llvm.org GIT mirror llvm / release_26 lib / Target / X86 / X86Instr64bit.td
release_26

Tree @release_26 (Download .tar.gz)

X86Instr64bit.td @release_26raw · 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
//====- X86Instr64bit.td - Describe X86-64 Instructions ----*- tablegen -*-===//
// 
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
// 
//===----------------------------------------------------------------------===//
//
// This file describes the X86-64 instruction set, defining the instructions,
// and properties of the instructions which are needed for code generation,
// machine code emission, and analysis.
//
//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//
// Operand Definitions.
//

// 64-bits but only 32 bits are significant.
def i64i32imm  : Operand<i64>;

// 64-bits but only 32 bits are significant, and those bits are treated as being
// pc relative.
def i64i32imm_pcrel : Operand<i64> {
  let PrintMethod = "print_pcrel_imm";
}


// 64-bits but only 8 bits are significant.
def i64i8imm   : Operand<i64> {
  let ParserMatchClass = ImmSExt8AsmOperand;
}

def lea64mem : Operand<i64> {
  let PrintMethod = "printlea64mem";
  let MIOperandInfo = (ops GR64, i8imm, GR64_NOSP, i32imm);
  let ParserMatchClass = X86MemAsmOperand;
}

def lea64_32mem : Operand<i32> {
  let PrintMethod = "printlea64_32mem";
  let AsmOperandLowerMethod = "lower_lea64_32mem";
  let MIOperandInfo = (ops GR32, i8imm, GR32_NOSP, i32imm);
  let ParserMatchClass = X86MemAsmOperand;
}

//===----------------------------------------------------------------------===//
// Complex Pattern Definitions.
//
def lea64addr : ComplexPattern<i64, 4, "SelectLEAAddr",
                        [add, sub, mul, X86mul_imm, shl, or, frameindex,
                         X86WrapperRIP], []>;

def tls64addr : ComplexPattern<i64, 4, "SelectTLSADDRAddr",
                               [tglobaltlsaddr], []>;

//===----------------------------------------------------------------------===//
// Pattern fragments.
//

def i64immSExt8  : PatLeaf<(i64 imm), [{
  // i64immSExt8 predicate - True if the 64-bit immediate fits in a 8-bit
  // sign extended field.
  return (int64_t)N->getZExtValue() == (int8_t)N->getZExtValue();
}]>;

def i64immSExt32  : PatLeaf<(i64 imm), [{
  // i64immSExt32 predicate - True if the 64-bit immediate fits in a 32-bit
  // sign extended field.
  return (int64_t)N->getZExtValue() == (int32_t)N->getZExtValue();
}]>;

def i64immZExt32  : PatLeaf<(i64 imm), [{
  // i64immZExt32 predicate - True if the 64-bit immediate fits in a 32-bit
  // unsignedsign extended field.
  return (uint64_t)N->getZExtValue() == (uint32_t)N->getZExtValue();
}]>;

def sextloadi64i8  : PatFrag<(ops node:$ptr), (i64 (sextloadi8 node:$ptr))>;
def sextloadi64i16 : PatFrag<(ops node:$ptr), (i64 (sextloadi16 node:$ptr))>;
def sextloadi64i32 : PatFrag<(ops node:$ptr), (i64 (sextloadi32 node:$ptr))>;

def zextloadi64i1  : PatFrag<(ops node:$ptr), (i64 (zextloadi1 node:$ptr))>;
def zextloadi64i8  : PatFrag<(ops node:$ptr), (i64 (zextloadi8 node:$ptr))>;
def zextloadi64i16 : PatFrag<(ops node:$ptr), (i64 (zextloadi16 node:$ptr))>;
def zextloadi64i32 : PatFrag<(ops node:$ptr), (i64 (zextloadi32 node:$ptr))>;

def extloadi64i1   : PatFrag<(ops node:$ptr), (i64 (extloadi1 node:$ptr))>;
def extloadi64i8   : PatFrag<(ops node:$ptr), (i64 (extloadi8 node:$ptr))>;
def extloadi64i16  : PatFrag<(ops node:$ptr), (i64 (extloadi16 node:$ptr))>;
def extloadi64i32  : PatFrag<(ops node:$ptr), (i64 (extloadi32 node:$ptr))>;

//===----------------------------------------------------------------------===//
// Instruction list...
//

// ADJCALLSTACKDOWN/UP implicitly use/def RSP because they may be expanded into
// a stack adjustment and the codegen must know that they may modify the stack
// pointer before prolog-epilog rewriting occurs.
// Pessimistically assume ADJCALLSTACKDOWN / ADJCALLSTACKUP will become
// sub / add which can clobber EFLAGS.
let Defs = [RSP, EFLAGS], Uses = [RSP] in {
def ADJCALLSTACKDOWN64 : I<0, Pseudo, (outs), (ins i32imm:$amt),
                           "#ADJCALLSTACKDOWN",
                           [(X86callseq_start timm:$amt)]>,
                          Requires<[In64BitMode]>;
def ADJCALLSTACKUP64   : I<0, Pseudo, (outs), (ins i32imm:$amt1, i32imm:$amt2),
                           "#ADJCALLSTACKUP",
                           [(X86callseq_end timm:$amt1, timm:$amt2)]>,
                          Requires<[In64BitMode]>;
}

//===----------------------------------------------------------------------===//
//  Call Instructions...
//
let isCall = 1 in
  // All calls clobber the non-callee saved registers. RSP is marked as
  // a use to prevent stack-pointer assignments that appear immediately
  // before calls from potentially appearing dead. Uses for argument
  // registers are added manually.
  let Defs = [RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11,
              FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
              MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
              XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
              XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
      Uses = [RSP] in {
      
    // NOTE: this pattern doesn't match "X86call imm", because we do not know
    // that the offset between an arbitrary immediate and the call will fit in
    // the 32-bit pcrel field that we have.
    def CALL64pcrel32 : Ii32<0xE8, RawFrm,
                          (outs), (ins i64i32imm_pcrel:$dst, variable_ops),
                          "call\t$dst", []>,
                        Requires<[In64BitMode, NotWin64]>;
    def CALL64r       : I<0xFF, MRM2r, (outs), (ins GR64:$dst, variable_ops),
                          "call\t{*}$dst", [(X86call GR64:$dst)]>,
                        Requires<[NotWin64]>;
    def CALL64m       : I<0xFF, MRM2m, (outs), (ins i64mem:$dst, variable_ops),
                          "call\t{*}$dst", [(X86call (loadi64 addr:$dst))]>,
                        Requires<[NotWin64]>;
  }

  // FIXME: We need to teach codegen about single list of call-clobbered registers.
let isCall = 1 in
  // All calls clobber the non-callee saved registers. RSP is marked as
  // a use to prevent stack-pointer assignments that appear immediately
  // before calls from potentially appearing dead. Uses for argument
  // registers are added manually.
  let Defs = [RAX, RCX, RDX, R8, R9, R10, R11,
              FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
              MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
              XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, EFLAGS],
      Uses = [RSP] in {
    def WINCALL64pcrel32 : I<0xE8, RawFrm,
                             (outs), (ins i64i32imm_pcrel:$dst, variable_ops),
                             "call\t$dst", []>,
                           Requires<[IsWin64]>;
    def WINCALL64r       : I<0xFF, MRM2r, (outs), (ins GR64:$dst, variable_ops),
                             "call\t{*}$dst",
                             [(X86call GR64:$dst)]>, Requires<[IsWin64]>;
    def WINCALL64m       : I<0xFF, MRM2m, (outs), (ins i64mem:$dst, variable_ops),
                             "call\t{*}$dst",
                             [(X86call (loadi64 addr:$dst))]>, Requires<[IsWin64]>;
  }


let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
def TCRETURNdi64 : I<0, Pseudo, (outs), (ins i64imm:$dst, i32imm:$offset,
                                         variable_ops),
                 "#TC_RETURN $dst $offset",
                 []>;

let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
def TCRETURNri64 : I<0, Pseudo, (outs), (ins GR64:$dst, i32imm:$offset,
                                         variable_ops),
                 "#TC_RETURN $dst $offset",
                 []>;


let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1 in
  def TAILJMPr64 : I<0xFF, MRM4r, (outs), (ins GR64:$dst),
                   "jmp{q}\t{*}$dst  # TAILCALL",
                   []>;     

// Branches
let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1 in {
  def JMP64r     : I<0xFF, MRM4r, (outs), (ins GR64:$dst), "jmp{q}\t{*}$dst",
                     [(brind GR64:$dst)]>;
  def JMP64m     : I<0xFF, MRM4m, (outs), (ins i64mem:$dst), "jmp{q}\t{*}$dst",
                     [(brind (loadi64 addr:$dst))]>;
}

//===----------------------------------------------------------------------===//
// EH Pseudo Instructions
//
let isTerminator = 1, isReturn = 1, isBarrier = 1,
    hasCtrlDep = 1 in {
def EH_RETURN64   : I<0xC3, RawFrm, (outs), (ins GR64:$addr),
                     "ret\t#eh_return, addr: $addr",
                     [(X86ehret GR64:$addr)]>;

}

//===----------------------------------------------------------------------===//
//  Miscellaneous Instructions...
//
let Defs = [RBP,RSP], Uses = [RBP,RSP], mayLoad = 1, neverHasSideEffects = 1 in
def LEAVE64  : I<0xC9, RawFrm,
                 (outs), (ins), "leave", []>;
let Defs = [RSP], Uses = [RSP], neverHasSideEffects=1 in {
let mayLoad = 1 in
def POP64r   : I<0x58, AddRegFrm,
                 (outs GR64:$reg), (ins), "pop{q}\t$reg", []>;
let mayStore = 1 in
def PUSH64r  : I<0x50, AddRegFrm,
                 (outs), (ins GR64:$reg), "push{q}\t$reg", []>;
}

let Defs = [RSP], Uses = [RSP], neverHasSideEffects = 1, mayStore = 1 in {
def PUSH64i8   : Ii8<0x6a, RawFrm, (outs), (ins i8imm:$imm), 
                     "push{q}\t$imm", []>;
def PUSH64i16  : Ii16<0x68, RawFrm, (outs), (ins i16imm:$imm), 
                      "push{q}\t$imm", []>;
def PUSH64i32  : Ii32<0x68, RawFrm, (outs), (ins i32imm:$imm), 
                      "push{q}\t$imm", []>;
}

let Defs = [RSP, EFLAGS], Uses = [RSP], mayLoad = 1 in
def POPFQ    : I<0x9D, RawFrm, (outs), (ins), "popf", []>, REX_W;
let Defs = [RSP], Uses = [RSP, EFLAGS], mayStore = 1 in
def PUSHFQ   : I<0x9C, RawFrm, (outs), (ins), "pushf", []>;

def LEA64_32r : I<0x8D, MRMSrcMem,
                  (outs GR32:$dst), (ins lea64_32mem:$src),
                  "lea{l}\t{$src|$dst}, {$dst|$src}",
                  [(set GR32:$dst, lea32addr:$src)]>, Requires<[In64BitMode]>;

let isReMaterializable = 1 in
def LEA64r   : RI<0x8D, MRMSrcMem, (outs GR64:$dst), (ins lea64mem:$src),
                  "lea{q}\t{$src|$dst}, {$dst|$src}",
                  [(set GR64:$dst, lea64addr:$src)]>;

let isTwoAddress = 1 in
def BSWAP64r : RI<0xC8, AddRegFrm, (outs GR64:$dst), (ins GR64:$src),
                  "bswap{q}\t$dst", 
                  [(set GR64:$dst, (bswap GR64:$src))]>, TB;

// Bit scan instructions.
let Defs = [EFLAGS] in {
def BSF64rr  : RI<0xBC, MRMSrcReg, (outs GR64:$dst), (ins GR64:$src),
                  "bsf{q}\t{$src, $dst|$dst, $src}",
                  [(set GR64:$dst, (X86bsf GR64:$src)), (implicit EFLAGS)]>, TB;
def BSF64rm  : RI<0xBC, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
                  "bsf{q}\t{$src, $dst|$dst, $src}",
                  [(set GR64:$dst, (X86bsf (loadi64 addr:$src))),
                   (implicit EFLAGS)]>, TB;

def BSR64rr  : RI<0xBD, MRMSrcReg, (outs GR64:$dst), (ins GR64:$src),
                  "bsr{q}\t{$src, $dst|$dst, $src}",
                  [(set GR64:$dst, (X86bsr GR64:$src)), (implicit EFLAGS)]>, TB;
def BSR64rm  : RI<0xBD, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
                  "bsr{q}\t{$src, $dst|$dst, $src}",
                  [(set GR64:$dst, (X86bsr (loadi64 addr:$src))),
                   (implicit EFLAGS)]>, TB;
} // Defs = [EFLAGS]

// Repeat string ops
let Defs = [RCX,RDI,RSI], Uses = [RCX,RDI,RSI] in
def REP_MOVSQ : RI<0xA5, RawFrm, (outs), (ins), "{rep;movsq|rep movsq}",
                   [(X86rep_movs i64)]>, REP;
let Defs = [RCX,RDI], Uses = [RAX,RCX,RDI] in
def REP_STOSQ : RI<0xAB, RawFrm, (outs), (ins), "{rep;stosq|rep stosq}",
                   [(X86rep_stos i64)]>, REP;

// Fast system-call instructions
def SYSEXIT64 : RI<0x35, RawFrm,
                   (outs), (ins), "sysexit", []>, TB;

