Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
//=- AArch64InstrInfo.td - Describe the AArch64 Instructions -*- tablegen -*-=//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// AArch64 Instruction definitions.
//
//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//
// ARM Instruction Predicate Definitions.
//
def HasV8_1a         : Predicate<"Subtarget->hasV8_1aOps()">,
                                 AssemblerPredicate<(all_of HasV8_1aOps), "armv8.1a">;
def HasV8_2a         : Predicate<"Subtarget->hasV8_2aOps()">,
                                 AssemblerPredicate<(all_of HasV8_2aOps), "armv8.2a">;
def HasV8_3a         : Predicate<"Subtarget->hasV8_3aOps()">,
                                 AssemblerPredicate<(all_of HasV8_3aOps), "armv8.3a">;
def HasV8_4a         : Predicate<"Subtarget->hasV8_4aOps()">,
                                 AssemblerPredicate<(all_of HasV8_4aOps), "armv8.4a">;
def HasV8_5a         : Predicate<"Subtarget->hasV8_5aOps()">,
                                 AssemblerPredicate<(all_of HasV8_5aOps), "armv8.5a">;
def HasV8_6a         : Predicate<"Subtarget->hasV8_6aOps()">,
                                 AssemblerPredicate<(all_of HasV8_6aOps), "armv8.6a">;
def HasVH            : Predicate<"Subtarget->hasVH()">,
                       AssemblerPredicate<(all_of FeatureVH), "vh">;

def HasLOR           : Predicate<"Subtarget->hasLOR()">,
                       AssemblerPredicate<(all_of FeatureLOR), "lor">;

def HasPA            : Predicate<"Subtarget->hasPA()">,
                       AssemblerPredicate<(all_of FeaturePA), "pa">;

def HasJS            : Predicate<"Subtarget->hasJS()">,
                       AssemblerPredicate<(all_of FeatureJS), "jsconv">;

def HasCCIDX         : Predicate<"Subtarget->hasCCIDX()">,
                       AssemblerPredicate<(all_of FeatureCCIDX), "ccidx">;

def HasComplxNum      : Predicate<"Subtarget->hasComplxNum()">,
                       AssemblerPredicate<(all_of FeatureComplxNum), "complxnum">;

def HasNV            : Predicate<"Subtarget->hasNV()">,
                       AssemblerPredicate<(all_of FeatureNV), "nv">;

def HasRASv8_4       : Predicate<"Subtarget->hasRASv8_4()">,
                       AssemblerPredicate<(all_of FeatureRASv8_4), "rasv8_4">;

def HasMPAM          : Predicate<"Subtarget->hasMPAM()">,
                       AssemblerPredicate<(all_of FeatureMPAM), "mpam">;

def HasDIT           : Predicate<"Subtarget->hasDIT()">,
                       AssemblerPredicate<(all_of FeatureDIT), "dit">;

def HasTRACEV8_4         : Predicate<"Subtarget->hasTRACEV8_4()">,
                       AssemblerPredicate<(all_of FeatureTRACEV8_4), "tracev8.4">;

def HasAM            : Predicate<"Subtarget->hasAM()">,
                       AssemblerPredicate<(all_of FeatureAM), "am">;

def HasSEL2          : Predicate<"Subtarget->hasSEL2()">,
                       AssemblerPredicate<(all_of FeatureSEL2), "sel2">;

def HasPMU           : Predicate<"Subtarget->hasPMU()">,
                       AssemblerPredicate<(all_of FeaturePMU), "pmu">;

def HasTLB_RMI          : Predicate<"Subtarget->hasTLB_RMI()">,
                       AssemblerPredicate<(all_of FeatureTLB_RMI), "tlb-rmi">;

def HasFMI           : Predicate<"Subtarget->hasFMI()">,
                       AssemblerPredicate<(all_of FeatureFMI), "fmi">;

def HasRCPC_IMMO      : Predicate<"Subtarget->hasRCPCImm()">,
                       AssemblerPredicate<(all_of FeatureRCPC_IMMO), "rcpc-immo">;

def HasFPARMv8       : Predicate<"Subtarget->hasFPARMv8()">,
                               AssemblerPredicate<(all_of FeatureFPARMv8), "fp-armv8">;
def HasNEON          : Predicate<"Subtarget->hasNEON()">,
                                 AssemblerPredicate<(all_of FeatureNEON), "neon">;
def HasCrypto        : Predicate<"Subtarget->hasCrypto()">,
                                 AssemblerPredicate<(all_of FeatureCrypto), "crypto">;
def HasSM4           : Predicate<"Subtarget->hasSM4()">,
                                 AssemblerPredicate<(all_of FeatureSM4), "sm4">;
def HasSHA3          : Predicate<"Subtarget->hasSHA3()">,
                                 AssemblerPredicate<(all_of FeatureSHA3), "sha3">;
def HasSHA2          : Predicate<"Subtarget->hasSHA2()">,
                                 AssemblerPredicate<(all_of FeatureSHA2), "sha2">;
def HasAES           : Predicate<"Subtarget->hasAES()">,
                                 AssemblerPredicate<(all_of FeatureAES), "aes">;
def HasDotProd       : Predicate<"Subtarget->hasDotProd()">,
                                 AssemblerPredicate<(all_of FeatureDotProd), "dotprod">;
def HasCRC           : Predicate<"Subtarget->hasCRC()">,
                                 AssemblerPredicate<(all_of FeatureCRC), "crc">;
def HasLSE           : Predicate<"Subtarget->hasLSE()">,
                                 AssemblerPredicate<(all_of FeatureLSE), "lse">;
def HasRAS           : Predicate<"Subtarget->hasRAS()">,
                                 AssemblerPredicate<(all_of FeatureRAS), "ras">;
def HasRDM           : Predicate<"Subtarget->hasRDM()">,
                                 AssemblerPredicate<(all_of FeatureRDM), "rdm">;
def HasPerfMon       : Predicate<"Subtarget->hasPerfMon()">;
def HasFullFP16      : Predicate<"Subtarget->hasFullFP16()">,
                                 AssemblerPredicate<(all_of FeatureFullFP16), "fullfp16">;
def HasFP16FML       : Predicate<"Subtarget->hasFP16FML()">,
                                 AssemblerPredicate<(all_of FeatureFP16FML), "fp16fml">;
def HasSPE           : Predicate<"Subtarget->hasSPE()">,
                                 AssemblerPredicate<(all_of FeatureSPE), "spe">;
def HasFuseAES       : Predicate<"Subtarget->hasFuseAES()">,
                                 AssemblerPredicate<(all_of FeatureFuseAES),
                                 "fuse-aes">;
def HasSVE           : Predicate<"Subtarget->hasSVE()">,
                                 AssemblerPredicate<(all_of FeatureSVE), "sve">;
def HasSVE2          : Predicate<"Subtarget->hasSVE2()">,
                                 AssemblerPredicate<(all_of FeatureSVE2), "sve2">;
def HasSVE2AES       : Predicate<"Subtarget->hasSVE2AES()">,
                                 AssemblerPredicate<(all_of FeatureSVE2AES), "sve2-aes">;
def HasSVE2SM4       : Predicate<"Subtarget->hasSVE2SM4()">,
                                 AssemblerPredicate<(all_of FeatureSVE2SM4), "sve2-sm4">;
def HasSVE2SHA3      : Predicate<"Subtarget->hasSVE2SHA3()">,
                                 AssemblerPredicate<(all_of FeatureSVE2SHA3), "sve2-sha3">;
def HasSVE2BitPerm   : Predicate<"Subtarget->hasSVE2BitPerm()">,
                                 AssemblerPredicate<(all_of FeatureSVE2BitPerm), "sve2-bitperm">;
def HasRCPC          : Predicate<"Subtarget->hasRCPC()">,
                                 AssemblerPredicate<(all_of FeatureRCPC), "rcpc">;
def HasAltNZCV       : Predicate<"Subtarget->hasAlternativeNZCV()">,
                       AssemblerPredicate<(all_of FeatureAltFPCmp), "altnzcv">;
def HasFRInt3264     : Predicate<"Subtarget->hasFRInt3264()">,
                       AssemblerPredicate<(all_of FeatureFRInt3264), "frint3264">;
def HasSB            : Predicate<"Subtarget->hasSB()">,
                       AssemblerPredicate<(all_of FeatureSB), "sb">;
def HasPredRes      : Predicate<"Subtarget->hasPredRes()">,
                       AssemblerPredicate<(all_of FeaturePredRes), "predres">;
def HasCCDP          : Predicate<"Subtarget->hasCCDP()">,
                       AssemblerPredicate<(all_of FeatureCacheDeepPersist), "ccdp">;
def HasBTI           : Predicate<"Subtarget->hasBTI()">,
                       AssemblerPredicate<(all_of FeatureBranchTargetId), "bti">;
def HasMTE           : Predicate<"Subtarget->hasMTE()">,
                       AssemblerPredicate<(all_of FeatureMTE), "mte">;
def HasTME           : Predicate<"Subtarget->hasTME()">,
                       AssemblerPredicate<(all_of FeatureTME), "tme">;
def HasETE           : Predicate<"Subtarget->hasETE()">,
                       AssemblerPredicate<(all_of FeatureETE), "ete">;
def HasTRBE          : Predicate<"Subtarget->hasTRBE()">,
                       AssemblerPredicate<(all_of FeatureTRBE), "trbe">;
def HasBF16          : Predicate<"Subtarget->hasBF16()">,
                       AssemblerPredicate<(all_of FeatureBF16), "bf16">;
def HasMatMulInt8    : Predicate<"Subtarget->hasMatMulInt8()">,
                       AssemblerPredicate<(all_of FeatureMatMulInt8), "i8mm">;
def HasMatMulFP32    : Predicate<"Subtarget->hasMatMulFP32()">,
                       AssemblerPredicate<(all_of FeatureMatMulFP32), "f32mm">;
def HasMatMulFP64    : Predicate<"Subtarget->hasMatMulFP64()">,
                       AssemblerPredicate<(all_of FeatureMatMulFP64), "f64mm">;
def IsLE             : Predicate<"Subtarget->isLittleEndian()">;
def IsBE             : Predicate<"!Subtarget->isLittleEndian()">;
def IsWindows        : Predicate<"Subtarget->isTargetWindows()">;
def UseExperimentalZeroingPseudos
    : Predicate<"Subtarget->useExperimentalZeroingPseudos()">;
def UseAlternateSExtLoadCVTF32
    : Predicate<"Subtarget->useAlternateSExtLoadCVTF32Pattern()">;

def UseNegativeImmediates
    : Predicate<"false">, AssemblerPredicate<(all_of (not FeatureNoNegativeImmediates)),
                                             "NegativeImmediates">;

def AArch64LocalRecover : SDNode<"ISD::LOCAL_RECOVER",
                                  SDTypeProfile<1, 1, [SDTCisSameAs<0, 1>,
                                                       SDTCisInt<1>]>>;


//===----------------------------------------------------------------------===//
// AArch64-specific DAG Nodes.
//

// SDTBinaryArithWithFlagsOut - RES1, FLAGS = op LHS, RHS
def SDTBinaryArithWithFlagsOut : SDTypeProfile<2, 2,
                                              [SDTCisSameAs<0, 2>,
                                               SDTCisSameAs<0, 3>,
                                               SDTCisInt<0>, SDTCisVT<1, i32>]>;

// SDTBinaryArithWithFlagsIn - RES1, FLAGS = op LHS, RHS, FLAGS
def SDTBinaryArithWithFlagsIn : SDTypeProfile<1, 3,
                                            [SDTCisSameAs<0, 1>,
                                             SDTCisSameAs<0, 2>,
                                             SDTCisInt<0>,
                                             SDTCisVT<3, i32>]>;

// SDTBinaryArithWithFlagsInOut - RES1, FLAGS = op LHS, RHS, FLAGS
def SDTBinaryArithWithFlagsInOut : SDTypeProfile<2, 3,
                                            [SDTCisSameAs<0, 2>,
                                             SDTCisSameAs<0, 3>,
                                             SDTCisInt<0>,
                                             SDTCisVT<1, i32>,
                                             SDTCisVT<4, i32>]>;

def SDT_AArch64Brcond  : SDTypeProfile<0, 3,
                                     [SDTCisVT<0, OtherVT>, SDTCisVT<1, i32>,
                                      SDTCisVT<2, i32>]>;
def SDT_AArch64cbz : SDTypeProfile<0, 2, [SDTCisInt<0>, SDTCisVT<1, OtherVT>]>;
def SDT_AArch64tbz : SDTypeProfile<0, 3, [SDTCisInt<0>, SDTCisInt<1>,
                                        SDTCisVT<2, OtherVT>]>;


def SDT_AArch64CSel  : SDTypeProfile<1, 4,
                                   [SDTCisSameAs<0, 1>,
                                    SDTCisSameAs<0, 2>,
                                    SDTCisInt<3>,
                                    SDTCisVT<4, i32>]>;
def SDT_AArch64CCMP : SDTypeProfile<1, 5,
                                    [SDTCisVT<0, i32>,
                                     SDTCisInt<1>,
                                     SDTCisSameAs<1, 2>,
                                     SDTCisInt<3>,
                                     SDTCisInt<4>,
                                     SDTCisVT<5, i32>]>;
def SDT_AArch64FCCMP : SDTypeProfile<1, 5,
                                     [SDTCisVT<0, i32>,
                                      SDTCisFP<1>,
                                      SDTCisSameAs<1, 2>,
                                      SDTCisInt<3>,
                                      SDTCisInt<4>,
                                      SDTCisVT<5, i32>]>;
def SDT_AArch64FCmp   : SDTypeProfile<0, 2,
                                   [SDTCisFP<0>,
                                    SDTCisSameAs<0, 1>]>;
def SDT_AArch64Dup   : SDTypeProfile<1, 1, [SDTCisVec<0>]>;
def SDT_AArch64DupLane   : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisInt<2>]>;
def SDT_AArch64Insr  : SDTypeProfile<1, 2, [SDTCisVec<0>]>;
def SDT_AArch64Zip   : SDTypeProfile<1, 2, [SDTCisVec<0>,
                                          SDTCisSameAs<0, 1>,
                                          SDTCisSameAs<0, 2>]>;
def SDT_AArch64MOVIedit : SDTypeProfile<1, 1, [SDTCisInt<1>]>;
def SDT_AArch64MOVIshift : SDTypeProfile<1, 2, [SDTCisInt<1>, SDTCisInt<2>]>;
def SDT_AArch64vecimm : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                           SDTCisInt<2>, SDTCisInt<3>]>;
def SDT_AArch64UnaryVec: SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisSameAs<0,1>]>;
def SDT_AArch64ExtVec: SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                          SDTCisSameAs<0,2>, SDTCisInt<3>]>;
def SDT_AArch64vshift : SDTypeProfile<1, 2, [SDTCisSameAs<0,1>, SDTCisInt<2>]>;

def SDT_AArch64vshiftinsert : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisInt<3>,
                                                 SDTCisSameAs<0,1>,
                                                 SDTCisSameAs<0,2>]>;

def SDT_AArch64unvec : SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisSameAs<0,1>]>;
def SDT_AArch64fcmpz : SDTypeProfile<1, 1, []>;
def SDT_AArch64fcmp  : SDTypeProfile<1, 2, [SDTCisSameAs<1,2>]>;
def SDT_AArch64binvec : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                           SDTCisSameAs<0,2>]>;
def SDT_AArch64trivec : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                           SDTCisSameAs<0,2>,
                                           SDTCisSameAs<0,3>]>;
def SDT_AArch64TCRET : SDTypeProfile<0, 2, [SDTCisPtrTy<0>]>;
def SDT_AArch64PREFETCH : SDTypeProfile<0, 2, [SDTCisVT<0, i32>, SDTCisPtrTy<1>]>;

def SDT_AArch64ITOF  : SDTypeProfile<1, 1, [SDTCisFP<0>, SDTCisSameAs<0,1>]>;

def SDT_AArch64TLSDescCall : SDTypeProfile<0, -2, [SDTCisPtrTy<0>,
                                                 SDTCisPtrTy<1>]>;

def SDT_AArch64ldp : SDTypeProfile<2, 1, [SDTCisVT<0, i64>, SDTCisSameAs<0, 1>, SDTCisPtrTy<2>]>;
def SDT_AArch64stp : SDTypeProfile<0, 3, [SDTCisVT<0, i64>, SDTCisSameAs<0, 1>, SDTCisPtrTy<2>]>;
def SDT_AArch64stnp : SDTypeProfile<0, 3, [SDTCisVT<0, v4i32>, SDTCisSameAs<0, 1>, SDTCisPtrTy<2>]>;

// Generates the general dynamic sequences, i.e.
//  adrp  x0, :tlsdesc:var
//  ldr   x1, [x0, #:tlsdesc_lo12:var]
//  add   x0, x0, #:tlsdesc_lo12:var
//  .tlsdesccall var
//  blr   x1

// (the TPIDR_EL0 offset is put directly in X0, hence no "result" here)
// number of operands (the variable)
def SDT_AArch64TLSDescCallSeq : SDTypeProfile<0,1,
                                          [SDTCisPtrTy<0>]>;

def SDT_AArch64WrapperLarge : SDTypeProfile<1, 4,
                                        [SDTCisVT<0, i64>, SDTCisVT<1, i32>,
                                         SDTCisSameAs<1, 2>, SDTCisSameAs<1, 3>,
                                         SDTCisSameAs<1, 4>]>;

def SDT_AArch64TBL : SDTypeProfile<1, 2, [
  SDTCisVec<0>, SDTCisSameAs<0, 1>, SDTCisInt<2>
]>;

// non-extending masked load fragment.
def nonext_masked_load :
  PatFrag<(ops node:$ptr, node:$pred, node:$def),
          (masked_ld node:$ptr, undef, node:$pred, node:$def), [{
  return cast<MaskedLoadSDNode>(N)->getExtensionType() == ISD::NON_EXTLOAD &&
         cast<MaskedLoadSDNode>(N)->isUnindexed() &&
         !cast<MaskedLoadSDNode>(N)->isNonTemporal();
}]>;
// sign extending masked load fragments.
def asext_masked_load :
  PatFrag<(ops node:$ptr, node:$pred, node:$def),
          (masked_ld node:$ptr, undef, node:$pred, node:$def),[{
  return (cast<MaskedLoadSDNode>(N)->getExtensionType() == ISD::EXTLOAD ||
          cast<MaskedLoadSDNode>(N)->getExtensionType() == ISD::SEXTLOAD) &&
         cast<MaskedLoadSDNode>(N)->isUnindexed();
}]>;
def asext_masked_load_i8 :
  PatFrag<(ops node:$ptr, node:$pred, node:$def),
          (asext_masked_load node:$ptr, node:$pred, node:$def), [{
  return cast<MaskedLoadSDNode>(N)->getMemoryVT().getScalarType() == MVT::i8;
}]>;
def asext_masked_load_i16 :
  PatFrag<(ops node:$ptr, node:$pred, node:$def),
          (asext_masked_load node:$ptr, node:$pred, node:$def), [{
  return cast<MaskedLoadSDNode>(N)->getMemoryVT().getScalarType() == MVT::i16;
}]>;
def asext_masked_load_i32 :
  PatFrag<(ops node:$ptr, node:$pred, node:$def),
          (asext_masked_load node:$ptr, node:$pred, node:$def), [{
  return cast<MaskedLoadSDNode>(N)->getMemoryVT().getScalarType() == MVT::i32;
}]>;
// zero extending masked load fragments.
def zext_masked_load :
  PatFrag<(ops node:$ptr, node:$pred, node:$def),
          (masked_ld node:$ptr, undef, node:$pred, node:$def), [{
  return cast<MaskedLoadSDNode>(N)->getExtensionType() == ISD::ZEXTLOAD &&
         cast<MaskedLoadSDNode>(N)->isUnindexed();
}]>;
def zext_masked_load_i8 :
  PatFrag<(ops node:$ptr, node:$pred, node:$def),
          (zext_masked_load node:$ptr, node:$pred, node:$def), [{
  return cast<MaskedLoadSDNode>(N)->getMemoryVT().getScalarType() == MVT::i8;
}]>;
def zext_masked_load_i16 :
  PatFrag<(ops node:$ptr, node:$pred, node:$def),
          (zext_masked_load node:$ptr, node:$pred, node:$def), [{
  return cast<MaskedLoadSDNode>(N)->getMemoryVT().getScalarType() == MVT::i16;
}]>;
def zext_masked_load_i32 :
  PatFrag<(ops node:$ptr, node:$pred, node:$def),
          (zext_masked_load node:$ptr, node:$pred, node:$def), [{
  return cast<MaskedLoadSDNode>(N)->getMemoryVT().getScalarType() == MVT::i32;
}]>;

def non_temporal_load :
   PatFrag<(ops node:$ptr, node:$pred, node:$def),
           (masked_ld node:$ptr, undef, node:$pred, node:$def), [{
   return cast<MaskedLoadSDNode>(N)->getExtensionType() == ISD::NON_EXTLOAD &&
          cast<MaskedLoadSDNode>(N)->isUnindexed() &&
          cast<MaskedLoadSDNode>(N)->isNonTemporal();
}]>;

// non-truncating masked store fragment.
def nontrunc_masked_store :
  PatFrag<(ops node:$val, node:$ptr, node:$pred),
          (masked_st node:$val, node:$ptr, undef, node:$pred), [{
  return !cast<MaskedStoreSDNode>(N)->isTruncatingStore() &&
         cast<MaskedStoreSDNode>(N)->isUnindexed() &&
         !cast<MaskedStoreSDNode>(N)->isNonTemporal();
}]>;
// truncating masked store fragments.
def trunc_masked_store :
  PatFrag<(ops node:$val, node:$ptr, node:$pred),
          (masked_st node:$val, node:$ptr, undef, node:$pred), [{
  return cast<MaskedStoreSDNode>(N)->isTruncatingStore() &&
         cast<MaskedStoreSDNode>(N)->isUnindexed();
}]>;
def trunc_masked_store_i8 :
  PatFrag<(ops node:$val, node:$ptr, node:$pred),
          (trunc_masked_store node:$val, node:$ptr, node:$pred), [{
  return cast<MaskedStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i8;
}]>;
def trunc_masked_store_i16 :
  PatFrag<(ops node:$val, node:$ptr, node:$pred),
          (trunc_masked_store node:$val, node:$ptr, node:$pred), [{
  return cast<MaskedStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i16;
}]>;
def trunc_masked_store_i32 :
  PatFrag<(ops node:$val, node:$ptr, node:$pred),
          (trunc_masked_store node:$val, node:$ptr, node:$pred), [{
  return cast<MaskedStoreSDNode>(N)->getMemoryVT().getScalarType() == MVT::i32;
}]>;

def non_temporal_store :
  PatFrag<(ops node:$val, node:$ptr, node:$pred),
          (masked_st node:$val, node:$ptr, undef, node:$pred), [{
  return !cast<MaskedStoreSDNode>(N)->isTruncatingStore() &&
         cast<MaskedStoreSDNode>(N)->isUnindexed() &&
         cast<MaskedStoreSDNode>(N)->isNonTemporal();
}]>;

// Node definitions.
def AArch64adrp          : SDNode<"AArch64ISD::ADRP", SDTIntUnaryOp, []>;
def AArch64adr           : SDNode<"AArch64ISD::ADR", SDTIntUnaryOp, []>;
def AArch64addlow        : SDNode<"AArch64ISD::ADDlow", SDTIntBinOp, []>;
def AArch64LOADgot       : SDNode<"AArch64ISD::LOADgot", SDTIntUnaryOp>;
def AArch64callseq_start : SDNode<"ISD::CALLSEQ_START",
                                SDCallSeqStart<[ SDTCisVT<0, i32>,
                                                 SDTCisVT<1, i32> ]>,
                                [SDNPHasChain, SDNPOutGlue]>;
def AArch64callseq_end   : SDNode<"ISD::CALLSEQ_END",
                                SDCallSeqEnd<[ SDTCisVT<0, i32>,
                                               SDTCisVT<1, i32> ]>,
                                [SDNPHasChain, SDNPOptInGlue, SDNPOutGlue]>;
def AArch64call          : SDNode<"AArch64ISD::CALL",
                                SDTypeProfile<0, -1, [SDTCisPtrTy<0>]>,
                                [SDNPHasChain, SDNPOptInGlue, SDNPOutGlue,
                                 SDNPVariadic]>;
def AArch64brcond        : SDNode<"AArch64ISD::BRCOND", SDT_AArch64Brcond,
                                [SDNPHasChain]>;
def AArch64cbz           : SDNode<"AArch64ISD::CBZ", SDT_AArch64cbz,
                                [SDNPHasChain]>;
def AArch64cbnz           : SDNode<"AArch64ISD::CBNZ", SDT_AArch64cbz,
                                [SDNPHasChain]>;
def AArch64tbz           : SDNode<"AArch64ISD::TBZ", SDT_AArch64tbz,
                                [SDNPHasChain]>;
def AArch64tbnz           : SDNode<"AArch64ISD::TBNZ", SDT_AArch64tbz,
                                [SDNPHasChain]>;


def AArch64csel          : SDNode<"AArch64ISD::CSEL", SDT_AArch64CSel>;
def AArch64csinv         : SDNode<"AArch64ISD::CSINV", SDT_AArch64CSel>;
def AArch64csneg         : SDNode<"AArch64ISD::CSNEG", SDT_AArch64CSel>;
def AArch64csinc         : SDNode<"AArch64ISD::CSINC", SDT_AArch64CSel>;
def AArch64retflag       : SDNode<"AArch64ISD::RET_FLAG", SDTNone,
                                [SDNPHasChain, SDNPOptInGlue, SDNPVariadic]>;
def AArch64adc       : SDNode<"AArch64ISD::ADC",  SDTBinaryArithWithFlagsIn >;
def AArch64sbc       : SDNode<"AArch64ISD::SBC",  SDTBinaryArithWithFlagsIn>;
def AArch64add_flag  : SDNode<"AArch64ISD::ADDS",  SDTBinaryArithWithFlagsOut,
                            [SDNPCommutative]>;
def AArch64sub_flag  : SDNode<"AArch64ISD::SUBS",  SDTBinaryArithWithFlagsOut>;
def AArch64and_flag  : SDNode<"AArch64ISD::ANDS",  SDTBinaryArithWithFlagsOut,
                            [SDNPCommutative]>;
def AArch64adc_flag  : SDNode<"AArch64ISD::ADCS",  SDTBinaryArithWithFlagsInOut>;
def AArch64sbc_flag  : SDNode<"AArch64ISD::SBCS",  SDTBinaryArithWithFlagsInOut>;

def AArch64ccmp      : SDNode<"AArch64ISD::CCMP",  SDT_AArch64CCMP>;
def AArch64ccmn      : SDNode<"AArch64ISD::CCMN",  SDT_AArch64CCMP>;
def AArch64fccmp     : SDNode<"AArch64ISD::FCCMP", SDT_AArch64FCCMP>;

def AArch64threadpointer : SDNode<"AArch64ISD::THREAD_POINTER", SDTPtrLeaf>;

def AArch64fcmp         : SDNode<"AArch64ISD::FCMP", SDT_AArch64FCmp>;
def AArch64strict_fcmp  : SDNode<"AArch64ISD::STRICT_FCMP", SDT_AArch64FCmp,
                                 [SDNPHasChain]>;
def AArch64strict_fcmpe : SDNode<"AArch64ISD::STRICT_FCMPE", SDT_AArch64FCmp,
                                 [SDNPHasChain]>;
def AArch64any_fcmp     : PatFrags<(ops node:$lhs, node:$rhs),
                                   [(AArch64strict_fcmp node:$lhs, node:$rhs),
                                    (AArch64fcmp node:$lhs, node:$rhs)]>;

def AArch64dup       : SDNode<"AArch64ISD::DUP", SDT_AArch64Dup>;
def AArch64duplane8  : SDNode<"AArch64ISD::DUPLANE8", SDT_AArch64DupLane>;
def AArch64duplane16 : SDNode<"AArch64ISD::DUPLANE16", SDT_AArch64DupLane>;
def AArch64duplane32 : SDNode<"AArch64ISD::DUPLANE32", SDT_AArch64DupLane>;
def AArch64duplane64 : SDNode<"AArch64ISD::DUPLANE64", SDT_AArch64DupLane>;

def AArch64insr      : SDNode<"AArch64ISD::INSR", SDT_AArch64Insr>;

def AArch64zip1      : SDNode<"AArch64ISD::ZIP1", SDT_AArch64Zip>;
def AArch64zip2      : SDNode<"AArch64ISD::ZIP2", SDT_AArch64Zip>;
def AArch64uzp1      : SDNode<"AArch64ISD::UZP1", SDT_AArch64Zip>;
def AArch64uzp2      : SDNode<"AArch64ISD::UZP2", SDT_AArch64Zip>;
def AArch64trn1      : SDNode<"AArch64ISD::TRN1", SDT_AArch64Zip>;
def AArch64trn2      : SDNode<"AArch64ISD::TRN2", SDT_AArch64Zip>;

def AArch64movi_edit : SDNode<"AArch64ISD::MOVIedit", SDT_AArch64MOVIedit>;
def AArch64movi_shift : SDNode<"AArch64ISD::MOVIshift", SDT_AArch64MOVIshift>;
def AArch64movi_msl : SDNode<"AArch64ISD::MOVImsl", SDT_AArch64MOVIshift>;
def AArch64mvni_shift : SDNode<"AArch64ISD::MVNIshift", SDT_AArch64MOVIshift>;
def AArch64mvni_msl : SDNode<"AArch64ISD::MVNImsl", SDT_AArch64MOVIshift>;
def AArch64movi : SDNode<"AArch64ISD::MOVI", SDT_AArch64MOVIedit>;
def AArch64fmov : SDNode<"AArch64ISD::FMOV", SDT_AArch64MOVIedit>;

def AArch64rev16 : SDNode<"AArch64ISD::REV16", SDT_AArch64UnaryVec>;
def AArch64rev32 : SDNode<"AArch64ISD::REV32", SDT_AArch64UnaryVec>;
def AArch64rev64 : SDNode<"AArch64ISD::REV64", SDT_AArch64UnaryVec>;
def AArch64ext : SDNode<"AArch64ISD::EXT", SDT_AArch64ExtVec>;

def AArch64vashr : SDNode<"AArch64ISD::VASHR", SDT_AArch64vshift>;
def AArch64vlshr : SDNode<"AArch64ISD::VLSHR", SDT_AArch64vshift>;
def AArch64vshl : SDNode<"AArch64ISD::VSHL", SDT_AArch64vshift>;
def AArch64sqshli : SDNode<"AArch64ISD::SQSHL_I", SDT_AArch64vshift>;
def AArch64uqshli : SDNode<"AArch64ISD::UQSHL_I", SDT_AArch64vshift>;
def AArch64sqshlui : SDNode<"AArch64ISD::SQSHLU_I", SDT_AArch64vshift>;
def AArch64srshri : SDNode<"AArch64ISD::SRSHR_I", SDT_AArch64vshift>;
def AArch64urshri : SDNode<"AArch64ISD::URSHR_I", SDT_AArch64vshift>;
def AArch64vsli : SDNode<"AArch64ISD::VSLI", SDT_AArch64vshiftinsert>;
def AArch64vsri : SDNode<"AArch64ISD::VSRI", SDT_AArch64vshiftinsert>;

def AArch64not: SDNode<"AArch64ISD::NOT", SDT_AArch64unvec>;
def AArch64bit: SDNode<"AArch64ISD::BIT", SDT_AArch64trivec>;
def AArch64bsp: SDNode<"AArch64ISD::BSP", SDT_AArch64trivec>;

def AArch64cmeq: SDNode<"AArch64ISD::CMEQ", SDT_AArch64binvec>;
def AArch64cmge: SDNode<"AArch64ISD::CMGE", SDT_AArch64binvec>;
def AArch64cmgt: SDNode<"AArch64ISD::CMGT", SDT_AArch64binvec>;
def AArch64cmhi: SDNode<"AArch64ISD::CMHI", SDT_AArch64binvec>;
def AArch64cmhs: SDNode<"AArch64ISD::CMHS", SDT_AArch64binvec>;

def AArch64fcmeq: SDNode<"AArch64ISD::FCMEQ", SDT_AArch64fcmp>;
def AArch64fcmge: SDNode<"AArch64ISD::FCMGE", SDT_AArch64fcmp>;
def AArch64fcmgt: SDNode<"AArch64ISD::FCMGT", SDT_AArch64fcmp>;

def AArch64cmeqz: SDNode<"AArch64ISD::CMEQz", SDT_AArch64unvec>;
def AArch64cmgez: SDNode<"AArch64ISD::CMGEz", SDT_AArch64unvec>;
def AArch64cmgtz: SDNode<"AArch64ISD::CMGTz", SDT_AArch64unvec>;
def AArch64cmlez: SDNode<"AArch64ISD::CMLEz", SDT_AArch64unvec>;
def AArch64cmltz: SDNode<"AArch64ISD::CMLTz", SDT_AArch64unvec>;
def AArch64cmtst : PatFrag<(ops node:$LHS, node:$RHS),
                        (AArch64not (AArch64cmeqz (and node:$LHS, node:$RHS)))>;

def AArch64fcmeqz: SDNode<"AArch64ISD::FCMEQz", SDT_AArch64fcmpz>;
def AArch64fcmgez: SDNode<"AArch64ISD::FCMGEz", SDT_AArch64fcmpz>;
def AArch64fcmgtz: SDNode<"AArch64ISD::FCMGTz", SDT_AArch64fcmpz>;
def AArch64fcmlez: SDNode<"AArch64ISD::FCMLEz", SDT_AArch64fcmpz>;
def AArch64fcmltz: SDNode<"AArch64ISD::FCMLTz", SDT_AArch64fcmpz>;

def AArch64bici: SDNode<"AArch64ISD::BICi", SDT_AArch64vecimm>;
def AArch64orri: SDNode<"AArch64ISD::ORRi", SDT_AArch64vecimm>;

def AArch64neg : SDNode<"AArch64ISD::NEG", SDT_AArch64unvec>;

def AArch64tcret: SDNode<"AArch64ISD::TC_RETURN", SDT_AArch64TCRET,
                  [SDNPHasChain,  SDNPOptInGlue, SDNPVariadic]>;

def AArch64Prefetch        : SDNode<"AArch64ISD::PREFETCH", SDT_AArch64PREFETCH,
                               [SDNPHasChain, SDNPSideEffect]>;

def AArch64sitof: SDNode<"AArch64ISD::SITOF", SDT_AArch64ITOF>;
def AArch64uitof: SDNode<"AArch64ISD::UITOF", SDT_AArch64ITOF>;

def AArch64tlsdesc_callseq : SDNode<"AArch64ISD::TLSDESC_CALLSEQ",
                                    SDT_AArch64TLSDescCallSeq,
                                    [SDNPInGlue, SDNPOutGlue, SDNPHasChain,
                                     SDNPVariadic]>;


def AArch64WrapperLarge : SDNode<"AArch64ISD::WrapperLarge",
                                 SDT_AArch64WrapperLarge>;

def AArch64NvCast : SDNode<"AArch64ISD::NVCAST", SDTUnaryOp>;

def SDT_AArch64mull : SDTypeProfile<1, 2, [SDTCisInt<0>, SDTCisInt<1>,
                                    SDTCisSameAs<1, 2>]>;
def AArch64smull    : SDNode<"AArch64ISD::SMULL", SDT_AArch64mull>;
def AArch64umull    : SDNode<"AArch64ISD::UMULL", SDT_AArch64mull>;

def AArch64frecpe   : SDNode<"AArch64ISD::FRECPE", SDTFPUnaryOp>;
def AArch64frecps   : SDNode<"AArch64ISD::FRECPS", SDTFPBinOp>;
def AArch64frsqrte  : SDNode<"AArch64ISD::FRSQRTE", SDTFPUnaryOp>;
def AArch64frsqrts  : SDNode<"AArch64ISD::FRSQRTS", SDTFPBinOp>;

def AArch64saddv    : SDNode<"AArch64ISD::SADDV", SDT_AArch64UnaryVec>;
def AArch64uaddv    : SDNode<"AArch64ISD::UADDV", SDT_AArch64UnaryVec>;
def AArch64sminv    : SDNode<"AArch64ISD::SMINV", SDT_AArch64UnaryVec>;
def AArch64uminv    : SDNode<"AArch64ISD::UMINV", SDT_AArch64UnaryVec>;
def AArch64smaxv    : SDNode<"AArch64ISD::SMAXV", SDT_AArch64UnaryVec>;
def AArch64umaxv    : SDNode<"AArch64ISD::UMAXV", SDT_AArch64UnaryVec>;

def AArch64srhadd   : SDNode<"AArch64ISD::SRHADD", SDT_AArch64binvec>;
def AArch64urhadd   : SDNode<"AArch64ISD::URHADD", SDT_AArch64binvec>;

def SDT_AArch64SETTAG : SDTypeProfile<0, 2, [SDTCisPtrTy<0>, SDTCisPtrTy<1>]>;
def AArch64stg : SDNode<"AArch64ISD::STG", SDT_AArch64SETTAG, [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
def AArch64stzg : SDNode<"AArch64ISD::STZG", SDT_AArch64SETTAG, [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
def AArch64st2g : SDNode<"AArch64ISD::ST2G", SDT_AArch64SETTAG, [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
def AArch64stz2g : SDNode<"AArch64ISD::STZ2G", SDT_AArch64SETTAG, [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;

def SDT_AArch64unpk : SDTypeProfile<1, 1, [
    SDTCisInt<0>, SDTCisInt<1>, SDTCisOpSmallerThanOp<1, 0>
]>;
def AArch64sunpkhi : SDNode<"AArch64ISD::SUNPKHI", SDT_AArch64unpk>;
def AArch64sunpklo : SDNode<"AArch64ISD::SUNPKLO", SDT_AArch64unpk>;
def AArch64uunpkhi : SDNode<"AArch64ISD::UUNPKHI", SDT_AArch64unpk>;
def AArch64uunpklo : SDNode<"AArch64ISD::UUNPKLO", SDT_AArch64unpk>;

def AArch64ldp : SDNode<"AArch64ISD::LDP", SDT_AArch64ldp, [SDNPHasChain, SDNPMayLoad, SDNPMemOperand]>;
def AArch64stp : SDNode<"AArch64ISD::STP", SDT_AArch64stp, [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;
def AArch64stnp : SDNode<"AArch64ISD::STNP", SDT_AArch64stnp, [SDNPHasChain, SDNPMayStore, SDNPMemOperand]>;

def AArch64tbl : SDNode<"AArch64ISD::TBL", SDT_AArch64TBL>;

//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//

// AArch64 Instruction Predicate Definitions.
// We could compute these on a per-module basis but doing so requires accessing
// the Function object through the <Target>Subtarget and objections were raised
// to that (see post-commit review comments for r301750).
let RecomputePerFunction = 1 in {
  def ForCodeSize   : Predicate<"shouldOptForSize(MF)">;
  def NotForCodeSize   : Predicate<"!shouldOptForSize(MF)">;
  // Avoid generating STRQro if it is slow, unless we're optimizing for code size.
  def UseSTRQro : Predicate<"!Subtarget->isSTRQroSlow() || shouldOptForSize(MF)">;

  def UseBTI : Predicate<[{ MF->getFunction().hasFnAttribute("branch-target-enforcement") }]>;
  def NotUseBTI : Predicate<[{ !MF->getFunction().hasFnAttribute("branch-target-enforcement") }]>;

  def SLSBLRMitigation : Predicate<[{ MF->getSubtarget<AArch64Subtarget>().hardenSlsBlr() }]>;
  def NoSLSBLRMitigation : Predicate<[{ !MF->getSubtarget<AArch64Subtarget>().hardenSlsBlr() }]>;
  // Toggles patterns which aren't beneficial in GlobalISel when we aren't
  // optimizing. This allows us to selectively use patterns without impacting
  // SelectionDAG's behaviour.
  // FIXME: One day there will probably be a nicer way to check for this, but
  // today is not that day.
  def OptimizedGISelOrOtherSelector : Predicate<"!MF->getFunction().hasOptNone() || MF->getProperties().hasProperty(MachineFunctionProperties::Property::FailedISel) || !MF->getProperties().hasProperty(MachineFunctionProperties::Property::Legalized)">;
}

include "AArch64InstrFormats.td"
include "SVEInstrFormats.td"

//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//
// Miscellaneous instructions.
//===----------------------------------------------------------------------===//

let Defs = [SP], Uses = [SP], hasSideEffects = 1, isCodeGenOnly = 1 in {
// We set Sched to empty list because we expect these instructions to simply get
// removed in most cases.
def ADJCALLSTACKDOWN : Pseudo<(outs), (ins i32imm:$amt1, i32imm:$amt2),
                              [(AArch64callseq_start timm:$amt1, timm:$amt2)]>,
                              Sched<[]>;
def ADJCALLSTACKUP : Pseudo<(outs), (ins i32imm:$amt1, i32imm:$amt2),
                            [(AArch64callseq_end timm:$amt1, timm:$amt2)]>,
                            Sched<[]>;
} // Defs = [SP], Uses = [SP], hasSideEffects = 1, isCodeGenOnly = 1

let isReMaterializable = 1, isCodeGenOnly = 1 in {
// FIXME: The following pseudo instructions are only needed because remat
// cannot handle multiple instructions.  When that changes, they can be
// removed, along with the AArch64Wrapper node.

let AddedComplexity = 10 in
def LOADgot : Pseudo<(outs GPR64:$dst), (ins i64imm:$addr),
                     [(set GPR64:$dst, (AArch64LOADgot tglobaladdr:$addr))]>,
              Sched<[WriteLDAdr]>;

// The MOVaddr instruction should match only when the add is not folded
// into a load or store address.
def MOVaddr
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (AArch64addlow (AArch64adrp tglobaladdr:$hi),
                                            tglobaladdr:$low))]>,
      Sched<[WriteAdrAdr]>;
def MOVaddrJT
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (AArch64addlow (AArch64adrp tjumptable:$hi),
                                             tjumptable:$low))]>,
      Sched<[WriteAdrAdr]>;
def MOVaddrCP
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (AArch64addlow (AArch64adrp tconstpool:$hi),
                                             tconstpool:$low))]>,
      Sched<[WriteAdrAdr]>;
def MOVaddrBA
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (AArch64addlow (AArch64adrp tblockaddress:$hi),
                                             tblockaddress:$low))]>,
      Sched<[WriteAdrAdr]>;
def MOVaddrTLS
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (AArch64addlow (AArch64adrp tglobaltlsaddr:$hi),
                                            tglobaltlsaddr:$low))]>,
      Sched<[WriteAdrAdr]>;
def MOVaddrEXT
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (AArch64addlow (AArch64adrp texternalsym:$hi),
                                            texternalsym:$low))]>,
      Sched<[WriteAdrAdr]>;
// Normally AArch64addlow either gets folded into a following ldr/str,
// or together with an adrp into MOVaddr above. For cases with TLS, it
// might appear without either of them, so allow lowering it into a plain
// add.
def ADDlowTLS
    : Pseudo<(outs GPR64:$dst), (ins GPR64:$src, i64imm:$low),
             [(set GPR64:$dst, (AArch64addlow GPR64:$src,
                                            tglobaltlsaddr:$low))]>,
      Sched<[WriteAdr]>;

} // isReMaterializable, isCodeGenOnly

def : Pat<(AArch64LOADgot tglobaltlsaddr:$addr),
          (LOADgot tglobaltlsaddr:$addr)>;

def : Pat<(AArch64LOADgot texternalsym:$addr),
          (LOADgot texternalsym:$addr)>;

def : Pat<(AArch64LOADgot tconstpool:$addr),
          (LOADgot tconstpool:$addr)>;

// 32-bit jump table destination is actually only 2 instructions since we can
// use the table itself as a PC-relative base. But optimization occurs after
// branch relaxation so be pessimistic.
let Size = 12, Constraints = "@earlyclobber $dst,@earlyclobber $scratch" in {
def JumpTableDest32 : Pseudo<(outs GPR64:$dst, GPR64sp:$scratch),
                             (ins GPR64:$table, GPR64:$entry, i32imm:$jti), []>,
                      Sched<[]>;
def JumpTableDest16 : Pseudo<(outs GPR64:$dst, GPR64sp:$scratch),
                             (ins GPR64:$table, GPR64:$entry, i32imm:$jti), []>,
                      Sched<[]>;
def JumpTableDest8 : Pseudo<(outs GPR64:$dst, GPR64sp:$scratch),
                            (ins GPR64:$table, GPR64:$entry, i32imm:$jti), []>,
                     Sched<[]>;
}

// Space-consuming pseudo to aid testing of placement and reachability
// algorithms. Immediate operand is the number of bytes this "instruction"
// occupies; register operands can be used to enforce dependency and constrain
// the scheduler.
let hasSideEffects = 1, mayLoad = 1, mayStore = 1 in
def SPACE : Pseudo<(outs GPR64:$Rd), (ins i32imm:$size, GPR64:$Rn),
                   [(set GPR64:$Rd, (int_aarch64_space imm:$size, GPR64:$Rn))]>,
            Sched<[]>;

let hasSideEffects = 1, isCodeGenOnly = 1 in {
  def SpeculationSafeValueX
      : Pseudo<(outs GPR64:$dst), (ins GPR64:$src), []>, Sched<[]>;
  def SpeculationSafeValueW
      : Pseudo<(outs GPR32:$dst), (ins GPR32:$src), []>, Sched<[]>;
}

// SpeculationBarrierEndBB must only be used after an unconditional control
// flow, i.e. after a terminator for which isBarrier is True.
let hasSideEffects = 1, isCodeGenOnly = 1, isTerminator = 1, isBarrier = 1 in {
  def SpeculationBarrierISBDSBEndBB
      : Pseudo<(outs), (ins), []>, Sched<[]>;
  def SpeculationBarrierSBEndBB
      : Pseudo<(outs), (ins), []>, Sched<[]>;
}

//===----------------------------------------------------------------------===//
// System instructions.
//===----------------------------------------------------------------------===//

def HINT : HintI<"hint">;
def : InstAlias<"nop",  (HINT 0b000)>;
def : InstAlias<"yield",(HINT 0b001)>;
def : InstAlias<"wfe",  (HINT 0b010)>;
def : InstAlias<"wfi",  (HINT 0b011)>;
def : InstAlias<"sev",  (HINT 0b100)>;
def : InstAlias<"sevl", (HINT 0b101)>;
def : InstAlias<"dgh",  (HINT 0b110)>;
def : InstAlias<"esb",  (HINT 0b10000)>, Requires<[HasRAS]>;
def : InstAlias<"csdb", (HINT 20)>;
// In order to be able to write readable assembly, LLVM should accept assembly
// inputs that use Branch Target Indentification mnemonics, even with BTI disabled.
// However, in order to be compatible with other assemblers (e.g. GAS), LLVM
// should not emit these mnemonics unless BTI is enabled.
def : InstAlias<"bti",  (HINT 32), 0>;
def : InstAlias<"bti $op", (HINT btihint_op:$op), 0>;
def : InstAlias<"bti",  (HINT 32)>, Requires<[HasBTI]>;
def : InstAlias<"bti $op", (HINT btihint_op:$op)>, Requires<[HasBTI]>;

// v8.2a Statistical Profiling extension
def : InstAlias<"psb $op",  (HINT psbhint_op:$op)>, Requires<[HasSPE]>;

// As far as LLVM is concerned this writes to the system's exclusive monitors.
let mayLoad = 1, mayStore = 1 in
def CLREX : CRmSystemI<imm0_15, 0b010, "clrex">;

// NOTE: ideally, this would have mayStore = 0, mayLoad = 0, but we cannot
// model patterns with sufficiently fine granularity.
let mayLoad = ?, mayStore = ? in {
def DMB   : CRmSystemI<barrier_op, 0b101, "dmb",
                       [(int_aarch64_dmb (i32 imm32_0_15:$CRm))]>;

def DSB   : CRmSystemI<barrier_op, 0b100, "dsb",
                       [(int_aarch64_dsb (i32 imm32_0_15:$CRm))]>;

def ISB   : CRmSystemI<barrier_op, 0b110, "isb",
                       [(int_aarch64_isb (i32 imm32_0_15:$CRm))]>;

def TSB   : CRmSystemI<barrier_op, 0b010, "tsb", []> {
  let CRm        = 0b0010;
  let Inst{12}   = 0;
  let Predicates = [HasTRACEV8_4];
}
}

// ARMv8.2-A Dot Product
let Predicates = [HasDotProd] in {
defm SDOT : SIMDThreeSameVectorDot<0, 0, "sdot", int_aarch64_neon_sdot>;
defm UDOT : SIMDThreeSameVectorDot<1, 0, "udot", int_aarch64_neon_udot>;
defm SDOTlane : SIMDThreeSameVectorDotIndex<0, 0, 0b10, "sdot", int_aarch64_neon_sdot>;
defm UDOTlane : SIMDThreeSameVectorDotIndex<1, 0, 0b10, "udot", int_aarch64_neon_udot>;
}

// ARMv8.6-A BFloat
let Predicates = [HasBF16] in {
defm BFDOT       : SIMDThreeSameVectorBFDot<1, "bfdot">;
defm BF16DOTlane : SIMDThreeSameVectorBF16DotI<0, "bfdot">;
def BFMMLA       : SIMDThreeSameVectorBF16MatrixMul<"bfmmla">;
def BFMLALB      : SIMDBF16MLAL<0, "bfmlalb", int_aarch64_neon_bfmlalb>;
def BFMLALT      : SIMDBF16MLAL<1, "bfmlalt", int_aarch64_neon_bfmlalt>;
def BFMLALBIdx   : SIMDBF16MLALIndex<0, "bfmlalb", int_aarch64_neon_bfmlalb>;
def BFMLALTIdx   : SIMDBF16MLALIndex<1, "bfmlalt", int_aarch64_neon_bfmlalt>;
def BFCVTN       : SIMD_BFCVTN;
def BFCVTN2      : SIMD_BFCVTN2;
def BFCVT        : BF16ToSinglePrecision<"bfcvt">;
}

// ARMv8.6A AArch64 matrix multiplication
let Predicates = [HasMatMulInt8] in {
def  SMMLA : SIMDThreeSameVectorMatMul<0, 0, "smmla", int_aarch64_neon_smmla>;
def  UMMLA : SIMDThreeSameVectorMatMul<0, 1, "ummla", int_aarch64_neon_ummla>;
def USMMLA : SIMDThreeSameVectorMatMul<1, 0, "usmmla", int_aarch64_neon_usmmla>;
defm USDOT : SIMDThreeSameVectorDot<0, 1, "usdot", int_aarch64_neon_usdot>;
defm USDOTlane : SIMDThreeSameVectorDotIndex<0, 1, 0b10, "usdot", int_aarch64_neon_usdot>;

// sudot lane has a pattern where usdot is expected (there is no sudot).
// The second operand is used in the dup operation to repeat the indexed
// element.
class BaseSIMDSUDOTIndex<bit Q, string dst_kind, string lhs_kind,
                         string rhs_kind, RegisterOperand RegType,
                         ValueType AccumType, ValueType InputType>
      : BaseSIMDThreeSameVectorDotIndex<Q, 0, 1, 0b00, "sudot", dst_kind,
                                        lhs_kind, rhs_kind, RegType, AccumType,
                                        InputType, null_frag> {
  let Pattern = [(set (AccumType RegType:$dst),
                      (AccumType (int_aarch64_neon_usdot (AccumType RegType:$Rd),
                                 (InputType (bitconvert (AccumType
                                    (AArch64duplane32 (v4i32 V128:$Rm),
                                        VectorIndexS:$idx)))),
                                 (InputType RegType:$Rn))))];
}

multiclass SIMDSUDOTIndex {
  def v8i8  : BaseSIMDSUDOTIndex<0, ".2s", ".8b", ".4b", V64, v2i32, v8i8>;
  def v16i8 : BaseSIMDSUDOTIndex<1, ".4s", ".16b", ".4b", V128, v4i32, v16i8>;
}

defm SUDOTlane : SIMDSUDOTIndex;

}

// ARMv8.2-A FP16 Fused Multiply-Add Long
let Predicates = [HasNEON, HasFP16FML] in {
defm FMLAL      : SIMDThreeSameVectorFML<0, 1, 0b001, "fmlal", int_aarch64_neon_fmlal>;
defm FMLSL      : SIMDThreeSameVectorFML<0, 1, 0b101, "fmlsl", int_aarch64_neon_fmlsl>;
defm FMLAL2     : SIMDThreeSameVectorFML<1, 0, 0b001, "fmlal2", int_aarch64_neon_fmlal2>;
defm FMLSL2     : SIMDThreeSameVectorFML<1, 0, 0b101, "fmlsl2", int_aarch64_neon_fmlsl2>;
defm FMLALlane  : SIMDThreeSameVectorFMLIndex<0, 0b0000, "fmlal", int_aarch64_neon_fmlal>;
defm FMLSLlane  : SIMDThreeSameVectorFMLIndex<0, 0b0100, "fmlsl", int_aarch64_neon_fmlsl>;
defm FMLAL2lane : SIMDThreeSameVectorFMLIndex<1, 0b1000, "fmlal2", int_aarch64_neon_fmlal2>;
defm FMLSL2lane : SIMDThreeSameVectorFMLIndex<1, 0b1100, "fmlsl2", int_aarch64_neon_fmlsl2>;
}

// Armv8.2-A Crypto extensions
let Predicates = [HasSHA3] in {
def SHA512H   : CryptoRRRTied<0b0, 0b00, "sha512h">;
def SHA512H2  : CryptoRRRTied<0b0, 0b01, "sha512h2">;
def SHA512SU0 : CryptoRRTied_2D<0b0, 0b00, "sha512su0">;
def SHA512SU1 : CryptoRRRTied_2D<0b0, 0b10, "sha512su1">;
def RAX1      : CryptoRRR_2D<0b0,0b11, "rax1">;
def EOR3      : CryptoRRRR_16B<0b00, "eor3">;
def BCAX      : CryptoRRRR_16B<0b01, "bcax">;
def XAR       : CryptoRRRi6<"xar">;
} // HasSHA3

let Predicates = [HasSM4] in {
def SM3TT1A   : CryptoRRRi2Tied<0b0, 0b00, "sm3tt1a">;
def SM3TT1B   : CryptoRRRi2Tied<0b0, 0b01, "sm3tt1b">;
def SM3TT2A   : CryptoRRRi2Tied<0b0, 0b10, "sm3tt2a">;
def SM3TT2B   : CryptoRRRi2Tied<0b0, 0b11, "sm3tt2b">;
def SM3SS1    : CryptoRRRR_4S<0b10, "sm3ss1">;
def SM3PARTW1 : CryptoRRRTied_4S<0b1, 0b00, "sm3partw1">;
def SM3PARTW2 : CryptoRRRTied_4S<0b1, 0b01, "sm3partw2">;
def SM4ENCKEY : CryptoRRR_4S<0b1, 0b10, "sm4ekey">;
def SM4E      : CryptoRRTied_4S<0b0, 0b01, "sm4e">;
} // HasSM4

let Predicates = [HasRCPC] in {
  // v8.3 Release Consistent Processor Consistent support, optional in v8.2.
  def LDAPRB  : RCPCLoad<0b00, "ldaprb", GPR32>;
  def LDAPRH  : RCPCLoad<0b01, "ldaprh", GPR32>;
  def LDAPRW  : RCPCLoad<0b10, "ldapr", GPR32>;
  def LDAPRX  : RCPCLoad<0b11, "ldapr", GPR64>;
}

// v8.3a complex add and multiply-accumulate. No predicate here, that is done
// inside the multiclass as the FP16 versions need different predicates.
defm FCMLA : SIMDThreeSameVectorTiedComplexHSD<1, 0b110, complexrotateop,
                                               "fcmla", null_frag>;
defm FCADD : SIMDThreeSameVectorComplexHSD<1, 0b111, complexrotateopodd,
                                           "fcadd", null_frag>;
defm FCMLA : SIMDIndexedTiedComplexHSD<1, 0, 1, complexrotateop, "fcmla",
                                       null_frag>;

let Predicates = [HasComplxNum, HasNEON, HasFullFP16] in {
  def : Pat<(v4f16 (int_aarch64_neon_vcadd_rot90 (v4f16 V64:$Rn), (v4f16 V64:$Rm))),
            (FCADDv4f16 (v4f16 V64:$Rn), (v4f16 V64:$Rm), (i32 0))>;
  def : Pat<(v4f16 (int_aarch64_neon_vcadd_rot270 (v4f16 V64:$Rn), (v4f16 V64:$Rm))),
            (FCADDv4f16 (v4f16 V64:$Rn), (v4f16 V64:$Rm), (i32 1))>;
  def : Pat<(v8f16 (int_aarch64_neon_vcadd_rot90 (v8f16 V128:$Rn), (v8f16 V128:$Rm))),
            (FCADDv8f16 (v8f16 V128:$Rn), (v8f16 V128:$Rm), (i32 0))>;
  def : Pat<(v8f16 (int_aarch64_neon_vcadd_rot270 (v8f16 V128:$Rn), (v8f16 V128:$Rm))),
            (FCADDv8f16 (v8f16 V128:$Rn), (v8f16 V128:$Rm), (i32 1))>;
}
let Predicates = [HasComplxNum, HasNEON] in {
  def : Pat<(v2f32 (int_aarch64_neon_vcadd_rot90 (v2f32 V64:$Rn), (v2f32 V64:$Rm))),
            (FCADDv2f32 (v2f32 V64:$Rn), (v2f32 V64:$Rm), (i32 0))>;
  def : Pat<(v2f32 (int_aarch64_neon_vcadd_rot270 (v2f32 V64:$Rn), (v2f32 V64:$Rm))),
            (FCADDv2f32 (v2f32 V64:$Rn), (v2f32 V64:$Rm), (i32 1))>;
  foreach Ty = [v4f32, v2f64] in {
    def : Pat<(Ty (int_aarch64_neon_vcadd_rot90 (Ty V128:$Rn), (Ty V128:$Rm))),
              (!cast<Instruction>("FCADD"#Ty) (Ty V128:$Rn), (Ty V128:$Rm), (i32 0))>;
    def : Pat<(Ty (int_aarch64_neon_vcadd_rot270 (Ty V128:$Rn), (Ty V128:$Rm))),
              (!cast<Instruction>("FCADD"#Ty) (Ty V128:$Rn), (Ty V128:$Rm), (i32 1))>;
  }
}

// v8.3a Pointer Authentication
// These instructions inhabit part of the hint space and so can be used for
// armv8 targets. Keeping the old HINT mnemonic when compiling without PA is
// important for compatibility with other assemblers (e.g. GAS) when building
// software compatible with both CPUs that do or don't implement PA.
let Uses = [LR], Defs = [LR] in {
  def PACIAZ   : SystemNoOperands<0b000, "hint\t#24">;
  def PACIBZ   : SystemNoOperands<0b010, "hint\t#26">;
  let isAuthenticated = 1 in {
    def AUTIAZ   : SystemNoOperands<0b100, "hint\t#28">;
    def AUTIBZ   : SystemNoOperands<0b110, "hint\t#30">;
  }
}
let Uses = [LR, SP], Defs = [LR] in {
  def PACIASP  : SystemNoOperands<0b001, "hint\t#25">;
  def PACIBSP  : SystemNoOperands<0b011, "hint\t#27">;
  let isAuthenticated = 1 in {
    def AUTIASP  : SystemNoOperands<0b101, "hint\t#29">;
    def AUTIBSP  : SystemNoOperands<0b111, "hint\t#31">;
  }
}
let Uses = [X16, X17], Defs = [X17], CRm = 0b0001 in {
  def PACIA1716  : SystemNoOperands<0b000, "hint\t#8">;
  def PACIB1716  : SystemNoOperands<0b010, "hint\t#10">;
  let isAuthenticated = 1 in {
    def AUTIA1716  : SystemNoOperands<0b100, "hint\t#12">;
    def AUTIB1716  : SystemNoOperands<0b110, "hint\t#14">;
  }
}

let Uses = [LR], Defs = [LR], CRm = 0b0000 in {
  def XPACLRI   : SystemNoOperands<0b111, "hint\t#7">;
}

// In order to be able to write readable assembly, LLVM should accept assembly
// inputs that use pointer authentication mnemonics, even with PA disabled.
// However, in order to be compatible with other assemblers (e.g. GAS), LLVM
// should not emit these mnemonics unless PA is enabled.
def : InstAlias<"paciaz", (PACIAZ), 0>;
def : InstAlias<"pacibz", (PACIBZ), 0>;
def : InstAlias<"autiaz", (AUTIAZ), 0>;
def : InstAlias<"autibz", (AUTIBZ), 0>;
def : InstAlias<"paciasp", (PACIASP), 0>;
def : InstAlias<"pacibsp", (PACIBSP), 0>;
def : InstAlias<"autiasp", (AUTIASP), 0>;
def : InstAlias<"autibsp", (AUTIBSP), 0>;
def : InstAlias<"pacia1716", (PACIA1716), 0>;
def : InstAlias<"pacib1716", (PACIB1716), 0>;
def : InstAlias<"autia1716", (AUTIA1716), 0>;
def : InstAlias<"autib1716", (AUTIB1716), 0>;
def : InstAlias<"xpaclri", (XPACLRI), 0>;

// These pointer authentication instructions require armv8.3a
let Predicates = [HasPA] in {

