llvm.org GIT mirror llvm / master lib / Target / AMDGPU / SIInstrInfo.td
master

Tree @master (Download .tar.gz)

SIInstrInfo.td @masterraw · history · blame

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 678
 679
 680
 681
 682
 683
 684
 685
 686
 687
 688
 689
 690
 691
 692
 693
 694
 695
 696
 697
 698
 699
 700
 701
 702
 703
 704
 705
 706
 707
 708
 709
 710
 711
 712
 713
 714
 715
 716
 717
 718
 719
 720
 721
 722
 723
 724
 725
 726
 727
 728
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 747
 748
 749
 750
 751
 752
 753
 754
 755
 756
 757
 758
 759
 760
 761
 762
 763
 764
 765
 766
 767
 768
 769
 770
 771
 772
 773
 774
 775
 776
 777
 778
 779
 780
 781
 782
 783
 784
 785
 786
 787
 788
 789
 790
 791
 792
 793
 794
 795
 796
 797
 798
 799
 800
 801
 802
 803
 804
 805
 806
 807
 808
 809
 810
 811
 812
 813
 814
 815
 816
 817
 818
 819
 820
 821
 822
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 925
 926
 927
 928
 929
 930
 931
 932
 933
 934
 935
 936
 937
 938
 939
 940
 941
 942
 943
 944
 945
 946
 947
 948
 949
 950
 951
 952
 953
 954
 955
 956
 957
 958
 959
 960
 961
 962
 963
 964
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
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
//===-- SIInstrInfo.td - SI Instruction Infos -------------*- 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
//
//===----------------------------------------------------------------------===//

def isWave32 : Predicate<"Subtarget->getWavefrontSize() == 32">,
  AssemblerPredicate <"FeatureWavefrontSize32">;
def isWave64 : Predicate<"Subtarget->getWavefrontSize() == 64">,
  AssemblerPredicate <"FeatureWavefrontSize64">;

def DisableInst : Predicate <"false">, AssemblerPredicate<"FeatureDisable">;

class GCNPredicateControl : PredicateControl {
  Predicate SIAssemblerPredicate = isGFX6GFX7;
  Predicate VIAssemblerPredicate = isGFX8GFX9;
}

// Execpt for the NONE field, this must be kept in sync with the
// SIEncodingFamily enum in AMDGPUInstrInfo.cpp
def SIEncodingFamily {
  int NONE = -1;
  int SI = 0;
  int VI = 1;
  int SDWA = 2;
  int SDWA9 = 3;
  int GFX80 = 4;
  int GFX9 = 5;
  int GFX10 = 6;
  int SDWA10 = 7;
}

//===----------------------------------------------------------------------===//
// SI DAG Nodes
//===----------------------------------------------------------------------===//

def AMDGPUclamp : SDNode<"AMDGPUISD::CLAMP", SDTFPUnaryOp>;

def SIsbuffer_load : SDNode<"AMDGPUISD::SBUFFER_LOAD",
  SDTypeProfile<1, 4, [SDTCisVT<1, v4i32>, SDTCisVT<2, i32>, SDTCisVT<3, i1>,
                       SDTCisVT<4, i1>]>,
  [SDNPMayLoad, SDNPMemOperand]
>;

def SIds_ordered_count : SDNode<"AMDGPUISD::DS_ORDERED_COUNT",
  SDTypeProfile<1, 2, [SDTCisVT<0, i32>, SDTCisVT<1, i32>, SDTCisVT<2, i16>]>,
  [SDNPMayLoad, SDNPMayStore, SDNPMemOperand, SDNPHasChain, SDNPInGlue]
>;

def SIatomic_inc : SDNode<"AMDGPUISD::ATOMIC_INC", SDTAtomic2,
  [SDNPMayLoad, SDNPMayStore, SDNPMemOperand, SDNPHasChain]
>;

def SIatomic_dec : SDNode<"AMDGPUISD::ATOMIC_DEC", SDTAtomic2,
  [SDNPMayLoad, SDNPMayStore, SDNPMemOperand, SDNPHasChain]
>;

def SDTAtomic2_f32 : SDTypeProfile<1, 2, [
  SDTCisSameAs<0,2>, SDTCisFP<0>, SDTCisPtrTy<1>
]>;

def SIatomic_fmin : SDNode<"AMDGPUISD::ATOMIC_LOAD_FMIN", SDTAtomic2_f32,
  [SDNPMayLoad, SDNPMayStore, SDNPMemOperand, SDNPHasChain]
>;

def SIatomic_fmax : SDNode<"AMDGPUISD::ATOMIC_LOAD_FMAX", SDTAtomic2_f32,
  [SDNPMayLoad, SDNPMayStore, SDNPMemOperand, SDNPHasChain]
>;

// load_d16_{lo|hi} ptr, tied_input
def SIload_d16 : SDTypeProfile<1, 2, [
  SDTCisPtrTy<1>,
  SDTCisSameAs<0, 2>
]>;


def SDTtbuffer_load : SDTypeProfile<1, 8,
  [                     // vdata
   SDTCisVT<1, v4i32>,  // rsrc
   SDTCisVT<2, i32>,    // vindex(VGPR)
   SDTCisVT<3, i32>,    // voffset(VGPR)
   SDTCisVT<4, i32>,    // soffset(SGPR)
   SDTCisVT<5, i32>,    // offset(imm)
   SDTCisVT<6, i32>,    // format(imm)
   SDTCisVT<7, i32>,    // cachepolicy, swizzled buffer(imm)
   SDTCisVT<8, i1>      // idxen(imm)
  ]>;

def SItbuffer_load :   SDNode<"AMDGPUISD::TBUFFER_LOAD_FORMAT", SDTtbuffer_load,
                              [SDNPMayLoad, SDNPMemOperand, SDNPHasChain]>;
def SItbuffer_load_d16 : SDNode<"AMDGPUISD::TBUFFER_LOAD_FORMAT_D16",
                                SDTtbuffer_load,
                                [SDNPMayLoad, SDNPMemOperand, SDNPHasChain]>;

def SDTtbuffer_store : SDTypeProfile<0, 9,
    [                     // vdata
     SDTCisVT<1, v4i32>,  // rsrc
     SDTCisVT<2, i32>,    // vindex(VGPR)
     SDTCisVT<3, i32>,    // voffset(VGPR)
     SDTCisVT<4, i32>,    // soffset(SGPR)
     SDTCisVT<5, i32>,    // offset(imm)
     SDTCisVT<6, i32>,    // format(imm)
     SDTCisVT<7, i32>,    // cachepolicy, swizzled buffer(imm)
     SDTCisVT<8, i1>      // idxen(imm)
    ]>;

def SItbuffer_store : SDNode<"AMDGPUISD::TBUFFER_STORE_FORMAT", SDTtbuffer_store,
                             [SDNPMayStore, SDNPMemOperand, SDNPHasChain]>;
def SItbuffer_store_d16 : SDNode<"AMDGPUISD::TBUFFER_STORE_FORMAT_D16",
                                SDTtbuffer_store,
                                [SDNPMayStore, SDNPMemOperand, SDNPHasChain]>;

def SDTBufferLoad : SDTypeProfile<1, 7,
    [                    // vdata
     SDTCisVT<1, v4i32>, // rsrc
     SDTCisVT<2, i32>,   // vindex(VGPR)
     SDTCisVT<3, i32>,   // voffset(VGPR)
     SDTCisVT<4, i32>,   // soffset(SGPR)
     SDTCisVT<5, i32>,   // offset(imm)
     SDTCisVT<6, i32>,   // cachepolicy, swizzled buffer(imm)
     SDTCisVT<7, i1>]>;  // idxen(imm)

def SIbuffer_load : SDNode <"AMDGPUISD::BUFFER_LOAD", SDTBufferLoad,
                            [SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;
def SIbuffer_load_ubyte : SDNode <"AMDGPUISD::BUFFER_LOAD_UBYTE", SDTBufferLoad,
                            [SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;
def SIbuffer_load_ushort : SDNode <"AMDGPUISD::BUFFER_LOAD_USHORT", SDTBufferLoad,
                            [SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;
def SIbuffer_load_byte : SDNode <"AMDGPUISD::BUFFER_LOAD_BYTE", SDTBufferLoad,
                            [SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;
def SIbuffer_load_short: SDNode <"AMDGPUISD::BUFFER_LOAD_SHORT", SDTBufferLoad,
                            [SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;
def SIbuffer_load_format : SDNode <"AMDGPUISD::BUFFER_LOAD_FORMAT", SDTBufferLoad,
                            [SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;
def SIbuffer_load_format_d16 : SDNode <"AMDGPUISD::BUFFER_LOAD_FORMAT_D16",
                                SDTBufferLoad,
                                [SDNPMemOperand, SDNPHasChain, SDNPMayLoad]>;

def SDTBufferStore : SDTypeProfile<0, 8,
    [                    // vdata
     SDTCisVT<1, v4i32>, // rsrc
     SDTCisVT<2, i32>,   // vindex(VGPR)
     SDTCisVT<3, i32>,   // voffset(VGPR)
     SDTCisVT<4, i32>,   // soffset(SGPR)
     SDTCisVT<5, i32>,   // offset(imm)
     SDTCisVT<6, i32>,   // cachepolicy, swizzled buffer(imm)
     SDTCisVT<7, i1>]>;  // idxen(imm)

def SIbuffer_store : SDNode <"AMDGPUISD::BUFFER_STORE", SDTBufferStore,
                             [SDNPMayStore, SDNPMemOperand, SDNPHasChain]>;
def SIbuffer_store_byte: SDNode <"AMDGPUISD::BUFFER_STORE_BYTE",
                         SDTBufferStore,
                         [SDNPMayStore, SDNPMemOperand, SDNPHasChain]>;
def SIbuffer_store_short : SDNode <"AMDGPUISD::BUFFER_STORE_SHORT",
                           SDTBufferStore,
                           [SDNPMayStore, SDNPMemOperand, SDNPHasChain]>;
def SIbuffer_store_format : SDNode <"AMDGPUISD::BUFFER_STORE_FORMAT",
                            SDTBufferStore,
                            [SDNPMayStore, SDNPMemOperand, SDNPHasChain]>;
def SIbuffer_store_format_d16 : SDNode <"AMDGPUISD::BUFFER_STORE_FORMAT_D16",
                            SDTBufferStore,
                            [SDNPMayStore, SDNPMemOperand, SDNPHasChain]>;

class SDBufferAtomic<string opcode> : SDNode <opcode,
  SDTypeProfile<1, 8,
       [SDTCisVT<2, v4i32>, // rsrc
       SDTCisVT<3, i32>,   // vindex(VGPR)
       SDTCisVT<4, i32>,   // voffset(VGPR)
       SDTCisVT<5, i32>,   // soffset(SGPR)
       SDTCisVT<6, i32>,   // offset(imm)
       SDTCisVT<7, i32>,   // cachepolicy(imm)
       SDTCisVT<8, i1>]>,  // idxen(imm)
  [SDNPMemOperand, SDNPHasChain, SDNPMayLoad, SDNPMayStore]
>;

class SDBufferAtomicNoRtn<string opcode, ValueType ty> : SDNode <opcode,
  SDTypeProfile<0, 8,
      [SDTCisVT<0, ty>,    // vdata
       SDTCisVT<1, v4i32>, // rsrc
       SDTCisVT<2, i32>,   // vindex(VGPR)
       SDTCisVT<3, i32>,   // voffset(VGPR)
       SDTCisVT<4, i32>,   // soffset(SGPR)
       SDTCisVT<5, i32>,   // offset(imm)
       SDTCisVT<6, i32>,   // cachepolicy(imm)
       SDTCisVT<7, i1>]>,  // idxen(imm)
  [SDNPMemOperand, SDNPHasChain, SDNPMayLoad, SDNPMayStore]
>;

def SIbuffer_atomic_swap : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_SWAP">;
def SIbuffer_atomic_add : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_ADD">;
def SIbuffer_atomic_sub : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_SUB">;
def SIbuffer_atomic_smin : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_SMIN">;
def SIbuffer_atomic_umin : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_UMIN">;
def SIbuffer_atomic_smax : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_SMAX">;
def SIbuffer_atomic_umax : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_UMAX">;
def SIbuffer_atomic_and : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_AND">;
def SIbuffer_atomic_or : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_OR">;
def SIbuffer_atomic_xor : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_XOR">;
def SIbuffer_atomic_inc : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_INC">;
def SIbuffer_atomic_dec : SDBufferAtomic <"AMDGPUISD::BUFFER_ATOMIC_DEC">;
def SIbuffer_atomic_fadd : SDBufferAtomicNoRtn <"AMDGPUISD::BUFFER_ATOMIC_FADD", f32>;
def SIbuffer_atomic_pk_fadd : SDBufferAtomicNoRtn <"AMDGPUISD::BUFFER_ATOMIC_PK_FADD", v2f16>;

def SIbuffer_atomic_cmpswap : SDNode <"AMDGPUISD::BUFFER_ATOMIC_CMPSWAP",
  SDTypeProfile<1, 9,
    [SDTCisVT<0, i32>,   // dst
     SDTCisVT<1, i32>,   // src
     SDTCisVT<2, i32>,   // cmp
     SDTCisVT<3, v4i32>, // rsrc
     SDTCisVT<4, i32>,   // vindex(VGPR)
     SDTCisVT<5, i32>,   // voffset(VGPR)
     SDTCisVT<6, i32>,   // soffset(SGPR)
     SDTCisVT<7, i32>,   // offset(imm)
     SDTCisVT<8, i32>,   // cachepolicy(imm)
     SDTCisVT<9, i1>]>,  // idxen(imm)
  [SDNPMemOperand, SDNPHasChain, SDNPMayLoad, SDNPMayStore]
>;

class SDGlobalAtomicNoRtn<string opcode, ValueType ty> : SDNode <opcode,
  SDTypeProfile<0, 2,
      [SDTCisPtrTy<0>,     // vaddr
       SDTCisVT<1, ty>]>,  // vdata
  [SDNPMemOperand, SDNPHasChain, SDNPMayLoad, SDNPMayStore]
>;

def SIglobal_atomic_fadd    : SDGlobalAtomicNoRtn <"AMDGPUISD::ATOMIC_FADD", f32>;
def SIglobal_atomic_pk_fadd : SDGlobalAtomicNoRtn <"AMDGPUISD::ATOMIC_PK_FADD", v2f16>;

def SIpc_add_rel_offset : SDNode<"AMDGPUISD::PC_ADD_REL_OFFSET",
  SDTypeProfile<1, 2, [SDTCisVT<0, iPTR>, SDTCisSameAs<0,1>, SDTCisSameAs<0,2>]>
>;

def SIlds : SDNode<"AMDGPUISD::LDS",
  SDTypeProfile<1, 1, [SDTCisVT<0, iPTR>, SDTCisSameAs<0,1>]>
>;

def SIload_d16_lo : SDNode<"AMDGPUISD::LOAD_D16_LO",
  SIload_d16,
  [SDNPMayLoad, SDNPMemOperand, SDNPHasChain]
>;

def SIload_d16_lo_u8 : SDNode<"AMDGPUISD::LOAD_D16_LO_U8",
  SIload_d16,
  [SDNPMayLoad, SDNPMemOperand, SDNPHasChain]
>;

def SIload_d16_lo_i8 : SDNode<"AMDGPUISD::LOAD_D16_LO_I8",
  SIload_d16,
  [SDNPMayLoad, SDNPMemOperand, SDNPHasChain]
>;

def SIload_d16_hi : SDNode<"AMDGPUISD::LOAD_D16_HI",
  SIload_d16,
  [SDNPMayLoad, SDNPMemOperand, SDNPHasChain]
>;

def SIload_d16_hi_u8 : SDNode<"AMDGPUISD::LOAD_D16_HI_U8",
  SIload_d16,
  [SDNPMayLoad, SDNPMemOperand, SDNPHasChain]
>;

def SIload_d16_hi_i8 : SDNode<"AMDGPUISD::LOAD_D16_HI_I8",
  SIload_d16,
  [SDNPMayLoad, SDNPMemOperand, SDNPHasChain]
>;

def SIdenorm_mode : SDNode<"AMDGPUISD::DENORM_MODE",
  SDTypeProfile<0 ,1, [SDTCisInt<0>]>,
  [SDNPHasChain, SDNPSideEffect, SDNPOptInGlue, SDNPOutGlue]
>;

