   APFloat::cmpLessThan &&
               Op.compare(APFloat(Op.getSemantics(), "1")) !=
                   APFloat::cmpGreaterThan;

      case LibFunc_sinh:
      case LibFunc_cosh:
      case LibFunc_sinhf:
      case LibFunc_coshf:
      case LibFunc_sinhl:
      case LibFunc_coshl:
        // FIXME: These boundaries are slightly conservative.
        if (OpC->getType()->isDoubleTy())
          return Op.compare(APFloat(-710.0)) != APFloat::cmpLessThan &&
                 Op.compare(APFloat(710.0)) != APFloat::cmpGreaterThan;
        if (OpC->getType()->isFloatTy())
          return Op.compare(APFloat(-89.0f)) != APFloat::cmpLessThan &&
                 Op.compare(APFloat(89.0f)) != APFloat::cmpGreaterThan;
        break;

      case LibFunc_sqrtl:
      case LibFunc_sqrt:
      case LibFunc_sqrtf:
        return Op.isNaN() || Op.isZero() || !Op.isNegative();

      // FIXME: Add more functions: sqrt_finite, atanh, expm1, log1p,
      // maybe others?
      default:
        break;
      }
    }
  }

  if (Call->getNumArgOperands() == 2) {
    ConstantFP *Op0C = dyn_cast<ConstantFP>(Call->getArgOperand(0));
    ConstantFP *Op1C = dyn_cast<ConstantFP>(Call->getArgOperand(1));
    if (Op0C && Op1C) {
      const APFloat &Op0 = Op0C->getValueAPF();
      const APFloat &Op1 = Op1C->getValueAPF();

      switch (Func) {
      case LibFunc_powl:
      case LibFunc_pow:
      case LibFunc_powf: {
        // FIXME: Stop using the host math library.
        // FIXME: The computation isn't done in the right precision.
        Type *Ty = Op0C->getType();
        if (Ty->isDoubleTy() || Ty->isFloatTy() || Ty->isHalfTy()) {
          if (Ty == Op1C->getType()) {
            double Op0V = getValueAsDouble(Op0C);
            double Op1V = getValueAsDouble(Op1C);
            return ConstantFoldBinaryFP(pow, Op0V, Op1V, Ty) != nullptr;
          }
        }
        break;
      }

      case LibFunc_fmodl:
      case LibFunc_fmod:
      case LibFunc_fmodf:
        return Op0.isNaN() || Op1.isNaN() ||
               (!Op0.isInfinity() && !Op1.isZero());

      default:
        break;
      }
    }
  }

  return false;
}