  // When PA is enabled, a better mnemonic should be emitted.
  def : InstAlias<"paciaz", (PACIAZ), 1>;
  def : InstAlias<"pacibz", (PACIBZ), 1>;
  def : InstAlias<"autiaz", (AUTIAZ), 1>;
  def : InstAlias<"autibz", (AUTIBZ), 1>;
  def : InstAlias<"paciasp", (PACIASP), 1>;
  def : InstAlias<"pacibsp", (PACIBSP), 1>;
  def : InstAlias<"autiasp", (AUTIASP), 1>;
  def : InstAlias<"autibsp", (AUTIBSP), 1>;
  def : InstAlias<"pacia1716", (PACIA1716), 1>;
  def : InstAlias<"pacib1716", (PACIB1716), 1>;
  def : InstAlias<"autia1716", (AUTIA1716), 1>;
  def : InstAlias<"autib1716", (AUTIB1716), 1>;
  def : InstAlias<"xpaclri", (XPACLRI), 1>;

  multiclass SignAuth<bits<3> prefix, bits<3> prefix_z, string asm> {
    def IA   : SignAuthOneData<prefix, 0b00, !strconcat(asm, "ia")>;
    def IB   : SignAuthOneData<prefix, 0b01, !strconcat(asm, "ib")>;
    def DA   : SignAuthOneData<prefix, 0b10, !strconcat(asm, "da")>;
    def DB   : SignAuthOneData<prefix, 0b11, !strconcat(asm, "db")>;
    def IZA  : SignAuthZero<prefix_z, 0b00, !strconcat(asm, "iza")>;
    def DZA  : SignAuthZero<prefix_z, 0b10, !strconcat(asm, "dza")>;
    def IZB  : SignAuthZero<prefix_z, 0b01, !strconcat(asm, "izb")>;
    def DZB  : SignAuthZero<prefix_z, 0b11, !strconcat(asm, "dzb")>;
  }

  defm PAC : SignAuth<0b000, 0b010, "pac">;
  defm AUT : SignAuth<0b001, 0b011, "aut">;

  def XPACI : SignAuthZero<0b100, 0b00, "xpaci">;
  def XPACD : SignAuthZero<0b100, 0b01, "xpacd">;
  def PACGA : SignAuthTwoOperand<0b1100, "pacga", null_frag>;

  // Combined Instructions
  let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1  in {
    def BRAA    : AuthBranchTwoOperands<0, 0, "braa">;
    def BRAB    : AuthBranchTwoOperands<0, 1, "brab">;
  }
  let isCall = 1, Defs = [LR], Uses = [SP] in {
    def BLRAA   : AuthBranchTwoOperands<1, 0, "blraa">;
    def BLRAB   : AuthBranchTwoOperands<1, 1, "blrab">;
  }

  let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1  in {
    def BRAAZ   : AuthOneOperand<0b000, 0, "braaz">;
    def BRABZ   : AuthOneOperand<0b000, 1, "brabz">;
  }
  let isCall = 1, Defs = [LR], Uses = [SP] in {
    def BLRAAZ  : AuthOneOperand<0b001, 0, "blraaz">;
    def BLRABZ  : AuthOneOperand<0b001, 1, "blrabz">;
  }

  let isReturn = 1, isTerminator = 1, isBarrier = 1 in {
    def RETAA   : AuthReturn<0b010, 0, "retaa">;
    def RETAB   : AuthReturn<0b010, 1, "retab">;
    def ERETAA  : AuthReturn<0b100, 0, "eretaa">;
    def ERETAB  : AuthReturn<0b100, 1, "eretab">;
  }

  defm LDRAA  : AuthLoad<0, "ldraa", simm10Scaled>;
  defm LDRAB  : AuthLoad<1, "ldrab", simm10Scaled>;

}

// v8.3a floating point conversion for javascript
let Predicates = [HasJS, HasFPARMv8] in
def FJCVTZS  : BaseFPToIntegerUnscaled<0b01, 0b11, 0b110, FPR64, GPR32,
                                      "fjcvtzs",
                                      [(set GPR32:$Rd,
                                         (int_aarch64_fjcvtzs FPR64:$Rn))]> {
  let Inst{31} = 0;
} // HasJS, HasFPARMv8

// v8.4 Flag manipulation instructions
let Predicates = [HasFMI] in {
def CFINV : SimpleSystemI<0, (ins), "cfinv", "">, Sched<[WriteSys]> {
  let Inst{20-5} = 0b0000001000000000;
}
def SETF8  : BaseFlagManipulation<0, 0, (ins GPR32:$Rn), "setf8", "{\t$Rn}">;
def SETF16 : BaseFlagManipulation<0, 1, (ins GPR32:$Rn), "setf16", "{\t$Rn}">;
def RMIF   : FlagRotate<(ins GPR64:$Rn, uimm6:$imm, imm0_15:$mask), "rmif",
                        "{\t$Rn, $imm, $mask}">;
} // HasFMI

// v8.5 flag manipulation instructions
let Predicates = [HasAltNZCV], Uses = [NZCV], Defs = [NZCV] in {

def XAFLAG : PstateWriteSimple<(ins), "xaflag", "">, Sched<[WriteSys]> {
  let Inst{18-16} = 0b000;
  let Inst{11-8} = 0b0000;
  let Unpredictable{11-8} = 0b1111;
  let Inst{7-5} = 0b001;
}

def AXFLAG : PstateWriteSimple<(ins), "axflag", "">, Sched<[WriteSys]> {
  let Inst{18-16} = 0b000;
  let Inst{11-8} = 0b0000;
  let Unpredictable{11-8} = 0b1111;
  let Inst{7-5} = 0b010;
}
} // HasAltNZCV


// Armv8.5-A speculation barrier
def SB : SimpleSystemI<0, (ins), "sb", "">, Sched<[]> {
  let Inst{20-5} = 0b0001100110000111;
  let Unpredictable{11-8} = 0b1111;
  let Predicates = [HasSB];
  let hasSideEffects = 1;
}

def : InstAlias<"clrex", (CLREX 0xf)>;
def : InstAlias<"isb", (ISB 0xf)>;
def : InstAlias<"ssbb", (DSB 0)>;
def : InstAlias<"pssbb", (DSB 4)>;

def MRS    : MRSI;
def MSR    : MSRI;
def MSRpstateImm1 : MSRpstateImm0_1;
def MSRpstateImm4 : MSRpstateImm0_15;

// The thread pointer (on Linux, at least, where this has been implemented) is
// TPIDR_EL0.
def MOVbaseTLS : Pseudo<(outs GPR64:$dst), (ins),
                       [(set GPR64:$dst, AArch64threadpointer)]>, Sched<[WriteSys]>;

let Uses = [ X9 ], Defs = [ X16, X17, LR, NZCV ] in {
def HWASAN_CHECK_MEMACCESS : Pseudo<
  (outs), (ins GPR64noip:$ptr, i32imm:$accessinfo),
  [(int_hwasan_check_memaccess X9, GPR64noip:$ptr, (i32 timm:$accessinfo))]>,
  Sched<[]>;
def HWASAN_CHECK_MEMACCESS_SHORTGRANULES : Pseudo<
  (outs), (ins GPR64noip:$ptr, i32imm:$accessinfo),
  [(int_hwasan_check_memaccess_shortgranules X9, GPR64noip:$ptr, (i32 timm:$accessinfo))]>,
  Sched<[]>;
}

// The cycle counter PMC register is PMCCNTR_EL0.
let Predicates = [HasPerfMon] in
def : Pat<(readcyclecounter), (MRS 0xdce8)>;

// FPCR register
def : Pat<(i64 (int_aarch64_get_fpcr)), (MRS 0xda20)>;

// Generic system instructions
def SYSxt  : SystemXtI<0, "sys">;
def SYSLxt : SystemLXtI<1, "sysl">;

def : InstAlias<"sys $op1, $Cn, $Cm, $op2",
                (SYSxt imm0_7:$op1, sys_cr_op:$Cn,
                 sys_cr_op:$Cm, imm0_7:$op2, XZR)>;


let Predicates = [HasTME] in {

def TSTART : TMSystemI<0b0000, "tstart",
                      [(set GPR64:$Rt, (int_aarch64_tstart))]>;

def TCOMMIT : TMSystemINoOperand<0b0000, "tcommit", [(int_aarch64_tcommit)]>;

def TCANCEL : TMSystemException<0b011, "tcancel",
                                [(int_aarch64_tcancel i64_imm0_65535:$imm)]>;

def TTEST : TMSystemI<0b0001, "ttest", [(set GPR64:$Rt, (int_aarch64_ttest))]> {
  let mayLoad = 0;
  let mayStore = 0;
}
} // HasTME

//===----------------------------------------------------------------------===//
// Move immediate instructions.
//===----------------------------------------------------------------------===//

defm MOVK : InsertImmediate<0b11, "movk">;
defm MOVN : MoveImmediate<0b00, "movn">;

let PostEncoderMethod = "fixMOVZ" in
defm MOVZ : MoveImmediate<0b10, "movz">;

// First group of aliases covers an implicit "lsl #0".
def : InstAlias<"movk $dst, $imm", (MOVKWi GPR32:$dst, i32_imm0_65535:$imm, 0), 0>;
def : InstAlias<"movk $dst, $imm", (MOVKXi GPR64:$dst, i32_imm0_65535:$imm, 0), 0>;
def : InstAlias<"movn $dst, $imm", (MOVNWi GPR32:$dst, i32_imm0_65535:$imm, 0)>;
def : InstAlias<"movn $dst, $imm", (MOVNXi GPR64:$dst, i32_imm0_65535:$imm, 0)>;
def : InstAlias<"movz $dst, $imm", (MOVZWi GPR32:$dst, i32_imm0_65535:$imm, 0)>;
def : InstAlias<"movz $dst, $imm", (MOVZXi GPR64:$dst, i32_imm0_65535:$imm, 0)>;

// Next, we have various ELF relocations with the ":XYZ_g0:sym" syntax.
def : InstAlias<"movz $Rd, $sym", (MOVZXi GPR64:$Rd, movw_symbol_g3:$sym, 48)>;
def : InstAlias<"movz $Rd, $sym", (MOVZXi GPR64:$Rd, movw_symbol_g2:$sym, 32)>;
def : InstAlias<"movz $Rd, $sym", (MOVZXi GPR64:$Rd, movw_symbol_g1:$sym, 16)>;
def : InstAlias<"movz $Rd, $sym", (MOVZXi GPR64:$Rd, movw_symbol_g0:$sym, 0)>;

def : InstAlias<"movn $Rd, $sym", (MOVNXi GPR64:$Rd, movw_symbol_g3:$sym, 48)>;
def : InstAlias<"movn $Rd, $sym", (MOVNXi GPR64:$Rd, movw_symbol_g2:$sym, 32)>;
def : InstAlias<"movn $Rd, $sym", (MOVNXi GPR64:$Rd, movw_symbol_g1:$sym, 16)>;
def : InstAlias<"movn $Rd, $sym", (MOVNXi GPR64:$Rd, movw_symbol_g0:$sym, 0)>;

def : InstAlias<"movk $Rd, $sym", (MOVKXi GPR64:$Rd, movw_symbol_g3:$sym, 48), 0>;
def : InstAlias<"movk $Rd, $sym", (MOVKXi GPR64:$Rd, movw_symbol_g2:$sym, 32), 0>;
def : InstAlias<"movk $Rd, $sym", (MOVKXi GPR64:$Rd, movw_symbol_g1:$sym, 16), 0>;
def : InstAlias<"movk $Rd, $sym", (MOVKXi GPR64:$Rd, movw_symbol_g0:$sym, 0), 0>;

def : InstAlias<"movz $Rd, $sym", (MOVZWi GPR32:$Rd, movw_symbol_g1:$sym, 16)>;
def : InstAlias<"movz $Rd, $sym", (MOVZWi GPR32:$Rd, movw_symbol_g0:$sym, 0)>;

def : InstAlias<"movn $Rd, $sym", (MOVNWi GPR32:$Rd, movw_symbol_g1:$sym, 16)>;
def : InstAlias<"movn $Rd, $sym", (MOVNWi GPR32:$Rd, movw_symbol_g0:$sym, 0)>;

def : InstAlias<"movk $Rd, $sym", (MOVKWi GPR32:$Rd, movw_symbol_g1:$sym, 16), 0>;
def : InstAlias<"movk $Rd, $sym", (MOVKWi GPR32:$Rd, movw_symbol_g0:$sym, 0), 0>;

// Final group of aliases covers true "mov $Rd, $imm" cases.
multiclass movw_mov_alias<string basename,Instruction INST, RegisterClass GPR,
                          int width, int shift> {
  def _asmoperand : AsmOperandClass {
    let Name = basename # width # "_lsl" # shift # "MovAlias";
    let PredicateMethod = "is" # basename # "MovAlias<" # width # ", "
                               # shift # ">";
    let RenderMethod = "add" # basename # "MovAliasOperands<" # shift # ">";
  }

  def _movimm : Operand<i32> {
    let ParserMatchClass = !cast<AsmOperandClass>(NAME # "_asmoperand");
  }

  def : InstAlias<"mov $Rd, $imm",
                  (INST GPR:$Rd, !cast<Operand>(NAME # "_movimm"):$imm, shift)>;
}

defm : movw_mov_alias<"MOVZ", MOVZWi, GPR32, 32, 0>;
defm : movw_mov_alias<"MOVZ", MOVZWi, GPR32, 32, 16>;

defm : movw_mov_alias<"MOVZ", MOVZXi, GPR64, 64, 0>;
defm : movw_mov_alias<"MOVZ", MOVZXi, GPR64, 64, 16>;
defm : movw_mov_alias<"MOVZ", MOVZXi, GPR64, 64, 32>;
defm : movw_mov_alias<"MOVZ", MOVZXi, GPR64, 64, 48>;

defm : movw_mov_alias<"MOVN", MOVNWi, GPR32, 32, 0>;
defm : movw_mov_alias<"MOVN", MOVNWi, GPR32, 32, 16>;

defm : movw_mov_alias<"MOVN", MOVNXi, GPR64, 64, 0>;
defm : movw_mov_alias<"MOVN", MOVNXi, GPR64, 64, 16>;
defm : movw_mov_alias<"MOVN", MOVNXi, GPR64, 64, 32>;
defm : movw_mov_alias<"MOVN", MOVNXi, GPR64, 64, 48>;

let isReMaterializable = 1, isCodeGenOnly = 1, isMoveImm = 1,
    isAsCheapAsAMove = 1 in {
// FIXME: The following pseudo instructions are only needed because remat
// cannot handle multiple instructions.  When that changes, we can select
// directly to the real instructions and get rid of these pseudos.

def MOVi32imm
    : Pseudo<(outs GPR32:$dst), (ins i32imm:$src),
             [(set GPR32:$dst, imm:$src)]>,
      Sched<[WriteImm]>;
def MOVi64imm
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$src),
             [(set GPR64:$dst, imm:$src)]>,
      Sched<[WriteImm]>;
} // isReMaterializable, isCodeGenOnly

// If possible, we want to use MOVi32imm even for 64-bit moves. This gives the
// eventual expansion code fewer bits to worry about getting right. Marshalling
// the types is a little tricky though:
def i64imm_32bit : ImmLeaf<i64, [{
  return (Imm & 0xffffffffULL) == static_cast<uint64_t>(Imm);
}]>;

def s64imm_32bit : ImmLeaf<i64, [{
  int64_t Imm64 = static_cast<int64_t>(Imm);
  return Imm64 >= std::numeric_limits<int32_t>::min() &&
         Imm64 <= std::numeric_limits<int32_t>::max();
}]>;

def trunc_imm : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(N->getZExtValue(), SDLoc(N), MVT::i32);
}]>;

def gi_trunc_imm : GICustomOperandRenderer<"renderTruncImm">,
  GISDNodeXFormEquiv<trunc_imm>;

let Predicates = [OptimizedGISelOrOtherSelector] in {
// The SUBREG_TO_REG isn't eliminated at -O0, which can result in pointless
// copies.
def : Pat<(i64 i64imm_32bit:$src),
          (SUBREG_TO_REG (i64 0), (MOVi32imm (trunc_imm imm:$src)), sub_32)>;
}

// Materialize FP constants via MOVi32imm/MOVi64imm (MachO large code model).
def bitcast_fpimm_to_i32 : SDNodeXForm<fpimm, [{
return CurDAG->getTargetConstant(
  N->getValueAPF().bitcastToAPInt().getZExtValue(), SDLoc(N), MVT::i32);
}]>;

def bitcast_fpimm_to_i64 : SDNodeXForm<fpimm, [{
return CurDAG->getTargetConstant(
  N->getValueAPF().bitcastToAPInt().getZExtValue(), SDLoc(N), MVT::i64);
}]>;


def : Pat<(f32 fpimm:$in),
  (COPY_TO_REGCLASS (MOVi32imm (bitcast_fpimm_to_i32 f32:$in)), FPR32)>;
def : Pat<(f64 fpimm:$in),
  (COPY_TO_REGCLASS (MOVi64imm (bitcast_fpimm_to_i64 f64:$in)), FPR64)>;


// Deal with the various forms of (ELF) large addressing with MOVZ/MOVK
// sequences.
def : Pat<(AArch64WrapperLarge tglobaladdr:$g3, tglobaladdr:$g2,
                             tglobaladdr:$g1, tglobaladdr:$g0),
          (MOVKXi (MOVKXi (MOVKXi (MOVZXi tglobaladdr:$g0, 0),
                                  tglobaladdr:$g1, 16),
                          tglobaladdr:$g2, 32),
                  tglobaladdr:$g3, 48)>;

def : Pat<(AArch64WrapperLarge tblockaddress:$g3, tblockaddress:$g2,
                             tblockaddress:$g1, tblockaddress:$g0),
          (MOVKXi (MOVKXi (MOVKXi (MOVZXi tblockaddress:$g0, 0),
                                  tblockaddress:$g1, 16),
                          tblockaddress:$g2, 32),
                  tblockaddress:$g3, 48)>;

def : Pat<(AArch64WrapperLarge tconstpool:$g3, tconstpool:$g2,
                             tconstpool:$g1, tconstpool:$g0),
          (MOVKXi (MOVKXi (MOVKXi (MOVZXi tconstpool:$g0, 0),
                                  tconstpool:$g1, 16),
                          tconstpool:$g2, 32),
                  tconstpool:$g3, 48)>;

def : Pat<(AArch64WrapperLarge tjumptable:$g3, tjumptable:$g2,
                             tjumptable:$g1, tjumptable:$g0),
          (MOVKXi (MOVKXi (MOVKXi (MOVZXi tjumptable:$g0, 0),
                                  tjumptable:$g1, 16),
                          tjumptable:$g2, 32),
                  tjumptable:$g3, 48)>;


//===----------------------------------------------------------------------===//
// Arithmetic instructions.
//===----------------------------------------------------------------------===//

// Add/subtract with carry.
defm ADC : AddSubCarry<0, "adc", "adcs", AArch64adc, AArch64adc_flag>;
defm SBC : AddSubCarry<1, "sbc", "sbcs", AArch64sbc, AArch64sbc_flag>;

def : InstAlias<"ngc $dst, $src",  (SBCWr  GPR32:$dst, WZR, GPR32:$src)>;
def : InstAlias<"ngc $dst, $src",  (SBCXr  GPR64:$dst, XZR, GPR64:$src)>;
def : InstAlias<"ngcs $dst, $src", (SBCSWr GPR32:$dst, WZR, GPR32:$src)>;
def : InstAlias<"ngcs $dst, $src", (SBCSXr GPR64:$dst, XZR, GPR64:$src)>;

// Add/subtract
defm ADD : AddSub<0, "add", "sub", add>;
defm SUB : AddSub<1, "sub", "add">;

def : InstAlias<"mov $dst, $src",
                (ADDWri GPR32sponly:$dst, GPR32sp:$src, 0, 0)>;
def : InstAlias<"mov $dst, $src",
                (ADDWri GPR32sp:$dst, GPR32sponly:$src, 0, 0)>;
def : InstAlias<"mov $dst, $src",
                (ADDXri GPR64sponly:$dst, GPR64sp:$src, 0, 0)>;
def : InstAlias<"mov $dst, $src",
                (ADDXri GPR64sp:$dst, GPR64sponly:$src, 0, 0)>;

defm ADDS : AddSubS<0, "adds", AArch64add_flag, "cmn", "subs", "cmp">;
defm SUBS : AddSubS<1, "subs", AArch64sub_flag, "cmp", "adds", "cmn">;

// Use SUBS instead of SUB to enable CSE between SUBS and SUB.
def : Pat<(sub GPR32sp:$Rn, addsub_shifted_imm32:$imm),
          (SUBSWri GPR32sp:$Rn, addsub_shifted_imm32:$imm)>;
def : Pat<(sub GPR64sp:$Rn, addsub_shifted_imm64:$imm),
          (SUBSXri GPR64sp:$Rn, addsub_shifted_imm64:$imm)>;
def : Pat<(sub GPR32:$Rn, GPR32:$Rm),
          (SUBSWrr GPR32:$Rn, GPR32:$Rm)>;
def : Pat<(sub GPR64:$Rn, GPR64:$Rm),
          (SUBSXrr GPR64:$Rn, GPR64:$Rm)>;
def : Pat<(sub GPR32:$Rn, arith_shifted_reg32:$Rm),
          (SUBSWrs GPR32:$Rn, arith_shifted_reg32:$Rm)>;
def : Pat<(sub GPR64:$Rn, arith_shifted_reg64:$Rm),
          (SUBSXrs GPR64:$Rn, arith_shifted_reg64:$Rm)>;
let AddedComplexity = 1 in {
def : Pat<(sub GPR32sp:$R2, arith_extended_reg32_i32:$R3),
          (SUBSWrx GPR32sp:$R2, arith_extended_reg32_i32:$R3)>;
def : Pat<(sub GPR64sp:$R2, arith_extended_reg32to64_i64:$R3),
          (SUBSXrx GPR64sp:$R2, arith_extended_reg32to64_i64:$R3)>;
}

// Because of the immediate format for add/sub-imm instructions, the
// expression (add x, -1) must be transformed to (SUB{W,X}ri x, 1).
//  These patterns capture that transformation.
let AddedComplexity = 1 in {
def : Pat<(add GPR32:$Rn, neg_addsub_shifted_imm32:$imm),
          (SUBSWri GPR32:$Rn, neg_addsub_shifted_imm32:$imm)>;
def : Pat<(add GPR64:$Rn, neg_addsub_shifted_imm64:$imm),
          (SUBSXri GPR64:$Rn, neg_addsub_shifted_imm64:$imm)>;
def : Pat<(sub GPR32:$Rn, neg_addsub_shifted_imm32:$imm),
          (ADDWri GPR32:$Rn, neg_addsub_shifted_imm32:$imm)>;
def : Pat<(sub GPR64:$Rn, neg_addsub_shifted_imm64:$imm),
          (ADDXri GPR64:$Rn, neg_addsub_shifted_imm64:$imm)>;
}

// Because of the immediate format for add/sub-imm instructions, the
// expression (add x, -1) must be transformed to (SUB{W,X}ri x, 1).
//  These patterns capture that transformation.
let AddedComplexity = 1 in {
def : Pat<(AArch64add_flag GPR32:$Rn, neg_addsub_shifted_imm32:$imm),
          (SUBSWri GPR32:$Rn, neg_addsub_shifted_imm32:$imm)>;
def : Pat<(AArch64add_flag GPR64:$Rn, neg_addsub_shifted_imm64:$imm),
          (SUBSXri GPR64:$Rn, neg_addsub_shifted_imm64:$imm)>;
def : Pat<(AArch64sub_flag GPR32:$Rn, neg_addsub_shifted_imm32:$imm),
          (ADDSWri GPR32:$Rn, neg_addsub_shifted_imm32:$imm)>;
def : Pat<(AArch64sub_flag GPR64:$Rn, neg_addsub_shifted_imm64:$imm),
          (ADDSXri GPR64:$Rn, neg_addsub_shifted_imm64:$imm)>;
}

def : InstAlias<"neg $dst, $src", (SUBWrs GPR32:$dst, WZR, GPR32:$src, 0), 3>;
def : InstAlias<"neg $dst, $src", (SUBXrs GPR64:$dst, XZR, GPR64:$src, 0), 3>;
def : InstAlias<"neg $dst, $src$shift",
                (SUBWrs GPR32:$dst, WZR, GPR32:$src, arith_shift32:$shift), 2>;
def : InstAlias<"neg $dst, $src$shift",
                (SUBXrs GPR64:$dst, XZR, GPR64:$src, arith_shift64:$shift), 2>;

def : InstAlias<"negs $dst, $src", (SUBSWrs GPR32:$dst, WZR, GPR32:$src, 0), 3>;
def : InstAlias<"negs $dst, $src", (SUBSXrs GPR64:$dst, XZR, GPR64:$src, 0), 3>;
def : InstAlias<"negs $dst, $src$shift",
                (SUBSWrs GPR32:$dst, WZR, GPR32:$src, arith_shift32:$shift), 2>;
def : InstAlias<"negs $dst, $src$shift",
                (SUBSXrs GPR64:$dst, XZR, GPR64:$src, arith_shift64:$shift), 2>;


// Unsigned/Signed divide
defm UDIV : Div<0, "udiv", udiv>;
defm SDIV : Div<1, "sdiv", sdiv>;

def : Pat<(int_aarch64_udiv GPR32:$Rn, GPR32:$Rm), (UDIVWr GPR32:$Rn, GPR32:$Rm)>;
def : Pat<(int_aarch64_udiv GPR64:$Rn, GPR64:$Rm), (UDIVXr GPR64:$Rn, GPR64:$Rm)>;
def : Pat<(int_aarch64_sdiv GPR32:$Rn, GPR32:$Rm), (SDIVWr GPR32:$Rn, GPR32:$Rm)>;
def : Pat<(int_aarch64_sdiv GPR64:$Rn, GPR64:$Rm), (SDIVXr GPR64:$Rn, GPR64:$Rm)>;

// Variable shift
defm ASRV : Shift<0b10, "asr", sra>;
defm LSLV : Shift<0b00, "lsl", shl>;
defm LSRV : Shift<0b01, "lsr", srl>;
defm RORV : Shift<0b11, "ror", rotr>;

def : ShiftAlias<"asrv", ASRVWr, GPR32>;
def : ShiftAlias<"asrv", ASRVXr, GPR64>;
def : ShiftAlias<"lslv", LSLVWr, GPR32>;
def : ShiftAlias<"lslv", LSLVXr, GPR64>;
def : ShiftAlias<"lsrv", LSRVWr, GPR32>;
def : ShiftAlias<"lsrv", LSRVXr, GPR64>;
def : ShiftAlias<"rorv", RORVWr, GPR32>;
def : ShiftAlias<"rorv", RORVXr, GPR64>;

// Multiply-add
let AddedComplexity = 5 in {
defm MADD : MulAccum<0, "madd", add>;
defm MSUB : MulAccum<1, "msub", sub>;

def : Pat<(i32 (mul GPR32:$Rn, GPR32:$Rm)),
          (MADDWrrr GPR32:$Rn, GPR32:$Rm, WZR)>;
def : Pat<(i64 (mul GPR64:$Rn, GPR64:$Rm)),
          (MADDXrrr GPR64:$Rn, GPR64:$Rm, XZR)>;

def : Pat<(i32 (ineg (mul GPR32:$Rn, GPR32:$Rm))),
          (MSUBWrrr GPR32:$Rn, GPR32:$Rm, WZR)>;
def : Pat<(i64 (ineg (mul GPR64:$Rn, GPR64:$Rm))),
          (MSUBXrrr GPR64:$Rn, GPR64:$Rm, XZR)>;
def : Pat<(i32 (mul (ineg GPR32:$Rn), GPR32:$Rm)),
          (MSUBWrrr GPR32:$Rn, GPR32:$Rm, WZR)>;
def : Pat<(i64 (mul (ineg GPR64:$Rn), GPR64:$Rm)),
          (MSUBXrrr GPR64:$Rn, GPR64:$Rm, XZR)>;
} // AddedComplexity = 5

let AddedComplexity = 5 in {
def SMADDLrrr : WideMulAccum<0, 0b001, "smaddl", add, sext>;
def SMSUBLrrr : WideMulAccum<1, 0b001, "smsubl", sub, sext>;
def UMADDLrrr : WideMulAccum<0, 0b101, "umaddl", add, zext>;
def UMSUBLrrr : WideMulAccum<1, 0b101, "umsubl", sub, zext>;

def : Pat<(i64 (mul (sext GPR32:$Rn), (sext GPR32:$Rm))),
          (SMADDLrrr GPR32:$Rn, GPR32:$Rm, XZR)>;
def : Pat<(i64 (mul (zext GPR32:$Rn), (zext GPR32:$Rm))),
          (UMADDLrrr GPR32:$Rn, GPR32:$Rm, XZR)>;

def : Pat<(i64 (ineg (mul (sext GPR32:$Rn), (sext GPR32:$Rm)))),
          (SMSUBLrrr GPR32:$Rn, GPR32:$Rm, XZR)>;
def : Pat<(i64 (ineg (mul (zext GPR32:$Rn), (zext GPR32:$Rm)))),
          (UMSUBLrrr GPR32:$Rn, GPR32:$Rm, XZR)>;

def : Pat<(i64 (mul (sext GPR32:$Rn), (s64imm_32bit:$C))),
          (SMADDLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), XZR)>;
def : Pat<(i64 (mul (zext GPR32:$Rn), (i64imm_32bit:$C))),
          (UMADDLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), XZR)>;
def : Pat<(i64 (mul (sext_inreg GPR64:$Rn, i32), (s64imm_32bit:$C))),
          (SMADDLrrr (i32 (EXTRACT_SUBREG GPR64:$Rn, sub_32)),
                     (MOVi32imm (trunc_imm imm:$C)), XZR)>;

def : Pat<(i64 (ineg (mul (sext GPR32:$Rn), (s64imm_32bit:$C)))),
          (SMSUBLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), XZR)>;
def : Pat<(i64 (ineg (mul (zext GPR32:$Rn), (i64imm_32bit:$C)))),
          (UMSUBLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), XZR)>;
def : Pat<(i64 (ineg (mul (sext_inreg GPR64:$Rn, i32), (s64imm_32bit:$C)))),
          (SMSUBLrrr (i32 (EXTRACT_SUBREG GPR64:$Rn, sub_32)),
                     (MOVi32imm (trunc_imm imm:$C)), XZR)>;

def : Pat<(i64 (add (mul (sext GPR32:$Rn), (s64imm_32bit:$C)), GPR64:$Ra)),
          (SMADDLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
def : Pat<(i64 (add (mul (zext GPR32:$Rn), (i64imm_32bit:$C)), GPR64:$Ra)),
          (UMADDLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
def : Pat<(i64 (add (mul (sext_inreg GPR64:$Rn, i32), (s64imm_32bit:$C)),
                    GPR64:$Ra)),
          (SMADDLrrr (i32 (EXTRACT_SUBREG GPR64:$Rn, sub_32)),
                     (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;

def : Pat<(i64 (sub GPR64:$Ra, (mul (sext GPR32:$Rn), (s64imm_32bit:$C)))),
          (SMSUBLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
def : Pat<(i64 (sub GPR64:$Ra, (mul (zext GPR32:$Rn), (i64imm_32bit:$C)))),
          (UMSUBLrrr GPR32:$Rn, (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
def : Pat<(i64 (sub GPR64:$Ra, (mul (sext_inreg GPR64:$Rn, i32),
                                    (s64imm_32bit:$C)))),
          (SMSUBLrrr (i32 (EXTRACT_SUBREG GPR64:$Rn, sub_32)),
                     (MOVi32imm (trunc_imm imm:$C)), GPR64:$Ra)>;
} // AddedComplexity = 5

def : MulAccumWAlias<"mul", MADDWrrr>;
def : MulAccumXAlias<"mul", MADDXrrr>;
def : MulAccumWAlias<"mneg", MSUBWrrr>;
def : MulAccumXAlias<"mneg", MSUBXrrr>;
def : WideMulAccumAlias<"smull", SMADDLrrr>;
def : WideMulAccumAlias<"smnegl", SMSUBLrrr>;
def : WideMulAccumAlias<"umull", UMADDLrrr>;
def : WideMulAccumAlias<"umnegl", UMSUBLrrr>;

// Multiply-high
def SMULHrr : MulHi<0b010, "smulh", mulhs>;
def UMULHrr : MulHi<0b110, "umulh", mulhu>;

// CRC32
def CRC32Brr : BaseCRC32<0, 0b00, 0, GPR32, int_aarch64_crc32b, "crc32b">;
def CRC32Hrr : BaseCRC32<0, 0b01, 0, GPR32, int_aarch64_crc32h, "crc32h">;
def CRC32Wrr : BaseCRC32<0, 0b10, 0, GPR32, int_aarch64_crc32w, "crc32w">;
def CRC32Xrr : BaseCRC32<1, 0b11, 0, GPR64, int_aarch64_crc32x, "crc32x">;

def CRC32CBrr : BaseCRC32<0, 0b00, 1, GPR32, int_aarch64_crc32cb, "crc32cb">;
def CRC32CHrr : BaseCRC32<0, 0b01, 1, GPR32, int_aarch64_crc32ch, "crc32ch">;
def CRC32CWrr : BaseCRC32<0, 0b10, 1, GPR32, int_aarch64_crc32cw, "crc32cw">;
def CRC32CXrr : BaseCRC32<1, 0b11, 1, GPR64, int_aarch64_crc32cx, "crc32cx">;

// v8.1 atomic CAS
defm CAS   : CompareAndSwap<0, 0, "">;
defm CASA  : CompareAndSwap<1, 0, "a">;
defm CASL  : CompareAndSwap<0, 1, "l">;
defm CASAL : CompareAndSwap<1, 1, "al">;

// v8.1 atomic CASP
defm CASP   : CompareAndSwapPair<0, 0, "">;
defm CASPA  : CompareAndSwapPair<1, 0, "a">;
defm CASPL  : CompareAndSwapPair<0, 1, "l">;
defm CASPAL : CompareAndSwapPair<1, 1, "al">;

// v8.1 atomic SWP
defm SWP   : Swap<0, 0, "">;
defm SWPA  : Swap<1, 0, "a">;
defm SWPL  : Swap<0, 1, "l">;
defm SWPAL : Swap<1, 1, "al">;

// v8.1 atomic LD<OP>(register). Performs load and then ST<OP>(register)
defm LDADD   : LDOPregister<0b000, "add", 0, 0, "">;
defm LDADDA  : LDOPregister<0b000, "add", 1, 0, "a">;
defm LDADDL  : LDOPregister<0b000, "add", 0, 1, "l">;
defm LDADDAL : LDOPregister<0b000, "add", 1, 1, "al">;

defm LDCLR   : LDOPregister<0b001, "clr", 0, 0, "">;
defm LDCLRA  : LDOPregister<0b001, "clr", 1, 0, "a">;
defm LDCLRL  : LDOPregister<0b001, "clr", 0, 1, "l">;
defm LDCLRAL : LDOPregister<0b001, "clr", 1, 1, "al">;

defm LDEOR   : LDOPregister<0b010, "eor", 0, 0, "">;
defm LDEORA  : LDOPregister<0b010, "eor", 1, 0, "a">;
defm LDEORL  : LDOPregister<0b010, "eor", 0, 1, "l">;
defm LDEORAL : LDOPregister<0b010, "eor", 1, 1, "al">;

defm LDSET   : LDOPregister<0b011, "set", 0, 0, "">;
defm LDSETA  : LDOPregister<0b011, "set", 1, 0, "a">;
defm LDSETL  : LDOPregister<0b011, "set", 0, 1, "l">;
defm LDSETAL : LDOPregister<0b011, "set", 1, 1, "al">;

defm LDSMAX   : LDOPregister<0b100, "smax", 0, 0, "">;
defm LDSMAXA  : LDOPregister<0b100, "smax", 1, 0, "a">;
defm LDSMAXL  : LDOPregister<0b100, "smax", 0, 1, "l">;
defm LDSMAXAL : LDOPregister<0b100, "smax", 1, 1, "al">;

defm LDSMIN   : LDOPregister<0b101, "smin", 0, 0, "">;
defm LDSMINA  : LDOPregister<0b101, "smin", 1, 0, "a">;
defm LDSMINL  : LDOPregister<0b101, "smin", 0, 1, "l">;
defm LDSMINAL : LDOPregister<0b101, "smin", 1, 1, "al">;

defm LDUMAX   : LDOPregister<0b110, "umax", 0, 0, "">;
defm LDUMAXA  : LDOPregister<0b110, "umax", 1, 0, "a">;
defm LDUMAXL  : LDOPregister<0b110, "umax", 0, 1, "l">;
defm LDUMAXAL : LDOPregister<0b110, "umax", 1, 1, "al">;

defm LDUMIN   : LDOPregister<0b111, "umin", 0, 0, "">;
defm LDUMINA  : LDOPregister<0b111, "umin", 1, 0, "a">;
defm LDUMINL  : LDOPregister<0b111, "umin", 0, 1, "l">;
defm LDUMINAL : LDOPregister<0b111, "umin", 1, 1, "al">;

// v8.1 atomic ST<OP>(register) as aliases to "LD<OP>(register) when Rt=xZR"
defm : STOPregister<"stadd","LDADD">; // STADDx
defm : STOPregister<"stclr","LDCLR">; // STCLRx
defm : STOPregister<"steor","LDEOR">; // STEORx
defm : STOPregister<"stset","LDSET">; // STSETx
defm : STOPregister<"stsmax","LDSMAX">;// STSMAXx
defm : STOPregister<"stsmin","LDSMIN">;// STSMINx
defm : STOPregister<"stumax","LDUMAX">;// STUMAXx
defm : STOPregister<"stumin","LDUMIN">;// STUMINx

// v8.5 Memory Tagging Extension
let Predicates = [HasMTE] in {

def IRG   : BaseTwoOperand<0b0100, GPR64sp, "irg", int_aarch64_irg, GPR64sp, GPR64>,
            Sched<[]>{
  let Inst{31} = 1;
}
def GMI   : BaseTwoOperand<0b0101, GPR64, "gmi", int_aarch64_gmi, GPR64sp>, Sched<[]>{
  let Inst{31} = 1;
  let isNotDuplicable = 1;
}
def ADDG  : AddSubG<0, "addg", null_frag>;
def SUBG  : AddSubG<1, "subg", null_frag>;

def : InstAlias<"irg $dst, $src", (IRG GPR64sp:$dst, GPR64sp:$src, XZR), 1>;

def SUBP : SUBP<0, "subp", int_aarch64_subp>, Sched<[]>;
def SUBPS : SUBP<1, "subps", null_frag>, Sched<[]>{
  let Defs = [NZCV];
}

def : InstAlias<"cmpp $lhs, $rhs", (SUBPS XZR, GPR64sp:$lhs, GPR64sp:$rhs), 0>;

def LDG : MemTagLoad<"ldg", "\t$Rt, [$Rn, $offset]">;

def : Pat<(int_aarch64_addg (am_indexedu6s128 GPR64sp:$Rn, uimm6s16:$imm6), imm0_15:$imm4),
          (ADDG GPR64sp:$Rn, imm0_63:$imm6, imm0_15:$imm4)>;
def : Pat<(int_aarch64_ldg GPR64:$Rt, (am_indexeds9s128 GPR64sp:$Rn,  simm9s16:$offset)),
          (LDG GPR64:$Rt, GPR64sp:$Rn,  simm9s16:$offset)>;

def : InstAlias<"ldg $Rt, [$Rn]", (LDG GPR64:$Rt, GPR64sp:$Rn, 0), 1>;

def LDGM : MemTagVector<1, "ldgm", "\t$Rt, [$Rn]",
                   (outs GPR64:$Rt), (ins GPR64sp:$Rn)>;
def STGM : MemTagVector<0, "stgm", "\t$Rt, [$Rn]",
                   (outs), (ins GPR64:$Rt, GPR64sp:$Rn)>;
def STZGM : MemTagVector<0, "stzgm", "\t$Rt, [$Rn]",
                   (outs), (ins GPR64:$Rt, GPR64sp:$Rn)> {
  let Inst{23} = 0;
}

defm STG   : MemTagStore<0b00, "stg">;
defm STZG  : MemTagStore<0b01, "stzg">;
defm ST2G  : MemTagStore<0b10, "st2g">;
defm STZ2G : MemTagStore<0b11, "stz2g">;

def : Pat<(AArch64stg GPR64sp:$Rn, (am_indexeds9s128 GPR64sp:$Rm, simm9s16:$imm)),
          (STGOffset $Rn, $Rm, $imm)>;
def : Pat<(AArch64stzg GPR64sp:$Rn, (am_indexeds9s128 GPR64sp:$Rm, simm9s16:$imm)),
          (STZGOffset $Rn, $Rm, $imm)>;
def : Pat<(AArch64st2g GPR64sp:$Rn, (am_indexeds9s128 GPR64sp:$Rm, simm9s16:$imm)),
          (ST2GOffset $Rn, $Rm, $imm)>;
def : Pat<(AArch64stz2g GPR64sp:$Rn, (am_indexeds9s128 GPR64sp:$Rm, simm9s16:$imm)),
          (STZ2GOffset $Rn, $Rm, $imm)>;

defm STGP     : StorePairOffset <0b01, 0, GPR64z, simm7s16, "stgp">;
def  STGPpre  : StorePairPreIdx <0b01, 0, GPR64z, simm7s16, "stgp">;
def  STGPpost : StorePairPostIdx<0b01, 0, GPR64z, simm7s16, "stgp">;

def : Pat<(int_aarch64_stg GPR64:$Rt, (am_indexeds9s128 GPR64sp:$Rn, simm9s16:$offset)),
          (STGOffset GPR64:$Rt, GPR64sp:$Rn,  simm9s16:$offset)>;

def : Pat<(int_aarch64_stgp (am_indexed7s128 GPR64sp:$Rn, simm7s16:$imm), GPR64:$Rt, GPR64:$Rt2),
          (STGPi $Rt, $Rt2, $Rn, $imm)>;

def IRGstack
    : Pseudo<(outs GPR64sp:$Rd), (ins GPR64sp:$Rsp, GPR64:$Rm), []>,
      Sched<[]>;
def TAGPstack
    : Pseudo<(outs GPR64sp:$Rd), (ins GPR64sp:$Rn, uimm6s16:$imm6, GPR64sp:$Rm, imm0_15:$imm4), []>,
      Sched<[]>;

// Explicit SP in the first operand prevents ShrinkWrap optimization
// from leaving this instruction out of the stack frame. When IRGstack
// is transformed into IRG, this operand is replaced with the actual
// register / expression for the tagged base pointer of the current function.
def : Pat<(int_aarch64_irg_sp i64:$Rm), (IRGstack SP, i64:$Rm)>;

// Large STG to be expanded into a loop. $sz is the size, $Rn is start address.
// $Rn_wback is one past the end of the range. $Rm is the loop counter.
let isCodeGenOnly=1, mayStore=1 in {
def STGloop_wback
    : Pseudo<(outs GPR64common:$Rm, GPR64sp:$Rn_wback), (ins i64imm:$sz, GPR64sp:$Rn),
             [], "$Rn = $Rn_wback,@earlyclobber $Rn_wback,@earlyclobber $Rm" >,
      Sched<[WriteAdr, WriteST]>;

def STZGloop_wback
    : Pseudo<(outs GPR64common:$Rm, GPR64sp:$Rn_wback), (ins i64imm:$sz, GPR64sp:$Rn),
             [], "$Rn = $Rn_wback,@earlyclobber $Rn_wback,@earlyclobber $Rm" >,
      Sched<[WriteAdr, WriteST]>;

// A variant of the above where $Rn2 is an independent register not tied to the input register $Rn.
// Their purpose is to use a FrameIndex operand as $Rn (which of course can not be written back).
def STGloop
    : Pseudo<(outs GPR64common:$Rm, GPR64sp:$Rn2), (ins i64imm:$sz, GPR64sp:$Rn),
             [], "@earlyclobber $Rn2,@earlyclobber $Rm" >,
      Sched<[WriteAdr, WriteST]>;

def STZGloop
    : Pseudo<(outs GPR64common:$Rm, GPR64sp:$Rn2), (ins i64imm:$sz, GPR64sp:$Rn),
             [], "@earlyclobber $Rn2,@earlyclobber $Rm" >,
      Sched<[WriteAdr, WriteST]>;
}

} // Predicates = [HasMTE]

//===----------------------------------------------------------------------===//
// Logical instructions.
//===----------------------------------------------------------------------===//

// (immediate)
defm ANDS : LogicalImmS<0b11, "ands", AArch64and_flag, "bics">;
defm AND  : LogicalImm<0b00, "and", and, "bic">;
defm EOR  : LogicalImm<0b10, "eor", xor, "eon">;
defm ORR  : LogicalImm<0b01, "orr", or, "orn">;

// FIXME: these aliases *are* canonical sometimes (when movz can't be
// used). Actually, it seems to be working right now, but putting logical_immXX
// here is a bit dodgy on the AsmParser side too.
def : InstAlias<"mov $dst, $imm", (ORRWri GPR32sp:$dst, WZR,
                                          logical_imm32:$imm), 0>;
def : InstAlias<"mov $dst, $imm", (ORRXri GPR64sp:$dst, XZR,
                                          logical_imm64:$imm), 0>;


// (register)
defm ANDS : LogicalRegS<0b11, 0, "ands", AArch64and_flag>;
defm BICS : LogicalRegS<0b11, 1, "bics",
                        BinOpFrag<(AArch64and_flag node:$LHS, (not node:$RHS))>>;
defm AND  : LogicalReg<0b00, 0, "and", and>;
defm BIC  : LogicalReg<0b00, 1, "bic",
                       BinOpFrag<(and node:$LHS, (not node:$RHS))>>;
defm EON  : LogicalReg<0b10, 1, "eon",
                       BinOpFrag<(not (xor node:$LHS, node:$RHS))>>;
defm EOR  : LogicalReg<0b10, 0, "eor", xor>;
defm ORN  : LogicalReg<0b01, 1, "orn",
                       BinOpFrag<(or node:$LHS, (not node:$RHS))>>;
defm ORR  : LogicalReg<0b01, 0, "orr", or>;

def : InstAlias<"mov $dst, $src", (ORRWrs GPR32:$dst, WZR, GPR32:$src, 0), 2>;
def : InstAlias<"mov $dst, $src", (ORRXrs GPR64:$dst, XZR, GPR64:$src, 0), 2>;

def : InstAlias<"mvn $Wd, $Wm", (ORNWrs GPR32:$Wd, WZR, GPR32:$Wm, 0), 3>;
def : InstAlias<"mvn $Xd, $Xm", (ORNXrs GPR64:$Xd, XZR, GPR64:$Xm, 0), 3>;

def : InstAlias<"mvn $Wd, $Wm$sh",
                (ORNWrs GPR32:$Wd, WZR, GPR32:$Wm, logical_shift32:$sh), 2>;
def : InstAlias<"mvn $Xd, $Xm$sh",
                (ORNXrs GPR64:$Xd, XZR, GPR64:$Xm, logical_shift64:$sh), 2>;

def : InstAlias<"tst $src1, $src2",
                (ANDSWri WZR, GPR32:$src1, logical_imm32:$src2), 2>;
def : InstAlias<"tst $src1, $src2",
                (ANDSXri XZR, GPR64:$src1, logical_imm64:$src2), 2>;

def : InstAlias<"tst $src1, $src2",
                        (ANDSWrs WZR, GPR32:$src1, GPR32:$src2, 0), 3>;
def : InstAlias<"tst $src1, $src2",
                        (ANDSXrs XZR, GPR64:$src1, GPR64:$src2, 0), 3>;

def : InstAlias<"tst $src1, $src2$sh",
               (ANDSWrs WZR, GPR32:$src1, GPR32:$src2, logical_shift32:$sh), 2>;
def : InstAlias<"tst $src1, $src2$sh",
               (ANDSXrs XZR, GPR64:$src1, GPR64:$src2, logical_shift64:$sh), 2>;


def : Pat<(not GPR32:$Wm), (ORNWrr WZR, GPR32:$Wm)>;
def : Pat<(not GPR64:$Xm), (ORNXrr XZR, GPR64:$Xm)>;


//===----------------------------------------------------------------------===//
// One operand data processing instructions.
//===----------------------------------------------------------------------===//

defm CLS    : OneOperandData<0b101, "cls">;
defm CLZ    : OneOperandData<0b100, "clz", ctlz>;
defm RBIT   : OneOperandData<0b000, "rbit", bitreverse>;

def  REV16Wr : OneWRegData<0b001, "rev16",
                                  UnOpFrag<(rotr (bswap node:$LHS), (i64 16))>>;
def  REV16Xr : OneXRegData<0b001, "rev16", null_frag>;

def : Pat<(cttz GPR32:$Rn),
          (CLZWr (RBITWr GPR32:$Rn))>;
def : Pat<(cttz GPR64:$Rn),
          (CLZXr (RBITXr GPR64:$Rn))>;
def : Pat<(ctlz (or (shl (xor (sra GPR32:$Rn, (i64 31)), GPR32:$Rn), (i64 1)),
                (i32 1))),
          (CLSWr GPR32:$Rn)>;
def : Pat<(ctlz (or (shl (xor (sra GPR64:$Rn, (i64 63)), GPR64:$Rn), (i64 1)),
                (i64 1))),
          (CLSXr GPR64:$Rn)>;
def : Pat<(int_aarch64_cls GPR32:$Rn), (CLSWr GPR32:$Rn)>;
def : Pat<(int_aarch64_cls64 GPR64:$Rm), (EXTRACT_SUBREG (CLSXr GPR64:$Rm), sub_32)>;

// Unlike the other one operand instructions, the instructions with the "rev"
// mnemonic do *not* just different in the size bit, but actually use different
// opcode bits for the different sizes.
def REVWr   : OneWRegData<0b010, "rev", bswap>;
def REVXr   : OneXRegData<0b011, "rev", bswap>;
def REV32Xr : OneXRegData<0b010, "rev32",
                                 UnOpFrag<(rotr (bswap node:$LHS), (i64 32))>>;

def : InstAlias<"rev64 $Rd, $Rn", (REVXr GPR64:$Rd, GPR64:$Rn), 0>;

// The bswap commutes with the rotr so we want a pattern for both possible
// orders.
def : Pat<(bswap (rotr GPR32:$Rn, (i64 16))), (REV16Wr GPR32:$Rn)>;
def : Pat<(bswap (rotr GPR64:$Rn, (i64 32))), (REV32Xr GPR64:$Rn)>;

//===----------------------------------------------------------------------===//
// Bitfield immediate extraction instruction.
//===----------------------------------------------------------------------===//
let hasSideEffects = 0 in
defm EXTR : ExtractImm<"extr">;
def : InstAlias<"ror $dst, $src, $shift",
            (EXTRWrri GPR32:$dst, GPR32:$src, GPR32:$src, imm0_31:$shift)>;
def : InstAlias<"ror $dst, $src, $shift",
            (EXTRXrri GPR64:$dst, GPR64:$src, GPR64:$src, imm0_63:$shift)>;

def : Pat<(rotr GPR32:$Rn, (i64 imm0_31:$imm)),
          (EXTRWrri GPR32:$Rn, GPR32:$Rn, imm0_31:$imm)>;
def : Pat<(rotr GPR64:$Rn, (i64 imm0_63:$imm)),
          (EXTRXrri GPR64:$Rn, GPR64:$Rn, imm0_63:$imm)>;

//===----------------------------------------------------------------------===//
// Other bitfield immediate instructions.
//===----------------------------------------------------------------------===//
let hasSideEffects = 0 in {
defm BFM  : BitfieldImmWith2RegArgs<0b01, "bfm">;
defm SBFM : BitfieldImm<0b00, "sbfm">;
defm UBFM : BitfieldImm<0b10, "ubfm">;
}

def i32shift_a : Operand<i64>, SDNodeXForm<imm, [{
  uint64_t enc = (32 - N->getZExtValue()) & 0x1f;
  return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i64);
}]>;

def i32shift_b : Operand<i64>, SDNodeXForm<imm, [{
  uint64_t enc = 31 - N->getZExtValue();
  return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i64);
}]>;

// min(7, 31 - shift_amt)
def i32shift_sext_i8 : Operand<i64>, SDNodeXForm<imm, [{
  uint64_t enc = 31 - N->getZExtValue();
  enc = enc > 7 ? 7 : enc;
  return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i64);
}]>;

// min(15, 31 - shift_amt)
def i32shift_sext_i16 : Operand<i64>, SDNodeXForm<imm, [{
  uint64_t enc = 31 - N->getZExtValue();
  enc = enc > 15 ? 15 : enc;
  return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i64);
}]>;

def i64shift_a : Operand<i64>, SDNodeXForm<imm, [{
  uint64_t enc = (64 - N->getZExtValue()) & 0x3f;
  return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i64);
}]>;

def i64shift_b : Operand<i64>, SDNodeXForm<imm, [{
  uint64_t enc = 63 - N->getZExtValue();
  return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i64);
}]>;

// min(7, 63 - shift_amt)
def i64shift_sext_i8 : Operand<i64>, SDNodeXForm<imm, [{
  uint64_t enc = 63 - N->getZExtValue();
  enc = enc > 7 ? 7 : enc;
  return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i64);
}]>;

// min(15, 63 - shift_amt)
def i64shift_sext_i16 : Operand<i64>, SDNodeXForm<imm, [{
  uint64_t enc = 63 - N->getZExtValue();
  enc = enc > 15 ? 15 : enc;
  return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i64);
}]>;

// min(31, 63 - shift_amt)
def i64shift_sext_i32 : Operand<i64>, SDNodeXForm<imm, [{
  uint64_t enc = 63 - N->getZExtValue();
  enc = enc > 31 ? 31 : enc;
  return CurDAG->getTargetConstant(enc, SDLoc(N), MVT::i64);
}]>;

def : Pat<(shl GPR32:$Rn, (i64 imm0_31:$imm)),
          (UBFMWri GPR32:$Rn, (i64 (i32shift_a imm0_31:$imm)),
                              (i64 (i32shift_b imm0_31:$imm)))>;
def : Pat<(shl GPR64:$Rn, (i64 imm0_63:$imm)),
          (UBFMXri GPR64:$Rn, (i64 (i64shift_a imm0_63:$imm)),
                              (i64 (i64shift_b imm0_63:$imm)))>;

let AddedComplexity = 10 in {
def : Pat<(sra GPR32:$Rn, (i64 imm0_31:$imm)),
          (SBFMWri GPR32:$Rn, imm0_31:$imm, 31)>;
def : Pat<(sra GPR64:$Rn, (i64 imm0_63:$imm)),
          (SBFMXri GPR64:$Rn, imm0_63:$imm, 63)>;
}

def : InstAlias<"asr $dst, $src, $shift",
                (SBFMWri GPR32:$dst, GPR32:$src, imm0_31:$shift, 31)>;
def : InstAlias<"asr $dst, $src, $shift",
                (SBFMXri GPR64:$dst, GPR64:$src, imm0_63:$shift, 63)>;
def : InstAlias<"sxtb $dst, $src", (SBFMWri GPR32:$dst, GPR32:$src, 0, 7)>;
def : InstAlias<"sxtb $dst, $src", (SBFMXri GPR64:$dst, GPR64:$src, 0, 7)>;
def : InstAlias<"sxth $dst, $src", (SBFMWri GPR32:$dst, GPR32:$src, 0, 15)>;
def : InstAlias<"sxth $dst, $src", (SBFMXri GPR64:$dst, GPR64:$src, 0, 15)>;
def : InstAlias<"sxtw $dst, $src", (SBFMXri GPR64:$dst, GPR64:$src, 0, 31)>;

def : Pat<(srl GPR32:$Rn, (i64 imm0_31:$imm)),
          (UBFMWri GPR32:$Rn, imm0_31:$imm, 31)>;
def : Pat<(srl GPR64:$Rn, (i64 imm0_63:$imm)),
          (UBFMXri GPR64:$Rn, imm0_63:$imm, 63)>;

def : InstAlias<"lsr $dst, $src, $shift",
                (UBFMWri GPR32:$dst, GPR32:$src, imm0_31:$shift, 31)>;
def : InstAlias<"lsr $dst, $src, $shift",
                (UBFMXri GPR64:$dst, GPR64:$src, imm0_63:$shift, 63)>;
def : InstAlias<"uxtb $dst, $src", (UBFMWri GPR32:$dst, GPR32:$src, 0, 7)>;
def : InstAlias<"uxtb $dst, $src", (UBFMXri GPR64:$dst, GPR64:$src, 0, 7)>;
def : InstAlias<"uxth $dst, $src", (UBFMWri GPR32:$dst, GPR32:$src, 0, 15)>;
def : InstAlias<"uxth $dst, $src", (UBFMXri GPR64:$dst, GPR64:$src, 0, 15)>;
def : InstAlias<"uxtw $dst, $src", (UBFMXri GPR64:$dst, GPR64:$src, 0, 31)>;

//===----------------------------------------------------------------------===//
// Conditional comparison instructions.
//===----------------------------------------------------------------------===//
defm CCMN : CondComparison<0, "ccmn", AArch64ccmn>;
defm CCMP : CondComparison<1, "ccmp", AArch64ccmp>;

//===----------------------------------------------------------------------===//
// Conditional select instructions.
//===----------------------------------------------------------------------===//
defm CSEL  : CondSelect<0, 0b00, "csel">;

def inc : PatFrag<(ops node:$in), (add node:$in, 1)>;
defm CSINC : CondSelectOp<0, 0b01, "csinc", inc>;
defm CSINV : CondSelectOp<1, 0b00, "csinv", not>;
defm CSNEG : CondSelectOp<1, 0b01, "csneg", ineg>;

def : Pat<(AArch64csinv GPR32:$tval, GPR32:$fval, (i32 imm:$cc), NZCV),
          (CSINVWr GPR32:$tval, GPR32:$fval, (i32 imm:$cc))>;
def : Pat<(AArch64csinv GPR64:$tval, GPR64:$fval, (i32 imm:$cc), NZCV),
          (CSINVXr GPR64:$tval, GPR64:$fval, (i32 imm:$cc))>;
def : Pat<(AArch64csneg GPR32:$tval, GPR32:$fval, (i32 imm:$cc), NZCV),
          (CSNEGWr GPR32:$tval, GPR32:$fval, (i32 imm:$cc))>;
def : Pat<(AArch64csneg GPR64:$tval, GPR64:$fval, (i32 imm:$cc), NZCV),
          (CSNEGXr GPR64:$tval, GPR64:$fval, (i32 imm:$cc))>;
def : Pat<(AArch64csinc GPR32:$tval, GPR32:$fval, (i32 imm:$cc), NZCV),
          (CSINCWr GPR32:$tval, GPR32:$fval, (i32 imm:$cc))>;
def : Pat<(AArch64csinc GPR64:$tval, GPR64:$fval, (i32 imm:$cc), NZCV),
          (CSINCXr GPR64:$tval, GPR64:$fval, (i32 imm:$cc))>;

def : Pat<(AArch64csel (i32 0), (i32 1), (i32 imm:$cc), NZCV),
          (CSINCWr WZR, WZR, (i32 imm:$cc))>;
def : Pat<(AArch64csel (i64 0), (i64 1), (i32 imm:$cc), NZCV),
          (CSINCXr XZR, XZR, (i32 imm:$cc))>;
def : Pat<(AArch64csel GPR32:$tval, (i32 1), (i32 imm:$cc), NZCV),
          (CSINCWr GPR32:$tval, WZR, (i32 imm:$cc))>;
def : Pat<(AArch64csel GPR64:$tval, (i64 1), (i32 imm:$cc), NZCV),
          (CSINCXr GPR64:$tval, XZR, (i32 imm:$cc))>;
def : Pat<(AArch64csel (i32 1), GPR32:$fval, (i32 imm:$cc), NZCV),
          (CSINCWr GPR32:$fval, WZR, (i32 (inv_cond_XFORM imm:$cc)))>;
def : Pat<(AArch64csel (i64 1), GPR64:$fval, (i32 imm:$cc), NZCV),
          (CSINCXr GPR64:$fval, XZR, (i32 (inv_cond_XFORM imm:$cc)))>;
def : Pat<(AArch64csel (i32 0), (i32 -1), (i32 imm:$cc), NZCV),
          (CSINVWr WZR, WZR, (i32 imm:$cc))>;
def : Pat<(AArch64csel (i64 0), (i64 -1), (i32 imm:$cc), NZCV),
          (CSINVXr XZR, XZR, (i32 imm:$cc))>;
def : Pat<(AArch64csel GPR32:$tval, (i32 -1), (i32 imm:$cc), NZCV),
          (CSINVWr GPR32:$tval, WZR, (i32 imm:$cc))>;
def : Pat<(AArch64csel GPR64:$tval, (i64 -1), (i32 imm:$cc), NZCV),
          (CSINVXr GPR64:$tval, XZR, (i32 imm:$cc))>;
def : Pat<(AArch64csel (i32 -1), GPR32:$fval, (i32 imm:$cc), NZCV),
          (CSINVWr GPR32:$fval, WZR, (i32 (inv_cond_XFORM imm:$cc)))>;
def : Pat<(AArch64csel (i64 -1), GPR64:$fval, (i32 imm:$cc), NZCV),
          (CSINVXr GPR64:$fval, XZR, (i32 (inv_cond_XFORM imm:$cc)))>;