//===----------------------------------------------------------------------===//
// ValueType helpers
//===----------------------------------------------------------------------===//

// Returns 1 if the source arguments have modifiers, 0 if they do not.
// XXX - do f16 instructions?
class isFloatType<ValueType SrcVT> {
  bit ret =
    !if(!eq(SrcVT.Value, f16.Value), 1,
    !if(!eq(SrcVT.Value, f32.Value), 1,
    !if(!eq(SrcVT.Value, f64.Value), 1,
    !if(!eq(SrcVT.Value, v2f16.Value), 1,
    !if(!eq(SrcVT.Value, v4f16.Value), 1,
    !if(!eq(SrcVT.Value, v2f32.Value), 1,
    !if(!eq(SrcVT.Value, v2f64.Value), 1,
    0)))))));
}

class isIntType<ValueType SrcVT> {
  bit ret =
    !if(!eq(SrcVT.Value, i16.Value), 1,
    !if(!eq(SrcVT.Value, i32.Value), 1,
    !if(!eq(SrcVT.Value, i64.Value), 1,
    0)));
}

class isPackedType<ValueType SrcVT> {
  bit ret =
    !if(!eq(SrcVT.Value, v2i16.Value), 1,
      !if(!eq(SrcVT.Value, v2f16.Value), 1,
        !if(!eq(SrcVT.Value, v4f16.Value), 1, 0)
    ));
}

//===----------------------------------------------------------------------===//
// PatFrags for global memory operations
//===----------------------------------------------------------------------===//

foreach as = [ "global", "flat", "constant", "local", "private", "region" ] in {
let AddressSpaces = !cast<AddressSpaceList>("LoadAddress_"#as).AddrSpaces in {


defm atomic_inc_#as : binary_atomic_op<SIatomic_inc>;
defm atomic_dec_#as : binary_atomic_op<SIatomic_dec>;
defm atomic_load_fmin_#as : binary_atomic_op<SIatomic_fmin, 0>;
defm atomic_load_fmax_#as : binary_atomic_op<SIatomic_fmax, 0>;


} // End let AddressSpaces = ...
} // End foreach AddrSpace

def atomic_fadd_global_noret : PatFrag<
  (ops node:$ptr, node:$value),
  (SIglobal_atomic_fadd node:$ptr, node:$value)> {
  // FIXME: Move this
  let MemoryVT = f32;
  let IsAtomic = 1;
  let AddressSpaces = StoreAddress_global.AddrSpaces;
}

def atomic_pk_fadd_global_noret : PatFrag<
    (ops node:$ptr, node:$value),
    (SIglobal_atomic_pk_fadd node:$ptr, node:$value)> {
  // FIXME: Move this
  let MemoryVT = v2f16;
  let IsAtomic = 1;
  let AddressSpaces = StoreAddress_global.AddrSpaces;
}

//===----------------------------------------------------------------------===//
// SDNodes PatFrags for loads/stores with a glue input.
// This is for SDNodes and PatFrag for local loads and stores to
// enable s_mov_b32 m0, -1 to be glued to the memory instructions.
//
// These mirror the regular load/store PatFrags and rely on special
// processing during Select() to add the glued copy.
//
//===----------------------------------------------------------------------===//

def AMDGPUld_glue : SDNode <"ISD::LOAD", SDTLoad,
  [SDNPHasChain, SDNPMayLoad, SDNPMemOperand, SDNPInGlue]
>;

def AMDGPUatomic_ld_glue : SDNode <"ISD::ATOMIC_LOAD", SDTAtomicLoad,
  [SDNPHasChain, SDNPMayLoad, SDNPMemOperand, SDNPInGlue]
>;

def unindexedload_glue : PatFrag <(ops node:$ptr), (AMDGPUld_glue node:$ptr)> {
  let IsLoad = 1;
  let IsUnindexed = 1;
}

def load_glue : PatFrag <(ops node:$ptr), (unindexedload_glue node:$ptr)> {
  let IsLoad = 1;
  let IsNonExtLoad = 1;
}

def atomic_load_32_glue : PatFrag<(ops node:$ptr),
  (AMDGPUatomic_ld_glue node:$ptr)> {
  let IsAtomic = 1;
  let MemoryVT = i32;
}

def atomic_load_64_glue : PatFrag<(ops node:$ptr),
  (AMDGPUatomic_ld_glue node:$ptr)> {
  let IsAtomic = 1;
  let MemoryVT = i64;
}

def extload_glue : PatFrag<(ops node:$ptr), (unindexedload_glue node:$ptr)> {
  let IsLoad = 1;
  let IsAnyExtLoad = 1;
}

def sextload_glue : PatFrag<(ops node:$ptr), (unindexedload_glue node:$ptr)> {
  let IsLoad = 1;
  let IsSignExtLoad = 1;
}

def zextload_glue : PatFrag<(ops node:$ptr), (unindexedload_glue node:$ptr)> {
  let IsLoad = 1;
  let IsZeroExtLoad = 1;
}

def extloadi8_glue : PatFrag<(ops node:$ptr), (extload_glue node:$ptr)> {
  let IsLoad = 1;
  let MemoryVT = i8;
}

def zextloadi8_glue : PatFrag<(ops node:$ptr), (zextload_glue node:$ptr)> {
  let IsLoad = 1;
  let MemoryVT = i8;
}

def extloadi16_glue : PatFrag<(ops node:$ptr), (extload_glue node:$ptr)> {
  let IsLoad = 1;
  let MemoryVT = i16;
}

def zextloadi16_glue : PatFrag<(ops node:$ptr), (zextload_glue node:$ptr)> {
  let IsLoad = 1;
  let MemoryVT = i16;
}

def sextloadi8_glue : PatFrag<(ops node:$ptr), (sextload_glue node:$ptr)> {
  let IsLoad = 1;
  let MemoryVT = i8;
}

def sextloadi16_glue : PatFrag<(ops node:$ptr), (sextload_glue node:$ptr)> {
  let IsLoad = 1;
  let MemoryVT = i16;
}


let IsLoad = 1, AddressSpaces = LoadAddress_local.AddrSpaces in {
def load_local_m0 : PatFrag<(ops node:$ptr), (load_glue node:$ptr)> {
  let IsNonExtLoad = 1;
}

let MemoryVT = i8 in {
def extloadi8_local_m0 : PatFrag<(ops node:$ptr), (extloadi8_glue node:$ptr)>;
def sextloadi8_local_m0 : PatFrag<(ops node:$ptr), (sextloadi8_glue node:$ptr)>;
def zextloadi8_local_m0 : PatFrag<(ops node:$ptr), (zextloadi8_glue node:$ptr)>;
}

let MemoryVT = i16 in {
def extloadi16_local_m0 : PatFrag<(ops node:$ptr), (extloadi16_glue node:$ptr)>;
def sextloadi16_local_m0 : PatFrag<(ops node:$ptr), (sextloadi16_glue node:$ptr)>;
def zextloadi16_local_m0 : PatFrag<(ops node:$ptr), (zextloadi16_glue node:$ptr)>;
}

def load_align8_local_m0 : PatFrag<(ops node:$ptr),
                                   (load_local_m0 node:$ptr)> {
  let IsLoad = 1;
  let IsNonExtLoad = 1;
  let MinAlignment = 8;
}
def load_align16_local_m0 : PatFrag<(ops node:$ptr),
                                    (load_local_m0 node:$ptr)> {
  let IsLoad = 1;
  let IsNonExtLoad = 1;
  let MinAlignment = 16;
}

} // End IsLoad = 1

let IsAtomic = 1, AddressSpaces = LoadAddress_local.AddrSpaces in {
def atomic_load_32_local_m0 : PatFrag<(ops node:$ptr),
                                      (atomic_load_32_glue node:$ptr)> {
  let MemoryVT = i32;
}
def atomic_load_64_local_m0 : PatFrag<(ops node:$ptr),
                                       (atomic_load_64_glue node:$ptr)> {
  let MemoryVT = i64;
}

} // End let AddressSpaces = LoadAddress_local.AddrSpaces


def AMDGPUst_glue : SDNode <"ISD::STORE", SDTStore,
  [SDNPHasChain, SDNPMayStore, SDNPMemOperand, SDNPInGlue]
>;

def AMDGPUatomic_st_glue : SDNode <"ISD::ATOMIC_STORE", SDTAtomicStore,
  [SDNPHasChain, SDNPMayStore, SDNPMemOperand, SDNPInGlue]
>;

def unindexedstore_glue : PatFrag<(ops node:$val, node:$ptr),
                                   (AMDGPUst_glue node:$val, node:$ptr)> {
  let IsStore = 1;
  let IsUnindexed = 1;
}

def store_glue : PatFrag<(ops node:$val, node:$ptr),
                         (unindexedstore_glue node:$val, node:$ptr)> {
  let IsStore = 1;
  let IsTruncStore = 0;
}

def truncstore_glue : PatFrag<(ops node:$val, node:$ptr),
  (unindexedstore_glue node:$val, node:$ptr)> {
  let IsStore = 1;
  let IsTruncStore = 1;
}

def truncstorei8_glue : PatFrag<(ops node:$val, node:$ptr),
                           (truncstore_glue node:$val, node:$ptr)> {
  let IsStore = 1;
  let MemoryVT = i8;
}

def truncstorei16_glue : PatFrag<(ops node:$val, node:$ptr),
                           (truncstore_glue node:$val, node:$ptr)> {
  let IsStore = 1;
  let MemoryVT = i16;
}

let IsStore = 1, AddressSpaces = StoreAddress_local.AddrSpaces in {
def store_local_m0 : PatFrag<(ops node:$val, node:$ptr),
                             (store_glue node:$val, node:$ptr)> {
  let IsStore = 1;
  let IsTruncStore = 0;
}

def truncstorei8_local_m0 : PatFrag<(ops node:$val, node:$ptr),
                                    (unindexedstore_glue node:$val, node:$ptr)> {
  let IsStore = 1;
  let MemoryVT = i8;
}

def truncstorei16_local_m0 : PatFrag<(ops node:$val, node:$ptr),
                                    (unindexedstore_glue node:$val, node:$ptr)> {
  let IsStore = 1;
  let MemoryVT = i16;
}
}

def store_align16_local_m0 : PatFrag <
  (ops node:$value, node:$ptr),
  (store_local_m0 node:$value, node:$ptr)> {
  let IsStore = 1;
  let IsTruncStore = 0;
  let MinAlignment = 16;
}

def store_align8_local_m0 : PatFrag <
  (ops node:$value, node:$ptr),
  (store_local_m0 node:$value, node:$ptr)> {
  let IsStore = 1;
  let IsTruncStore = 0;
  let MinAlignment = 8;
}

let AddressSpaces = StoreAddress_local.AddrSpaces in {

def atomic_store_local_32_m0 : PatFrag <
  (ops node:$value, node:$ptr),
  (AMDGPUatomic_st_glue node:$value, node:$ptr)> {
  let IsAtomic = 1;
  let MemoryVT = i32;
}
def atomic_store_local_64_m0 : PatFrag <
  (ops node:$value, node:$ptr),
  (AMDGPUatomic_st_glue node:$value, node:$ptr)> {
  let IsAtomic = 1;
  let MemoryVT = i64;
}
} // End let AddressSpaces = StoreAddress_local.AddrSpaces


def si_setcc_uniform : PatFrag <
  (ops node:$lhs, node:$rhs, node:$cond),
  (setcc node:$lhs, node:$rhs, node:$cond), [{
  for (SDNode *Use : N->uses()) {
    if (Use->isMachineOpcode() || Use->getOpcode() != ISD::CopyToReg)
      return false;

    unsigned Reg = cast<RegisterSDNode>(Use->getOperand(1))->getReg();
    if (Reg != AMDGPU::SCC)
      return false;
  }
  return true;
}]>;