//===----------------------------------------------------------------------===//
//  Move Instructions...
//

let neverHasSideEffects = 1 in
def MOV64rr : RI<0x89, MRMDestReg, (outs GR64:$dst), (ins GR64:$src),
                 "mov{q}\t{$src, $dst|$dst, $src}", []>;

let isReMaterializable = 1, isAsCheapAsAMove = 1  in {
def MOV64ri : RIi64<0xB8, AddRegFrm, (outs GR64:$dst), (ins i64imm:$src),
                    "movabs{q}\t{$src, $dst|$dst, $src}",
                    [(set GR64:$dst, imm:$src)]>;
def MOV64ri32 : RIi32<0xC7, MRM0r, (outs GR64:$dst), (ins i64i32imm:$src),
                      "mov{q}\t{$src, $dst|$dst, $src}",
                      [(set GR64:$dst, i64immSExt32:$src)]>;
}

let canFoldAsLoad = 1 in
def MOV64rm : RI<0x8B, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
                 "mov{q}\t{$src, $dst|$dst, $src}",
                 [(set GR64:$dst, (load addr:$src))]>;

def MOV64mr : RI<0x89, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src),
                 "mov{q}\t{$src, $dst|$dst, $src}",
                 [(store GR64:$src, addr:$dst)]>;
def MOV64mi32 : RIi32<0xC7, MRM0m, (outs), (ins i64mem:$dst, i64i32imm:$src),
                      "mov{q}\t{$src, $dst|$dst, $src}",
                      [(store i64immSExt32:$src, addr:$dst)]>;

// Sign/Zero extenders

// MOVSX64rr8 always has a REX prefix and it has an 8-bit register
// operand, which makes it a rare instruction with an 8-bit register
// operand that can never access an h register. If support for h registers
// were generalized, this would require a special register class.
def MOVSX64rr8 : RI<0xBE, MRMSrcReg, (outs GR64:$dst), (ins GR8 :$src),
                    "movs{bq|x}\t{$src, $dst|$dst, $src}",
                    [(set GR64:$dst, (sext GR8:$src))]>, TB;
def MOVSX64rm8 : RI<0xBE, MRMSrcMem, (outs GR64:$dst), (ins i8mem :$src),
                    "movs{bq|x}\t{$src, $dst|$dst, $src}",
                    [(set GR64:$dst, (sextloadi64i8 addr:$src))]>, TB;
def MOVSX64rr16: RI<0xBF, MRMSrcReg, (outs GR64:$dst), (ins GR16:$src),
                    "movs{wq|x}\t{$src, $dst|$dst, $src}",
                    [(set GR64:$dst, (sext GR16:$src))]>, TB;
def MOVSX64rm16: RI<0xBF, MRMSrcMem, (outs GR64:$dst), (ins i16mem:$src),
                    "movs{wq|x}\t{$src, $dst|$dst, $src}",
                    [(set GR64:$dst, (sextloadi64i16 addr:$src))]>, TB;
def MOVSX64rr32: RI<0x63, MRMSrcReg, (outs GR64:$dst), (ins GR32:$src),
                    "movs{lq|xd}\t{$src, $dst|$dst, $src}",
                    [(set GR64:$dst, (sext GR32:$src))]>;
def MOVSX64rm32: RI<0x63, MRMSrcMem, (outs GR64:$dst), (ins i32mem:$src),
                    "movs{lq|xd}\t{$src, $dst|$dst, $src}",
                    [(set GR64:$dst, (sextloadi64i32 addr:$src))]>;

// Use movzbl instead of movzbq when the destination is a register; it's
// equivalent due to implicit zero-extending, and it has a smaller encoding.
def MOVZX64rr8 : I<0xB6, MRMSrcReg, (outs GR64:$dst), (ins GR8 :$src),
                   "movz{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                   [(set GR64:$dst, (zext GR8:$src))]>, TB;
def MOVZX64rm8 : I<0xB6, MRMSrcMem, (outs GR64:$dst), (ins i8mem :$src),
                   "movz{bl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                   [(set GR64:$dst, (zextloadi64i8 addr:$src))]>, TB;
// Use movzwl instead of movzwq when the destination is a register; it's
// equivalent due to implicit zero-extending, and it has a smaller encoding.
def MOVZX64rr16: I<0xB7, MRMSrcReg, (outs GR64:$dst), (ins GR16:$src),
                   "movz{wl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                   [(set GR64:$dst, (zext GR16:$src))]>, TB;
def MOVZX64rm16: I<0xB7, MRMSrcMem, (outs GR64:$dst), (ins i16mem:$src),
                   "movz{wl|x}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                   [(set GR64:$dst, (zextloadi64i16 addr:$src))]>, TB;

// There's no movzlq instruction, but movl can be used for this purpose, using
// implicit zero-extension. The preferred way to do 32-bit-to-64-bit zero
// extension on x86-64 is to use a SUBREG_TO_REG to utilize implicit
// zero-extension, however this isn't possible when the 32-bit value is
// defined by a truncate or is copied from something where the high bits aren't
// necessarily all zero. In such cases, we fall back to these explicit zext
// instructions.
def MOVZX64rr32 : I<0x89, MRMDestReg, (outs GR64:$dst), (ins GR32:$src),
                    "mov{l}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                    [(set GR64:$dst, (zext GR32:$src))]>;
def MOVZX64rm32 : I<0x8B, MRMSrcMem, (outs GR64:$dst), (ins i32mem:$src),
                    "mov{l}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                    [(set GR64:$dst, (zextloadi64i32 addr:$src))]>;

// Any instruction that defines a 32-bit result leaves the high half of the
// register. Truncate can be lowered to EXTRACT_SUBREG. CopyFromReg may
// be copying from a truncate. And x86's cmov doesn't do anything if the
// condition is false. But any other 32-bit operation will zero-extend
// up to 64 bits.
def def32 : PatLeaf<(i32 GR32:$src), [{
  return N->getOpcode() != ISD::TRUNCATE &&
         N->getOpcode() != TargetInstrInfo::EXTRACT_SUBREG &&
         N->getOpcode() != ISD::CopyFromReg &&
         N->getOpcode() != X86ISD::CMOV;
}]>;

// In the case of a 32-bit def that is known to implicitly zero-extend,
// we can use a SUBREG_TO_REG.
def : Pat<(i64 (zext def32:$src)),
          (SUBREG_TO_REG (i64 0), GR32:$src, x86_subreg_32bit)>;

let neverHasSideEffects = 1 in {
  let Defs = [RAX], Uses = [EAX] in
  def CDQE : RI<0x98, RawFrm, (outs), (ins),
               "{cltq|cdqe}", []>;     // RAX = signext(EAX)

  let Defs = [RAX,RDX], Uses = [RAX] in
  def CQO  : RI<0x99, RawFrm, (outs), (ins),
                "{cqto|cqo}", []>; // RDX:RAX = signext(RAX)
}

//===----------------------------------------------------------------------===//
//  Arithmetic Instructions...
//

let Defs = [EFLAGS] in {
let isTwoAddress = 1 in {
let isConvertibleToThreeAddress = 1 in {
let isCommutable = 1 in
// Register-Register Addition
def ADD64rr    : RI<0x01, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                    "add{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (add GR64:$src1, GR64:$src2)),
                     (implicit EFLAGS)]>;

// Register-Integer Addition
def ADD64ri8  : RIi8<0x83, MRM0r, (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
                     "add{q}\t{$src2, $dst|$dst, $src2}",
                     [(set GR64:$dst, (add GR64:$src1, i64immSExt8:$src2)),
                      (implicit EFLAGS)]>;
def ADD64ri32 : RIi32<0x81, MRM0r, (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
                      "add{q}\t{$src2, $dst|$dst, $src2}",
                      [(set GR64:$dst, (add GR64:$src1, i64immSExt32:$src2)),
                       (implicit EFLAGS)]>;
} // isConvertibleToThreeAddress

// Register-Memory Addition
def ADD64rm     : RI<0x03, MRMSrcMem, (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                     "add{q}\t{$src2, $dst|$dst, $src2}",
                     [(set GR64:$dst, (add GR64:$src1, (load addr:$src2))),
                      (implicit EFLAGS)]>;
} // isTwoAddress

// Memory-Register Addition
def ADD64mr  : RI<0x01, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
                  "add{q}\t{$src2, $dst|$dst, $src2}",
                  [(store (add (load addr:$dst), GR64:$src2), addr:$dst),
                   (implicit EFLAGS)]>;
def ADD64mi8 : RIi8<0x83, MRM0m, (outs), (ins i64mem:$dst, i64i8imm :$src2),
                    "add{q}\t{$src2, $dst|$dst, $src2}",
                [(store (add (load addr:$dst), i64immSExt8:$src2), addr:$dst),
                 (implicit EFLAGS)]>;
def ADD64mi32 : RIi32<0x81, MRM0m, (outs), (ins i64mem:$dst, i64i32imm :$src2),
                      "add{q}\t{$src2, $dst|$dst, $src2}",
               [(store (add (load addr:$dst), i64immSExt32:$src2), addr:$dst),
                (implicit EFLAGS)]>;

let Uses = [EFLAGS] in {
let isTwoAddress = 1 in {
let isCommutable = 1 in
def ADC64rr  : RI<0x11, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                  "adc{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (adde GR64:$src1, GR64:$src2))]>;

def ADC64rm  : RI<0x13, MRMSrcMem , (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                  "adc{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (adde GR64:$src1, (load addr:$src2)))]>;

def ADC64ri8 : RIi8<0x83, MRM2r, (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
                    "adc{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (adde GR64:$src1, i64immSExt8:$src2))]>;
def ADC64ri32 : RIi32<0x81, MRM2r, (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
                      "adc{q}\t{$src2, $dst|$dst, $src2}",
                      [(set GR64:$dst, (adde GR64:$src1, i64immSExt32:$src2))]>;
} // isTwoAddress

def ADC64mr  : RI<0x11, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
                  "adc{q}\t{$src2, $dst|$dst, $src2}",
                  [(store (adde (load addr:$dst), GR64:$src2), addr:$dst)]>;
def ADC64mi8 : RIi8<0x83, MRM2m, (outs), (ins i64mem:$dst, i64i8imm :$src2),
                    "adc{q}\t{$src2, $dst|$dst, $src2}",
                 [(store (adde (load addr:$dst), i64immSExt8:$src2), addr:$dst)]>;
def ADC64mi32 : RIi32<0x81, MRM2m, (outs), (ins i64mem:$dst, i64i32imm:$src2),
                      "adc{q}\t{$src2, $dst|$dst, $src2}",
                 [(store (adde (load addr:$dst), i64immSExt8:$src2), addr:$dst)]>;
} // Uses = [EFLAGS]

let isTwoAddress = 1 in {
// Register-Register Subtraction
def SUB64rr  : RI<0x29, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                  "sub{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (sub GR64:$src1, GR64:$src2)),
                   (implicit EFLAGS)]>;

// Register-Memory Subtraction
def SUB64rm  : RI<0x2B, MRMSrcMem, (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                  "sub{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (sub GR64:$src1, (load addr:$src2))),
                   (implicit EFLAGS)]>;

// Register-Integer Subtraction
def SUB64ri8 : RIi8<0x83, MRM5r, (outs GR64:$dst),
                                 (ins GR64:$src1, i64i8imm:$src2),
                    "sub{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (sub GR64:$src1, i64immSExt8:$src2)),
                     (implicit EFLAGS)]>;
def SUB64ri32 : RIi32<0x81, MRM5r, (outs GR64:$dst),
                                   (ins GR64:$src1, i64i32imm:$src2),
                      "sub{q}\t{$src2, $dst|$dst, $src2}",
                      [(set GR64:$dst, (sub GR64:$src1, i64immSExt32:$src2)),
                       (implicit EFLAGS)]>;
} // isTwoAddress

// Memory-Register Subtraction
def SUB64mr  : RI<0x29, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2), 
                  "sub{q}\t{$src2, $dst|$dst, $src2}",
                  [(store (sub (load addr:$dst), GR64:$src2), addr:$dst),
                   (implicit EFLAGS)]>;

// Memory-Integer Subtraction
def SUB64mi8 : RIi8<0x83, MRM5m, (outs), (ins i64mem:$dst, i64i8imm :$src2), 
                    "sub{q}\t{$src2, $dst|$dst, $src2}",
                    [(store (sub (load addr:$dst), i64immSExt8:$src2),
                            addr:$dst),
                     (implicit EFLAGS)]>;
def SUB64mi32 : RIi32<0x81, MRM5m, (outs), (ins i64mem:$dst, i64i32imm:$src2),
                      "sub{q}\t{$src2, $dst|$dst, $src2}",
                      [(store (sub (load addr:$dst), i64immSExt32:$src2),
                              addr:$dst),
                       (implicit EFLAGS)]>;

let Uses = [EFLAGS] in {
let isTwoAddress = 1 in {
def SBB64rr    : RI<0x19, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                    "sbb{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (sube GR64:$src1, GR64:$src2))]>;

def SBB64rm  : RI<0x1B, MRMSrcMem, (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                  "sbb{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (sube GR64:$src1, (load addr:$src2)))]>;

def SBB64ri8 : RIi8<0x83, MRM3r, (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
                    "sbb{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (sube GR64:$src1, i64immSExt8:$src2))]>;
def SBB64ri32 : RIi32<0x81, MRM3r, (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
                      "sbb{q}\t{$src2, $dst|$dst, $src2}",
                      [(set GR64:$dst, (sube GR64:$src1, i64immSExt32:$src2))]>;
} // isTwoAddress

def SBB64mr  : RI<0x19, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2), 
                  "sbb{q}\t{$src2, $dst|$dst, $src2}",
                  [(store (sube (load addr:$dst), GR64:$src2), addr:$dst)]>;
def SBB64mi8 : RIi8<0x83, MRM3m, (outs), (ins i64mem:$dst, i64i8imm :$src2), 
                    "sbb{q}\t{$src2, $dst|$dst, $src2}",
               [(store (sube (load addr:$dst), i64immSExt8:$src2), addr:$dst)]>;
def SBB64mi32 : RIi32<0x81, MRM3m, (outs), (ins i64mem:$dst, i64i32imm:$src2), 
                      "sbb{q}\t{$src2, $dst|$dst, $src2}",
              [(store (sube (load addr:$dst), i64immSExt32:$src2), addr:$dst)]>;
} // Uses = [EFLAGS]
} // Defs = [EFLAGS]