// The inverse of the condition code from the alias instruction is what is used
// in the aliased instruction. The parser all ready inverts the condition code
// for these aliases.
def : InstAlias<"cset $dst, $cc",
                (CSINCWr GPR32:$dst, WZR, WZR, inv_ccode:$cc)>;
def : InstAlias<"cset $dst, $cc",
                (CSINCXr GPR64:$dst, XZR, XZR, inv_ccode:$cc)>;

def : InstAlias<"csetm $dst, $cc",
                (CSINVWr GPR32:$dst, WZR, WZR, inv_ccode:$cc)>;
def : InstAlias<"csetm $dst, $cc",
                (CSINVXr GPR64:$dst, XZR, XZR, inv_ccode:$cc)>;

def : InstAlias<"cinc $dst, $src, $cc",
                (CSINCWr GPR32:$dst, GPR32:$src, GPR32:$src, inv_ccode:$cc)>;
def : InstAlias<"cinc $dst, $src, $cc",
                (CSINCXr GPR64:$dst, GPR64:$src, GPR64:$src, inv_ccode:$cc)>;

def : InstAlias<"cinv $dst, $src, $cc",
                (CSINVWr GPR32:$dst, GPR32:$src, GPR32:$src, inv_ccode:$cc)>;
def : InstAlias<"cinv $dst, $src, $cc",
                (CSINVXr GPR64:$dst, GPR64:$src, GPR64:$src, inv_ccode:$cc)>;

def : InstAlias<"cneg $dst, $src, $cc",
                (CSNEGWr GPR32:$dst, GPR32:$src, GPR32:$src, inv_ccode:$cc)>;
def : InstAlias<"cneg $dst, $src, $cc",
                (CSNEGXr GPR64:$dst, GPR64:$src, GPR64:$src, inv_ccode:$cc)>;

//===----------------------------------------------------------------------===//
// PC-relative instructions.
//===----------------------------------------------------------------------===//
let isReMaterializable = 1 in {
let hasSideEffects = 0, mayStore = 0, mayLoad = 0 in {
def ADR  : ADRI<0, "adr", adrlabel,
                [(set GPR64:$Xd, (AArch64adr tglobaladdr:$label))]>;
} // hasSideEffects = 0

def ADRP : ADRI<1, "adrp", adrplabel,
                [(set GPR64:$Xd, (AArch64adrp tglobaladdr:$label))]>;
} // isReMaterializable = 1

// page address of a constant pool entry, block address
def : Pat<(AArch64adr tconstpool:$cp), (ADR tconstpool:$cp)>;
def : Pat<(AArch64adr tblockaddress:$cp), (ADR tblockaddress:$cp)>;
def : Pat<(AArch64adr texternalsym:$sym), (ADR texternalsym:$sym)>;
def : Pat<(AArch64adr tjumptable:$sym), (ADR tjumptable:$sym)>;
def : Pat<(AArch64adrp tconstpool:$cp), (ADRP tconstpool:$cp)>;
def : Pat<(AArch64adrp tblockaddress:$cp), (ADRP tblockaddress:$cp)>;
def : Pat<(AArch64adrp texternalsym:$sym), (ADRP texternalsym:$sym)>;

//===----------------------------------------------------------------------===//
// Unconditional branch (register) instructions.
//===----------------------------------------------------------------------===//

let isReturn = 1, isTerminator = 1, isBarrier = 1 in {
def RET  : BranchReg<0b0010, "ret", []>;
def DRPS : SpecialReturn<0b0101, "drps">;
def ERET : SpecialReturn<0b0100, "eret">;
} // isReturn = 1, isTerminator = 1, isBarrier = 1

// Default to the LR register.
def : InstAlias<"ret", (RET LR)>;

let isCall = 1, Defs = [LR], Uses = [SP] in {
  def BLR : BranchReg<0b0001, "blr", []>;
  def BLRNoIP : Pseudo<(outs), (ins GPR64noip:$Rn), []>,
                Sched<[WriteBrReg]>,
                PseudoInstExpansion<(BLR GPR64:$Rn)>;
} // isCall

def : Pat<(AArch64call GPR64:$Rn),
          (BLR GPR64:$Rn)>,
      Requires<[NoSLSBLRMitigation]>;
def : Pat<(AArch64call GPR64noip:$Rn),
          (BLRNoIP GPR64noip:$Rn)>,
      Requires<[SLSBLRMitigation]>;

let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1 in {
def BR  : BranchReg<0b0000, "br", [(brind GPR64:$Rn)]>;
} // isBranch, isTerminator, isBarrier, isIndirectBranch

// Create a separate pseudo-instruction for codegen to use so that we don't
// flag lr as used in every function. It'll be restored before the RET by the
// epilogue if it's legitimately used.
def RET_ReallyLR : Pseudo<(outs), (ins), [(AArch64retflag)]>,
                   Sched<[WriteBrReg]> {
  let isTerminator = 1;
  let isBarrier = 1;
  let isReturn = 1;
}

// This is a directive-like pseudo-instruction. The purpose is to insert an
// R_AARCH64_TLSDESC_CALL relocation at the offset of the following instruction
// (which in the usual case is a BLR).
let hasSideEffects = 1 in
def TLSDESCCALL : Pseudo<(outs), (ins i64imm:$sym), []>, Sched<[]> {
  let AsmString = ".tlsdesccall $sym";
}

// Pseudo instruction to tell the streamer to emit a 'B' character into the
// augmentation string.
def EMITBKEY : Pseudo<(outs), (ins), []>, Sched<[]> {}

// FIXME: maybe the scratch register used shouldn't be fixed to X1?
// FIXME: can "hasSideEffects be dropped?
let isCall = 1, Defs = [LR, X0, X1], hasSideEffects = 1,
    isCodeGenOnly = 1 in
def TLSDESC_CALLSEQ
    : Pseudo<(outs), (ins i64imm:$sym),
             [(AArch64tlsdesc_callseq tglobaltlsaddr:$sym)]>,
      Sched<[WriteI, WriteLD, WriteI, WriteBrReg]>;
def : Pat<(AArch64tlsdesc_callseq texternalsym:$sym),
          (TLSDESC_CALLSEQ texternalsym:$sym)>;

//===----------------------------------------------------------------------===//
// Conditional branch (immediate) instruction.
//===----------------------------------------------------------------------===//
def Bcc : BranchCond;

//===----------------------------------------------------------------------===//
// Compare-and-branch instructions.
//===----------------------------------------------------------------------===//
defm CBZ  : CmpBranch<0, "cbz", AArch64cbz>;
defm CBNZ : CmpBranch<1, "cbnz", AArch64cbnz>;

//===----------------------------------------------------------------------===//
// Test-bit-and-branch instructions.
//===----------------------------------------------------------------------===//
defm TBZ  : TestBranch<0, "tbz", AArch64tbz>;
defm TBNZ : TestBranch<1, "tbnz", AArch64tbnz>;

//===----------------------------------------------------------------------===//
// Unconditional branch (immediate) instructions.
//===----------------------------------------------------------------------===//
let isBranch = 1, isTerminator = 1, isBarrier = 1 in {
def B  : BranchImm<0, "b", [(br bb:$addr)]>;
} // isBranch, isTerminator, isBarrier

let isCall = 1, Defs = [LR], Uses = [SP] in {
def BL : CallImm<1, "bl", [(AArch64call tglobaladdr:$addr)]>;
} // isCall
def : Pat<(AArch64call texternalsym:$func), (BL texternalsym:$func)>;

//===----------------------------------------------------------------------===//
// Exception generation instructions.
//===----------------------------------------------------------------------===//
let isTrap = 1 in {
def BRK   : ExceptionGeneration<0b001, 0b00, "brk">;
}
def DCPS1 : ExceptionGeneration<0b101, 0b01, "dcps1">;
def DCPS2 : ExceptionGeneration<0b101, 0b10, "dcps2">;
def DCPS3 : ExceptionGeneration<0b101, 0b11, "dcps3">;
def HLT   : ExceptionGeneration<0b010, 0b00, "hlt">;
def HVC   : ExceptionGeneration<0b000, 0b10, "hvc">;
def SMC   : ExceptionGeneration<0b000, 0b11, "smc">;
def SVC   : ExceptionGeneration<0b000, 0b01, "svc">;

// DCPSn defaults to an immediate operand of zero if unspecified.
def : InstAlias<"dcps1", (DCPS1 0)>;
def : InstAlias<"dcps2", (DCPS2 0)>;
def : InstAlias<"dcps3", (DCPS3 0)>;

def UDF : UDFType<0, "udf">;

//===----------------------------------------------------------------------===//
// Load instructions.
//===----------------------------------------------------------------------===//

// Pair (indexed, offset)
defm LDPW : LoadPairOffset<0b00, 0, GPR32z, simm7s4, "ldp">;
defm LDPX : LoadPairOffset<0b10, 0, GPR64z, simm7s8, "ldp">;
defm LDPS : LoadPairOffset<0b00, 1, FPR32Op, simm7s4, "ldp">;
defm LDPD : LoadPairOffset<0b01, 1, FPR64Op, simm7s8, "ldp">;
defm LDPQ : LoadPairOffset<0b10, 1, FPR128Op, simm7s16, "ldp">;

defm LDPSW : LoadPairOffset<0b01, 0, GPR64z, simm7s4, "ldpsw">;

// Pair (pre-indexed)
def LDPWpre : LoadPairPreIdx<0b00, 0, GPR32z, simm7s4, "ldp">;
def LDPXpre : LoadPairPreIdx<0b10, 0, GPR64z, simm7s8, "ldp">;
def LDPSpre : LoadPairPreIdx<0b00, 1, FPR32Op, simm7s4, "ldp">;
def LDPDpre : LoadPairPreIdx<0b01, 1, FPR64Op, simm7s8, "ldp">;
def LDPQpre : LoadPairPreIdx<0b10, 1, FPR128Op, simm7s16, "ldp">;

def LDPSWpre : LoadPairPreIdx<0b01, 0, GPR64z, simm7s4, "ldpsw">;

// Pair (post-indexed)
def LDPWpost : LoadPairPostIdx<0b00, 0, GPR32z, simm7s4, "ldp">;
def LDPXpost : LoadPairPostIdx<0b10, 0, GPR64z, simm7s8, "ldp">;
def LDPSpost : LoadPairPostIdx<0b00, 1, FPR32Op, simm7s4, "ldp">;
def LDPDpost : LoadPairPostIdx<0b01, 1, FPR64Op, simm7s8, "ldp">;
def LDPQpost : LoadPairPostIdx<0b10, 1, FPR128Op, simm7s16, "ldp">;

def LDPSWpost : LoadPairPostIdx<0b01, 0, GPR64z, simm7s4, "ldpsw">;


// Pair (no allocate)
defm LDNPW : LoadPairNoAlloc<0b00, 0, GPR32z, simm7s4, "ldnp">;
defm LDNPX : LoadPairNoAlloc<0b10, 0, GPR64z, simm7s8, "ldnp">;
defm LDNPS : LoadPairNoAlloc<0b00, 1, FPR32Op, simm7s4, "ldnp">;
defm LDNPD : LoadPairNoAlloc<0b01, 1, FPR64Op, simm7s8, "ldnp">;
defm LDNPQ : LoadPairNoAlloc<0b10, 1, FPR128Op, simm7s16, "ldnp">;

def : Pat<(AArch64ldp (am_indexed7s64 GPR64sp:$Rn, simm7s8:$offset)),
          (LDPXi GPR64sp:$Rn, simm7s8:$offset)>;

//---
// (register offset)
//---

// Integer
defm LDRBB : Load8RO<0b00,  0, 0b01, GPR32, "ldrb", i32, zextloadi8>;
defm LDRHH : Load16RO<0b01, 0, 0b01, GPR32, "ldrh", i32, zextloadi16>;
defm LDRW  : Load32RO<0b10, 0, 0b01, GPR32, "ldr", i32, load>;
defm LDRX  : Load64RO<0b11, 0, 0b01, GPR64, "ldr", i64, load>;

// Floating-point
defm LDRB : Load8RO<0b00,   1, 0b01, FPR8Op,   "ldr", untyped, load>;
defm LDRH : Load16RO<0b01,  1, 0b01, FPR16Op,  "ldr", f16, load>;
defm LDRS : Load32RO<0b10,  1, 0b01, FPR32Op,  "ldr", f32, load>;
defm LDRD : Load64RO<0b11,  1, 0b01, FPR64Op,  "ldr", f64, load>;
defm LDRQ : Load128RO<0b00, 1, 0b11, FPR128Op, "ldr", f128, load>;

// Load sign-extended half-word
defm LDRSHW : Load16RO<0b01, 0, 0b11, GPR32, "ldrsh", i32, sextloadi16>;
defm LDRSHX : Load16RO<0b01, 0, 0b10, GPR64, "ldrsh", i64, sextloadi16>;

// Load sign-extended byte
defm LDRSBW : Load8RO<0b00, 0, 0b11, GPR32, "ldrsb", i32, sextloadi8>;
defm LDRSBX : Load8RO<0b00, 0, 0b10, GPR64, "ldrsb", i64, sextloadi8>;

// Load sign-extended word
defm LDRSW  : Load32RO<0b10, 0, 0b10, GPR64, "ldrsw", i64, sextloadi32>;

// Pre-fetch.
defm PRFM : PrefetchRO<0b11, 0, 0b10, "prfm">;

// For regular load, we do not have any alignment requirement.
// Thus, it is safe to directly map the vector loads with interesting
// addressing modes.
// FIXME: We could do the same for bitconvert to floating point vectors.
multiclass ScalToVecROLoadPat<ROAddrMode ro, SDPatternOperator loadop,
                              ValueType ScalTy, ValueType VecTy,
                              Instruction LOADW, Instruction LOADX,
                              SubRegIndex sub> {
  def : Pat<(VecTy (scalar_to_vector (ScalTy
              (loadop (ro.Wpat GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$offset))))),
            (INSERT_SUBREG (VecTy (IMPLICIT_DEF)),
                           (LOADW GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$offset),
                           sub)>;

  def : Pat<(VecTy (scalar_to_vector (ScalTy
              (loadop (ro.Xpat GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$offset))))),
            (INSERT_SUBREG (VecTy (IMPLICIT_DEF)),
                           (LOADX GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$offset),
                           sub)>;
}

let AddedComplexity = 10 in {
defm : ScalToVecROLoadPat<ro8,  extloadi8,  i32, v8i8,  LDRBroW, LDRBroX, bsub>;
defm : ScalToVecROLoadPat<ro8,  extloadi8,  i32, v16i8, LDRBroW, LDRBroX, bsub>;

defm : ScalToVecROLoadPat<ro16, extloadi16, i32, v4i16, LDRHroW, LDRHroX, hsub>;
defm : ScalToVecROLoadPat<ro16, extloadi16, i32, v8i16, LDRHroW, LDRHroX, hsub>;

defm : ScalToVecROLoadPat<ro16, load,       i32, v4f16, LDRHroW, LDRHroX, hsub>;
defm : ScalToVecROLoadPat<ro16, load,       i32, v8f16, LDRHroW, LDRHroX, hsub>;

defm : ScalToVecROLoadPat<ro32, load,       i32, v2i32, LDRSroW, LDRSroX, ssub>;
defm : ScalToVecROLoadPat<ro32, load,       i32, v4i32, LDRSroW, LDRSroX, ssub>;

defm : ScalToVecROLoadPat<ro32, load,       f32, v2f32, LDRSroW, LDRSroX, ssub>;
defm : ScalToVecROLoadPat<ro32, load,       f32, v4f32, LDRSroW, LDRSroX, ssub>;

defm : ScalToVecROLoadPat<ro64, load,       i64, v2i64, LDRDroW, LDRDroX, dsub>;

defm : ScalToVecROLoadPat<ro64, load,       f64, v2f64, LDRDroW, LDRDroX, dsub>;


def : Pat <(v1i64 (scalar_to_vector (i64
                      (load (ro_Windexed64 GPR64sp:$Rn, GPR32:$Rm,
                                           ro_Wextend64:$extend))))),
           (LDRDroW GPR64sp:$Rn, GPR32:$Rm, ro_Wextend64:$extend)>;

def : Pat <(v1i64 (scalar_to_vector (i64
                      (load (ro_Xindexed64 GPR64sp:$Rn, GPR64:$Rm,
                                           ro_Xextend64:$extend))))),
           (LDRDroX GPR64sp:$Rn, GPR64:$Rm, ro_Xextend64:$extend)>;
}

// Match all load 64 bits width whose type is compatible with FPR64
multiclass VecROLoadPat<ROAddrMode ro, ValueType VecTy,
                        Instruction LOADW, Instruction LOADX> {

  def : Pat<(VecTy (load (ro.Wpat GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend))),
            (LOADW GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend)>;

  def : Pat<(VecTy (load (ro.Xpat GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend))),
            (LOADX GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend)>;
}

let AddedComplexity = 10 in {
let Predicates = [IsLE] in {
  // We must do vector loads with LD1 in big-endian.
  defm : VecROLoadPat<ro64, v2i32, LDRDroW, LDRDroX>;
  defm : VecROLoadPat<ro64, v2f32, LDRDroW, LDRDroX>;
  defm : VecROLoadPat<ro64, v8i8,  LDRDroW, LDRDroX>;
  defm : VecROLoadPat<ro64, v4i16, LDRDroW, LDRDroX>;
  defm : VecROLoadPat<ro64, v4f16, LDRDroW, LDRDroX>;
  defm : VecROLoadPat<ro64, v4bf16, LDRDroW, LDRDroX>;
}

defm : VecROLoadPat<ro64, v1i64,  LDRDroW, LDRDroX>;
defm : VecROLoadPat<ro64, v1f64,  LDRDroW, LDRDroX>;

// Match all load 128 bits width whose type is compatible with FPR128
let Predicates = [IsLE] in {
  // We must do vector loads with LD1 in big-endian.
  defm : VecROLoadPat<ro128, v2i64,  LDRQroW, LDRQroX>;
  defm : VecROLoadPat<ro128, v2f64,  LDRQroW, LDRQroX>;
  defm : VecROLoadPat<ro128, v4i32,  LDRQroW, LDRQroX>;
  defm : VecROLoadPat<ro128, v4f32,  LDRQroW, LDRQroX>;
  defm : VecROLoadPat<ro128, v8i16,  LDRQroW, LDRQroX>;
  defm : VecROLoadPat<ro128, v8f16,  LDRQroW, LDRQroX>;
  defm : VecROLoadPat<ro128, v8bf16,  LDRQroW, LDRQroX>;
  defm : VecROLoadPat<ro128, v16i8,  LDRQroW, LDRQroX>;
}
} // AddedComplexity = 10

// zextload -> i64
multiclass ExtLoadTo64ROPat<ROAddrMode ro, SDPatternOperator loadop,
                            Instruction INSTW, Instruction INSTX> {
  def : Pat<(i64 (loadop (ro.Wpat GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend))),
            (SUBREG_TO_REG (i64 0),
                           (INSTW GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend),
                           sub_32)>;

  def : Pat<(i64 (loadop (ro.Xpat GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend))),
            (SUBREG_TO_REG (i64 0),
                           (INSTX GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend),
                           sub_32)>;
}

let AddedComplexity = 10 in {
  defm : ExtLoadTo64ROPat<ro8,  zextloadi8,  LDRBBroW, LDRBBroX>;
  defm : ExtLoadTo64ROPat<ro16, zextloadi16, LDRHHroW, LDRHHroX>;
  defm : ExtLoadTo64ROPat<ro32, zextloadi32, LDRWroW,  LDRWroX>;

  // zextloadi1 -> zextloadi8
  defm : ExtLoadTo64ROPat<ro8,  zextloadi1,  LDRBBroW, LDRBBroX>;

  // extload -> zextload
  defm : ExtLoadTo64ROPat<ro8,  extloadi8,   LDRBBroW, LDRBBroX>;
  defm : ExtLoadTo64ROPat<ro16, extloadi16,  LDRHHroW, LDRHHroX>;
  defm : ExtLoadTo64ROPat<ro32, extloadi32,  LDRWroW,  LDRWroX>;

  // extloadi1 -> zextloadi8
  defm : ExtLoadTo64ROPat<ro8,  extloadi1,   LDRBBroW, LDRBBroX>;
}


// zextload -> i64
multiclass ExtLoadTo32ROPat<ROAddrMode ro, SDPatternOperator loadop,
                            Instruction INSTW, Instruction INSTX> {
  def : Pat<(i32 (loadop (ro.Wpat GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend))),
            (INSTW GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend)>;

  def : Pat<(i32 (loadop (ro.Xpat GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend))),
            (INSTX GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend)>;

}

let AddedComplexity = 10 in {
  // extload -> zextload
  defm : ExtLoadTo32ROPat<ro8,  extloadi8,   LDRBBroW, LDRBBroX>;
  defm : ExtLoadTo32ROPat<ro16, extloadi16,  LDRHHroW, LDRHHroX>;
  defm : ExtLoadTo32ROPat<ro32, extloadi32,  LDRWroW,  LDRWroX>;

  // zextloadi1 -> zextloadi8
  defm : ExtLoadTo32ROPat<ro8, zextloadi1, LDRBBroW, LDRBBroX>;
}

//---
// (unsigned immediate)
//---
defm LDRX : LoadUI<0b11, 0, 0b01, GPR64z, uimm12s8, "ldr",
                   [(set GPR64z:$Rt,
                         (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset)))]>;
defm LDRW : LoadUI<0b10, 0, 0b01, GPR32z, uimm12s4, "ldr",
                   [(set GPR32z:$Rt,
                         (load (am_indexed32 GPR64sp:$Rn, uimm12s4:$offset)))]>;
defm LDRB : LoadUI<0b00, 1, 0b01, FPR8Op, uimm12s1, "ldr",
                   [(set FPR8Op:$Rt,
                         (load (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset)))]>;
defm LDRH : LoadUI<0b01, 1, 0b01, FPR16Op, uimm12s2, "ldr",
                   [(set (f16 FPR16Op:$Rt),
                         (load (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset)))]>;
defm LDRS : LoadUI<0b10, 1, 0b01, FPR32Op, uimm12s4, "ldr",
                   [(set (f32 FPR32Op:$Rt),
                         (load (am_indexed32 GPR64sp:$Rn, uimm12s4:$offset)))]>;
defm LDRD : LoadUI<0b11, 1, 0b01, FPR64Op, uimm12s8, "ldr",
                   [(set (f64 FPR64Op:$Rt),
                         (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset)))]>;
defm LDRQ : LoadUI<0b00, 1, 0b11, FPR128Op, uimm12s16, "ldr",
                 [(set (f128 FPR128Op:$Rt),
                       (load (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset)))]>;

// bf16 load pattern
def : Pat <(bf16 (load (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset))),
           (LDRHui GPR64sp:$Rn, uimm12s2:$offset)>;

// For regular load, we do not have any alignment requirement.
// Thus, it is safe to directly map the vector loads with interesting
// addressing modes.
// FIXME: We could do the same for bitconvert to floating point vectors.
def : Pat <(v8i8 (scalar_to_vector (i32
               (extloadi8 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))))),
           (INSERT_SUBREG (v8i8 (IMPLICIT_DEF)),
                          (LDRBui GPR64sp:$Rn, uimm12s1:$offset), bsub)>;
def : Pat <(v16i8 (scalar_to_vector (i32
               (extloadi8 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))))),
           (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
                          (LDRBui GPR64sp:$Rn, uimm12s1:$offset), bsub)>;
def : Pat <(v4i16 (scalar_to_vector (i32
               (extloadi16 (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset))))),
           (INSERT_SUBREG (v4i16 (IMPLICIT_DEF)),
                          (LDRHui GPR64sp:$Rn, uimm12s2:$offset), hsub)>;
def : Pat <(v8i16 (scalar_to_vector (i32
               (extloadi16 (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset))))),
           (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)),
                          (LDRHui GPR64sp:$Rn, uimm12s2:$offset), hsub)>;
def : Pat <(v2i32 (scalar_to_vector (i32
               (load (am_indexed32 GPR64sp:$Rn, uimm12s4:$offset))))),
           (INSERT_SUBREG (v2i32 (IMPLICIT_DEF)),
                          (LDRSui GPR64sp:$Rn, uimm12s4:$offset), ssub)>;
def : Pat <(v4i32 (scalar_to_vector (i32
               (load (am_indexed32 GPR64sp:$Rn, uimm12s4:$offset))))),
           (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)),
                          (LDRSui GPR64sp:$Rn, uimm12s4:$offset), ssub)>;
def : Pat <(v1i64 (scalar_to_vector (i64
               (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))))),
           (LDRDui GPR64sp:$Rn, uimm12s8:$offset)>;
def : Pat <(v2i64 (scalar_to_vector (i64
               (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))))),
           (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)),
                          (LDRDui GPR64sp:$Rn, uimm12s8:$offset), dsub)>;

// Match all load 64 bits width whose type is compatible with FPR64
let Predicates = [IsLE] in {
  // We must use LD1 to perform vector loads in big-endian.
  def : Pat<(v2f32 (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))),
            (LDRDui GPR64sp:$Rn, uimm12s8:$offset)>;
  def : Pat<(v8i8 (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))),
            (LDRDui GPR64sp:$Rn, uimm12s8:$offset)>;
  def : Pat<(v4i16 (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))),
            (LDRDui GPR64sp:$Rn, uimm12s8:$offset)>;
  def : Pat<(v2i32 (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))),
            (LDRDui GPR64sp:$Rn, uimm12s8:$offset)>;
  def : Pat<(v4f16 (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))),
            (LDRDui GPR64sp:$Rn, uimm12s8:$offset)>;
  def : Pat<(v4bf16 (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))),
            (LDRDui GPR64sp:$Rn, uimm12s8:$offset)>;
}
def : Pat<(v1f64 (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))),
          (LDRDui GPR64sp:$Rn, uimm12s8:$offset)>;
def : Pat<(v1i64 (load (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))),
          (LDRDui GPR64sp:$Rn, uimm12s8:$offset)>;

// Match all load 128 bits width whose type is compatible with FPR128
let Predicates = [IsLE] in {
  // We must use LD1 to perform vector loads in big-endian.
  def : Pat<(v4f32 (load (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset))),
            (LDRQui GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(v2f64 (load (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset))),
            (LDRQui GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(v16i8 (load (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset))),
            (LDRQui GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(v8i16 (load (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset))),
            (LDRQui GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(v4i32 (load (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset))),
            (LDRQui GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(v2i64 (load (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset))),
            (LDRQui GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(v8f16 (load (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset))),
            (LDRQui GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(v8bf16 (load (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset))),
            (LDRQui GPR64sp:$Rn, uimm12s16:$offset)>;
}
def : Pat<(f128  (load (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset))),
          (LDRQui GPR64sp:$Rn, uimm12s16:$offset)>;

defm LDRHH : LoadUI<0b01, 0, 0b01, GPR32, uimm12s2, "ldrh",
                    [(set GPR32:$Rt,
                          (zextloadi16 (am_indexed16 GPR64sp:$Rn,
                                                     uimm12s2:$offset)))]>;
defm LDRBB : LoadUI<0b00, 0, 0b01, GPR32, uimm12s1, "ldrb",
                    [(set GPR32:$Rt,
                          (zextloadi8 (am_indexed8 GPR64sp:$Rn,
                                                   uimm12s1:$offset)))]>;
// zextload -> i64
def : Pat<(i64 (zextloadi8 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))),
    (SUBREG_TO_REG (i64 0), (LDRBBui GPR64sp:$Rn, uimm12s1:$offset), sub_32)>;
def : Pat<(i64 (zextloadi16 (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset))),
    (SUBREG_TO_REG (i64 0), (LDRHHui GPR64sp:$Rn, uimm12s2:$offset), sub_32)>;

// zextloadi1 -> zextloadi8
def : Pat<(i32 (zextloadi1 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))),
          (LDRBBui GPR64sp:$Rn, uimm12s1:$offset)>;
def : Pat<(i64 (zextloadi1 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))),
    (SUBREG_TO_REG (i64 0), (LDRBBui GPR64sp:$Rn, uimm12s1:$offset), sub_32)>;

// extload -> zextload
def : Pat<(i32 (extloadi16 (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset))),
          (LDRHHui GPR64sp:$Rn, uimm12s2:$offset)>;
def : Pat<(i32 (extloadi8 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))),
          (LDRBBui GPR64sp:$Rn, uimm12s1:$offset)>;
def : Pat<(i32 (extloadi1 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))),
          (LDRBBui GPR64sp:$Rn, uimm12s1:$offset)>;
def : Pat<(i64 (extloadi32 (am_indexed32 GPR64sp:$Rn, uimm12s4:$offset))),
    (SUBREG_TO_REG (i64 0), (LDRWui GPR64sp:$Rn, uimm12s4:$offset), sub_32)>;
def : Pat<(i64 (extloadi16 (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset))),
    (SUBREG_TO_REG (i64 0), (LDRHHui GPR64sp:$Rn, uimm12s2:$offset), sub_32)>;
def : Pat<(i64 (extloadi8 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))),
    (SUBREG_TO_REG (i64 0), (LDRBBui GPR64sp:$Rn, uimm12s1:$offset), sub_32)>;
def : Pat<(i64 (extloadi1 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))),
    (SUBREG_TO_REG (i64 0), (LDRBBui GPR64sp:$Rn, uimm12s1:$offset), sub_32)>;

// load sign-extended half-word
defm LDRSHW : LoadUI<0b01, 0, 0b11, GPR32, uimm12s2, "ldrsh",
                     [(set GPR32:$Rt,
                           (sextloadi16 (am_indexed16 GPR64sp:$Rn,
                                                      uimm12s2:$offset)))]>;
defm LDRSHX : LoadUI<0b01, 0, 0b10, GPR64, uimm12s2, "ldrsh",
                     [(set GPR64:$Rt,
                           (sextloadi16 (am_indexed16 GPR64sp:$Rn,
                                                      uimm12s2:$offset)))]>;

// load sign-extended byte
defm LDRSBW : LoadUI<0b00, 0, 0b11, GPR32, uimm12s1, "ldrsb",
                     [(set GPR32:$Rt,
                           (sextloadi8 (am_indexed8 GPR64sp:$Rn,
                                                    uimm12s1:$offset)))]>;
defm LDRSBX : LoadUI<0b00, 0, 0b10, GPR64, uimm12s1, "ldrsb",
                     [(set GPR64:$Rt,
                           (sextloadi8 (am_indexed8 GPR64sp:$Rn,
                                                    uimm12s1:$offset)))]>;

// load sign-extended word
defm LDRSW  : LoadUI<0b10, 0, 0b10, GPR64, uimm12s4, "ldrsw",
                     [(set GPR64:$Rt,
                           (sextloadi32 (am_indexed32 GPR64sp:$Rn,
                                                      uimm12s4:$offset)))]>;

// load zero-extended word
def : Pat<(i64 (zextloadi32 (am_indexed32 GPR64sp:$Rn, uimm12s4:$offset))),
      (SUBREG_TO_REG (i64 0), (LDRWui GPR64sp:$Rn, uimm12s4:$offset), sub_32)>;

// Pre-fetch.
def PRFMui : PrefetchUI<0b11, 0, 0b10, "prfm",
                        [(AArch64Prefetch imm:$Rt,
                                        (am_indexed64 GPR64sp:$Rn,
                                                      uimm12s8:$offset))]>;

def : InstAlias<"prfm $Rt, [$Rn]", (PRFMui prfop:$Rt, GPR64sp:$Rn, 0)>;

//---
// (literal)

def alignedglobal : PatLeaf<(iPTR iPTR:$label), [{
  if (auto *G = dyn_cast<GlobalAddressSDNode>(N)) {
    const DataLayout &DL = MF->getDataLayout();
    Align Align = G->getGlobal()->getPointerAlignment(DL);
    return Align >= 4 && G->getOffset() % 4 == 0;
  }
  if (auto *C = dyn_cast<ConstantPoolSDNode>(N))
    return C->getAlign() >= 4 && C->getOffset() % 4 == 0;
  return false;
}]>;

def LDRWl : LoadLiteral<0b00, 0, GPR32z, "ldr",
  [(set GPR32z:$Rt, (load (AArch64adr alignedglobal:$label)))]>;
def LDRXl : LoadLiteral<0b01, 0, GPR64z, "ldr",
  [(set GPR64z:$Rt, (load (AArch64adr alignedglobal:$label)))]>;
def LDRSl : LoadLiteral<0b00, 1, FPR32Op, "ldr",
  [(set (f32 FPR32Op:$Rt), (load (AArch64adr alignedglobal:$label)))]>;
def LDRDl : LoadLiteral<0b01, 1, FPR64Op, "ldr",
  [(set (f64 FPR64Op:$Rt), (load (AArch64adr alignedglobal:$label)))]>;
def LDRQl : LoadLiteral<0b10, 1, FPR128Op, "ldr",
  [(set (f128 FPR128Op:$Rt), (load (AArch64adr alignedglobal:$label)))]>;

// load sign-extended word
def LDRSWl : LoadLiteral<0b10, 0, GPR64z, "ldrsw",
  [(set GPR64z:$Rt, (sextloadi32 (AArch64adr alignedglobal:$label)))]>;

let AddedComplexity = 20 in {
def : Pat<(i64 (zextloadi32 (AArch64adr alignedglobal:$label))),
        (SUBREG_TO_REG (i64 0), (LDRWl $label), sub_32)>;
}

// prefetch
def PRFMl : PrefetchLiteral<0b11, 0, "prfm", []>;
//                   [(AArch64Prefetch imm:$Rt, tglobaladdr:$label)]>;

//---
// (unscaled immediate)
defm LDURX : LoadUnscaled<0b11, 0, 0b01, GPR64z, "ldur",
                    [(set GPR64z:$Rt,
                          (load (am_unscaled64 GPR64sp:$Rn, simm9:$offset)))]>;
defm LDURW : LoadUnscaled<0b10, 0, 0b01, GPR32z, "ldur",
                    [(set GPR32z:$Rt,
                          (load (am_unscaled32 GPR64sp:$Rn, simm9:$offset)))]>;
defm LDURB : LoadUnscaled<0b00, 1, 0b01, FPR8Op, "ldur",
                    [(set FPR8Op:$Rt,
                          (load (am_unscaled8 GPR64sp:$Rn, simm9:$offset)))]>;
defm LDURH : LoadUnscaled<0b01, 1, 0b01, FPR16Op, "ldur",
                    [(set (f16 FPR16Op:$Rt),
                          (load (am_unscaled16 GPR64sp:$Rn, simm9:$offset)))]>;
defm LDURS : LoadUnscaled<0b10, 1, 0b01, FPR32Op, "ldur",
                    [(set (f32 FPR32Op:$Rt),
                          (load (am_unscaled32 GPR64sp:$Rn, simm9:$offset)))]>;
defm LDURD : LoadUnscaled<0b11, 1, 0b01, FPR64Op, "ldur",
                    [(set (f64 FPR64Op:$Rt),
                          (load (am_unscaled64 GPR64sp:$Rn, simm9:$offset)))]>;
defm LDURQ : LoadUnscaled<0b00, 1, 0b11, FPR128Op, "ldur",
                    [(set (f128 FPR128Op:$Rt),
                          (load (am_unscaled128 GPR64sp:$Rn, simm9:$offset)))]>;

defm LDURHH
    : LoadUnscaled<0b01, 0, 0b01, GPR32, "ldurh",
             [(set GPR32:$Rt,
                    (zextloadi16 (am_unscaled16 GPR64sp:$Rn, simm9:$offset)))]>;
defm LDURBB
    : LoadUnscaled<0b00, 0, 0b01, GPR32, "ldurb",
             [(set GPR32:$Rt,
                    (zextloadi8 (am_unscaled16 GPR64sp:$Rn, simm9:$offset)))]>;

// Match all load 64 bits width whose type is compatible with FPR64
let Predicates = [IsLE] in {
  def : Pat<(v2f32 (load (am_unscaled64 GPR64sp:$Rn, simm9:$offset))),
            (LDURDi GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(v2i32 (load (am_unscaled64 GPR64sp:$Rn, simm9:$offset))),
            (LDURDi GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(v4i16 (load (am_unscaled64 GPR64sp:$Rn, simm9:$offset))),
            (LDURDi GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(v8i8 (load (am_unscaled64 GPR64sp:$Rn, simm9:$offset))),
            (LDURDi GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(v4f16 (load (am_unscaled64 GPR64sp:$Rn, simm9:$offset))),
            (LDURDi GPR64sp:$Rn, simm9:$offset)>;
}
def : Pat<(v1f64 (load (am_unscaled64 GPR64sp:$Rn, simm9:$offset))),
          (LDURDi GPR64sp:$Rn, simm9:$offset)>;
def : Pat<(v1i64 (load (am_unscaled64 GPR64sp:$Rn, simm9:$offset))),
          (LDURDi GPR64sp:$Rn, simm9:$offset)>;

// Match all load 128 bits width whose type is compatible with FPR128
let Predicates = [IsLE] in {
  def : Pat<(v2f64 (load (am_unscaled128 GPR64sp:$Rn, simm9:$offset))),
            (LDURQi GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(v2i64 (load (am_unscaled128 GPR64sp:$Rn, simm9:$offset))),
            (LDURQi GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(v4f32 (load (am_unscaled128 GPR64sp:$Rn, simm9:$offset))),
            (LDURQi GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(v4i32 (load (am_unscaled128 GPR64sp:$Rn, simm9:$offset))),
            (LDURQi GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(v8i16 (load (am_unscaled128 GPR64sp:$Rn, simm9:$offset))),
            (LDURQi GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(v16i8 (load (am_unscaled128 GPR64sp:$Rn, simm9:$offset))),
            (LDURQi GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(v8f16 (load (am_unscaled128 GPR64sp:$Rn, simm9:$offset))),
            (LDURQi GPR64sp:$Rn, simm9:$offset)>;
}

//  anyext -> zext
def : Pat<(i32 (extloadi16 (am_unscaled16 GPR64sp:$Rn, simm9:$offset))),
          (LDURHHi GPR64sp:$Rn, simm9:$offset)>;
def : Pat<(i32 (extloadi8 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))),
          (LDURBBi GPR64sp:$Rn, simm9:$offset)>;
def : Pat<(i32 (extloadi1 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))),
          (LDURBBi GPR64sp:$Rn, simm9:$offset)>;
def : Pat<(i64 (extloadi32 (am_unscaled32 GPR64sp:$Rn, simm9:$offset))),
    (SUBREG_TO_REG (i64 0), (LDURWi GPR64sp:$Rn, simm9:$offset), sub_32)>;
def : Pat<(i64 (extloadi16 (am_unscaled16 GPR64sp:$Rn, simm9:$offset))),
    (SUBREG_TO_REG (i64 0), (LDURHHi GPR64sp:$Rn, simm9:$offset), sub_32)>;
def : Pat<(i64 (extloadi8 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))),
    (SUBREG_TO_REG (i64 0), (LDURBBi GPR64sp:$Rn, simm9:$offset), sub_32)>;
def : Pat<(i64 (extloadi1 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))),
    (SUBREG_TO_REG (i64 0), (LDURBBi GPR64sp:$Rn, simm9:$offset), sub_32)>;
// unscaled zext
def : Pat<(i32 (zextloadi16 (am_unscaled16 GPR64sp:$Rn, simm9:$offset))),
          (LDURHHi GPR64sp:$Rn, simm9:$offset)>;
def : Pat<(i32 (zextloadi8 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))),
          (LDURBBi GPR64sp:$Rn, simm9:$offset)>;
def : Pat<(i32 (zextloadi1 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))),
          (LDURBBi GPR64sp:$Rn, simm9:$offset)>;
def : Pat<(i64 (zextloadi32 (am_unscaled32 GPR64sp:$Rn, simm9:$offset))),
    (SUBREG_TO_REG (i64 0), (LDURWi GPR64sp:$Rn, simm9:$offset), sub_32)>;
def : Pat<(i64 (zextloadi16 (am_unscaled16 GPR64sp:$Rn, simm9:$offset))),
    (SUBREG_TO_REG (i64 0), (LDURHHi GPR64sp:$Rn, simm9:$offset), sub_32)>;
def : Pat<(i64 (zextloadi8 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))),
    (SUBREG_TO_REG (i64 0), (LDURBBi GPR64sp:$Rn, simm9:$offset), sub_32)>;
def : Pat<(i64 (zextloadi1 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))),
    (SUBREG_TO_REG (i64 0), (LDURBBi GPR64sp:$Rn, simm9:$offset), sub_32)>;


//---
// LDR mnemonics fall back to LDUR for negative or unaligned offsets.

// Define new assembler match classes as we want to only match these when
// the don't otherwise match the scaled addressing mode for LDR/STR. Don't
// associate a DiagnosticType either, as we want the diagnostic for the
// canonical form (the scaled operand) to take precedence.
class SImm9OffsetOperand<int Width> : AsmOperandClass {
  let Name = "SImm9OffsetFB" # Width;
  let PredicateMethod = "isSImm9OffsetFB<" # Width # ">";
  let RenderMethod = "addImmOperands";
}

def SImm9OffsetFB8Operand : SImm9OffsetOperand<8>;
def SImm9OffsetFB16Operand : SImm9OffsetOperand<16>;
def SImm9OffsetFB32Operand : SImm9OffsetOperand<32>;
def SImm9OffsetFB64Operand : SImm9OffsetOperand<64>;
def SImm9OffsetFB128Operand : SImm9OffsetOperand<128>;

def simm9_offset_fb8 : Operand<i64> {
  let ParserMatchClass = SImm9OffsetFB8Operand;
}
def simm9_offset_fb16 : Operand<i64> {
  let ParserMatchClass = SImm9OffsetFB16Operand;
}
def simm9_offset_fb32 : Operand<i64> {
  let ParserMatchClass = SImm9OffsetFB32Operand;
}
def simm9_offset_fb64 : Operand<i64> {
  let ParserMatchClass = SImm9OffsetFB64Operand;
}
def simm9_offset_fb128 : Operand<i64> {
  let ParserMatchClass = SImm9OffsetFB128Operand;
}

def : InstAlias<"ldr $Rt, [$Rn, $offset]",
                (LDURXi GPR64:$Rt, GPR64sp:$Rn, simm9_offset_fb64:$offset), 0>;
def : InstAlias<"ldr $Rt, [$Rn, $offset]",
                (LDURWi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb32:$offset), 0>;
def : InstAlias<"ldr $Rt, [$Rn, $offset]",
                (LDURBi FPR8Op:$Rt, GPR64sp:$Rn, simm9_offset_fb8:$offset), 0>;
def : InstAlias<"ldr $Rt, [$Rn, $offset]",
                (LDURHi FPR16Op:$Rt, GPR64sp:$Rn, simm9_offset_fb16:$offset), 0>;
def : InstAlias<"ldr $Rt, [$Rn, $offset]",
                (LDURSi FPR32Op:$Rt, GPR64sp:$Rn, simm9_offset_fb32:$offset), 0>;
def : InstAlias<"ldr $Rt, [$Rn, $offset]",
                (LDURDi FPR64Op:$Rt, GPR64sp:$Rn, simm9_offset_fb64:$offset), 0>;
def : InstAlias<"ldr $Rt, [$Rn, $offset]",
               (LDURQi FPR128Op:$Rt, GPR64sp:$Rn, simm9_offset_fb128:$offset), 0>;

// zextload -> i64
def : Pat<(i64 (zextloadi8 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))),
  (SUBREG_TO_REG (i64 0), (LDURBBi GPR64sp:$Rn, simm9:$offset), sub_32)>;
def : Pat<(i64 (zextloadi16 (am_unscaled16 GPR64sp:$Rn, simm9:$offset))),
  (SUBREG_TO_REG (i64 0), (LDURHHi GPR64sp:$Rn, simm9:$offset), sub_32)>;

// load sign-extended half-word
defm LDURSHW
    : LoadUnscaled<0b01, 0, 0b11, GPR32, "ldursh",
               [(set GPR32:$Rt,
                    (sextloadi16 (am_unscaled16 GPR64sp:$Rn, simm9:$offset)))]>;
defm LDURSHX
    : LoadUnscaled<0b01, 0, 0b10, GPR64, "ldursh",
              [(set GPR64:$Rt,
                    (sextloadi16 (am_unscaled16 GPR64sp:$Rn, simm9:$offset)))]>;

// load sign-extended byte
defm LDURSBW
    : LoadUnscaled<0b00, 0, 0b11, GPR32, "ldursb",
                [(set GPR32:$Rt,
                      (sextloadi8 (am_unscaled8 GPR64sp:$Rn, simm9:$offset)))]>;
defm LDURSBX
    : LoadUnscaled<0b00, 0, 0b10, GPR64, "ldursb",
                [(set GPR64:$Rt,
                      (sextloadi8 (am_unscaled8 GPR64sp:$Rn, simm9:$offset)))]>;

// load sign-extended word
defm LDURSW
    : LoadUnscaled<0b10, 0, 0b10, GPR64, "ldursw",
              [(set GPR64:$Rt,
                    (sextloadi32 (am_unscaled32 GPR64sp:$Rn, simm9:$offset)))]>;

// zero and sign extending aliases from generic LDR* mnemonics to LDUR*.
def : InstAlias<"ldrb $Rt, [$Rn, $offset]",
                (LDURBBi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb8:$offset), 0>;
def : InstAlias<"ldrh $Rt, [$Rn, $offset]",
                (LDURHHi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb16:$offset), 0>;
def : InstAlias<"ldrsb $Rt, [$Rn, $offset]",
                (LDURSBWi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb8:$offset), 0>;
def : InstAlias<"ldrsb $Rt, [$Rn, $offset]",
                (LDURSBXi GPR64:$Rt, GPR64sp:$Rn, simm9_offset_fb8:$offset), 0>;
def : InstAlias<"ldrsh $Rt, [$Rn, $offset]",
                (LDURSHWi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb16:$offset), 0>;
def : InstAlias<"ldrsh $Rt, [$Rn, $offset]",
                (LDURSHXi GPR64:$Rt, GPR64sp:$Rn, simm9_offset_fb16:$offset), 0>;
def : InstAlias<"ldrsw $Rt, [$Rn, $offset]",
                (LDURSWi GPR64:$Rt, GPR64sp:$Rn, simm9_offset_fb32:$offset), 0>;

// Pre-fetch.
defm PRFUM : PrefetchUnscaled<0b11, 0, 0b10, "prfum",
                  [(AArch64Prefetch imm:$Rt,
                                  (am_unscaled64 GPR64sp:$Rn, simm9:$offset))]>;

//---
// (unscaled immediate, unprivileged)
defm LDTRX : LoadUnprivileged<0b11, 0, 0b01, GPR64, "ldtr">;
defm LDTRW : LoadUnprivileged<0b10, 0, 0b01, GPR32, "ldtr">;

defm LDTRH : LoadUnprivileged<0b01, 0, 0b01, GPR32, "ldtrh">;
defm LDTRB : LoadUnprivileged<0b00, 0, 0b01, GPR32, "ldtrb">;

// load sign-extended half-word
defm LDTRSHW : LoadUnprivileged<0b01, 0, 0b11, GPR32, "ldtrsh">;
defm LDTRSHX : LoadUnprivileged<0b01, 0, 0b10, GPR64, "ldtrsh">;

// load sign-extended byte
defm LDTRSBW : LoadUnprivileged<0b00, 0, 0b11, GPR32, "ldtrsb">;
defm LDTRSBX : LoadUnprivileged<0b00, 0, 0b10, GPR64, "ldtrsb">;

// load sign-extended word
defm LDTRSW  : LoadUnprivileged<0b10, 0, 0b10, GPR64, "ldtrsw">;

//---
// (immediate pre-indexed)
def LDRWpre : LoadPreIdx<0b10, 0, 0b01, GPR32z, "ldr">;
def LDRXpre : LoadPreIdx<0b11, 0, 0b01, GPR64z, "ldr">;
def LDRBpre : LoadPreIdx<0b00, 1, 0b01, FPR8Op,  "ldr">;
def LDRHpre : LoadPreIdx<0b01, 1, 0b01, FPR16Op, "ldr">;
def LDRSpre : LoadPreIdx<0b10, 1, 0b01, FPR32Op, "ldr">;
def LDRDpre : LoadPreIdx<0b11, 1, 0b01, FPR64Op, "ldr">;
def LDRQpre : LoadPreIdx<0b00, 1, 0b11, FPR128Op, "ldr">;

// load sign-extended half-word
def LDRSHWpre : LoadPreIdx<0b01, 0, 0b11, GPR32z, "ldrsh">;
def LDRSHXpre : LoadPreIdx<0b01, 0, 0b10, GPR64z, "ldrsh">;

// load sign-extended byte
def LDRSBWpre : LoadPreIdx<0b00, 0, 0b11, GPR32z, "ldrsb">;
def LDRSBXpre : LoadPreIdx<0b00, 0, 0b10, GPR64z, "ldrsb">;

// load zero-extended byte
def LDRBBpre : LoadPreIdx<0b00, 0, 0b01, GPR32z, "ldrb">;
def LDRHHpre : LoadPreIdx<0b01, 0, 0b01, GPR32z, "ldrh">;

// load sign-extended word
def LDRSWpre : LoadPreIdx<0b10, 0, 0b10, GPR64z, "ldrsw">;

//---
// (immediate post-indexed)
def LDRWpost : LoadPostIdx<0b10, 0, 0b01, GPR32z, "ldr">;
def LDRXpost : LoadPostIdx<0b11, 0, 0b01, GPR64z, "ldr">;
def LDRBpost : LoadPostIdx<0b00, 1, 0b01, FPR8Op,  "ldr">;
def LDRHpost : LoadPostIdx<0b01, 1, 0b01, FPR16Op, "ldr">;
def LDRSpost : LoadPostIdx<0b10, 1, 0b01, FPR32Op, "ldr">;
def LDRDpost : LoadPostIdx<0b11, 1, 0b01, FPR64Op, "ldr">;
def LDRQpost : LoadPostIdx<0b00, 1, 0b11, FPR128Op, "ldr">;

// load sign-extended half-word
def LDRSHWpost : LoadPostIdx<0b01, 0, 0b11, GPR32z, "ldrsh">;
def LDRSHXpost : LoadPostIdx<0b01, 0, 0b10, GPR64z, "ldrsh">;

// load sign-extended byte
def LDRSBWpost : LoadPostIdx<0b00, 0, 0b11, GPR32z, "ldrsb">;
def LDRSBXpost : LoadPostIdx<0b00, 0, 0b10, GPR64z, "ldrsb">;

// load zero-extended byte
def LDRBBpost : LoadPostIdx<0b00, 0, 0b01, GPR32z, "ldrb">;
def LDRHHpost : LoadPostIdx<0b01, 0, 0b01, GPR32z, "ldrh">;

// load sign-extended word
def LDRSWpost : LoadPostIdx<0b10, 0, 0b10, GPR64z, "ldrsw">;

//===----------------------------------------------------------------------===//
// Store instructions.
//===----------------------------------------------------------------------===//

// Pair (indexed, offset)
// FIXME: Use dedicated range-checked addressing mode operand here.
defm STPW : StorePairOffset<0b00, 0, GPR32z, simm7s4, "stp">;
defm STPX : StorePairOffset<0b10, 0, GPR64z, simm7s8, "stp">;
defm STPS : StorePairOffset<0b00, 1, FPR32Op, simm7s4, "stp">;
defm STPD : StorePairOffset<0b01, 1, FPR64Op, simm7s8, "stp">;
defm STPQ : StorePairOffset<0b10, 1, FPR128Op, simm7s16, "stp">;

// Pair (pre-indexed)
def STPWpre : StorePairPreIdx<0b00, 0, GPR32z, simm7s4, "stp">;
def STPXpre : StorePairPreIdx<0b10, 0, GPR64z, simm7s8, "stp">;
def STPSpre : StorePairPreIdx<0b00, 1, FPR32Op, simm7s4, "stp">;
def STPDpre : StorePairPreIdx<0b01, 1, FPR64Op, simm7s8, "stp">;
def STPQpre : StorePairPreIdx<0b10, 1, FPR128Op, simm7s16, "stp">;

// Pair (pre-indexed)
def STPWpost : StorePairPostIdx<0b00, 0, GPR32z, simm7s4, "stp">;
def STPXpost : StorePairPostIdx<0b10, 0, GPR64z, simm7s8, "stp">;
def STPSpost : StorePairPostIdx<0b00, 1, FPR32Op, simm7s4, "stp">;
def STPDpost : StorePairPostIdx<0b01, 1, FPR64Op, simm7s8, "stp">;
def STPQpost : StorePairPostIdx<0b10, 1, FPR128Op, simm7s16, "stp">;

// Pair (no allocate)
defm STNPW : StorePairNoAlloc<0b00, 0, GPR32z, simm7s4, "stnp">;
defm STNPX : StorePairNoAlloc<0b10, 0, GPR64z, simm7s8, "stnp">;
defm STNPS : StorePairNoAlloc<0b00, 1, FPR32Op, simm7s4, "stnp">;
defm STNPD : StorePairNoAlloc<0b01, 1, FPR64Op, simm7s8, "stnp">;
defm STNPQ : StorePairNoAlloc<0b10, 1, FPR128Op, simm7s16, "stnp">;

def : Pat<(AArch64stp GPR64z:$Rt, GPR64z:$Rt2, (am_indexed7s64 GPR64sp:$Rn, simm7s8:$offset)),
          (STPXi GPR64z:$Rt, GPR64z:$Rt2, GPR64sp:$Rn, simm7s8:$offset)>;

def : Pat<(AArch64stnp FPR128:$Rt, FPR128:$Rt2, (am_indexed7s128 GPR64sp:$Rn, simm7s16:$offset)),
          (STNPQi FPR128:$Rt, FPR128:$Rt2, GPR64sp:$Rn, simm7s16:$offset)>;


//---
// (Register offset)

// Integer
defm STRBB : Store8RO< 0b00, 0, 0b00, GPR32, "strb", i32, truncstorei8>;
defm STRHH : Store16RO<0b01, 0, 0b00, GPR32, "strh", i32, truncstorei16>;
defm STRW  : Store32RO<0b10, 0, 0b00, GPR32, "str",  i32, store>;
defm STRX  : Store64RO<0b11, 0, 0b00, GPR64, "str",  i64, store>;


// Floating-point
defm STRB : Store8RO< 0b00,  1, 0b00, FPR8Op,   "str", untyped, store>;
defm STRH : Store16RO<0b01,  1, 0b00, FPR16Op,  "str", f16,     store>;
defm STRS : Store32RO<0b10,  1, 0b00, FPR32Op,  "str", f32,     store>;
defm STRD : Store64RO<0b11,  1, 0b00, FPR64Op,  "str", f64,     store>;
defm STRQ : Store128RO<0b00, 1, 0b10, FPR128Op, "str", f128,    store>;

let Predicates = [UseSTRQro], AddedComplexity = 10 in {
  def : Pat<(store (f128 FPR128:$Rt),
                        (ro_Windexed128 GPR64sp:$Rn, GPR32:$Rm,
                                        ro_Wextend128:$extend)),
            (STRQroW FPR128:$Rt, GPR64sp:$Rn, GPR32:$Rm, ro_Wextend128:$extend)>;
  def : Pat<(store (f128 FPR128:$Rt),
                        (ro_Xindexed128 GPR64sp:$Rn, GPR64:$Rm,
                                        ro_Xextend128:$extend)),
            (STRQroX FPR128:$Rt, GPR64sp:$Rn, GPR64:$Rm, ro_Wextend128:$extend)>;
}

multiclass TruncStoreFrom64ROPat<ROAddrMode ro, SDPatternOperator storeop,
                                 Instruction STRW, Instruction STRX> {

  def : Pat<(storeop GPR64:$Rt,
                     (ro.Wpat GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend)),
            (STRW (EXTRACT_SUBREG GPR64:$Rt, sub_32),
                  GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend)>;

  def : Pat<(storeop GPR64:$Rt,
                     (ro.Xpat GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend)),
            (STRX (EXTRACT_SUBREG GPR64:$Rt, sub_32),
                  GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend)>;
}

let AddedComplexity = 10 in {
  // truncstore i64
  defm : TruncStoreFrom64ROPat<ro8,  truncstorei8,  STRBBroW, STRBBroX>;
  defm : TruncStoreFrom64ROPat<ro16, truncstorei16, STRHHroW, STRHHroX>;
  defm : TruncStoreFrom64ROPat<ro32, truncstorei32, STRWroW,  STRWroX>;
}

multiclass VecROStorePat<ROAddrMode ro, ValueType VecTy, RegisterClass FPR,
                         Instruction STRW, Instruction STRX> {
  def : Pat<(store (VecTy FPR:$Rt),
                   (ro.Wpat GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend)),
            (STRW FPR:$Rt, GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend)>;

  def : Pat<(store (VecTy FPR:$Rt),
                   (ro.Xpat GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend)),
            (STRX FPR:$Rt, GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend)>;
}

let AddedComplexity = 10 in {
// Match all store 64 bits width whose type is compatible with FPR64
let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  defm : VecROStorePat<ro64, v2i32, FPR64, STRDroW, STRDroX>;
  defm : VecROStorePat<ro64, v2f32, FPR64, STRDroW, STRDroX>;
  defm : VecROStorePat<ro64, v4i16, FPR64, STRDroW, STRDroX>;
  defm : VecROStorePat<ro64, v8i8, FPR64, STRDroW, STRDroX>;
  defm : VecROStorePat<ro64, v4f16, FPR64, STRDroW, STRDroX>;
  defm : VecROStorePat<ro64, v4bf16, FPR64, STRDroW, STRDroX>;
}

defm : VecROStorePat<ro64, v1i64, FPR64, STRDroW, STRDroX>;
defm : VecROStorePat<ro64, v1f64, FPR64, STRDroW, STRDroX>;

// Match all store 128 bits width whose type is compatible with FPR128
let Predicates = [IsLE, UseSTRQro] in {
  // We must use ST1 to store vectors in big-endian.
  defm : VecROStorePat<ro128, v2i64, FPR128, STRQroW, STRQroX>;
  defm : VecROStorePat<ro128, v2f64, FPR128, STRQroW, STRQroX>;
  defm : VecROStorePat<ro128, v4i32, FPR128, STRQroW, STRQroX>;
  defm : VecROStorePat<ro128, v4f32, FPR128, STRQroW, STRQroX>;
  defm : VecROStorePat<ro128, v8i16, FPR128, STRQroW, STRQroX>;
  defm : VecROStorePat<ro128, v16i8, FPR128, STRQroW, STRQroX>;
  defm : VecROStorePat<ro128, v8f16, FPR128, STRQroW, STRQroX>;
  defm : VecROStorePat<ro128, v8bf16, FPR128, STRQroW, STRQroX>;
}
} // AddedComplexity = 10

// Match stores from lane 0 to the appropriate subreg's store.
multiclass VecROStoreLane0Pat<ROAddrMode ro, SDPatternOperator storeop,
                              ValueType VecTy, ValueType STy,
                              SubRegIndex SubRegIdx,
                              Instruction STRW, Instruction STRX> {

  def : Pat<(storeop (STy (vector_extract (VecTy VecListOne128:$Vt), 0)),
                     (ro.Wpat GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend)),
            (STRW (EXTRACT_SUBREG VecListOne128:$Vt, SubRegIdx),
                  GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend)>;

  def : Pat<(storeop (STy (vector_extract (VecTy VecListOne128:$Vt), 0)),
                     (ro.Xpat GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend)),
            (STRX (EXTRACT_SUBREG VecListOne128:$Vt, SubRegIdx),
                  GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend)>;
}

let AddedComplexity = 19 in {
  defm : VecROStoreLane0Pat<ro16, truncstorei16, v8i16, i32, hsub, STRHroW, STRHroX>;
  defm : VecROStoreLane0Pat<ro16,         store, v8f16, f16, hsub, STRHroW, STRHroX>;
  defm : VecROStoreLane0Pat<ro32,         store, v4i32, i32, ssub, STRSroW, STRSroX>;
  defm : VecROStoreLane0Pat<ro32,         store, v4f32, f32, ssub, STRSroW, STRSroX>;
  defm : VecROStoreLane0Pat<ro64,         store, v2i64, i64, dsub, STRDroW, STRDroX>;
  defm : VecROStoreLane0Pat<ro64,         store, v2f64, f64, dsub, STRDroW, STRDroX>;
}

//---
// (unsigned immediate)
defm STRX : StoreUIz<0b11, 0, 0b00, GPR64z, uimm12s8, "str",
                   [(store GPR64z:$Rt,
                            (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))]>;
defm STRW : StoreUIz<0b10, 0, 0b00, GPR32z, uimm12s4, "str",
                    [(store GPR32z:$Rt,
                            (am_indexed32 GPR64sp:$Rn, uimm12s4:$offset))]>;
defm STRB : StoreUI<0b00, 1, 0b00, FPR8Op, uimm12s1, "str",
                    [(store FPR8Op:$Rt,
                            (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))]>;
defm STRH : StoreUI<0b01, 1, 0b00, FPR16Op, uimm12s2, "str",
                    [(store (f16 FPR16Op:$Rt),
                            (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset))]>;
defm STRS : StoreUI<0b10, 1, 0b00, FPR32Op, uimm12s4, "str",
                    [(store (f32 FPR32Op:$Rt),
                            (am_indexed32 GPR64sp:$Rn, uimm12s4:$offset))]>;
defm STRD : StoreUI<0b11, 1, 0b00, FPR64Op, uimm12s8, "str",
                    [(store (f64 FPR64Op:$Rt),
                            (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset))]>;
defm STRQ : StoreUI<0b00, 1, 0b10, FPR128Op, uimm12s16, "str", []>;

defm STRHH : StoreUIz<0b01, 0, 0b00, GPR32z, uimm12s2, "strh",
                     [(truncstorei16 GPR32z:$Rt,
                                     (am_indexed16 GPR64sp:$Rn,
                                                   uimm12s2:$offset))]>;
defm STRBB : StoreUIz<0b00, 0, 0b00, GPR32z, uimm12s1,  "strb",
                     [(truncstorei8 GPR32z:$Rt,
                                    (am_indexed8 GPR64sp:$Rn,
                                                 uimm12s1:$offset))]>;