//===----------------------------------------------------------------------===//
// SDNodes PatFrags for d16 loads
//===----------------------------------------------------------------------===//

class LoadD16Frag <SDPatternOperator op> : PatFrag<(ops node:$ptr, node:$tied_in), (op node:$ptr, node:$tied_in)>;
class LocalLoadD16 <SDPatternOperator op> : LoadD16Frag <op>, LocalAddress;
class GlobalLoadD16 <SDPatternOperator op> : LoadD16Frag <op>, GlobalLoadAddress;
class PrivateLoadD16 <SDPatternOperator op> : LoadD16Frag <op>, PrivateAddress;
class FlatLoadD16 <SDPatternOperator op> : LoadD16Frag <op>, FlatLoadAddress;

def load_d16_hi_local : LocalLoadD16 <SIload_d16_hi>;
def az_extloadi8_d16_hi_local : LocalLoadD16 <SIload_d16_hi_u8>;
def sextloadi8_d16_hi_local : LocalLoadD16 <SIload_d16_hi_i8>;

def load_d16_hi_global : GlobalLoadD16 <SIload_d16_hi>;
def az_extloadi8_d16_hi_global : GlobalLoadD16 <SIload_d16_hi_u8>;
def sextloadi8_d16_hi_global : GlobalLoadD16 <SIload_d16_hi_i8>;

def load_d16_hi_private : PrivateLoadD16 <SIload_d16_hi>;
def az_extloadi8_d16_hi_private : PrivateLoadD16 <SIload_d16_hi_u8>;
def sextloadi8_d16_hi_private : PrivateLoadD16 <SIload_d16_hi_i8>;

def load_d16_hi_flat : FlatLoadD16 <SIload_d16_hi>;
def az_extloadi8_d16_hi_flat : FlatLoadD16 <SIload_d16_hi_u8>;
def sextloadi8_d16_hi_flat : FlatLoadD16 <SIload_d16_hi_i8>;


def load_d16_lo_local : LocalLoadD16 <SIload_d16_lo>;
def az_extloadi8_d16_lo_local : LocalLoadD16 <SIload_d16_lo_u8>;
def sextloadi8_d16_lo_local : LocalLoadD16 <SIload_d16_lo_i8>;

def load_d16_lo_global : GlobalLoadD16 <SIload_d16_lo>;
def az_extloadi8_d16_lo_global : GlobalLoadD16 <SIload_d16_lo_u8>;
def sextloadi8_d16_lo_global : GlobalLoadD16 <SIload_d16_lo_i8>;

def load_d16_lo_private : PrivateLoadD16 <SIload_d16_lo>;
def az_extloadi8_d16_lo_private : PrivateLoadD16 <SIload_d16_lo_u8>;
def sextloadi8_d16_lo_private : PrivateLoadD16 <SIload_d16_lo_i8>;

def load_d16_lo_flat : FlatLoadD16 <SIload_d16_lo>;
def az_extloadi8_d16_lo_flat : FlatLoadD16 <SIload_d16_lo_u8>;
def sextloadi8_d16_lo_flat : FlatLoadD16 <SIload_d16_lo_i8>;



def lshr_rev : PatFrag <
  (ops node:$src1, node:$src0),
  (srl $src0, $src1)
>;

def ashr_rev : PatFrag <
  (ops node:$src1, node:$src0),
  (sra $src0, $src1)
>;

def lshl_rev : PatFrag <
  (ops node:$src1, node:$src0),
  (shl $src0, $src1)
>;

def add_ctpop : PatFrag <
  (ops node:$src0, node:$src1),
  (add (ctpop $src0), $src1)
>;

multiclass SIAtomicM0Glue2 <string op_name, bit is_amdgpu = 0,
                            SDTypeProfile tc = SDTAtomic2,
                            bit IsInt = 1> {

  def _glue : SDNode <
    !if(is_amdgpu, "AMDGPUISD", "ISD")#"::ATOMIC_"#op_name, tc,
    [SDNPHasChain, SDNPMayStore, SDNPMayLoad, SDNPMemOperand, SDNPInGlue]
  >;

  let AddressSpaces = StoreAddress_local.AddrSpaces in {
    defm _local_m0 : binary_atomic_op <!cast<SDNode>(NAME#"_glue"), IsInt>;
  }

  let AddressSpaces = StoreAddress_region.AddrSpaces in {
    defm _region_m0 : binary_atomic_op <!cast<SDNode>(NAME#"_glue"), IsInt>;
  }
}

defm atomic_load_add : SIAtomicM0Glue2 <"LOAD_ADD">;
defm atomic_load_sub : SIAtomicM0Glue2 <"LOAD_SUB">;
defm atomic_inc : SIAtomicM0Glue2 <"INC", 1>;
defm atomic_dec : SIAtomicM0Glue2 <"DEC", 1>;
defm atomic_load_and : SIAtomicM0Glue2 <"LOAD_AND">;
defm atomic_load_min : SIAtomicM0Glue2 <"LOAD_MIN">;
defm atomic_load_max : SIAtomicM0Glue2 <"LOAD_MAX">;
defm atomic_load_or : SIAtomicM0Glue2 <"LOAD_OR">;
defm atomic_load_xor : SIAtomicM0Glue2 <"LOAD_XOR">;
defm atomic_load_umin : SIAtomicM0Glue2 <"LOAD_UMIN">;
defm atomic_load_umax : SIAtomicM0Glue2 <"LOAD_UMAX">;
defm atomic_swap : SIAtomicM0Glue2 <"SWAP">;
defm atomic_load_fadd : SIAtomicM0Glue2 <"LOAD_FADD", 0, SDTAtomic2_f32, 0>;
defm atomic_load_fmin : SIAtomicM0Glue2 <"LOAD_FMIN", 1, SDTAtomic2_f32, 0>;
defm atomic_load_fmax : SIAtomicM0Glue2 <"LOAD_FMAX", 1, SDTAtomic2_f32, 0>;

def as_i1imm : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(N->getZExtValue(), SDLoc(N), MVT::i1);
}]>;

def as_i8imm : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(N->getZExtValue(), SDLoc(N), MVT::i8);
}]>;

def as_i16imm : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(N->getSExtValue(), SDLoc(N), MVT::i16);
}]>;

def as_i32imm: SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(N->getSExtValue(), SDLoc(N), MVT::i32);
}]>;

def as_i32timm: SDNodeXForm<timm, [{
  return CurDAG->getTargetConstant(N->getSExtValue(), SDLoc(N), MVT::i32);
}]>;

def as_i64imm: SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(N->getSExtValue(), SDLoc(N), MVT::i64);
}]>;

def cond_as_i32imm: SDNodeXForm<cond, [{
  return CurDAG->getTargetConstant(N->get(), SDLoc(N), MVT::i32);
}]>;

// Copied from the AArch64 backend:
def bitcast_fpimm_to_i32 : SDNodeXForm<fpimm, [{
return CurDAG->getTargetConstant(
  N->getValueAPF().bitcastToAPInt().getZExtValue(), SDLoc(N), MVT::i32);
}]>;

def frameindex_to_targetframeindex : SDNodeXForm<frameindex, [{
  auto FI = cast<FrameIndexSDNode>(N);
  return CurDAG->getTargetFrameIndex(FI->getIndex(), MVT::i32);
}]>;

// Copied from the AArch64 backend:
def bitcast_fpimm_to_i64 : SDNodeXForm<fpimm, [{
return CurDAG->getTargetConstant(
  N->getValueAPF().bitcastToAPInt().getZExtValue(), SDLoc(N), MVT::i64);
}]>;

class bitextract_imm<int bitnum> : SDNodeXForm<imm, [{
  uint64_t Imm = N->getZExtValue();
  unsigned Bit = (Imm >> }] # bitnum # [{ ) & 1;
  return CurDAG->getTargetConstant(Bit, SDLoc(N), MVT::i1);
}]>;

def SIMM16bit : ImmLeaf <i32,
  [{return isInt<16>(Imm);}]
>;

def UIMM16bit : ImmLeaf <i32,
  [{return isUInt<16>(Imm);}]
>;

def i64imm_32bit : ImmLeaf<i64, [{
  return (Imm & 0xffffffffULL) == static_cast<uint64_t>(Imm);
}]>;

class InlineImm <ValueType vt> : PatLeaf <(vt imm), [{
  return isInlineImmediate(N);
}]>;

class InlineFPImm <ValueType vt> : PatLeaf <(vt fpimm), [{
  return isInlineImmediate(N);
}]>;

class VGPRImm <dag frag> : PatLeaf<frag, [{
  return isVGPRImm(N);
}]>;

def NegateImm : SDNodeXForm<imm, [{
  return CurDAG->getConstant(-N->getSExtValue(), SDLoc(N), MVT::i32);
}]>;

// TODO: When FP inline imm values work?
def NegSubInlineConst32 : ImmLeaf<i32, [{
  return Imm < -16 && Imm >= -64;
}], NegateImm>;

def NegSubInlineConst16 : ImmLeaf<i16, [{
  return Imm < -16 && Imm >= -64;
}], NegateImm>;

def ShiftAmt32Imm : PatLeaf <(imm), [{
  return N->getZExtValue() < 32;
}]>;

def getNegV2I16Imm : SDNodeXForm<build_vector, [{
  return SDValue(packNegConstantV2I16(N, *CurDAG), 0);
}]>;

def NegSubInlineConstV216 : PatLeaf<(build_vector), [{
  assert(N->getNumOperands() == 2);
  assert(N->getOperand(0).getValueType().getSizeInBits() == 16);
  SDValue Src0 = N->getOperand(0);
  SDValue Src1 = N->getOperand(1);
  if (Src0 == Src1)
    return isNegInlineImmediate(Src0.getNode());

  return (isNullConstantOrUndef(Src0) && isNegInlineImmediate(Src1.getNode())) ||
         (isNullConstantOrUndef(Src1) && isNegInlineImmediate(Src0.getNode()));
}], getNegV2I16Imm>;

//===----------------------------------------------------------------------===//
// Custom Operands
//===----------------------------------------------------------------------===//

def SoppBrTarget : AsmOperandClass {
  let Name = "SoppBrTarget";
  let ParserMethod = "parseSOppBrTarget";
}

def sopp_brtarget : Operand<OtherVT> {
  let EncoderMethod = "getSOPPBrEncoding";
  let DecoderMethod = "decodeSoppBrTarget";
  let OperandType = "OPERAND_PCREL";
  let ParserMatchClass = SoppBrTarget;
}

def si_ga : Operand<iPTR>;

def InterpSlotMatchClass : AsmOperandClass {
  let Name = "InterpSlot";
  let PredicateMethod = "isInterpSlot";
  let ParserMethod = "parseInterpSlot";
  let RenderMethod = "addImmOperands";
}

def InterpSlot : Operand<i32> {
  let PrintMethod = "printInterpSlot";
  let ParserMatchClass = InterpSlotMatchClass;
  let OperandType = "OPERAND_IMMEDIATE";
}

def AttrMatchClass : AsmOperandClass {
  let Name = "Attr";
  let PredicateMethod = "isInterpAttr";
  let ParserMethod = "parseInterpAttr";
  let RenderMethod = "addImmOperands";
}

// It appears to be necessary to create a separate operand for this to
// be able to parse attr<num> with no space.
def Attr : Operand<i32> {
  let PrintMethod = "printInterpAttr";
  let ParserMatchClass = AttrMatchClass;
  let OperandType = "OPERAND_IMMEDIATE";
}

def AttrChanMatchClass : AsmOperandClass {
  let Name = "AttrChan";
  let PredicateMethod = "isAttrChan";
  let RenderMethod = "addImmOperands";
}

def AttrChan : Operand<i32> {
  let PrintMethod = "printInterpAttrChan";
  let ParserMatchClass = AttrChanMatchClass;
  let OperandType = "OPERAND_IMMEDIATE";
}

def SendMsgMatchClass : AsmOperandClass {
  let Name = "SendMsg";
  let PredicateMethod = "isSendMsg";
  let ParserMethod = "parseSendMsgOp";
  let RenderMethod = "addImmOperands";
}

def SwizzleMatchClass : AsmOperandClass {
  let Name = "Swizzle";
  let PredicateMethod = "isSwizzle";
  let ParserMethod = "parseSwizzleOp";
  let RenderMethod = "addImmOperands";
  let IsOptional = 1;
}

def EndpgmMatchClass : AsmOperandClass {
  let Name = "EndpgmImm";
  let PredicateMethod = "isEndpgm";
  let ParserMethod = "parseEndpgmOp";
  let RenderMethod = "addImmOperands";
  let IsOptional = 1;
}

def ExpTgtMatchClass : AsmOperandClass {
  let Name = "ExpTgt";
  let PredicateMethod = "isExpTgt";
  let ParserMethod = "parseExpTgt";
  let RenderMethod = "printExpTgt";
}

def SWaitMatchClass : AsmOperandClass {
  let Name = "SWaitCnt";
  let RenderMethod = "addImmOperands";
  let ParserMethod = "parseSWaitCntOps";
}

def VReg32OrOffClass : AsmOperandClass {
  let Name = "VReg32OrOff";
  let ParserMethod = "parseVReg32OrOff";
}

let OperandType = "OPERAND_IMMEDIATE" in {
def SendMsgImm : Operand<i32> {
  let PrintMethod = "printSendMsg";
  let ParserMatchClass = SendMsgMatchClass;
}

def SwizzleImm : Operand<i16> {
  let PrintMethod = "printSwizzle";
  let ParserMatchClass = SwizzleMatchClass;
}

def EndpgmImm : Operand<i16> {
  let PrintMethod = "printEndpgm";
  let ParserMatchClass = EndpgmMatchClass;
}

def WAIT_FLAG : Operand <i32> {
  let ParserMatchClass = SWaitMatchClass;
  let PrintMethod = "printWaitFlag";
}
} // End OperandType = "OPERAND_IMMEDIATE"

include "SIInstrFormats.td"
include "VIInstrFormats.td"

def BoolReg : AsmOperandClass {
  let Name = "BoolReg";
  let ParserMethod = "parseBoolReg";
  let RenderMethod = "addRegOperands";
}

class BoolRC : RegisterOperand<SReg_1> {
  let ParserMatchClass = BoolReg;
  let DecoderMethod = "decodeBoolReg";
}

def SSrc_i1 : RegisterOperand<SReg_1_XEXEC> {
  let ParserMatchClass = BoolReg;
  let DecoderMethod = "decodeBoolReg";
}

def VOPDstS64orS32 : BoolRC {
  let PrintMethod = "printVOPDst";
}

// SCSrc_i1 is the operand for pseudo instructions only.
// Boolean immeadiates shall not be exposed to codegen instructions.
def SCSrc_i1 : RegisterOperand<SReg_1_XEXEC> {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_REG_IMM_INT32";
  let ParserMatchClass = BoolReg;
  let DecoderMethod = "decodeBoolReg";
}