// Unsigned multiplication
let Defs = [RAX,RDX,EFLAGS], Uses = [RAX], neverHasSideEffects = 1 in {
def MUL64r : RI<0xF7, MRM4r, (outs), (ins GR64:$src),
                "mul{q}\t$src", []>;         // RAX,RDX = RAX*GR64
let mayLoad = 1 in
def MUL64m : RI<0xF7, MRM4m, (outs), (ins i64mem:$src),
                "mul{q}\t$src", []>;         // RAX,RDX = RAX*[mem64]

// Signed multiplication
def IMUL64r : RI<0xF7, MRM5r, (outs), (ins GR64:$src),
                 "imul{q}\t$src", []>;         // RAX,RDX = RAX*GR64
let mayLoad = 1 in
def IMUL64m : RI<0xF7, MRM5m, (outs), (ins i64mem:$src),
                 "imul{q}\t$src", []>;         // RAX,RDX = RAX*[mem64]
}

let Defs = [EFLAGS] in {
let isTwoAddress = 1 in {
let isCommutable = 1 in
// Register-Register Signed Integer Multiplication
def IMUL64rr : RI<0xAF, MRMSrcReg, (outs GR64:$dst),
                                   (ins GR64:$src1, GR64:$src2),
                  "imul{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (mul GR64:$src1, GR64:$src2)),
                   (implicit EFLAGS)]>, TB;

// Register-Memory Signed Integer Multiplication
def IMUL64rm : RI<0xAF, MRMSrcMem, (outs GR64:$dst),
                                   (ins GR64:$src1, i64mem:$src2),
                  "imul{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (mul GR64:$src1, (load addr:$src2))),
                   (implicit EFLAGS)]>, TB;
} // isTwoAddress

// Suprisingly enough, these are not two address instructions!

// Register-Integer Signed Integer Multiplication
def IMUL64rri8 : RIi8<0x6B, MRMSrcReg,                      // GR64 = GR64*I8
                      (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
                      "imul{q}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                      [(set GR64:$dst, (mul GR64:$src1, i64immSExt8:$src2)),
                       (implicit EFLAGS)]>;
def IMUL64rri32 : RIi32<0x69, MRMSrcReg,                    // GR64 = GR64*I32
                        (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
                        "imul{q}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                       [(set GR64:$dst, (mul GR64:$src1, i64immSExt32:$src2)),
                        (implicit EFLAGS)]>;

// Memory-Integer Signed Integer Multiplication
def IMUL64rmi8 : RIi8<0x6B, MRMSrcMem,                      // GR64 = [mem64]*I8
                      (outs GR64:$dst), (ins i64mem:$src1, i64i8imm: $src2),
                      "imul{q}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                      [(set GR64:$dst, (mul (load addr:$src1),
                                            i64immSExt8:$src2)),
                       (implicit EFLAGS)]>;
def IMUL64rmi32 : RIi32<0x69, MRMSrcMem,                   // GR64 = [mem64]*I32
                        (outs GR64:$dst), (ins i64mem:$src1, i64i32imm:$src2),
                        "imul{q}\t{$src2, $src1, $dst|$dst, $src1, $src2}",
                        [(set GR64:$dst, (mul (load addr:$src1),
                                              i64immSExt32:$src2)),
                         (implicit EFLAGS)]>;
} // Defs = [EFLAGS]

// Unsigned division / remainder
let Defs = [RAX,RDX,EFLAGS], Uses = [RAX,RDX] in {
def DIV64r : RI<0xF7, MRM6r, (outs), (ins GR64:$src),        // RDX:RAX/r64 = RAX,RDX
                "div{q}\t$src", []>;
// Signed division / remainder
def IDIV64r: RI<0xF7, MRM7r, (outs), (ins GR64:$src),        // RDX:RAX/r64 = RAX,RDX
                "idiv{q}\t$src", []>;
let mayLoad = 1 in {
def DIV64m : RI<0xF7, MRM6m, (outs), (ins i64mem:$src),      // RDX:RAX/[mem64] = RAX,RDX
                "div{q}\t$src", []>;
def IDIV64m: RI<0xF7, MRM7m, (outs), (ins i64mem:$src),      // RDX:RAX/[mem64] = RAX,RDX
                "idiv{q}\t$src", []>;
}
}

// Unary instructions
let Defs = [EFLAGS], CodeSize = 2 in {
let isTwoAddress = 1 in
def NEG64r : RI<0xF7, MRM3r, (outs GR64:$dst), (ins GR64:$src), "neg{q}\t$dst",
                [(set GR64:$dst, (ineg GR64:$src)),
                 (implicit EFLAGS)]>;
def NEG64m : RI<0xF7, MRM3m, (outs), (ins i64mem:$dst), "neg{q}\t$dst",
                [(store (ineg (loadi64 addr:$dst)), addr:$dst),
                 (implicit EFLAGS)]>;

let isTwoAddress = 1, isConvertibleToThreeAddress = 1 in
def INC64r : RI<0xFF, MRM0r, (outs GR64:$dst), (ins GR64:$src), "inc{q}\t$dst",
                [(set GR64:$dst, (add GR64:$src, 1)),
                 (implicit EFLAGS)]>;
def INC64m : RI<0xFF, MRM0m, (outs), (ins i64mem:$dst), "inc{q}\t$dst",
                [(store (add (loadi64 addr:$dst), 1), addr:$dst),
                 (implicit EFLAGS)]>;

let isTwoAddress = 1, isConvertibleToThreeAddress = 1 in
def DEC64r : RI<0xFF, MRM1r, (outs GR64:$dst), (ins GR64:$src), "dec{q}\t$dst",
                [(set GR64:$dst, (add GR64:$src, -1)),
                 (implicit EFLAGS)]>;
def DEC64m : RI<0xFF, MRM1m, (outs), (ins i64mem:$dst), "dec{q}\t$dst",
                [(store (add (loadi64 addr:$dst), -1), addr:$dst),
                 (implicit EFLAGS)]>;

// In 64-bit mode, single byte INC and DEC cannot be encoded.
let isTwoAddress = 1, isConvertibleToThreeAddress = 1 in {
// Can transform into LEA.
def INC64_16r : I<0xFF, MRM0r, (outs GR16:$dst), (ins GR16:$src), "inc{w}\t$dst",
                  [(set GR16:$dst, (add GR16:$src, 1)),
                   (implicit EFLAGS)]>,
                OpSize, Requires<[In64BitMode]>;
def INC64_32r : I<0xFF, MRM0r, (outs GR32:$dst), (ins GR32:$src), "inc{l}\t$dst",
                  [(set GR32:$dst, (add GR32:$src, 1)),
                   (implicit EFLAGS)]>,
                Requires<[In64BitMode]>;
def DEC64_16r : I<0xFF, MRM1r, (outs GR16:$dst), (ins GR16:$src), "dec{w}\t$dst",
                  [(set GR16:$dst, (add GR16:$src, -1)),
                   (implicit EFLAGS)]>,
                OpSize, Requires<[In64BitMode]>;
def DEC64_32r : I<0xFF, MRM1r, (outs GR32:$dst), (ins GR32:$src), "dec{l}\t$dst",
                  [(set GR32:$dst, (add GR32:$src, -1)),
                   (implicit EFLAGS)]>,
                Requires<[In64BitMode]>;
} // isConvertibleToThreeAddress

// These are duplicates of their 32-bit counterparts. Only needed so X86 knows
// how to unfold them.
let isTwoAddress = 0, CodeSize = 2 in {
  def INC64_16m : I<0xFF, MRM0m, (outs), (ins i16mem:$dst), "inc{w}\t$dst",
                    [(store (add (loadi16 addr:$dst), 1), addr:$dst),
                     (implicit EFLAGS)]>,
                  OpSize, Requires<[In64BitMode]>;
  def INC64_32m : I<0xFF, MRM0m, (outs), (ins i32mem:$dst), "inc{l}\t$dst",
                    [(store (add (loadi32 addr:$dst), 1), addr:$dst),
                     (implicit EFLAGS)]>,
                  Requires<[In64BitMode]>;
  def DEC64_16m : I<0xFF, MRM1m, (outs), (ins i16mem:$dst), "dec{w}\t$dst",
                    [(store (add (loadi16 addr:$dst), -1), addr:$dst),
                     (implicit EFLAGS)]>,
                  OpSize, Requires<[In64BitMode]>;
  def DEC64_32m : I<0xFF, MRM1m, (outs), (ins i32mem:$dst), "dec{l}\t$dst",
                    [(store (add (loadi32 addr:$dst), -1), addr:$dst),
                     (implicit EFLAGS)]>,
                  Requires<[In64BitMode]>;
}
} // Defs = [EFLAGS], CodeSize


let Defs = [EFLAGS] in {
// Shift instructions
let isTwoAddress = 1 in {
let Uses = [CL] in
def SHL64rCL : RI<0xD3, MRM4r, (outs GR64:$dst), (ins GR64:$src),
                  "shl{q}\t{%cl, $dst|$dst, %CL}",
                  [(set GR64:$dst, (shl GR64:$src, CL))]>;
let isConvertibleToThreeAddress = 1 in   // Can transform into LEA.
def SHL64ri  : RIi8<0xC1, MRM4r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
                    "shl{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (shl GR64:$src1, (i8 imm:$src2)))]>;
// NOTE: We don't use shifts of a register by one, because 'add reg,reg' is
// cheaper.
} // isTwoAddress

let Uses = [CL] in
def SHL64mCL : RI<0xD3, MRM4m, (outs), (ins i64mem:$dst),
                  "shl{q}\t{%cl, $dst|$dst, %CL}",
                  [(store (shl (loadi64 addr:$dst), CL), addr:$dst)]>;
def SHL64mi : RIi8<0xC1, MRM4m, (outs), (ins i64mem:$dst, i8imm:$src),
                  "shl{q}\t{$src, $dst|$dst, $src}",
                 [(store (shl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
def SHL64m1 : RI<0xD1, MRM4m, (outs), (ins i64mem:$dst),
                  "shl{q}\t$dst",
                 [(store (shl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;

let isTwoAddress = 1 in {
let Uses = [CL] in
def SHR64rCL : RI<0xD3, MRM5r, (outs GR64:$dst), (ins GR64:$src),
                  "shr{q}\t{%cl, $dst|$dst, %CL}",
                  [(set GR64:$dst, (srl GR64:$src, CL))]>;
def SHR64ri : RIi8<0xC1, MRM5r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
                  "shr{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (srl GR64:$src1, (i8 imm:$src2)))]>;
def SHR64r1  : RI<0xD1, MRM5r, (outs GR64:$dst), (ins GR64:$src1),
                 "shr{q}\t$dst",
                 [(set GR64:$dst, (srl GR64:$src1, (i8 1)))]>;
} // isTwoAddress

let Uses = [CL] in
def SHR64mCL : RI<0xD3, MRM5m, (outs), (ins i64mem:$dst),
                  "shr{q}\t{%cl, $dst|$dst, %CL}",
                  [(store (srl (loadi64 addr:$dst), CL), addr:$dst)]>;
def SHR64mi : RIi8<0xC1, MRM5m, (outs), (ins i64mem:$dst, i8imm:$src),
                  "shr{q}\t{$src, $dst|$dst, $src}",
                 [(store (srl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
def SHR64m1 : RI<0xD1, MRM5m, (outs), (ins i64mem:$dst),
                  "shr{q}\t$dst",
                 [(store (srl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;

let isTwoAddress = 1 in {
let Uses = [CL] in
def SAR64rCL : RI<0xD3, MRM7r, (outs GR64:$dst), (ins GR64:$src),
                 "sar{q}\t{%cl, $dst|$dst, %CL}",
                 [(set GR64:$dst, (sra GR64:$src, CL))]>;
def SAR64ri  : RIi8<0xC1, MRM7r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
                   "sar{q}\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (sra GR64:$src1, (i8 imm:$src2)))]>;
def SAR64r1  : RI<0xD1, MRM7r, (outs GR64:$dst), (ins GR64:$src1),
                 "sar{q}\t$dst",
                 [(set GR64:$dst, (sra GR64:$src1, (i8 1)))]>;
} // isTwoAddress

let Uses = [CL] in
def SAR64mCL : RI<0xD3, MRM7m, (outs), (ins i64mem:$dst), 
                 "sar{q}\t{%cl, $dst|$dst, %CL}",
                 [(store (sra (loadi64 addr:$dst), CL), addr:$dst)]>;
def SAR64mi  : RIi8<0xC1, MRM7m, (outs), (ins i64mem:$dst, i8imm:$src),
                    "sar{q}\t{$src, $dst|$dst, $src}",
                 [(store (sra (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
def SAR64m1 : RI<0xD1, MRM7m, (outs), (ins i64mem:$dst),
                  "sar{q}\t$dst",
                 [(store (sra (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;