// bf16 store pattern
def : Pat<(store (bf16 FPR16Op:$Rt),
                 (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset)),
          (STRHui FPR16:$Rt, GPR64sp:$Rn, uimm12s2:$offset)>;

let AddedComplexity = 10 in {

// Match all store 64 bits width whose type is compatible with FPR64
def : Pat<(store (v1i64 FPR64:$Rt),
                 (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset)),
          (STRDui FPR64:$Rt, GPR64sp:$Rn, uimm12s8:$offset)>;
def : Pat<(store (v1f64 FPR64:$Rt),
                 (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset)),
          (STRDui FPR64:$Rt, GPR64sp:$Rn, uimm12s8:$offset)>;

let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  def : Pat<(store (v2f32 FPR64:$Rt),
                   (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset)),
            (STRDui FPR64:$Rt, GPR64sp:$Rn, uimm12s8:$offset)>;
  def : Pat<(store (v8i8 FPR64:$Rt),
                   (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset)),
            (STRDui FPR64:$Rt, GPR64sp:$Rn, uimm12s8:$offset)>;
  def : Pat<(store (v4i16 FPR64:$Rt),
                   (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset)),
            (STRDui FPR64:$Rt, GPR64sp:$Rn, uimm12s8:$offset)>;
  def : Pat<(store (v2i32 FPR64:$Rt),
                   (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset)),
            (STRDui FPR64:$Rt, GPR64sp:$Rn, uimm12s8:$offset)>;
  def : Pat<(store (v4f16 FPR64:$Rt),
                   (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset)),
            (STRDui FPR64:$Rt, GPR64sp:$Rn, uimm12s8:$offset)>;
  def : Pat<(store (v4bf16 FPR64:$Rt),
                   (am_indexed64 GPR64sp:$Rn, uimm12s8:$offset)),
            (STRDui FPR64:$Rt, GPR64sp:$Rn, uimm12s8:$offset)>;
}

// Match all store 128 bits width whose type is compatible with FPR128
def : Pat<(store (f128  FPR128:$Rt),
                 (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset)),
          (STRQui FPR128:$Rt, GPR64sp:$Rn, uimm12s16:$offset)>;

let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  def : Pat<(store (v4f32 FPR128:$Rt),
                   (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset)),
            (STRQui FPR128:$Rt, GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(store (v2f64 FPR128:$Rt),
                   (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset)),
            (STRQui FPR128:$Rt, GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(store (v16i8 FPR128:$Rt),
                   (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset)),
            (STRQui FPR128:$Rt, GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(store (v8i16 FPR128:$Rt),
                   (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset)),
            (STRQui FPR128:$Rt, GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(store (v4i32 FPR128:$Rt),
                   (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset)),
            (STRQui FPR128:$Rt, GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(store (v2i64 FPR128:$Rt),
                   (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset)),
            (STRQui FPR128:$Rt, GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(store (v8f16 FPR128:$Rt),
                   (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset)),
            (STRQui FPR128:$Rt, GPR64sp:$Rn, uimm12s16:$offset)>;
  def : Pat<(store (v8bf16 FPR128:$Rt),
                   (am_indexed128 GPR64sp:$Rn, uimm12s16:$offset)),
            (STRQui FPR128:$Rt, GPR64sp:$Rn, uimm12s16:$offset)>;
}

// truncstore i64
def : Pat<(truncstorei32 GPR64:$Rt,
                         (am_indexed32 GPR64sp:$Rn, uimm12s4:$offset)),
  (STRWui (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$Rn, uimm12s4:$offset)>;
def : Pat<(truncstorei16 GPR64:$Rt,
                         (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset)),
  (STRHHui (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$Rn, uimm12s2:$offset)>;
def : Pat<(truncstorei8 GPR64:$Rt, (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset)),
  (STRBBui (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$Rn, uimm12s1:$offset)>;

} // AddedComplexity = 10

// Match stores from lane 0 to the appropriate subreg's store.
multiclass VecStoreLane0Pat<Operand UIAddrMode, SDPatternOperator storeop,
                            ValueType VTy, ValueType STy,
                            SubRegIndex SubRegIdx, Operand IndexType,
                            Instruction STR> {
  def : Pat<(storeop (STy (vector_extract (VTy VecListOne128:$Vt), 0)),
                     (UIAddrMode GPR64sp:$Rn, IndexType:$offset)),
            (STR (EXTRACT_SUBREG VecListOne128:$Vt, SubRegIdx),
                 GPR64sp:$Rn, IndexType:$offset)>;
}

let AddedComplexity = 19 in {
  defm : VecStoreLane0Pat<am_indexed16, truncstorei16, v8i16, i32, hsub, uimm12s2, STRHui>;
  defm : VecStoreLane0Pat<am_indexed16,         store, v8f16, f16, hsub, uimm12s2, STRHui>;
  defm : VecStoreLane0Pat<am_indexed32,         store, v4i32, i32, ssub, uimm12s4, STRSui>;
  defm : VecStoreLane0Pat<am_indexed32,         store, v4f32, f32, ssub, uimm12s4, STRSui>;
  defm : VecStoreLane0Pat<am_indexed64,         store, v2i64, i64, dsub, uimm12s8, STRDui>;
  defm : VecStoreLane0Pat<am_indexed64,         store, v2f64, f64, dsub, uimm12s8, STRDui>;
}

//---
// (unscaled immediate)
defm STURX : StoreUnscaled<0b11, 0, 0b00, GPR64z, "stur",
                         [(store GPR64z:$Rt,
                                 (am_unscaled64 GPR64sp:$Rn, simm9:$offset))]>;
defm STURW : StoreUnscaled<0b10, 0, 0b00, GPR32z, "stur",
                         [(store GPR32z:$Rt,
                                 (am_unscaled32 GPR64sp:$Rn, simm9:$offset))]>;
defm STURB : StoreUnscaled<0b00, 1, 0b00, FPR8Op, "stur",
                         [(store FPR8Op:$Rt,
                                 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))]>;
defm STURH : StoreUnscaled<0b01, 1, 0b00, FPR16Op, "stur",
                         [(store (f16 FPR16Op:$Rt),
                                 (am_unscaled16 GPR64sp:$Rn, simm9:$offset))]>;
defm STURS : StoreUnscaled<0b10, 1, 0b00, FPR32Op, "stur",
                         [(store (f32 FPR32Op:$Rt),
                                 (am_unscaled32 GPR64sp:$Rn, simm9:$offset))]>;
defm STURD : StoreUnscaled<0b11, 1, 0b00, FPR64Op, "stur",
                         [(store (f64 FPR64Op:$Rt),
                                 (am_unscaled64 GPR64sp:$Rn, simm9:$offset))]>;
defm STURQ : StoreUnscaled<0b00, 1, 0b10, FPR128Op, "stur",
                         [(store (f128 FPR128Op:$Rt),
                                 (am_unscaled128 GPR64sp:$Rn, simm9:$offset))]>;
defm STURHH : StoreUnscaled<0b01, 0, 0b00, GPR32z, "sturh",
                         [(truncstorei16 GPR32z:$Rt,
                                 (am_unscaled16 GPR64sp:$Rn, simm9:$offset))]>;
defm STURBB : StoreUnscaled<0b00, 0, 0b00, GPR32z, "sturb",
                         [(truncstorei8 GPR32z:$Rt,
                                  (am_unscaled8 GPR64sp:$Rn, simm9:$offset))]>;

// Armv8.4 Weaker Release Consistency enhancements
//         LDAPR & STLR with Immediate Offset instructions
let Predicates = [HasRCPC_IMMO] in {
defm STLURB     : BaseStoreUnscaleV84<"stlurb",  0b00, 0b00, GPR32>;
defm STLURH     : BaseStoreUnscaleV84<"stlurh",  0b01, 0b00, GPR32>;
defm STLURW     : BaseStoreUnscaleV84<"stlur",   0b10, 0b00, GPR32>;
defm STLURX     : BaseStoreUnscaleV84<"stlur",   0b11, 0b00, GPR64>;
defm LDAPURB    : BaseLoadUnscaleV84<"ldapurb",  0b00, 0b01, GPR32>;
defm LDAPURSBW  : BaseLoadUnscaleV84<"ldapursb", 0b00, 0b11, GPR32>;
defm LDAPURSBX  : BaseLoadUnscaleV84<"ldapursb", 0b00, 0b10, GPR64>;
defm LDAPURH    : BaseLoadUnscaleV84<"ldapurh",  0b01, 0b01, GPR32>;
defm LDAPURSHW  : BaseLoadUnscaleV84<"ldapursh", 0b01, 0b11, GPR32>;
defm LDAPURSHX  : BaseLoadUnscaleV84<"ldapursh", 0b01, 0b10, GPR64>;
defm LDAPUR     : BaseLoadUnscaleV84<"ldapur",   0b10, 0b01, GPR32>;
defm LDAPURSW   : BaseLoadUnscaleV84<"ldapursw", 0b10, 0b10, GPR64>;
defm LDAPURX    : BaseLoadUnscaleV84<"ldapur",   0b11, 0b01, GPR64>;
}

// Match all store 64 bits width whose type is compatible with FPR64
def : Pat<(store (v1f64 FPR64:$Rt), (am_unscaled64 GPR64sp:$Rn, simm9:$offset)),
          (STURDi FPR64:$Rt, GPR64sp:$Rn, simm9:$offset)>;
def : Pat<(store (v1i64 FPR64:$Rt), (am_unscaled64 GPR64sp:$Rn, simm9:$offset)),
          (STURDi FPR64:$Rt, GPR64sp:$Rn, simm9:$offset)>;

let AddedComplexity = 10 in {

let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  def : Pat<(store (v2f32 FPR64:$Rt),
                   (am_unscaled64 GPR64sp:$Rn, simm9:$offset)),
            (STURDi FPR64:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v8i8 FPR64:$Rt),
                   (am_unscaled64 GPR64sp:$Rn, simm9:$offset)),
            (STURDi FPR64:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v4i16 FPR64:$Rt),
                   (am_unscaled64 GPR64sp:$Rn, simm9:$offset)),
            (STURDi FPR64:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v2i32 FPR64:$Rt),
                   (am_unscaled64 GPR64sp:$Rn, simm9:$offset)),
            (STURDi FPR64:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v4f16 FPR64:$Rt),
                   (am_unscaled64 GPR64sp:$Rn, simm9:$offset)),
            (STURDi FPR64:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v4bf16 FPR64:$Rt),
                   (am_unscaled64 GPR64sp:$Rn, simm9:$offset)),
            (STURDi FPR64:$Rt, GPR64sp:$Rn, simm9:$offset)>;
}

// Match all store 128 bits width whose type is compatible with FPR128
def : Pat<(store (f128 FPR128:$Rt), (am_unscaled128 GPR64sp:$Rn, simm9:$offset)),
          (STURQi FPR128:$Rt, GPR64sp:$Rn, simm9:$offset)>;

let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  def : Pat<(store (v4f32 FPR128:$Rt),
                   (am_unscaled128 GPR64sp:$Rn, simm9:$offset)),
            (STURQi FPR128:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v2f64 FPR128:$Rt),
                   (am_unscaled128 GPR64sp:$Rn, simm9:$offset)),
            (STURQi FPR128:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v16i8 FPR128:$Rt),
                   (am_unscaled128 GPR64sp:$Rn, simm9:$offset)),
            (STURQi FPR128:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v8i16 FPR128:$Rt),
                   (am_unscaled128 GPR64sp:$Rn, simm9:$offset)),
            (STURQi FPR128:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v4i32 FPR128:$Rt),
                   (am_unscaled128 GPR64sp:$Rn, simm9:$offset)),
            (STURQi FPR128:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v2i64 FPR128:$Rt),
                   (am_unscaled128 GPR64sp:$Rn, simm9:$offset)),
            (STURQi FPR128:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v2f64 FPR128:$Rt),
                   (am_unscaled128 GPR64sp:$Rn, simm9:$offset)),
            (STURQi FPR128:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v8f16 FPR128:$Rt),
                   (am_unscaled128 GPR64sp:$Rn, simm9:$offset)),
            (STURQi FPR128:$Rt, GPR64sp:$Rn, simm9:$offset)>;
  def : Pat<(store (v8bf16 FPR128:$Rt),
                   (am_unscaled128 GPR64sp:$Rn, simm9:$offset)),
            (STURQi FPR128:$Rt, GPR64sp:$Rn, simm9:$offset)>;
}

} // AddedComplexity = 10

// unscaled i64 truncating stores
def : Pat<(truncstorei32 GPR64:$Rt, (am_unscaled32 GPR64sp:$Rn, simm9:$offset)),
  (STURWi (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$Rn, simm9:$offset)>;
def : Pat<(truncstorei16 GPR64:$Rt, (am_unscaled16 GPR64sp:$Rn, simm9:$offset)),
  (STURHHi (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$Rn, simm9:$offset)>;
def : Pat<(truncstorei8 GPR64:$Rt, (am_unscaled8 GPR64sp:$Rn, simm9:$offset)),
  (STURBBi (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$Rn, simm9:$offset)>;

// Match stores from lane 0 to the appropriate subreg's store.
multiclass VecStoreULane0Pat<SDPatternOperator StoreOp,
                             ValueType VTy, ValueType STy,
                             SubRegIndex SubRegIdx, Instruction STR> {
  defm : VecStoreLane0Pat<am_unscaled128, StoreOp, VTy, STy, SubRegIdx, simm9, STR>;
}

let AddedComplexity = 19 in {
  defm : VecStoreULane0Pat<truncstorei16, v8i16, i32, hsub, STURHi>;
  defm : VecStoreULane0Pat<store,         v8f16, f16, hsub, STURHi>;
  defm : VecStoreULane0Pat<store,         v4i32, i32, ssub, STURSi>;
  defm : VecStoreULane0Pat<store,         v4f32, f32, ssub, STURSi>;
  defm : VecStoreULane0Pat<store,         v2i64, i64, dsub, STURDi>;
  defm : VecStoreULane0Pat<store,         v2f64, f64, dsub, STURDi>;
}

//---
// STR mnemonics fall back to STUR for negative or unaligned offsets.
def : InstAlias<"str $Rt, [$Rn, $offset]",
                (STURXi GPR64:$Rt, GPR64sp:$Rn, simm9_offset_fb64:$offset), 0>;
def : InstAlias<"str $Rt, [$Rn, $offset]",
                (STURWi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb32:$offset), 0>;
def : InstAlias<"str $Rt, [$Rn, $offset]",
                (STURBi FPR8Op:$Rt, GPR64sp:$Rn, simm9_offset_fb8:$offset), 0>;
def : InstAlias<"str $Rt, [$Rn, $offset]",
                (STURHi FPR16Op:$Rt, GPR64sp:$Rn, simm9_offset_fb16:$offset), 0>;
def : InstAlias<"str $Rt, [$Rn, $offset]",
                (STURSi FPR32Op:$Rt, GPR64sp:$Rn, simm9_offset_fb32:$offset), 0>;
def : InstAlias<"str $Rt, [$Rn, $offset]",
                (STURDi FPR64Op:$Rt, GPR64sp:$Rn, simm9_offset_fb64:$offset), 0>;
def : InstAlias<"str $Rt, [$Rn, $offset]",
                (STURQi FPR128Op:$Rt, GPR64sp:$Rn, simm9_offset_fb128:$offset), 0>;

def : InstAlias<"strb $Rt, [$Rn, $offset]",
                (STURBBi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb8:$offset), 0>;
def : InstAlias<"strh $Rt, [$Rn, $offset]",
                (STURHHi GPR32:$Rt, GPR64sp:$Rn, simm9_offset_fb16:$offset), 0>;

//---
// (unscaled immediate, unprivileged)
defm STTRW : StoreUnprivileged<0b10, 0, 0b00, GPR32, "sttr">;
defm STTRX : StoreUnprivileged<0b11, 0, 0b00, GPR64, "sttr">;

defm STTRH : StoreUnprivileged<0b01, 0, 0b00, GPR32, "sttrh">;
defm STTRB : StoreUnprivileged<0b00, 0, 0b00, GPR32, "sttrb">;

//---
// (immediate pre-indexed)
def STRWpre : StorePreIdx<0b10, 0, 0b00, GPR32z, "str",  pre_store, i32>;
def STRXpre : StorePreIdx<0b11, 0, 0b00, GPR64z, "str",  pre_store, i64>;
def STRBpre : StorePreIdx<0b00, 1, 0b00, FPR8Op,  "str",  pre_store, untyped>;
def STRHpre : StorePreIdx<0b01, 1, 0b00, FPR16Op, "str",  pre_store, f16>;
def STRSpre : StorePreIdx<0b10, 1, 0b00, FPR32Op, "str",  pre_store, f32>;
def STRDpre : StorePreIdx<0b11, 1, 0b00, FPR64Op, "str",  pre_store, f64>;
def STRQpre : StorePreIdx<0b00, 1, 0b10, FPR128Op, "str", pre_store, f128>;

def STRBBpre : StorePreIdx<0b00, 0, 0b00, GPR32z, "strb", pre_truncsti8,  i32>;
def STRHHpre : StorePreIdx<0b01, 0, 0b00, GPR32z, "strh", pre_truncsti16, i32>;

// truncstore i64
def : Pat<(pre_truncsti32 GPR64:$Rt, GPR64sp:$addr, simm9:$off),
  (STRWpre (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$addr,
           simm9:$off)>;
def : Pat<(pre_truncsti16 GPR64:$Rt, GPR64sp:$addr, simm9:$off),
  (STRHHpre (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$addr,
            simm9:$off)>;
def : Pat<(pre_truncsti8 GPR64:$Rt, GPR64sp:$addr, simm9:$off),
  (STRBBpre (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$addr,
            simm9:$off)>;

def : Pat<(pre_store (v8i8 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpre FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v4i16 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpre FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v2i32 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpre FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v2f32 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpre FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v1i64 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpre FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v1f64 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpre FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v4f16 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpre FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;

def : Pat<(pre_store (v16i8 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpre FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v8i16 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpre FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v4i32 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpre FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v4f32 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpre FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v2i64 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpre FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v2f64 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpre FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(pre_store (v8f16 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpre FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;

//---
// (immediate post-indexed)
def STRWpost : StorePostIdx<0b10, 0, 0b00, GPR32z,  "str", post_store, i32>;
def STRXpost : StorePostIdx<0b11, 0, 0b00, GPR64z,  "str", post_store, i64>;
def STRBpost : StorePostIdx<0b00, 1, 0b00, FPR8Op,   "str", post_store, untyped>;
def STRHpost : StorePostIdx<0b01, 1, 0b00, FPR16Op,  "str", post_store, f16>;
def STRSpost : StorePostIdx<0b10, 1, 0b00, FPR32Op,  "str", post_store, f32>;
def STRDpost : StorePostIdx<0b11, 1, 0b00, FPR64Op,  "str", post_store, f64>;
def STRQpost : StorePostIdx<0b00, 1, 0b10, FPR128Op, "str", post_store, f128>;

def STRBBpost : StorePostIdx<0b00, 0, 0b00, GPR32z, "strb", post_truncsti8, i32>;
def STRHHpost : StorePostIdx<0b01, 0, 0b00, GPR32z, "strh", post_truncsti16, i32>;

// truncstore i64
def : Pat<(post_truncsti32 GPR64:$Rt, GPR64sp:$addr, simm9:$off),
  (STRWpost (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$addr,
            simm9:$off)>;
def : Pat<(post_truncsti16 GPR64:$Rt, GPR64sp:$addr, simm9:$off),
  (STRHHpost (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$addr,
             simm9:$off)>;
def : Pat<(post_truncsti8 GPR64:$Rt, GPR64sp:$addr, simm9:$off),
  (STRBBpost (EXTRACT_SUBREG GPR64:$Rt, sub_32), GPR64sp:$addr,
             simm9:$off)>;

def : Pat<(post_store (v8i8 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpost FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v4i16 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpost FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v2i32 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpost FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v2f32 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpost FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v1i64 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpost FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v1f64 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpost FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v4f16 FPR64:$Rt), GPR64sp:$addr, simm9:$off),
          (STRDpost FPR64:$Rt, GPR64sp:$addr, simm9:$off)>;

def : Pat<(post_store (v16i8 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpost FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v8i16 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpost FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v4i32 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpost FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v4f32 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpost FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v2i64 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpost FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v2f64 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpost FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;
def : Pat<(post_store (v8f16 FPR128:$Rt), GPR64sp:$addr, simm9:$off),
          (STRQpost FPR128:$Rt, GPR64sp:$addr, simm9:$off)>;

//===----------------------------------------------------------------------===//
// Load/store exclusive instructions.
//===----------------------------------------------------------------------===//

def LDARW  : LoadAcquire   <0b10, 1, 1, 0, 1, GPR32, "ldar">;
def LDARX  : LoadAcquire   <0b11, 1, 1, 0, 1, GPR64, "ldar">;
def LDARB  : LoadAcquire   <0b00, 1, 1, 0, 1, GPR32, "ldarb">;
def LDARH  : LoadAcquire   <0b01, 1, 1, 0, 1, GPR32, "ldarh">;

def LDAXRW : LoadExclusive <0b10, 0, 1, 0, 1, GPR32, "ldaxr">;
def LDAXRX : LoadExclusive <0b11, 0, 1, 0, 1, GPR64, "ldaxr">;
def LDAXRB : LoadExclusive <0b00, 0, 1, 0, 1, GPR32, "ldaxrb">;
def LDAXRH : LoadExclusive <0b01, 0, 1, 0, 1, GPR32, "ldaxrh">;

def LDXRW  : LoadExclusive <0b10, 0, 1, 0, 0, GPR32, "ldxr">;
def LDXRX  : LoadExclusive <0b11, 0, 1, 0, 0, GPR64, "ldxr">;
def LDXRB  : LoadExclusive <0b00, 0, 1, 0, 0, GPR32, "ldxrb">;
def LDXRH  : LoadExclusive <0b01, 0, 1, 0, 0, GPR32, "ldxrh">;

def STLRW  : StoreRelease  <0b10, 1, 0, 0, 1, GPR32, "stlr">;
def STLRX  : StoreRelease  <0b11, 1, 0, 0, 1, GPR64, "stlr">;
def STLRB  : StoreRelease  <0b00, 1, 0, 0, 1, GPR32, "stlrb">;
def STLRH  : StoreRelease  <0b01, 1, 0, 0, 1, GPR32, "stlrh">;

def STLXRW : StoreExclusive<0b10, 0, 0, 0, 1, GPR32, "stlxr">;
def STLXRX : StoreExclusive<0b11, 0, 0, 0, 1, GPR64, "stlxr">;
def STLXRB : StoreExclusive<0b00, 0, 0, 0, 1, GPR32, "stlxrb">;
def STLXRH : StoreExclusive<0b01, 0, 0, 0, 1, GPR32, "stlxrh">;

def STXRW  : StoreExclusive<0b10, 0, 0, 0, 0, GPR32, "stxr">;
def STXRX  : StoreExclusive<0b11, 0, 0, 0, 0, GPR64, "stxr">;
def STXRB  : StoreExclusive<0b00, 0, 0, 0, 0, GPR32, "stxrb">;
def STXRH  : StoreExclusive<0b01, 0, 0, 0, 0, GPR32, "stxrh">;

def LDAXPW : LoadExclusivePair<0b10, 0, 1, 1, 1, GPR32, "ldaxp">;
def LDAXPX : LoadExclusivePair<0b11, 0, 1, 1, 1, GPR64, "ldaxp">;

def LDXPW  : LoadExclusivePair<0b10, 0, 1, 1, 0, GPR32, "ldxp">;
def LDXPX  : LoadExclusivePair<0b11, 0, 1, 1, 0, GPR64, "ldxp">;

def STLXPW : StoreExclusivePair<0b10, 0, 0, 1, 1, GPR32, "stlxp">;
def STLXPX : StoreExclusivePair<0b11, 0, 0, 1, 1, GPR64, "stlxp">;

def STXPW  : StoreExclusivePair<0b10, 0, 0, 1, 0, GPR32, "stxp">;
def STXPX  : StoreExclusivePair<0b11, 0, 0, 1, 0, GPR64, "stxp">;

let Predicates = [HasLOR] in {
  // v8.1a "Limited Order Region" extension load-acquire instructions
  def LDLARW  : LoadAcquire   <0b10, 1, 1, 0, 0, GPR32, "ldlar">;
  def LDLARX  : LoadAcquire   <0b11, 1, 1, 0, 0, GPR64, "ldlar">;
  def LDLARB  : LoadAcquire   <0b00, 1, 1, 0, 0, GPR32, "ldlarb">;
  def LDLARH  : LoadAcquire   <0b01, 1, 1, 0, 0, GPR32, "ldlarh">;

  // v8.1a "Limited Order Region" extension store-release instructions
  def STLLRW  : StoreRelease   <0b10, 1, 0, 0, 0, GPR32, "stllr">;
  def STLLRX  : StoreRelease   <0b11, 1, 0, 0, 0, GPR64, "stllr">;
  def STLLRB  : StoreRelease   <0b00, 1, 0, 0, 0, GPR32, "stllrb">;
  def STLLRH  : StoreRelease   <0b01, 1, 0, 0, 0, GPR32, "stllrh">;
}

//===----------------------------------------------------------------------===//
// Scaled floating point to integer conversion instructions.
//===----------------------------------------------------------------------===//

defm FCVTAS : FPToIntegerUnscaled<0b00, 0b100, "fcvtas", int_aarch64_neon_fcvtas>;
defm FCVTAU : FPToIntegerUnscaled<0b00, 0b101, "fcvtau", int_aarch64_neon_fcvtau>;
defm FCVTMS : FPToIntegerUnscaled<0b10, 0b000, "fcvtms", int_aarch64_neon_fcvtms>;
defm FCVTMU : FPToIntegerUnscaled<0b10, 0b001, "fcvtmu", int_aarch64_neon_fcvtmu>;
defm FCVTNS : FPToIntegerUnscaled<0b00, 0b000, "fcvtns", int_aarch64_neon_fcvtns>;
defm FCVTNU : FPToIntegerUnscaled<0b00, 0b001, "fcvtnu", int_aarch64_neon_fcvtnu>;
defm FCVTPS : FPToIntegerUnscaled<0b01, 0b000, "fcvtps", int_aarch64_neon_fcvtps>;
defm FCVTPU : FPToIntegerUnscaled<0b01, 0b001, "fcvtpu", int_aarch64_neon_fcvtpu>;
defm FCVTZS : FPToIntegerUnscaled<0b11, 0b000, "fcvtzs", any_fp_to_sint>;
defm FCVTZU : FPToIntegerUnscaled<0b11, 0b001, "fcvtzu", any_fp_to_uint>;
defm FCVTZS : FPToIntegerScaled<0b11, 0b000, "fcvtzs", any_fp_to_sint>;
defm FCVTZU : FPToIntegerScaled<0b11, 0b001, "fcvtzu", any_fp_to_uint>;

multiclass FPToIntegerIntPats<Intrinsic round, string INST> {
  def : Pat<(i32 (round f16:$Rn)), (!cast<Instruction>(INST # UWHr) $Rn)>;
  def : Pat<(i64 (round f16:$Rn)), (!cast<Instruction>(INST # UXHr) $Rn)>;
  def : Pat<(i32 (round f32:$Rn)), (!cast<Instruction>(INST # UWSr) $Rn)>;
  def : Pat<(i64 (round f32:$Rn)), (!cast<Instruction>(INST # UXSr) $Rn)>;
  def : Pat<(i32 (round f64:$Rn)), (!cast<Instruction>(INST # UWDr) $Rn)>;
  def : Pat<(i64 (round f64:$Rn)), (!cast<Instruction>(INST # UXDr) $Rn)>;

  def : Pat<(i32 (round (fmul f16:$Rn, fixedpoint_f16_i32:$scale))),
            (!cast<Instruction>(INST # SWHri) $Rn, $scale)>;
  def : Pat<(i64 (round (fmul f16:$Rn, fixedpoint_f16_i64:$scale))),
            (!cast<Instruction>(INST # SXHri) $Rn, $scale)>;
  def : Pat<(i32 (round (fmul f32:$Rn, fixedpoint_f32_i32:$scale))),
            (!cast<Instruction>(INST # SWSri) $Rn, $scale)>;
  def : Pat<(i64 (round (fmul f32:$Rn, fixedpoint_f32_i64:$scale))),
            (!cast<Instruction>(INST # SXSri) $Rn, $scale)>;
  def : Pat<(i32 (round (fmul f64:$Rn, fixedpoint_f64_i32:$scale))),
            (!cast<Instruction>(INST # SWDri) $Rn, $scale)>;
  def : Pat<(i64 (round (fmul f64:$Rn, fixedpoint_f64_i64:$scale))),
            (!cast<Instruction>(INST # SXDri) $Rn, $scale)>;
}

defm : FPToIntegerIntPats<int_aarch64_neon_fcvtzs, "FCVTZS">;
defm : FPToIntegerIntPats<int_aarch64_neon_fcvtzu, "FCVTZU">;

multiclass FPToIntegerPats<SDNode to_int, SDNode round, string INST> {
  def : Pat<(i32 (to_int (round f32:$Rn))),
            (!cast<Instruction>(INST # UWSr) f32:$Rn)>;
  def : Pat<(i64 (to_int (round f32:$Rn))),
            (!cast<Instruction>(INST # UXSr) f32:$Rn)>;
  def : Pat<(i32 (to_int (round f64:$Rn))),
            (!cast<Instruction>(INST # UWDr) f64:$Rn)>;
  def : Pat<(i64 (to_int (round f64:$Rn))),
            (!cast<Instruction>(INST # UXDr) f64:$Rn)>;
}

defm : FPToIntegerPats<fp_to_sint, fceil,  "FCVTPS">;
defm : FPToIntegerPats<fp_to_uint, fceil,  "FCVTPU">;
defm : FPToIntegerPats<fp_to_sint, ffloor, "FCVTMS">;
defm : FPToIntegerPats<fp_to_uint, ffloor, "FCVTMU">;
defm : FPToIntegerPats<fp_to_sint, ftrunc, "FCVTZS">;
defm : FPToIntegerPats<fp_to_uint, ftrunc, "FCVTZU">;
defm : FPToIntegerPats<fp_to_sint, fround, "FCVTAS">;
defm : FPToIntegerPats<fp_to_uint, fround, "FCVTAU">;

let Predicates = [HasFullFP16] in {
  def : Pat<(i32 (lround f16:$Rn)),
            (!cast<Instruction>(FCVTASUWHr) f16:$Rn)>;
  def : Pat<(i64 (lround f16:$Rn)),
            (!cast<Instruction>(FCVTASUXHr) f16:$Rn)>;
  def : Pat<(i64 (llround f16:$Rn)),
            (!cast<Instruction>(FCVTASUXHr) f16:$Rn)>;
}
def : Pat<(i32 (lround f32:$Rn)),
          (!cast<Instruction>(FCVTASUWSr) f32:$Rn)>;
def : Pat<(i32 (lround f64:$Rn)),
          (!cast<Instruction>(FCVTASUWDr) f64:$Rn)>;
def : Pat<(i64 (lround f32:$Rn)),
          (!cast<Instruction>(FCVTASUXSr) f32:$Rn)>;
def : Pat<(i64 (lround f64:$Rn)),
          (!cast<Instruction>(FCVTASUXDr) f64:$Rn)>;
def : Pat<(i64 (llround f32:$Rn)),
          (!cast<Instruction>(FCVTASUXSr) f32:$Rn)>;
def : Pat<(i64 (llround f64:$Rn)),
          (!cast<Instruction>(FCVTASUXDr) f64:$Rn)>;

//===----------------------------------------------------------------------===//
// Scaled integer to floating point conversion instructions.
//===----------------------------------------------------------------------===//

defm SCVTF : IntegerToFP<0, "scvtf", any_sint_to_fp>;
defm UCVTF : IntegerToFP<1, "ucvtf", any_uint_to_fp>;

//===----------------------------------------------------------------------===//
// Unscaled integer to floating point conversion instruction.
//===----------------------------------------------------------------------===//

defm FMOV : UnscaledConversion<"fmov">;

// Add pseudo ops for FMOV 0 so we can mark them as isReMaterializable
let isReMaterializable = 1, isCodeGenOnly = 1, isAsCheapAsAMove = 1 in {
def FMOVH0 : Pseudo<(outs FPR16:$Rd), (ins), [(set f16:$Rd, (fpimm0))]>,
    Sched<[WriteF]>, Requires<[HasFullFP16]>;
def FMOVS0 : Pseudo<(outs FPR32:$Rd), (ins), [(set f32:$Rd, (fpimm0))]>,
    Sched<[WriteF]>;
def FMOVD0 : Pseudo<(outs FPR64:$Rd), (ins), [(set f64:$Rd, (fpimm0))]>,
    Sched<[WriteF]>;
}
// Similarly add aliases
def : InstAlias<"fmov $Rd, #0.0", (FMOVWHr FPR16:$Rd, WZR), 0>,
    Requires<[HasFullFP16]>;
def : InstAlias<"fmov $Rd, #0.0", (FMOVWSr FPR32:$Rd, WZR), 0>;
def : InstAlias<"fmov $Rd, #0.0", (FMOVXDr FPR64:$Rd, XZR), 0>;

//===----------------------------------------------------------------------===//
// Floating point conversion instruction.
//===----------------------------------------------------------------------===//

defm FCVT : FPConversion<"fcvt">;

//===----------------------------------------------------------------------===//
// Floating point single operand instructions.
//===----------------------------------------------------------------------===//

defm FABS   : SingleOperandFPData<0b0001, "fabs", fabs>;
defm FMOV   : SingleOperandFPData<0b0000, "fmov">;
defm FNEG   : SingleOperandFPData<0b0010, "fneg", fneg>;
defm FRINTA : SingleOperandFPData<0b1100, "frinta", fround>;
defm FRINTI : SingleOperandFPData<0b1111, "frinti", fnearbyint>;
defm FRINTM : SingleOperandFPData<0b1010, "frintm", ffloor>;
defm FRINTN : SingleOperandFPData<0b1000, "frintn", int_aarch64_neon_frintn>;
defm FRINTP : SingleOperandFPData<0b1001, "frintp", fceil>;

def : Pat<(v1f64 (int_aarch64_neon_frintn (v1f64 FPR64:$Rn))),
          (FRINTNDr FPR64:$Rn)>;

defm FRINTX : SingleOperandFPData<0b1110, "frintx", frint>;
defm FRINTZ : SingleOperandFPData<0b1011, "frintz", ftrunc>;

let SchedRW = [WriteFDiv] in {
defm FSQRT  : SingleOperandFPData<0b0011, "fsqrt", fsqrt>;
}

let Predicates = [HasFRInt3264] in {
  defm FRINT32Z : FRIntNNT<0b00, "frint32z">;
  defm FRINT64Z : FRIntNNT<0b10, "frint64z">;
  defm FRINT32X : FRIntNNT<0b01, "frint32x">;
  defm FRINT64X : FRIntNNT<0b11, "frint64x">;
} // HasFRInt3264

let Predicates = [HasFullFP16] in {
  def : Pat<(i32 (lrint f16:$Rn)),
            (FCVTZSUWHr (!cast<Instruction>(FRINTXHr) f16:$Rn))>;
  def : Pat<(i64 (lrint f16:$Rn)),
            (FCVTZSUXHr (!cast<Instruction>(FRINTXHr) f16:$Rn))>;
  def : Pat<(i64 (llrint f16:$Rn)),
            (FCVTZSUXHr (!cast<Instruction>(FRINTXHr) f16:$Rn))>;
}
def : Pat<(i32 (lrint f32:$Rn)),
          (FCVTZSUWSr (!cast<Instruction>(FRINTXSr) f32:$Rn))>;
def : Pat<(i32 (lrint f64:$Rn)),
          (FCVTZSUWDr (!cast<Instruction>(FRINTXDr) f64:$Rn))>;
def : Pat<(i64 (lrint f32:$Rn)),
          (FCVTZSUXSr (!cast<Instruction>(FRINTXSr) f32:$Rn))>;
def : Pat<(i64 (lrint f64:$Rn)),
          (FCVTZSUXDr (!cast<Instruction>(FRINTXDr) f64:$Rn))>;
def : Pat<(i64 (llrint f32:$Rn)),
          (FCVTZSUXSr (!cast<Instruction>(FRINTXSr) f32:$Rn))>;
def : Pat<(i64 (llrint f64:$Rn)),
          (FCVTZSUXDr (!cast<Instruction>(FRINTXDr) f64:$Rn))>;

//===----------------------------------------------------------------------===//
// Floating point two operand instructions.
//===----------------------------------------------------------------------===//

defm FADD   : TwoOperandFPData<0b0010, "fadd", fadd>;
let SchedRW = [WriteFDiv] in {
defm FDIV   : TwoOperandFPData<0b0001, "fdiv", fdiv>;
}
defm FMAXNM : TwoOperandFPData<0b0110, "fmaxnm", fmaxnum>;
defm FMAX   : TwoOperandFPData<0b0100, "fmax", fmaximum>;
defm FMINNM : TwoOperandFPData<0b0111, "fminnm", fminnum>;
defm FMIN   : TwoOperandFPData<0b0101, "fmin", fminimum>;
let SchedRW = [WriteFMul] in {
defm FMUL   : TwoOperandFPData<0b0000, "fmul", fmul>;
defm FNMUL  : TwoOperandFPDataNeg<0b1000, "fnmul", fmul>;
}
defm FSUB   : TwoOperandFPData<0b0011, "fsub", fsub>;

def : Pat<(v1f64 (fmaximum (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
          (FMAXDrr FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(v1f64 (fminimum (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
          (FMINDrr FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(v1f64 (fmaxnum (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
          (FMAXNMDrr FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(v1f64 (fminnum (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
          (FMINNMDrr FPR64:$Rn, FPR64:$Rm)>;

//===----------------------------------------------------------------------===//
// Floating point three operand instructions.
//===----------------------------------------------------------------------===//

defm FMADD  : ThreeOperandFPData<0, 0, "fmadd", fma>;
defm FMSUB  : ThreeOperandFPData<0, 1, "fmsub",
     TriOpFrag<(fma node:$LHS, (fneg node:$MHS), node:$RHS)> >;
defm FNMADD : ThreeOperandFPData<1, 0, "fnmadd",
     TriOpFrag<(fneg (fma node:$LHS, node:$MHS, node:$RHS))> >;
defm FNMSUB : ThreeOperandFPData<1, 1, "fnmsub",
     TriOpFrag<(fma node:$LHS, node:$MHS, (fneg node:$RHS))> >;

// The following def pats catch the case where the LHS of an FMA is negated.
// The TriOpFrag above catches the case where the middle operand is negated.

// N.b. FMSUB etc have the accumulator at the *end* of (outs), unlike
// the NEON variant.

// Here we handle first -(a + b*c) for FNMADD:

let Predicates = [HasNEON, HasFullFP16] in
def : Pat<(f16 (fma (fneg FPR16:$Rn), FPR16:$Rm, FPR16:$Ra)),
          (FMSUBHrrr FPR16:$Rn, FPR16:$Rm, FPR16:$Ra)>;

def : Pat<(f32 (fma (fneg FPR32:$Rn), FPR32:$Rm, FPR32:$Ra)),
          (FMSUBSrrr FPR32:$Rn, FPR32:$Rm, FPR32:$Ra)>;

def : Pat<(f64 (fma (fneg FPR64:$Rn), FPR64:$Rm, FPR64:$Ra)),
          (FMSUBDrrr FPR64:$Rn, FPR64:$Rm, FPR64:$Ra)>;

// Now it's time for "(-a) + (-b)*c"

let Predicates = [HasNEON, HasFullFP16] in
def : Pat<(f16 (fma (fneg FPR16:$Rn), FPR16:$Rm, (fneg FPR16:$Ra))),
          (FNMADDHrrr FPR16:$Rn, FPR16:$Rm, FPR16:$Ra)>;

def : Pat<(f32 (fma (fneg FPR32:$Rn), FPR32:$Rm, (fneg FPR32:$Ra))),
          (FNMADDSrrr FPR32:$Rn, FPR32:$Rm, FPR32:$Ra)>;

def : Pat<(f64 (fma (fneg FPR64:$Rn), FPR64:$Rm, (fneg FPR64:$Ra))),
          (FNMADDDrrr FPR64:$Rn, FPR64:$Rm, FPR64:$Ra)>;

// And here "(-a) + b*(-c)"

let Predicates = [HasNEON, HasFullFP16] in
def : Pat<(f16 (fma FPR16:$Rn, (fneg FPR16:$Rm), (fneg FPR16:$Ra))),
          (FNMADDHrrr FPR16:$Rn, FPR16:$Rm, FPR16:$Ra)>;

def : Pat<(f32 (fma FPR32:$Rn, (fneg FPR32:$Rm), (fneg FPR32:$Ra))),
          (FNMADDSrrr FPR32:$Rn, FPR32:$Rm, FPR32:$Ra)>;

def : Pat<(f64 (fma FPR64:$Rn, (fneg FPR64:$Rm), (fneg FPR64:$Ra))),
          (FNMADDDrrr FPR64:$Rn, FPR64:$Rm, FPR64:$Ra)>;

//===----------------------------------------------------------------------===//
// Floating point comparison instructions.
//===----------------------------------------------------------------------===//

defm FCMPE : FPComparison<1, "fcmpe", AArch64strict_fcmpe>;
defm FCMP  : FPComparison<0, "fcmp", AArch64any_fcmp>;

//===----------------------------------------------------------------------===//
// Floating point conditional comparison instructions.
//===----------------------------------------------------------------------===//

defm FCCMPE : FPCondComparison<1, "fccmpe">;
defm FCCMP  : FPCondComparison<0, "fccmp", AArch64fccmp>;

//===----------------------------------------------------------------------===//
// Floating point conditional select instruction.
//===----------------------------------------------------------------------===//

defm FCSEL : FPCondSelect<"fcsel">;

// CSEL instructions providing f128 types need to be handled by a
// pseudo-instruction since the eventual code will need to introduce basic
// blocks and control flow.
def F128CSEL : Pseudo<(outs FPR128:$Rd),
                      (ins FPR128:$Rn, FPR128:$Rm, ccode:$cond),
                      [(set (f128 FPR128:$Rd),
                            (AArch64csel FPR128:$Rn, FPR128:$Rm,
                                       (i32 imm:$cond), NZCV))]> {
  let Uses = [NZCV];
  let usesCustomInserter = 1;
  let hasNoSchedulingInfo = 1;
}

//===----------------------------------------------------------------------===//
// Instructions used for emitting unwind opcodes on ARM64 Windows.
//===----------------------------------------------------------------------===//
let isPseudo = 1 in {
  def SEH_StackAlloc : Pseudo<(outs), (ins i32imm:$size), []>, Sched<[]>;
  def SEH_SaveFPLR : Pseudo<(outs), (ins i32imm:$offs), []>, Sched<[]>;
  def SEH_SaveFPLR_X : Pseudo<(outs), (ins i32imm:$offs), []>, Sched<[]>;
  def SEH_SaveReg : Pseudo<(outs), (ins i32imm:$reg, i32imm:$offs), []>, Sched<[]>;
  def SEH_SaveReg_X : Pseudo<(outs), (ins i32imm:$reg, i32imm:$offs), []>, Sched<[]>;
  def SEH_SaveRegP : Pseudo<(outs), (ins i32imm:$reg0, i32imm:$reg1, i32imm:$offs), []>, Sched<[]>;
  def SEH_SaveRegP_X : Pseudo<(outs), (ins i32imm:$reg0, i32imm:$reg1, i32imm:$offs), []>, Sched<[]>;
  def SEH_SaveFReg : Pseudo<(outs), (ins i32imm:$reg, i32imm:$offs), []>, Sched<[]>;
  def SEH_SaveFReg_X :  Pseudo<(outs), (ins i32imm:$reg, i32imm:$offs), []>, Sched<[]>;
  def SEH_SaveFRegP : Pseudo<(outs), (ins i32imm:$reg0, i32imm:$reg1, i32imm:$offs), []>, Sched<[]>;
  def SEH_SaveFRegP_X : Pseudo<(outs), (ins i32imm:$reg0, i32imm:$reg1, i32imm:$offs), []>, Sched<[]>;
  def SEH_SetFP : Pseudo<(outs), (ins), []>, Sched<[]>;
  def SEH_AddFP : Pseudo<(outs), (ins i32imm:$offs), []>, Sched<[]>;
  def SEH_Nop : Pseudo<(outs), (ins), []>, Sched<[]>;
  def SEH_PrologEnd : Pseudo<(outs), (ins), []>, Sched<[]>;
  def SEH_EpilogStart : Pseudo<(outs), (ins), []>, Sched<[]>;
  def SEH_EpilogEnd : Pseudo<(outs), (ins), []>, Sched<[]>;
}

// Pseudo instructions for Windows EH
//===----------------------------------------------------------------------===//
let isTerminator = 1, hasSideEffects = 1, isBarrier = 1, hasCtrlDep = 1,
    isCodeGenOnly = 1, isReturn = 1, isEHScopeReturn = 1, isPseudo = 1 in {
   def CLEANUPRET : Pseudo<(outs), (ins), [(cleanupret)]>, Sched<[]>;
   let usesCustomInserter = 1 in
     def CATCHRET : Pseudo<(outs), (ins am_brcond:$dst, am_brcond:$src), [(catchret bb:$dst, bb:$src)]>,
                    Sched<[]>;
}

//===----------------------------------------------------------------------===//
// Floating point immediate move.
//===----------------------------------------------------------------------===//

let isReMaterializable = 1 in {
defm FMOV : FPMoveImmediate<"fmov">;
}

//===----------------------------------------------------------------------===//
// Advanced SIMD two vector instructions.
//===----------------------------------------------------------------------===//

defm UABDL   : SIMDLongThreeVectorBHSabdl<1, 0b0111, "uabdl",
                                          int_aarch64_neon_uabd>;
// Match UABDL in log2-shuffle patterns.
def : Pat<(abs (v8i16 (sub (zext (v8i8 V64:$opA)),
                           (zext (v8i8 V64:$opB))))),
          (UABDLv8i8_v8i16 V64:$opA, V64:$opB)>;
def : Pat<(xor (v8i16 (AArch64vashr v8i16:$src, (i32 15))),
               (v8i16 (add (sub (zext (v8i8 V64:$opA)),
                                (zext (v8i8 V64:$opB))),
                           (AArch64vashr v8i16:$src, (i32 15))))),
          (UABDLv8i8_v8i16 V64:$opA, V64:$opB)>;
def : Pat<(abs (v8i16 (sub (zext (extract_high_v16i8 V128:$opA)),
                           (zext (extract_high_v16i8 V128:$opB))))),
          (UABDLv16i8_v8i16 V128:$opA, V128:$opB)>;
def : Pat<(xor (v8i16 (AArch64vashr v8i16:$src, (i32 15))),
               (v8i16 (add (sub (zext (extract_high_v16i8 V128:$opA)),
                                (zext (extract_high_v16i8 V128:$opB))),
                           (AArch64vashr v8i16:$src, (i32 15))))),
          (UABDLv16i8_v8i16 V128:$opA, V128:$opB)>;
def : Pat<(abs (v4i32 (sub (zext (v4i16 V64:$opA)),
                           (zext (v4i16 V64:$opB))))),
          (UABDLv4i16_v4i32 V64:$opA, V64:$opB)>;
def : Pat<(abs (v4i32 (sub (zext (extract_high_v8i16 V128:$opA)),
                           (zext (extract_high_v8i16 V128:$opB))))),
          (UABDLv8i16_v4i32 V128:$opA, V128:$opB)>;
def : Pat<(abs (v2i64 (sub (zext (v2i32 V64:$opA)),
                           (zext (v2i32 V64:$opB))))),
          (UABDLv2i32_v2i64 V64:$opA, V64:$opB)>;
def : Pat<(abs (v2i64 (sub (zext (extract_high_v4i32 V128:$opA)),
                           (zext (extract_high_v4i32 V128:$opB))))),
          (UABDLv4i32_v2i64 V128:$opA, V128:$opB)>;

defm ABS    : SIMDTwoVectorBHSD<0, 0b01011, "abs", abs>;
defm CLS    : SIMDTwoVectorBHS<0, 0b00100, "cls", int_aarch64_neon_cls>;
defm CLZ    : SIMDTwoVectorBHS<1, 0b00100, "clz", ctlz>;
defm CMEQ   : SIMDCmpTwoVector<0, 0b01001, "cmeq", AArch64cmeqz>;
defm CMGE   : SIMDCmpTwoVector<1, 0b01000, "cmge", AArch64cmgez>;
defm CMGT   : SIMDCmpTwoVector<0, 0b01000, "cmgt", AArch64cmgtz>;
defm CMLE   : SIMDCmpTwoVector<1, 0b01001, "cmle", AArch64cmlez>;
defm CMLT   : SIMDCmpTwoVector<0, 0b01010, "cmlt", AArch64cmltz>;
defm CNT    : SIMDTwoVectorB<0, 0b00, 0b00101, "cnt", ctpop>;
defm FABS   : SIMDTwoVectorFP<0, 1, 0b01111, "fabs", fabs>;

defm FCMEQ  : SIMDFPCmpTwoVector<0, 1, 0b01101, "fcmeq", AArch64fcmeqz>;
defm FCMGE  : SIMDFPCmpTwoVector<1, 1, 0b01100, "fcmge", AArch64fcmgez>;
defm FCMGT  : SIMDFPCmpTwoVector<0, 1, 0b01100, "fcmgt", AArch64fcmgtz>;
defm FCMLE  : SIMDFPCmpTwoVector<1, 1, 0b01101, "fcmle", AArch64fcmlez>;
defm FCMLT  : SIMDFPCmpTwoVector<0, 1, 0b01110, "fcmlt", AArch64fcmltz>;
defm FCVTAS : SIMDTwoVectorFPToInt<0,0,0b11100, "fcvtas",int_aarch64_neon_fcvtas>;
defm FCVTAU : SIMDTwoVectorFPToInt<1,0,0b11100, "fcvtau",int_aarch64_neon_fcvtau>;
defm FCVTL  : SIMDFPWidenTwoVector<0, 0, 0b10111, "fcvtl">;
def : Pat<(v4f32 (int_aarch64_neon_vcvthf2fp (v4i16 V64:$Rn))),
          (FCVTLv4i16 V64:$Rn)>;
def : Pat<(v4f32 (int_aarch64_neon_vcvthf2fp (extract_subvector (v8i16 V128:$Rn),
                                                              (i64 4)))),
          (FCVTLv8i16 V128:$Rn)>;
def : Pat<(v2f64 (fpextend (v2f32 V64:$Rn))), (FCVTLv2i32 V64:$Rn)>;

def : Pat<(v4f32 (fpextend (v4f16 V64:$Rn))), (FCVTLv4i16 V64:$Rn)>;

defm FCVTMS : SIMDTwoVectorFPToInt<0,0,0b11011, "fcvtms",int_aarch64_neon_fcvtms>;
defm FCVTMU : SIMDTwoVectorFPToInt<1,0,0b11011, "fcvtmu",int_aarch64_neon_fcvtmu>;
defm FCVTNS : SIMDTwoVectorFPToInt<0,0,0b11010, "fcvtns",int_aarch64_neon_fcvtns>;
defm FCVTNU : SIMDTwoVectorFPToInt<1,0,0b11010, "fcvtnu",int_aarch64_neon_fcvtnu>;
defm FCVTN  : SIMDFPNarrowTwoVector<0, 0, 0b10110, "fcvtn">;
def : Pat<(v4i16 (int_aarch64_neon_vcvtfp2hf (v4f32 V128:$Rn))),
          (FCVTNv4i16 V128:$Rn)>;
def : Pat<(concat_vectors V64:$Rd,
                          (v4i16 (int_aarch64_neon_vcvtfp2hf (v4f32 V128:$Rn)))),
          (FCVTNv8i16 (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub), V128:$Rn)>;
def : Pat<(v2f32 (fpround (v2f64 V128:$Rn))), (FCVTNv2i32 V128:$Rn)>;
def : Pat<(v4f16 (fpround (v4f32 V128:$Rn))), (FCVTNv4i16 V128:$Rn)>;
def : Pat<(concat_vectors V64:$Rd, (v2f32 (fpround (v2f64 V128:$Rn)))),
          (FCVTNv4i32 (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub), V128:$Rn)>;
defm FCVTPS : SIMDTwoVectorFPToInt<0,1,0b11010, "fcvtps",int_aarch64_neon_fcvtps>;
defm FCVTPU : SIMDTwoVectorFPToInt<1,1,0b11010, "fcvtpu",int_aarch64_neon_fcvtpu>;
defm FCVTXN : SIMDFPInexactCvtTwoVector<1, 0, 0b10110, "fcvtxn",
                                        int_aarch64_neon_fcvtxn>;
defm FCVTZS : SIMDTwoVectorFPToInt<0, 1, 0b11011, "fcvtzs", fp_to_sint>;
defm FCVTZU : SIMDTwoVectorFPToInt<1, 1, 0b11011, "fcvtzu", fp_to_uint>;

def : Pat<(v4i16 (int_aarch64_neon_fcvtzs v4f16:$Rn)), (FCVTZSv4f16 $Rn)>;
def : Pat<(v8i16 (int_aarch64_neon_fcvtzs v8f16:$Rn)), (FCVTZSv8f16 $Rn)>;
def : Pat<(v2i32 (int_aarch64_neon_fcvtzs v2f32:$Rn)), (FCVTZSv2f32 $Rn)>;
def : Pat<(v4i32 (int_aarch64_neon_fcvtzs v4f32:$Rn)), (FCVTZSv4f32 $Rn)>;
def : Pat<(v2i64 (int_aarch64_neon_fcvtzs v2f64:$Rn)), (FCVTZSv2f64 $Rn)>;

def : Pat<(v4i16 (int_aarch64_neon_fcvtzu v4f16:$Rn)), (FCVTZUv4f16 $Rn)>;
def : Pat<(v8i16 (int_aarch64_neon_fcvtzu v8f16:$Rn)), (FCVTZUv8f16 $Rn)>;
def : Pat<(v2i32 (int_aarch64_neon_fcvtzu v2f32:$Rn)), (FCVTZUv2f32 $Rn)>;
def : Pat<(v4i32 (int_aarch64_neon_fcvtzu v4f32:$Rn)), (FCVTZUv4f32 $Rn)>;
def : Pat<(v2i64 (int_aarch64_neon_fcvtzu v2f64:$Rn)), (FCVTZUv2f64 $Rn)>;

defm FNEG   : SIMDTwoVectorFP<1, 1, 0b01111, "fneg", fneg>;
defm FRECPE : SIMDTwoVectorFP<0, 1, 0b11101, "frecpe", int_aarch64_neon_frecpe>;
defm FRINTA : SIMDTwoVectorFP<1, 0, 0b11000, "frinta", fround>;
defm FRINTI : SIMDTwoVectorFP<1, 1, 0b11001, "frinti", fnearbyint>;
defm FRINTM : SIMDTwoVectorFP<0, 0, 0b11001, "frintm", ffloor>;
defm FRINTN : SIMDTwoVectorFP<0, 0, 0b11000, "frintn", int_aarch64_neon_frintn>;
defm FRINTP : SIMDTwoVectorFP<0, 1, 0b11000, "frintp", fceil>;
defm FRINTX : SIMDTwoVectorFP<1, 0, 0b11001, "frintx", frint>;
defm FRINTZ : SIMDTwoVectorFP<0, 1, 0b11001, "frintz", ftrunc>;

let Predicates = [HasFRInt3264] in {
  defm FRINT32Z : FRIntNNTVector<0, 0, "frint32z">;
  defm FRINT64Z : FRIntNNTVector<0, 1, "frint64z">;
  defm FRINT32X : FRIntNNTVector<1, 0, "frint32x">;
  defm FRINT64X : FRIntNNTVector<1, 1, "frint64x">;
} // HasFRInt3264

defm FRSQRTE: SIMDTwoVectorFP<1, 1, 0b11101, "frsqrte", int_aarch64_neon_frsqrte>;
defm FSQRT  : SIMDTwoVectorFP<1, 1, 0b11111, "fsqrt", fsqrt>;
defm NEG    : SIMDTwoVectorBHSD<1, 0b01011, "neg",
                               UnOpFrag<(sub immAllZerosV, node:$LHS)> >;
defm NOT    : SIMDTwoVectorB<1, 0b00, 0b00101, "not", vnot>;
// Aliases for MVN -> NOT.
def : InstAlias<"mvn{ $Vd.8b, $Vn.8b|.8b $Vd, $Vn}",
                (NOTv8i8 V64:$Vd, V64:$Vn)>;
def : InstAlias<"mvn{ $Vd.16b, $Vn.16b|.16b $Vd, $Vn}",
                (NOTv16i8 V128:$Vd, V128:$Vn)>;

def : Pat<(AArch64neg (v8i8  V64:$Rn)),  (NEGv8i8  V64:$Rn)>;
def : Pat<(AArch64neg (v16i8 V128:$Rn)), (NEGv16i8 V128:$Rn)>;
def : Pat<(AArch64neg (v4i16 V64:$Rn)),  (NEGv4i16 V64:$Rn)>;
def : Pat<(AArch64neg (v8i16 V128:$Rn)), (NEGv8i16 V128:$Rn)>;
def : Pat<(AArch64neg (v2i32 V64:$Rn)),  (NEGv2i32 V64:$Rn)>;
def : Pat<(AArch64neg (v4i32 V128:$Rn)), (NEGv4i32 V128:$Rn)>;
def : Pat<(AArch64neg (v2i64 V128:$Rn)), (NEGv2i64 V128:$Rn)>;

def : Pat<(AArch64not (v8i8 V64:$Rn)),   (NOTv8i8  V64:$Rn)>;
def : Pat<(AArch64not (v16i8 V128:$Rn)), (NOTv16i8 V128:$Rn)>;
def : Pat<(AArch64not (v4i16 V64:$Rn)),  (NOTv8i8  V64:$Rn)>;
def : Pat<(AArch64not (v8i16 V128:$Rn)), (NOTv16i8 V128:$Rn)>;
def : Pat<(AArch64not (v2i32 V64:$Rn)),  (NOTv8i8  V64:$Rn)>;
def : Pat<(AArch64not (v1i64 V64:$Rn)),  (NOTv8i8  V64:$Rn)>;
def : Pat<(AArch64not (v4i32 V128:$Rn)), (NOTv16i8 V128:$Rn)>;
def : Pat<(AArch64not (v2i64 V128:$Rn)), (NOTv16i8 V128:$Rn)>;

def : Pat<(vnot (v4i16 V64:$Rn)),  (NOTv8i8  V64:$Rn)>;
def : Pat<(vnot (v8i16 V128:$Rn)), (NOTv16i8 V128:$Rn)>;
def : Pat<(vnot (v2i32 V64:$Rn)),  (NOTv8i8  V64:$Rn)>;
def : Pat<(vnot (v4i32 V128:$Rn)), (NOTv16i8 V128:$Rn)>;
def : Pat<(vnot (v2i64 V128:$Rn)), (NOTv16i8 V128:$Rn)>;

defm RBIT   : SIMDTwoVectorB<1, 0b01, 0b00101, "rbit", int_aarch64_neon_rbit>;
defm REV16  : SIMDTwoVectorB<0, 0b00, 0b00001, "rev16", AArch64rev16>;
defm REV32  : SIMDTwoVectorBH<1, 0b00000, "rev32", AArch64rev32>;
defm REV64  : SIMDTwoVectorBHS<0, 0b00000, "rev64", AArch64rev64>;
defm SADALP : SIMDLongTwoVectorTied<0, 0b00110, "sadalp",
       BinOpFrag<(add node:$LHS, (int_aarch64_neon_saddlp node:$RHS))> >;
defm SADDLP : SIMDLongTwoVector<0, 0b00010, "saddlp", int_aarch64_neon_saddlp>;
defm SCVTF  : SIMDTwoVectorIntToFP<0, 0, 0b11101, "scvtf", sint_to_fp>;
defm SHLL   : SIMDVectorLShiftLongBySizeBHS;
defm SQABS  : SIMDTwoVectorBHSD<0, 0b00111, "sqabs", int_aarch64_neon_sqabs>;
defm SQNEG  : SIMDTwoVectorBHSD<1, 0b00111, "sqneg", int_aarch64_neon_sqneg>;
defm SQXTN  : SIMDMixedTwoVector<0, 0b10100, "sqxtn", int_aarch64_neon_sqxtn>;
defm SQXTUN : SIMDMixedTwoVector<1, 0b10010, "sqxtun", int_aarch64_neon_sqxtun>;
defm SUQADD : SIMDTwoVectorBHSDTied<0, 0b00011, "suqadd",int_aarch64_neon_suqadd>;
defm UADALP : SIMDLongTwoVectorTied<1, 0b00110, "uadalp",
       BinOpFrag<(add node:$LHS, (int_aarch64_neon_uaddlp node:$RHS))> >;
defm UADDLP : SIMDLongTwoVector<1, 0b00010, "uaddlp",
                    int_aarch64_neon_uaddlp>;
defm UCVTF  : SIMDTwoVectorIntToFP<1, 0, 0b11101, "ucvtf", uint_to_fp>;
defm UQXTN  : SIMDMixedTwoVector<1, 0b10100, "uqxtn", int_aarch64_neon_uqxtn>;
defm URECPE : SIMDTwoVectorS<0, 1, 0b11100, "urecpe", int_aarch64_neon_urecpe>;
defm URSQRTE: SIMDTwoVectorS<1, 1, 0b11100, "ursqrte", int_aarch64_neon_ursqrte>;
defm USQADD : SIMDTwoVectorBHSDTied<1, 0b00011, "usqadd",int_aarch64_neon_usqadd>;
defm XTN    : SIMDMixedTwoVector<0, 0b10010, "xtn", trunc>;

def : Pat<(v4f16  (AArch64rev32 V64:$Rn)),  (REV32v4i16 V64:$Rn)>;
def : Pat<(v4f16  (AArch64rev64 V64:$Rn)),  (REV64v4i16 V64:$Rn)>;
def : Pat<(v4bf16 (AArch64rev32 V64:$Rn)),  (REV32v4i16 V64:$Rn)>;
def : Pat<(v4bf16 (AArch64rev64 V64:$Rn)),  (REV64v4i16 V64:$Rn)>;
def : Pat<(v8f16  (AArch64rev32 V128:$Rn)), (REV32v8i16 V128:$Rn)>;
def : Pat<(v8f16  (AArch64rev64 V128:$Rn)), (REV64v8i16 V128:$Rn)>;
def : Pat<(v8bf16 (AArch64rev32 V128:$Rn)), (REV32v8i16 V128:$Rn)>;
def : Pat<(v8bf16 (AArch64rev64 V128:$Rn)), (REV64v8i16 V128:$Rn)>;
def : Pat<(v2f32  (AArch64rev64 V64:$Rn)),  (REV64v2i32 V64:$Rn)>;
def : Pat<(v4f32  (AArch64rev64 V128:$Rn)), (REV64v4i32 V128:$Rn)>;