// ===----------------------------------------------------------------------===//
// ExpSrc* Special cases for exp src operands which are printed as
// "off" depending on en operand.
// ===----------------------------------------------------------------------===//

def ExpSrc0 : RegisterOperand<VGPR_32> {
  let PrintMethod = "printExpSrc0";
  let ParserMatchClass = VReg32OrOffClass;
}

def ExpSrc1 : RegisterOperand<VGPR_32> {
  let PrintMethod = "printExpSrc1";
  let ParserMatchClass = VReg32OrOffClass;
}

def ExpSrc2 : RegisterOperand<VGPR_32> {
  let PrintMethod = "printExpSrc2";
  let ParserMatchClass = VReg32OrOffClass;
}

def ExpSrc3 : RegisterOperand<VGPR_32> {
  let PrintMethod = "printExpSrc3";
  let ParserMatchClass = VReg32OrOffClass;
}

class SDWASrc<ValueType vt> : RegisterOperand<VS_32> {
  let OperandNamespace = "AMDGPU";
  string Type = !if(isFloatType<vt>.ret, "FP", "INT");
  let OperandType = "OPERAND_REG_INLINE_C_"#Type#vt.Size;
  let DecoderMethod = "decodeSDWASrc"#vt.Size;
  let EncoderMethod = "getSDWASrcEncoding";
}

def SDWASrc_i32 : SDWASrc<i32>;
def SDWASrc_i16 : SDWASrc<i16>;
def SDWASrc_f32 : SDWASrc<f32>;
def SDWASrc_f16 : SDWASrc<f16>;

def SDWAVopcDst : BoolRC {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_SDWA_VOPC_DST";
  let EncoderMethod = "getSDWAVopcDstEncoding";
  let DecoderMethod = "decodeSDWAVopcDst";
  let PrintMethod = "printVOPDst";
}

class NamedMatchClass<string CName, bit Optional = 1> : AsmOperandClass {
  let Name = "Imm"#CName;
  let PredicateMethod = "is"#CName;
  let ParserMethod = !if(Optional, "parseOptionalOperand", "parse"#CName);
  let RenderMethod = "addImmOperands";
  let IsOptional = Optional;
  let DefaultMethod = !if(Optional, "default"#CName, ?);
}

class NamedOperandBit<string Name, AsmOperandClass MatchClass> : Operand<i1> {
  let PrintMethod = "print"#Name;
  let ParserMatchClass = MatchClass;
}

class NamedOperandU8<string Name, AsmOperandClass MatchClass> : Operand<i8> {
  let PrintMethod = "print"#Name;
  let ParserMatchClass = MatchClass;
}

class NamedOperandU16<string Name, AsmOperandClass MatchClass> : Operand<i16> {
  let PrintMethod = "print"#Name;
  let ParserMatchClass = MatchClass;
}

class NamedOperandU32<string Name, AsmOperandClass MatchClass> : Operand<i32> {
  let PrintMethod = "print"#Name;
  let ParserMatchClass = MatchClass;
}

class NamedOperandU32Default0<string Name, AsmOperandClass MatchClass> :
  OperandWithDefaultOps<i32, (ops (i32 0))> {
  let PrintMethod = "print"#Name;
  let ParserMatchClass = MatchClass;
}

let OperandType = "OPERAND_IMMEDIATE" in {

def offen : NamedOperandBit<"Offen", NamedMatchClass<"Offen">>;
def idxen : NamedOperandBit<"Idxen", NamedMatchClass<"Idxen">>;
def addr64 : NamedOperandBit<"Addr64", NamedMatchClass<"Addr64">>;

def flat_offset : NamedOperandU16<"FlatOffset", NamedMatchClass<"FlatOffset">>;
def offset : NamedOperandU16<"Offset", NamedMatchClass<"Offset">>;
def offset0 : NamedOperandU8<"Offset0", NamedMatchClass<"Offset0">>;
def offset1 : NamedOperandU8<"Offset1", NamedMatchClass<"Offset1">>;

def gds : NamedOperandBit<"GDS", NamedMatchClass<"GDS">>;

def omod : NamedOperandU32<"OModSI", NamedMatchClass<"OModSI">>;
def clampmod : NamedOperandBit<"ClampSI", NamedMatchClass<"ClampSI">>;
def highmod : NamedOperandBit<"High", NamedMatchClass<"High">>;

def DLC : NamedOperandBit<"DLC", NamedMatchClass<"DLC">>;
def GLC : NamedOperandBit<"GLC", NamedMatchClass<"GLC">>;
def SLC : NamedOperandBit<"SLC", NamedMatchClass<"SLC">>;
def TFE : NamedOperandBit<"TFE", NamedMatchClass<"TFE">>;
def SWZ : NamedOperandBit<"SWZ", NamedMatchClass<"SWZ">>;
def UNorm : NamedOperandBit<"UNorm", NamedMatchClass<"UNorm">>;
def DA : NamedOperandBit<"DA", NamedMatchClass<"DA">>;
def R128A16 : NamedOperandBit<"R128A16", NamedMatchClass<"R128A16">>;
def D16 : NamedOperandBit<"D16", NamedMatchClass<"D16">>;
def LWE : NamedOperandBit<"LWE", NamedMatchClass<"LWE">>;
def exp_compr : NamedOperandBit<"ExpCompr", NamedMatchClass<"ExpCompr">>;
def exp_vm : NamedOperandBit<"ExpVM", NamedMatchClass<"ExpVM">>;

def FORMAT : NamedOperandU8<"FORMAT", NamedMatchClass<"FORMAT">>;

def DMask : NamedOperandU16<"DMask", NamedMatchClass<"DMask">>;
def Dim : NamedOperandU8<"Dim", NamedMatchClass<"Dim", 0>>;

def dpp8 : NamedOperandU32<"DPP8", NamedMatchClass<"DPP8", 0>>;

def dpp_ctrl : NamedOperandU32<"DPPCtrl", NamedMatchClass<"DPPCtrl", 0>>;
def row_mask : NamedOperandU32<"RowMask", NamedMatchClass<"RowMask">>;
def bank_mask : NamedOperandU32<"BankMask", NamedMatchClass<"BankMask">>;
def bound_ctrl : NamedOperandBit<"BoundCtrl", NamedMatchClass<"BoundCtrl">>;
def FI : NamedOperandU32<"FI", NamedMatchClass<"FI">>;

def dst_sel : NamedOperandU32<"SDWADstSel", NamedMatchClass<"SDWADstSel">>;
def src0_sel : NamedOperandU32<"SDWASrc0Sel", NamedMatchClass<"SDWASrc0Sel">>;
def src1_sel : NamedOperandU32<"SDWASrc1Sel", NamedMatchClass<"SDWASrc1Sel">>;
def dst_unused : NamedOperandU32<"SDWADstUnused", NamedMatchClass<"SDWADstUnused">>;

def op_sel : NamedOperandU32Default0<"OpSel", NamedMatchClass<"OpSel">>;
def op_sel_hi : NamedOperandU32Default0<"OpSelHi", NamedMatchClass<"OpSelHi">>;
def neg_lo : NamedOperandU32Default0<"NegLo", NamedMatchClass<"NegLo">>;
def neg_hi : NamedOperandU32Default0<"NegHi", NamedMatchClass<"NegHi">>;

def blgp : NamedOperandU32<"BLGP", NamedMatchClass<"BLGP">>;
def cbsz : NamedOperandU32<"CBSZ", NamedMatchClass<"CBSZ">>;
def abid : NamedOperandU32<"ABID", NamedMatchClass<"ABID">>;

def hwreg : NamedOperandU16<"Hwreg", NamedMatchClass<"Hwreg", 0>>;

def exp_tgt : NamedOperandU8<"ExpTgt", NamedMatchClass<"ExpTgt", 0>> {

}

} // End OperandType = "OPERAND_IMMEDIATE"

class KImmMatchClass<int size> : AsmOperandClass {
  let Name = "KImmFP"#size;
  let PredicateMethod = "isKImmFP"#size;
  let ParserMethod = "parseImm";
  let RenderMethod = "addKImmFP"#size#"Operands";
}

class kimmOperand<ValueType vt> : Operand<vt> {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_KIMM"#vt.Size;
  let PrintMethod = "printU"#vt.Size#"ImmOperand";
  let ParserMatchClass = !cast<AsmOperandClass>("KImmFP"#vt.Size#"MatchClass");
}

// 32-bit VALU immediate operand that uses the constant bus.
def KImmFP32MatchClass : KImmMatchClass<32>;
def f32kimm : kimmOperand<i32>;

// 32-bit VALU immediate operand with a 16-bit value that uses the
// constant bus.
def KImmFP16MatchClass : KImmMatchClass<16>;
def f16kimm : kimmOperand<i16>;

class FPInputModsMatchClass <int opSize> : AsmOperandClass {
  let Name = "RegOrImmWithFP"#opSize#"InputMods";
  let ParserMethod = "parseRegOrImmWithFPInputMods";
  let PredicateMethod = "isRegOrImmWithFP"#opSize#"InputMods";
}

def FP16InputModsMatchClass : FPInputModsMatchClass<16>;
def FP32InputModsMatchClass : FPInputModsMatchClass<32>;
def FP64InputModsMatchClass : FPInputModsMatchClass<64>;

class InputMods <AsmOperandClass matchClass> : Operand <i32> {
  let OperandNamespace = "AMDGPU";
  let OperandType = "OPERAND_INPUT_MODS";
  let ParserMatchClass = matchClass;
}

class FPInputMods <FPInputModsMatchClass matchClass> : InputMods <matchClass> {
  let PrintMethod = "printOperandAndFPInputMods";
}

def FP16InputMods : FPInputMods<FP16InputModsMatchClass>;
def FP32InputMods : FPInputMods<FP32InputModsMatchClass>;
def FP64InputMods : FPInputMods<FP64InputModsMatchClass>;

class IntInputModsMatchClass <int opSize> : AsmOperandClass {
  let Name = "RegOrImmWithInt"#opSize#"InputMods";
  let ParserMethod = "parseRegOrImmWithIntInputMods";
  let PredicateMethod = "isRegOrImmWithInt"#opSize#"InputMods";
}
def Int32InputModsMatchClass : IntInputModsMatchClass<32>;
def Int64InputModsMatchClass : IntInputModsMatchClass<64>;

class IntInputMods <IntInputModsMatchClass matchClass> : InputMods <matchClass> {
  let PrintMethod = "printOperandAndIntInputMods";
}
def Int32InputMods : IntInputMods<Int32InputModsMatchClass>;
def Int64InputMods : IntInputMods<Int64InputModsMatchClass>;

class OpSelModsMatchClass : AsmOperandClass {
  let Name = "OpSelMods";
  let ParserMethod = "parseRegOrImm";
  let PredicateMethod = "isRegOrImm";
}

def IntOpSelModsMatchClass : OpSelModsMatchClass;
def IntOpSelMods : InputMods<IntOpSelModsMatchClass>;

class FPSDWAInputModsMatchClass <int opSize> : AsmOperandClass {
  let Name = "SDWAWithFP"#opSize#"InputMods";
  let ParserMethod = "parseRegOrImmWithFPInputMods";
  let PredicateMethod = "isSDWAFP"#opSize#"Operand";
}

def FP16SDWAInputModsMatchClass : FPSDWAInputModsMatchClass<16>;
def FP32SDWAInputModsMatchClass : FPSDWAInputModsMatchClass<32>;

class FPSDWAInputMods <FPSDWAInputModsMatchClass matchClass> :
  InputMods <matchClass> {
  let PrintMethod = "printOperandAndFPInputMods";
}

def FP16SDWAInputMods : FPSDWAInputMods<FP16SDWAInputModsMatchClass>;
def FP32SDWAInputMods : FPSDWAInputMods<FP32SDWAInputModsMatchClass>;

def FPVRegInputModsMatchClass : AsmOperandClass {
  let Name = "VRegWithFPInputMods";
  let ParserMethod = "parseRegWithFPInputMods";
  let PredicateMethod = "isVReg32";
}

def FPVRegInputMods : InputMods <FPVRegInputModsMatchClass> {
  let PrintMethod = "printOperandAndFPInputMods";
}

class IntSDWAInputModsMatchClass <int opSize> : AsmOperandClass {
  let Name = "SDWAWithInt"#opSize#"InputMods";
  let ParserMethod = "parseRegOrImmWithIntInputMods";
  let PredicateMethod = "isSDWAInt"#opSize#"Operand";
}

def Int16SDWAInputModsMatchClass : IntSDWAInputModsMatchClass<16>;
def Int32SDWAInputModsMatchClass : IntSDWAInputModsMatchClass<32>;

class IntSDWAInputMods <IntSDWAInputModsMatchClass matchClass> :
  InputMods <matchClass> {
  let PrintMethod = "printOperandAndIntInputMods";
}

def Int16SDWAInputMods : IntSDWAInputMods<Int16SDWAInputModsMatchClass>;
def Int32SDWAInputMods : IntSDWAInputMods<Int32SDWAInputModsMatchClass>;

def IntVRegInputModsMatchClass : AsmOperandClass {
  let Name = "VRegWithIntInputMods";
  let ParserMethod = "parseRegWithIntInputMods";
  let PredicateMethod = "isVReg32";
}

def IntVRegInputMods : InputMods <IntVRegInputModsMatchClass> {
  let PrintMethod = "printOperandAndIntInputMods";
}

class PackedFPInputModsMatchClass <int opSize> : AsmOperandClass {
  let Name = "PackedFP"#opSize#"InputMods";
  let ParserMethod = "parseRegOrImm";
  let PredicateMethod = "isRegOrImm";
//  let PredicateMethod = "isPackedFP"#opSize#"InputMods";
}

class PackedIntInputModsMatchClass <int opSize> : AsmOperandClass {
  let Name = "PackedInt"#opSize#"InputMods";
  let ParserMethod = "parseRegOrImm";
  let PredicateMethod = "isRegOrImm";
//  let PredicateMethod = "isPackedInt"#opSize#"InputMods";
}

def PackedF16InputModsMatchClass : PackedFPInputModsMatchClass<16>;
def PackedI16InputModsMatchClass : PackedIntInputModsMatchClass<16>;

class PackedFPInputMods <PackedFPInputModsMatchClass matchClass> : InputMods <matchClass> {
//  let PrintMethod = "printPackedFPInputMods";
}

class PackedIntInputMods <PackedIntInputModsMatchClass matchClass> : InputMods <matchClass> {
  //let PrintMethod = "printPackedIntInputMods";
}

def PackedF16InputMods : PackedFPInputMods<PackedF16InputModsMatchClass>;
def PackedI16InputMods : PackedIntInputMods<PackedI16InputModsMatchClass>;