// Rotate instructions
let isTwoAddress = 1 in {
let Uses = [CL] in
def ROL64rCL : RI<0xD3, MRM0r, (outs GR64:$dst), (ins GR64:$src),
                  "rol{q}\t{%cl, $dst|$dst, %CL}",
                  [(set GR64:$dst, (rotl GR64:$src, CL))]>;
def ROL64ri  : RIi8<0xC1, MRM0r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
                    "rol{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (rotl GR64:$src1, (i8 imm:$src2)))]>;
def ROL64r1  : RI<0xD1, MRM0r, (outs GR64:$dst), (ins GR64:$src1),
                  "rol{q}\t$dst",
                  [(set GR64:$dst, (rotl GR64:$src1, (i8 1)))]>;
} // isTwoAddress

let Uses = [CL] in
def ROL64mCL :  I<0xD3, MRM0m, (outs), (ins i64mem:$dst),
                  "rol{q}\t{%cl, $dst|$dst, %CL}",
                  [(store (rotl (loadi64 addr:$dst), CL), addr:$dst)]>;
def ROL64mi  : RIi8<0xC1, MRM0m, (outs), (ins i64mem:$dst, i8imm:$src),
                    "rol{q}\t{$src, $dst|$dst, $src}",
                [(store (rotl (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
def ROL64m1  : RI<0xD1, MRM0m, (outs), (ins i64mem:$dst),
                 "rol{q}\t$dst",
               [(store (rotl (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;

let isTwoAddress = 1 in {
let Uses = [CL] in
def ROR64rCL : RI<0xD3, MRM1r, (outs GR64:$dst), (ins GR64:$src),
                  "ror{q}\t{%cl, $dst|$dst, %CL}",
                  [(set GR64:$dst, (rotr GR64:$src, CL))]>;
def ROR64ri  : RIi8<0xC1, MRM1r, (outs GR64:$dst), (ins GR64:$src1, i8imm:$src2),
                    "ror{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (rotr GR64:$src1, (i8 imm:$src2)))]>;
def ROR64r1  : RI<0xD1, MRM1r, (outs GR64:$dst), (ins GR64:$src1),
                  "ror{q}\t$dst",
                  [(set GR64:$dst, (rotr GR64:$src1, (i8 1)))]>;
} // isTwoAddress

let Uses = [CL] in
def ROR64mCL : RI<0xD3, MRM1m, (outs), (ins i64mem:$dst), 
                  "ror{q}\t{%cl, $dst|$dst, %CL}",
                  [(store (rotr (loadi64 addr:$dst), CL), addr:$dst)]>;
def ROR64mi  : RIi8<0xC1, MRM1m, (outs), (ins i64mem:$dst, i8imm:$src),
                    "ror{q}\t{$src, $dst|$dst, $src}",
                [(store (rotr (loadi64 addr:$dst), (i8 imm:$src)), addr:$dst)]>;
def ROR64m1  : RI<0xD1, MRM1m, (outs), (ins i64mem:$dst),
                 "ror{q}\t$dst",
               [(store (rotr (loadi64 addr:$dst), (i8 1)), addr:$dst)]>;

// Double shift instructions (generalizations of rotate)
let isTwoAddress = 1 in {
let Uses = [CL] in {
def SHLD64rrCL : RI<0xA5, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                    "shld{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
                    [(set GR64:$dst, (X86shld GR64:$src1, GR64:$src2, CL))]>, TB;
def SHRD64rrCL : RI<0xAD, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                    "shrd{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
                    [(set GR64:$dst, (X86shrd GR64:$src1, GR64:$src2, CL))]>, TB;
}

let isCommutable = 1 in {  // FIXME: Update X86InstrInfo::commuteInstruction
def SHLD64rri8 : RIi8<0xA4, MRMDestReg,
                      (outs GR64:$dst), (ins GR64:$src1, GR64:$src2, i8imm:$src3),
                      "shld{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
                      [(set GR64:$dst, (X86shld GR64:$src1, GR64:$src2,
                                       (i8 imm:$src3)))]>,
                 TB;
def SHRD64rri8 : RIi8<0xAC, MRMDestReg,
                      (outs GR64:$dst), (ins GR64:$src1, GR64:$src2, i8imm:$src3),
                      "shrd{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
                      [(set GR64:$dst, (X86shrd GR64:$src1, GR64:$src2,
                                       (i8 imm:$src3)))]>,
                 TB;
} // isCommutable
} // isTwoAddress

let Uses = [CL] in {
def SHLD64mrCL : RI<0xA5, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
                    "shld{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
                    [(store (X86shld (loadi64 addr:$dst), GR64:$src2, CL),
                      addr:$dst)]>, TB;
def SHRD64mrCL : RI<0xAD, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
                    "shrd{q}\t{%cl, $src2, $dst|$dst, $src2, %CL}",
                    [(store (X86shrd (loadi64 addr:$dst), GR64:$src2, CL),
                      addr:$dst)]>, TB;
}
def SHLD64mri8 : RIi8<0xA4, MRMDestMem,
                      (outs), (ins i64mem:$dst, GR64:$src2, i8imm:$src3),
                      "shld{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
                      [(store (X86shld (loadi64 addr:$dst), GR64:$src2,
                                       (i8 imm:$src3)), addr:$dst)]>,
                 TB;
def SHRD64mri8 : RIi8<0xAC, MRMDestMem, 
                      (outs), (ins i64mem:$dst, GR64:$src2, i8imm:$src3),
                      "shrd{q}\t{$src3, $src2, $dst|$dst, $src2, $src3}",
                      [(store (X86shrd (loadi64 addr:$dst), GR64:$src2,
                                       (i8 imm:$src3)), addr:$dst)]>,
                 TB;
} // Defs = [EFLAGS]

//===----------------------------------------------------------------------===//
//  Logical Instructions...
//

let isTwoAddress = 1 , AddedComplexity = 15 in
def NOT64r : RI<0xF7, MRM2r, (outs GR64:$dst), (ins GR64:$src), "not{q}\t$dst",
                [(set GR64:$dst, (not GR64:$src))]>;
def NOT64m : RI<0xF7, MRM2m, (outs), (ins i64mem:$dst), "not{q}\t$dst",
                [(store (not (loadi64 addr:$dst)), addr:$dst)]>;

let Defs = [EFLAGS] in {
let isTwoAddress = 1 in {
let isCommutable = 1 in
def AND64rr  : RI<0x21, MRMDestReg, 
                  (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                  "and{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (and GR64:$src1, GR64:$src2)),
                   (implicit EFLAGS)]>;
def AND64rm  : RI<0x23, MRMSrcMem,
                  (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                  "and{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (and GR64:$src1, (load addr:$src2))),
                   (implicit EFLAGS)]>;
def AND64ri8 : RIi8<0x83, MRM4r, 
                    (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
                    "and{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (and GR64:$src1, i64immSExt8:$src2)),
                     (implicit EFLAGS)]>;
def AND64ri32  : RIi32<0x81, MRM4r, 
                       (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
                       "and{q}\t{$src2, $dst|$dst, $src2}",
                       [(set GR64:$dst, (and GR64:$src1, i64immSExt32:$src2)),
                        (implicit EFLAGS)]>;
} // isTwoAddress

def AND64mr  : RI<0x21, MRMDestMem,
                  (outs), (ins i64mem:$dst, GR64:$src),
                  "and{q}\t{$src, $dst|$dst, $src}",
                  [(store (and (load addr:$dst), GR64:$src), addr:$dst),
                   (implicit EFLAGS)]>;
def AND64mi8 : RIi8<0x83, MRM4m,
                    (outs), (ins i64mem:$dst, i64i8imm :$src),
                    "and{q}\t{$src, $dst|$dst, $src}",
                 [(store (and (load addr:$dst), i64immSExt8:$src), addr:$dst),
                  (implicit EFLAGS)]>;
def AND64mi32  : RIi32<0x81, MRM4m,
                       (outs), (ins i64mem:$dst, i64i32imm:$src),
                       "and{q}\t{$src, $dst|$dst, $src}",
             [(store (and (loadi64 addr:$dst), i64immSExt32:$src), addr:$dst),
              (implicit EFLAGS)]>;

let isTwoAddress = 1 in {
let isCommutable = 1 in
def OR64rr   : RI<0x09, MRMDestReg, (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                  "or{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (or GR64:$src1, GR64:$src2)),
                   (implicit EFLAGS)]>;
def OR64rm   : RI<0x0B, MRMSrcMem , (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                  "or{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (or GR64:$src1, (load addr:$src2))),
                   (implicit EFLAGS)]>;
def OR64ri8  : RIi8<0x83, MRM1r, (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
                    "or{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (or GR64:$src1, i64immSExt8:$src2)),
                     (implicit EFLAGS)]>;
def OR64ri32 : RIi32<0x81, MRM1r, (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2),
                     "or{q}\t{$src2, $dst|$dst, $src2}",
                     [(set GR64:$dst, (or GR64:$src1, i64immSExt32:$src2)),
                      (implicit EFLAGS)]>;
} // isTwoAddress

def OR64mr : RI<0x09, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src),
                "or{q}\t{$src, $dst|$dst, $src}",
                [(store (or (load addr:$dst), GR64:$src), addr:$dst),
                 (implicit EFLAGS)]>;
def OR64mi8  : RIi8<0x83, MRM1m, (outs), (ins i64mem:$dst, i64i8imm:$src),
                    "or{q}\t{$src, $dst|$dst, $src}",
                  [(store (or (load addr:$dst), i64immSExt8:$src), addr:$dst),
                   (implicit EFLAGS)]>;
def OR64mi32 : RIi32<0x81, MRM1m, (outs), (ins i64mem:$dst, i64i32imm:$src),
                     "or{q}\t{$src, $dst|$dst, $src}",
              [(store (or (loadi64 addr:$dst), i64immSExt32:$src), addr:$dst),
               (implicit EFLAGS)]>;

let isTwoAddress = 1 in {
let isCommutable = 1 in
def XOR64rr  : RI<0x31, MRMDestReg,  (outs GR64:$dst), (ins GR64:$src1, GR64:$src2), 
                  "xor{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (xor GR64:$src1, GR64:$src2)),
                   (implicit EFLAGS)]>;
def XOR64rm  : RI<0x33, MRMSrcMem, (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2), 
                  "xor{q}\t{$src2, $dst|$dst, $src2}",
                  [(set GR64:$dst, (xor GR64:$src1, (load addr:$src2))),
                   (implicit EFLAGS)]>;
def XOR64ri8 : RIi8<0x83, MRM6r,  (outs GR64:$dst), (ins GR64:$src1, i64i8imm:$src2),
                    "xor{q}\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (xor GR64:$src1, i64immSExt8:$src2)),
                     (implicit EFLAGS)]>;
def XOR64ri32 : RIi32<0x81, MRM6r, 
                      (outs GR64:$dst), (ins GR64:$src1, i64i32imm:$src2), 
                      "xor{q}\t{$src2, $dst|$dst, $src2}",
                      [(set GR64:$dst, (xor GR64:$src1, i64immSExt32:$src2)),
                       (implicit EFLAGS)]>;
} // isTwoAddress

def XOR64mr  : RI<0x31, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src),
                  "xor{q}\t{$src, $dst|$dst, $src}",
                  [(store (xor (load addr:$dst), GR64:$src), addr:$dst),
                   (implicit EFLAGS)]>;
def XOR64mi8 : RIi8<0x83, MRM6m, (outs), (ins i64mem:$dst, i64i8imm :$src),
                    "xor{q}\t{$src, $dst|$dst, $src}",
                 [(store (xor (load addr:$dst), i64immSExt8:$src), addr:$dst),
                  (implicit EFLAGS)]>;
def XOR64mi32 : RIi32<0x81, MRM6m, (outs), (ins i64mem:$dst, i64i32imm:$src),
                      "xor{q}\t{$src, $dst|$dst, $src}",
             [(store (xor (loadi64 addr:$dst), i64immSExt32:$src), addr:$dst),
              (implicit EFLAGS)]>;
} // Defs = [EFLAGS]

//===----------------------------------------------------------------------===//
//  Comparison Instructions...
//

// Integer comparison
let Defs = [EFLAGS] in {
let isCommutable = 1 in
def TEST64rr : RI<0x85, MRMDestReg, (outs), (ins GR64:$src1, GR64:$src2),
                  "test{q}\t{$src2, $src1|$src1, $src2}",
                  [(X86cmp (and GR64:$src1, GR64:$src2), 0),
                   (implicit EFLAGS)]>;
def TEST64rm : RI<0x85, MRMSrcMem, (outs), (ins GR64:$src1, i64mem:$src2),
                  "test{q}\t{$src2, $src1|$src1, $src2}",
                  [(X86cmp (and GR64:$src1, (loadi64 addr:$src2)), 0),
                   (implicit EFLAGS)]>;
def TEST64ri32 : RIi32<0xF7, MRM0r, (outs),
                                        (ins GR64:$src1, i64i32imm:$src2),
                       "test{q}\t{$src2, $src1|$src1, $src2}",
                     [(X86cmp (and GR64:$src1, i64immSExt32:$src2), 0),
                      (implicit EFLAGS)]>;
def TEST64mi32 : RIi32<0xF7, MRM0m, (outs),
                                        (ins i64mem:$src1, i64i32imm:$src2),
                       "test{q}\t{$src2, $src1|$src1, $src2}",
                [(X86cmp (and (loadi64 addr:$src1), i64immSExt32:$src2), 0),
                 (implicit EFLAGS)]>;

def CMP64rr : RI<0x39, MRMDestReg, (outs), (ins GR64:$src1, GR64:$src2),
                 "cmp{q}\t{$src2, $src1|$src1, $src2}",
                 [(X86cmp GR64:$src1, GR64:$src2),
                  (implicit EFLAGS)]>;
def CMP64mr : RI<0x39, MRMDestMem, (outs), (ins i64mem:$src1, GR64:$src2),
                 "cmp{q}\t{$src2, $src1|$src1, $src2}",
                 [(X86cmp (loadi64 addr:$src1), GR64:$src2),
                   (implicit EFLAGS)]>;
def CMP64rm : RI<0x3B, MRMSrcMem, (outs), (ins GR64:$src1, i64mem:$src2),
                 "cmp{q}\t{$src2, $src1|$src1, $src2}",
                 [(X86cmp GR64:$src1, (loadi64 addr:$src2)),
                  (implicit EFLAGS)]>;
def CMP64ri8 : RIi8<0x83, MRM7r, (outs), (ins GR64:$src1, i64i8imm:$src2),
                    "cmp{q}\t{$src2, $src1|$src1, $src2}",
                    [(X86cmp GR64:$src1, i64immSExt8:$src2),
                     (implicit EFLAGS)]>;
def CMP64ri32 : RIi32<0x81, MRM7r, (outs), (ins GR64:$src1, i64i32imm:$src2),
                      "cmp{q}\t{$src2, $src1|$src1, $src2}",
                      [(X86cmp GR64:$src1, i64immSExt32:$src2),
                       (implicit EFLAGS)]>;
def CMP64mi8 : RIi8<0x83, MRM7m, (outs), (ins i64mem:$src1, i64i8imm:$src2),
                    "cmp{q}\t{$src2, $src1|$src1, $src2}",
                    [(X86cmp (loadi64 addr:$src1), i64immSExt8:$src2),
                     (implicit EFLAGS)]>;
def CMP64mi32 : RIi32<0x81, MRM7m, (outs),
                                       (ins i64mem:$src1, i64i32imm:$src2),
                      "cmp{q}\t{$src2, $src1|$src1, $src2}",
                      [(X86cmp (loadi64 addr:$src1), i64immSExt32:$src2),
                       (implicit EFLAGS)]>;
} // Defs = [EFLAGS]