// Patterns for vector long shift (by element width). These need to match all
// three of zext, sext and anyext so it's easier to pull the patterns out of the
// definition.
multiclass SIMDVectorLShiftLongBySizeBHSPats<SDPatternOperator ext> {
  def : Pat<(AArch64vshl (v8i16 (ext (v8i8 V64:$Rn))), (i32 8)),
            (SHLLv8i8 V64:$Rn)>;
  def : Pat<(AArch64vshl (v8i16 (ext (extract_high_v16i8 V128:$Rn))), (i32 8)),
            (SHLLv16i8 V128:$Rn)>;
  def : Pat<(AArch64vshl (v4i32 (ext (v4i16 V64:$Rn))), (i32 16)),
            (SHLLv4i16 V64:$Rn)>;
  def : Pat<(AArch64vshl (v4i32 (ext (extract_high_v8i16 V128:$Rn))), (i32 16)),
            (SHLLv8i16 V128:$Rn)>;
  def : Pat<(AArch64vshl (v2i64 (ext (v2i32 V64:$Rn))), (i32 32)),
            (SHLLv2i32 V64:$Rn)>;
  def : Pat<(AArch64vshl (v2i64 (ext (extract_high_v4i32 V128:$Rn))), (i32 32)),
            (SHLLv4i32 V128:$Rn)>;
}

defm : SIMDVectorLShiftLongBySizeBHSPats<anyext>;
defm : SIMDVectorLShiftLongBySizeBHSPats<zext>;
defm : SIMDVectorLShiftLongBySizeBHSPats<sext>;

//===----------------------------------------------------------------------===//
// Advanced SIMD three vector instructions.
//===----------------------------------------------------------------------===//

defm ADD     : SIMDThreeSameVector<0, 0b10000, "add", add>;
defm ADDP    : SIMDThreeSameVector<0, 0b10111, "addp", int_aarch64_neon_addp>;
defm CMEQ    : SIMDThreeSameVector<1, 0b10001, "cmeq", AArch64cmeq>;
defm CMGE    : SIMDThreeSameVector<0, 0b00111, "cmge", AArch64cmge>;
defm CMGT    : SIMDThreeSameVector<0, 0b00110, "cmgt", AArch64cmgt>;
defm CMHI    : SIMDThreeSameVector<1, 0b00110, "cmhi", AArch64cmhi>;
defm CMHS    : SIMDThreeSameVector<1, 0b00111, "cmhs", AArch64cmhs>;
defm CMTST   : SIMDThreeSameVector<0, 0b10001, "cmtst", AArch64cmtst>;
defm FABD    : SIMDThreeSameVectorFP<1,1,0b010,"fabd", int_aarch64_neon_fabd>;
let Predicates = [HasNEON] in {
foreach VT = [ v2f32, v4f32, v2f64 ] in
def : Pat<(fabs (fsub VT:$Rn, VT:$Rm)), (!cast<Instruction>("FABD"#VT) VT:$Rn, VT:$Rm)>;
}
let Predicates = [HasNEON, HasFullFP16] in {
foreach VT = [ v4f16, v8f16 ] in
def : Pat<(fabs (fsub VT:$Rn, VT:$Rm)), (!cast<Instruction>("FABD"#VT) VT:$Rn, VT:$Rm)>;
}
defm FACGE   : SIMDThreeSameVectorFPCmp<1,0,0b101,"facge",int_aarch64_neon_facge>;
defm FACGT   : SIMDThreeSameVectorFPCmp<1,1,0b101,"facgt",int_aarch64_neon_facgt>;
defm FADDP   : SIMDThreeSameVectorFP<1,0,0b010,"faddp",int_aarch64_neon_faddp>;
defm FADD    : SIMDThreeSameVectorFP<0,0,0b010,"fadd", fadd>;
defm FCMEQ   : SIMDThreeSameVectorFPCmp<0, 0, 0b100, "fcmeq", AArch64fcmeq>;
defm FCMGE   : SIMDThreeSameVectorFPCmp<1, 0, 0b100, "fcmge", AArch64fcmge>;
defm FCMGT   : SIMDThreeSameVectorFPCmp<1, 1, 0b100, "fcmgt", AArch64fcmgt>;
defm FDIV    : SIMDThreeSameVectorFP<1,0,0b111,"fdiv", fdiv>;
defm FMAXNMP : SIMDThreeSameVectorFP<1,0,0b000,"fmaxnmp", int_aarch64_neon_fmaxnmp>;
defm FMAXNM  : SIMDThreeSameVectorFP<0,0,0b000,"fmaxnm", fmaxnum>;
defm FMAXP   : SIMDThreeSameVectorFP<1,0,0b110,"fmaxp", int_aarch64_neon_fmaxp>;
defm FMAX    : SIMDThreeSameVectorFP<0,0,0b110,"fmax", fmaximum>;
defm FMINNMP : SIMDThreeSameVectorFP<1,1,0b000,"fminnmp", int_aarch64_neon_fminnmp>;
defm FMINNM  : SIMDThreeSameVectorFP<0,1,0b000,"fminnm", fminnum>;
defm FMINP   : SIMDThreeSameVectorFP<1,1,0b110,"fminp", int_aarch64_neon_fminp>;
defm FMIN    : SIMDThreeSameVectorFP<0,1,0b110,"fmin", fminimum>;

// NOTE: The operands of the PatFrag are reordered on FMLA/FMLS because the
// instruction expects the addend first, while the fma intrinsic puts it last.
defm FMLA     : SIMDThreeSameVectorFPTied<0, 0, 0b001, "fmla",
            TriOpFrag<(fma node:$RHS, node:$MHS, node:$LHS)> >;
defm FMLS     : SIMDThreeSameVectorFPTied<0, 1, 0b001, "fmls",
            TriOpFrag<(fma node:$MHS, (fneg node:$RHS), node:$LHS)> >;

// The following def pats catch the case where the LHS of an FMA is negated.
// The TriOpFrag above catches the case where the middle operand is negated.
def : Pat<(v2f32 (fma (fneg V64:$Rn), V64:$Rm, V64:$Rd)),
          (FMLSv2f32 V64:$Rd, V64:$Rn, V64:$Rm)>;

def : Pat<(v4f32 (fma (fneg V128:$Rn), V128:$Rm, V128:$Rd)),
          (FMLSv4f32 V128:$Rd, V128:$Rn, V128:$Rm)>;

def : Pat<(v2f64 (fma (fneg V128:$Rn), V128:$Rm, V128:$Rd)),
          (FMLSv2f64 V128:$Rd, V128:$Rn, V128:$Rm)>;

defm FMULX    : SIMDThreeSameVectorFP<0,0,0b011,"fmulx", int_aarch64_neon_fmulx>;
defm FMUL     : SIMDThreeSameVectorFP<1,0,0b011,"fmul", fmul>;
defm FRECPS   : SIMDThreeSameVectorFP<0,0,0b111,"frecps", int_aarch64_neon_frecps>;
defm FRSQRTS  : SIMDThreeSameVectorFP<0,1,0b111,"frsqrts", int_aarch64_neon_frsqrts>;
defm FSUB     : SIMDThreeSameVectorFP<0,1,0b010,"fsub", fsub>;

// MLA and MLS are generated in MachineCombine
defm MLA      : SIMDThreeSameVectorBHSTied<0, 0b10010, "mla", null_frag>;
defm MLS      : SIMDThreeSameVectorBHSTied<1, 0b10010, "mls", null_frag>;

defm MUL      : SIMDThreeSameVectorBHS<0, 0b10011, "mul", mul>;
defm PMUL     : SIMDThreeSameVectorB<1, 0b10011, "pmul", int_aarch64_neon_pmul>;
defm SABA     : SIMDThreeSameVectorBHSTied<0, 0b01111, "saba",
      TriOpFrag<(add node:$LHS, (int_aarch64_neon_sabd node:$MHS, node:$RHS))> >;
defm SABD     : SIMDThreeSameVectorBHS<0,0b01110,"sabd", int_aarch64_neon_sabd>;
defm SHADD    : SIMDThreeSameVectorBHS<0,0b00000,"shadd", int_aarch64_neon_shadd>;
defm SHSUB    : SIMDThreeSameVectorBHS<0,0b00100,"shsub", int_aarch64_neon_shsub>;
defm SMAXP    : SIMDThreeSameVectorBHS<0,0b10100,"smaxp", int_aarch64_neon_smaxp>;
defm SMAX     : SIMDThreeSameVectorBHS<0,0b01100,"smax", smax>;
defm SMINP    : SIMDThreeSameVectorBHS<0,0b10101,"sminp", int_aarch64_neon_sminp>;
defm SMIN     : SIMDThreeSameVectorBHS<0,0b01101,"smin", smin>;
defm SQADD    : SIMDThreeSameVector<0,0b00001,"sqadd", int_aarch64_neon_sqadd>;
defm SQDMULH  : SIMDThreeSameVectorHS<0,0b10110,"sqdmulh",int_aarch64_neon_sqdmulh>;
defm SQRDMULH : SIMDThreeSameVectorHS<1,0b10110,"sqrdmulh",int_aarch64_neon_sqrdmulh>;
defm SQRSHL   : SIMDThreeSameVector<0,0b01011,"sqrshl", int_aarch64_neon_sqrshl>;
defm SQSHL    : SIMDThreeSameVector<0,0b01001,"sqshl", int_aarch64_neon_sqshl>;
defm SQSUB    : SIMDThreeSameVector<0,0b00101,"sqsub", int_aarch64_neon_sqsub>;
defm SRHADD   : SIMDThreeSameVectorBHS<0,0b00010,"srhadd", AArch64srhadd>;
defm SRSHL    : SIMDThreeSameVector<0,0b01010,"srshl", int_aarch64_neon_srshl>;
defm SSHL     : SIMDThreeSameVector<0,0b01000,"sshl", int_aarch64_neon_sshl>;
defm SUB      : SIMDThreeSameVector<1,0b10000,"sub", sub>;
defm UABA     : SIMDThreeSameVectorBHSTied<1, 0b01111, "uaba",
      TriOpFrag<(add node:$LHS, (int_aarch64_neon_uabd node:$MHS, node:$RHS))> >;
defm UABD     : SIMDThreeSameVectorBHS<1,0b01110,"uabd", int_aarch64_neon_uabd>;
defm UHADD    : SIMDThreeSameVectorBHS<1,0b00000,"uhadd", int_aarch64_neon_uhadd>;
defm UHSUB    : SIMDThreeSameVectorBHS<1,0b00100,"uhsub", int_aarch64_neon_uhsub>;
defm UMAXP    : SIMDThreeSameVectorBHS<1,0b10100,"umaxp", int_aarch64_neon_umaxp>;
defm UMAX     : SIMDThreeSameVectorBHS<1,0b01100,"umax", umax>;
defm UMINP    : SIMDThreeSameVectorBHS<1,0b10101,"uminp", int_aarch64_neon_uminp>;
defm UMIN     : SIMDThreeSameVectorBHS<1,0b01101,"umin", umin>;
defm UQADD    : SIMDThreeSameVector<1,0b00001,"uqadd", int_aarch64_neon_uqadd>;
defm UQRSHL   : SIMDThreeSameVector<1,0b01011,"uqrshl", int_aarch64_neon_uqrshl>;
defm UQSHL    : SIMDThreeSameVector<1,0b01001,"uqshl", int_aarch64_neon_uqshl>;
defm UQSUB    : SIMDThreeSameVector<1,0b00101,"uqsub", int_aarch64_neon_uqsub>;
defm URHADD   : SIMDThreeSameVectorBHS<1,0b00010,"urhadd", AArch64urhadd>;
defm URSHL    : SIMDThreeSameVector<1,0b01010,"urshl", int_aarch64_neon_urshl>;
defm USHL     : SIMDThreeSameVector<1,0b01000,"ushl", int_aarch64_neon_ushl>;
defm SQRDMLAH : SIMDThreeSameVectorSQRDMLxHTiedHS<1,0b10000,"sqrdmlah",
                                                  int_aarch64_neon_sqadd>;
defm SQRDMLSH : SIMDThreeSameVectorSQRDMLxHTiedHS<1,0b10001,"sqrdmlsh",
                                                    int_aarch64_neon_sqsub>;

// Extra saturate patterns, other than the intrinsics matches above
defm : SIMDThreeSameVectorExtraPatterns<"SQADD", saddsat>;
defm : SIMDThreeSameVectorExtraPatterns<"UQADD", uaddsat>;
defm : SIMDThreeSameVectorExtraPatterns<"SQSUB", ssubsat>;
defm : SIMDThreeSameVectorExtraPatterns<"UQSUB", usubsat>;

defm AND : SIMDLogicalThreeVector<0, 0b00, "and", and>;
defm BIC : SIMDLogicalThreeVector<0, 0b01, "bic",
                                  BinOpFrag<(and node:$LHS, (vnot node:$RHS))> >;
defm EOR : SIMDLogicalThreeVector<1, 0b00, "eor", xor>;
defm ORN : SIMDLogicalThreeVector<0, 0b11, "orn",
                                  BinOpFrag<(or node:$LHS, (vnot node:$RHS))> >;
defm ORR : SIMDLogicalThreeVector<0, 0b10, "orr", or>;

// Pseudo bitwise select pattern BSP.
// It is expanded into BSL/BIT/BIF after register allocation.
defm BSP : SIMDLogicalThreeVectorPseudo<TriOpFrag<(or (and node:$LHS, node:$MHS),
                                                      (and (vnot node:$LHS), node:$RHS))>>;
defm BSL : SIMDLogicalThreeVectorTied<1, 0b01, "bsl">;
defm BIT : SIMDLogicalThreeVectorTied<1, 0b10, "bit", AArch64bit>;
defm BIF : SIMDLogicalThreeVectorTied<1, 0b11, "bif">;

def : Pat<(AArch64bsp (v8i8 V64:$Rd), V64:$Rn, V64:$Rm),
          (BSPv8i8 V64:$Rd, V64:$Rn, V64:$Rm)>;
def : Pat<(AArch64bsp (v4i16 V64:$Rd), V64:$Rn, V64:$Rm),
          (BSPv8i8 V64:$Rd, V64:$Rn, V64:$Rm)>;
def : Pat<(AArch64bsp (v2i32 V64:$Rd), V64:$Rn, V64:$Rm),
          (BSPv8i8 V64:$Rd, V64:$Rn, V64:$Rm)>;
def : Pat<(AArch64bsp (v1i64 V64:$Rd), V64:$Rn, V64:$Rm),
          (BSPv8i8 V64:$Rd, V64:$Rn, V64:$Rm)>;

def : Pat<(AArch64bsp (v16i8 V128:$Rd), V128:$Rn, V128:$Rm),
          (BSPv16i8 V128:$Rd, V128:$Rn, V128:$Rm)>;
def : Pat<(AArch64bsp (v8i16 V128:$Rd), V128:$Rn, V128:$Rm),
          (BSPv16i8 V128:$Rd, V128:$Rn, V128:$Rm)>;
def : Pat<(AArch64bsp (v4i32 V128:$Rd), V128:$Rn, V128:$Rm),
          (BSPv16i8 V128:$Rd, V128:$Rn, V128:$Rm)>;
def : Pat<(AArch64bsp (v2i64 V128:$Rd), V128:$Rn, V128:$Rm),
          (BSPv16i8 V128:$Rd, V128:$Rn, V128:$Rm)>;

def : InstAlias<"mov{\t$dst.16b, $src.16b|.16b\t$dst, $src}",
                (ORRv16i8 V128:$dst, V128:$src, V128:$src), 1>;
def : InstAlias<"mov{\t$dst.8h, $src.8h|.8h\t$dst, $src}",
                (ORRv16i8 V128:$dst, V128:$src, V128:$src), 0>;
def : InstAlias<"mov{\t$dst.4s, $src.4s|.4s\t$dst, $src}",
                (ORRv16i8 V128:$dst, V128:$src, V128:$src), 0>;
def : InstAlias<"mov{\t$dst.2d, $src.2d|.2d\t$dst, $src}",
                (ORRv16i8 V128:$dst, V128:$src, V128:$src), 0>;

def : InstAlias<"mov{\t$dst.8b, $src.8b|.8b\t$dst, $src}",
                (ORRv8i8 V64:$dst, V64:$src, V64:$src), 1>;
def : InstAlias<"mov{\t$dst.4h, $src.4h|.4h\t$dst, $src}",
                (ORRv8i8 V64:$dst, V64:$src, V64:$src), 0>;
def : InstAlias<"mov{\t$dst.2s, $src.2s|.2s\t$dst, $src}",
                (ORRv8i8 V64:$dst, V64:$src, V64:$src), 0>;
def : InstAlias<"mov{\t$dst.1d, $src.1d|.1d\t$dst, $src}",
                (ORRv8i8 V64:$dst, V64:$src, V64:$src), 0>;

def : InstAlias<"{cmls\t$dst.8b, $src1.8b, $src2.8b" #
                "|cmls.8b\t$dst, $src1, $src2}",
                (CMHSv8i8 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmls\t$dst.16b, $src1.16b, $src2.16b" #
                "|cmls.16b\t$dst, $src1, $src2}",
                (CMHSv16i8 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmls\t$dst.4h, $src1.4h, $src2.4h" #
                "|cmls.4h\t$dst, $src1, $src2}",
                (CMHSv4i16 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmls\t$dst.8h, $src1.8h, $src2.8h" #
                "|cmls.8h\t$dst, $src1, $src2}",
                (CMHSv8i16 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmls\t$dst.2s, $src1.2s, $src2.2s" #
                "|cmls.2s\t$dst, $src1, $src2}",
                (CMHSv2i32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmls\t$dst.4s, $src1.4s, $src2.4s" #
                "|cmls.4s\t$dst, $src1, $src2}",
                (CMHSv4i32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmls\t$dst.2d, $src1.2d, $src2.2d" #
                "|cmls.2d\t$dst, $src1, $src2}",
                (CMHSv2i64 V128:$dst, V128:$src2, V128:$src1), 0>;

def : InstAlias<"{cmlo\t$dst.8b, $src1.8b, $src2.8b" #
                "|cmlo.8b\t$dst, $src1, $src2}",
                (CMHIv8i8 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmlo\t$dst.16b, $src1.16b, $src2.16b" #
                "|cmlo.16b\t$dst, $src1, $src2}",
                (CMHIv16i8 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmlo\t$dst.4h, $src1.4h, $src2.4h" #
                "|cmlo.4h\t$dst, $src1, $src2}",
                (CMHIv4i16 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmlo\t$dst.8h, $src1.8h, $src2.8h" #
                "|cmlo.8h\t$dst, $src1, $src2}",
                (CMHIv8i16 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmlo\t$dst.2s, $src1.2s, $src2.2s" #
                "|cmlo.2s\t$dst, $src1, $src2}",
                (CMHIv2i32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmlo\t$dst.4s, $src1.4s, $src2.4s" #
                "|cmlo.4s\t$dst, $src1, $src2}",
                (CMHIv4i32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmlo\t$dst.2d, $src1.2d, $src2.2d" #
                "|cmlo.2d\t$dst, $src1, $src2}",
                (CMHIv2i64 V128:$dst, V128:$src2, V128:$src1), 0>;

def : InstAlias<"{cmle\t$dst.8b, $src1.8b, $src2.8b" #
                "|cmle.8b\t$dst, $src1, $src2}",
                (CMGEv8i8 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmle\t$dst.16b, $src1.16b, $src2.16b" #
                "|cmle.16b\t$dst, $src1, $src2}",
                (CMGEv16i8 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmle\t$dst.4h, $src1.4h, $src2.4h" #
                "|cmle.4h\t$dst, $src1, $src2}",
                (CMGEv4i16 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmle\t$dst.8h, $src1.8h, $src2.8h" #
                "|cmle.8h\t$dst, $src1, $src2}",
                (CMGEv8i16 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmle\t$dst.2s, $src1.2s, $src2.2s" #
                "|cmle.2s\t$dst, $src1, $src2}",
                (CMGEv2i32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmle\t$dst.4s, $src1.4s, $src2.4s" #
                "|cmle.4s\t$dst, $src1, $src2}",
                (CMGEv4i32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmle\t$dst.2d, $src1.2d, $src2.2d" #
                "|cmle.2d\t$dst, $src1, $src2}",
                (CMGEv2i64 V128:$dst, V128:$src2, V128:$src1), 0>;

def : InstAlias<"{cmlt\t$dst.8b, $src1.8b, $src2.8b" #
                "|cmlt.8b\t$dst, $src1, $src2}",
                (CMGTv8i8 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmlt\t$dst.16b, $src1.16b, $src2.16b" #
                "|cmlt.16b\t$dst, $src1, $src2}",
                (CMGTv16i8 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmlt\t$dst.4h, $src1.4h, $src2.4h" #
                "|cmlt.4h\t$dst, $src1, $src2}",
                (CMGTv4i16 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmlt\t$dst.8h, $src1.8h, $src2.8h" #
                "|cmlt.8h\t$dst, $src1, $src2}",
                (CMGTv8i16 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmlt\t$dst.2s, $src1.2s, $src2.2s" #
                "|cmlt.2s\t$dst, $src1, $src2}",
                (CMGTv2i32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{cmlt\t$dst.4s, $src1.4s, $src2.4s" #
                "|cmlt.4s\t$dst, $src1, $src2}",
                (CMGTv4i32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{cmlt\t$dst.2d, $src1.2d, $src2.2d" #
                "|cmlt.2d\t$dst, $src1, $src2}",
                (CMGTv2i64 V128:$dst, V128:$src2, V128:$src1), 0>;

let Predicates = [HasNEON, HasFullFP16] in {
def : InstAlias<"{fcmle\t$dst.4h, $src1.4h, $src2.4h" #
                "|fcmle.4h\t$dst, $src1, $src2}",
                (FCMGEv4f16 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{fcmle\t$dst.8h, $src1.8h, $src2.8h" #
                "|fcmle.8h\t$dst, $src1, $src2}",
                (FCMGEv8f16 V128:$dst, V128:$src2, V128:$src1), 0>;
}
def : InstAlias<"{fcmle\t$dst.2s, $src1.2s, $src2.2s" #
                "|fcmle.2s\t$dst, $src1, $src2}",
                (FCMGEv2f32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{fcmle\t$dst.4s, $src1.4s, $src2.4s" #
                "|fcmle.4s\t$dst, $src1, $src2}",
                (FCMGEv4f32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{fcmle\t$dst.2d, $src1.2d, $src2.2d" #
                "|fcmle.2d\t$dst, $src1, $src2}",
                (FCMGEv2f64 V128:$dst, V128:$src2, V128:$src1), 0>;

let Predicates = [HasNEON, HasFullFP16] in {
def : InstAlias<"{fcmlt\t$dst.4h, $src1.4h, $src2.4h" #
                "|fcmlt.4h\t$dst, $src1, $src2}",
                (FCMGTv4f16 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{fcmlt\t$dst.8h, $src1.8h, $src2.8h" #
                "|fcmlt.8h\t$dst, $src1, $src2}",
                (FCMGTv8f16 V128:$dst, V128:$src2, V128:$src1), 0>;
}
def : InstAlias<"{fcmlt\t$dst.2s, $src1.2s, $src2.2s" #
                "|fcmlt.2s\t$dst, $src1, $src2}",
                (FCMGTv2f32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{fcmlt\t$dst.4s, $src1.4s, $src2.4s" #
                "|fcmlt.4s\t$dst, $src1, $src2}",
                (FCMGTv4f32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{fcmlt\t$dst.2d, $src1.2d, $src2.2d" #
                "|fcmlt.2d\t$dst, $src1, $src2}",
                (FCMGTv2f64 V128:$dst, V128:$src2, V128:$src1), 0>;

let Predicates = [HasNEON, HasFullFP16] in {
def : InstAlias<"{facle\t$dst.4h, $src1.4h, $src2.4h" #
                "|facle.4h\t$dst, $src1, $src2}",
                (FACGEv4f16 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{facle\t$dst.8h, $src1.8h, $src2.8h" #
                "|facle.8h\t$dst, $src1, $src2}",
                (FACGEv8f16 V128:$dst, V128:$src2, V128:$src1), 0>;
}
def : InstAlias<"{facle\t$dst.2s, $src1.2s, $src2.2s" #
                "|facle.2s\t$dst, $src1, $src2}",
                (FACGEv2f32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{facle\t$dst.4s, $src1.4s, $src2.4s" #
                "|facle.4s\t$dst, $src1, $src2}",
                (FACGEv4f32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{facle\t$dst.2d, $src1.2d, $src2.2d" #
                "|facle.2d\t$dst, $src1, $src2}",
                (FACGEv2f64 V128:$dst, V128:$src2, V128:$src1), 0>;

let Predicates = [HasNEON, HasFullFP16] in {
def : InstAlias<"{faclt\t$dst.4h, $src1.4h, $src2.4h" #
                "|faclt.4h\t$dst, $src1, $src2}",
                (FACGTv4f16 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{faclt\t$dst.8h, $src1.8h, $src2.8h" #
                "|faclt.8h\t$dst, $src1, $src2}",
                (FACGTv8f16 V128:$dst, V128:$src2, V128:$src1), 0>;
}
def : InstAlias<"{faclt\t$dst.2s, $src1.2s, $src2.2s" #
                "|faclt.2s\t$dst, $src1, $src2}",
                (FACGTv2f32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{faclt\t$dst.4s, $src1.4s, $src2.4s" #
                "|faclt.4s\t$dst, $src1, $src2}",
                (FACGTv4f32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{faclt\t$dst.2d, $src1.2d, $src2.2d" #
                "|faclt.2d\t$dst, $src1, $src2}",
                (FACGTv2f64 V128:$dst, V128:$src2, V128:$src1), 0>;

//===----------------------------------------------------------------------===//
// Advanced SIMD three scalar instructions.
//===----------------------------------------------------------------------===//

defm ADD      : SIMDThreeScalarD<0, 0b10000, "add", add>;
defm CMEQ     : SIMDThreeScalarD<1, 0b10001, "cmeq", AArch64cmeq>;
defm CMGE     : SIMDThreeScalarD<0, 0b00111, "cmge", AArch64cmge>;
defm CMGT     : SIMDThreeScalarD<0, 0b00110, "cmgt", AArch64cmgt>;
defm CMHI     : SIMDThreeScalarD<1, 0b00110, "cmhi", AArch64cmhi>;
defm CMHS     : SIMDThreeScalarD<1, 0b00111, "cmhs", AArch64cmhs>;
defm CMTST    : SIMDThreeScalarD<0, 0b10001, "cmtst", AArch64cmtst>;
defm FABD     : SIMDFPThreeScalar<1, 1, 0b010, "fabd", int_aarch64_sisd_fabd>;
def : Pat<(v1f64 (int_aarch64_neon_fabd (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
          (FABD64 FPR64:$Rn, FPR64:$Rm)>;
let Predicates = [HasFullFP16] in {
def : Pat<(fabs (fsub f16:$Rn, f16:$Rm)), (FABD16 f16:$Rn, f16:$Rm)>;
}
def : Pat<(fabs (fsub f32:$Rn, f32:$Rm)), (FABD32 f32:$Rn, f32:$Rm)>;
def : Pat<(fabs (fsub f64:$Rn, f64:$Rm)), (FABD64 f64:$Rn, f64:$Rm)>;
defm FACGE    : SIMDThreeScalarFPCmp<1, 0, 0b101, "facge",
                                     int_aarch64_neon_facge>;
defm FACGT    : SIMDThreeScalarFPCmp<1, 1, 0b101, "facgt",
                                     int_aarch64_neon_facgt>;
defm FCMEQ    : SIMDThreeScalarFPCmp<0, 0, 0b100, "fcmeq", AArch64fcmeq>;
defm FCMGE    : SIMDThreeScalarFPCmp<1, 0, 0b100, "fcmge", AArch64fcmge>;
defm FCMGT    : SIMDThreeScalarFPCmp<1, 1, 0b100, "fcmgt", AArch64fcmgt>;
defm FMULX    : SIMDFPThreeScalar<0, 0, 0b011, "fmulx", int_aarch64_neon_fmulx>;
defm FRECPS   : SIMDFPThreeScalar<0, 0, 0b111, "frecps", int_aarch64_neon_frecps>;
defm FRSQRTS  : SIMDFPThreeScalar<0, 1, 0b111, "frsqrts", int_aarch64_neon_frsqrts>;
defm SQADD    : SIMDThreeScalarBHSD<0, 0b00001, "sqadd", int_aarch64_neon_sqadd>;
defm SQDMULH  : SIMDThreeScalarHS<  0, 0b10110, "sqdmulh", int_aarch64_neon_sqdmulh>;
defm SQRDMULH : SIMDThreeScalarHS<  1, 0b10110, "sqrdmulh", int_aarch64_neon_sqrdmulh>;
defm SQRSHL   : SIMDThreeScalarBHSD<0, 0b01011, "sqrshl",int_aarch64_neon_sqrshl>;
defm SQSHL    : SIMDThreeScalarBHSD<0, 0b01001, "sqshl", int_aarch64_neon_sqshl>;
defm SQSUB    : SIMDThreeScalarBHSD<0, 0b00101, "sqsub", int_aarch64_neon_sqsub>;
defm SRSHL    : SIMDThreeScalarD<   0, 0b01010, "srshl", int_aarch64_neon_srshl>;
defm SSHL     : SIMDThreeScalarD<   0, 0b01000, "sshl", int_aarch64_neon_sshl>;
defm SUB      : SIMDThreeScalarD<   1, 0b10000, "sub", sub>;
defm UQADD    : SIMDThreeScalarBHSD<1, 0b00001, "uqadd", int_aarch64_neon_uqadd>;
defm UQRSHL   : SIMDThreeScalarBHSD<1, 0b01011, "uqrshl",int_aarch64_neon_uqrshl>;
defm UQSHL    : SIMDThreeScalarBHSD<1, 0b01001, "uqshl", int_aarch64_neon_uqshl>;
defm UQSUB    : SIMDThreeScalarBHSD<1, 0b00101, "uqsub", int_aarch64_neon_uqsub>;
defm URSHL    : SIMDThreeScalarD<   1, 0b01010, "urshl", int_aarch64_neon_urshl>;
defm USHL     : SIMDThreeScalarD<   1, 0b01000, "ushl", int_aarch64_neon_ushl>;
let Predicates = [HasRDM] in {
  defm SQRDMLAH : SIMDThreeScalarHSTied<1, 0, 0b10000, "sqrdmlah">;
  defm SQRDMLSH : SIMDThreeScalarHSTied<1, 0, 0b10001, "sqrdmlsh">;
  def : Pat<(i32 (int_aarch64_neon_sqadd
                   (i32 FPR32:$Rd),
                   (i32 (int_aarch64_neon_sqrdmulh (i32 FPR32:$Rn),
                                                   (i32 FPR32:$Rm))))),
            (SQRDMLAHv1i32 FPR32:$Rd, FPR32:$Rn, FPR32:$Rm)>;
  def : Pat<(i32 (int_aarch64_neon_sqsub
                   (i32 FPR32:$Rd),
                   (i32 (int_aarch64_neon_sqrdmulh (i32 FPR32:$Rn),
                                                   (i32 FPR32:$Rm))))),
            (SQRDMLSHv1i32 FPR32:$Rd, FPR32:$Rn, FPR32:$Rm)>;
}

def : InstAlias<"cmls $dst, $src1, $src2",
                (CMHSv1i64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
def : InstAlias<"cmle $dst, $src1, $src2",
                (CMGEv1i64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
def : InstAlias<"cmlo $dst, $src1, $src2",
                (CMHIv1i64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
def : InstAlias<"cmlt $dst, $src1, $src2",
                (CMGTv1i64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
def : InstAlias<"fcmle $dst, $src1, $src2",
                (FCMGE32 FPR32:$dst, FPR32:$src2, FPR32:$src1), 0>;
def : InstAlias<"fcmle $dst, $src1, $src2",
                (FCMGE64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
def : InstAlias<"fcmlt $dst, $src1, $src2",
                (FCMGT32 FPR32:$dst, FPR32:$src2, FPR32:$src1), 0>;
def : InstAlias<"fcmlt $dst, $src1, $src2",
                (FCMGT64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
def : InstAlias<"facle $dst, $src1, $src2",
                (FACGE32 FPR32:$dst, FPR32:$src2, FPR32:$src1), 0>;
def : InstAlias<"facle $dst, $src1, $src2",
                (FACGE64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;
def : InstAlias<"faclt $dst, $src1, $src2",
                (FACGT32 FPR32:$dst, FPR32:$src2, FPR32:$src1), 0>;
def : InstAlias<"faclt $dst, $src1, $src2",
                (FACGT64 FPR64:$dst, FPR64:$src2, FPR64:$src1), 0>;

//===----------------------------------------------------------------------===//
// Advanced SIMD three scalar instructions (mixed operands).
//===----------------------------------------------------------------------===//
defm SQDMULL  : SIMDThreeScalarMixedHS<0, 0b11010, "sqdmull",
                                       int_aarch64_neon_sqdmulls_scalar>;
defm SQDMLAL  : SIMDThreeScalarMixedTiedHS<0, 0b10010, "sqdmlal">;
defm SQDMLSL  : SIMDThreeScalarMixedTiedHS<0, 0b10110, "sqdmlsl">;

def : Pat<(i64 (int_aarch64_neon_sqadd (i64 FPR64:$Rd),
                   (i64 (int_aarch64_neon_sqdmulls_scalar (i32 FPR32:$Rn),
                                                        (i32 FPR32:$Rm))))),
          (SQDMLALi32 FPR64:$Rd, FPR32:$Rn, FPR32:$Rm)>;
def : Pat<(i64 (int_aarch64_neon_sqsub (i64 FPR64:$Rd),
                   (i64 (int_aarch64_neon_sqdmulls_scalar (i32 FPR32:$Rn),
                                                        (i32 FPR32:$Rm))))),
          (SQDMLSLi32 FPR64:$Rd, FPR32:$Rn, FPR32:$Rm)>;

//===----------------------------------------------------------------------===//
// Advanced SIMD two scalar instructions.
//===----------------------------------------------------------------------===//

defm ABS    : SIMDTwoScalarD<    0, 0b01011, "abs", abs>;
defm CMEQ   : SIMDCmpTwoScalarD< 0, 0b01001, "cmeq", AArch64cmeqz>;
defm CMGE   : SIMDCmpTwoScalarD< 1, 0b01000, "cmge", AArch64cmgez>;
defm CMGT   : SIMDCmpTwoScalarD< 0, 0b01000, "cmgt", AArch64cmgtz>;
defm CMLE   : SIMDCmpTwoScalarD< 1, 0b01001, "cmle", AArch64cmlez>;
defm CMLT   : SIMDCmpTwoScalarD< 0, 0b01010, "cmlt", AArch64cmltz>;
defm FCMEQ  : SIMDFPCmpTwoScalar<0, 1, 0b01101, "fcmeq", AArch64fcmeqz>;
defm FCMGE  : SIMDFPCmpTwoScalar<1, 1, 0b01100, "fcmge", AArch64fcmgez>;
defm FCMGT  : SIMDFPCmpTwoScalar<0, 1, 0b01100, "fcmgt", AArch64fcmgtz>;
defm FCMLE  : SIMDFPCmpTwoScalar<1, 1, 0b01101, "fcmle", AArch64fcmlez>;
defm FCMLT  : SIMDFPCmpTwoScalar<0, 1, 0b01110, "fcmlt", AArch64fcmltz>;
defm FCVTAS : SIMDFPTwoScalar<   0, 0, 0b11100, "fcvtas">;
defm FCVTAU : SIMDFPTwoScalar<   1, 0, 0b11100, "fcvtau">;
defm FCVTMS : SIMDFPTwoScalar<   0, 0, 0b11011, "fcvtms">;
defm FCVTMU : SIMDFPTwoScalar<   1, 0, 0b11011, "fcvtmu">;
defm FCVTNS : SIMDFPTwoScalar<   0, 0, 0b11010, "fcvtns">;
defm FCVTNU : SIMDFPTwoScalar<   1, 0, 0b11010, "fcvtnu">;
defm FCVTPS : SIMDFPTwoScalar<   0, 1, 0b11010, "fcvtps">;
defm FCVTPU : SIMDFPTwoScalar<   1, 1, 0b11010, "fcvtpu">;
def  FCVTXNv1i64 : SIMDInexactCvtTwoScalar<0b10110, "fcvtxn">;
defm FCVTZS : SIMDFPTwoScalar<   0, 1, 0b11011, "fcvtzs">;
defm FCVTZU : SIMDFPTwoScalar<   1, 1, 0b11011, "fcvtzu">;
defm FRECPE : SIMDFPTwoScalar<   0, 1, 0b11101, "frecpe">;
defm FRECPX : SIMDFPTwoScalar<   0, 1, 0b11111, "frecpx">;
defm FRSQRTE : SIMDFPTwoScalar<  1, 1, 0b11101, "frsqrte">;
defm NEG    : SIMDTwoScalarD<    1, 0b01011, "neg",
                                 UnOpFrag<(sub immAllZerosV, node:$LHS)> >;
defm SCVTF  : SIMDFPTwoScalarCVT<   0, 0, 0b11101, "scvtf", AArch64sitof>;
defm SQABS  : SIMDTwoScalarBHSD< 0, 0b00111, "sqabs", int_aarch64_neon_sqabs>;
defm SQNEG  : SIMDTwoScalarBHSD< 1, 0b00111, "sqneg", int_aarch64_neon_sqneg>;
defm SQXTN  : SIMDTwoScalarMixedBHS< 0, 0b10100, "sqxtn", int_aarch64_neon_scalar_sqxtn>;
defm SQXTUN : SIMDTwoScalarMixedBHS< 1, 0b10010, "sqxtun", int_aarch64_neon_scalar_sqxtun>;
defm SUQADD : SIMDTwoScalarBHSDTied< 0, 0b00011, "suqadd",
                                     int_aarch64_neon_suqadd>;
defm UCVTF  : SIMDFPTwoScalarCVT<   1, 0, 0b11101, "ucvtf", AArch64uitof>;
defm UQXTN  : SIMDTwoScalarMixedBHS<1, 0b10100, "uqxtn", int_aarch64_neon_scalar_uqxtn>;
defm USQADD : SIMDTwoScalarBHSDTied< 1, 0b00011, "usqadd",
                                    int_aarch64_neon_usqadd>;

def : Pat<(AArch64neg (v1i64 V64:$Rn)), (NEGv1i64 V64:$Rn)>;

def : Pat<(v1i64 (int_aarch64_neon_fcvtas (v1f64 FPR64:$Rn))),
          (FCVTASv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_aarch64_neon_fcvtau (v1f64 FPR64:$Rn))),
          (FCVTAUv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_aarch64_neon_fcvtms (v1f64 FPR64:$Rn))),
          (FCVTMSv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_aarch64_neon_fcvtmu (v1f64 FPR64:$Rn))),
          (FCVTMUv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_aarch64_neon_fcvtns (v1f64 FPR64:$Rn))),
          (FCVTNSv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_aarch64_neon_fcvtnu (v1f64 FPR64:$Rn))),
          (FCVTNUv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_aarch64_neon_fcvtps (v1f64 FPR64:$Rn))),
          (FCVTPSv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_aarch64_neon_fcvtpu (v1f64 FPR64:$Rn))),
          (FCVTPUv1i64 FPR64:$Rn)>;

def : Pat<(f16 (int_aarch64_neon_frecpe (f16 FPR16:$Rn))),
          (FRECPEv1f16 FPR16:$Rn)>;
def : Pat<(f32 (int_aarch64_neon_frecpe (f32 FPR32:$Rn))),
          (FRECPEv1i32 FPR32:$Rn)>;
def : Pat<(f64 (int_aarch64_neon_frecpe (f64 FPR64:$Rn))),
          (FRECPEv1i64 FPR64:$Rn)>;
def : Pat<(v1f64 (int_aarch64_neon_frecpe (v1f64 FPR64:$Rn))),
          (FRECPEv1i64 FPR64:$Rn)>;

def : Pat<(f32 (AArch64frecpe (f32 FPR32:$Rn))),
          (FRECPEv1i32 FPR32:$Rn)>;
def : Pat<(v2f32 (AArch64frecpe (v2f32 V64:$Rn))),
          (FRECPEv2f32 V64:$Rn)>;
def : Pat<(v4f32 (AArch64frecpe (v4f32 FPR128:$Rn))),
          (FRECPEv4f32 FPR128:$Rn)>;
def : Pat<(f64 (AArch64frecpe (f64 FPR64:$Rn))),
          (FRECPEv1i64 FPR64:$Rn)>;
def : Pat<(v1f64 (AArch64frecpe (v1f64 FPR64:$Rn))),
          (FRECPEv1i64 FPR64:$Rn)>;
def : Pat<(v2f64 (AArch64frecpe (v2f64 FPR128:$Rn))),
          (FRECPEv2f64 FPR128:$Rn)>;

def : Pat<(f32 (AArch64frecps (f32 FPR32:$Rn), (f32 FPR32:$Rm))),
          (FRECPS32 FPR32:$Rn, FPR32:$Rm)>;
def : Pat<(v2f32 (AArch64frecps (v2f32 V64:$Rn), (v2f32 V64:$Rm))),
          (FRECPSv2f32 V64:$Rn, V64:$Rm)>;
def : Pat<(v4f32 (AArch64frecps (v4f32 FPR128:$Rn), (v4f32 FPR128:$Rm))),
          (FRECPSv4f32 FPR128:$Rn, FPR128:$Rm)>;
def : Pat<(f64 (AArch64frecps (f64 FPR64:$Rn), (f64 FPR64:$Rm))),
          (FRECPS64 FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(v2f64 (AArch64frecps (v2f64 FPR128:$Rn), (v2f64 FPR128:$Rm))),
          (FRECPSv2f64 FPR128:$Rn, FPR128:$Rm)>;

def : Pat<(f16 (int_aarch64_neon_frecpx (f16 FPR16:$Rn))),
          (FRECPXv1f16 FPR16:$Rn)>;
def : Pat<(f32 (int_aarch64_neon_frecpx (f32 FPR32:$Rn))),
          (FRECPXv1i32 FPR32:$Rn)>;
def : Pat<(f64 (int_aarch64_neon_frecpx (f64 FPR64:$Rn))),
          (FRECPXv1i64 FPR64:$Rn)>;

def : Pat<(f16 (int_aarch64_neon_frsqrte (f16 FPR16:$Rn))),
          (FRSQRTEv1f16 FPR16:$Rn)>;
def : Pat<(f32 (int_aarch64_neon_frsqrte (f32 FPR32:$Rn))),
          (FRSQRTEv1i32 FPR32:$Rn)>;
def : Pat<(f64 (int_aarch64_neon_frsqrte (f64 FPR64:$Rn))),
          (FRSQRTEv1i64 FPR64:$Rn)>;
def : Pat<(v1f64 (int_aarch64_neon_frsqrte (v1f64 FPR64:$Rn))),
          (FRSQRTEv1i64 FPR64:$Rn)>;

def : Pat<(f32 (AArch64frsqrte (f32 FPR32:$Rn))),
          (FRSQRTEv1i32 FPR32:$Rn)>;
def : Pat<(v2f32 (AArch64frsqrte (v2f32 V64:$Rn))),
          (FRSQRTEv2f32 V64:$Rn)>;
def : Pat<(v4f32 (AArch64frsqrte (v4f32 FPR128:$Rn))),
          (FRSQRTEv4f32 FPR128:$Rn)>;
def : Pat<(f64 (AArch64frsqrte (f64 FPR64:$Rn))),
          (FRSQRTEv1i64 FPR64:$Rn)>;
def : Pat<(v1f64 (AArch64frsqrte (v1f64 FPR64:$Rn))),
          (FRSQRTEv1i64 FPR64:$Rn)>;
def : Pat<(v2f64 (AArch64frsqrte (v2f64 FPR128:$Rn))),
          (FRSQRTEv2f64 FPR128:$Rn)>;

def : Pat<(f32 (AArch64frsqrts (f32 FPR32:$Rn), (f32 FPR32:$Rm))),
          (FRSQRTS32 FPR32:$Rn, FPR32:$Rm)>;
def : Pat<(v2f32 (AArch64frsqrts (v2f32 V64:$Rn), (v2f32 V64:$Rm))),
          (FRSQRTSv2f32 V64:$Rn, V64:$Rm)>;
def : Pat<(v4f32 (AArch64frsqrts (v4f32 FPR128:$Rn), (v4f32 FPR128:$Rm))),
          (FRSQRTSv4f32 FPR128:$Rn, FPR128:$Rm)>;
def : Pat<(f64 (AArch64frsqrts (f64 FPR64:$Rn), (f64 FPR64:$Rm))),
          (FRSQRTS64 FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(v2f64 (AArch64frsqrts (v2f64 FPR128:$Rn), (v2f64 FPR128:$Rm))),
          (FRSQRTSv2f64 FPR128:$Rn, FPR128:$Rm)>;

// If an integer is about to be converted to a floating point value,
// just load it on the floating point unit.
// Here are the patterns for 8 and 16-bits to float.
// 8-bits -> float.
multiclass UIntToFPROLoadPat<ValueType DstTy, ValueType SrcTy,
                             SDPatternOperator loadop, Instruction UCVTF,
                             ROAddrMode ro, Instruction LDRW, Instruction LDRX,
                             SubRegIndex sub> {
  def : Pat<(DstTy (uint_to_fp (SrcTy
                     (loadop (ro.Wpat GPR64sp:$Rn, GPR32:$Rm,
                                      ro.Wext:$extend))))),
           (UCVTF (INSERT_SUBREG (DstTy (IMPLICIT_DEF)),
                                 (LDRW GPR64sp:$Rn, GPR32:$Rm, ro.Wext:$extend),
                                 sub))>;

  def : Pat<(DstTy (uint_to_fp (SrcTy
                     (loadop (ro.Xpat GPR64sp:$Rn, GPR64:$Rm,
                                      ro.Wext:$extend))))),
           (UCVTF (INSERT_SUBREG (DstTy (IMPLICIT_DEF)),
                                 (LDRX GPR64sp:$Rn, GPR64:$Rm, ro.Xext:$extend),
                                 sub))>;
}

defm : UIntToFPROLoadPat<f32, i32, zextloadi8,
                         UCVTFv1i32, ro8, LDRBroW, LDRBroX, bsub>;
def : Pat <(f32 (uint_to_fp (i32
               (zextloadi8 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))))),
           (UCVTFv1i32 (INSERT_SUBREG (f32 (IMPLICIT_DEF)),
                          (LDRBui GPR64sp:$Rn, uimm12s1:$offset), bsub))>;
def : Pat <(f32 (uint_to_fp (i32
                     (zextloadi8 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))))),
           (UCVTFv1i32 (INSERT_SUBREG (f32 (IMPLICIT_DEF)),
                          (LDURBi GPR64sp:$Rn, simm9:$offset), bsub))>;
// 16-bits -> float.
defm : UIntToFPROLoadPat<f32, i32, zextloadi16,
                         UCVTFv1i32, ro16, LDRHroW, LDRHroX, hsub>;
def : Pat <(f32 (uint_to_fp (i32
                  (zextloadi16 (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset))))),
           (UCVTFv1i32 (INSERT_SUBREG (f32 (IMPLICIT_DEF)),
                          (LDRHui GPR64sp:$Rn, uimm12s2:$offset), hsub))>;
def : Pat <(f32 (uint_to_fp (i32
                  (zextloadi16 (am_unscaled16 GPR64sp:$Rn, simm9:$offset))))),
           (UCVTFv1i32 (INSERT_SUBREG (f32 (IMPLICIT_DEF)),
                          (LDURHi GPR64sp:$Rn, simm9:$offset), hsub))>;
// 32-bits are handled in target specific dag combine:
// performIntToFpCombine.
// 64-bits integer to 32-bits floating point, not possible with
// UCVTF on floating point registers (both source and destination
// must have the same size).

// Here are the patterns for 8, 16, 32, and 64-bits to double.
// 8-bits -> double.
defm : UIntToFPROLoadPat<f64, i32, zextloadi8,
                         UCVTFv1i64, ro8, LDRBroW, LDRBroX, bsub>;
def : Pat <(f64 (uint_to_fp (i32
                    (zextloadi8 (am_indexed8 GPR64sp:$Rn, uimm12s1:$offset))))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDRBui GPR64sp:$Rn, uimm12s1:$offset), bsub))>;
def : Pat <(f64 (uint_to_fp (i32
                  (zextloadi8 (am_unscaled8 GPR64sp:$Rn, simm9:$offset))))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDURBi GPR64sp:$Rn, simm9:$offset), bsub))>;
// 16-bits -> double.
defm : UIntToFPROLoadPat<f64, i32, zextloadi16,
                         UCVTFv1i64, ro16, LDRHroW, LDRHroX, hsub>;
def : Pat <(f64 (uint_to_fp (i32
                  (zextloadi16 (am_indexed16 GPR64sp:$Rn, uimm12s2:$offset))))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDRHui GPR64sp:$Rn, uimm12s2:$offset), hsub))>;
def : Pat <(f64 (uint_to_fp (i32
                  (zextloadi16 (am_unscaled16 GPR64sp:$Rn, simm9:$offset))))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDURHi GPR64sp:$Rn, simm9:$offset), hsub))>;
// 32-bits -> double.
defm : UIntToFPROLoadPat<f64, i32, load,
                         UCVTFv1i64, ro32, LDRSroW, LDRSroX, ssub>;
def : Pat <(f64 (uint_to_fp (i32
                  (load (am_indexed32 GPR64sp:$Rn, uimm12s4:$offset))))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDRSui GPR64sp:$Rn, uimm12s4:$offset), ssub))>;
def : Pat <(f64 (uint_to_fp (i32
                  (load (am_unscaled32 GPR64sp:$Rn, simm9:$offset))))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDURSi GPR64sp:$Rn, simm9:$offset), ssub))>;
// 64-bits -> double are handled in target specific dag combine:
// performIntToFpCombine.

//===----------------------------------------------------------------------===//
// Advanced SIMD three different-sized vector instructions.
//===----------------------------------------------------------------------===//

defm ADDHN  : SIMDNarrowThreeVectorBHS<0,0b0100,"addhn", int_aarch64_neon_addhn>;
defm SUBHN  : SIMDNarrowThreeVectorBHS<0,0b0110,"subhn", int_aarch64_neon_subhn>;
defm RADDHN : SIMDNarrowThreeVectorBHS<1,0b0100,"raddhn",int_aarch64_neon_raddhn>;
defm RSUBHN : SIMDNarrowThreeVectorBHS<1,0b0110,"rsubhn",int_aarch64_neon_rsubhn>;
defm PMULL  : SIMDDifferentThreeVectorBD<0,0b1110,"pmull",int_aarch64_neon_pmull>;
defm SABAL  : SIMDLongThreeVectorTiedBHSabal<0,0b0101,"sabal",
                                             int_aarch64_neon_sabd>;
defm SABDL   : SIMDLongThreeVectorBHSabdl<0, 0b0111, "sabdl",
                                          int_aarch64_neon_sabd>;
defm SADDL   : SIMDLongThreeVectorBHS<   0, 0b0000, "saddl",
            BinOpFrag<(add (sext node:$LHS), (sext node:$RHS))>>;
defm SADDW   : SIMDWideThreeVectorBHS<   0, 0b0001, "saddw",
                 BinOpFrag<(add node:$LHS, (sext node:$RHS))>>;
defm SMLAL   : SIMDLongThreeVectorTiedBHS<0, 0b1000, "smlal",
    TriOpFrag<(add node:$LHS, (int_aarch64_neon_smull node:$MHS, node:$RHS))>>;
defm SMLSL   : SIMDLongThreeVectorTiedBHS<0, 0b1010, "smlsl",
    TriOpFrag<(sub node:$LHS, (int_aarch64_neon_smull node:$MHS, node:$RHS))>>;
defm SMULL   : SIMDLongThreeVectorBHS<0, 0b1100, "smull", int_aarch64_neon_smull>;
defm SQDMLAL : SIMDLongThreeVectorSQDMLXTiedHS<0, 0b1001, "sqdmlal",
                                               int_aarch64_neon_sqadd>;
defm SQDMLSL : SIMDLongThreeVectorSQDMLXTiedHS<0, 0b1011, "sqdmlsl",
                                               int_aarch64_neon_sqsub>;
defm SQDMULL : SIMDLongThreeVectorHS<0, 0b1101, "sqdmull",
                                     int_aarch64_neon_sqdmull>;
defm SSUBL   : SIMDLongThreeVectorBHS<0, 0b0010, "ssubl",
                 BinOpFrag<(sub (sext node:$LHS), (sext node:$RHS))>>;
defm SSUBW   : SIMDWideThreeVectorBHS<0, 0b0011, "ssubw",
                 BinOpFrag<(sub node:$LHS, (sext node:$RHS))>>;
defm UABAL   : SIMDLongThreeVectorTiedBHSabal<1, 0b0101, "uabal",
                                              int_aarch64_neon_uabd>;
defm UADDL   : SIMDLongThreeVectorBHS<1, 0b0000, "uaddl",
                 BinOpFrag<(add (zext node:$LHS), (zext node:$RHS))>>;
defm UADDW   : SIMDWideThreeVectorBHS<1, 0b0001, "uaddw",
                 BinOpFrag<(add node:$LHS, (zext node:$RHS))>>;
defm UMLAL   : SIMDLongThreeVectorTiedBHS<1, 0b1000, "umlal",
    TriOpFrag<(add node:$LHS, (int_aarch64_neon_umull node:$MHS, node:$RHS))>>;
defm UMLSL   : SIMDLongThreeVectorTiedBHS<1, 0b1010, "umlsl",
    TriOpFrag<(sub node:$LHS, (int_aarch64_neon_umull node:$MHS, node:$RHS))>>;
defm UMULL   : SIMDLongThreeVectorBHS<1, 0b1100, "umull", int_aarch64_neon_umull>;
defm USUBL   : SIMDLongThreeVectorBHS<1, 0b0010, "usubl",
                 BinOpFrag<(sub (zext node:$LHS), (zext node:$RHS))>>;
defm USUBW   : SIMDWideThreeVectorBHS<   1, 0b0011, "usubw",
                 BinOpFrag<(sub node:$LHS, (zext node:$RHS))>>;

// Additional patterns for SMULL and UMULL
multiclass Neon_mul_widen_patterns<SDPatternOperator opnode,
  Instruction INST8B, Instruction INST4H, Instruction INST2S> {
  def : Pat<(v8i16 (opnode (v8i8 V64:$Rn), (v8i8 V64:$Rm))),
            (INST8B V64:$Rn, V64:$Rm)>;
  def : Pat<(v4i32 (opnode (v4i16 V64:$Rn), (v4i16 V64:$Rm))),
            (INST4H V64:$Rn, V64:$Rm)>;
  def : Pat<(v2i64 (opnode (v2i32 V64:$Rn), (v2i32 V64:$Rm))),
            (INST2S V64:$Rn, V64:$Rm)>;
}

defm : Neon_mul_widen_patterns<AArch64smull, SMULLv8i8_v8i16,
  SMULLv4i16_v4i32, SMULLv2i32_v2i64>;
defm : Neon_mul_widen_patterns<AArch64umull, UMULLv8i8_v8i16,
  UMULLv4i16_v4i32, UMULLv2i32_v2i64>;

// Patterns for smull2/umull2.
multiclass Neon_mul_high_patterns<SDPatternOperator opnode,
  Instruction INST8B, Instruction INST4H, Instruction INST2S> {
  def : Pat<(v8i16 (opnode (extract_high_v16i8 V128:$Rn),
                           (extract_high_v16i8 V128:$Rm))),
             (INST8B V128:$Rn, V128:$Rm)>;
  def : Pat<(v4i32 (opnode (extract_high_v8i16 V128:$Rn),
                           (extract_high_v8i16 V128:$Rm))),
             (INST4H V128:$Rn, V128:$Rm)>;
  def : Pat<(v2i64 (opnode (extract_high_v4i32 V128:$Rn),
                           (extract_high_v4i32 V128:$Rm))),
             (INST2S V128:$Rn, V128:$Rm)>;
}

defm : Neon_mul_high_patterns<AArch64smull, SMULLv16i8_v8i16,
  SMULLv8i16_v4i32, SMULLv4i32_v2i64>;
defm : Neon_mul_high_patterns<AArch64umull, UMULLv16i8_v8i16,
  UMULLv8i16_v4i32, UMULLv4i32_v2i64>;

// Additional patterns for SMLAL/SMLSL and UMLAL/UMLSL
multiclass Neon_mulacc_widen_patterns<SDPatternOperator opnode,
  Instruction INST8B, Instruction INST4H, Instruction INST2S> {
  def : Pat<(v8i16 (opnode (v8i16 V128:$Rd), (v8i8 V64:$Rn), (v8i8 V64:$Rm))),
            (INST8B V128:$Rd, V64:$Rn, V64:$Rm)>;
  def : Pat<(v4i32 (opnode (v4i32 V128:$Rd), (v4i16 V64:$Rn), (v4i16 V64:$Rm))),
            (INST4H V128:$Rd, V64:$Rn, V64:$Rm)>;
  def : Pat<(v2i64 (opnode (v2i64 V128:$Rd), (v2i32 V64:$Rn), (v2i32 V64:$Rm))),
            (INST2S  V128:$Rd, V64:$Rn, V64:$Rm)>;
}

defm : Neon_mulacc_widen_patterns<
  TriOpFrag<(add node:$LHS, (AArch64smull node:$MHS, node:$RHS))>,
  SMLALv8i8_v8i16, SMLALv4i16_v4i32, SMLALv2i32_v2i64>;
defm : Neon_mulacc_widen_patterns<
  TriOpFrag<(add node:$LHS, (AArch64umull node:$MHS, node:$RHS))>,
  UMLALv8i8_v8i16, UMLALv4i16_v4i32, UMLALv2i32_v2i64>;
defm : Neon_mulacc_widen_patterns<
  TriOpFrag<(sub node:$LHS, (AArch64smull node:$MHS, node:$RHS))>,
  SMLSLv8i8_v8i16, SMLSLv4i16_v4i32, SMLSLv2i32_v2i64>;
defm : Neon_mulacc_widen_patterns<
  TriOpFrag<(sub node:$LHS, (AArch64umull node:$MHS, node:$RHS))>,
  UMLSLv8i8_v8i16, UMLSLv4i16_v4i32, UMLSLv2i32_v2i64>;

// Patterns for 64-bit pmull
def : Pat<(int_aarch64_neon_pmull64 V64:$Rn, V64:$Rm),
          (PMULLv1i64 V64:$Rn, V64:$Rm)>;
def : Pat<(int_aarch64_neon_pmull64 (extractelt (v2i64 V128:$Rn), (i64 1)),
                                    (extractelt (v2i64 V128:$Rm), (i64 1))),
          (PMULLv2i64 V128:$Rn, V128:$Rm)>;

// CodeGen patterns for addhn and subhn instructions, which can actually be
// written in LLVM IR without too much difficulty.