//===----------------------------------------------------------------------===//
// Complex patterns
//===----------------------------------------------------------------------===//

def DS1Addr1Offset : ComplexPattern<i32, 2, "SelectDS1Addr1Offset">;
def DS64Bit4ByteAligned : ComplexPattern<i32, 3, "SelectDS64Bit4ByteAligned">;

def MOVRELOffset : ComplexPattern<i32, 2, "SelectMOVRELOffset">;

def VOP3Mods0 : ComplexPattern<untyped, 4, "SelectVOP3Mods0">;
def VOP3Mods0Clamp : ComplexPattern<untyped, 3, "SelectVOP3Mods0Clamp">;
def VOP3Mods0Clamp0OMod : ComplexPattern<untyped, 4, "SelectVOP3Mods0Clamp0OMod">;
def VOP3Mods  : ComplexPattern<untyped, 2, "SelectVOP3Mods">;
def VOP3NoMods : ComplexPattern<untyped, 1, "SelectVOP3NoMods">;
// VOP3Mods, but the input source is known to never be NaN.
def VOP3Mods_nnan : ComplexPattern<fAny, 2, "SelectVOP3Mods_NNaN">;
// VOP3Mods, but only allowed for f32 operands.
def VOP3Mods_f32 : ComplexPattern<fAny, 2, "SelectVOP3Mods_f32">;

def VOP3OMods : ComplexPattern<untyped, 3, "SelectVOP3OMods">;

def VOP3PMods  : ComplexPattern<untyped, 2, "SelectVOP3PMods">;
def VOP3PMods0 : ComplexPattern<untyped, 3, "SelectVOP3PMods0">;

def VOP3OpSel  : ComplexPattern<untyped, 2, "SelectVOP3OpSel">;
def VOP3OpSel0 : ComplexPattern<untyped, 3, "SelectVOP3OpSel0">;

def VOP3OpSelMods  : ComplexPattern<untyped, 2, "SelectVOP3OpSelMods">;
def VOP3OpSelMods0 : ComplexPattern<untyped, 3, "SelectVOP3OpSelMods0">;

def VOP3PMadMixMods  : ComplexPattern<untyped, 2, "SelectVOP3PMadMixMods">;


def Hi16Elt  : ComplexPattern<untyped, 1, "SelectHi16Elt">;

//===----------------------------------------------------------------------===//
// SI assembler operands
//===----------------------------------------------------------------------===//

def SIOperand {
  int ZERO = 0x80;
  int VCC = 0x6A;
  int FLAT_SCR = 0x68;
}

// This should be kept in sync with SISrcMods enum
def SRCMODS {
  int NONE = 0;
  int NEG = 1;
  int ABS = 2;
  int NEG_ABS = 3;

  int NEG_HI = ABS;
  int OP_SEL_0 = 4;
  int OP_SEL_1 = 8;
  int DST_OP_SEL = 8;
}

def DSTCLAMP {
  int NONE = 0;
  int ENABLE = 1;
}

def DSTOMOD {
  int NONE = 0;
}

def TRAPID{
  int LLVM_TRAP = 2;
  int LLVM_DEBUG_TRAP = 3;
}

def HWREG {
  int MODE = 1;
  int STATUS = 2;
  int TRAPSTS = 3;
  int HW_ID = 4;
  int GPR_ALLOC = 5;
  int LDS_ALLOC = 6;
  int IB_STS = 7;
  int MEM_BASES = 15;
  int TBA_LO = 16;
  int TBA_HI = 17;
  int TMA_LO = 18;
  int TMA_HI = 19;
  int FLAT_SCR_LO = 20;
  int FLAT_SCR_HI = 21;
  int XNACK_MASK = 22;
  int POPS_PACKER = 25;
}

class getHwRegImm<int Reg, int Offset = 0, int Size = 32> {
  int ret = !or(Reg,
                !or(!shl(Offset, 6),
                    !shl(!add(Size, -1), 11)));
}

//===----------------------------------------------------------------------===//
//
// SI Instruction multiclass helpers.
//
// Instructions with _32 take 32-bit operands.
// Instructions with _64 take 64-bit operands.
//
// VOP_* instructions can use either a 32-bit or 64-bit encoding.  The 32-bit
// encoding is the standard encoding, but instruction that make use of
// any of the instruction modifiers must use the 64-bit encoding.
//
// Instructions with _e32 use the 32-bit encoding.
// Instructions with _e64 use the 64-bit encoding.
//
//===----------------------------------------------------------------------===//

class SIMCInstr <string pseudo, int subtarget> {
  string PseudoInstr = pseudo;
  int Subtarget = subtarget;
}

//===----------------------------------------------------------------------===//
// EXP classes
//===----------------------------------------------------------------------===//

class EXP_Helper<bit done, SDPatternOperator node = null_frag> : EXPCommon<
  (outs),
  (ins exp_tgt:$tgt,
       ExpSrc0:$src0, ExpSrc1:$src1, ExpSrc2:$src2, ExpSrc3:$src3,
       exp_vm:$vm, exp_compr:$compr, i8imm:$en),
  "exp$tgt $src0, $src1, $src2, $src3"#!if(done, " done", "")#"$compr$vm",
  [(node (i8 timm:$tgt), (i8 timm:$en),
         f32:$src0, f32:$src1, f32:$src2, f32:$src3,
         (i1 timm:$compr), (i1 timm:$vm))]> {
  let AsmMatchConverter = "cvtExp";
}

// Split EXP instruction into EXP and EXP_DONE so we can set
// mayLoad for done=1.
multiclass EXP_m<bit done, SDPatternOperator node> {
  let mayLoad = done, DisableWQM = 1 in {
    let isPseudo = 1, isCodeGenOnly = 1 in {
      def "" : EXP_Helper<done, node>,
               SIMCInstr <"exp"#!if(done, "_done", ""), SIEncodingFamily.NONE>;
    }

    let done = done in {
      def _si : EXP_Helper<done>,
                SIMCInstr <"exp"#!if(done, "_done", ""), SIEncodingFamily.SI>,
                EXPe {
        let AssemblerPredicates = [isGFX6GFX7];
        let DecoderNamespace = "GFX6GFX7";
        let DisableDecoder = DisableSIDecoder;
      }

      def _vi : EXP_Helper<done>,
                SIMCInstr <"exp"#!if(done, "_done", ""), SIEncodingFamily.VI>,
                EXPe_vi {
        let AssemblerPredicates = [isGFX8GFX9];
        let DecoderNamespace = "GFX8";
        let DisableDecoder = DisableVIDecoder;
      }

      def _gfx10 : EXP_Helper<done>,
                SIMCInstr <"exp"#!if(done, "_done", ""), SIEncodingFamily.GFX10>,
                EXPe {
        let AssemblerPredicates = [isGFX10Plus];
        let DecoderNamespace = "GFX10";
        let DisableDecoder = DisableSIDecoder;
      }
    }
  }
}

//===----------------------------------------------------------------------===//
// Vector ALU classes
//===----------------------------------------------------------------------===//

class getNumSrcArgs<ValueType Src0, ValueType Src1, ValueType Src2> {
  int ret =
    !if (!eq(Src0.Value, untyped.Value),      0,
      !if (!eq(Src1.Value, untyped.Value),    1,   // VOP1
         !if (!eq(Src2.Value, untyped.Value), 2,   // VOP2
                                              3))); // VOP3
}

// Returns the register class to use for the destination of VOP[123C]
// instructions for the given VT.
class getVALUDstForVT<ValueType VT> {
  RegisterOperand ret = !if(!eq(VT.Size, 32), VOPDstOperand<VGPR_32>,
                          !if(!eq(VT.Size, 128), VOPDstOperand<VReg_128>,
                            !if(!eq(VT.Size, 64), VOPDstOperand<VReg_64>,
                              !if(!eq(VT.Size, 16), VOPDstOperand<VGPR_32>,
                              VOPDstS64orS32)))); // else VT == i1
}

// Returns the register class to use for the destination of VOP[12C]
// instructions with SDWA extension
class getSDWADstForVT<ValueType VT> {
  RegisterOperand ret = !if(!eq(VT.Size, 1),
                            SDWAVopcDst, // VOPC
                            VOPDstOperand<VGPR_32>); // VOP1/2 32-bit dst
}

// Returns the register class to use for source 0 of VOP[12C]
// instructions for the given VT.
class getVOPSrc0ForVT<ValueType VT> {
  bit isFP = isFloatType<VT>.ret;

  RegisterOperand ret =
    !if(isFP,
      !if(!eq(VT.Size, 64),
         VSrc_f64,
         !if(!eq(VT.Value, f16.Value),
            VSrc_f16,
            !if(!eq(VT.Value, v2f16.Value),
               VSrc_v2f16,
               !if(!eq(VT.Value, v4f16.Value),
                 AVSrc_64,
                 VSrc_f32
               )
            )
         )
       ),
       !if(!eq(VT.Size, 64),
          VSrc_b64,
          !if(!eq(VT.Value, i16.Value),
             VSrc_b16,
             !if(!eq(VT.Value, v2i16.Value),
                VSrc_v2b16,
                VSrc_b32
             )
          )
       )
    );
}

// Returns the vreg register class to use for source operand given VT
class getVregSrcForVT<ValueType VT> {
  RegisterClass ret = !if(!eq(VT.Size, 128), VReg_128,
                        !if(!eq(VT.Size, 96), VReg_96,
                          !if(!eq(VT.Size, 64), VReg_64,
                            !if(!eq(VT.Size, 48), VReg_64,
                              VGPR_32))));
}

class getSDWASrcForVT <ValueType VT> {
  bit isFP = isFloatType<VT>.ret;
  RegisterOperand retFlt = !if(!eq(VT.Size, 16), SDWASrc_f16, SDWASrc_f32);
  RegisterOperand retInt = !if(!eq(VT.Size, 16), SDWASrc_i16, SDWASrc_i32);
  RegisterOperand ret = !if(isFP, retFlt, retInt);
}

// Returns the register class to use for sources of VOP3 instructions for the
// given VT.
class getVOP3SrcForVT<ValueType VT> {
  bit isFP = isFloatType<VT>.ret;
  RegisterOperand ret =
  !if(!eq(VT.Size, 128),
     VSrc_128,
     !if(!eq(VT.Size, 64),
        !if(isFP,
           VSrc_f64,
           VSrc_b64),
        !if(!eq(VT.Value, i1.Value),
           SSrc_i1,
           !if(isFP,
              !if(!eq(VT.Value, f16.Value),
                 VSrc_f16,
                 !if(!eq(VT.Value, v2f16.Value),
                    VSrc_v2f16,
                    !if(!eq(VT.Value, v4f16.Value),
                      AVSrc_64,
                      VSrc_f32
                    )
                 )
              ),
              !if(!eq(VT.Value, i16.Value),
                 VSrc_b16,
                 !if(!eq(VT.Value, v2i16.Value),
                    VSrc_v2b16,
                    VSrc_b32
                 )
              )
           )
        )
     )
  );
}

// Float or packed int
class isModifierType<ValueType SrcVT> {
  bit ret =
    !if(!eq(SrcVT.Value, f16.Value), 1,
    !if(!eq(SrcVT.Value, f32.Value), 1,
    !if(!eq(SrcVT.Value, f64.Value), 1,
    !if(!eq(SrcVT.Value, v2f16.Value), 1,
    !if(!eq(SrcVT.Value, v2i16.Value), 1,
    0)))));
}

// Return type of input modifiers operand for specified input operand
class getSrcMod <ValueType VT, bit EnableF32SrcMods> {
  bit isFP = isFloatType<VT>.ret;
  bit isPacked = isPackedType<VT>.ret;
  Operand ret =  !if(!eq(VT.Size, 64),
                     !if(isFP, FP64InputMods, Int64InputMods),
                       !if(isFP,
                         !if(!eq(VT.Value, f16.Value),
                            FP16InputMods,
                            FP32InputMods
                          ),
                         !if(EnableF32SrcMods, FP32InputMods, Int32InputMods))
                     );
}

class getOpSelMod <ValueType VT> {
  Operand ret = !if(!eq(VT.Value, f16.Value), FP16InputMods, IntOpSelMods);
}

// Return type of input modifiers operand specified input operand for DPP
class getSrcModExt <ValueType VT> {
  bit isFP = isFloatType<VT>.ret;
  Operand ret = !if(isFP, FPVRegInputMods, IntVRegInputMods);
}

// Return type of input modifiers operand specified input operand for SDWA
class getSrcModSDWA <ValueType VT> {
  Operand ret = !if(!eq(VT.Value, f16.Value), FP16SDWAInputMods,
                !if(!eq(VT.Value, f32.Value), FP32SDWAInputMods,
                !if(!eq(VT.Value, i16.Value), Int16SDWAInputMods,
                Int32SDWAInputMods)));
}

// Returns the input arguments for VOP[12C] instructions for the given SrcVT.
class getIns32 <RegisterOperand Src0RC, RegisterClass Src1RC, int NumSrcArgs> {
  dag ret = !if(!eq(NumSrcArgs, 1), (ins Src0RC:$src0),               // VOP1
            !if(!eq(NumSrcArgs, 2), (ins Src0RC:$src0, Src1RC:$src1), // VOP2
                                    (ins)));
}

// Returns the input arguments for VOP3 instructions for the given SrcVT.
class getIns64 <RegisterOperand Src0RC, RegisterOperand Src1RC,
                RegisterOperand Src2RC, int NumSrcArgs,
                bit HasIntClamp, bit HasModifiers, bit HasSrc2Mods, bit HasOMod,
                Operand Src0Mod, Operand Src1Mod, Operand Src2Mod> {

  dag ret =
    !if (!eq(NumSrcArgs, 0),
      // VOP1 without input operands (V_NOP, V_CLREXCP)
      (ins),
      /* else */
    !if (!eq(NumSrcArgs, 1),
      !if (!eq(HasModifiers, 1),
        // VOP1 with modifiers
        (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
             clampmod:$clamp, omod:$omod)
      /* else */,
        // VOP1 without modifiers
        !if (!eq(HasIntClamp, 1),
          (ins Src0RC:$src0, clampmod:$clamp),
          (ins Src0RC:$src0))
      /* endif */ ),
    !if (!eq(NumSrcArgs, 2),
      !if (!eq(HasModifiers, 1),
        // VOP 2 with modifiers
        !if( !eq(HasOMod, 1),
          (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
               Src1Mod:$src1_modifiers, Src1RC:$src1,
               clampmod:$clamp, omod:$omod),
           (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
               Src1Mod:$src1_modifiers, Src1RC:$src1,
               clampmod:$clamp))
      /* else */,
        // VOP2 without modifiers
        !if (!eq(HasIntClamp, 1),
          (ins Src0RC:$src0, Src1RC:$src1, clampmod:$clamp),
          (ins Src0RC:$src0, Src1RC:$src1))

      /* endif */ )
    /* NumSrcArgs == 3 */,
      !if (!eq(HasModifiers, 1),
        !if (!eq(HasSrc2Mods, 1),
          // VOP3 with modifiers
          !if (!eq(HasOMod, 1),
            (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                 Src1Mod:$src1_modifiers, Src1RC:$src1,
                 Src2Mod:$src2_modifiers, Src2RC:$src2,
                 clampmod:$clamp, omod:$omod),
            !if (!eq(HasIntClamp, 1),
              (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                   Src1Mod:$src1_modifiers, Src1RC:$src1,
                   Src2Mod:$src2_modifiers, Src2RC:$src2,
                   clampmod:$clamp),
              (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                   Src1Mod:$src1_modifiers, Src1RC:$src1,
                   Src2Mod:$src2_modifiers, Src2RC:$src2))),
          // VOP3 with modifiers except src2
          !if (!eq(HasOMod, 1),
            (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                 Src1Mod:$src1_modifiers, Src1RC:$src1,
                 Src2RC:$src2, clampmod:$clamp, omod:$omod),
            !if (!eq(HasIntClamp, 1),
              (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                   Src1Mod:$src1_modifiers, Src1RC:$src1,
                   Src2RC:$src2, clampmod:$clamp),
              (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                   Src1Mod:$src1_modifiers, Src1RC:$src1,
                   Src2RC:$src2))))
      /* else */,
        // VOP3 without modifiers
        !if (!eq(HasIntClamp, 1),
          (ins Src0RC:$src0, Src1RC:$src1, Src2RC:$src2, clampmod:$clamp),
          (ins Src0RC:$src0, Src1RC:$src1, Src2RC:$src2))
      /* endif */ ))));
}

/// XXX - src1 may only allow VGPRs?