// Bit tests.
// TODO: BTC, BTR, and BTS
let Defs = [EFLAGS] in {
def BT64rr : RI<0xA3, MRMDestReg, (outs), (ins GR64:$src1, GR64:$src2),
               "bt{q}\t{$src2, $src1|$src1, $src2}",
               [(X86bt GR64:$src1, GR64:$src2),
                (implicit EFLAGS)]>, TB;

// Unlike with the register+register form, the memory+register form of the
// bt instruction does not ignore the high bits of the index. From ISel's
// perspective, this is pretty bizarre. Disable these instructions for now.
//def BT64mr : RI<0xA3, MRMDestMem, (outs), (ins i64mem:$src1, GR64:$src2),
//               "bt{q}\t{$src2, $src1|$src1, $src2}",
//               [(X86bt (loadi64 addr:$src1), GR64:$src2),
//                (implicit EFLAGS)]>, TB;

def BT64ri8 : Ii8<0xBA, MRM4r, (outs), (ins GR64:$src1, i64i8imm:$src2),
                "bt{q}\t{$src2, $src1|$src1, $src2}",
                [(X86bt GR64:$src1, i64immSExt8:$src2),
                 (implicit EFLAGS)]>, TB;
// Note that these instructions don't need FastBTMem because that
// only applies when the other operand is in a register. When it's
// an immediate, bt is still fast.
def BT64mi8 : Ii8<0xBA, MRM4m, (outs), (ins i64mem:$src1, i64i8imm:$src2),
                "bt{q}\t{$src2, $src1|$src1, $src2}",
                [(X86bt (loadi64 addr:$src1), i64immSExt8:$src2),
                 (implicit EFLAGS)]>, TB;
} // Defs = [EFLAGS]

// Conditional moves
let Uses = [EFLAGS], isTwoAddress = 1 in {
let isCommutable = 1 in {
def CMOVB64rr : RI<0x42, MRMSrcReg,       // if <u, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovb\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                     X86_COND_B, EFLAGS))]>, TB;
def CMOVAE64rr: RI<0x43, MRMSrcReg,       // if >=u, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovae\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                     X86_COND_AE, EFLAGS))]>, TB;
def CMOVE64rr : RI<0x44, MRMSrcReg,       // if ==, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmove\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                     X86_COND_E, EFLAGS))]>, TB;
def CMOVNE64rr: RI<0x45, MRMSrcReg,       // if !=, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovne\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_NE, EFLAGS))]>, TB;
def CMOVBE64rr: RI<0x46, MRMSrcReg,       // if <=u, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovbe\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_BE, EFLAGS))]>, TB;
def CMOVA64rr : RI<0x47, MRMSrcReg,       // if >u, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmova\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_A, EFLAGS))]>, TB;
def CMOVL64rr : RI<0x4C, MRMSrcReg,       // if <s, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovl\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_L, EFLAGS))]>, TB;
def CMOVGE64rr: RI<0x4D, MRMSrcReg,       // if >=s, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovge\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_GE, EFLAGS))]>, TB;
def CMOVLE64rr: RI<0x4E, MRMSrcReg,       // if <=s, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovle\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_LE, EFLAGS))]>, TB;
def CMOVG64rr : RI<0x4F, MRMSrcReg,       // if >s, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovg\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_G, EFLAGS))]>, TB;
def CMOVS64rr : RI<0x48, MRMSrcReg,       // if signed, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovs\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_S, EFLAGS))]>, TB;
def CMOVNS64rr: RI<0x49, MRMSrcReg,       // if !signed, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovns\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_NS, EFLAGS))]>, TB;
def CMOVP64rr : RI<0x4A, MRMSrcReg,       // if parity, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovp\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_P, EFLAGS))]>, TB;
def CMOVNP64rr : RI<0x4B, MRMSrcReg,       // if !parity, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovnp\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                     X86_COND_NP, EFLAGS))]>, TB;
def CMOVO64rr : RI<0x40, MRMSrcReg,       // if overflow, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovo\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                    X86_COND_O, EFLAGS))]>, TB;
def CMOVNO64rr : RI<0x41, MRMSrcReg,       // if !overflow, GR64 = GR64
                   (outs GR64:$dst), (ins GR64:$src1, GR64:$src2),
                   "cmovno\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (X86cmov GR64:$src1, GR64:$src2,
                                     X86_COND_NO, EFLAGS))]>, TB;
} // isCommutable = 1

def CMOVB64rm : RI<0x42, MRMSrcMem,       // if <u, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovb\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                     X86_COND_B, EFLAGS))]>, TB;
def CMOVAE64rm: RI<0x43, MRMSrcMem,       // if >=u, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovae\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                     X86_COND_AE, EFLAGS))]>, TB;
def CMOVE64rm : RI<0x44, MRMSrcMem,       // if ==, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmove\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                     X86_COND_E, EFLAGS))]>, TB;
def CMOVNE64rm: RI<0x45, MRMSrcMem,       // if !=, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovne\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_NE, EFLAGS))]>, TB;
def CMOVBE64rm: RI<0x46, MRMSrcMem,       // if <=u, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovbe\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_BE, EFLAGS))]>, TB;
def CMOVA64rm : RI<0x47, MRMSrcMem,       // if >u, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmova\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_A, EFLAGS))]>, TB;
def CMOVL64rm : RI<0x4C, MRMSrcMem,       // if <s, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovl\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_L, EFLAGS))]>, TB;
def CMOVGE64rm: RI<0x4D, MRMSrcMem,       // if >=s, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovge\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_GE, EFLAGS))]>, TB;
def CMOVLE64rm: RI<0x4E, MRMSrcMem,       // if <=s, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovle\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_LE, EFLAGS))]>, TB;
def CMOVG64rm : RI<0x4F, MRMSrcMem,       // if >s, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovg\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_G, EFLAGS))]>, TB;
def CMOVS64rm : RI<0x48, MRMSrcMem,       // if signed, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovs\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_S, EFLAGS))]>, TB;
def CMOVNS64rm: RI<0x49, MRMSrcMem,       // if !signed, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovns\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_NS, EFLAGS))]>, TB;
def CMOVP64rm : RI<0x4A, MRMSrcMem,       // if parity, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovp\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_P, EFLAGS))]>, TB;
def CMOVNP64rm : RI<0x4B, MRMSrcMem,       // if !parity, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovnp\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                     X86_COND_NP, EFLAGS))]>, TB;
def CMOVO64rm : RI<0x40, MRMSrcMem,       // if overflow, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovo\t{$src2, $dst|$dst, $src2}",
                   [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                    X86_COND_O, EFLAGS))]>, TB;
def CMOVNO64rm : RI<0x41, MRMSrcMem,       // if !overflow, GR64 = [mem64]
                   (outs GR64:$dst), (ins GR64:$src1, i64mem:$src2),
                   "cmovno\t{$src2, $dst|$dst, $src2}",
                    [(set GR64:$dst, (X86cmov GR64:$src1, (loadi64 addr:$src2),
                                     X86_COND_NO, EFLAGS))]>, TB;
} // isTwoAddress

//===----------------------------------------------------------------------===//
//  Conversion Instructions...
//

// f64 -> signed i64
def Int_CVTSD2SI64rr: RSDI<0x2D, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
                           "cvtsd2si{q}\t{$src, $dst|$dst, $src}",
                           [(set GR64:$dst,
                             (int_x86_sse2_cvtsd2si64 VR128:$src))]>;
def Int_CVTSD2SI64rm: RSDI<0x2D, MRMSrcMem, (outs GR64:$dst), (ins f128mem:$src),
                           "cvtsd2si{q}\t{$src, $dst|$dst, $src}",
                           [(set GR64:$dst, (int_x86_sse2_cvtsd2si64
                                             (load addr:$src)))]>;
def CVTTSD2SI64rr: RSDI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins FR64:$src),
                        "cvttsd2si{q}\t{$src, $dst|$dst, $src}",
                        [(set GR64:$dst, (fp_to_sint FR64:$src))]>;
def CVTTSD2SI64rm: RSDI<0x2C, MRMSrcMem, (outs GR64:$dst), (ins f64mem:$src),
                        "cvttsd2si{q}\t{$src, $dst|$dst, $src}",
                        [(set GR64:$dst, (fp_to_sint (loadf64 addr:$src)))]>;
def Int_CVTTSD2SI64rr: RSDI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
                            "cvttsd2si{q}\t{$src, $dst|$dst, $src}",
                            [(set GR64:$dst,
                              (int_x86_sse2_cvttsd2si64 VR128:$src))]>;
def Int_CVTTSD2SI64rm: RSDI<0x2C, MRMSrcMem, (outs GR64:$dst), (ins f128mem:$src),
                            "cvttsd2si{q}\t{$src, $dst|$dst, $src}",
                            [(set GR64:$dst,
                              (int_x86_sse2_cvttsd2si64
                               (load addr:$src)))]>;

// Signed i64 -> f64
def CVTSI2SD64rr: RSDI<0x2A, MRMSrcReg, (outs FR64:$dst), (ins GR64:$src),
                       "cvtsi2sd{q}\t{$src, $dst|$dst, $src}",
                       [(set FR64:$dst, (sint_to_fp GR64:$src))]>;
def CVTSI2SD64rm: RSDI<0x2A, MRMSrcMem, (outs FR64:$dst), (ins i64mem:$src),
                       "cvtsi2sd{q}\t{$src, $dst|$dst, $src}",
                       [(set FR64:$dst, (sint_to_fp (loadi64 addr:$src)))]>;

let isTwoAddress = 1 in {
def Int_CVTSI2SD64rr: RSDI<0x2A, MRMSrcReg,
                           (outs VR128:$dst), (ins VR128:$src1, GR64:$src2),
                           "cvtsi2sd{q}\t{$src2, $dst|$dst, $src2}",
                           [(set VR128:$dst,
                             (int_x86_sse2_cvtsi642sd VR128:$src1,
                              GR64:$src2))]>;
def Int_CVTSI2SD64rm: RSDI<0x2A, MRMSrcMem,
                           (outs VR128:$dst), (ins VR128:$src1, i64mem:$src2),
                           "cvtsi2sd{q}\t{$src2, $dst|$dst, $src2}",
                           [(set VR128:$dst,
                             (int_x86_sse2_cvtsi642sd VR128:$src1,
                              (loadi64 addr:$src2)))]>;
} // isTwoAddress

// Signed i64 -> f32
def CVTSI2SS64rr: RSSI<0x2A, MRMSrcReg, (outs FR32:$dst), (ins GR64:$src),
                       "cvtsi2ss{q}\t{$src, $dst|$dst, $src}",
                       [(set FR32:$dst, (sint_to_fp GR64:$src))]>;
def CVTSI2SS64rm: RSSI<0x2A, MRMSrcMem, (outs FR32:$dst), (ins i64mem:$src),
                       "cvtsi2ss{q}\t{$src, $dst|$dst, $src}",
                       [(set FR32:$dst, (sint_to_fp (loadi64 addr:$src)))]>;

let isTwoAddress = 1 in {
  def Int_CVTSI2SS64rr : RSSI<0x2A, MRMSrcReg,
                              (outs VR128:$dst), (ins VR128:$src1, GR64:$src2),
                              "cvtsi2ss{q}\t{$src2, $dst|$dst, $src2}",
                              [(set VR128:$dst,
                                (int_x86_sse_cvtsi642ss VR128:$src1,
                                 GR64:$src2))]>;
  def Int_CVTSI2SS64rm : RSSI<0x2A, MRMSrcMem,
                              (outs VR128:$dst), (ins VR128:$src1, i64mem:$src2),
                              "cvtsi2ss{q}\t{$src2, $dst|$dst, $src2}",
                              [(set VR128:$dst,
                                (int_x86_sse_cvtsi642ss VR128:$src1,
                                 (loadi64 addr:$src2)))]>;
}