// ADDHN
def : Pat<(v8i8 (trunc (v8i16 (AArch64vlshr (add V128:$Rn, V128:$Rm), (i32 8))))),
          (ADDHNv8i16_v8i8 V128:$Rn, V128:$Rm)>;
def : Pat<(v4i16 (trunc (v4i32 (AArch64vlshr (add V128:$Rn, V128:$Rm),
                                           (i32 16))))),
          (ADDHNv4i32_v4i16 V128:$Rn, V128:$Rm)>;
def : Pat<(v2i32 (trunc (v2i64 (AArch64vlshr (add V128:$Rn, V128:$Rm),
                                           (i32 32))))),
          (ADDHNv2i64_v2i32 V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v8i8 V64:$Rd),
                          (trunc (v8i16 (AArch64vlshr (add V128:$Rn, V128:$Rm),
                                                    (i32 8))))),
          (ADDHNv8i16_v16i8 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v4i16 V64:$Rd),
                          (trunc (v4i32 (AArch64vlshr (add V128:$Rn, V128:$Rm),
                                                    (i32 16))))),
          (ADDHNv4i32_v8i16 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v2i32 V64:$Rd),
                          (trunc (v2i64 (AArch64vlshr (add V128:$Rn, V128:$Rm),
                                                    (i32 32))))),
          (ADDHNv2i64_v4i32 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;

// SUBHN
def : Pat<(v8i8 (trunc (v8i16 (AArch64vlshr (sub V128:$Rn, V128:$Rm), (i32 8))))),
          (SUBHNv8i16_v8i8 V128:$Rn, V128:$Rm)>;
def : Pat<(v4i16 (trunc (v4i32 (AArch64vlshr (sub V128:$Rn, V128:$Rm),
                                           (i32 16))))),
          (SUBHNv4i32_v4i16 V128:$Rn, V128:$Rm)>;
def : Pat<(v2i32 (trunc (v2i64 (AArch64vlshr (sub V128:$Rn, V128:$Rm),
                                           (i32 32))))),
          (SUBHNv2i64_v2i32 V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v8i8 V64:$Rd),
                          (trunc (v8i16 (AArch64vlshr (sub V128:$Rn, V128:$Rm),
                                                    (i32 8))))),
          (SUBHNv8i16_v16i8 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v4i16 V64:$Rd),
                          (trunc (v4i32 (AArch64vlshr (sub V128:$Rn, V128:$Rm),
                                                    (i32 16))))),
          (SUBHNv4i32_v8i16 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v2i32 V64:$Rd),
                          (trunc (v2i64 (AArch64vlshr (sub V128:$Rn, V128:$Rm),
                                                    (i32 32))))),
          (SUBHNv2i64_v4i32 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;

//----------------------------------------------------------------------------
// AdvSIMD bitwise extract from vector instruction.
//----------------------------------------------------------------------------

defm EXT : SIMDBitwiseExtract<"ext">;

def AdjustExtImm : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(8 + N->getZExtValue(), SDLoc(N), MVT::i32);
}]>;
multiclass ExtPat<ValueType VT64, ValueType VT128, int N> {
  def : Pat<(VT64 (AArch64ext V64:$Rn, V64:$Rm, (i32 imm:$imm))),
            (EXTv8i8 V64:$Rn, V64:$Rm, imm:$imm)>;
  def : Pat<(VT128 (AArch64ext V128:$Rn, V128:$Rm, (i32 imm:$imm))),
            (EXTv16i8 V128:$Rn, V128:$Rm, imm:$imm)>;
  // We use EXT to handle extract_subvector to copy the upper 64-bits of a
  // 128-bit vector.
  def : Pat<(VT64 (extract_subvector V128:$Rn, (i64 N))),
            (EXTRACT_SUBREG (EXTv16i8 V128:$Rn, V128:$Rn, 8), dsub)>;
  // A 64-bit EXT of two halves of the same 128-bit register can be done as a
  // single 128-bit EXT.
  def : Pat<(VT64 (AArch64ext (extract_subvector V128:$Rn, (i64 0)),
                              (extract_subvector V128:$Rn, (i64 N)),
                              (i32 imm:$imm))),
            (EXTRACT_SUBREG (EXTv16i8 V128:$Rn, V128:$Rn, imm:$imm), dsub)>;
  // A 64-bit EXT of the high half of a 128-bit register can be done using a
  // 128-bit EXT of the whole register with an adjustment to the immediate. The
  // top half of the other operand will be unset, but that doesn't matter as it
  // will not be used.
  def : Pat<(VT64 (AArch64ext (extract_subvector V128:$Rn, (i64 N)),
                              V64:$Rm,
                              (i32 imm:$imm))),
            (EXTRACT_SUBREG (EXTv16i8 V128:$Rn,
                                      (SUBREG_TO_REG (i32 0), V64:$Rm, dsub),
                                      (AdjustExtImm imm:$imm)), dsub)>;
}

defm : ExtPat<v8i8, v16i8, 8>;
defm : ExtPat<v4i16, v8i16, 4>;
defm : ExtPat<v4f16, v8f16, 4>;
defm : ExtPat<v4bf16, v8bf16, 4>;
defm : ExtPat<v2i32, v4i32, 2>;
defm : ExtPat<v2f32, v4f32, 2>;
defm : ExtPat<v1i64, v2i64, 1>;
defm : ExtPat<v1f64, v2f64, 1>;

//----------------------------------------------------------------------------
// AdvSIMD zip vector
//----------------------------------------------------------------------------

defm TRN1 : SIMDZipVector<0b010, "trn1", AArch64trn1>;
defm TRN2 : SIMDZipVector<0b110, "trn2", AArch64trn2>;
defm UZP1 : SIMDZipVector<0b001, "uzp1", AArch64uzp1>;
defm UZP2 : SIMDZipVector<0b101, "uzp2", AArch64uzp2>;
defm ZIP1 : SIMDZipVector<0b011, "zip1", AArch64zip1>;
defm ZIP2 : SIMDZipVector<0b111, "zip2", AArch64zip2>;

//----------------------------------------------------------------------------
// AdvSIMD TBL/TBX instructions
//----------------------------------------------------------------------------

defm TBL : SIMDTableLookup<    0, "tbl">;
defm TBX : SIMDTableLookupTied<1, "tbx">;

def : Pat<(v8i8 (int_aarch64_neon_tbl1 (v16i8 VecListOne128:$Rn), (v8i8 V64:$Ri))),
          (TBLv8i8One VecListOne128:$Rn, V64:$Ri)>;
def : Pat<(v16i8 (int_aarch64_neon_tbl1 (v16i8 V128:$Ri), (v16i8 V128:$Rn))),
          (TBLv16i8One V128:$Ri, V128:$Rn)>;

def : Pat<(v8i8 (int_aarch64_neon_tbx1 (v8i8 V64:$Rd),
                  (v16i8 VecListOne128:$Rn), (v8i8 V64:$Ri))),
          (TBXv8i8One V64:$Rd, VecListOne128:$Rn, V64:$Ri)>;
def : Pat<(v16i8 (int_aarch64_neon_tbx1 (v16i8 V128:$Rd),
                   (v16i8 V128:$Ri), (v16i8 V128:$Rn))),
          (TBXv16i8One V128:$Rd, V128:$Ri, V128:$Rn)>;


//----------------------------------------------------------------------------
// AdvSIMD scalar CPY instruction
//----------------------------------------------------------------------------

defm CPY : SIMDScalarCPY<"cpy">;

//----------------------------------------------------------------------------
// AdvSIMD scalar pairwise instructions
//----------------------------------------------------------------------------

defm ADDP    : SIMDPairwiseScalarD<0, 0b11011, "addp">;
defm FADDP   : SIMDFPPairwiseScalar<0, 0b01101, "faddp">;
defm FMAXNMP : SIMDFPPairwiseScalar<0, 0b01100, "fmaxnmp">;
defm FMAXP   : SIMDFPPairwiseScalar<0, 0b01111, "fmaxp">;
defm FMINNMP : SIMDFPPairwiseScalar<1, 0b01100, "fminnmp">;
defm FMINP   : SIMDFPPairwiseScalar<1, 0b01111, "fminp">;
def : Pat<(v2i64 (AArch64saddv V128:$Rn)),
          (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)), (ADDPv2i64p V128:$Rn), dsub)>;
def : Pat<(v2i64 (AArch64uaddv V128:$Rn)),
          (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)), (ADDPv2i64p V128:$Rn), dsub)>;
def : Pat<(f32 (int_aarch64_neon_faddv (v2f32 V64:$Rn))),
          (FADDPv2i32p V64:$Rn)>;
def : Pat<(f32 (int_aarch64_neon_faddv (v4f32 V128:$Rn))),
          (FADDPv2i32p (EXTRACT_SUBREG (FADDPv4f32 V128:$Rn, V128:$Rn), dsub))>;
def : Pat<(f64 (int_aarch64_neon_faddv (v2f64 V128:$Rn))),
          (FADDPv2i64p V128:$Rn)>;
def : Pat<(f32 (int_aarch64_neon_fmaxnmv (v2f32 V64:$Rn))),
          (FMAXNMPv2i32p V64:$Rn)>;
def : Pat<(f64 (int_aarch64_neon_fmaxnmv (v2f64 V128:$Rn))),
          (FMAXNMPv2i64p V128:$Rn)>;
def : Pat<(f32 (int_aarch64_neon_fmaxv (v2f32 V64:$Rn))),
          (FMAXPv2i32p V64:$Rn)>;
def : Pat<(f64 (int_aarch64_neon_fmaxv (v2f64 V128:$Rn))),
          (FMAXPv2i64p V128:$Rn)>;
def : Pat<(f32 (int_aarch64_neon_fminnmv (v2f32 V64:$Rn))),
          (FMINNMPv2i32p V64:$Rn)>;
def : Pat<(f64 (int_aarch64_neon_fminnmv (v2f64 V128:$Rn))),
          (FMINNMPv2i64p V128:$Rn)>;
def : Pat<(f32 (int_aarch64_neon_fminv (v2f32 V64:$Rn))),
          (FMINPv2i32p V64:$Rn)>;
def : Pat<(f64 (int_aarch64_neon_fminv (v2f64 V128:$Rn))),
          (FMINPv2i64p V128:$Rn)>;

//----------------------------------------------------------------------------
// AdvSIMD INS/DUP instructions
//----------------------------------------------------------------------------

def DUPv8i8gpr  : SIMDDupFromMain<0, {?,?,?,?,1}, ".8b", v8i8, V64, GPR32>;
def DUPv16i8gpr : SIMDDupFromMain<1, {?,?,?,?,1}, ".16b", v16i8, V128, GPR32>;
def DUPv4i16gpr : SIMDDupFromMain<0, {?,?,?,1,0}, ".4h", v4i16, V64, GPR32>;
def DUPv8i16gpr : SIMDDupFromMain<1, {?,?,?,1,0}, ".8h", v8i16, V128, GPR32>;
def DUPv2i32gpr : SIMDDupFromMain<0, {?,?,1,0,0}, ".2s", v2i32, V64, GPR32>;
def DUPv4i32gpr : SIMDDupFromMain<1, {?,?,1,0,0}, ".4s", v4i32, V128, GPR32>;
def DUPv2i64gpr : SIMDDupFromMain<1, {?,1,0,0,0}, ".2d", v2i64, V128, GPR64>;

def DUPv2i64lane : SIMDDup64FromElement;
def DUPv2i32lane : SIMDDup32FromElement<0, ".2s", v2i32, V64>;
def DUPv4i32lane : SIMDDup32FromElement<1, ".4s", v4i32, V128>;
def DUPv4i16lane : SIMDDup16FromElement<0, ".4h", v4i16, V64>;
def DUPv8i16lane : SIMDDup16FromElement<1, ".8h", v8i16, V128>;
def DUPv8i8lane  : SIMDDup8FromElement <0, ".8b", v8i8, V64>;
def DUPv16i8lane : SIMDDup8FromElement <1, ".16b", v16i8, V128>;

// DUP from a 64-bit register to a 64-bit register is just a copy
def : Pat<(v1i64 (AArch64dup (i64 GPR64:$Rn))),
          (COPY_TO_REGCLASS GPR64:$Rn, FPR64)>;
def : Pat<(v1f64 (AArch64dup (f64 FPR64:$Rn))),
          (COPY_TO_REGCLASS FPR64:$Rn, FPR64)>;

def : Pat<(v2f32 (AArch64dup (f32 FPR32:$Rn))),
          (v2f32 (DUPv2i32lane
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR32:$Rn, ssub),
            (i64 0)))>;
def : Pat<(v4f32 (AArch64dup (f32 FPR32:$Rn))),
          (v4f32 (DUPv4i32lane
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR32:$Rn, ssub),
            (i64 0)))>;
def : Pat<(v2f64 (AArch64dup (f64 FPR64:$Rn))),
          (v2f64 (DUPv2i64lane
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR64:$Rn, dsub),
            (i64 0)))>;
def : Pat<(v4f16 (AArch64dup (f16 FPR16:$Rn))),
          (v4f16 (DUPv4i16lane
            (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)), FPR16:$Rn, hsub),
            (i64 0)))>;
def : Pat<(v4bf16 (AArch64dup (bf16 FPR16:$Rn))),
          (v4bf16 (DUPv4i16lane
            (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)), FPR16:$Rn, hsub),
            (i64 0)))>;
def : Pat<(v8f16 (AArch64dup (f16 FPR16:$Rn))),
          (v8f16 (DUPv8i16lane
            (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)), FPR16:$Rn, hsub),
            (i64 0)))>;
def : Pat<(v8bf16 (AArch64dup (bf16 FPR16:$Rn))),
          (v8bf16 (DUPv8i16lane
            (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)), FPR16:$Rn, hsub),
            (i64 0)))>;

def : Pat<(v4f16 (AArch64duplane16 (v8f16 V128:$Rn), VectorIndexH:$imm)),
          (DUPv4i16lane V128:$Rn, VectorIndexH:$imm)>;
def : Pat<(v8f16 (AArch64duplane16 (v8f16 V128:$Rn), VectorIndexH:$imm)),
          (DUPv8i16lane V128:$Rn, VectorIndexH:$imm)>;

def : Pat<(v4bf16 (AArch64duplane16 (v8bf16 V128:$Rn), VectorIndexH:$imm)),
          (DUPv4i16lane V128:$Rn, VectorIndexH:$imm)>;
def : Pat<(v8bf16 (AArch64duplane16 (v8bf16 V128:$Rn), VectorIndexH:$imm)),
          (DUPv8i16lane V128:$Rn, VectorIndexH:$imm)>;

def : Pat<(v2f32 (AArch64duplane32 (v4f32 V128:$Rn), VectorIndexS:$imm)),
          (DUPv2i32lane V128:$Rn, VectorIndexS:$imm)>;
def : Pat<(v4f32 (AArch64duplane32 (v4f32 V128:$Rn), VectorIndexS:$imm)),
         (DUPv4i32lane V128:$Rn, VectorIndexS:$imm)>;
def : Pat<(v2f64 (AArch64duplane64 (v2f64 V128:$Rn), VectorIndexD:$imm)),
          (DUPv2i64lane V128:$Rn, VectorIndexD:$imm)>;

// If there's an (AArch64dup (vector_extract ...) ...), we can use a duplane
// instruction even if the types don't match: we just have to remap the lane
// carefully. N.b. this trick only applies to truncations.
def VecIndex_x2 : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(2 * N->getZExtValue(), SDLoc(N), MVT::i64);
}]>;
def VecIndex_x4 : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(4 * N->getZExtValue(), SDLoc(N), MVT::i64);
}]>;
def VecIndex_x8 : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(8 * N->getZExtValue(), SDLoc(N), MVT::i64);
}]>;

multiclass DUPWithTruncPats<ValueType ResVT, ValueType Src64VT,
                            ValueType Src128VT, ValueType ScalVT,
                            Instruction DUP, SDNodeXForm IdxXFORM> {
  def : Pat<(ResVT (AArch64dup (ScalVT (vector_extract (Src128VT V128:$Rn),
                                                     imm:$idx)))),
            (DUP V128:$Rn, (IdxXFORM imm:$idx))>;

  def : Pat<(ResVT (AArch64dup (ScalVT (vector_extract (Src64VT V64:$Rn),
                                                     imm:$idx)))),
            (DUP (SUBREG_TO_REG (i64 0), V64:$Rn, dsub), (IdxXFORM imm:$idx))>;
}

defm : DUPWithTruncPats<v8i8,   v4i16, v8i16, i32, DUPv8i8lane,  VecIndex_x2>;
defm : DUPWithTruncPats<v8i8,   v2i32, v4i32, i32, DUPv8i8lane,  VecIndex_x4>;
defm : DUPWithTruncPats<v4i16,  v2i32, v4i32, i32, DUPv4i16lane, VecIndex_x2>;

defm : DUPWithTruncPats<v16i8,  v4i16, v8i16, i32, DUPv16i8lane, VecIndex_x2>;
defm : DUPWithTruncPats<v16i8,  v2i32, v4i32, i32, DUPv16i8lane, VecIndex_x4>;
defm : DUPWithTruncPats<v8i16,  v2i32, v4i32, i32, DUPv8i16lane, VecIndex_x2>;

multiclass DUPWithTrunci64Pats<ValueType ResVT, Instruction DUP,
                               SDNodeXForm IdxXFORM> {
  def : Pat<(ResVT (AArch64dup (i32 (trunc (extractelt (v2i64 V128:$Rn),
                                                         imm:$idx))))),
            (DUP V128:$Rn, (IdxXFORM imm:$idx))>;

  def : Pat<(ResVT (AArch64dup (i32 (trunc (extractelt (v1i64 V64:$Rn),
                                                       imm:$idx))))),
            (DUP (SUBREG_TO_REG (i64 0), V64:$Rn, dsub), (IdxXFORM imm:$idx))>;
}

defm : DUPWithTrunci64Pats<v8i8,  DUPv8i8lane,   VecIndex_x8>;
defm : DUPWithTrunci64Pats<v4i16, DUPv4i16lane,  VecIndex_x4>;
defm : DUPWithTrunci64Pats<v2i32, DUPv2i32lane,  VecIndex_x2>;

defm : DUPWithTrunci64Pats<v16i8, DUPv16i8lane, VecIndex_x8>;
defm : DUPWithTrunci64Pats<v8i16, DUPv8i16lane, VecIndex_x4>;
defm : DUPWithTrunci64Pats<v4i32, DUPv4i32lane, VecIndex_x2>;

// SMOV and UMOV definitions, with some extra patterns for convenience
defm SMOV : SMov;
defm UMOV : UMov;

def : Pat<(sext_inreg (vector_extract (v16i8 V128:$Rn), VectorIndexB:$idx), i8),
          (i32 (SMOVvi8to32 V128:$Rn, VectorIndexB:$idx))>;
def : Pat<(sext_inreg (vector_extract (v16i8 V128:$Rn), VectorIndexB:$idx), i8),
          (i64 (SMOVvi8to64 V128:$Rn, VectorIndexB:$idx))>;
def : Pat<(sext_inreg (vector_extract (v8i16 V128:$Rn), VectorIndexH:$idx),i16),
          (i32 (SMOVvi16to32 V128:$Rn, VectorIndexH:$idx))>;
def : Pat<(sext_inreg (vector_extract (v8i16 V128:$Rn), VectorIndexH:$idx),i16),
          (i64 (SMOVvi16to64 V128:$Rn, VectorIndexH:$idx))>;
def : Pat<(sext_inreg (vector_extract (v8i16 V128:$Rn), VectorIndexH:$idx),i16),
          (i32 (SMOVvi16to32 V128:$Rn, VectorIndexH:$idx))>;
def : Pat<(sext (i32 (vector_extract (v4i32 V128:$Rn), VectorIndexS:$idx))),
          (i64 (SMOVvi32to64 V128:$Rn, VectorIndexS:$idx))>;

def : Pat<(sext_inreg (i64 (anyext (i32 (vector_extract (v16i8 V128:$Rn),
            VectorIndexB:$idx)))), i8),
          (i64 (SMOVvi8to64 V128:$Rn, VectorIndexB:$idx))>;
def : Pat<(sext_inreg (i64 (anyext (i32 (vector_extract (v8i16 V128:$Rn),
            VectorIndexH:$idx)))), i16),
          (i64 (SMOVvi16to64 V128:$Rn, VectorIndexH:$idx))>;

// Extracting i8 or i16 elements will have the zero-extend transformed to
// an 'and' mask by type legalization since neither i8 nor i16 are legal types
// for AArch64. Match these patterns here since UMOV already zeroes out the high
// bits of the destination register.
def : Pat<(and (vector_extract (v16i8 V128:$Rn), VectorIndexB:$idx),
               (i32 0xff)),
          (i32 (UMOVvi8 V128:$Rn, VectorIndexB:$idx))>;
def : Pat<(and (vector_extract (v8i16 V128:$Rn), VectorIndexH:$idx),
               (i32 0xffff)),
          (i32 (UMOVvi16 V128:$Rn, VectorIndexH:$idx))>;

defm INS : SIMDIns;

def : Pat<(v16i8 (scalar_to_vector GPR32:$Rn)),
          (SUBREG_TO_REG (i32 0),
                         (f32 (COPY_TO_REGCLASS GPR32:$Rn, FPR32)), ssub)>;
def : Pat<(v8i8 (scalar_to_vector GPR32:$Rn)),
          (SUBREG_TO_REG (i32 0),
                         (f32 (COPY_TO_REGCLASS GPR32:$Rn, FPR32)), ssub)>;

def : Pat<(v8i16 (scalar_to_vector GPR32:$Rn)),
          (SUBREG_TO_REG (i32 0),
                         (f32 (COPY_TO_REGCLASS GPR32:$Rn, FPR32)), ssub)>;
def : Pat<(v4i16 (scalar_to_vector GPR32:$Rn)),
          (SUBREG_TO_REG (i32 0),
                         (f32 (COPY_TO_REGCLASS GPR32:$Rn, FPR32)), ssub)>;

def : Pat<(v4f16 (scalar_to_vector (f16 FPR16:$Rn))),
          (INSERT_SUBREG (v4f16 (IMPLICIT_DEF)), FPR16:$Rn, hsub)>;
def : Pat<(v8f16 (scalar_to_vector (f16 FPR16:$Rn))),
          (INSERT_SUBREG (v8f16 (IMPLICIT_DEF)), FPR16:$Rn, hsub)>;

def : Pat<(v4bf16 (scalar_to_vector (bf16 FPR16:$Rn))),
          (INSERT_SUBREG (v4bf16 (IMPLICIT_DEF)), FPR16:$Rn, hsub)>;
def : Pat<(v8bf16 (scalar_to_vector (bf16 FPR16:$Rn))),
          (INSERT_SUBREG (v8bf16 (IMPLICIT_DEF)), FPR16:$Rn, hsub)>;

def : Pat<(v2i32 (scalar_to_vector (i32 FPR32:$Rn))),
            (v2i32 (INSERT_SUBREG (v2i32 (IMPLICIT_DEF)),
                                  (i32 FPR32:$Rn), ssub))>;
def : Pat<(v4i32 (scalar_to_vector (i32 FPR32:$Rn))),
            (v4i32 (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)),
                                  (i32 FPR32:$Rn), ssub))>;

def : Pat<(v2i64 (scalar_to_vector (i64 FPR64:$Rn))),
            (v2i64 (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)),
                                  (i64 FPR64:$Rn), dsub))>;

def : Pat<(v4f16 (scalar_to_vector (f16 FPR16:$Rn))),
          (INSERT_SUBREG (v4f16 (IMPLICIT_DEF)), FPR16:$Rn, hsub)>;
def : Pat<(v8f16 (scalar_to_vector (f16 FPR16:$Rn))),
          (INSERT_SUBREG (v8f16 (IMPLICIT_DEF)), FPR16:$Rn, hsub)>;

def : Pat<(v4bf16 (scalar_to_vector (bf16 FPR16:$Rn))),
          (INSERT_SUBREG (v4bf16 (IMPLICIT_DEF)), FPR16:$Rn, hsub)>;
def : Pat<(v8bf16 (scalar_to_vector (bf16 FPR16:$Rn))),
          (INSERT_SUBREG (v8bf16 (IMPLICIT_DEF)), FPR16:$Rn, hsub)>;

def : Pat<(v4f32 (scalar_to_vector (f32 FPR32:$Rn))),
          (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), FPR32:$Rn, ssub)>;
def : Pat<(v2f32 (scalar_to_vector (f32 FPR32:$Rn))),
          (INSERT_SUBREG (v2f32 (IMPLICIT_DEF)), FPR32:$Rn, ssub)>;

def : Pat<(v2f64 (scalar_to_vector (f64 FPR64:$Rn))),
          (INSERT_SUBREG (v2f64 (IMPLICIT_DEF)), FPR64:$Rn, dsub)>;

def : Pat<(v4f16 (vector_insert (v4f16 V64:$Rn),
            (f16 FPR16:$Rm), (i64 VectorIndexS:$imm))),
          (EXTRACT_SUBREG
            (INSvi16lane
              (v8f16 (INSERT_SUBREG (v8f16 (IMPLICIT_DEF)), V64:$Rn, dsub)),
              VectorIndexS:$imm,
              (v8f16 (INSERT_SUBREG (v8f16 (IMPLICIT_DEF)), FPR16:$Rm, hsub)),
              (i64 0)),
            dsub)>;

def : Pat<(v8f16 (vector_insert (v8f16 V128:$Rn),
            (f16 FPR16:$Rm), (i64 VectorIndexH:$imm))),
          (INSvi16lane
            V128:$Rn, VectorIndexH:$imm,
            (v8f16 (INSERT_SUBREG (v8f16 (IMPLICIT_DEF)), FPR16:$Rm, hsub)),
            (i64 0))>;

def : Pat<(v4bf16 (vector_insert (v4bf16 V64:$Rn),
            (bf16 FPR16:$Rm), (i64 VectorIndexS:$imm))),
          (EXTRACT_SUBREG
            (INSvi16lane
              (v8bf16 (INSERT_SUBREG (v8bf16 (IMPLICIT_DEF)), V64:$Rn, dsub)),
              VectorIndexS:$imm,
              (v8bf16 (INSERT_SUBREG (v8bf16 (IMPLICIT_DEF)), FPR16:$Rm, hsub)),
              (i64 0)),
            dsub)>;

def : Pat<(v8bf16 (vector_insert (v8bf16 V128:$Rn),
            (bf16 FPR16:$Rm), (i64 VectorIndexH:$imm))),
          (INSvi16lane
            V128:$Rn, VectorIndexH:$imm,
            (v8bf16 (INSERT_SUBREG (v8bf16 (IMPLICIT_DEF)), FPR16:$Rm, hsub)),
            (i64 0))>;

def : Pat<(v2f32 (vector_insert (v2f32 V64:$Rn),
            (f32 FPR32:$Rm), (i64 VectorIndexS:$imm))),
          (EXTRACT_SUBREG
            (INSvi32lane
              (v4f32 (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), V64:$Rn, dsub)),
              VectorIndexS:$imm,
              (v4f32 (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), FPR32:$Rm, ssub)),
              (i64 0)),
            dsub)>;
def : Pat<(v4f32 (vector_insert (v4f32 V128:$Rn),
            (f32 FPR32:$Rm), (i64 VectorIndexS:$imm))),
          (INSvi32lane
            V128:$Rn, VectorIndexS:$imm,
            (v4f32 (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), FPR32:$Rm, ssub)),
            (i64 0))>;
def : Pat<(v2f64 (vector_insert (v2f64 V128:$Rn),
            (f64 FPR64:$Rm), (i64 VectorIndexD:$imm))),
          (INSvi64lane
            V128:$Rn, VectorIndexD:$imm,
            (v2f64 (INSERT_SUBREG (v2f64 (IMPLICIT_DEF)), FPR64:$Rm, dsub)),
            (i64 0))>;

// Copy an element at a constant index in one vector into a constant indexed
// element of another.
// FIXME refactor to a shared class/dev parameterized on vector type, vector
// index type and INS extension
def : Pat<(v16i8 (int_aarch64_neon_vcopy_lane
                   (v16i8 V128:$Vd), VectorIndexB:$idx, (v16i8 V128:$Vs),
                   VectorIndexB:$idx2)),
          (v16i8 (INSvi8lane
                   V128:$Vd, VectorIndexB:$idx, V128:$Vs, VectorIndexB:$idx2)
          )>;
def : Pat<(v8i16 (int_aarch64_neon_vcopy_lane
                   (v8i16 V128:$Vd), VectorIndexH:$idx, (v8i16 V128:$Vs),
                   VectorIndexH:$idx2)),
          (v8i16 (INSvi16lane
                   V128:$Vd, VectorIndexH:$idx, V128:$Vs, VectorIndexH:$idx2)
          )>;
def : Pat<(v4i32 (int_aarch64_neon_vcopy_lane
                   (v4i32 V128:$Vd), VectorIndexS:$idx, (v4i32 V128:$Vs),
                   VectorIndexS:$idx2)),
          (v4i32 (INSvi32lane
                   V128:$Vd, VectorIndexS:$idx, V128:$Vs, VectorIndexS:$idx2)
          )>;
def : Pat<(v2i64 (int_aarch64_neon_vcopy_lane
                   (v2i64 V128:$Vd), VectorIndexD:$idx, (v2i64 V128:$Vs),
                   VectorIndexD:$idx2)),
          (v2i64 (INSvi64lane
                   V128:$Vd, VectorIndexD:$idx, V128:$Vs, VectorIndexD:$idx2)
          )>;

multiclass Neon_INS_elt_pattern<ValueType VT128, ValueType VT64,
                                ValueType VTScal, Instruction INS> {
  def : Pat<(VT128 (vector_insert V128:$src,
                        (VTScal (vector_extract (VT128 V128:$Rn), imm:$Immn)),
                        imm:$Immd)),
            (INS V128:$src, imm:$Immd, V128:$Rn, imm:$Immn)>;

  def : Pat<(VT128 (vector_insert V128:$src,
                        (VTScal (vector_extract (VT64 V64:$Rn), imm:$Immn)),
                        imm:$Immd)),
            (INS V128:$src, imm:$Immd,
                 (SUBREG_TO_REG (i64 0), V64:$Rn, dsub), imm:$Immn)>;

  def : Pat<(VT64 (vector_insert V64:$src,
                        (VTScal (vector_extract (VT128 V128:$Rn), imm:$Immn)),
                        imm:$Immd)),
            (EXTRACT_SUBREG (INS (SUBREG_TO_REG (i64 0), V64:$src, dsub),
                                 imm:$Immd, V128:$Rn, imm:$Immn),
                            dsub)>;

  def : Pat<(VT64 (vector_insert V64:$src,
                        (VTScal (vector_extract (VT64 V64:$Rn), imm:$Immn)),
                        imm:$Immd)),
            (EXTRACT_SUBREG
                (INS (SUBREG_TO_REG (i64 0), V64:$src, dsub), imm:$Immd,
                     (SUBREG_TO_REG (i64 0), V64:$Rn, dsub), imm:$Immn),
                dsub)>;
}

defm : Neon_INS_elt_pattern<v8f16, v4f16, f16, INSvi16lane>;
defm : Neon_INS_elt_pattern<v8bf16, v4bf16, bf16, INSvi16lane>;
defm : Neon_INS_elt_pattern<v4f32, v2f32, f32, INSvi32lane>;
defm : Neon_INS_elt_pattern<v2f64, v1f64, f64, INSvi64lane>;


// Floating point vector extractions are codegen'd as either a sequence of
// subregister extractions, or a MOV (aka CPY here, alias for DUP) if
// the lane number is anything other than zero.
def : Pat<(vector_extract (v2f64 V128:$Rn), 0),
          (f64 (EXTRACT_SUBREG V128:$Rn, dsub))>;
def : Pat<(vector_extract (v4f32 V128:$Rn), 0),
          (f32 (EXTRACT_SUBREG V128:$Rn, ssub))>;
def : Pat<(vector_extract (v8f16 V128:$Rn), 0),
          (f16 (EXTRACT_SUBREG V128:$Rn, hsub))>;
def : Pat<(vector_extract (v8bf16 V128:$Rn), 0),
          (bf16 (EXTRACT_SUBREG V128:$Rn, hsub))>;


def : Pat<(vector_extract (v2f64 V128:$Rn), VectorIndexD:$idx),
          (f64 (CPYi64 V128:$Rn, VectorIndexD:$idx))>;
def : Pat<(vector_extract (v4f32 V128:$Rn), VectorIndexS:$idx),
          (f32 (CPYi32 V128:$Rn, VectorIndexS:$idx))>;
def : Pat<(vector_extract (v8f16 V128:$Rn), VectorIndexH:$idx),
          (f16 (CPYi16 V128:$Rn, VectorIndexH:$idx))>;
def : Pat<(vector_extract (v8bf16 V128:$Rn), VectorIndexH:$idx),
          (bf16 (CPYi16 V128:$Rn, VectorIndexH:$idx))>;

// All concat_vectors operations are canonicalised to act on i64 vectors for
// AArch64. In the general case we need an instruction, which had just as well be
// INS.
class ConcatPat<ValueType DstTy, ValueType SrcTy>
  : Pat<(DstTy (concat_vectors (SrcTy V64:$Rd), V64:$Rn)),
        (INSvi64lane (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub), 1,
                     (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rn, dsub), 0)>;

def : ConcatPat<v2i64, v1i64>;
def : ConcatPat<v2f64, v1f64>;
def : ConcatPat<v4i32, v2i32>;
def : ConcatPat<v4f32, v2f32>;
def : ConcatPat<v8i16, v4i16>;
def : ConcatPat<v8f16, v4f16>;
def : ConcatPat<v8bf16, v4bf16>;
def : ConcatPat<v16i8, v8i8>;

// If the high lanes are undef, though, we can just ignore them:
class ConcatUndefPat<ValueType DstTy, ValueType SrcTy>
  : Pat<(DstTy (concat_vectors (SrcTy V64:$Rn), undef)),
        (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rn, dsub)>;

def : ConcatUndefPat<v2i64, v1i64>;
def : ConcatUndefPat<v2f64, v1f64>;
def : ConcatUndefPat<v4i32, v2i32>;
def : ConcatUndefPat<v4f32, v2f32>;
def : ConcatUndefPat<v8i16, v4i16>;
def : ConcatUndefPat<v16i8, v8i8>;

//----------------------------------------------------------------------------
// AdvSIMD across lanes instructions
//----------------------------------------------------------------------------

defm ADDV    : SIMDAcrossLanesBHS<0, 0b11011, "addv">;
defm SMAXV   : SIMDAcrossLanesBHS<0, 0b01010, "smaxv">;
defm SMINV   : SIMDAcrossLanesBHS<0, 0b11010, "sminv">;
defm UMAXV   : SIMDAcrossLanesBHS<1, 0b01010, "umaxv">;
defm UMINV   : SIMDAcrossLanesBHS<1, 0b11010, "uminv">;
defm SADDLV  : SIMDAcrossLanesHSD<0, 0b00011, "saddlv">;
defm UADDLV  : SIMDAcrossLanesHSD<1, 0b00011, "uaddlv">;
defm FMAXNMV : SIMDFPAcrossLanes<0b01100, 0, "fmaxnmv", int_aarch64_neon_fmaxnmv>;
defm FMAXV   : SIMDFPAcrossLanes<0b01111, 0, "fmaxv", int_aarch64_neon_fmaxv>;
defm FMINNMV : SIMDFPAcrossLanes<0b01100, 1, "fminnmv", int_aarch64_neon_fminnmv>;
defm FMINV   : SIMDFPAcrossLanes<0b01111, 1, "fminv", int_aarch64_neon_fminv>;

// Patterns for across-vector intrinsics, that have a node equivalent, that
// returns a vector (with only the low lane defined) instead of a scalar.
// In effect, opNode is the same as (scalar_to_vector (IntNode)).
multiclass SIMDAcrossLanesIntrinsic<string baseOpc,
                                    SDPatternOperator opNode> {
// If a lane instruction caught the vector_extract around opNode, we can
// directly match the latter to the instruction.
def : Pat<(v8i8 (opNode V64:$Rn)),
          (INSERT_SUBREG (v8i8 (IMPLICIT_DEF)),
           (!cast<Instruction>(!strconcat(baseOpc, "v8i8v")) V64:$Rn), bsub)>;
def : Pat<(v16i8 (opNode V128:$Rn)),
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
           (!cast<Instruction>(!strconcat(baseOpc, "v16i8v")) V128:$Rn), bsub)>;
def : Pat<(v4i16 (opNode V64:$Rn)),
          (INSERT_SUBREG (v4i16 (IMPLICIT_DEF)),
           (!cast<Instruction>(!strconcat(baseOpc, "v4i16v")) V64:$Rn), hsub)>;
def : Pat<(v8i16 (opNode V128:$Rn)),
          (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)),
           (!cast<Instruction>(!strconcat(baseOpc, "v8i16v")) V128:$Rn), hsub)>;
def : Pat<(v4i32 (opNode V128:$Rn)),
          (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)),
           (!cast<Instruction>(!strconcat(baseOpc, "v4i32v")) V128:$Rn), ssub)>;


// If none did, fallback to the explicit patterns, consuming the vector_extract.
def : Pat<(i32 (vector_extract (insert_subvector undef, (v8i8 (opNode V64:$Rn)),
            (i32 0)), (i64 0))),
          (EXTRACT_SUBREG (INSERT_SUBREG (v8i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v8i8v")) V64:$Rn),
            bsub), ssub)>;
def : Pat<(i32 (vector_extract (v16i8 (opNode V128:$Rn)), (i64 0))),
          (EXTRACT_SUBREG (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v16i8v")) V128:$Rn),
            bsub), ssub)>;
def : Pat<(i32 (vector_extract (insert_subvector undef,
            (v4i16 (opNode V64:$Rn)), (i32 0)), (i64 0))),
          (EXTRACT_SUBREG (INSERT_SUBREG (v4i16 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v4i16v")) V64:$Rn),
            hsub), ssub)>;
def : Pat<(i32 (vector_extract (v8i16 (opNode V128:$Rn)), (i64 0))),
          (EXTRACT_SUBREG (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v8i16v")) V128:$Rn),
            hsub), ssub)>;
def : Pat<(i32 (vector_extract (v4i32 (opNode V128:$Rn)), (i64 0))),
          (EXTRACT_SUBREG (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v4i32v")) V128:$Rn),
            ssub), ssub)>;

}

multiclass SIMDAcrossLanesSignedIntrinsic<string baseOpc,
                                          SDPatternOperator opNode>
    : SIMDAcrossLanesIntrinsic<baseOpc, opNode> {
// If there is a sign extension after this intrinsic, consume it as smov already
// performed it
def : Pat<(i32 (sext_inreg (i32 (vector_extract (insert_subvector undef,
            (opNode (v8i8 V64:$Rn)), (i32 0)), (i64 0))), i8)),
          (i32 (SMOVvi8to32
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
              (!cast<Instruction>(!strconcat(baseOpc, "v8i8v")) V64:$Rn), bsub),
            (i64 0)))>;
def : Pat<(i32 (sext_inreg (i32 (vector_extract
            (opNode (v16i8 V128:$Rn)), (i64 0))), i8)),
          (i32 (SMOVvi8to32
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
             (!cast<Instruction>(!strconcat(baseOpc, "v16i8v")) V128:$Rn), bsub),
            (i64 0)))>;
def : Pat<(i32 (sext_inreg (i32 (vector_extract (insert_subvector undef,
            (opNode (v4i16 V64:$Rn)), (i32 0)), (i64 0))), i16)),
          (i32 (SMOVvi16to32
           (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v4i16v")) V64:$Rn), hsub),
           (i64 0)))>;
def : Pat<(i32 (sext_inreg (i32 (vector_extract
            (opNode (v8i16 V128:$Rn)), (i64 0))), i16)),
          (i32 (SMOVvi16to32
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
             (!cast<Instruction>(!strconcat(baseOpc, "v8i16v")) V128:$Rn), hsub),
            (i64 0)))>;
}

multiclass SIMDAcrossLanesUnsignedIntrinsic<string baseOpc,
                                            SDPatternOperator opNode>
    : SIMDAcrossLanesIntrinsic<baseOpc, opNode> {
// If there is a masking operation keeping only what has been actually
// generated, consume it.
def : Pat<(i32 (and (i32 (vector_extract (insert_subvector undef,
            (opNode (v8i8 V64:$Rn)), (i32 0)), (i64 0))), maski8_or_more)),
      (i32 (EXTRACT_SUBREG
        (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
          (!cast<Instruction>(!strconcat(baseOpc, "v8i8v")) V64:$Rn), bsub),
        ssub))>;
def : Pat<(i32 (and (i32 (vector_extract (opNode (v16i8 V128:$Rn)), (i64 0))),
            maski8_or_more)),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v16i8v")) V128:$Rn), bsub),
          ssub))>;
def : Pat<(i32 (and (i32 (vector_extract (insert_subvector undef,
            (opNode (v4i16 V64:$Rn)), (i32 0)), (i64 0))), maski16_or_more)),
          (i32 (EXTRACT_SUBREG
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
              (!cast<Instruction>(!strconcat(baseOpc, "v4i16v")) V64:$Rn), hsub),
            ssub))>;
def : Pat<(i32 (and (i32 (vector_extract (opNode (v8i16 V128:$Rn)), (i64 0))),
            maski16_or_more)),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v8i16v")) V128:$Rn), hsub),
          ssub))>;
}

defm : SIMDAcrossLanesSignedIntrinsic<"ADDV",  AArch64saddv>;
// vaddv_[su]32 is special; -> ADDP Vd.2S,Vn.2S,Vm.2S; return Vd.s[0];Vn==Vm
def : Pat<(v2i32 (AArch64saddv (v2i32 V64:$Rn))),
          (ADDPv2i32 V64:$Rn, V64:$Rn)>;

defm : SIMDAcrossLanesUnsignedIntrinsic<"ADDV", AArch64uaddv>;
// vaddv_[su]32 is special; -> ADDP Vd.2S,Vn.2S,Vm.2S; return Vd.s[0];Vn==Vm
def : Pat<(v2i32 (AArch64uaddv (v2i32 V64:$Rn))),
          (ADDPv2i32 V64:$Rn, V64:$Rn)>;

defm : SIMDAcrossLanesSignedIntrinsic<"SMAXV", AArch64smaxv>;
def : Pat<(v2i32 (AArch64smaxv (v2i32 V64:$Rn))),
          (SMAXPv2i32 V64:$Rn, V64:$Rn)>;

defm : SIMDAcrossLanesSignedIntrinsic<"SMINV", AArch64sminv>;
def : Pat<(v2i32 (AArch64sminv (v2i32 V64:$Rn))),
          (SMINPv2i32 V64:$Rn, V64:$Rn)>;

defm : SIMDAcrossLanesUnsignedIntrinsic<"UMAXV", AArch64umaxv>;
def : Pat<(v2i32 (AArch64umaxv (v2i32 V64:$Rn))),
          (UMAXPv2i32 V64:$Rn, V64:$Rn)>;

defm : SIMDAcrossLanesUnsignedIntrinsic<"UMINV", AArch64uminv>;
def : Pat<(v2i32 (AArch64uminv (v2i32 V64:$Rn))),
          (UMINPv2i32 V64:$Rn, V64:$Rn)>;

multiclass SIMDAcrossLanesSignedLongIntrinsic<string baseOpc, Intrinsic intOp> {
  def : Pat<(i32 (intOp (v8i8 V64:$Rn))),
        (i32 (SMOVvi16to32
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v8i8v")) V64:$Rn), hsub),
          (i64 0)))>;
def : Pat<(i32 (intOp (v16i8 V128:$Rn))),
        (i32 (SMOVvi16to32
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
           (!cast<Instruction>(!strconcat(baseOpc, "v16i8v")) V128:$Rn), hsub),
          (i64 0)))>;

def : Pat<(i32 (intOp (v4i16 V64:$Rn))),
          (i32 (EXTRACT_SUBREG
           (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v4i16v")) V64:$Rn), ssub),
           ssub))>;
def : Pat<(i32 (intOp (v8i16 V128:$Rn))),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
           (!cast<Instruction>(!strconcat(baseOpc, "v8i16v")) V128:$Rn), ssub),
          ssub))>;

def : Pat<(i64 (intOp (v4i32 V128:$Rn))),
        (i64 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
           (!cast<Instruction>(!strconcat(baseOpc, "v4i32v")) V128:$Rn), dsub),
          dsub))>;
}

multiclass SIMDAcrossLanesUnsignedLongIntrinsic<string baseOpc,
                                                Intrinsic intOp> {
  def : Pat<(i32 (intOp (v8i8 V64:$Rn))),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v8i8v")) V64:$Rn), hsub),
          ssub))>;
def : Pat<(i32 (intOp (v16i8 V128:$Rn))),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v16i8v")) V128:$Rn), hsub),
          ssub))>;

def : Pat<(i32 (intOp (v4i16 V64:$Rn))),
          (i32 (EXTRACT_SUBREG
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
              (!cast<Instruction>(!strconcat(baseOpc, "v4i16v")) V64:$Rn), ssub),
            ssub))>;
def : Pat<(i32 (intOp (v8i16 V128:$Rn))),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v8i16v")) V128:$Rn), ssub),
          ssub))>;

def : Pat<(i64 (intOp (v4i32 V128:$Rn))),
        (i64 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v4i32v")) V128:$Rn), dsub),
          dsub))>;
}

defm : SIMDAcrossLanesSignedLongIntrinsic<"SADDLV", int_aarch64_neon_saddlv>;
defm : SIMDAcrossLanesUnsignedLongIntrinsic<"UADDLV", int_aarch64_neon_uaddlv>;

// The vaddlv_s32 intrinsic gets mapped to SADDLP.
def : Pat<(i64 (int_aarch64_neon_saddlv (v2i32 V64:$Rn))),
          (i64 (EXTRACT_SUBREG
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
              (SADDLPv2i32_v1i64 V64:$Rn), dsub),
            dsub))>;
// The vaddlv_u32 intrinsic gets mapped to UADDLP.
def : Pat<(i64 (int_aarch64_neon_uaddlv (v2i32 V64:$Rn))),
          (i64 (EXTRACT_SUBREG
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
              (UADDLPv2i32_v1i64 V64:$Rn), dsub),
            dsub))>;

//------------------------------------------------------------------------------
// AdvSIMD modified immediate instructions
//------------------------------------------------------------------------------

// AdvSIMD BIC
defm BIC : SIMDModifiedImmVectorShiftTied<1, 0b11, 0b01, "bic", AArch64bici>;
// AdvSIMD ORR
defm ORR : SIMDModifiedImmVectorShiftTied<0, 0b11, 0b01, "orr", AArch64orri>;

def : InstAlias<"bic $Vd.4h, $imm", (BICv4i16 V64:$Vd,  imm0_255:$imm, 0)>;
def : InstAlias<"bic $Vd.8h, $imm", (BICv8i16 V128:$Vd, imm0_255:$imm, 0)>;
def : InstAlias<"bic $Vd.2s, $imm", (BICv2i32 V64:$Vd,  imm0_255:$imm, 0)>;
def : InstAlias<"bic $Vd.4s, $imm", (BICv4i32 V128:$Vd, imm0_255:$imm, 0)>;

def : InstAlias<"bic.4h $Vd, $imm", (BICv4i16 V64:$Vd,  imm0_255:$imm, 0)>;
def : InstAlias<"bic.8h $Vd, $imm", (BICv8i16 V128:$Vd, imm0_255:$imm, 0)>;
def : InstAlias<"bic.2s $Vd, $imm", (BICv2i32 V64:$Vd,  imm0_255:$imm, 0)>;
def : InstAlias<"bic.4s $Vd, $imm", (BICv4i32 V128:$Vd, imm0_255:$imm, 0)>;

def : InstAlias<"orr $Vd.4h, $imm", (ORRv4i16 V64:$Vd,  imm0_255:$imm, 0)>;
def : InstAlias<"orr $Vd.8h, $imm", (ORRv8i16 V128:$Vd, imm0_255:$imm, 0)>;
def : InstAlias<"orr $Vd.2s, $imm", (ORRv2i32 V64:$Vd,  imm0_255:$imm, 0)>;
def : InstAlias<"orr $Vd.4s, $imm", (ORRv4i32 V128:$Vd, imm0_255:$imm, 0)>;

def : InstAlias<"orr.4h $Vd, $imm", (ORRv4i16 V64:$Vd,  imm0_255:$imm, 0)>;
def : InstAlias<"orr.8h $Vd, $imm", (ORRv8i16 V128:$Vd, imm0_255:$imm, 0)>;
def : InstAlias<"orr.2s $Vd, $imm", (ORRv2i32 V64:$Vd,  imm0_255:$imm, 0)>;
def : InstAlias<"orr.4s $Vd, $imm", (ORRv4i32 V128:$Vd, imm0_255:$imm, 0)>;

// AdvSIMD FMOV
def FMOVv2f64_ns : SIMDModifiedImmVectorNoShift<1, 1, 0, 0b1111, V128, fpimm8,
                                              "fmov", ".2d",
                       [(set (v2f64 V128:$Rd), (AArch64fmov imm0_255:$imm8))]>;
def FMOVv2f32_ns : SIMDModifiedImmVectorNoShift<0, 0, 0, 0b1111, V64,  fpimm8,
                                              "fmov", ".2s",
                       [(set (v2f32 V64:$Rd), (AArch64fmov imm0_255:$imm8))]>;
def FMOVv4f32_ns : SIMDModifiedImmVectorNoShift<1, 0, 0, 0b1111, V128, fpimm8,
                                              "fmov", ".4s",
                       [(set (v4f32 V128:$Rd), (AArch64fmov imm0_255:$imm8))]>;
let Predicates = [HasNEON, HasFullFP16] in {
def FMOVv4f16_ns : SIMDModifiedImmVectorNoShift<0, 0, 1, 0b1111, V64,  fpimm8,
                                              "fmov", ".4h",
                       [(set (v4f16 V64:$Rd), (AArch64fmov imm0_255:$imm8))]>;
def FMOVv8f16_ns : SIMDModifiedImmVectorNoShift<1, 0, 1, 0b1111, V128, fpimm8,
                                              "fmov", ".8h",
                       [(set (v8f16 V128:$Rd), (AArch64fmov imm0_255:$imm8))]>;
} // Predicates = [HasNEON, HasFullFP16]

// AdvSIMD MOVI

// EDIT byte mask: scalar
let isReMaterializable = 1, isAsCheapAsAMove = 1 in
def MOVID      : SIMDModifiedImmScalarNoShift<0, 1, 0b1110, "movi",
                    [(set FPR64:$Rd, simdimmtype10:$imm8)]>;
// The movi_edit node has the immediate value already encoded, so we use
// a plain imm0_255 here.
def : Pat<(f64 (AArch64movi_edit imm0_255:$shift)),
          (MOVID imm0_255:$shift)>;

// EDIT byte mask: 2d

// The movi_edit node has the immediate value already encoded, so we use
// a plain imm0_255 in the pattern
let isReMaterializable = 1, isAsCheapAsAMove = 1 in
def MOVIv2d_ns   : SIMDModifiedImmVectorNoShift<1, 1, 0, 0b1110, V128,
                                                simdimmtype10,
                                                "movi", ".2d",
                   [(set (v2i64 V128:$Rd), (AArch64movi_edit imm0_255:$imm8))]>;

def : Pat<(v2i64 immAllZerosV), (MOVIv2d_ns (i32 0))>;
def : Pat<(v4i32 immAllZerosV), (MOVIv2d_ns (i32 0))>;
def : Pat<(v8i16 immAllZerosV), (MOVIv2d_ns (i32 0))>;
def : Pat<(v16i8 immAllZerosV), (MOVIv2d_ns (i32 0))>;

def : Pat<(v2i64 immAllOnesV), (MOVIv2d_ns (i32 255))>;
def : Pat<(v4i32 immAllOnesV), (MOVIv2d_ns (i32 255))>;
def : Pat<(v8i16 immAllOnesV), (MOVIv2d_ns (i32 255))>;
def : Pat<(v16i8 immAllOnesV), (MOVIv2d_ns (i32 255))>;

// Set 64-bit vectors to all 0/1 by extracting from a 128-bit register as the
// extract is free and this gives better MachineCSE results.
def : Pat<(v1i64 immAllZerosV), (EXTRACT_SUBREG (MOVIv2d_ns (i32 0)), dsub)>;
def : Pat<(v2i32 immAllZerosV), (EXTRACT_SUBREG (MOVIv2d_ns (i32 0)), dsub)>;
def : Pat<(v4i16 immAllZerosV), (EXTRACT_SUBREG (MOVIv2d_ns (i32 0)), dsub)>;
def : Pat<(v8i8  immAllZerosV), (EXTRACT_SUBREG (MOVIv2d_ns (i32 0)), dsub)>;

def : Pat<(v1i64 immAllOnesV), (EXTRACT_SUBREG (MOVIv2d_ns (i32 255)), dsub)>;
def : Pat<(v2i32 immAllOnesV), (EXTRACT_SUBREG (MOVIv2d_ns (i32 255)), dsub)>;
def : Pat<(v4i16 immAllOnesV), (EXTRACT_SUBREG (MOVIv2d_ns (i32 255)), dsub)>;
def : Pat<(v8i8  immAllOnesV), (EXTRACT_SUBREG (MOVIv2d_ns (i32 255)), dsub)>;

// EDIT per word & halfword: 2s, 4h, 4s, & 8h
let isReMaterializable = 1, isAsCheapAsAMove = 1 in
defm MOVI      : SIMDModifiedImmVectorShift<0, 0b10, 0b00, "movi">;

def : InstAlias<"movi $Vd.4h, $imm", (MOVIv4i16 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"movi $Vd.8h, $imm", (MOVIv8i16 V128:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"movi $Vd.2s, $imm", (MOVIv2i32 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"movi $Vd.4s, $imm", (MOVIv4i32 V128:$Vd, imm0_255:$imm, 0), 0>;

def : InstAlias<"movi.4h $Vd, $imm", (MOVIv4i16 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"movi.8h $Vd, $imm", (MOVIv8i16 V128:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"movi.2s $Vd, $imm", (MOVIv2i32 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"movi.4s $Vd, $imm", (MOVIv4i32 V128:$Vd, imm0_255:$imm, 0), 0>;

def : Pat<(v2i32 (AArch64movi_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MOVIv2i32 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v4i32 (AArch64movi_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MOVIv4i32 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v4i16 (AArch64movi_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MOVIv4i16 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v8i16 (AArch64movi_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MOVIv8i16 imm0_255:$imm8, imm:$shift)>;

let isReMaterializable = 1, isAsCheapAsAMove = 1 in {
// EDIT per word: 2s & 4s with MSL shifter
def MOVIv2s_msl  : SIMDModifiedImmMoveMSL<0, 0, {1,1,0,?}, V64, "movi", ".2s",
                      [(set (v2i32 V64:$Rd),
                            (AArch64movi_msl imm0_255:$imm8, (i32 imm:$shift)))]>;
def MOVIv4s_msl  : SIMDModifiedImmMoveMSL<1, 0, {1,1,0,?}, V128, "movi", ".4s",
                      [(set (v4i32 V128:$Rd),
                            (AArch64movi_msl imm0_255:$imm8, (i32 imm:$shift)))]>;

// Per byte: 8b & 16b
def MOVIv8b_ns   : SIMDModifiedImmVectorNoShift<0, 0, 0, 0b1110, V64,  imm0_255,
                                                 "movi", ".8b",
                       [(set (v8i8 V64:$Rd), (AArch64movi imm0_255:$imm8))]>;

def MOVIv16b_ns  : SIMDModifiedImmVectorNoShift<1, 0, 0, 0b1110, V128, imm0_255,
                                                 "movi", ".16b",
                       [(set (v16i8 V128:$Rd), (AArch64movi imm0_255:$imm8))]>;
}

// AdvSIMD MVNI

// EDIT per word & halfword: 2s, 4h, 4s, & 8h
let isReMaterializable = 1, isAsCheapAsAMove = 1 in
defm MVNI      : SIMDModifiedImmVectorShift<1, 0b10, 0b00, "mvni">;

def : InstAlias<"mvni $Vd.4h, $imm", (MVNIv4i16 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni $Vd.8h, $imm", (MVNIv8i16 V128:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni $Vd.2s, $imm", (MVNIv2i32 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni $Vd.4s, $imm", (MVNIv4i32 V128:$Vd, imm0_255:$imm, 0), 0>;

def : InstAlias<"mvni.4h $Vd, $imm", (MVNIv4i16 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni.8h $Vd, $imm", (MVNIv8i16 V128:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni.2s $Vd, $imm", (MVNIv2i32 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni.4s $Vd, $imm", (MVNIv4i32 V128:$Vd, imm0_255:$imm, 0), 0>;

def : Pat<(v2i32 (AArch64mvni_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MVNIv2i32 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v4i32 (AArch64mvni_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MVNIv4i32 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v4i16 (AArch64mvni_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MVNIv4i16 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v8i16 (AArch64mvni_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MVNIv8i16 imm0_255:$imm8, imm:$shift)>;

// EDIT per word: 2s & 4s with MSL shifter
let isReMaterializable = 1, isAsCheapAsAMove = 1 in {
def MVNIv2s_msl   : SIMDModifiedImmMoveMSL<0, 1, {1,1,0,?}, V64, "mvni", ".2s",
                      [(set (v2i32 V64:$Rd),
                            (AArch64mvni_msl imm0_255:$imm8, (i32 imm:$shift)))]>;
def MVNIv4s_msl   : SIMDModifiedImmMoveMSL<1, 1, {1,1,0,?}, V128, "mvni", ".4s",
                      [(set (v4i32 V128:$Rd),
                            (AArch64mvni_msl imm0_255:$imm8, (i32 imm:$shift)))]>;
}

//----------------------------------------------------------------------------
// AdvSIMD indexed element
//----------------------------------------------------------------------------

let hasSideEffects = 0 in {
  defm FMLA  : SIMDFPIndexedTied<0, 0b0001, "fmla">;
  defm FMLS  : SIMDFPIndexedTied<0, 0b0101, "fmls">;
}

// NOTE: Operands are reordered in the FMLA/FMLS PatFrags because the
// instruction expects the addend first, while the intrinsic expects it last.