// The modifiers (except clamp) are dummy operands for the benefit of
// printing and parsing. They defer their values to looking at the
// srcN_modifiers for what to print.
class getInsVOP3P <RegisterOperand Src0RC, RegisterOperand Src1RC,
                   RegisterOperand Src2RC, int NumSrcArgs,
                   bit HasClamp,
                   Operand Src0Mod, Operand Src1Mod, Operand Src2Mod> {
  dag ret = !if (!eq(NumSrcArgs, 2),
    !if (HasClamp,
      (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
           Src1Mod:$src1_modifiers, Src1RC:$src1,
           clampmod:$clamp,
           op_sel:$op_sel, op_sel_hi:$op_sel_hi,
           neg_lo:$neg_lo, neg_hi:$neg_hi),
      (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
           Src1Mod:$src1_modifiers, Src1RC:$src1,
           op_sel:$op_sel, op_sel_hi:$op_sel_hi,
           neg_lo:$neg_lo, neg_hi:$neg_hi)),
    // else NumSrcArgs == 3
    !if (HasClamp,
      (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
           Src1Mod:$src1_modifiers, Src1RC:$src1,
           Src2Mod:$src2_modifiers, Src2RC:$src2,
           clampmod:$clamp,
           op_sel:$op_sel, op_sel_hi:$op_sel_hi,
           neg_lo:$neg_lo, neg_hi:$neg_hi),
      (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
           Src1Mod:$src1_modifiers, Src1RC:$src1,
           Src2Mod:$src2_modifiers, Src2RC:$src2,
           op_sel:$op_sel, op_sel_hi:$op_sel_hi,
           neg_lo:$neg_lo, neg_hi:$neg_hi))
  );
}

class getInsVOP3OpSel <RegisterOperand Src0RC,
                       RegisterOperand Src1RC,
                       RegisterOperand Src2RC,
                       int NumSrcArgs,
                       bit HasClamp,
                       Operand Src0Mod,
                       Operand Src1Mod,
                       Operand Src2Mod> {
  dag ret = !if (!eq(NumSrcArgs, 2),
    !if (HasClamp,
      (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
           Src1Mod:$src1_modifiers, Src1RC:$src1,
           clampmod:$clamp,
           op_sel:$op_sel),
      (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
           Src1Mod:$src1_modifiers, Src1RC:$src1,
           op_sel:$op_sel)),
    // else NumSrcArgs == 3
    !if (HasClamp,
      (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
           Src1Mod:$src1_modifiers, Src1RC:$src1,
           Src2Mod:$src2_modifiers, Src2RC:$src2,
           clampmod:$clamp,
           op_sel:$op_sel),
      (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
           Src1Mod:$src1_modifiers, Src1RC:$src1,
           Src2Mod:$src2_modifiers, Src2RC:$src2,
           op_sel:$op_sel))
  );
}

class getInsDPP <RegisterOperand DstRC, RegisterClass Src0RC, RegisterClass Src1RC,
                 int NumSrcArgs, bit HasModifiers,
                 Operand Src0Mod, Operand Src1Mod> {

  dag ret = !if (!eq(NumSrcArgs, 0),
                // VOP1 without input operands (V_NOP)
                (ins dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
                     bank_mask:$bank_mask, bound_ctrl:$bound_ctrl),
            !if (!eq(NumSrcArgs, 1),
              !if (!eq(HasModifiers, 1),
                // VOP1_DPP with modifiers
                (ins DstRC:$old, Src0Mod:$src0_modifiers,
                     Src0RC:$src0, dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
                     bank_mask:$bank_mask, bound_ctrl:$bound_ctrl)
              /* else */,
                // VOP1_DPP without modifiers
                (ins DstRC:$old, Src0RC:$src0,
                     dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
                     bank_mask:$bank_mask, bound_ctrl:$bound_ctrl)
              /* endif */)
              /* NumSrcArgs == 2 */,
              !if (!eq(HasModifiers, 1),
                // VOP2_DPP with modifiers
                (ins DstRC:$old,
                     Src0Mod:$src0_modifiers, Src0RC:$src0,
                     Src1Mod:$src1_modifiers, Src1RC:$src1,
                     dpp_ctrl:$dpp_ctrl, row_mask:$row_mask,
                     bank_mask:$bank_mask, bound_ctrl:$bound_ctrl)
              /* else */,
                // VOP2_DPP without modifiers
                (ins DstRC:$old,
                     Src0RC:$src0, Src1RC:$src1, dpp_ctrl:$dpp_ctrl,
                     row_mask:$row_mask, bank_mask:$bank_mask,
                     bound_ctrl:$bound_ctrl)
             /* endif */)));
}

class getInsDPP16 <RegisterOperand DstRC, RegisterClass Src0RC, RegisterClass Src1RC,
                   int NumSrcArgs, bit HasModifiers,
                   Operand Src0Mod, Operand Src1Mod> {
  dag ret = !con(getInsDPP<DstRC, Src0RC, Src1RC, NumSrcArgs,
                           HasModifiers, Src0Mod, Src1Mod>.ret,
                 (ins FI:$fi));
}

class getInsDPP8 <RegisterOperand DstRC, RegisterClass Src0RC, RegisterClass Src1RC,
                 int NumSrcArgs, bit HasModifiers,
                 Operand Src0Mod, Operand Src1Mod> {
  dag ret = !if (!eq(NumSrcArgs, 0),
                // VOP1 without input operands (V_NOP)
                (ins dpp8:$dpp8, FI:$fi),
            !if (!eq(NumSrcArgs, 1),
              !if (!eq(HasModifiers, 1),
                // VOP1_DPP with modifiers
                (ins DstRC:$old, Src0Mod:$src0_modifiers,
                     Src0RC:$src0, dpp8:$dpp8, FI:$fi)
              /* else */,
                // VOP1_DPP without modifiers
                (ins DstRC:$old, Src0RC:$src0, dpp8:$dpp8, FI:$fi)
              /* endif */)
              /* NumSrcArgs == 2 */,
              !if (!eq(HasModifiers, 1),
                // VOP2_DPP with modifiers
                (ins DstRC:$old,
                     Src0Mod:$src0_modifiers, Src0RC:$src0,
                     Src1Mod:$src1_modifiers, Src1RC:$src1,
                     dpp8:$dpp8, FI:$fi)
              /* else */,
                // VOP2_DPP without modifiers
                (ins DstRC:$old,
                     Src0RC:$src0, Src1RC:$src1, dpp8:$dpp8, FI:$fi)
             /* endif */)));
}


// Ins for SDWA
class getInsSDWA <RegisterOperand Src0RC, RegisterOperand Src1RC, int NumSrcArgs,
                  bit HasSDWAOMod, Operand Src0Mod, Operand Src1Mod,
                  ValueType DstVT> {

  dag ret = !if(!eq(NumSrcArgs, 0),
               // VOP1 without input operands (V_NOP)
               (ins),
            !if(!eq(NumSrcArgs, 1),
               // VOP1
               !if(!eq(HasSDWAOMod, 0),
                  // VOP1_SDWA without omod
                  (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                       clampmod:$clamp,
                       dst_sel:$dst_sel, dst_unused:$dst_unused,
                       src0_sel:$src0_sel),
                  // VOP1_SDWA with omod
                  (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                       clampmod:$clamp, omod:$omod,
                       dst_sel:$dst_sel, dst_unused:$dst_unused,
                       src0_sel:$src0_sel)),
            !if(!eq(NumSrcArgs, 2),
               !if(!eq(DstVT.Size, 1),
                  // VOPC_SDWA
                  (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                       Src1Mod:$src1_modifiers, Src1RC:$src1,
                       clampmod:$clamp, src0_sel:$src0_sel, src1_sel:$src1_sel),
                  // VOP2_SDWA
                  !if(!eq(HasSDWAOMod, 0),
                     // VOP2_SDWA without omod
                     (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                          Src1Mod:$src1_modifiers, Src1RC:$src1,
                          clampmod:$clamp,
                          dst_sel:$dst_sel, dst_unused:$dst_unused,
                          src0_sel:$src0_sel, src1_sel:$src1_sel),
                     // VOP2_SDWA with omod
                     (ins Src0Mod:$src0_modifiers, Src0RC:$src0,
                          Src1Mod:$src1_modifiers, Src1RC:$src1,
                          clampmod:$clamp, omod:$omod,
                          dst_sel:$dst_sel, dst_unused:$dst_unused,
                          src0_sel:$src0_sel, src1_sel:$src1_sel))),
            (ins)/* endif */)));
}

// Outs for DPP and SDWA
class getOutsExt <bit HasDst, ValueType DstVT, RegisterOperand DstRCExt> {
  dag ret = !if(HasDst,
                !if(!eq(DstVT.Size, 1),
                    (outs), // no dst for VOPC, we use "vcc"-token as dst in SDWA VOPC instructions
                    (outs DstRCExt:$vdst)),
                (outs)); // V_NOP
}

// Outs for SDWA
class getOutsSDWA <bit HasDst, ValueType DstVT, RegisterOperand DstRCSDWA> {
  dag ret = !if(HasDst,
                !if(!eq(DstVT.Size, 1),
                    (outs DstRCSDWA:$sdst),
                    (outs DstRCSDWA:$vdst)),
                (outs)); // V_NOP
}

// Returns the assembly string for the inputs and outputs of a VOP[12C]
// instruction.  This does not add the _e32 suffix, so it can be reused
// by getAsm64.
class getAsm32 <bit HasDst, int NumSrcArgs, ValueType DstVT = i32> {
  string dst = !if(!eq(DstVT.Size, 1), "$sdst", "$vdst"); // use $sdst for VOPC
  string src0 = ", $src0";
  string src1 = ", $src1";
  string src2 = ", $src2";
  string ret = !if(HasDst, dst, "") #
               !if(!eq(NumSrcArgs, 1), src0, "") #
               !if(!eq(NumSrcArgs, 2), src0#src1, "") #
               !if(!eq(NumSrcArgs, 3), src0#src1#src2, "");
}

// Returns the assembly string for the inputs and outputs of a VOP3
// instruction.
class getAsm64 <bit HasDst, int NumSrcArgs, bit HasIntClamp, bit HasModifiers,
                bit HasOMod, ValueType DstVT = i32> {
  string dst = !if(!eq(DstVT.Size, 1), "$sdst", "$vdst"); // use $sdst for VOPC
  string src0 = !if(!eq(NumSrcArgs, 1), "$src0_modifiers", "$src0_modifiers,");
  string src1 = !if(!eq(NumSrcArgs, 1), "",
                   !if(!eq(NumSrcArgs, 2), " $src1_modifiers",
                                           " $src1_modifiers,"));
  string src2 = !if(!eq(NumSrcArgs, 3), " $src2_modifiers", "");
  string iclamp = !if(HasIntClamp, "$clamp", "");
  string ret =
  !if(!eq(HasModifiers, 0),
      getAsm32<HasDst, NumSrcArgs, DstVT>.ret # iclamp,
      dst#", "#src0#src1#src2#"$clamp"#!if(HasOMod, "$omod", ""));
}

// Returns the assembly string for the inputs and outputs of a VOP3P
// instruction.
class getAsmVOP3P <bit HasDst, int NumSrcArgs, bit HasModifiers,
                   bit HasClamp, ValueType DstVT = i32> {
  string dst = " $vdst";
  string src0 = !if(!eq(NumSrcArgs, 1), "$src0", "$src0,");
  string src1 = !if(!eq(NumSrcArgs, 1), "",
                   !if(!eq(NumSrcArgs, 2), " $src1",
                                           " $src1,"));
  string src2 = !if(!eq(NumSrcArgs, 3), " $src2", "");

  string mods = !if(HasModifiers, "$neg_lo$neg_hi", "");
  string clamp = !if(HasClamp, "$clamp", "");