// f32 -> signed i64
def Int_CVTSS2SI64rr: RSSI<0x2D, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
                           "cvtss2si{q}\t{$src, $dst|$dst, $src}",
                           [(set GR64:$dst,
                             (int_x86_sse_cvtss2si64 VR128:$src))]>;
def Int_CVTSS2SI64rm: RSSI<0x2D, MRMSrcMem, (outs GR64:$dst), (ins f32mem:$src),
                           "cvtss2si{q}\t{$src, $dst|$dst, $src}",
                           [(set GR64:$dst, (int_x86_sse_cvtss2si64
                                             (load addr:$src)))]>;
def CVTTSS2SI64rr: RSSI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins FR32:$src),
                        "cvttss2si{q}\t{$src, $dst|$dst, $src}",
                        [(set GR64:$dst, (fp_to_sint FR32:$src))]>;
def CVTTSS2SI64rm: RSSI<0x2C, MRMSrcMem, (outs GR64:$dst), (ins f32mem:$src),
                        "cvttss2si{q}\t{$src, $dst|$dst, $src}",
                        [(set GR64:$dst, (fp_to_sint (loadf32 addr:$src)))]>;
def Int_CVTTSS2SI64rr: RSSI<0x2C, MRMSrcReg, (outs GR64:$dst), (ins VR128:$src),
                            "cvttss2si{q}\t{$src, $dst|$dst, $src}",
                            [(set GR64:$dst,
                              (int_x86_sse_cvttss2si64 VR128:$src))]>;
def Int_CVTTSS2SI64rm: RSSI<0x2C, MRMSrcMem, (outs GR64:$dst), (ins f32mem:$src),
                            "cvttss2si{q}\t{$src, $dst|$dst, $src}",
                            [(set GR64:$dst,
                              (int_x86_sse_cvttss2si64 (load addr:$src)))]>;

//===----------------------------------------------------------------------===//
// Alias Instructions
//===----------------------------------------------------------------------===//

// Alias instructions that map movr0 to xor. Use xorl instead of xorq; it's
// equivalent due to implicit zero-extending, and it sometimes has a smaller
// encoding.
// FIXME: AddedComplexity gives this a higher priority than MOV64ri32. Remove
// when we have a better way to specify isel priority.
let AddedComplexity = 1 in
def : Pat<(i64 0),
          (SUBREG_TO_REG (i64 0), (MOV32r0), x86_subreg_32bit)>;


// Materialize i64 constant where top 32-bits are zero.
let AddedComplexity = 1, isReMaterializable = 1, isAsCheapAsAMove = 1 in
def MOV64ri64i32 : Ii32<0xB8, AddRegFrm, (outs GR64:$dst), (ins i64i32imm:$src),
                        "mov{l}\t{$src, ${dst:subreg32}|${dst:subreg32}, $src}",
                        [(set GR64:$dst, i64immZExt32:$src)]>;

//===----------------------------------------------------------------------===//
// Thread Local Storage Instructions
//===----------------------------------------------------------------------===//

// All calls clobber the non-callee saved registers. RSP is marked as
// a use to prevent stack-pointer assignments that appear immediately
// before calls from potentially appearing dead.
let Defs = [RAX, RCX, RDX, RSI, RDI, R8, R9, R10, R11,
            FP0, FP1, FP2, FP3, FP4, FP5, FP6, ST0, ST1,
            MM0, MM1, MM2, MM3, MM4, MM5, MM6, MM7,
            XMM0, XMM1, XMM2, XMM3, XMM4, XMM5, XMM6, XMM7,
            XMM8, XMM9, XMM10, XMM11, XMM12, XMM13, XMM14, XMM15, EFLAGS],
    Uses = [RSP] in
def TLS_addr64 : I<0, Pseudo, (outs), (ins lea64mem:$sym),
                   ".byte\t0x66; "
                   "leaq\t$sym(%rip), %rdi; "
                   ".word\t0x6666; "
                   "rex64; "
                   "call\t__tls_get_addr@PLT",
                  [(X86tlsaddr tls64addr:$sym)]>,
                  Requires<[In64BitMode]>;

let AddedComplexity = 5, isCodeGenOnly = 1 in
def MOV64GSrm : RI<0x8B, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
                 "movq\t%gs:$src, $dst",
                 [(set GR64:$dst, (gsload addr:$src))]>, SegGS;

let AddedComplexity = 5, isCodeGenOnly = 1 in
def MOV64FSrm : RI<0x8B, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$src),
                 "movq\t%fs:$src, $dst",
                 [(set GR64:$dst, (fsload addr:$src))]>, SegFS;

//===----------------------------------------------------------------------===//
// Atomic Instructions
//===----------------------------------------------------------------------===//

let Defs = [RAX, EFLAGS], Uses = [RAX] in {
def LCMPXCHG64 : RI<0xB1, MRMDestMem, (outs), (ins i64mem:$ptr, GR64:$swap),
               "lock\n\t"
               "cmpxchgq\t$swap,$ptr",
               [(X86cas addr:$ptr, GR64:$swap, 8)]>, TB, LOCK;
}

let Constraints = "$val = $dst" in {
let Defs = [EFLAGS] in
def LXADD64 : RI<0xC1, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$ptr,GR64:$val),
               "lock\n\t"
               "xadd\t$val, $ptr",
               [(set GR64:$dst, (atomic_load_add_64 addr:$ptr, GR64:$val))]>,
                TB, LOCK;

def XCHG64rm : RI<0x87, MRMSrcMem, (outs GR64:$dst), (ins i64mem:$ptr,GR64:$val),
                  "xchg\t$val, $ptr", 
                  [(set GR64:$dst, (atomic_swap_64 addr:$ptr, GR64:$val))]>;
}

// Optimized codegen when the non-memory output is not used.
// FIXME: Use normal add / sub instructions and add lock prefix dynamically.
def LOCK_ADD64mr : RI<0x03, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2),
                      "lock\n\t"
                      "add{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
def LOCK_ADD64mi8 : RIi8<0x83, MRM0m, (outs),
                                      (ins i64mem:$dst, i64i8imm :$src2),
                    "lock\n\t"
                    "add{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
def LOCK_ADD64mi32 : RIi32<0x81, MRM0m, (outs),
                                        (ins i64mem:$dst, i64i32imm :$src2),
                      "lock\n\t"
                      "add{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
def LOCK_SUB64mr : RI<0x29, MRMDestMem, (outs), (ins i64mem:$dst, GR64:$src2), 
                      "lock\n\t"
                      "sub{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
def LOCK_SUB64mi8 : RIi8<0x83, MRM5m, (outs),
                                      (ins i64mem:$dst, i64i8imm :$src2), 
                      "lock\n\t"
                      "sub{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
def LOCK_SUB64mi32 : RIi32<0x81, MRM5m, (outs),
                                        (ins i64mem:$dst, i64i32imm:$src2),
                      "lock\n\t"
                      "sub{q}\t{$src2, $dst|$dst, $src2}", []>, LOCK;
def LOCK_INC64m : RI<0xFF, MRM0m, (outs), (ins i64mem:$dst),
                     "lock\n\t"
                     "inc{q}\t$dst", []>, LOCK;
def LOCK_DEC64m : RI<0xFF, MRM1m, (outs), (ins i64mem:$dst),
                      "lock\n\t"
                      "dec{q}\t$dst", []>, LOCK;

// Atomic exchange, and, or, xor
let Constraints = "$val = $dst", Defs = [EFLAGS],
                  usesCustomDAGSchedInserter = 1 in {
def ATOMAND64 : I<0, Pseudo, (outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
               "#ATOMAND64 PSEUDO!", 
               [(set GR64:$dst, (atomic_load_and_64 addr:$ptr, GR64:$val))]>;
def ATOMOR64 : I<0, Pseudo, (outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
               "#ATOMOR64 PSEUDO!", 
               [(set GR64:$dst, (atomic_load_or_64 addr:$ptr, GR64:$val))]>;
def ATOMXOR64 : I<0, Pseudo,(outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
               "#ATOMXOR64 PSEUDO!", 
               [(set GR64:$dst, (atomic_load_xor_64 addr:$ptr, GR64:$val))]>;
def ATOMNAND64 : I<0, Pseudo,(outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
               "#ATOMNAND64 PSEUDO!", 
               [(set GR64:$dst, (atomic_load_nand_64 addr:$ptr, GR64:$val))]>;
def ATOMMIN64: I<0, Pseudo, (outs GR64:$dst), (ins i64mem:$ptr, GR64:$val),
               "#ATOMMIN64 PSEUDO!", 
               [(set GR64:$dst, (atomic_load_min_64 addr:$ptr, GR64:$val))]>;
def ATOMMAX64: I<0, Pseudo, (outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
               "#ATOMMAX64 PSEUDO!", 
               [(set GR64:$dst, (atomic_load_max_64 addr:$ptr, GR64:$val))]>;
def ATOMUMIN64: I<0, Pseudo, (outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
               "#ATOMUMIN64 PSEUDO!", 
               [(set GR64:$dst, (atomic_load_umin_64 addr:$ptr, GR64:$val))]>;
def ATOMUMAX64: I<0, Pseudo, (outs GR64:$dst),(ins i64mem:$ptr, GR64:$val),
               "#ATOMUMAX64 PSEUDO!", 
               [(set GR64:$dst, (atomic_load_umax_64 addr:$ptr, GR64:$val))]>;
}

//===----------------------------------------------------------------------===//
// Non-Instruction Patterns
//===----------------------------------------------------------------------===//

// ConstantPool GlobalAddress, ExternalSymbol, and JumpTable when not in small
// code model mode, should use 'movabs'.  FIXME: This is really a hack, the
//  'movabs' predicate should handle this sort of thing.
def : Pat<(i64 (X86Wrapper tconstpool  :$dst)),
          (MOV64ri tconstpool  :$dst)>, Requires<[FarData]>;
def : Pat<(i64 (X86Wrapper tjumptable  :$dst)),
          (MOV64ri tjumptable  :$dst)>, Requires<[FarData]>;
def : Pat<(i64 (X86Wrapper tglobaladdr :$dst)),
          (MOV64ri tglobaladdr :$dst)>, Requires<[FarData]>;
def : Pat<(i64 (X86Wrapper texternalsym:$dst)),
          (MOV64ri texternalsym:$dst)>, Requires<[FarData]>;

// In static codegen with small code model, we can get the address of a label
// into a register with 'movl'.  FIXME: This is a hack, the 'imm' predicate of
// the MOV64ri64i32 should accept these.
def : Pat<(i64 (X86Wrapper tconstpool  :$dst)),
          (MOV64ri64i32 tconstpool  :$dst)>, Requires<[SmallCode]>;
def : Pat<(i64 (X86Wrapper tjumptable  :$dst)),
          (MOV64ri64i32 tjumptable  :$dst)>, Requires<[SmallCode]>;
def : Pat<(i64 (X86Wrapper tglobaladdr :$dst)),
          (MOV64ri64i32 tglobaladdr :$dst)>, Requires<[SmallCode]>;
def : Pat<(i64 (X86Wrapper texternalsym:$dst)),
          (MOV64ri64i32 texternalsym:$dst)>, Requires<[SmallCode]>;

// In kernel code model, we can get the address of a label
// into a register with 'movq'.  FIXME: This is a hack, the 'imm' predicate of
// the MOV64ri32 should accept these.
def : Pat<(i64 (X86Wrapper tconstpool  :$dst)),
          (MOV64ri32 tconstpool  :$dst)>, Requires<[KernelCode]>;
def : Pat<(i64 (X86Wrapper tjumptable  :$dst)),
          (MOV64ri32 tjumptable  :$dst)>, Requires<[KernelCode]>;
def : Pat<(i64 (X86Wrapper tglobaladdr :$dst)),
          (MOV64ri32 tglobaladdr :$dst)>, Requires<[KernelCode]>;
def : Pat<(i64 (X86Wrapper texternalsym:$dst)),
          (MOV64ri32 texternalsym:$dst)>, Requires<[KernelCode]>;

// If we have small model and -static mode, it is safe to store global addresses
// directly as immediates.  FIXME: This is really a hack, the 'imm' predicate
// for MOV64mi32 should handle this sort of thing.
def : Pat<(store (i64 (X86Wrapper tconstpool:$src)), addr:$dst),
          (MOV64mi32 addr:$dst, tconstpool:$src)>,
          Requires<[NearData, IsStatic]>;
def : Pat<(store (i64 (X86Wrapper tjumptable:$src)), addr:$dst),
          (MOV64mi32 addr:$dst, tjumptable:$src)>,
          Requires<[NearData, IsStatic]>;
def : Pat<(store (i64 (X86Wrapper tglobaladdr:$src)), addr:$dst),
          (MOV64mi32 addr:$dst, tglobaladdr:$src)>,
          Requires<[NearData, IsStatic]>;
def : Pat<(store (i64 (X86Wrapper texternalsym:$src)), addr:$dst),
          (MOV64mi32 addr:$dst, texternalsym:$src)>,
          Requires<[NearData, IsStatic]>;

// Calls
// Direct PC relative function call for small code model. 32-bit displacement
// sign extended to 64-bit.
def : Pat<(X86call (i64 tglobaladdr:$dst)),
          (CALL64pcrel32 tglobaladdr:$dst)>, Requires<[NotWin64]>;
def : Pat<(X86call (i64 texternalsym:$dst)),
          (CALL64pcrel32 texternalsym:$dst)>, Requires<[NotWin64]>;

def : Pat<(X86call (i64 tglobaladdr:$dst)),
          (WINCALL64pcrel32 tglobaladdr:$dst)>, Requires<[IsWin64]>;
def : Pat<(X86call (i64 texternalsym:$dst)),
          (WINCALL64pcrel32 texternalsym:$dst)>, Requires<[IsWin64]>;

// tailcall stuff
def : Pat<(X86tcret GR64:$dst, imm:$off),
          (TCRETURNri64 GR64:$dst, imm:$off)>;

def : Pat<(X86tcret (i64 tglobaladdr:$dst), imm:$off),
          (TCRETURNdi64 texternalsym:$dst, imm:$off)>;

def : Pat<(X86tcret (i64 texternalsym:$dst), imm:$off),
          (TCRETURNdi64 texternalsym:$dst, imm:$off)>;

// Comparisons.