// On the other hand, there are quite a few valid combinatorial options due to
// the commutativity of multiplication and the fact that (-x) * y = x * (-y).
defm : SIMDFPIndexedTiedPatterns<"FMLA",
           TriOpFrag<(fma node:$RHS, node:$MHS, node:$LHS)>>;
defm : SIMDFPIndexedTiedPatterns<"FMLA",
           TriOpFrag<(fma node:$MHS, node:$RHS, node:$LHS)>>;

defm : SIMDFPIndexedTiedPatterns<"FMLS",
           TriOpFrag<(fma node:$MHS, (fneg node:$RHS), node:$LHS)> >;
defm : SIMDFPIndexedTiedPatterns<"FMLS",
           TriOpFrag<(fma node:$RHS, (fneg node:$MHS), node:$LHS)> >;
defm : SIMDFPIndexedTiedPatterns<"FMLS",
           TriOpFrag<(fma (fneg node:$RHS), node:$MHS, node:$LHS)> >;
defm : SIMDFPIndexedTiedPatterns<"FMLS",
           TriOpFrag<(fma (fneg node:$MHS), node:$RHS, node:$LHS)> >;

multiclass FMLSIndexedAfterNegPatterns<SDPatternOperator OpNode> {
  // 3 variants for the .2s version: DUPLANE from 128-bit, DUPLANE from 64-bit
  // and DUP scalar.
  def : Pat<(v2f32 (OpNode (v2f32 V64:$Rd), (v2f32 V64:$Rn),
                           (AArch64duplane32 (v4f32 (fneg V128:$Rm)),
                                           VectorIndexS:$idx))),
            (FMLSv2i32_indexed V64:$Rd, V64:$Rn, V128:$Rm, VectorIndexS:$idx)>;
  def : Pat<(v2f32 (OpNode (v2f32 V64:$Rd), (v2f32 V64:$Rn),
                           (v2f32 (AArch64duplane32
                                      (v4f32 (insert_subvector undef,
                                                 (v2f32 (fneg V64:$Rm)),
                                                 (i32 0))),
                                      VectorIndexS:$idx)))),
            (FMLSv2i32_indexed V64:$Rd, V64:$Rn,
                               (SUBREG_TO_REG (i32 0), V64:$Rm, dsub),
                               VectorIndexS:$idx)>;
  def : Pat<(v2f32 (OpNode (v2f32 V64:$Rd), (v2f32 V64:$Rn),
                           (AArch64dup (f32 (fneg FPR32Op:$Rm))))),
            (FMLSv2i32_indexed V64:$Rd, V64:$Rn,
                (SUBREG_TO_REG (i32 0), FPR32Op:$Rm, ssub), (i64 0))>;

  // 3 variants for the .4s version: DUPLANE from 128-bit, DUPLANE from 64-bit
  // and DUP scalar.
  def : Pat<(v4f32 (OpNode (v4f32 V128:$Rd), (v4f32 V128:$Rn),
                           (AArch64duplane32 (v4f32 (fneg V128:$Rm)),
                                           VectorIndexS:$idx))),
            (FMLSv4i32_indexed V128:$Rd, V128:$Rn, V128:$Rm,
                               VectorIndexS:$idx)>;
  def : Pat<(v4f32 (OpNode (v4f32 V128:$Rd), (v4f32 V128:$Rn),
                           (v4f32 (AArch64duplane32
                                      (v4f32 (insert_subvector undef,
                                                 (v2f32 (fneg V64:$Rm)),
                                                 (i32 0))),
                                      VectorIndexS:$idx)))),
            (FMLSv4i32_indexed V128:$Rd, V128:$Rn,
                               (SUBREG_TO_REG (i32 0), V64:$Rm, dsub),
                               VectorIndexS:$idx)>;
  def : Pat<(v4f32 (OpNode (v4f32 V128:$Rd), (v4f32 V128:$Rn),
                           (AArch64dup (f32 (fneg FPR32Op:$Rm))))),
            (FMLSv4i32_indexed V128:$Rd, V128:$Rn,
                (SUBREG_TO_REG (i32 0), FPR32Op:$Rm, ssub), (i64 0))>;

  // 2 variants for the .2d version: DUPLANE from 128-bit, and DUP scalar
  // (DUPLANE from 64-bit would be trivial).
  def : Pat<(v2f64 (OpNode (v2f64 V128:$Rd), (v2f64 V128:$Rn),
                           (AArch64duplane64 (v2f64 (fneg V128:$Rm)),
                                           VectorIndexD:$idx))),
            (FMLSv2i64_indexed
                V128:$Rd, V128:$Rn, V128:$Rm, VectorIndexS:$idx)>;
  def : Pat<(v2f64 (OpNode (v2f64 V128:$Rd), (v2f64 V128:$Rn),
                           (AArch64dup (f64 (fneg FPR64Op:$Rm))))),
            (FMLSv2i64_indexed V128:$Rd, V128:$Rn,
                (SUBREG_TO_REG (i32 0), FPR64Op:$Rm, dsub), (i64 0))>;

  // 2 variants for 32-bit scalar version: extract from .2s or from .4s
  def : Pat<(f32 (OpNode (f32 FPR32:$Rd), (f32 FPR32:$Rn),
                         (vector_extract (v4f32 (fneg V128:$Rm)),
                                         VectorIndexS:$idx))),
            (FMLSv1i32_indexed FPR32:$Rd, FPR32:$Rn,
                V128:$Rm, VectorIndexS:$idx)>;
  def : Pat<(f32 (OpNode (f32 FPR32:$Rd), (f32 FPR32:$Rn),
                         (vector_extract (v4f32 (insert_subvector undef,
                                                    (v2f32 (fneg V64:$Rm)),
                                                    (i32 0))),
                                         VectorIndexS:$idx))),
            (FMLSv1i32_indexed FPR32:$Rd, FPR32:$Rn,
                (SUBREG_TO_REG (i32 0), V64:$Rm, dsub), VectorIndexS:$idx)>;

  // 1 variant for 64-bit scalar version: extract from .1d or from .2d
  def : Pat<(f64 (OpNode (f64 FPR64:$Rd), (f64 FPR64:$Rn),
                         (vector_extract (v2f64 (fneg V128:$Rm)),
                                         VectorIndexS:$idx))),
            (FMLSv1i64_indexed FPR64:$Rd, FPR64:$Rn,
                V128:$Rm, VectorIndexS:$idx)>;
}

defm : FMLSIndexedAfterNegPatterns<
           TriOpFrag<(fma node:$RHS, node:$MHS, node:$LHS)> >;
defm : FMLSIndexedAfterNegPatterns<
           TriOpFrag<(fma node:$MHS, node:$RHS, node:$LHS)> >;

defm FMULX : SIMDFPIndexed<1, 0b1001, "fmulx", int_aarch64_neon_fmulx>;
defm FMUL  : SIMDFPIndexed<0, 0b1001, "fmul", fmul>;

def : Pat<(v2f32 (fmul V64:$Rn, (AArch64dup (f32 FPR32:$Rm)))),
          (FMULv2i32_indexed V64:$Rn,
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR32:$Rm, ssub),
            (i64 0))>;
def : Pat<(v4f32 (fmul V128:$Rn, (AArch64dup (f32 FPR32:$Rm)))),
          (FMULv4i32_indexed V128:$Rn,
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR32:$Rm, ssub),
            (i64 0))>;
def : Pat<(v2f64 (fmul V128:$Rn, (AArch64dup (f64 FPR64:$Rm)))),
          (FMULv2i64_indexed V128:$Rn,
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR64:$Rm, dsub),
            (i64 0))>;

defm SQDMULH : SIMDIndexedHS<0, 0b1100, "sqdmulh", int_aarch64_neon_sqdmulh>;
defm SQRDMULH : SIMDIndexedHS<0, 0b1101, "sqrdmulh", int_aarch64_neon_sqrdmulh>;

defm SQDMULH : SIMDIndexedHSPatterns<int_aarch64_neon_sqdmulh_lane,
                                     int_aarch64_neon_sqdmulh_laneq>;
defm SQRDMULH : SIMDIndexedHSPatterns<int_aarch64_neon_sqrdmulh_lane,
                                      int_aarch64_neon_sqrdmulh_laneq>;

// Generated by MachineCombine
defm MLA   : SIMDVectorIndexedHSTied<1, 0b0000, "mla", null_frag>;
defm MLS   : SIMDVectorIndexedHSTied<1, 0b0100, "mls", null_frag>;

defm MUL   : SIMDVectorIndexedHS<0, 0b1000, "mul", mul>;
defm SMLAL : SIMDVectorIndexedLongSDTied<0, 0b0010, "smlal",
    TriOpFrag<(add node:$LHS, (int_aarch64_neon_smull node:$MHS, node:$RHS))>>;
defm SMLSL : SIMDVectorIndexedLongSDTied<0, 0b0110, "smlsl",
    TriOpFrag<(sub node:$LHS, (int_aarch64_neon_smull node:$MHS, node:$RHS))>>;
defm SMULL : SIMDVectorIndexedLongSD<0, 0b1010, "smull",
                int_aarch64_neon_smull>;
defm SQDMLAL : SIMDIndexedLongSQDMLXSDTied<0, 0b0011, "sqdmlal",
                                           int_aarch64_neon_sqadd>;
defm SQDMLSL : SIMDIndexedLongSQDMLXSDTied<0, 0b0111, "sqdmlsl",
                                           int_aarch64_neon_sqsub>;
defm SQRDMLAH : SIMDIndexedSQRDMLxHSDTied<1, 0b1101, "sqrdmlah",
                                          int_aarch64_neon_sqadd>;
defm SQRDMLSH : SIMDIndexedSQRDMLxHSDTied<1, 0b1111, "sqrdmlsh",
                                          int_aarch64_neon_sqsub>;
defm SQDMULL : SIMDIndexedLongSD<0, 0b1011, "sqdmull", int_aarch64_neon_sqdmull>;
defm UMLAL   : SIMDVectorIndexedLongSDTied<1, 0b0010, "umlal",
    TriOpFrag<(add node:$LHS, (int_aarch64_neon_umull node:$MHS, node:$RHS))>>;
defm UMLSL   : SIMDVectorIndexedLongSDTied<1, 0b0110, "umlsl",
    TriOpFrag<(sub node:$LHS, (int_aarch64_neon_umull node:$MHS, node:$RHS))>>;
defm UMULL   : SIMDVectorIndexedLongSD<1, 0b1010, "umull",
                int_aarch64_neon_umull>;

// A scalar sqdmull with the second operand being a vector lane can be
// handled directly with the indexed instruction encoding.
def : Pat<(int_aarch64_neon_sqdmulls_scalar (i32 FPR32:$Rn),
                                          (vector_extract (v4i32 V128:$Vm),
                                                           VectorIndexS:$idx)),
          (SQDMULLv1i64_indexed FPR32:$Rn, V128:$Vm, VectorIndexS:$idx)>;

//----------------------------------------------------------------------------
// AdvSIMD scalar shift instructions
//----------------------------------------------------------------------------
defm FCVTZS : SIMDFPScalarRShift<0, 0b11111, "fcvtzs">;
defm FCVTZU : SIMDFPScalarRShift<1, 0b11111, "fcvtzu">;
defm SCVTF  : SIMDFPScalarRShift<0, 0b11100, "scvtf">;
defm UCVTF  : SIMDFPScalarRShift<1, 0b11100, "ucvtf">;
// Codegen patterns for the above. We don't put these directly on the
// instructions because TableGen's type inference can't handle the truth.
// Having the same base pattern for fp <--> int totally freaks it out.
def : Pat<(int_aarch64_neon_vcvtfp2fxs FPR32:$Rn, vecshiftR32:$imm),
          (FCVTZSs FPR32:$Rn, vecshiftR32:$imm)>;
def : Pat<(int_aarch64_neon_vcvtfp2fxu FPR32:$Rn, vecshiftR32:$imm),
          (FCVTZUs FPR32:$Rn, vecshiftR32:$imm)>;
def : Pat<(i64 (int_aarch64_neon_vcvtfp2fxs (f64 FPR64:$Rn), vecshiftR64:$imm)),
          (FCVTZSd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(i64 (int_aarch64_neon_vcvtfp2fxu (f64 FPR64:$Rn), vecshiftR64:$imm)),
          (FCVTZUd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(v1i64 (int_aarch64_neon_vcvtfp2fxs (v1f64 FPR64:$Rn),
                                            vecshiftR64:$imm)),
          (FCVTZSd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(v1i64 (int_aarch64_neon_vcvtfp2fxu (v1f64 FPR64:$Rn),
                                            vecshiftR64:$imm)),
          (FCVTZUd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(int_aarch64_neon_vcvtfxu2fp FPR32:$Rn, vecshiftR32:$imm),
          (UCVTFs FPR32:$Rn, vecshiftR32:$imm)>;
def : Pat<(f64 (int_aarch64_neon_vcvtfxu2fp (i64 FPR64:$Rn), vecshiftR64:$imm)),
          (UCVTFd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(v1f64 (int_aarch64_neon_vcvtfxs2fp (v1i64 FPR64:$Rn),
                                            vecshiftR64:$imm)),
          (SCVTFd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(f64 (int_aarch64_neon_vcvtfxs2fp (i64 FPR64:$Rn), vecshiftR64:$imm)),
          (SCVTFd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(v1f64 (int_aarch64_neon_vcvtfxu2fp (v1i64 FPR64:$Rn),
                                            vecshiftR64:$imm)),
          (UCVTFd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(int_aarch64_neon_vcvtfxs2fp FPR32:$Rn, vecshiftR32:$imm),
          (SCVTFs FPR32:$Rn, vecshiftR32:$imm)>;

// Patterns for FP16 Instrinsics - requires reg copy to/from as i16s not supported.

def : Pat<(f16 (int_aarch64_neon_vcvtfxs2fp (i32 (sext_inreg FPR32:$Rn, i16)), vecshiftR16:$imm)),
          (SCVTFh (EXTRACT_SUBREG FPR32:$Rn, hsub), vecshiftR16:$imm)>;
def : Pat<(f16 (int_aarch64_neon_vcvtfxs2fp (i32 FPR32:$Rn), vecshiftR16:$imm)),
          (SCVTFh (EXTRACT_SUBREG FPR32:$Rn, hsub), vecshiftR16:$imm)>;
def : Pat<(f16 (int_aarch64_neon_vcvtfxs2fp (i64 FPR64:$Rn), vecshiftR16:$imm)),
          (SCVTFh (EXTRACT_SUBREG FPR64:$Rn, hsub), vecshiftR16:$imm)>;
def : Pat<(f16 (int_aarch64_neon_vcvtfxu2fp
            (and FPR32:$Rn, (i32 65535)),
            vecshiftR16:$imm)),
          (UCVTFh (EXTRACT_SUBREG FPR32:$Rn, hsub), vecshiftR16:$imm)>;
def : Pat<(f16 (int_aarch64_neon_vcvtfxu2fp FPR32:$Rn, vecshiftR16:$imm)),
          (UCVTFh (EXTRACT_SUBREG FPR32:$Rn, hsub), vecshiftR16:$imm)>;
def : Pat<(f16 (int_aarch64_neon_vcvtfxu2fp (i64 FPR64:$Rn), vecshiftR16:$imm)),
          (UCVTFh (EXTRACT_SUBREG FPR64:$Rn, hsub), vecshiftR16:$imm)>;
def : Pat<(i32 (int_aarch64_neon_vcvtfp2fxs (f16 FPR16:$Rn), vecshiftR32:$imm)),
          (i32 (INSERT_SUBREG
            (i32 (IMPLICIT_DEF)),
            (FCVTZSh FPR16:$Rn, vecshiftR32:$imm),
            hsub))>;
def : Pat<(i64 (int_aarch64_neon_vcvtfp2fxs (f16 FPR16:$Rn), vecshiftR64:$imm)),
          (i64 (INSERT_SUBREG
            (i64 (IMPLICIT_DEF)),
            (FCVTZSh FPR16:$Rn, vecshiftR64:$imm),
            hsub))>;
def : Pat<(i32 (int_aarch64_neon_vcvtfp2fxu (f16 FPR16:$Rn), vecshiftR32:$imm)),
          (i32 (INSERT_SUBREG
            (i32 (IMPLICIT_DEF)),
            (FCVTZUh FPR16:$Rn, vecshiftR32:$imm),
            hsub))>;
def : Pat<(i64 (int_aarch64_neon_vcvtfp2fxu (f16 FPR16:$Rn), vecshiftR64:$imm)),
          (i64 (INSERT_SUBREG
            (i64 (IMPLICIT_DEF)),
            (FCVTZUh FPR16:$Rn, vecshiftR64:$imm),
            hsub))>;
def : Pat<(i32 (int_aarch64_neon_facge (f16 FPR16:$Rn), (f16 FPR16:$Rm))),
          (i32 (INSERT_SUBREG
            (i32 (IMPLICIT_DEF)),
            (FACGE16 FPR16:$Rn, FPR16:$Rm),
            hsub))>;
def : Pat<(i32 (int_aarch64_neon_facgt (f16 FPR16:$Rn), (f16 FPR16:$Rm))),
          (i32 (INSERT_SUBREG
            (i32 (IMPLICIT_DEF)),
            (FACGT16 FPR16:$Rn, FPR16:$Rm),
            hsub))>;

defm SHL      : SIMDScalarLShiftD<   0, 0b01010, "shl", AArch64vshl>;
defm SLI      : SIMDScalarLShiftDTied<1, 0b01010, "sli">;
defm SQRSHRN  : SIMDScalarRShiftBHS< 0, 0b10011, "sqrshrn",
                                     int_aarch64_neon_sqrshrn>;
defm SQRSHRUN : SIMDScalarRShiftBHS< 1, 0b10001, "sqrshrun",
                                     int_aarch64_neon_sqrshrun>;
defm SQSHLU   : SIMDScalarLShiftBHSD<1, 0b01100, "sqshlu", AArch64sqshlui>;
defm SQSHL    : SIMDScalarLShiftBHSD<0, 0b01110, "sqshl", AArch64sqshli>;
defm SQSHRN   : SIMDScalarRShiftBHS< 0, 0b10010, "sqshrn",
                                     int_aarch64_neon_sqshrn>;
defm SQSHRUN  : SIMDScalarRShiftBHS< 1, 0b10000, "sqshrun",
                                     int_aarch64_neon_sqshrun>;
defm SRI      : SIMDScalarRShiftDTied<   1, 0b01000, "sri">;
defm SRSHR    : SIMDScalarRShiftD<   0, 0b00100, "srshr", AArch64srshri>;
defm SRSRA    : SIMDScalarRShiftDTied<   0, 0b00110, "srsra",
    TriOpFrag<(add node:$LHS,
                   (AArch64srshri node:$MHS, node:$RHS))>>;
defm SSHR     : SIMDScalarRShiftD<   0, 0b00000, "sshr", AArch64vashr>;
defm SSRA     : SIMDScalarRShiftDTied<   0, 0b00010, "ssra",
    TriOpFrag<(add node:$LHS,
                   (AArch64vashr node:$MHS, node:$RHS))>>;
defm UQRSHRN  : SIMDScalarRShiftBHS< 1, 0b10011, "uqrshrn",
                                     int_aarch64_neon_uqrshrn>;
defm UQSHL    : SIMDScalarLShiftBHSD<1, 0b01110, "uqshl", AArch64uqshli>;
defm UQSHRN   : SIMDScalarRShiftBHS< 1, 0b10010, "uqshrn",
                                     int_aarch64_neon_uqshrn>;
defm URSHR    : SIMDScalarRShiftD<   1, 0b00100, "urshr", AArch64urshri>;
defm URSRA    : SIMDScalarRShiftDTied<   1, 0b00110, "ursra",
    TriOpFrag<(add node:$LHS,
                   (AArch64urshri node:$MHS, node:$RHS))>>;
defm USHR     : SIMDScalarRShiftD<   1, 0b00000, "ushr", AArch64vlshr>;
defm USRA     : SIMDScalarRShiftDTied<   1, 0b00010, "usra",
    TriOpFrag<(add node:$LHS,
                   (AArch64vlshr node:$MHS, node:$RHS))>>;

//----------------------------------------------------------------------------
// AdvSIMD vector shift instructions
//----------------------------------------------------------------------------
defm FCVTZS:SIMDVectorRShiftSD<0, 0b11111, "fcvtzs", int_aarch64_neon_vcvtfp2fxs>;
defm FCVTZU:SIMDVectorRShiftSD<1, 0b11111, "fcvtzu", int_aarch64_neon_vcvtfp2fxu>;
defm SCVTF: SIMDVectorRShiftToFP<0, 0b11100, "scvtf",
                                   int_aarch64_neon_vcvtfxs2fp>;
defm RSHRN   : SIMDVectorRShiftNarrowBHS<0, 0b10001, "rshrn",
                                         int_aarch64_neon_rshrn>;
defm SHL     : SIMDVectorLShiftBHSD<0, 0b01010, "shl", AArch64vshl>;
defm SHRN    : SIMDVectorRShiftNarrowBHS<0, 0b10000, "shrn",
                          BinOpFrag<(trunc (AArch64vashr node:$LHS, node:$RHS))>>;
defm SLI     : SIMDVectorLShiftBHSDTied<1, 0b01010, "sli", AArch64vsli>;
def : Pat<(v1i64 (AArch64vsli (v1i64 FPR64:$Rd), (v1i64 FPR64:$Rn),
                                      (i32 vecshiftL64:$imm))),
          (SLId FPR64:$Rd, FPR64:$Rn, vecshiftL64:$imm)>;
defm SQRSHRN : SIMDVectorRShiftNarrowBHS<0, 0b10011, "sqrshrn",
                                         int_aarch64_neon_sqrshrn>;
defm SQRSHRUN: SIMDVectorRShiftNarrowBHS<1, 0b10001, "sqrshrun",
                                         int_aarch64_neon_sqrshrun>;
defm SQSHLU : SIMDVectorLShiftBHSD<1, 0b01100, "sqshlu", AArch64sqshlui>;
defm SQSHL  : SIMDVectorLShiftBHSD<0, 0b01110, "sqshl", AArch64sqshli>;
defm SQSHRN  : SIMDVectorRShiftNarrowBHS<0, 0b10010, "sqshrn",
                                         int_aarch64_neon_sqshrn>;
defm SQSHRUN : SIMDVectorRShiftNarrowBHS<1, 0b10000, "sqshrun",
                                         int_aarch64_neon_sqshrun>;
defm SRI     : SIMDVectorRShiftBHSDTied<1, 0b01000, "sri", AArch64vsri>;
def : Pat<(v1i64 (AArch64vsri (v1i64 FPR64:$Rd), (v1i64 FPR64:$Rn),
                                      (i32 vecshiftR64:$imm))),
          (SRId FPR64:$Rd, FPR64:$Rn, vecshiftR64:$imm)>;
defm SRSHR   : SIMDVectorRShiftBHSD<0, 0b00100, "srshr", AArch64srshri>;
defm SRSRA   : SIMDVectorRShiftBHSDTied<0, 0b00110, "srsra",
                 TriOpFrag<(add node:$LHS,
                                (AArch64srshri node:$MHS, node:$RHS))> >;
defm SSHLL   : SIMDVectorLShiftLongBHSD<0, 0b10100, "sshll",
                BinOpFrag<(AArch64vshl (sext node:$LHS), node:$RHS)>>;

defm SSHR    : SIMDVectorRShiftBHSD<0, 0b00000, "sshr", AArch64vashr>;
defm SSRA    : SIMDVectorRShiftBHSDTied<0, 0b00010, "ssra",
                TriOpFrag<(add node:$LHS, (AArch64vashr node:$MHS, node:$RHS))>>;
defm UCVTF   : SIMDVectorRShiftToFP<1, 0b11100, "ucvtf",
                        int_aarch64_neon_vcvtfxu2fp>;
defm UQRSHRN : SIMDVectorRShiftNarrowBHS<1, 0b10011, "uqrshrn",
                                         int_aarch64_neon_uqrshrn>;
defm UQSHL   : SIMDVectorLShiftBHSD<1, 0b01110, "uqshl", AArch64uqshli>;
defm UQSHRN  : SIMDVectorRShiftNarrowBHS<1, 0b10010, "uqshrn",
                                         int_aarch64_neon_uqshrn>;
defm URSHR   : SIMDVectorRShiftBHSD<1, 0b00100, "urshr", AArch64urshri>;
defm URSRA   : SIMDVectorRShiftBHSDTied<1, 0b00110, "ursra",
                TriOpFrag<(add node:$LHS,
                               (AArch64urshri node:$MHS, node:$RHS))> >;
defm USHLL   : SIMDVectorLShiftLongBHSD<1, 0b10100, "ushll",
                BinOpFrag<(AArch64vshl (zext node:$LHS), node:$RHS)>>;
defm USHR    : SIMDVectorRShiftBHSD<1, 0b00000, "ushr", AArch64vlshr>;
defm USRA    : SIMDVectorRShiftBHSDTied<1, 0b00010, "usra",
                TriOpFrag<(add node:$LHS, (AArch64vlshr node:$MHS, node:$RHS))> >;

// SHRN patterns for when a logical right shift was used instead of arithmetic
// (the immediate guarantees no sign bits actually end up in the result so it
// doesn't matter).
def : Pat<(v8i8 (trunc (AArch64vlshr (v8i16 V128:$Rn), vecshiftR16Narrow:$imm))),
          (SHRNv8i8_shift V128:$Rn, vecshiftR16Narrow:$imm)>;
def : Pat<(v4i16 (trunc (AArch64vlshr (v4i32 V128:$Rn), vecshiftR32Narrow:$imm))),
          (SHRNv4i16_shift V128:$Rn, vecshiftR32Narrow:$imm)>;
def : Pat<(v2i32 (trunc (AArch64vlshr (v2i64 V128:$Rn), vecshiftR64Narrow:$imm))),
          (SHRNv2i32_shift V128:$Rn, vecshiftR64Narrow:$imm)>;

def : Pat<(v16i8 (concat_vectors (v8i8 V64:$Rd),
                                 (trunc (AArch64vlshr (v8i16 V128:$Rn),
                                                    vecshiftR16Narrow:$imm)))),
          (SHRNv16i8_shift (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
                           V128:$Rn, vecshiftR16Narrow:$imm)>;
def : Pat<(v8i16 (concat_vectors (v4i16 V64:$Rd),
                                 (trunc (AArch64vlshr (v4i32 V128:$Rn),
                                                    vecshiftR32Narrow:$imm)))),
          (SHRNv8i16_shift (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
                           V128:$Rn, vecshiftR32Narrow:$imm)>;
def : Pat<(v4i32 (concat_vectors (v2i32 V64:$Rd),
                                 (trunc (AArch64vlshr (v2i64 V128:$Rn),
                                                    vecshiftR64Narrow:$imm)))),
          (SHRNv4i32_shift (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
                           V128:$Rn, vecshiftR32Narrow:$imm)>;

// Vector sign and zero extensions are implemented with SSHLL and USSHLL.
// Anyexts are implemented as zexts.
def : Pat<(v8i16 (sext   (v8i8 V64:$Rn))),  (SSHLLv8i8_shift  V64:$Rn, (i32 0))>;
def : Pat<(v8i16 (zext   (v8i8 V64:$Rn))),  (USHLLv8i8_shift  V64:$Rn, (i32 0))>;
def : Pat<(v8i16 (anyext (v8i8 V64:$Rn))),  (USHLLv8i8_shift  V64:$Rn, (i32 0))>;
def : Pat<(v4i32 (sext   (v4i16 V64:$Rn))), (SSHLLv4i16_shift V64:$Rn, (i32 0))>;
def : Pat<(v4i32 (zext   (v4i16 V64:$Rn))), (USHLLv4i16_shift V64:$Rn, (i32 0))>;
def : Pat<(v4i32 (anyext (v4i16 V64:$Rn))), (USHLLv4i16_shift V64:$Rn, (i32 0))>;
def : Pat<(v2i64 (sext   (v2i32 V64:$Rn))), (SSHLLv2i32_shift V64:$Rn, (i32 0))>;
def : Pat<(v2i64 (zext   (v2i32 V64:$Rn))), (USHLLv2i32_shift V64:$Rn, (i32 0))>;
def : Pat<(v2i64 (anyext (v2i32 V64:$Rn))), (USHLLv2i32_shift V64:$Rn, (i32 0))>;
// Also match an extend from the upper half of a 128 bit source register.
def : Pat<(v8i16 (anyext (v8i8 (extract_subvector V128:$Rn, (i64 8)) ))),
          (USHLLv16i8_shift V128:$Rn, (i32 0))>;
def : Pat<(v8i16 (zext   (v8i8 (extract_subvector V128:$Rn, (i64 8)) ))),
          (USHLLv16i8_shift V128:$Rn, (i32 0))>;
def : Pat<(v8i16 (sext   (v8i8 (extract_subvector V128:$Rn, (i64 8)) ))),
          (SSHLLv16i8_shift V128:$Rn, (i32 0))>;
def : Pat<(v4i32 (anyext (v4i16 (extract_subvector V128:$Rn, (i64 4)) ))),
          (USHLLv8i16_shift V128:$Rn, (i32 0))>;
def : Pat<(v4i32 (zext   (v4i16 (extract_subvector V128:$Rn, (i64 4)) ))),
          (USHLLv8i16_shift V128:$Rn, (i32 0))>;
def : Pat<(v4i32 (sext   (v4i16 (extract_subvector V128:$Rn, (i64 4)) ))),
          (SSHLLv8i16_shift V128:$Rn, (i32 0))>;
def : Pat<(v2i64 (anyext (v2i32 (extract_subvector V128:$Rn, (i64 2)) ))),
          (USHLLv4i32_shift V128:$Rn, (i32 0))>;
def : Pat<(v2i64 (zext   (v2i32 (extract_subvector V128:$Rn, (i64 2)) ))),
          (USHLLv4i32_shift V128:$Rn, (i32 0))>;
def : Pat<(v2i64 (sext   (v2i32 (extract_subvector V128:$Rn, (i64 2)) ))),
          (SSHLLv4i32_shift V128:$Rn, (i32 0))>;

// Vector shift sxtl aliases
def : InstAlias<"sxtl.8h $dst, $src1",
                (SSHLLv8i8_shift V128:$dst, V64:$src1, 0)>;
def : InstAlias<"sxtl $dst.8h, $src1.8b",
                (SSHLLv8i8_shift V128:$dst, V64:$src1, 0)>;
def : InstAlias<"sxtl.4s $dst, $src1",
                (SSHLLv4i16_shift V128:$dst, V64:$src1, 0)>;
def : InstAlias<"sxtl $dst.4s, $src1.4h",
                (SSHLLv4i16_shift V128:$dst, V64:$src1, 0)>;
def : InstAlias<"sxtl.2d $dst, $src1",
                (SSHLLv2i32_shift V128:$dst, V64:$src1, 0)>;
def : InstAlias<"sxtl $dst.2d, $src1.2s",
                (SSHLLv2i32_shift V128:$dst, V64:$src1, 0)>;

// Vector shift sxtl2 aliases
def : InstAlias<"sxtl2.8h $dst, $src1",
                (SSHLLv16i8_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"sxtl2 $dst.8h, $src1.16b",
                (SSHLLv16i8_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"sxtl2.4s $dst, $src1",
                (SSHLLv8i16_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"sxtl2 $dst.4s, $src1.8h",
                (SSHLLv8i16_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"sxtl2.2d $dst, $src1",
                (SSHLLv4i32_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"sxtl2 $dst.2d, $src1.4s",
                (SSHLLv4i32_shift V128:$dst, V128:$src1, 0)>;

// Vector shift uxtl aliases
def : InstAlias<"uxtl.8h $dst, $src1",
                (USHLLv8i8_shift V128:$dst, V64:$src1, 0)>;
def : InstAlias<"uxtl $dst.8h, $src1.8b",
                (USHLLv8i8_shift V128:$dst, V64:$src1, 0)>;
def : InstAlias<"uxtl.4s $dst, $src1",
                (USHLLv4i16_shift V128:$dst, V64:$src1, 0)>;
def : InstAlias<"uxtl $dst.4s, $src1.4h",
                (USHLLv4i16_shift V128:$dst, V64:$src1, 0)>;
def : InstAlias<"uxtl.2d $dst, $src1",
                (USHLLv2i32_shift V128:$dst, V64:$src1, 0)>;
def : InstAlias<"uxtl $dst.2d, $src1.2s",
                (USHLLv2i32_shift V128:$dst, V64:$src1, 0)>;

// Vector shift uxtl2 aliases
def : InstAlias<"uxtl2.8h $dst, $src1",
                (USHLLv16i8_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"uxtl2 $dst.8h, $src1.16b",
                (USHLLv16i8_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"uxtl2.4s $dst, $src1",
                (USHLLv8i16_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"uxtl2 $dst.4s, $src1.8h",
                (USHLLv8i16_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"uxtl2.2d $dst, $src1",
                (USHLLv4i32_shift V128:$dst, V128:$src1, 0)>;
def : InstAlias<"uxtl2 $dst.2d, $src1.4s",
                (USHLLv4i32_shift V128:$dst, V128:$src1, 0)>;

// If an integer is about to be converted to a floating point value,
// just load it on the floating point unit.
// These patterns are more complex because floating point loads do not
// support sign extension.
// The sign extension has to be explicitly added and is only supported for
// one step: byte-to-half, half-to-word, word-to-doubleword.
// SCVTF GPR -> FPR is 9 cycles.
// SCVTF FPR -> FPR is 4 cyclces.
// (sign extension with lengthen) SXTL FPR -> FPR is 2 cycles.
// Therefore, we can do 2 sign extensions and one SCVTF FPR -> FPR
// and still being faster.
// However, this is not good for code size.
// 8-bits -> float. 2 sizes step-up.
class SExtLoadi8CVTf32Pat<dag addrmode, dag INST>
  : Pat<(f32 (sint_to_fp (i32 (sextloadi8 addrmode)))),
        (SCVTFv1i32 (f32 (EXTRACT_SUBREG
                            (SSHLLv4i16_shift
                              (f64
                                (EXTRACT_SUBREG
                                  (SSHLLv8i8_shift
                                    (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                        INST,
                                        bsub),
                                    0),
                                  dsub)),
                               0),
                             ssub)))>,
    Requires<[NotForCodeSize, UseAlternateSExtLoadCVTF32]>;

def : SExtLoadi8CVTf32Pat<(ro8.Wpat GPR64sp:$Rn, GPR32:$Rm, ro8.Wext:$ext),
                          (LDRBroW  GPR64sp:$Rn, GPR32:$Rm, ro8.Wext:$ext)>;
def : SExtLoadi8CVTf32Pat<(ro8.Xpat GPR64sp:$Rn, GPR64:$Rm, ro8.Xext:$ext),
                          (LDRBroX  GPR64sp:$Rn, GPR64:$Rm, ro8.Xext:$ext)>;
def : SExtLoadi8CVTf32Pat<(am_indexed8 GPR64sp:$Rn, uimm12s1:$offset),
                          (LDRBui GPR64sp:$Rn, uimm12s1:$offset)>;
def : SExtLoadi8CVTf32Pat<(am_unscaled8 GPR64sp:$Rn, simm9:$offset),
                          (LDURBi GPR64sp:$Rn, simm9:$offset)>;

// 16-bits -> float. 1 size step-up.
class SExtLoadi16CVTf32Pat<dag addrmode, dag INST>
  : Pat<(f32 (sint_to_fp (i32 (sextloadi16 addrmode)))),
        (SCVTFv1i32 (f32 (EXTRACT_SUBREG
                            (SSHLLv4i16_shift
                                (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                  INST,
                                  hsub),
                                0),
                            ssub)))>, Requires<[NotForCodeSize]>;

def : SExtLoadi16CVTf32Pat<(ro16.Wpat GPR64sp:$Rn, GPR32:$Rm, ro16.Wext:$ext),
                           (LDRHroW   GPR64sp:$Rn, GPR32:$Rm, ro16.Wext:$ext)>;
def : SExtLoadi16CVTf32Pat<(ro16.Xpat GPR64sp:$Rn, GPR64:$Rm, ro16.Xext:$ext),
                           (LDRHroX   GPR64sp:$Rn, GPR64:$Rm, ro16.Xext:$ext)>;
def : SExtLoadi16CVTf32Pat<(am_indexed16 GPR64sp:$Rn, uimm12s2:$offset),
                           (LDRHui GPR64sp:$Rn, uimm12s2:$offset)>;
def : SExtLoadi16CVTf32Pat<(am_unscaled16 GPR64sp:$Rn, simm9:$offset),
                           (LDURHi GPR64sp:$Rn, simm9:$offset)>;

// 32-bits to 32-bits are handled in target specific dag combine:
// performIntToFpCombine.
// 64-bits integer to 32-bits floating point, not possible with
// SCVTF on floating point registers (both source and destination
// must have the same size).

// Here are the patterns for 8, 16, 32, and 64-bits to double.
// 8-bits -> double. 3 size step-up: give up.
// 16-bits -> double. 2 size step.
class SExtLoadi16CVTf64Pat<dag addrmode, dag INST>
  : Pat <(f64 (sint_to_fp (i32 (sextloadi16 addrmode)))),
           (SCVTFv1i64 (f64 (EXTRACT_SUBREG
                              (SSHLLv2i32_shift
                                 (f64
                                  (EXTRACT_SUBREG
                                    (SSHLLv4i16_shift
                                      (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                        INST,
                                        hsub),
                                     0),
                                   dsub)),
                               0),
                             dsub)))>,
    Requires<[NotForCodeSize, UseAlternateSExtLoadCVTF32]>;

def : SExtLoadi16CVTf64Pat<(ro16.Wpat GPR64sp:$Rn, GPR32:$Rm, ro16.Wext:$ext),
                           (LDRHroW GPR64sp:$Rn, GPR32:$Rm, ro16.Wext:$ext)>;
def : SExtLoadi16CVTf64Pat<(ro16.Xpat GPR64sp:$Rn, GPR64:$Rm, ro16.Xext:$ext),
                           (LDRHroX GPR64sp:$Rn, GPR64:$Rm, ro16.Xext:$ext)>;
def : SExtLoadi16CVTf64Pat<(am_indexed16 GPR64sp:$Rn, uimm12s2:$offset),
                           (LDRHui GPR64sp:$Rn, uimm12s2:$offset)>;
def : SExtLoadi16CVTf64Pat<(am_unscaled16 GPR64sp:$Rn, simm9:$offset),
                           (LDURHi GPR64sp:$Rn, simm9:$offset)>;
// 32-bits -> double. 1 size step-up.
class SExtLoadi32CVTf64Pat<dag addrmode, dag INST>
  : Pat <(f64 (sint_to_fp (i32 (load addrmode)))),
           (SCVTFv1i64 (f64 (EXTRACT_SUBREG
                              (SSHLLv2i32_shift
                                (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                  INST,
                                  ssub),
                               0),
                             dsub)))>, Requires<[NotForCodeSize]>;

def : SExtLoadi32CVTf64Pat<(ro32.Wpat GPR64sp:$Rn, GPR32:$Rm, ro32.Wext:$ext),
                           (LDRSroW GPR64sp:$Rn, GPR32:$Rm, ro32.Wext:$ext)>;
def : SExtLoadi32CVTf64Pat<(ro32.Xpat GPR64sp:$Rn, GPR64:$Rm, ro32.Xext:$ext),
                           (LDRSroX GPR64sp:$Rn, GPR64:$Rm, ro32.Xext:$ext)>;
def : SExtLoadi32CVTf64Pat<(am_indexed32 GPR64sp:$Rn, uimm12s4:$offset),
                           (LDRSui GPR64sp:$Rn, uimm12s4:$offset)>;
def : SExtLoadi32CVTf64Pat<(am_unscaled32 GPR64sp:$Rn, simm9:$offset),
                           (LDURSi GPR64sp:$Rn, simm9:$offset)>;

// 64-bits -> double are handled in target specific dag combine:
// performIntToFpCombine.


//----------------------------------------------------------------------------
// AdvSIMD Load-Store Structure
//----------------------------------------------------------------------------
defm LD1 : SIMDLd1Multiple<"ld1">;
defm LD2 : SIMDLd2Multiple<"ld2">;
defm LD3 : SIMDLd3Multiple<"ld3">;
defm LD4 : SIMDLd4Multiple<"ld4">;

defm ST1 : SIMDSt1Multiple<"st1">;
defm ST2 : SIMDSt2Multiple<"st2">;
defm ST3 : SIMDSt3Multiple<"st3">;
defm ST4 : SIMDSt4Multiple<"st4">;

class Ld1Pat<ValueType ty, Instruction INST>
  : Pat<(ty (load GPR64sp:$Rn)), (INST GPR64sp:$Rn)>;

def : Ld1Pat<v16i8, LD1Onev16b>;
def : Ld1Pat<v8i16, LD1Onev8h>;
def : Ld1Pat<v4i32, LD1Onev4s>;
def : Ld1Pat<v2i64, LD1Onev2d>;
def : Ld1Pat<v8i8,  LD1Onev8b>;
def : Ld1Pat<v4i16, LD1Onev4h>;
def : Ld1Pat<v2i32, LD1Onev2s>;
def : Ld1Pat<v1i64, LD1Onev1d>;

class St1Pat<ValueType ty, Instruction INST>
  : Pat<(store ty:$Vt, GPR64sp:$Rn),
        (INST ty:$Vt, GPR64sp:$Rn)>;

def : St1Pat<v16i8, ST1Onev16b>;
def : St1Pat<v8i16, ST1Onev8h>;
def : St1Pat<v4i32, ST1Onev4s>;
def : St1Pat<v2i64, ST1Onev2d>;
def : St1Pat<v8i8,  ST1Onev8b>;
def : St1Pat<v4i16, ST1Onev4h>;
def : St1Pat<v2i32, ST1Onev2s>;
def : St1Pat<v1i64, ST1Onev1d>;

//---
// Single-element
//---

defm LD1R          : SIMDLdR<0, 0b110, 0, "ld1r", "One", 1, 2, 4, 8>;
defm LD2R          : SIMDLdR<1, 0b110, 0, "ld2r", "Two", 2, 4, 8, 16>;
defm LD3R          : SIMDLdR<0, 0b111, 0, "ld3r", "Three", 3, 6, 12, 24>;
defm LD4R          : SIMDLdR<1, 0b111, 0, "ld4r", "Four", 4, 8, 16, 32>;
let mayLoad = 1, hasSideEffects = 0 in {
defm LD1 : SIMDLdSingleBTied<0, 0b000,       "ld1", VecListOneb,   GPR64pi1>;
defm LD1 : SIMDLdSingleHTied<0, 0b010, 0,    "ld1", VecListOneh,   GPR64pi2>;
defm LD1 : SIMDLdSingleSTied<0, 0b100, 0b00, "ld1", VecListOnes,   GPR64pi4>;
defm LD1 : SIMDLdSingleDTied<0, 0b100, 0b01, "ld1", VecListOned,   GPR64pi8>;
defm LD2 : SIMDLdSingleBTied<1, 0b000,       "ld2", VecListTwob,   GPR64pi2>;
defm LD2 : SIMDLdSingleHTied<1, 0b010, 0,    "ld2", VecListTwoh,   GPR64pi4>;
defm LD2 : SIMDLdSingleSTied<1, 0b100, 0b00, "ld2", VecListTwos,   GPR64pi8>;
defm LD2 : SIMDLdSingleDTied<1, 0b100, 0b01, "ld2", VecListTwod,   GPR64pi16>;
defm LD3 : SIMDLdSingleBTied<0, 0b001,       "ld3", VecListThreeb, GPR64pi3>;
defm LD3 : SIMDLdSingleHTied<0, 0b011, 0,    "ld3", VecListThreeh, GPR64pi6>;
defm LD3 : SIMDLdSingleSTied<0, 0b101, 0b00, "ld3", VecListThrees, GPR64pi12>;
defm LD3 : SIMDLdSingleDTied<0, 0b101, 0b01, "ld3", VecListThreed, GPR64pi24>;
defm LD4 : SIMDLdSingleBTied<1, 0b001,       "ld4", VecListFourb,  GPR64pi4>;
defm LD4 : SIMDLdSingleHTied<1, 0b011, 0,    "ld4", VecListFourh,  GPR64pi8>;
defm LD4 : SIMDLdSingleSTied<1, 0b101, 0b00, "ld4", VecListFours,  GPR64pi16>;
defm LD4 : SIMDLdSingleDTied<1, 0b101, 0b01, "ld4", VecListFourd,  GPR64pi32>;
}

def : Pat<(v8i8 (AArch64dup (i32 (extloadi8 GPR64sp:$Rn)))),
          (LD1Rv8b GPR64sp:$Rn)>;
def : Pat<(v16i8 (AArch64dup (i32 (extloadi8 GPR64sp:$Rn)))),
          (LD1Rv16b GPR64sp:$Rn)>;
def : Pat<(v4i16 (AArch64dup (i32 (extloadi16 GPR64sp:$Rn)))),
          (LD1Rv4h GPR64sp:$Rn)>;
def : Pat<(v8i16 (AArch64dup (i32 (extloadi16 GPR64sp:$Rn)))),
          (LD1Rv8h GPR64sp:$Rn)>;
def : Pat<(v2i32 (AArch64dup (i32 (load GPR64sp:$Rn)))),
          (LD1Rv2s GPR64sp:$Rn)>;
def : Pat<(v4i32 (AArch64dup (i32 (load GPR64sp:$Rn)))),
          (LD1Rv4s GPR64sp:$Rn)>;
def : Pat<(v2i64 (AArch64dup (i64 (load GPR64sp:$Rn)))),
          (LD1Rv2d GPR64sp:$Rn)>;
def : Pat<(v1i64 (AArch64dup (i64 (load GPR64sp:$Rn)))),
          (LD1Rv1d GPR64sp:$Rn)>;
// Grab the floating point version too
def : Pat<(v2f32 (AArch64dup (f32 (load GPR64sp:$Rn)))),
          (LD1Rv2s GPR64sp:$Rn)>;
def : Pat<(v4f32 (AArch64dup (f32 (load GPR64sp:$Rn)))),
          (LD1Rv4s GPR64sp:$Rn)>;
def : Pat<(v2f64 (AArch64dup (f64 (load GPR64sp:$Rn)))),
          (LD1Rv2d GPR64sp:$Rn)>;
def : Pat<(v1f64 (AArch64dup (f64 (load GPR64sp:$Rn)))),
          (LD1Rv1d GPR64sp:$Rn)>;
def : Pat<(v4f16 (AArch64dup (f16 (load GPR64sp:$Rn)))),
          (LD1Rv4h GPR64sp:$Rn)>;
def : Pat<(v8f16 (AArch64dup (f16 (load GPR64sp:$Rn)))),
          (LD1Rv8h GPR64sp:$Rn)>;
def : Pat<(v4bf16 (AArch64dup (bf16 (load GPR64sp:$Rn)))),
          (LD1Rv4h GPR64sp:$Rn)>;
def : Pat<(v8bf16 (AArch64dup (bf16 (load GPR64sp:$Rn)))),
          (LD1Rv8h GPR64sp:$Rn)>;

class Ld1Lane128Pat<SDPatternOperator scalar_load, Operand VecIndex,
                    ValueType VTy, ValueType STy, Instruction LD1>
  : Pat<(vector_insert (VTy VecListOne128:$Rd),
           (STy (scalar_load GPR64sp:$Rn)), VecIndex:$idx),
        (LD1 VecListOne128:$Rd, VecIndex:$idx, GPR64sp:$Rn)>;

def : Ld1Lane128Pat<extloadi8,  VectorIndexB, v16i8, i32, LD1i8>;
def : Ld1Lane128Pat<extloadi16, VectorIndexH, v8i16, i32, LD1i16>;
def : Ld1Lane128Pat<load,       VectorIndexS, v4i32, i32, LD1i32>;
def : Ld1Lane128Pat<load,       VectorIndexS, v4f32, f32, LD1i32>;
def : Ld1Lane128Pat<load,       VectorIndexD, v2i64, i64, LD1i64>;
def : Ld1Lane128Pat<load,       VectorIndexD, v2f64, f64, LD1i64>;
def : Ld1Lane128Pat<load,       VectorIndexH, v8f16, f16, LD1i16>;
def : Ld1Lane128Pat<load,       VectorIndexH, v8bf16, bf16, LD1i16>;

class Ld1Lane64Pat<SDPatternOperator scalar_load, Operand VecIndex,
                   ValueType VTy, ValueType STy, Instruction LD1>
  : Pat<(vector_insert (VTy VecListOne64:$Rd),
           (STy (scalar_load GPR64sp:$Rn)), VecIndex:$idx),
        (EXTRACT_SUBREG
            (LD1 (SUBREG_TO_REG (i32 0), VecListOne64:$Rd, dsub),
                          VecIndex:$idx, GPR64sp:$Rn),
            dsub)>;

def : Ld1Lane64Pat<extloadi8,  VectorIndexB, v8i8,  i32, LD1i8>;
def : Ld1Lane64Pat<extloadi16, VectorIndexH, v4i16, i32, LD1i16>;
def : Ld1Lane64Pat<load,       VectorIndexS, v2i32, i32, LD1i32>;
def : Ld1Lane64Pat<load,       VectorIndexS, v2f32, f32, LD1i32>;
def : Ld1Lane64Pat<load,       VectorIndexH, v4f16, f16, LD1i16>;
def : Ld1Lane64Pat<load,       VectorIndexH, v4bf16, bf16, LD1i16>;


defm LD1 : SIMDLdSt1SingleAliases<"ld1">;
defm LD2 : SIMDLdSt2SingleAliases<"ld2">;
defm LD3 : SIMDLdSt3SingleAliases<"ld3">;
defm LD4 : SIMDLdSt4SingleAliases<"ld4">;

// Stores
defm ST1 : SIMDStSingleB<0, 0b000,       "st1", VecListOneb, GPR64pi1>;
defm ST1 : SIMDStSingleH<0, 0b010, 0,    "st1", VecListOneh, GPR64pi2>;
defm ST1 : SIMDStSingleS<0, 0b100, 0b00, "st1", VecListOnes, GPR64pi4>;
defm ST1 : SIMDStSingleD<0, 0b100, 0b01, "st1", VecListOned, GPR64pi8>;

let AddedComplexity = 19 in
class St1Lane128Pat<SDPatternOperator scalar_store, Operand VecIndex,
                    ValueType VTy, ValueType STy, Instruction ST1>
  : Pat<(scalar_store
             (STy (vector_extract (VTy VecListOne128:$Vt), VecIndex:$idx)),
             GPR64sp:$Rn),
        (ST1 VecListOne128:$Vt, VecIndex:$idx, GPR64sp:$Rn)>;

def : St1Lane128Pat<truncstorei8,  VectorIndexB, v16i8, i32, ST1i8>;
def : St1Lane128Pat<truncstorei16, VectorIndexH, v8i16, i32, ST1i16>;
def : St1Lane128Pat<store,         VectorIndexS, v4i32, i32, ST1i32>;
def : St1Lane128Pat<store,         VectorIndexS, v4f32, f32, ST1i32>;
def : St1Lane128Pat<store,         VectorIndexD, v2i64, i64, ST1i64>;
def : St1Lane128Pat<store,         VectorIndexD, v2f64, f64, ST1i64>;
def : St1Lane128Pat<store,         VectorIndexH, v8f16, f16, ST1i16>;
def : St1Lane128Pat<store,         VectorIndexH, v8bf16, bf16, ST1i16>;

let AddedComplexity = 19 in
class St1Lane64Pat<SDPatternOperator scalar_store, Operand VecIndex,
                   ValueType VTy, ValueType STy, Instruction ST1>
  : Pat<(scalar_store
             (STy (vector_extract (VTy VecListOne64:$Vt), VecIndex:$idx)),
             GPR64sp:$Rn),
        (ST1 (SUBREG_TO_REG (i32 0), VecListOne64:$Vt, dsub),
             VecIndex:$idx, GPR64sp:$Rn)>;

def : St1Lane64Pat<truncstorei8,  VectorIndexB, v8i8, i32, ST1i8>;
def : St1Lane64Pat<truncstorei16, VectorIndexH, v4i16, i32, ST1i16>;
def : St1Lane64Pat<store,         VectorIndexS, v2i32, i32, ST1i32>;
def : St1Lane64Pat<store,         VectorIndexS, v2f32, f32, ST1i32>;
def : St1Lane64Pat<store,         VectorIndexH, v4f16, f16, ST1i16>;
def : St1Lane64Pat<store,         VectorIndexH, v4bf16, bf16, ST1i16>;

multiclass St1LanePost64Pat<SDPatternOperator scalar_store, Operand VecIndex,
                             ValueType VTy, ValueType STy, Instruction ST1,
                             int offset> {
  def : Pat<(scalar_store
              (STy (vector_extract (VTy VecListOne64:$Vt), VecIndex:$idx)),
              GPR64sp:$Rn, offset),
        (ST1 (SUBREG_TO_REG (i32 0), VecListOne64:$Vt, dsub),
             VecIndex:$idx, GPR64sp:$Rn, XZR)>;

  def : Pat<(scalar_store
              (STy (vector_extract (VTy VecListOne64:$Vt), VecIndex:$idx)),
              GPR64sp:$Rn, GPR64:$Rm),
        (ST1 (SUBREG_TO_REG (i32 0), VecListOne64:$Vt, dsub),
             VecIndex:$idx, GPR64sp:$Rn, $Rm)>;
}

defm : St1LanePost64Pat<post_truncsti8, VectorIndexB, v8i8, i32, ST1i8_POST, 1>;
defm : St1LanePost64Pat<post_truncsti16, VectorIndexH, v4i16, i32, ST1i16_POST,
                        2>;
defm : St1LanePost64Pat<post_store, VectorIndexS, v2i32, i32, ST1i32_POST, 4>;
defm : St1LanePost64Pat<post_store, VectorIndexS, v2f32, f32, ST1i32_POST, 4>;
defm : St1LanePost64Pat<post_store, VectorIndexD, v1i64, i64, ST1i64_POST, 8>;
defm : St1LanePost64Pat<post_store, VectorIndexD, v1f64, f64, ST1i64_POST, 8>;
defm : St1LanePost64Pat<post_store, VectorIndexH, v4f16, f16, ST1i16_POST, 2>;
defm : St1LanePost64Pat<post_store, VectorIndexH, v4bf16, bf16, ST1i16_POST, 2>;

multiclass St1LanePost128Pat<SDPatternOperator scalar_store, Operand VecIndex,
                             ValueType VTy, ValueType STy, Instruction ST1,
                             int offset> {
  def : Pat<(scalar_store
              (STy (vector_extract (VTy VecListOne128:$Vt), VecIndex:$idx)),
              GPR64sp:$Rn, offset),
        (ST1 VecListOne128:$Vt, VecIndex:$idx, GPR64sp:$Rn, XZR)>;

  def : Pat<(scalar_store
              (STy (vector_extract (VTy VecListOne128:$Vt), VecIndex:$idx)),
              GPR64sp:$Rn, GPR64:$Rm),
        (ST1 VecListOne128:$Vt, VecIndex:$idx, GPR64sp:$Rn, $Rm)>;
}

defm : St1LanePost128Pat<post_truncsti8, VectorIndexB, v16i8, i32, ST1i8_POST,
                         1>;
defm : St1LanePost128Pat<post_truncsti16, VectorIndexH, v8i16, i32, ST1i16_POST,
                         2>;
defm : St1LanePost128Pat<post_store, VectorIndexS, v4i32, i32, ST1i32_POST, 4>;
defm : St1LanePost128Pat<post_store, VectorIndexS, v4f32, f32, ST1i32_POST, 4>;
defm : St1LanePost128Pat<post_store, VectorIndexD, v2i64, i64, ST1i64_POST, 8>;
defm : St1LanePost128Pat<post_store, VectorIndexD, v2f64, f64, ST1i64_POST, 8>;
defm : St1LanePost128Pat<post_store, VectorIndexH, v8f16, f16, ST1i16_POST, 2>;
defm : St1LanePost128Pat<post_store, VectorIndexH, v8bf16, bf16, ST1i16_POST, 2>;

let mayStore = 1, hasSideEffects = 0 in {
defm ST2 : SIMDStSingleB<1, 0b000,       "st2", VecListTwob,   GPR64pi2>;
defm ST2 : SIMDStSingleH<1, 0b010, 0,    "st2", VecListTwoh,   GPR64pi4>;
defm ST2 : SIMDStSingleS<1, 0b100, 0b00, "st2", VecListTwos,   GPR64pi8>;
defm ST2 : SIMDStSingleD<1, 0b100, 0b01, "st2", VecListTwod,   GPR64pi16>;
defm ST3 : SIMDStSingleB<0, 0b001,       "st3", VecListThreeb, GPR64pi3>;
defm ST3 : SIMDStSingleH<0, 0b011, 0,    "st3", VecListThreeh, GPR64pi6>;
defm ST3 : SIMDStSingleS<0, 0b101, 0b00, "st3", VecListThrees, GPR64pi12>;
defm ST3 : SIMDStSingleD<0, 0b101, 0b01, "st3", VecListThreed, GPR64pi24>;
defm ST4 : SIMDStSingleB<1, 0b001,       "st4", VecListFourb,  GPR64pi4>;
defm ST4 : SIMDStSingleH<1, 0b011, 0,    "st4", VecListFourh,  GPR64pi8>;
defm ST4 : SIMDStSingleS<1, 0b101, 0b00, "st4", VecListFours,  GPR64pi16>;
defm ST4 : SIMDStSingleD<1, 0b101, 0b01, "st4", VecListFourd,  GPR64pi32>;
}

defm ST1 : SIMDLdSt1SingleAliases<"st1">;
defm ST2 : SIMDLdSt2SingleAliases<"st2">;
defm ST3 : SIMDLdSt3SingleAliases<"st3">;
defm ST4 : SIMDLdSt4SingleAliases<"st4">;

//----------------------------------------------------------------------------
// Crypto extensions
//----------------------------------------------------------------------------

let Predicates = [HasAES] in {
def AESErr   : AESTiedInst<0b0100, "aese",   int_aarch64_crypto_aese>;
def AESDrr   : AESTiedInst<0b0101, "aesd",   int_aarch64_crypto_aesd>;
def AESMCrr  : AESInst<    0b0110, "aesmc",  int_aarch64_crypto_aesmc>;
def AESIMCrr : AESInst<    0b0111, "aesimc", int_aarch64_crypto_aesimc>;
}

// Pseudo instructions for AESMCrr/AESIMCrr with a register constraint required
// for AES fusion on some CPUs.
let hasSideEffects = 0, mayStore = 0, mayLoad = 0 in {
def AESMCrrTied: Pseudo<(outs V128:$Rd), (ins V128:$Rn), [], "$Rn = $Rd">,
                        Sched<[WriteV]>;
def AESIMCrrTied: Pseudo<(outs V128:$Rd), (ins V128:$Rn), [], "$Rn = $Rd">,
                         Sched<[WriteV]>;
}

// Only use constrained versions of AES(I)MC instructions if they are paired with
// AESE/AESD.
def : Pat<(v16i8 (int_aarch64_crypto_aesmc
            (v16i8 (int_aarch64_crypto_aese (v16i8 V128:$src1),
                                            (v16i8 V128:$src2))))),
          (v16i8 (AESMCrrTied (v16i8 (AESErr (v16i8 V128:$src1),
                                             (v16i8 V128:$src2)))))>,
          Requires<[HasFuseAES]>;

def : Pat<(v16i8 (int_aarch64_crypto_aesimc
            (v16i8 (int_aarch64_crypto_aesd (v16i8 V128:$src1),
                                            (v16i8 V128:$src2))))),
          (v16i8 (AESIMCrrTied (v16i8 (AESDrr (v16i8 V128:$src1),
                                              (v16i8 V128:$src2)))))>,
          Requires<[HasFuseAES]>;

let Predicates = [HasSHA2] in {
def SHA1Crrr     : SHATiedInstQSV<0b000, "sha1c",   int_aarch64_crypto_sha1c>;
def SHA1Prrr     : SHATiedInstQSV<0b001, "sha1p",   int_aarch64_crypto_sha1p>;
def SHA1Mrrr     : SHATiedInstQSV<0b010, "sha1m",   int_aarch64_crypto_sha1m>;
def SHA1SU0rrr   : SHATiedInstVVV<0b011, "sha1su0", int_aarch64_crypto_sha1su0>;
def SHA256Hrrr   : SHATiedInstQQV<0b100, "sha256h", int_aarch64_crypto_sha256h>;
def SHA256H2rrr  : SHATiedInstQQV<0b101, "sha256h2",int_aarch64_crypto_sha256h2>;
def SHA256SU1rrr :SHATiedInstVVV<0b110, "sha256su1",int_aarch64_crypto_sha256su1>;

def SHA1Hrr     : SHAInstSS<    0b0000, "sha1h",    int_aarch64_crypto_sha1h>;
def SHA1SU1rr   : SHATiedInstVV<0b0001, "sha1su1",  int_aarch64_crypto_sha1su1>;
def SHA256SU0rr : SHATiedInstVV<0b0010, "sha256su0",int_aarch64_crypto_sha256su0>;
}

//----------------------------------------------------------------------------
// Compiler-pseudos
//----------------------------------------------------------------------------
// FIXME: Like for X86, these should go in their own separate .td file.

def def32 : PatLeaf<(i32 GPR32:$src), [{
  return isDef32(*N);
}]>;

// 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:$src)), (SUBREG_TO_REG (i64 0), GPR32:$src, sub_32)>;

// For an anyext, we don't care what the high bits are, so we can perform an
// INSERT_SUBREF into an IMPLICIT_DEF.
def : Pat<(i64 (anyext GPR32:$src)),
          (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GPR32:$src, sub_32)>;

// When we need to explicitly zero-extend, we use a 32-bit MOV instruction and
// then assert the extension has happened.
def : Pat<(i64 (zext GPR32:$src)),
          (SUBREG_TO_REG (i32 0), (ORRWrs WZR, GPR32:$src, 0), sub_32)>;

// To sign extend, we use a signed bitfield move instruction (SBFM) on the
// containing super-reg.
def : Pat<(i64 (sext GPR32:$src)),
   (SBFMXri (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GPR32:$src, sub_32), 0, 31)>;
def : Pat<(i64 (sext_inreg GPR64:$src, i32)), (SBFMXri GPR64:$src, 0, 31)>;
def : Pat<(i64 (sext_inreg GPR64:$src, i16)), (SBFMXri GPR64:$src, 0, 15)>;
def : Pat<(i64 (sext_inreg GPR64:$src, i8)),  (SBFMXri GPR64:$src, 0, 7)>;
def : Pat<(i64 (sext_inreg GPR64:$src, i1)),  (SBFMXri GPR64:$src, 0, 0)>;
def : Pat<(i32 (sext_inreg GPR32:$src, i16)), (SBFMWri GPR32:$src, 0, 15)>;
def : Pat<(i32 (sext_inreg GPR32:$src, i8)),  (SBFMWri GPR32:$src, 0, 7)>;
def : Pat<(i32 (sext_inreg GPR32:$src, i1)),  (SBFMWri GPR32:$src, 0, 0)>;

def : Pat<(shl (sext_inreg GPR32:$Rn, i8), (i64 imm0_31:$imm)),
          (SBFMWri GPR32:$Rn, (i64 (i32shift_a       imm0_31:$imm)),
                              (i64 (i32shift_sext_i8 imm0_31:$imm)))>;
def : Pat<(shl (sext_inreg GPR64:$Rn, i8), (i64 imm0_63:$imm)),
          (SBFMXri GPR64:$Rn, (i64 (i64shift_a imm0_63:$imm)),
                              (i64 (i64shift_sext_i8 imm0_63:$imm)))>;

def : Pat<(shl (sext_inreg GPR32:$Rn, i16), (i64 imm0_31:$imm)),
          (SBFMWri GPR32:$Rn, (i64 (i32shift_a        imm0_31:$imm)),
                              (i64 (i32shift_sext_i16 imm0_31:$imm)))>;
def : Pat<(shl (sext_inreg GPR64:$Rn, i16), (i64 imm0_63:$imm)),
          (SBFMXri GPR64:$Rn, (i64 (i64shift_a        imm0_63:$imm)),
                              (i64 (i64shift_sext_i16 imm0_63:$imm)))>;

def : Pat<(shl (i64 (sext GPR32:$Rn)), (i64 imm0_63:$imm)),
          (SBFMXri (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GPR32:$Rn, sub_32),
                   (i64 (i64shift_a        imm0_63:$imm)),
                   (i64 (i64shift_sext_i32 imm0_63:$imm)))>;