  // Each modifier is printed as an array of bits for each operand, so
  // all operands are printed as part of src0_modifiers.
  string ret = dst#", "#src0#src1#src2#"$op_sel$op_sel_hi"#mods#clamp;
}

class getAsmVOP3OpSel <int NumSrcArgs,
                       bit HasClamp,
                       bit Src0HasMods,
                       bit Src1HasMods,
                       bit Src2HasMods> {
  string dst = " $vdst";

  string isrc0 = !if(!eq(NumSrcArgs, 1), "$src0", "$src0,");
  string isrc1 = !if(!eq(NumSrcArgs, 1), "",
                     !if(!eq(NumSrcArgs, 2), " $src1",
                                             " $src1,"));
  string isrc2 = !if(!eq(NumSrcArgs, 3), " $src2", "");

  string fsrc0 = !if(!eq(NumSrcArgs, 1), "$src0_modifiers", "$src0_modifiers,");
  string fsrc1 = !if(!eq(NumSrcArgs, 1), "",
                     !if(!eq(NumSrcArgs, 2), " $src1_modifiers",
                                             " $src1_modifiers,"));
  string fsrc2 = !if(!eq(NumSrcArgs, 3), " $src2_modifiers", "");

  string src0 = !if(Src0HasMods, fsrc0, isrc0);
  string src1 = !if(Src1HasMods, fsrc1, isrc1);
  string src2 = !if(Src2HasMods, fsrc2, isrc2);

  string clamp = !if(HasClamp, "$clamp", "");

  string ret = dst#", "#src0#src1#src2#"$op_sel"#clamp;
}

class getAsmDPP <bit HasDst, int NumSrcArgs, bit HasModifiers, ValueType DstVT = i32> {
  string dst = !if(HasDst,
                   !if(!eq(DstVT.Size, 1),
                       "$sdst",
                       "$vdst"),
                    ""); // use $sdst for VOPC
  string src0 = !if(!eq(NumSrcArgs, 1), "$src0_modifiers", "$src0_modifiers,");
  string src1 = !if(!eq(NumSrcArgs, 1), "",
                   !if(!eq(NumSrcArgs, 2), " $src1_modifiers",
                                           " $src1_modifiers,"));
  string args = !if(!eq(HasModifiers, 0),
                     getAsm32<0, NumSrcArgs, DstVT>.ret,
                     ", "#src0#src1);
  string ret = dst#args#" $dpp_ctrl$row_mask$bank_mask$bound_ctrl";
}

class getAsmDPP16 <bit HasDst, int NumSrcArgs, bit HasModifiers, ValueType DstVT = i32> {
  string ret = getAsmDPP<HasDst, NumSrcArgs, HasModifiers, DstVT>.ret#"$fi";
}

class getAsmDPP8 <bit HasDst, int NumSrcArgs, bit HasModifiers, ValueType DstVT = i32> {
  string dst = !if(HasDst,
                   !if(!eq(DstVT.Size, 1),
                       "$sdst",
                       "$vdst"),
                    ""); // use $sdst for VOPC
  string src0 = !if(!eq(NumSrcArgs, 1), "$src0_modifiers", "$src0_modifiers,");
  string src1 = !if(!eq(NumSrcArgs, 1), "",
                   !if(!eq(NumSrcArgs, 2), " $src1_modifiers",
                                           " $src1_modifiers,"));
  string args = !if(!eq(HasModifiers, 0),
                     getAsm32<0, NumSrcArgs, DstVT>.ret,
                     ", "#src0#src1);
  string ret = dst#args#"$dpp8$fi";
}

class getAsmSDWA <bit HasDst, int NumSrcArgs, ValueType DstVT = i32> {
  string dst = !if(HasDst,
                   !if(!eq(DstVT.Size, 1),
                       " vcc", // use vcc token as dst for VOPC instructioins
                       "$vdst"),
                    "");
  string src0 = "$src0_modifiers";
  string src1 = "$src1_modifiers";
  string args = !if(!eq(NumSrcArgs, 0),
                    "",
                    !if(!eq(NumSrcArgs, 1),
                        ", "#src0#"$clamp",
                        ", "#src0#", "#src1#"$clamp"
                     )
                );
  string sdwa = !if(!eq(NumSrcArgs, 0),
                    "",
                    !if(!eq(NumSrcArgs, 1),
                        " $dst_sel $dst_unused $src0_sel",
                        !if(!eq(DstVT.Size, 1),
                            " $src0_sel $src1_sel", // No dst_sel and dst_unused for VOPC
                            " $dst_sel $dst_unused $src0_sel $src1_sel"
                        )
                    )
                );
  string ret = dst#args#sdwa;
}

class getAsmSDWA9 <bit HasDst, bit HasOMod, int NumSrcArgs,
                   ValueType DstVT = i32> {
  string dst = !if(HasDst,
                   !if(!eq(DstVT.Size, 1),
                       "$sdst", // VOPC
                       "$vdst"), // VOP1/2
                    "");
  string src0 = "$src0_modifiers";
  string src1 = "$src1_modifiers";
  string out_mods = !if(!eq(HasOMod, 0), "$clamp", "$clamp$omod");
  string args = !if(!eq(NumSrcArgs, 0), "",
                    !if(!eq(NumSrcArgs, 1),
                        ", "#src0,
                        ", "#src0#", "#src1
                     )
                );
  string sdwa = !if(!eq(NumSrcArgs, 0), "",
                    !if(!eq(NumSrcArgs, 1),
                        out_mods#" $dst_sel $dst_unused $src0_sel",
                        !if(!eq(DstVT.Size, 1),
                            " $src0_sel $src1_sel", // No dst_sel, dst_unused and output modifiers for VOPC
                            out_mods#" $dst_sel $dst_unused $src0_sel $src1_sel"
                        )
                    )
                );
  string ret = dst#args#sdwa;
}


// Function that checks if instruction supports DPP and SDWA
class getHasExt <int NumSrcArgs, ValueType DstVT = i32, ValueType Src0VT = i32,
                 ValueType Src1VT = i32> {
  bit ret = !if(!eq(NumSrcArgs, 3),
                0, // NumSrcArgs == 3 - No DPP or SDWA for VOP3
                !if(!eq(DstVT.Size, 64),
                    0, // 64-bit dst - No DPP or SDWA for 64-bit operands
                    !if(!eq(Src0VT.Size, 64),
                        0, // 64-bit src0
                        !if(!eq(Src1VT.Size, 64),
                            0, // 64-bit src2
                            1
                        )
                    )
                )
            );
}

class getHasDPP <int NumSrcArgs, ValueType DstVT = i32, ValueType Src0VT = i32,
                 ValueType Src1VT = i32> {
  bit ret = !if(!eq(NumSrcArgs, 0), 0,
                getHasExt<NumSrcArgs, DstVT, Src0VT, Src1VT>.ret);
}

class BitOr<bit a, bit b> {
  bit ret = !if(a, 1, !if(b, 1, 0));
}

class BitAnd<bit a, bit b> {
  bit ret = !if(a, !if(b, 1, 0), 0);
}

def PatGenMode {
  int NoPattern = 0;
  int Pattern   = 1;
}

class VOPProfile <list<ValueType> _ArgVT, bit _EnableF32SrcMods = 0,
                  bit _EnableClamp = 0> {

  field list<ValueType> ArgVT = _ArgVT;
  field bit EnableF32SrcMods = _EnableF32SrcMods;
  field bit EnableClamp = _EnableClamp;

  field ValueType DstVT = ArgVT[0];
  field ValueType Src0VT = ArgVT[1];
  field ValueType Src1VT = ArgVT[2];
  field ValueType Src2VT = ArgVT[3];
  field RegisterOperand DstRC = getVALUDstForVT<DstVT>.ret;
  field RegisterOperand DstRCDPP = getVALUDstForVT<DstVT>.ret;
  field RegisterOperand DstRCSDWA = getSDWADstForVT<DstVT>.ret;
  field RegisterOperand Src0RC32 = getVOPSrc0ForVT<Src0VT>.ret;
  field RegisterClass Src1RC32 = getVregSrcForVT<Src1VT>.ret;
  field RegisterOperand Src0RC64 = getVOP3SrcForVT<Src0VT>.ret;
  field RegisterOperand Src1RC64 = getVOP3SrcForVT<Src1VT>.ret;
  field RegisterOperand Src2RC64 = getVOP3SrcForVT<Src2VT>.ret;
  field RegisterClass Src0DPP = getVregSrcForVT<Src0VT>.ret;
  field RegisterClass Src1DPP = getVregSrcForVT<Src1VT>.ret;
  field RegisterOperand Src0SDWA = getSDWASrcForVT<Src0VT>.ret;
  field RegisterOperand Src1SDWA = getSDWASrcForVT<Src0VT>.ret;
  field Operand Src0Mod = getSrcMod<Src0VT, EnableF32SrcMods>.ret;
  field Operand Src1Mod = getSrcMod<Src1VT, EnableF32SrcMods>.ret;
  field Operand Src2Mod = getSrcMod<Src2VT, EnableF32SrcMods>.ret;
  field Operand Src0ModDPP = getSrcModExt<Src0VT>.ret;
  field Operand Src1ModDPP = getSrcModExt<Src1VT>.ret;
  field Operand Src0ModSDWA = getSrcModSDWA<Src0VT>.ret;
  field Operand Src1ModSDWA = getSrcModSDWA<Src1VT>.ret;


  field bit HasDst = !if(!eq(DstVT.Value, untyped.Value), 0, 1);
  field bit HasDst32 = HasDst;
  field bit EmitDst = HasDst; // force dst encoding, see v_movreld_b32 special case
  field int NumSrcArgs = getNumSrcArgs<Src0VT, Src1VT, Src2VT>.ret;
  field bit HasSrc0 = !if(!eq(Src0VT.Value, untyped.Value), 0, 1);
  field bit HasSrc1 = !if(!eq(Src1VT.Value, untyped.Value), 0, 1);
  field bit HasSrc2 = !if(!eq(Src2VT.Value, untyped.Value), 0, 1);

  // TODO: Modifiers logic is somewhat adhoc here, to be refined later
  // HasModifiers affects the normal and DPP encodings. We take note of EnableF32SrcMods, which
  // enables modifiers for i32 type.
  field bit HasModifiers = BitOr<isModifierType<Src0VT>.ret, EnableF32SrcMods>.ret;

  // HasSrc*FloatMods affects the SDWA encoding. We ignore EnableF32SrcMods.
  field bit HasSrc0FloatMods = isFloatType<Src0VT>.ret;
  field bit HasSrc1FloatMods = isFloatType<Src1VT>.ret;
  field bit HasSrc2FloatMods = isFloatType<Src2VT>.ret;

  // HasSrc*IntMods affects the SDWA encoding. We ignore EnableF32SrcMods.
  field bit HasSrc0IntMods = isIntType<Src0VT>.ret;
  field bit HasSrc1IntMods = isIntType<Src1VT>.ret;
  field bit HasSrc2IntMods = isIntType<Src2VT>.ret;

  field bit HasSrc0Mods = HasModifiers;
  field bit HasSrc1Mods = !if(HasModifiers, BitOr<HasSrc1FloatMods, HasSrc1IntMods>.ret, 0);
  field bit HasSrc2Mods = !if(HasModifiers, BitOr<HasSrc2FloatMods, HasSrc2IntMods>.ret, 0);

  field bit HasClamp = BitOr<isModifierType<Src0VT>.ret, EnableClamp>.ret;
  field bit HasSDWAClamp = EmitDst;
  field bit HasFPClamp = BitAnd<isFloatType<DstVT>.ret, HasClamp>.ret;
  field bit HasIntClamp = !if(isFloatType<DstVT>.ret, 0, HasClamp);
  field bit HasClampLo = HasClamp;
  field bit HasClampHi = BitAnd<isPackedType<DstVT>.ret, HasClamp>.ret;
  field bit HasHigh = 0;

  field bit IsPacked = isPackedType<Src0VT>.ret;
  field bit HasOpSel = IsPacked;
  field bit HasOMod = !if(HasOpSel, 0, isFloatType<DstVT>.ret);
  field bit HasSDWAOMod = isFloatType<DstVT>.ret;

  field bit HasExt = getHasExt<NumSrcArgs, DstVT, Src0VT, Src1VT>.ret;
  field bit HasExtDPP = getHasDPP<NumSrcArgs, DstVT, Src0VT, Src1VT>.ret;
  field bit HasExtSDWA = HasExt;
  field bit HasExtSDWA9 = HasExt;
  field int NeedPatGen = PatGenMode.NoPattern;

  field bit IsMAI = 0;
  field bit IsDOT = 0;

  field Operand Src0PackedMod = !if(HasSrc0FloatMods, PackedF16InputMods, PackedI16InputMods);
  field Operand Src1PackedMod = !if(HasSrc1FloatMods, PackedF16InputMods, PackedI16InputMods);
  field Operand Src2PackedMod = !if(HasSrc2FloatMods, PackedF16InputMods, PackedI16InputMods);

  field dag Outs = !if(HasDst,(outs DstRC:$vdst),(outs));

  // VOP3b instructions are a special case with a second explicit
  // output. This is manually overridden for them.
  field dag Outs32 = Outs;
  field dag Outs64 = Outs;
  field dag OutsDPP = getOutsExt<HasDst, DstVT, DstRCDPP>.ret;
  field dag OutsDPP8 = getOutsExt<HasDst, DstVT, DstRCDPP>.ret;
  field dag OutsSDWA = getOutsSDWA<HasDst, DstVT, DstRCSDWA>.ret;

  field dag Ins32 = getIns32<Src0RC32, Src1RC32, NumSrcArgs>.ret;
  field dag Ins64 = getIns64<Src0RC64, Src1RC64, Src2RC64, NumSrcArgs,
                             HasIntClamp, HasModifiers, HasSrc2Mods,
                             HasOMod, Src0Mod, Src1Mod, Src2Mod>.ret;
  field dag InsVOP3P = getInsVOP3P<Src0RC64, Src1RC64, Src2RC64,
                                   NumSrcArgs, HasClamp,
                                   Src0PackedMod, Src1PackedMod, Src2PackedMod>.ret;
  field dag InsVOP3OpSel = getInsVOP3OpSel<Src0RC64, Src1RC64, Src2RC64,
                                           NumSrcArgs,
                                           HasClamp,
                                           getOpSelMod<Src0VT>.ret,
                                           getOpSelMod<Src1VT>.ret,
                                           getOpSelMod<Src2VT>.ret>.ret;
  field dag InsDPP = !if(HasExtDPP,
                         getInsDPP<DstRCDPP, Src0DPP, Src1DPP, NumSrcArgs,
                                   HasModifiers, Src0ModDPP, Src1ModDPP>.ret,
                         (ins));
  field dag InsDPP16 = getInsDPP16<DstRCDPP, Src0DPP, Src1DPP, NumSrcArgs,
                                   HasModifiers, Src0ModDPP, Src1ModDPP>.ret;
  field dag InsDPP8 = getInsDPP8<DstRCDPP, Src0DPP, Src1DPP, NumSrcArgs, 0,
                                 Src0ModDPP, Src1ModDPP>.ret;
  field dag InsSDWA = getInsSDWA<Src0SDWA, Src1SDWA, NumSrcArgs,
                                 HasSDWAOMod, Src0ModSDWA, Src1ModSDWA,
                                 DstVT>.ret;


  field string Asm32 = getAsm32<HasDst, NumSrcArgs, DstVT>.ret;
  field string Asm64 = getAsm64<HasDst, NumSrcArgs, HasIntClamp, HasModifiers, HasOMod, DstVT>.ret;
  field string AsmVOP3P = getAsmVOP3P<HasDst, NumSrcArgs, HasModifiers, HasClamp, DstVT>.ret;
  field string AsmVOP3OpSel = getAsmVOP3OpSel<NumSrcArgs,
                                              HasClamp,
                                              HasSrc0FloatMods,
                                              HasSrc1FloatMods,
                                              HasSrc2FloatMods>.ret;
  field string AsmDPP = !if(HasExtDPP,
                            getAsmDPP<HasDst, NumSrcArgs, HasModifiers, DstVT>.ret, "");
  field string AsmDPP16 = getAsmDPP16<HasDst, NumSrcArgs, HasModifiers, DstVT>.ret;
  field string AsmDPP8 = getAsmDPP8<HasDst, NumSrcArgs, 0, DstVT>.ret;
  field string AsmSDWA = getAsmSDWA<HasDst, NumSrcArgs, DstVT>.ret;
  field string AsmSDWA9 = getAsmSDWA9<HasDst, HasSDWAOMod, NumSrcArgs, DstVT>.ret;