// TEST R,R is smaller than CMP R,0
def : Pat<(parallel (X86cmp GR64:$src1, 0), (implicit EFLAGS)),
          (TEST64rr GR64:$src1, GR64:$src1)>;

// Conditional moves with folded loads with operands swapped and conditions
// inverted.
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_B, EFLAGS),
          (CMOVAE64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_AE, EFLAGS),
          (CMOVB64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_E, EFLAGS),
          (CMOVNE64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_NE, EFLAGS),
          (CMOVE64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_BE, EFLAGS),
          (CMOVA64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_A, EFLAGS),
          (CMOVBE64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_L, EFLAGS),
          (CMOVGE64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_GE, EFLAGS),
          (CMOVL64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_LE, EFLAGS),
          (CMOVG64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_G, EFLAGS),
          (CMOVLE64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_P, EFLAGS),
          (CMOVNP64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_NP, EFLAGS),
          (CMOVP64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_S, EFLAGS),
          (CMOVNS64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_NS, EFLAGS),
          (CMOVS64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_O, EFLAGS),
          (CMOVNO64rm GR64:$src2, addr:$src1)>;
def : Pat<(X86cmov (loadi64 addr:$src1), GR64:$src2, X86_COND_NO, EFLAGS),
          (CMOVO64rm GR64:$src2, addr:$src1)>;

// zextload bool -> zextload byte
def : Pat<(zextloadi64i1 addr:$src), (MOVZX64rm8 addr:$src)>;

// extload
// When extloading from 16-bit and smaller memory locations into 64-bit registers,
// use zero-extending loads so that the entire 64-bit register is defined, avoiding
// partial-register updates.
def : Pat<(extloadi64i1 addr:$src),  (MOVZX64rm8  addr:$src)>;
def : Pat<(extloadi64i8 addr:$src),  (MOVZX64rm8  addr:$src)>;
def : Pat<(extloadi64i16 addr:$src), (MOVZX64rm16 addr:$src)>;
// For other extloads, use subregs, since the high contents of the register are
// defined after an extload.
def : Pat<(extloadi64i32 addr:$src),
          (INSERT_SUBREG (i64 (IMPLICIT_DEF)), (MOV32rm addr:$src),
                         x86_subreg_32bit)>;
def : Pat<(extloadi16i1 addr:$src), 
          (INSERT_SUBREG (i16 (IMPLICIT_DEF)), (MOV8rm addr:$src), 
                         x86_subreg_8bit)>,
         Requires<[In64BitMode]>;
def : Pat<(extloadi16i8 addr:$src), 
          (INSERT_SUBREG (i16 (IMPLICIT_DEF)), (MOV8rm addr:$src), 
                         x86_subreg_8bit)>,
         Requires<[In64BitMode]>;

// anyext
def : Pat<(i64 (anyext GR8:$src)),
          (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR8:$src, x86_subreg_8bit)>;
def : Pat<(i64 (anyext GR16:$src)),
          (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR16:$src, x86_subreg_16bit)>;
def : Pat<(i64 (anyext GR32:$src)), 
          (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GR32:$src, x86_subreg_32bit)>;
def : Pat<(i16 (anyext GR8:$src)),
          (INSERT_SUBREG (i16 (IMPLICIT_DEF)), GR8:$src, x86_subreg_8bit)>,
         Requires<[In64BitMode]>;
def : Pat<(i32 (anyext GR8:$src)),
          (INSERT_SUBREG (i32 (IMPLICIT_DEF)), GR8:$src, x86_subreg_8bit)>,
         Requires<[In64BitMode]>;

//===----------------------------------------------------------------------===//
// Some peepholes
//===----------------------------------------------------------------------===//

// Odd encoding trick: -128 fits into an 8-bit immediate field while
// +128 doesn't, so in this special case use a sub instead of an add.
def : Pat<(add GR64:$src1, 128),
          (SUB64ri8 GR64:$src1, -128)>;
def : Pat<(store (add (loadi64 addr:$dst), 128), addr:$dst),
          (SUB64mi8 addr:$dst, -128)>;

// The same trick applies for 32-bit immediate fields in 64-bit
// instructions.
def : Pat<(add GR64:$src1, 0x0000000080000000),
          (SUB64ri32 GR64:$src1, 0xffffffff80000000)>;
def : Pat<(store (add (loadi64 addr:$dst), 0x00000000800000000), addr:$dst),
          (SUB64mi32 addr:$dst, 0xffffffff80000000)>;

// r & (2^32-1) ==> movz
def : Pat<(and GR64:$src, 0x00000000FFFFFFFF),
          (MOVZX64rr32 (EXTRACT_SUBREG GR64:$src, x86_subreg_32bit))>;
// r & (2^16-1) ==> movz
def : Pat<(and GR64:$src, 0xffff),
          (MOVZX64rr16 (i16 (EXTRACT_SUBREG GR64:$src, x86_subreg_16bit)))>;
// r & (2^8-1) ==> movz
def : Pat<(and GR64:$src, 0xff),
          (MOVZX64rr8 (i8 (EXTRACT_SUBREG GR64:$src, x86_subreg_8bit)))>;
// r & (2^8-1) ==> movz
def : Pat<(and GR32:$src1, 0xff),
           (MOVZX32rr8 (EXTRACT_SUBREG GR32:$src1, x86_subreg_8bit))>,
      Requires<[In64BitMode]>;
// r & (2^8-1) ==> movz
def : Pat<(and GR16:$src1, 0xff),
           (MOVZX16rr8 (i8 (EXTRACT_SUBREG GR16:$src1, x86_subreg_8bit)))>,
      Requires<[In64BitMode]>;

// sext_inreg patterns
def : Pat<(sext_inreg GR64:$src, i32),
          (MOVSX64rr32 (EXTRACT_SUBREG GR64:$src, x86_subreg_32bit))>;
def : Pat<(sext_inreg GR64:$src, i16),
          (MOVSX64rr16 (EXTRACT_SUBREG GR64:$src, x86_subreg_16bit))>;
def : Pat<(sext_inreg GR64:$src, i8),
          (MOVSX64rr8 (EXTRACT_SUBREG GR64:$src, x86_subreg_8bit))>;
def : Pat<(sext_inreg GR32:$src, i8),
          (MOVSX32rr8 (EXTRACT_SUBREG GR32:$src, x86_subreg_8bit))>,
      Requires<[In64BitMode]>;
def : Pat<(sext_inreg GR16:$src, i8),
          (MOVSX16rr8 (i8 (EXTRACT_SUBREG GR16:$src, x86_subreg_8bit)))>,
      Requires<[In64BitMode]>;

// trunc patterns
def : Pat<(i32 (trunc GR64:$src)),
          (EXTRACT_SUBREG GR64:$src, x86_subreg_32bit)>;
def : Pat<(i16 (trunc GR64:$src)),
          (EXTRACT_SUBREG GR64:$src, x86_subreg_16bit)>;
def : Pat<(i8 (trunc GR64:$src)),
          (EXTRACT_SUBREG GR64:$src, x86_subreg_8bit)>;
def : Pat<(i8 (trunc GR32:$src)),
          (EXTRACT_SUBREG GR32:$src, x86_subreg_8bit)>,
      Requires<[In64BitMode]>;
def : Pat<(i8 (trunc GR16:$src)),
          (EXTRACT_SUBREG GR16:$src, x86_subreg_8bit)>,
      Requires<[In64BitMode]>;

// h-register tricks.
// For now, be conservative on x86-64 and use an h-register extract only if the
// value is immediately zero-extended or stored, which are somewhat common
// cases. This uses a bunch of code to prevent a register requiring a REX prefix
// from being allocated in the same instruction as the h register, as there's
// currently no way to describe this requirement to the register allocator.

// h-register extract and zero-extend.
def : Pat<(and (srl_su GR64:$src, (i8 8)), (i64 255)),
          (SUBREG_TO_REG
            (i64 0),
            (MOVZX32_NOREXrr8
              (EXTRACT_SUBREG (COPY_TO_REGCLASS GR64:$src, GR64_ABCD),
                              x86_subreg_8bit_hi)),
            x86_subreg_32bit)>;
def : Pat<(and (srl_su GR32:$src, (i8 8)), (i32 255)),
          (MOVZX32_NOREXrr8
            (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_ABCD),
                            x86_subreg_8bit_hi))>,
      Requires<[In64BitMode]>;
def : Pat<(srl_su GR16:$src, (i8 8)),
          (EXTRACT_SUBREG
            (MOVZX32_NOREXrr8
              (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD),
                              x86_subreg_8bit_hi)),
            x86_subreg_16bit)>,
      Requires<[In64BitMode]>;
def : Pat<(i32 (zext (srl_su GR16:$src, (i8 8)))),
          (MOVZX32_NOREXrr8
            (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD),
                            x86_subreg_8bit_hi))>,
      Requires<[In64BitMode]>;
def : Pat<(i64 (zext (srl_su GR16:$src, (i8 8)))),
          (SUBREG_TO_REG
            (i64 0),
            (MOVZX32_NOREXrr8
              (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD),
                              x86_subreg_8bit_hi)),
            x86_subreg_32bit)>;

// h-register extract and store.
def : Pat<(store (i8 (trunc_su (srl_su GR64:$src, (i8 8)))), addr:$dst),
          (MOV8mr_NOREX
            addr:$dst,
            (EXTRACT_SUBREG (COPY_TO_REGCLASS GR64:$src, GR64_ABCD),
                            x86_subreg_8bit_hi))>;
def : Pat<(store (i8 (trunc_su (srl_su GR32:$src, (i8 8)))), addr:$dst),
          (MOV8mr_NOREX
            addr:$dst,
            (EXTRACT_SUBREG (COPY_TO_REGCLASS GR32:$src, GR32_ABCD),
                            x86_subreg_8bit_hi))>,
      Requires<[In64BitMode]>;
def : Pat<(store (i8 (trunc_su (srl_su GR16:$src, (i8 8)))), addr:$dst),
          (MOV8mr_NOREX
            addr:$dst,
            (EXTRACT_SUBREG (COPY_TO_REGCLASS GR16:$src, GR16_ABCD),
                            x86_subreg_8bit_hi))>,
      Requires<[In64BitMode]>;

// (shl x, 1) ==> (add x, x)
def : Pat<(shl GR64:$src1, (i8 1)), (ADD64rr GR64:$src1, GR64:$src1)>;

// (shl x (and y, 63)) ==> (shl x, y)
def : Pat<(shl GR64:$src1, (and CL:$amt, 63)),
          (SHL64rCL GR64:$src1)>;
def : Pat<(store (shl (loadi64 addr:$dst), (and CL:$amt, 63)), addr:$dst),
          (SHL64mCL addr:$dst)>;

def : Pat<(srl GR64:$src1, (and CL:$amt, 63)),
          (SHR64rCL GR64:$src1)>;
def : Pat<(store (srl (loadi64 addr:$dst), (and CL:$amt, 63)), addr:$dst),
          (SHR64mCL addr:$dst)>;

def : Pat<(sra GR64:$src1, (and CL:$amt, 63)),
          (SAR64rCL GR64:$src1)>;
def : Pat<(store (sra (loadi64 addr:$dst), (and CL:$amt, 63)), addr:$dst),
          (SAR64mCL addr:$dst)>;

// (or (x >> c) | (y << (64 - c))) ==> (shrd64 x, y, c)
def : Pat<(or (srl GR64:$src1, CL:$amt),
              (shl GR64:$src2, (sub 64, CL:$amt))),
          (SHRD64rrCL GR64:$src1, GR64:$src2)>;

def : Pat<(store (or (srl (loadi64 addr:$dst), CL:$amt),
                     (shl GR64:$src2, (sub 64, CL:$amt))), addr:$dst),
          (SHRD64mrCL addr:$dst, GR64:$src2)>;

def : Pat<(or (srl GR64:$src1, (i8 (trunc RCX:$amt))),
              (shl GR64:$src2, (i8 (trunc (sub 64, RCX:$amt))))),
          (SHRD64rrCL GR64:$src1, GR64:$src2)>;

def : Pat<(store (or (srl (loadi64 addr:$dst), (i8 (trunc RCX:$amt))),
                     (shl GR64:$src2, (i8 (trunc (sub 64, RCX:$amt))))),
                 addr:$dst),
          (SHRD64mrCL addr:$dst, GR64:$src2)>;

def : Pat<(shrd GR64:$src1, (i8 imm:$amt1), GR64:$src2, (i8 imm:$amt2)),
          (SHRD64rri8 GR64:$src1, GR64:$src2, (i8 imm:$amt1))>;

def : Pat<(store (shrd (loadi64 addr:$dst), (i8 imm:$amt1),
                       GR64:$src2, (i8 imm:$amt2)), addr:$dst),
          (SHRD64mri8 addr:$dst, GR64:$src2, (i8 imm:$amt1))>;