// sra patterns have an AddedComplexity of 10, so make sure we have a higher
// AddedComplexity for the following patterns since we want to match sext + sra
// patterns before we attempt to match a single sra node.
let AddedComplexity = 20 in {
// We support all sext + sra combinations which preserve at least one bit of the
// original value which is to be sign extended. E.g. we support shifts up to
// bitwidth-1 bits.
def : Pat<(sra (sext_inreg GPR32:$Rn, i8), (i64 imm0_7:$imm)),
          (SBFMWri GPR32:$Rn, (i64 imm0_7:$imm), 7)>;
def : Pat<(sra (sext_inreg GPR64:$Rn, i8), (i64 imm0_7:$imm)),
          (SBFMXri GPR64:$Rn, (i64 imm0_7:$imm), 7)>;

def : Pat<(sra (sext_inreg GPR32:$Rn, i16), (i64 imm0_15:$imm)),
          (SBFMWri GPR32:$Rn, (i64 imm0_15:$imm), 15)>;
def : Pat<(sra (sext_inreg GPR64:$Rn, i16), (i64 imm0_15:$imm)),
          (SBFMXri GPR64:$Rn, (i64 imm0_15:$imm), 15)>;

def : Pat<(sra (i64 (sext GPR32:$Rn)), (i64 imm0_31:$imm)),
          (SBFMXri (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GPR32:$Rn, sub_32),
                   (i64 imm0_31:$imm), 31)>;
} // AddedComplexity = 20

// To truncate, we can simply extract from a subregister.
def : Pat<(i32 (trunc GPR64sp:$src)),
          (i32 (EXTRACT_SUBREG GPR64sp:$src, sub_32))>;

// __builtin_trap() uses the BRK instruction on AArch64.
def : Pat<(trap), (BRK 1)>;
def : Pat<(debugtrap), (BRK 0xF000)>, Requires<[IsWindows]>;

// Multiply high patterns which multiply the lower subvector using smull/umull
// and the upper subvector with smull2/umull2. Then shuffle the high the high
// part of both results together.
def : Pat<(v16i8 (mulhs V128:$Rn, V128:$Rm)),
          (UZP2v16i8
           (SMULLv8i8_v8i16 (EXTRACT_SUBREG V128:$Rn, dsub),
                            (EXTRACT_SUBREG V128:$Rm, dsub)),
           (SMULLv16i8_v8i16 V128:$Rn, V128:$Rm))>;
def : Pat<(v8i16 (mulhs V128:$Rn, V128:$Rm)),
          (UZP2v8i16
           (SMULLv4i16_v4i32 (EXTRACT_SUBREG V128:$Rn, dsub),
                             (EXTRACT_SUBREG V128:$Rm, dsub)),
           (SMULLv8i16_v4i32 V128:$Rn, V128:$Rm))>;
def : Pat<(v4i32 (mulhs V128:$Rn, V128:$Rm)),
          (UZP2v4i32
           (SMULLv2i32_v2i64 (EXTRACT_SUBREG V128:$Rn, dsub),
                             (EXTRACT_SUBREG V128:$Rm, dsub)),
           (SMULLv4i32_v2i64 V128:$Rn, V128:$Rm))>;

def : Pat<(v16i8 (mulhu V128:$Rn, V128:$Rm)),
          (UZP2v16i8
           (UMULLv8i8_v8i16 (EXTRACT_SUBREG V128:$Rn, dsub),
                            (EXTRACT_SUBREG V128:$Rm, dsub)),
           (UMULLv16i8_v8i16 V128:$Rn, V128:$Rm))>;
def : Pat<(v8i16 (mulhu V128:$Rn, V128:$Rm)),
          (UZP2v8i16
           (UMULLv4i16_v4i32 (EXTRACT_SUBREG V128:$Rn, dsub),
                             (EXTRACT_SUBREG V128:$Rm, dsub)),
           (UMULLv8i16_v4i32 V128:$Rn, V128:$Rm))>;
def : Pat<(v4i32 (mulhu V128:$Rn, V128:$Rm)),
          (UZP2v4i32
           (UMULLv2i32_v2i64 (EXTRACT_SUBREG V128:$Rn, dsub),
                             (EXTRACT_SUBREG V128:$Rm, dsub)),
           (UMULLv4i32_v2i64 V128:$Rn, V128:$Rm))>;

// Conversions within AdvSIMD types in the same register size are free.
// But because we need a consistent lane ordering, in big endian many
// conversions require one or more REV instructions.
//
// Consider a simple memory load followed by a bitconvert then a store.
//   v0 = load v2i32
//   v1 = BITCAST v2i32 v0 to v4i16
//        store v4i16 v2
//
// In big endian mode every memory access has an implicit byte swap. LDR and
// STR do a 64-bit byte swap, whereas LD1/ST1 do a byte swap per lane - that
// is, they treat the vector as a sequence of elements to be byte-swapped.
// The two pairs of instructions are fundamentally incompatible. We've decided
// to use LD1/ST1 only to simplify compiler implementation.
//
// LD1/ST1 perform the equivalent of a sequence of LDR/STR + REV. This makes
// the original code sequence:
//   v0 = load v2i32
//   v1 = REV v2i32                  (implicit)
//   v2 = BITCAST v2i32 v1 to v4i16
//   v3 = REV v4i16 v2               (implicit)
//        store v4i16 v3
//
// But this is now broken - the value stored is different to the value loaded
// due to lane reordering. To fix this, on every BITCAST we must perform two
// other REVs:
//   v0 = load v2i32
//   v1 = REV v2i32                  (implicit)
//   v2 = REV v2i32
//   v3 = BITCAST v2i32 v2 to v4i16
//   v4 = REV v4i16
//   v5 = REV v4i16 v4               (implicit)
//        store v4i16 v5
//
// This means an extra two instructions, but actually in most cases the two REV
// instructions can be combined into one. For example:
//   (REV64_2s (REV64_4h X)) === (REV32_4h X)
//
// There is also no 128-bit REV instruction. This must be synthesized with an
// EXT instruction.
//
// Most bitconverts require some sort of conversion. The only exceptions are:
//   a) Identity conversions -  vNfX <-> vNiX
//   b) Single-lane-to-scalar - v1fX <-> fX or v1iX <-> iX
//

// Natural vector casts (64 bit)
def : Pat<(v8i8 (AArch64NvCast (v2i32 FPR64:$src))), (v8i8 FPR64:$src)>;
def : Pat<(v4i16 (AArch64NvCast (v2i32 FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v4f16 (AArch64NvCast (v2i32 FPR64:$src))), (v4f16 FPR64:$src)>;
def : Pat<(v4bf16 (AArch64NvCast (v2i32 FPR64:$src))), (v4bf16 FPR64:$src)>;
def : Pat<(v2i32 (AArch64NvCast (v2i32 FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v2f32 (AArch64NvCast (v2i32 FPR64:$src))), (v2f32 FPR64:$src)>;
def : Pat<(v1i64 (AArch64NvCast (v2i32 FPR64:$src))), (v1i64 FPR64:$src)>;

def : Pat<(v8i8 (AArch64NvCast (v4i16 FPR64:$src))), (v8i8 FPR64:$src)>;
def : Pat<(v4i16 (AArch64NvCast (v4i16 FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v4f16 (AArch64NvCast (v4i16 FPR64:$src))), (v4f16 FPR64:$src)>;
def : Pat<(v4bf16 (AArch64NvCast (v4i16 FPR64:$src))), (v4bf16 FPR64:$src)>;
def : Pat<(v2i32 (AArch64NvCast (v4i16 FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v1i64 (AArch64NvCast (v4i16 FPR64:$src))), (v1i64 FPR64:$src)>;

def : Pat<(v8i8 (AArch64NvCast (v8i8 FPR64:$src))), (v8i8 FPR64:$src)>;
def : Pat<(v4i16 (AArch64NvCast (v8i8 FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v4f16 (AArch64NvCast (v8i8 FPR64:$src))), (v4f16 FPR64:$src)>;
def : Pat<(v4bf16 (AArch64NvCast (v8i8 FPR64:$src))), (v4bf16 FPR64:$src)>;
def : Pat<(v2i32 (AArch64NvCast (v8i8 FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v2f32 (AArch64NvCast (v8i8 FPR64:$src))), (v2f32 FPR64:$src)>;
def : Pat<(v1i64 (AArch64NvCast (v8i8 FPR64:$src))), (v1i64 FPR64:$src)>;

def : Pat<(v8i8 (AArch64NvCast (f64 FPR64:$src))), (v8i8 FPR64:$src)>;
def : Pat<(v4i16 (AArch64NvCast (f64 FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v4f16 (AArch64NvCast (f64 FPR64:$src))), (v4f16 FPR64:$src)>;
def : Pat<(v4bf16 (AArch64NvCast (f64 FPR64:$src))), (v4bf16 FPR64:$src)>;
def : Pat<(v2i32 (AArch64NvCast (f64 FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v2f32 (AArch64NvCast (f64 FPR64:$src))), (v2f32 FPR64:$src)>;
def : Pat<(v1i64 (AArch64NvCast (f64 FPR64:$src))), (v1i64 FPR64:$src)>;
def : Pat<(v1f64 (AArch64NvCast (f64 FPR64:$src))), (v1f64 FPR64:$src)>;

def : Pat<(v8i8 (AArch64NvCast (v2f32 FPR64:$src))), (v8i8 FPR64:$src)>;
def : Pat<(v4i16 (AArch64NvCast (v2f32 FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v2i32 (AArch64NvCast (v2f32 FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v2f32 (AArch64NvCast (v2f32 FPR64:$src))), (v2f32 FPR64:$src)>;
def : Pat<(v1i64 (AArch64NvCast (v2f32 FPR64:$src))), (v1i64 FPR64:$src)>;
def : Pat<(v1f64 (AArch64NvCast (v2f32 FPR64:$src))), (v1f64 FPR64:$src)>;

// Natural vector casts (128 bit)
def : Pat<(v16i8 (AArch64NvCast (v4i32 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v8i16 (AArch64NvCast (v4i32 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8f16 (AArch64NvCast (v4i32 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8bf16 (AArch64NvCast (v4i32 FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v4i32 (AArch64NvCast (v4i32 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4f32 (AArch64NvCast (v4i32 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v2i64 (AArch64NvCast (v4i32 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2f64 (AArch64NvCast (v4i32 FPR128:$src))), (v2f64 FPR128:$src)>;

def : Pat<(v16i8 (AArch64NvCast (v8i16 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v8i16 (AArch64NvCast (v8i16 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8f16 (AArch64NvCast (v8i16 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8bf16 (AArch64NvCast (v8i16 FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v4i32 (AArch64NvCast (v8i16 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v2i64 (AArch64NvCast (v8i16 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v4f32 (AArch64NvCast (v8i16 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v2f64 (AArch64NvCast (v8i16 FPR128:$src))), (v2f64 FPR128:$src)>;

def : Pat<(v16i8 (AArch64NvCast (v16i8 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v8i16 (AArch64NvCast (v16i8 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8f16 (AArch64NvCast (v16i8 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8bf16 (AArch64NvCast (v16i8 FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v4i32 (AArch64NvCast (v16i8 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v2i64 (AArch64NvCast (v16i8 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v4f32 (AArch64NvCast (v16i8 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v2f64 (AArch64NvCast (v16i8 FPR128:$src))), (v2f64 FPR128:$src)>;

def : Pat<(v16i8 (AArch64NvCast (v2i64 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v8i16 (AArch64NvCast (v2i64 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8f16 (AArch64NvCast (v2i64 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8bf16 (AArch64NvCast (v2i64 FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v4i32 (AArch64NvCast (v2i64 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v2i64 (AArch64NvCast (v2i64 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v4f32 (AArch64NvCast (v2i64 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v2f64 (AArch64NvCast (v2i64 FPR128:$src))), (v2f64 FPR128:$src)>;

def : Pat<(v16i8 (AArch64NvCast (v4f32 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v8i16 (AArch64NvCast (v4f32 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v4i32 (AArch64NvCast (v4f32 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4f32 (AArch64NvCast (v4f32 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v2i64 (AArch64NvCast (v4f32 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v8f16 (AArch64NvCast (v4f32 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8bf16 (AArch64NvCast (v4f32 FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v2f64 (AArch64NvCast (v4f32 FPR128:$src))), (v2f64 FPR128:$src)>;

def : Pat<(v16i8 (AArch64NvCast (v2f64 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v8i16 (AArch64NvCast (v2f64 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v4i32 (AArch64NvCast (v2f64 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v2i64 (AArch64NvCast (v2f64 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2f64 (AArch64NvCast (v2f64 FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v8f16 (AArch64NvCast (v2f64 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8bf16 (AArch64NvCast (v2f64 FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v4f32 (AArch64NvCast (v2f64 FPR128:$src))), (v4f32 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v8i8  (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;
def : Pat<(v4i16 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;
def : Pat<(v2i32 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;
def : Pat<(v4f16 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;
def : Pat<(v4bf16 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;
def : Pat<(v2f32 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;

def : Pat<(i64 (bitconvert (v8i8  V64:$Vn))),
          (COPY_TO_REGCLASS V64:$Vn, GPR64)>;
def : Pat<(i64 (bitconvert (v4i16 V64:$Vn))),
          (COPY_TO_REGCLASS V64:$Vn, GPR64)>;
def : Pat<(i64 (bitconvert (v2i32 V64:$Vn))),
          (COPY_TO_REGCLASS V64:$Vn, GPR64)>;
def : Pat<(i64 (bitconvert (v4f16 V64:$Vn))),
          (COPY_TO_REGCLASS V64:$Vn, GPR64)>;
def : Pat<(i64 (bitconvert (v4bf16 V64:$Vn))),
          (COPY_TO_REGCLASS V64:$Vn, GPR64)>;
def : Pat<(i64 (bitconvert (v2f32 V64:$Vn))),
          (COPY_TO_REGCLASS V64:$Vn, GPR64)>;
def : Pat<(i64 (bitconvert (v1f64 V64:$Vn))),
          (COPY_TO_REGCLASS V64:$Vn, GPR64)>;
}
let Predicates = [IsBE] in {
def : Pat<(v8i8  (bitconvert GPR64:$Xn)),
                 (REV64v8i8 (COPY_TO_REGCLASS GPR64:$Xn, FPR64))>;
def : Pat<(v4i16 (bitconvert GPR64:$Xn)),
                 (REV64v4i16 (COPY_TO_REGCLASS GPR64:$Xn, FPR64))>;
def : Pat<(v2i32 (bitconvert GPR64:$Xn)),
                 (REV64v2i32 (COPY_TO_REGCLASS GPR64:$Xn, FPR64))>;
def : Pat<(v4f16 (bitconvert GPR64:$Xn)),
                 (REV64v4i16 (COPY_TO_REGCLASS GPR64:$Xn, FPR64))>;
def : Pat<(v4bf16 (bitconvert GPR64:$Xn)),
                  (REV64v4i16 (COPY_TO_REGCLASS GPR64:$Xn, FPR64))>;
def : Pat<(v2f32 (bitconvert GPR64:$Xn)),
                 (REV64v2i32 (COPY_TO_REGCLASS GPR64:$Xn, FPR64))>;

def : Pat<(i64 (bitconvert (v8i8  V64:$Vn))),
          (REV64v8i8 (COPY_TO_REGCLASS V64:$Vn, GPR64))>;
def : Pat<(i64 (bitconvert (v4i16 V64:$Vn))),
          (REV64v4i16 (COPY_TO_REGCLASS V64:$Vn, GPR64))>;
def : Pat<(i64 (bitconvert (v2i32 V64:$Vn))),
          (REV64v2i32 (COPY_TO_REGCLASS V64:$Vn, GPR64))>;
def : Pat<(i64 (bitconvert (v4f16 V64:$Vn))),
          (REV64v4i16 (COPY_TO_REGCLASS V64:$Vn, GPR64))>;
def : Pat<(i64 (bitconvert (v4bf16 V64:$Vn))),
          (REV64v4i16 (COPY_TO_REGCLASS V64:$Vn, GPR64))>;
def : Pat<(i64 (bitconvert (v2f32 V64:$Vn))),
          (REV64v2i32 (COPY_TO_REGCLASS V64:$Vn, GPR64))>;
}
def : Pat<(v1i64 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;
def : Pat<(v1f64 (bitconvert GPR64:$Xn)), (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;
def : Pat<(i64 (bitconvert (v1i64 V64:$Vn))),
          (COPY_TO_REGCLASS V64:$Vn, GPR64)>;
def : Pat<(v1i64 (scalar_to_vector GPR64:$Xn)),
          (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;
def : Pat<(v1f64 (scalar_to_vector GPR64:$Xn)),
          (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;
def : Pat<(v1f64 (scalar_to_vector (f64 FPR64:$Xn))), (v1f64 FPR64:$Xn)>;

def : Pat<(f32 (bitconvert (i32 GPR32:$Xn))),
          (COPY_TO_REGCLASS GPR32:$Xn, FPR32)>;
def : Pat<(i32 (bitconvert (f32 FPR32:$Xn))),
          (COPY_TO_REGCLASS FPR32:$Xn, GPR32)>;
def : Pat<(f64 (bitconvert (i64 GPR64:$Xn))),
          (COPY_TO_REGCLASS GPR64:$Xn, FPR64)>;
def : Pat<(i64 (bitconvert (f64 FPR64:$Xn))),
          (COPY_TO_REGCLASS FPR64:$Xn, GPR64)>;
def : Pat<(i64 (bitconvert (v1f64 V64:$Vn))),
          (COPY_TO_REGCLASS V64:$Vn, GPR64)>;

let Predicates = [IsLE] in {
def : Pat<(v1i64 (bitconvert (v2i32 FPR64:$src))), (v1i64 FPR64:$src)>;
def : Pat<(v1i64 (bitconvert (v4i16 FPR64:$src))), (v1i64 FPR64:$src)>;
def : Pat<(v1i64 (bitconvert (v8i8  FPR64:$src))), (v1i64 FPR64:$src)>;
def : Pat<(v1i64 (bitconvert (v4f16 FPR64:$src))), (v1i64 FPR64:$src)>;
def : Pat<(v1i64 (bitconvert (v4bf16 FPR64:$src))), (v1i64 FPR64:$src)>;
def : Pat<(v1i64 (bitconvert (v2f32 FPR64:$src))), (v1i64 FPR64:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v1i64 (bitconvert (v2i32 FPR64:$src))),
                             (v1i64 (REV64v2i32 FPR64:$src))>;
def : Pat<(v1i64 (bitconvert (v4i16 FPR64:$src))),
                             (v1i64 (REV64v4i16 FPR64:$src))>;
def : Pat<(v1i64 (bitconvert (v8i8  FPR64:$src))),
                             (v1i64 (REV64v8i8 FPR64:$src))>;
def : Pat<(v1i64 (bitconvert (v4f16 FPR64:$src))),
                             (v1i64 (REV64v4i16 FPR64:$src))>;
def : Pat<(v1i64 (bitconvert (v4bf16 FPR64:$src))),
                             (v1i64 (REV64v4i16 FPR64:$src))>;
def : Pat<(v1i64 (bitconvert (v2f32 FPR64:$src))),
                             (v1i64 (REV64v2i32 FPR64:$src))>;
}
def : Pat<(v1i64 (bitconvert (v1f64 FPR64:$src))), (v1i64 FPR64:$src)>;
def : Pat<(v1i64 (bitconvert (f64   FPR64:$src))), (v1i64 FPR64:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v2i32 (bitconvert (v1i64 FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v2i32 (bitconvert (v4i16 FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v2i32 (bitconvert (v8i8  FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v2i32 (bitconvert (f64   FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v2i32 (bitconvert (v1f64 FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v2i32 (bitconvert (v4f16 FPR64:$src))), (v2i32 FPR64:$src)>;
def : Pat<(v2i32 (bitconvert (v4bf16 FPR64:$src))), (v2i32 FPR64:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v2i32 (bitconvert (v1i64 FPR64:$src))),
                             (v2i32 (REV64v2i32 FPR64:$src))>;
def : Pat<(v2i32 (bitconvert (v4i16 FPR64:$src))),
                             (v2i32 (REV32v4i16 FPR64:$src))>;
def : Pat<(v2i32 (bitconvert (v8i8  FPR64:$src))),
                             (v2i32 (REV32v8i8 FPR64:$src))>;
def : Pat<(v2i32 (bitconvert (f64   FPR64:$src))),
                             (v2i32 (REV64v2i32 FPR64:$src))>;
def : Pat<(v2i32 (bitconvert (v1f64 FPR64:$src))),
                             (v2i32 (REV64v2i32 FPR64:$src))>;
def : Pat<(v2i32 (bitconvert (v4f16 FPR64:$src))),
                             (v2i32 (REV32v4i16 FPR64:$src))>;
def : Pat<(v2i32 (bitconvert (v4bf16 FPR64:$src))),
                             (v2i32 (REV32v4i16 FPR64:$src))>;
}
def : Pat<(v2i32 (bitconvert (v2f32 FPR64:$src))), (v2i32 FPR64:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v4i16 (bitconvert (v1i64 FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v4i16 (bitconvert (v2i32 FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v4i16 (bitconvert (v8i8  FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v4i16 (bitconvert (f64   FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v4i16 (bitconvert (v2f32 FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v4i16 (bitconvert (v1f64 FPR64:$src))), (v4i16 FPR64:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v4i16 (bitconvert (v1i64 FPR64:$src))),
                             (v4i16 (REV64v4i16 FPR64:$src))>;
def : Pat<(v4i16 (bitconvert (v2i32 FPR64:$src))),
                             (v4i16 (REV32v4i16 FPR64:$src))>;
def : Pat<(v4i16 (bitconvert (v8i8  FPR64:$src))),
                             (v4i16 (REV16v8i8 FPR64:$src))>;
def : Pat<(v4i16 (bitconvert (f64   FPR64:$src))),
                             (v4i16 (REV64v4i16 FPR64:$src))>;
def : Pat<(v4i16 (bitconvert (v2f32 FPR64:$src))),
                             (v4i16 (REV32v4i16 FPR64:$src))>;
def : Pat<(v4i16 (bitconvert (v1f64 FPR64:$src))),
                             (v4i16 (REV64v4i16 FPR64:$src))>;
}
def : Pat<(v4i16 (bitconvert (v4f16 FPR64:$src))), (v4i16 FPR64:$src)>;
def : Pat<(v4i16 (bitconvert (v4bf16 FPR64:$src))), (v4i16 FPR64:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v4f16 (bitconvert (v1i64 FPR64:$src))), (v4f16 FPR64:$src)>;
def : Pat<(v4f16 (bitconvert (v2i32 FPR64:$src))), (v4f16 FPR64:$src)>;
def : Pat<(v4f16 (bitconvert (v8i8  FPR64:$src))), (v4f16 FPR64:$src)>;
def : Pat<(v4f16 (bitconvert (f64   FPR64:$src))), (v4f16 FPR64:$src)>;
def : Pat<(v4f16 (bitconvert (v2f32 FPR64:$src))), (v4f16 FPR64:$src)>;
def : Pat<(v4f16 (bitconvert (v1f64 FPR64:$src))), (v4f16 FPR64:$src)>;

def : Pat<(v4bf16 (bitconvert (v1i64 FPR64:$src))), (v4bf16 FPR64:$src)>;
def : Pat<(v4bf16 (bitconvert (v2i32 FPR64:$src))), (v4bf16 FPR64:$src)>;
def : Pat<(v4bf16 (bitconvert (v8i8  FPR64:$src))), (v4bf16 FPR64:$src)>;
def : Pat<(v4bf16 (bitconvert (f64   FPR64:$src))), (v4bf16 FPR64:$src)>;
def : Pat<(v4bf16 (bitconvert (v2f32 FPR64:$src))), (v4bf16 FPR64:$src)>;
def : Pat<(v4bf16 (bitconvert (v1f64 FPR64:$src))), (v4bf16 FPR64:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v4f16 (bitconvert (v1i64 FPR64:$src))),
                             (v4f16 (REV64v4i16 FPR64:$src))>;
def : Pat<(v4f16 (bitconvert (v2i32 FPR64:$src))),
                             (v4f16 (REV32v4i16 FPR64:$src))>;
def : Pat<(v4f16 (bitconvert (v8i8  FPR64:$src))),
                             (v4f16 (REV16v8i8 FPR64:$src))>;
def : Pat<(v4f16 (bitconvert (f64   FPR64:$src))),
                             (v4f16 (REV64v4i16 FPR64:$src))>;
def : Pat<(v4f16 (bitconvert (v2f32 FPR64:$src))),
                             (v4f16 (REV32v4i16 FPR64:$src))>;
def : Pat<(v4f16 (bitconvert (v1f64 FPR64:$src))),
                             (v4f16 (REV64v4i16 FPR64:$src))>;

def : Pat<(v4bf16 (bitconvert (v1i64 FPR64:$src))),
                             (v4bf16 (REV64v4i16 FPR64:$src))>;
def : Pat<(v4bf16 (bitconvert (v2i32 FPR64:$src))),
                             (v4bf16 (REV32v4i16 FPR64:$src))>;
def : Pat<(v4bf16 (bitconvert (v8i8  FPR64:$src))),
                             (v4bf16 (REV16v8i8 FPR64:$src))>;
def : Pat<(v4bf16 (bitconvert (f64   FPR64:$src))),
                             (v4bf16 (REV64v4i16 FPR64:$src))>;
def : Pat<(v4bf16 (bitconvert (v2f32 FPR64:$src))),
                             (v4bf16 (REV32v4i16 FPR64:$src))>;
def : Pat<(v4bf16 (bitconvert (v1f64 FPR64:$src))),
                             (v4bf16 (REV64v4i16 FPR64:$src))>;
}
def : Pat<(v4f16 (bitconvert (v4i16 FPR64:$src))), (v4f16 FPR64:$src)>;
def : Pat<(v4bf16 (bitconvert (v4i16 FPR64:$src))), (v4bf16 FPR64:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v8i8  (bitconvert (v1i64 FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (v2i32 FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (v4i16 FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (f64   FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (v2f32 FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (v1f64 FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (v4f16 FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (v4bf16 FPR64:$src))), (v8i8  FPR64:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v8i8  (bitconvert (v1i64 FPR64:$src))),
                             (v8i8 (REV64v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (v2i32 FPR64:$src))),
                             (v8i8 (REV32v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (v4i16 FPR64:$src))),
                             (v8i8 (REV16v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (f64   FPR64:$src))),
                             (v8i8 (REV64v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (v2f32 FPR64:$src))),
                             (v8i8 (REV32v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (v1f64 FPR64:$src))),
                             (v8i8 (REV64v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (v4f16 FPR64:$src))),
                             (v8i8 (REV16v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (v4bf16 FPR64:$src))),
                             (v8i8 (REV16v8i8 FPR64:$src))>;
}

let Predicates = [IsLE] in {
def : Pat<(f64   (bitconvert (v2i32 FPR64:$src))), (f64   FPR64:$src)>;
def : Pat<(f64   (bitconvert (v4i16 FPR64:$src))), (f64   FPR64:$src)>;
def : Pat<(f64   (bitconvert (v2f32 FPR64:$src))), (f64   FPR64:$src)>;
def : Pat<(f64   (bitconvert (v8i8  FPR64:$src))), (f64   FPR64:$src)>;
def : Pat<(f64   (bitconvert (v4f16 FPR64:$src))), (f64   FPR64:$src)>;
def : Pat<(f64   (bitconvert (v4bf16 FPR64:$src))), (f64   FPR64:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(f64   (bitconvert (v2i32 FPR64:$src))),
                             (f64 (REV64v2i32 FPR64:$src))>;
def : Pat<(f64   (bitconvert (v4i16 FPR64:$src))),
                             (f64 (REV64v4i16 FPR64:$src))>;
def : Pat<(f64   (bitconvert (v2f32 FPR64:$src))),
                             (f64 (REV64v2i32 FPR64:$src))>;
def : Pat<(f64   (bitconvert (v8i8  FPR64:$src))),
                             (f64 (REV64v8i8 FPR64:$src))>;
def : Pat<(f64   (bitconvert (v4f16 FPR64:$src))),
                             (f64 (REV64v4i16 FPR64:$src))>;
def : Pat<(f64   (bitconvert (v4bf16 FPR64:$src))),
                             (f64 (REV64v4i16 FPR64:$src))>;
}
def : Pat<(f64   (bitconvert (v1i64 FPR64:$src))), (f64   FPR64:$src)>;
def : Pat<(f64   (bitconvert (v1f64 FPR64:$src))), (f64   FPR64:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v1f64 (bitconvert (v2i32 FPR64:$src))), (v1f64 FPR64:$src)>;
def : Pat<(v1f64 (bitconvert (v4i16 FPR64:$src))), (v1f64 FPR64:$src)>;
def : Pat<(v1f64 (bitconvert (v8i8  FPR64:$src))), (v1f64 FPR64:$src)>;
def : Pat<(v1f64 (bitconvert (v2f32 FPR64:$src))), (v1f64 FPR64:$src)>;
def : Pat<(v1f64 (bitconvert (v4f16 FPR64:$src))), (v1f64 FPR64:$src)>;
def : Pat<(v1f64 (bitconvert (v4bf16 FPR64:$src))), (v1f64 FPR64:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v1f64 (bitconvert (v2i32 FPR64:$src))),
                             (v1f64 (REV64v2i32 FPR64:$src))>;
def : Pat<(v1f64 (bitconvert (v4i16 FPR64:$src))),
                             (v1f64 (REV64v4i16 FPR64:$src))>;
def : Pat<(v1f64 (bitconvert (v8i8  FPR64:$src))),
                             (v1f64 (REV64v8i8 FPR64:$src))>;
def : Pat<(v1f64 (bitconvert (v2f32 FPR64:$src))),
                             (v1f64 (REV64v2i32 FPR64:$src))>;
def : Pat<(v1f64 (bitconvert (v4f16 FPR64:$src))),
                             (v1f64 (REV64v4i16 FPR64:$src))>;
def : Pat<(v1f64 (bitconvert (v4bf16 FPR64:$src))),
                             (v1f64 (REV64v4i16 FPR64:$src))>;
}
def : Pat<(v1f64 (bitconvert (v1i64 FPR64:$src))), (v1f64 FPR64:$src)>;
def : Pat<(v1f64 (bitconvert (f64   FPR64:$src))), (v1f64 FPR64:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v2f32 (bitconvert (v1i64 FPR64:$src))), (v2f32 FPR64:$src)>;
def : Pat<(v2f32 (bitconvert (v4i16 FPR64:$src))), (v2f32 FPR64:$src)>;
def : Pat<(v2f32 (bitconvert (v8i8  FPR64:$src))), (v2f32 FPR64:$src)>;
def : Pat<(v2f32 (bitconvert (v1f64 FPR64:$src))), (v2f32 FPR64:$src)>;
def : Pat<(v2f32 (bitconvert (f64   FPR64:$src))), (v2f32 FPR64:$src)>;
def : Pat<(v2f32 (bitconvert (v4f16 FPR64:$src))), (v2f32 FPR64:$src)>;
def : Pat<(v2f32 (bitconvert (v4bf16 FPR64:$src))), (v2f32 FPR64:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v2f32 (bitconvert (v1i64 FPR64:$src))),
                             (v2f32 (REV64v2i32 FPR64:$src))>;
def : Pat<(v2f32 (bitconvert (v4i16 FPR64:$src))),
                             (v2f32 (REV32v4i16 FPR64:$src))>;
def : Pat<(v2f32 (bitconvert (v8i8  FPR64:$src))),
                             (v2f32 (REV32v8i8 FPR64:$src))>;
def : Pat<(v2f32 (bitconvert (v1f64 FPR64:$src))),
                             (v2f32 (REV64v2i32 FPR64:$src))>;
def : Pat<(v2f32 (bitconvert (f64   FPR64:$src))),
                             (v2f32 (REV64v2i32 FPR64:$src))>;
def : Pat<(v2f32 (bitconvert (v4f16 FPR64:$src))),
                             (v2f32 (REV32v4i16 FPR64:$src))>;
def : Pat<(v2f32 (bitconvert (v4bf16 FPR64:$src))),
                             (v2f32 (REV32v4i16 FPR64:$src))>;
}
def : Pat<(v2f32 (bitconvert (v2i32 FPR64:$src))), (v2f32 FPR64:$src)>;

let Predicates = [IsLE] in {
def : Pat<(f128 (bitconvert (v2i64 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v4i32 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v8i16 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v2f64 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v4f32 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v8f16 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v8bf16 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v16i8 FPR128:$src))), (f128 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(f128 (bitconvert (v2i64 FPR128:$src))),
                            (f128 (EXTv16i8 FPR128:$src, FPR128:$src, (i32 8)))>;
def : Pat<(f128 (bitconvert (v4i32 FPR128:$src))),
                            (f128 (EXTv16i8 (REV64v4i32 FPR128:$src),
                                            (REV64v4i32 FPR128:$src), (i32 8)))>;
def : Pat<(f128 (bitconvert (v8i16 FPR128:$src))),
                            (f128 (EXTv16i8 (REV64v8i16 FPR128:$src),
                                            (REV64v8i16 FPR128:$src), (i32 8)))>;
def : Pat<(f128 (bitconvert (v8f16 FPR128:$src))),
                            (f128 (EXTv16i8 (REV64v8i16 FPR128:$src),
                                            (REV64v8i16 FPR128:$src), (i32 8)))>;
def : Pat<(f128 (bitconvert (v8bf16 FPR128:$src))),
                            (f128 (EXTv16i8 (REV64v8i16 FPR128:$src),
                                            (REV64v8i16 FPR128:$src), (i32 8)))>;
def : Pat<(f128 (bitconvert (v2f64 FPR128:$src))),
                            (f128 (EXTv16i8 FPR128:$src, FPR128:$src, (i32 8)))>;
def : Pat<(f128 (bitconvert (v4f32 FPR128:$src))),
                            (f128 (EXTv16i8 (REV64v4i32 FPR128:$src),
                                            (REV64v4i32 FPR128:$src), (i32 8)))>;
def : Pat<(f128 (bitconvert (v16i8 FPR128:$src))),
                            (f128 (EXTv16i8 (REV64v16i8 FPR128:$src),
                                            (REV64v16i8 FPR128:$src), (i32 8)))>;
}

let Predicates = [IsLE] in {
def : Pat<(v2f64 (bitconvert (f128  FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v2f64 (bitconvert (v4i32 FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v2f64 (bitconvert (v8i16 FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v2f64 (bitconvert (v8f16 FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v2f64 (bitconvert (v8bf16 FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v2f64 (bitconvert (v16i8 FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v2f64 (bitconvert (v4f32 FPR128:$src))), (v2f64 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v2f64 (bitconvert (f128  FPR128:$src))),
                             (v2f64 (EXTv16i8 FPR128:$src,
                                              FPR128:$src, (i32 8)))>;
def : Pat<(v2f64 (bitconvert (v4i32 FPR128:$src))),
                             (v2f64 (REV64v4i32 FPR128:$src))>;
def : Pat<(v2f64 (bitconvert (v8i16 FPR128:$src))),
                             (v2f64 (REV64v8i16 FPR128:$src))>;
def : Pat<(v2f64 (bitconvert (v8f16 FPR128:$src))),
                             (v2f64 (REV64v8i16 FPR128:$src))>;
def : Pat<(v2f64 (bitconvert (v8bf16 FPR128:$src))),
                             (v2f64 (REV64v8i16 FPR128:$src))>;
def : Pat<(v2f64 (bitconvert (v16i8 FPR128:$src))),
                             (v2f64 (REV64v16i8 FPR128:$src))>;
def : Pat<(v2f64 (bitconvert (v4f32 FPR128:$src))),
                             (v2f64 (REV64v4i32 FPR128:$src))>;
}
def : Pat<(v2f64 (bitconvert (v2i64 FPR128:$src))), (v2f64 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v4f32 (bitconvert (f128  FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v4f32 (bitconvert (v8i16 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v4f32 (bitconvert (v8f16 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v4f32 (bitconvert (v8bf16 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v4f32 (bitconvert (v16i8 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v4f32 (bitconvert (v2i64 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v4f32 (bitconvert (v2f64 FPR128:$src))), (v4f32 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v4f32 (bitconvert (f128  FPR128:$src))),
                             (v4f32 (EXTv16i8 (REV64v4i32 FPR128:$src),
                                    (REV64v4i32 FPR128:$src), (i32 8)))>;
def : Pat<(v4f32 (bitconvert (v8i16 FPR128:$src))),
                             (v4f32 (REV32v8i16 FPR128:$src))>;
def : Pat<(v4f32 (bitconvert (v8f16 FPR128:$src))),
                             (v4f32 (REV32v8i16 FPR128:$src))>;
def : Pat<(v4f32 (bitconvert (v8bf16 FPR128:$src))),
                             (v4f32 (REV32v8i16 FPR128:$src))>;
def : Pat<(v4f32 (bitconvert (v16i8 FPR128:$src))),
                             (v4f32 (REV32v16i8 FPR128:$src))>;
def : Pat<(v4f32 (bitconvert (v2i64 FPR128:$src))),
                             (v4f32 (REV64v4i32 FPR128:$src))>;
def : Pat<(v4f32 (bitconvert (v2f64 FPR128:$src))),
                             (v4f32 (REV64v4i32 FPR128:$src))>;
}
def : Pat<(v4f32 (bitconvert (v4i32 FPR128:$src))), (v4f32 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v2i64 (bitconvert (f128  FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2i64 (bitconvert (v4i32 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2i64 (bitconvert (v8i16 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2i64 (bitconvert (v16i8 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2i64 (bitconvert (v4f32 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2i64 (bitconvert (v8f16 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2i64 (bitconvert (v8bf16 FPR128:$src))), (v2i64 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v2i64 (bitconvert (f128  FPR128:$src))),
                             (v2i64 (EXTv16i8 FPR128:$src,
                                              FPR128:$src, (i32 8)))>;
def : Pat<(v2i64 (bitconvert (v4i32 FPR128:$src))),
                             (v2i64 (REV64v4i32 FPR128:$src))>;
def : Pat<(v2i64 (bitconvert (v8i16 FPR128:$src))),
                             (v2i64 (REV64v8i16 FPR128:$src))>;
def : Pat<(v2i64 (bitconvert (v16i8 FPR128:$src))),
                             (v2i64 (REV64v16i8 FPR128:$src))>;
def : Pat<(v2i64 (bitconvert (v4f32 FPR128:$src))),
                             (v2i64 (REV64v4i32 FPR128:$src))>;
def : Pat<(v2i64 (bitconvert (v8f16 FPR128:$src))),
                             (v2i64 (REV64v8i16 FPR128:$src))>;
def : Pat<(v2i64 (bitconvert (v8bf16 FPR128:$src))),
                             (v2i64 (REV64v8i16 FPR128:$src))>;
}
def : Pat<(v2i64 (bitconvert (v2f64 FPR128:$src))), (v2i64 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v4i32 (bitconvert (f128  FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4i32 (bitconvert (v2i64 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4i32 (bitconvert (v8i16 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4i32 (bitconvert (v16i8 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4i32 (bitconvert (v2f64 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4i32 (bitconvert (v8f16 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4i32 (bitconvert (v8bf16 FPR128:$src))), (v4i32 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v4i32 (bitconvert (f128  FPR128:$src))),
                             (v4i32 (EXTv16i8 (REV64v4i32 FPR128:$src),
                                              (REV64v4i32 FPR128:$src),
                                              (i32 8)))>;
def : Pat<(v4i32 (bitconvert (v2i64 FPR128:$src))),
                             (v4i32 (REV64v4i32 FPR128:$src))>;
def : Pat<(v4i32 (bitconvert (v8i16 FPR128:$src))),
                             (v4i32 (REV32v8i16 FPR128:$src))>;
def : Pat<(v4i32 (bitconvert (v16i8 FPR128:$src))),
                             (v4i32 (REV32v16i8 FPR128:$src))>;
def : Pat<(v4i32 (bitconvert (v2f64 FPR128:$src))),
                             (v4i32 (REV64v4i32 FPR128:$src))>;
def : Pat<(v4i32 (bitconvert (v8f16 FPR128:$src))),
                             (v4i32 (REV32v8i16 FPR128:$src))>;
def : Pat<(v4i32 (bitconvert (v8bf16 FPR128:$src))),
                             (v4i32 (REV32v8i16 FPR128:$src))>;
}
def : Pat<(v4i32 (bitconvert (v4f32 FPR128:$src))), (v4i32 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v8i16 (bitconvert (f128  FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v2i64 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v4i32 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v16i8 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v2f64 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v4f32 FPR128:$src))), (v8i16 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v8i16 (bitconvert (f128  FPR128:$src))),
                             (v8i16 (EXTv16i8 (REV64v8i16 FPR128:$src),
                                              (REV64v8i16 FPR128:$src),
                                              (i32 8)))>;
def : Pat<(v8i16 (bitconvert (v2i64 FPR128:$src))),
                             (v8i16 (REV64v8i16 FPR128:$src))>;
def : Pat<(v8i16 (bitconvert (v4i32 FPR128:$src))),
                             (v8i16 (REV32v8i16 FPR128:$src))>;
def : Pat<(v8i16 (bitconvert (v16i8 FPR128:$src))),
                             (v8i16 (REV16v16i8 FPR128:$src))>;
def : Pat<(v8i16 (bitconvert (v2f64 FPR128:$src))),
                             (v8i16 (REV64v8i16 FPR128:$src))>;
def : Pat<(v8i16 (bitconvert (v4f32 FPR128:$src))),
                             (v8i16 (REV32v8i16 FPR128:$src))>;
}
def : Pat<(v8i16 (bitconvert (v8f16 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v8bf16 FPR128:$src))), (v8i16 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v8f16 (bitconvert (f128  FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8f16 (bitconvert (v2i64 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8f16 (bitconvert (v4i32 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8f16 (bitconvert (v16i8 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8f16 (bitconvert (v2f64 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8f16 (bitconvert (v4f32 FPR128:$src))), (v8f16 FPR128:$src)>;

def : Pat<(v8bf16 (bitconvert (f128  FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v8bf16 (bitconvert (v2i64 FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v8bf16 (bitconvert (v4i32 FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v8bf16 (bitconvert (v16i8 FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v8bf16 (bitconvert (v2f64 FPR128:$src))), (v8bf16 FPR128:$src)>;
def : Pat<(v8bf16 (bitconvert (v4f32 FPR128:$src))), (v8bf16 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v8f16 (bitconvert (f128  FPR128:$src))),
                             (v8f16 (EXTv16i8 (REV64v8i16 FPR128:$src),
                                              (REV64v8i16 FPR128:$src),
                                              (i32 8)))>;
def : Pat<(v8f16 (bitconvert (v2i64 FPR128:$src))),
                             (v8f16 (REV64v8i16 FPR128:$src))>;
def : Pat<(v8f16 (bitconvert (v4i32 FPR128:$src))),
                             (v8f16 (REV32v8i16 FPR128:$src))>;
def : Pat<(v8f16 (bitconvert (v16i8 FPR128:$src))),
                             (v8f16 (REV16v16i8 FPR128:$src))>;
def : Pat<(v8f16 (bitconvert (v2f64 FPR128:$src))),
                             (v8f16 (REV64v8i16 FPR128:$src))>;
def : Pat<(v8f16 (bitconvert (v4f32 FPR128:$src))),
                             (v8f16 (REV32v8i16 FPR128:$src))>;

def : Pat<(v8bf16 (bitconvert (f128  FPR128:$src))),
                             (v8bf16 (EXTv16i8 (REV64v8i16 FPR128:$src),
                                              (REV64v8i16 FPR128:$src),
                                              (i32 8)))>;
def : Pat<(v8bf16 (bitconvert (v2i64 FPR128:$src))),
                             (v8bf16 (REV64v8i16 FPR128:$src))>;
def : Pat<(v8bf16 (bitconvert (v4i32 FPR128:$src))),
                             (v8bf16 (REV32v8i16 FPR128:$src))>;
def : Pat<(v8bf16 (bitconvert (v16i8 FPR128:$src))),
                             (v8bf16 (REV16v16i8 FPR128:$src))>;
def : Pat<(v8bf16 (bitconvert (v2f64 FPR128:$src))),
                             (v8bf16 (REV64v8i16 FPR128:$src))>;
def : Pat<(v8bf16 (bitconvert (v4f32 FPR128:$src))),
                             (v8bf16 (REV32v8i16 FPR128:$src))>;
}
def : Pat<(v8f16 (bitconvert (v8i16 FPR128:$src))), (v8f16 FPR128:$src)>;
def : Pat<(v8bf16 (bitconvert (v8i16 FPR128:$src))), (v8bf16 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v16i8 (bitconvert (f128  FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v2i64 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v4i32 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v8i16 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v2f64 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v4f32 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v8f16 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v8bf16 FPR128:$src))), (v16i8 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v16i8 (bitconvert (f128  FPR128:$src))),
                             (v16i8 (EXTv16i8 (REV64v16i8 FPR128:$src),
                                              (REV64v16i8 FPR128:$src),
                                              (i32 8)))>;
def : Pat<(v16i8 (bitconvert (v2i64 FPR128:$src))),
                             (v16i8 (REV64v16i8 FPR128:$src))>;
def : Pat<(v16i8 (bitconvert (v4i32 FPR128:$src))),
                             (v16i8 (REV32v16i8 FPR128:$src))>;
def : Pat<(v16i8 (bitconvert (v8i16 FPR128:$src))),
                             (v16i8 (REV16v16i8 FPR128:$src))>;
def : Pat<(v16i8 (bitconvert (v2f64 FPR128:$src))),
                             (v16i8 (REV64v16i8 FPR128:$src))>;
def : Pat<(v16i8 (bitconvert (v4f32 FPR128:$src))),
                             (v16i8 (REV32v16i8 FPR128:$src))>;
def : Pat<(v16i8 (bitconvert (v8f16 FPR128:$src))),
                             (v16i8 (REV16v16i8 FPR128:$src))>;
def : Pat<(v16i8 (bitconvert (v8bf16 FPR128:$src))),
                             (v16i8 (REV16v16i8 FPR128:$src))>;
}

def : Pat<(v4i16 (extract_subvector V128:$Rn, (i64 0))),
           (EXTRACT_SUBREG V128:$Rn, dsub)>;
def : Pat<(v8i8 (extract_subvector V128:$Rn, (i64 0))),
           (EXTRACT_SUBREG V128:$Rn, dsub)>;
def : Pat<(v2f32 (extract_subvector V128:$Rn, (i64 0))),
           (EXTRACT_SUBREG V128:$Rn, dsub)>;
def : Pat<(v4f16 (extract_subvector V128:$Rn, (i64 0))),
           (EXTRACT_SUBREG V128:$Rn, dsub)>;
def : Pat<(v4bf16 (extract_subvector V128:$Rn, (i64 0))),
           (EXTRACT_SUBREG V128:$Rn, dsub)>;
def : Pat<(v2i32 (extract_subvector V128:$Rn, (i64 0))),
           (EXTRACT_SUBREG V128:$Rn, dsub)>;
def : Pat<(v1i64 (extract_subvector V128:$Rn, (i64 0))),
           (EXTRACT_SUBREG V128:$Rn, dsub)>;
def : Pat<(v1f64 (extract_subvector V128:$Rn, (i64 0))),
           (EXTRACT_SUBREG V128:$Rn, dsub)>;

def : Pat<(v8i8 (extract_subvector (v16i8 FPR128:$Rn), (i64 1))),
          (EXTRACT_SUBREG (DUPv2i64lane FPR128:$Rn, 1), dsub)>;
def : Pat<(v4i16 (extract_subvector (v8i16 FPR128:$Rn), (i64 1))),
          (EXTRACT_SUBREG (DUPv2i64lane FPR128:$Rn, 1), dsub)>;
def : Pat<(v2i32 (extract_subvector (v4i32 FPR128:$Rn), (i64 1))),
          (EXTRACT_SUBREG (DUPv2i64lane FPR128:$Rn, 1), dsub)>;
def : Pat<(v1i64 (extract_subvector (v2i64 FPR128:$Rn), (i64 1))),
          (EXTRACT_SUBREG (DUPv2i64lane FPR128:$Rn, 1), dsub)>;

// A 64-bit subvector insert to the first 128-bit vector position
// is a subregister copy that needs no instruction.
multiclass InsertSubvectorUndef<ValueType Ty> {
  def : Pat<(insert_subvector undef, (v1i64 FPR64:$src), (Ty 0)),
            (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
  def : Pat<(insert_subvector undef, (v1f64 FPR64:$src), (Ty 0)),
            (INSERT_SUBREG (v2f64 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
  def : Pat<(insert_subvector undef, (v2i32 FPR64:$src), (Ty 0)),
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
  def : Pat<(insert_subvector undef, (v2f32 FPR64:$src), (Ty 0)),
            (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
  def : Pat<(insert_subvector undef, (v4i16 FPR64:$src), (Ty 0)),
            (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
  def : Pat<(insert_subvector undef, (v4f16 FPR64:$src), (Ty 0)),
            (INSERT_SUBREG (v8f16 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
  def : Pat<(insert_subvector undef, (v4bf16 FPR64:$src), (Ty 0)),
            (INSERT_SUBREG (v8bf16 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
  def : Pat<(insert_subvector undef, (v8i8 FPR64:$src), (Ty 0)),
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
}

defm : InsertSubvectorUndef<i32>;
defm : InsertSubvectorUndef<i64>;

// Use pair-wise add instructions when summing up the lanes for v2f64, v2i64
// or v2f32.
def : Pat<(i64 (add (vector_extract (v2i64 FPR128:$Rn), (i64 0)),
                    (vector_extract (v2i64 FPR128:$Rn), (i64 1)))),
           (i64 (ADDPv2i64p (v2i64 FPR128:$Rn)))>;
def : Pat<(f64 (fadd (vector_extract (v2f64 FPR128:$Rn), (i64 0)),
                     (vector_extract (v2f64 FPR128:$Rn), (i64 1)))),
           (f64 (FADDPv2i64p (v2f64 FPR128:$Rn)))>;
    // vector_extract on 64-bit vectors gets promoted to a 128 bit vector,
    // so we match on v4f32 here, not v2f32. This will also catch adding
    // the low two lanes of a true v4f32 vector.
def : Pat<(fadd (vector_extract (v4f32 FPR128:$Rn), (i64 0)),
                (vector_extract (v4f32 FPR128:$Rn), (i64 1))),
          (f32 (FADDPv2i32p (EXTRACT_SUBREG FPR128:$Rn, dsub)))>;

// Scalar 64-bit shifts in FPR64 registers.
def : Pat<(i64 (int_aarch64_neon_sshl (i64 FPR64:$Rn), (i64 FPR64:$Rm))),
          (SSHLv1i64 FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(i64 (int_aarch64_neon_ushl (i64 FPR64:$Rn), (i64 FPR64:$Rm))),
          (USHLv1i64 FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(i64 (int_aarch64_neon_srshl (i64 FPR64:$Rn), (i64 FPR64:$Rm))),
          (SRSHLv1i64 FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(i64 (int_aarch64_neon_urshl (i64 FPR64:$Rn), (i64 FPR64:$Rm))),
          (URSHLv1i64 FPR64:$Rn, FPR64:$Rm)>;

// Patterns for nontemporal/no-allocate stores.
// We have to resort to tricks to turn a single-input store into a store pair,
// because there is no single-input nontemporal store, only STNP.
let Predicates = [IsLE] in {
let AddedComplexity = 15 in {
class NTStore128Pat<ValueType VT> :
  Pat<(nontemporalstore (VT FPR128:$Rt),
        (am_indexed7s64 GPR64sp:$Rn, simm7s8:$offset)),
      (STNPDi (EXTRACT_SUBREG FPR128:$Rt, dsub),
              (CPYi64 FPR128:$Rt, (i64 1)),
              GPR64sp:$Rn, simm7s8:$offset)>;

def : NTStore128Pat<v2i64>;
def : NTStore128Pat<v4i32>;
def : NTStore128Pat<v8i16>;
def : NTStore128Pat<v16i8>;

class NTStore64Pat<ValueType VT> :
  Pat<(nontemporalstore (VT FPR64:$Rt),
        (am_indexed7s32 GPR64sp:$Rn, simm7s4:$offset)),
      (STNPSi (EXTRACT_SUBREG FPR64:$Rt, ssub),
              (CPYi32 (SUBREG_TO_REG (i64 0), FPR64:$Rt, dsub), (i64 1)),
              GPR64sp:$Rn, simm7s4:$offset)>;

// FIXME: Shouldn't v1f64 loads/stores be promoted to v1i64?
def : NTStore64Pat<v1f64>;
def : NTStore64Pat<v1i64>;
def : NTStore64Pat<v2i32>;
def : NTStore64Pat<v4i16>;
def : NTStore64Pat<v8i8>;

def : Pat<(nontemporalstore GPR64:$Rt,
            (am_indexed7s32 GPR64sp:$Rn, simm7s4:$offset)),
          (STNPWi (EXTRACT_SUBREG GPR64:$Rt, sub_32),
                  (EXTRACT_SUBREG (UBFMXri GPR64:$Rt, 32, 63), sub_32),
                  GPR64sp:$Rn, simm7s4:$offset)>;
} // AddedComplexity=10
} // Predicates = [IsLE]

// Tail call return handling. These are all compiler pseudo-instructions,
// so no encoding information or anything like that.
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1, Uses = [SP] in {
  def TCRETURNdi : Pseudo<(outs), (ins i64imm:$dst, i32imm:$FPDiff), []>,
                   Sched<[WriteBrReg]>;
  def TCRETURNri : Pseudo<(outs), (ins tcGPR64:$dst, i32imm:$FPDiff), []>,
                   Sched<[WriteBrReg]>;
  // Indirect tail-call with any register allowed, used by MachineOutliner when
  // this is proven safe.
  // FIXME: If we have to add any more hacks like this, we should instead relax
  // some verifier checks for outlined functions.
  def TCRETURNriALL : Pseudo<(outs), (ins GPR64:$dst, i32imm:$FPDiff), []>,
                      Sched<[WriteBrReg]>;
  // Indirect tail-call limited to only use registers (x16 and x17) which are
  // allowed to tail-call a "BTI c" instruction.
  def TCRETURNriBTI : Pseudo<(outs), (ins rtcGPR64:$dst, i32imm:$FPDiff), []>,
                      Sched<[WriteBrReg]>;
}

def : Pat<(AArch64tcret tcGPR64:$dst, (i32 timm:$FPDiff)),
          (TCRETURNri tcGPR64:$dst, imm:$FPDiff)>,
      Requires<[NotUseBTI]>;
def : Pat<(AArch64tcret rtcGPR64:$dst, (i32 timm:$FPDiff)),
          (TCRETURNriBTI rtcGPR64:$dst, imm:$FPDiff)>,
      Requires<[UseBTI]>;
def : Pat<(AArch64tcret tglobaladdr:$dst, (i32 timm:$FPDiff)),
          (TCRETURNdi texternalsym:$dst, imm:$FPDiff)>;
def : Pat<(AArch64tcret texternalsym:$dst, (i32 timm:$FPDiff)),
          (TCRETURNdi texternalsym:$dst, imm:$FPDiff)>;

def MOVMCSym : Pseudo<(outs GPR64:$dst), (ins i64imm:$sym), []>, Sched<[]>;
def : Pat<(i64 (AArch64LocalRecover mcsym:$sym)), (MOVMCSym mcsym:$sym)>;

// Extracting lane zero is a special case where we can just use a plain
// EXTRACT_SUBREG instruction, which will become FMOV. This is easier for the
// rest of the compiler, especially the register allocator and copy propagation,
// to reason about, so is preferred when it's possible to use it.
let AddedComplexity = 10 in {
  def : Pat<(i64 (extractelt (v2i64 V128:$V), (i64 0))), (EXTRACT_SUBREG V128:$V, dsub)>;
  def : Pat<(i32 (extractelt (v4i32 V128:$V), (i64 0))), (EXTRACT_SUBREG V128:$V, ssub)>;
  def : Pat<(i32 (extractelt (v2i32 V64:$V), (i64 0))), (EXTRACT_SUBREG V64:$V, ssub)>;
}

// dot_v4i8
class mul_v4i8<SDPatternOperator ldop> :
  PatFrag<(ops node:$Rn, node:$Rm, node:$offset),
          (mul (ldop (add node:$Rn, node:$offset)),
               (ldop (add node:$Rm, node:$offset)))>;
class mulz_v4i8<SDPatternOperator ldop> :
  PatFrag<(ops node:$Rn, node:$Rm),
          (mul (ldop node:$Rn), (ldop node:$Rm))>;

def load_v4i8 :
  OutPatFrag<(ops node:$R),
             (INSERT_SUBREG
              (v2i32 (IMPLICIT_DEF)),
               (i32 (COPY_TO_REGCLASS (LDRWui node:$R, (i64 0)), FPR32)),
              ssub)>;

class dot_v4i8<Instruction DOT, SDPatternOperator ldop> :
  Pat<(i32 (add (mul_v4i8<ldop> GPR64sp:$Rn, GPR64sp:$Rm, (i64 3)),
           (add (mul_v4i8<ldop> GPR64sp:$Rn, GPR64sp:$Rm, (i64 2)),
           (add (mul_v4i8<ldop> GPR64sp:$Rn, GPR64sp:$Rm, (i64 1)),
                (mulz_v4i8<ldop> GPR64sp:$Rn, GPR64sp:$Rm))))),
      (EXTRACT_SUBREG (i64 (DOT (DUPv2i32gpr WZR),
                                (load_v4i8 GPR64sp:$Rn),
                                (load_v4i8 GPR64sp:$Rm))),
                      sub_32)>, Requires<[HasDotProd]>;

// dot_v8i8
class ee_v8i8<SDPatternOperator extend> :
  PatFrag<(ops node:$V, node:$K),
          (v4i16 (extract_subvector (v8i16 (extend node:$V)), node:$K))>;

class mul_v8i8<SDPatternOperator mulop, SDPatternOperator extend> :
  PatFrag<(ops node:$M, node:$N, node:$K),
          (mulop (v4i16 (ee_v8i8<extend> node:$M, node:$K)),
                 (v4i16 (ee_v8i8<extend> node:$N, node:$K)))>;

class idot_v8i8<SDPatternOperator mulop, SDPatternOperator extend> :
  PatFrag<(ops node:$M, node:$N),
          (i32 (extractelt
           (v4i32 (AArch64uaddv
            (add (mul_v8i8<mulop, extend> node:$M, node:$N, (i64 0)),
                 (mul_v8i8<mulop, extend> node:$M, node:$N, (i64 4))))),
           (i64 0)))>;

// vaddv_[su]32 is special; -> ADDP Vd.2S,Vn.2S,Vm.2S; return Vd.s[0];Vn==Vm
def VADDV_32 : OutPatFrag<(ops node:$R), (ADDPv2i32 node:$R, node:$R)>;

class odot_v8i8<Instruction DOT> :
  OutPatFrag<(ops node:$Vm, node:$Vn),
             (EXTRACT_SUBREG
              (VADDV_32
               (i64 (DOT (DUPv2i32gpr WZR),
                         (v8i8 node:$Vm),
                         (v8i8 node:$Vn)))),
              sub_32)>;

class dot_v8i8<Instruction DOT, SDPatternOperator mulop,
                    SDPatternOperator extend> :
  Pat<(idot_v8i8<mulop, extend> V64:$Vm, V64:$Vn),
      (odot_v8i8<DOT> V64:$Vm, V64:$Vn)>,
  Requires<[HasDotProd]>;

// dot_v16i8
class ee_v16i8<SDPatternOperator extend> :
  PatFrag<(ops node:$V, node:$K1, node:$K2),
          (v4i16 (extract_subvector
           (v8i16 (extend
            (v8i8 (extract_subvector node:$V, node:$K1)))), node:$K2))>;

class mul_v16i8<SDPatternOperator mulop, SDPatternOperator extend> :
  PatFrag<(ops node:$M, node:$N, node:$K1, node:$K2),
          (v4i32
           (mulop (v4i16 (ee_v16i8<extend> node:$M, node:$K1, node:$K2)),
                  (v4i16 (ee_v16i8<extend> node:$N, node:$K1, node:$K2))))>;

class idot_v16i8<SDPatternOperator m, SDPatternOperator x> :
  PatFrag<(ops node:$M, node:$N),
          (i32 (extractelt
           (v4i32 (AArch64uaddv
            (add
             (add (mul_v16i8<m, x> node:$M, node:$N, (i64 0), (i64 0)),
                  (mul_v16i8<m, x> node:$M, node:$N, (i64 8), (i64 0))),
             (add (mul_v16i8<m, x> node:$M, node:$N, (i64 0), (i64 4)),
                  (mul_v16i8<m, x> node:$M, node:$N, (i64 8), (i64 4)))))),
           (i64 0)))>;

class odot_v16i8<Instruction DOT> :
  OutPatFrag<(ops node:$Vm, node:$Vn),
             (i32 (ADDVv4i32v
              (DOT (DUPv4i32gpr WZR), node:$Vm, node:$Vn)))>;

class dot_v16i8<Instruction DOT, SDPatternOperator mulop,
                SDPatternOperator extend> :
  Pat<(idot_v16i8<mulop, extend> V128:$Vm, V128:$Vn),
      (odot_v16i8<DOT> V128:$Vm, V128:$Vn)>,
  Requires<[HasDotProd]>;

let AddedComplexity = 10 in {
  def : dot_v4i8<SDOTv8i8, sextloadi8>;
  def : dot_v4i8<UDOTv8i8, zextloadi8>;
  def : dot_v8i8<SDOTv8i8, AArch64smull, sext>;
  def : dot_v8i8<UDOTv8i8, AArch64umull, zext>;
  def : dot_v16i8<SDOTv16i8, AArch64smull, sext>;
  def : dot_v16i8<UDOTv16i8, AArch64umull, zext>;

  // FIXME: add patterns to generate vector by element dot product.
  // FIXME: add SVE dot-product patterns.
}

include "AArch64InstrAtomics.td"
include "AArch64SVEInstrInfo.td"

include "AArch64InstrGISel.td"