// (or (x << c) | (y >> (64 - c))) ==> (shld64 x, y, c)
def : Pat<(or (shl GR64:$src1, CL:$amt),
              (srl GR64:$src2, (sub 64, CL:$amt))),
          (SHLD64rrCL GR64:$src1, GR64:$src2)>;

def : Pat<(store (or (shl (loadi64 addr:$dst), CL:$amt),
                     (srl GR64:$src2, (sub 64, CL:$amt))), addr:$dst),
          (SHLD64mrCL addr:$dst, GR64:$src2)>;

def : Pat<(or (shl GR64:$src1, (i8 (trunc RCX:$amt))),
              (srl GR64:$src2, (i8 (trunc (sub 64, RCX:$amt))))),
          (SHLD64rrCL GR64:$src1, GR64:$src2)>;

def : Pat<(store (or (shl (loadi64 addr:$dst), (i8 (trunc RCX:$amt))),
                     (srl GR64:$src2, (i8 (trunc (sub 64, RCX:$amt))))),
                 addr:$dst),
          (SHLD64mrCL addr:$dst, GR64:$src2)>;

def : Pat<(shld GR64:$src1, (i8 imm:$amt1), GR64:$src2, (i8 imm:$amt2)),
          (SHLD64rri8 GR64:$src1, GR64:$src2, (i8 imm:$amt1))>;

def : Pat<(store (shld (loadi64 addr:$dst), (i8 imm:$amt1),
                       GR64:$src2, (i8 imm:$amt2)), addr:$dst),
          (SHLD64mri8 addr:$dst, GR64:$src2, (i8 imm:$amt1))>;

// X86 specific add which produces a flag.
def : Pat<(addc GR64:$src1, GR64:$src2),
          (ADD64rr GR64:$src1, GR64:$src2)>;
def : Pat<(addc GR64:$src1, (load addr:$src2)),
          (ADD64rm GR64:$src1, addr:$src2)>;
def : Pat<(addc GR64:$src1, i64immSExt8:$src2),
          (ADD64ri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(addc GR64:$src1, i64immSExt32:$src2),
          (ADD64ri32 GR64:$src1, imm:$src2)>;

def : Pat<(subc GR64:$src1, GR64:$src2),
          (SUB64rr GR64:$src1, GR64:$src2)>;
def : Pat<(subc GR64:$src1, (load addr:$src2)),
          (SUB64rm GR64:$src1, addr:$src2)>;
def : Pat<(subc GR64:$src1, i64immSExt8:$src2),
          (SUB64ri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(subc GR64:$src1, imm:$src2),
          (SUB64ri32 GR64:$src1, i64immSExt32:$src2)>;

//===----------------------------------------------------------------------===//
// EFLAGS-defining Patterns
//===----------------------------------------------------------------------===//

// Register-Register Addition with EFLAGS result
def : Pat<(parallel (X86add_flag GR64:$src1, GR64:$src2),
                    (implicit EFLAGS)),
          (ADD64rr GR64:$src1, GR64:$src2)>;

// Register-Integer Addition with EFLAGS result
def : Pat<(parallel (X86add_flag GR64:$src1, i64immSExt8:$src2),
                    (implicit EFLAGS)),
          (ADD64ri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(parallel (X86add_flag GR64:$src1, i64immSExt32:$src2),
                    (implicit EFLAGS)),
          (ADD64ri32 GR64:$src1, i64immSExt32:$src2)>;

// Register-Memory Addition with EFLAGS result
def : Pat<(parallel (X86add_flag GR64:$src1, (loadi64 addr:$src2)),
                    (implicit EFLAGS)),
          (ADD64rm GR64:$src1, addr:$src2)>;

// Memory-Register Addition with EFLAGS result
def : Pat<(parallel (store (X86add_flag (loadi64 addr:$dst), GR64:$src2),
                           addr:$dst),
                    (implicit EFLAGS)),
          (ADD64mr addr:$dst, GR64:$src2)>;
def : Pat<(parallel (store (X86add_flag (loadi64 addr:$dst), i64immSExt8:$src2),
                           addr:$dst),
                    (implicit EFLAGS)),
          (ADD64mi8 addr:$dst, i64immSExt8:$src2)>;
def : Pat<(parallel (store (X86add_flag (loadi64 addr:$dst), i64immSExt32:$src2),
                           addr:$dst),
                    (implicit EFLAGS)),
          (ADD64mi32 addr:$dst, i64immSExt32:$src2)>;

// Register-Register Subtraction with EFLAGS result
def : Pat<(parallel (X86sub_flag GR64:$src1, GR64:$src2),
                    (implicit EFLAGS)),
          (SUB64rr GR64:$src1, GR64:$src2)>;

// Register-Memory Subtraction with EFLAGS result
def : Pat<(parallel (X86sub_flag GR64:$src1, (loadi64 addr:$src2)),
                    (implicit EFLAGS)),
          (SUB64rm GR64:$src1, addr:$src2)>;

// Register-Integer Subtraction with EFLAGS result
def : Pat<(parallel (X86sub_flag GR64:$src1, i64immSExt8:$src2),
                    (implicit EFLAGS)),
          (SUB64ri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(parallel (X86sub_flag GR64:$src1, i64immSExt32:$src2),
                    (implicit EFLAGS)),
          (SUB64ri32 GR64:$src1, i64immSExt32:$src2)>;

// Memory-Register Subtraction with EFLAGS result
def : Pat<(parallel (store (X86sub_flag (loadi64 addr:$dst), GR64:$src2),
                           addr:$dst),
                    (implicit EFLAGS)),
          (SUB64mr addr:$dst, GR64:$src2)>;

// Memory-Integer Subtraction with EFLAGS result
def : Pat<(parallel (store (X86sub_flag (loadi64 addr:$dst), i64immSExt8:$src2),
                           addr:$dst),
                    (implicit EFLAGS)),
          (SUB64mi8 addr:$dst, i64immSExt8:$src2)>;
def : Pat<(parallel (store (X86sub_flag (loadi64 addr:$dst), i64immSExt32:$src2),
                           addr:$dst),
                    (implicit EFLAGS)),
          (SUB64mi32 addr:$dst, i64immSExt32:$src2)>;

// Register-Register Signed Integer Multiplication with EFLAGS result
def : Pat<(parallel (X86smul_flag GR64:$src1, GR64:$src2),
                    (implicit EFLAGS)),
          (IMUL64rr GR64:$src1, GR64:$src2)>;

// Register-Memory Signed Integer Multiplication with EFLAGS result
def : Pat<(parallel (X86smul_flag GR64:$src1, (loadi64 addr:$src2)),
                    (implicit EFLAGS)),
          (IMUL64rm GR64:$src1, addr:$src2)>;

// Register-Integer Signed Integer Multiplication with EFLAGS result
def : Pat<(parallel (X86smul_flag GR64:$src1, i64immSExt8:$src2),
                    (implicit EFLAGS)),
          (IMUL64rri8 GR64:$src1, i64immSExt8:$src2)>;
def : Pat<(parallel (X86smul_flag GR64:$src1, i64immSExt32:$src2),
                    (implicit EFLAGS)),
          (IMUL64rri32 GR64:$src1, i64immSExt32:$src2)>;

// Memory-Integer Signed Integer Multiplication with EFLAGS result
def : Pat<(parallel (X86smul_flag (loadi64 addr:$src1), i64immSExt8:$src2),
                    (implicit EFLAGS)),
          (IMUL64rmi8 addr:$src1, i64immSExt8:$src2)>;
def : Pat<(parallel (X86smul_flag (loadi64 addr:$src1), i64immSExt32:$src2),
                    (implicit EFLAGS)),
          (IMUL64rmi32 addr:$src1, i64immSExt32:$src2)>;

// INC and DEC with EFLAGS result. Note that these do not set CF.
def : Pat<(parallel (X86inc_flag GR16:$src), (implicit EFLAGS)),
          (INC64_16r GR16:$src)>, Requires<[In64BitMode]>;
def : Pat<(parallel (store (i16 (X86inc_flag (loadi16 addr:$dst))), addr:$dst),
                    (implicit EFLAGS)),
          (INC64_16m addr:$dst)>, Requires<[In64BitMode]>;
def : Pat<(parallel (X86dec_flag GR16:$src), (implicit EFLAGS)),
          (DEC64_16r GR16:$src)>, Requires<[In64BitMode]>;
def : Pat<(parallel (store (i16 (X86dec_flag (loadi16 addr:$dst))), addr:$dst),
                    (implicit EFLAGS)),
          (DEC64_16m addr:$dst)>, Requires<[In64BitMode]>;

def : Pat<(parallel (X86inc_flag GR32:$src), (implicit EFLAGS)),
          (INC64_32r GR32:$src)>, Requires<[In64BitMode]>;
def : Pat<(parallel (store (i32 (X86inc_flag (loadi32 addr:$dst))), addr:$dst),
                    (implicit EFLAGS)),
          (INC64_32m addr:$dst)>, Requires<[In64BitMode]>;
def : Pat<(parallel (X86dec_flag GR32:$src), (implicit EFLAGS)),
          (DEC64_32r GR32:$src)>, Requires<[In64BitMode]>;
def : Pat<(parallel (store (i32 (X86dec_flag (loadi32 addr:$dst))), addr:$dst),
                    (implicit EFLAGS)),
          (DEC64_32m addr:$dst)>, Requires<[In64BitMode]>;

def : Pat<(parallel (X86inc_flag GR64:$src), (implicit EFLAGS)),
          (INC64r GR64:$src)>;
def : Pat<(parallel (store (i64 (X86inc_flag (loadi64 addr:$dst))), addr:$dst),
                    (implicit EFLAGS)),
          (INC64m addr:$dst)>;
def : Pat<(parallel (X86dec_flag GR64:$src), (implicit EFLAGS)),
          (DEC64r GR64:$src)>;
def : Pat<(parallel (store (i64 (X86dec_flag (loadi64 addr:$dst))), addr:$dst),
                    (implicit EFLAGS)),
          (DEC64m addr:$dst)>;

//===----------------------------------------------------------------------===//
// X86-64 SSE Instructions
//===----------------------------------------------------------------------===//

// Move instructions...

def MOV64toPQIrr : RPDI<0x6E, MRMSrcReg, (outs VR128:$dst), (ins GR64:$src),
                        "mov{d|q}\t{$src, $dst|$dst, $src}",
                        [(set VR128:$dst,
                          (v2i64 (scalar_to_vector GR64:$src)))]>;
def MOVPQIto64rr  : RPDI<0x7E, MRMDestReg, (outs GR64:$dst), (ins VR128:$src),
                         "mov{d|q}\t{$src, $dst|$dst, $src}",
                         [(set GR64:$dst, (vector_extract (v2i64 VR128:$src),
                                           (iPTR 0)))]>;

def MOV64toSDrr : RPDI<0x6E, MRMSrcReg, (outs FR64:$dst), (ins GR64:$src),
                       "mov{d|q}\t{$src, $dst|$dst, $src}",
                       [(set FR64:$dst, (bitconvert GR64:$src))]>;
def MOV64toSDrm : RPDI<0x6E, MRMSrcMem, (outs FR64:$dst), (ins i64mem:$src),
                       "movq\t{$src, $dst|$dst, $src}",
                       [(set FR64:$dst, (bitconvert (loadi64 addr:$src)))]>;

def MOVSDto64rr  : RPDI<0x7E, MRMDestReg, (outs GR64:$dst), (ins FR64:$src),
                        "mov{d|q}\t{$src, $dst|$dst, $src}",
                        [(set GR64:$dst, (bitconvert FR64:$src))]>;
def MOVSDto64mr  : RPDI<0x7E, MRMDestMem, (outs), (ins i64mem:$dst, FR64:$src),
                        "movq\t{$src, $dst|$dst, $src}",
                        [(store (i64 (bitconvert FR64:$src)), addr:$dst)]>;

//===----------------------------------------------------------------------===//
// X86-64 SSE4.1 Instructions
//===----------------------------------------------------------------------===//

/// SS41I_extract32 - SSE 4.1 extract 32 bits to int reg or memory destination
multiclass SS41I_extract64<bits<8> opc, string OpcodeStr> {
  def rr : SS4AIi8<opc, MRMDestReg, (outs GR64:$dst),
                 (ins VR128:$src1, i32i8imm:$src2),
                 !strconcat(OpcodeStr, 
                  "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
                 [(set GR64:$dst,
                  (extractelt (v2i64 VR128:$src1), imm:$src2))]>, OpSize, REX_W;
  def mr : SS4AIi8<opc, MRMDestMem, (outs),
                 (ins i64mem:$dst, VR128:$src1, i32i8imm:$src2),
                 !strconcat(OpcodeStr, 
                  "\t{$src2, $src1, $dst|$dst, $src1, $src2}"),
                 [(store (extractelt (v2i64 VR128:$src1), imm:$src2),
                          addr:$dst)]>, OpSize, REX_W;
}

defm PEXTRQ      : SS41I_extract64<0x16, "pextrq">;

let isTwoAddress = 1 in {
  multiclass SS41I_insert64<bits<8> opc, string OpcodeStr> {
    def rr : SS4AIi8<opc, MRMSrcReg, (outs VR128:$dst),
                   (ins VR128:$src1, GR64:$src2, i32i8imm:$src3),
                   !strconcat(OpcodeStr, 
                    "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
                   [(set VR128:$dst, 
                     (v2i64 (insertelt VR128:$src1, GR64:$src2, imm:$src3)))]>,
                   OpSize, REX_W;
    def rm : SS4AIi8<opc, MRMSrcMem, (outs VR128:$dst),
                   (ins VR128:$src1, i64mem:$src2, i32i8imm:$src3),
                   !strconcat(OpcodeStr,
                    "\t{$src3, $src2, $dst|$dst, $src2, $src3}"),
                   [(set VR128:$dst, 
                     (v2i64 (insertelt VR128:$src1, (loadi64 addr:$src2),
                                       imm:$src3)))]>, OpSize, REX_W;
  }
}

defm PINSRQ      : SS41I_insert64<0x22, "pinsrq">;