  field string TieRegDPP = "$old";
}

class VOP_NO_EXT <VOPProfile p> : VOPProfile <p.ArgVT> {
  let HasExt = 0;
  let HasExtDPP = 0;
  let HasExtSDWA = 0;
  let HasExtSDWA9 = 0;
}

class VOP_PAT_GEN <VOPProfile p, int mode=PatGenMode.Pattern> : VOPProfile <p.ArgVT> {
  let NeedPatGen = mode;
}

def VOP_F16_F16 : VOPProfile <[f16, f16, untyped, untyped]>;
def VOP_F16_I16 : VOPProfile <[f16, i16, untyped, untyped]>;
def VOP_I16_F16 : VOPProfile <[i16, f16, untyped, untyped]>;

def VOP_F16_F16_F16 : VOPProfile <[f16, f16, f16, untyped]>;
def VOP_F16_F16_I16 : VOPProfile <[f16, f16, i16, untyped]>;
def VOP_F16_F16_I32 : VOPProfile <[f16, f16, i32, untyped]>;
def VOP_I16_I16_I16 : VOPProfile <[i16, i16, i16, untyped]>;

def VOP_I16_I16_I16_I16 : VOPProfile <[i16, i16, i16, i16, untyped]>;
def VOP_F16_F16_F16_F16 : VOPProfile <[f16, f16, f16, f16, untyped]>;

def VOP_I32_I16_I16_I32 : VOPProfile <[i32, i16, i16, i32, untyped]>;

def VOP_V2F16_V2F16_V2F16 : VOPProfile <[v2f16, v2f16, v2f16, untyped]>;
def VOP_V2I16_V2I16_V2I16 : VOPProfile <[v2i16, v2i16, v2i16, untyped]>;
def VOP_B32_F16_F16 : VOPProfile <[i32, f16, f16, untyped]>;

def VOP_V2F16_V2F16_V2F16_V2F16 : VOPProfile <[v2f16, v2f16, v2f16, v2f16]>;
def VOP_V2I16_V2I16_V2I16_V2I16 : VOPProfile <[v2i16, v2i16, v2i16, v2i16]>;
def VOP_V2I16_F32_F32 : VOPProfile <[v2i16, f32, f32, untyped]>;
def VOP_V2I16_I32_I32 : VOPProfile <[v2i16, i32, i32, untyped]>;

def VOP_F32_V2F16_V2F16_V2F16 : VOPProfile <[f32, v2f16, v2f16, v2f16]>;

def VOP_NONE : VOPProfile <[untyped, untyped, untyped, untyped]>;

def VOP_F32_F32 : VOPProfile <[f32, f32, untyped, untyped]>;
def VOP_F32_F64 : VOPProfile <[f32, f64, untyped, untyped]>;
def VOP_F32_I32 : VOPProfile <[f32, i32, untyped, untyped]>;
def VOP_F64_F32 : VOPProfile <[f64, f32, untyped, untyped]>;
def VOP_F64_F64 : VOPProfile <[f64, f64, untyped, untyped]>;
def VOP_F64_I32 : VOPProfile <[f64, i32, untyped, untyped]>;
def VOP_I32_F32 : VOPProfile <[i32, f32, untyped, untyped]>;
def VOP_I32_F64 : VOPProfile <[i32, f64, untyped, untyped]>;
def VOP_I32_I32 : VOPProfile <[i32, i32, untyped, untyped]>;
def VOP_F16_F32 : VOPProfile <[f16, f32, untyped, untyped]>;
def VOP_F32_F16 : VOPProfile <[f32, f16, untyped, untyped]>;

def VOP_F32_F32_F16 : VOPProfile <[f32, f32, f16, untyped]>;
def VOP_F32_F32_F32 : VOPProfile <[f32, f32, f32, untyped]>;
def VOP_F32_F32_I32 : VOPProfile <[f32, f32, i32, untyped]>;
def VOP_F64_F64_F64 : VOPProfile <[f64, f64, f64, untyped]>;
def VOP_F64_F64_I32 : VOPProfile <[f64, f64, i32, untyped]>;
def VOP_I32_F32_F32 : VOPProfile <[i32, f32, f32, untyped]>;
def VOP_I32_F32_I32 : VOPProfile <[i32, f32, i32, untyped]>;
def VOP_I32_I32_I32 : VOPProfile <[i32, i32, i32, untyped]>;
def VOP_I32_I32_I32_ARITH : VOPProfile <[i32, i32, i32, untyped], 0, /*EnableClamp=*/1>;
def VOP_V2F16_F32_F32 : VOPProfile <[v2f16, f32, f32, untyped]>;
def VOP_F32_F16_F16_F16 : VOPProfile <[f32, f16, f16, f16]>;

def VOP_I64_I64_I32 : VOPProfile <[i64, i64, i32, untyped]>;
def VOP_I64_I32_I64 : VOPProfile <[i64, i32, i64, untyped]>;
def VOP_I64_I64_I64 : VOPProfile <[i64, i64, i64, untyped]>;

def VOP_F16_F32_F16_F32 : VOPProfile <[f16, f32, f16, f32]>;
def VOP_F32_F32_F16_F16 : VOPProfile <[f32, f32, f16, f16]>;
def VOP_F32_F32_F32_F32 : VOPProfile <[f32, f32, f32, f32]>;
def VOP_F64_F64_F64_F64 : VOPProfile <[f64, f64, f64, f64]>;
def VOP_I32_I32_I32_I32 : VOPProfile <[i32, i32, i32, i32]>;
def VOP_I64_I32_I32_I64 : VOPProfile <[i64, i32, i32, i64]>;
def VOP_I32_F32_I32_I32 : VOPProfile <[i32, f32, i32, i32]>;
def VOP_I64_I64_I32_I64 : VOPProfile <[i64, i64, i32, i64]>;
def VOP_V4I32_I64_I32_V4I32 : VOPProfile <[v4i32, i64, i32, v4i32]>;

def VOP_F32_V2F16_V2F16_F32 : VOPProfile <[f32, v2f16, v2f16, f32]>;
def VOP_I32_V2I16_V2I16_I32 : VOPProfile <[i32, v2i16, v2i16, i32]>;

def VOP_V4F32_F32_F32_V4F32       : VOPProfile <[v4f32,  f32,   f32,   v4f32]>;
def VOP_V16F32_F32_F32_V16F32     : VOPProfile <[v16f32, f32,   f32,   v16f32]>;
def VOP_V32F32_F32_F32_V32F32     : VOPProfile <[v32f32, f32,   f32,   v32f32]>;
def VOP_V4F32_V4F16_V4F16_V4F32   : VOPProfile <[v4f32,  v4f16, v4f16, v4f32]>;
def VOP_V16F32_V4F16_V4F16_V16F32 : VOPProfile <[v16f32, v4f16, v4f16, v16f32]>;
def VOP_V32F32_V4F16_V4F16_V32F32 : VOPProfile <[v32f32, v4f16, v4f16, v32f32]>;
def VOP_V4F32_V2I16_V2I16_V4F32   : VOPProfile <[v4f32,  v2i16, v2i16, v4f32]>;
def VOP_V16F32_V2I16_V2I16_V16F32 : VOPProfile <[v16f32, v2i16, v2i16, v16f32]>;
def VOP_V32F32_V2I16_V2I16_V32F32 : VOPProfile <[v32f32, v2i16, v2i16, v32f32]>;
def VOP_V4I32_I32_I32_V4I32       : VOPProfile <[v4i32,  i32,   i32,   v4i32]>;
def VOP_V16I32_I32_I32_V16I32     : VOPProfile <[v16i32, i32,   i32,   v16i32]>;
def VOP_V32I32_I32_I32_V32I32     : VOPProfile <[v32i32, i32,   i32,   v32i32]>;

class Commutable_REV <string revOp, bit isOrig> {
  string RevOp = revOp;
  bit IsOrig = isOrig;
}

class AtomicNoRet <string noRetOp, bit isRet> {
  string NoRetOp = noRetOp;
  bit IsRet = isRet;
}

//===----------------------------------------------------------------------===//
// Interpolation opcodes
//===----------------------------------------------------------------------===//

class VINTRPDstOperand <RegisterClass rc> : RegisterOperand <rc, "printVINTRPDst">;

class VINTRP_Pseudo <string opName, dag outs, dag ins, list<dag> pattern> :
  VINTRPCommon <outs, ins, "", pattern>,
  SIMCInstr<opName, SIEncodingFamily.NONE> {
  let isPseudo = 1;
  let isCodeGenOnly = 1;
}

// FIXME-GFX10: WIP.
class VINTRP_Real_si <bits <2> op, string opName, dag outs, dag ins,
                      string asm, int encodingFamily> :
  VINTRPCommon <outs, ins, asm, []>,
  VINTRPe <op>,
  SIMCInstr<opName, encodingFamily> {
  let DisableDecoder = DisableSIDecoder;
}

class VINTRP_Real_vi <bits <2> op, string opName, dag outs, dag ins,
                      string asm> :
  VINTRPCommon <outs, ins, asm, []>,
  VINTRPe_vi <op>,
  SIMCInstr<opName, SIEncodingFamily.VI> {
  let AssemblerPredicate = VIAssemblerPredicate;
  let DecoderNamespace = "GFX8";
  let DisableDecoder = DisableVIDecoder;
}

// FIXME-GFX10: WIP.
multiclass VINTRP_m <bits <2> op, dag outs, dag ins, string asm,
                     list<dag> pattern = []> {
  def "" : VINTRP_Pseudo <NAME, outs, ins, pattern>;

  let AssemblerPredicate = isGFX6GFX7, DecoderNamespace = "GFX6GFX7" in {
    def _si : VINTRP_Real_si <op, NAME, outs, ins, asm, SIEncodingFamily.SI>;
  } // End AssemblerPredicate = isGFX6GFX7, DecoderNamespace = "GFX6GFX7"

  def _vi : VINTRP_Real_vi <op, NAME, outs, ins, asm>;

  let AssemblerPredicate = isGFX10Plus, DecoderNamespace = "GFX10" in {
    def _gfx10 : VINTRP_Real_si<op, NAME, outs, ins, asm, SIEncodingFamily.GFX10>;
  } // End AssemblerPredicate = isGFX10Plus, DecoderNamespace = "GFX10"
}
//===----------------------------------------------------------------------===//
// Vector instruction mappings
//===----------------------------------------------------------------------===//

// Maps an opcode in e32 form to its e64 equivalent
def getVOPe64 : InstrMapping {
  let FilterClass = "VOP";
  let RowFields = ["OpName"];
  let ColFields = ["Size", "VOP3"];
  let KeyCol = ["4", "0"];
  let ValueCols = [["8", "1"]];
}

// Maps an opcode in e64 form to its e32 equivalent
def getVOPe32 : InstrMapping {
  let FilterClass = "VOP";
  let RowFields = ["OpName"];
  let ColFields = ["Size", "VOP3"];
  let KeyCol = ["8", "1"];
  let ValueCols = [["4", "0"]];
}

// Maps ordinary instructions to their SDWA counterparts
def getSDWAOp : InstrMapping {
  let FilterClass = "VOP";
  let RowFields = ["OpName"];
  let ColFields = ["AsmVariantName"];
  let KeyCol = ["Default"];
  let ValueCols = [["SDWA"]];
}

// Maps SDWA instructions to their ordinary counterparts
def getBasicFromSDWAOp : InstrMapping {
  let FilterClass = "VOP";
  let RowFields = ["OpName"];
  let ColFields = ["AsmVariantName"];
  let KeyCol = ["SDWA"];
  let ValueCols = [["Default"]];
}

// Maps ordinary instructions to their DPP counterparts
def getDPPOp32 : InstrMapping {
  let FilterClass = "VOP";
  let RowFields = ["OpName"];
  let ColFields = ["AsmVariantName"];
  let KeyCol = ["Default"];
  let ValueCols = [["DPP"]];
}

// Maps an commuted opcode to its original version
def getCommuteOrig : InstrMapping {
  let FilterClass = "Commutable_REV";
  let RowFields = ["RevOp"];
  let ColFields = ["IsOrig"];
  let KeyCol = ["0"];
  let ValueCols = [["1"]];
}

// Maps an original opcode to its commuted version
def getCommuteRev : InstrMapping {
  let FilterClass = "Commutable_REV";
  let RowFields = ["RevOp"];
  let ColFields = ["IsOrig"];
  let KeyCol = ["1"];
  let ValueCols = [["0"]];
}

def getMCOpcodeGen : InstrMapping {
  let FilterClass = "SIMCInstr";
  let RowFields = ["PseudoInstr"];
  let ColFields = ["Subtarget"];
  let KeyCol = [!cast<string>(SIEncodingFamily.NONE)];
  let ValueCols = [[!cast<string>(SIEncodingFamily.SI)],
                   [!cast<string>(SIEncodingFamily.VI)],
                   [!cast<string>(SIEncodingFamily.SDWA)],
                   [!cast<string>(SIEncodingFamily.SDWA9)],
                   // GFX80 encoding is added to work around a multiple matching
                   // issue for buffer instructions with unpacked d16 data. This
                   // does not actually change the encoding, and thus may be
                   // removed later.
                   [!cast<string>(SIEncodingFamily.GFX80)],
                   [!cast<string>(SIEncodingFamily.GFX9)],
                   [!cast<string>(SIEncodingFamily.GFX10)],
                   [!cast<string>(SIEncodingFamily.SDWA10)]];
}

// Get equivalent SOPK instruction.
def getSOPKOp : InstrMapping {
  let FilterClass = "SOPKInstTable";
  let RowFields = ["BaseCmpOp"];
  let ColFields = ["IsSOPK"];
  let KeyCol = ["0"];
  let ValueCols = [["1"]];
}

def getAddr64Inst : InstrMapping {
  let FilterClass = "MUBUFAddr64Table";
  let RowFields = ["OpName"];
  let ColFields = ["IsAddr64"];
  let KeyCol = ["0"];
  let ValueCols = [["1"]];
}

def getIfAddr64Inst : InstrMapping {
  let FilterClass = "MUBUFAddr64Table";
  let RowFields = ["OpName"];
  let ColFields = ["IsAddr64"];
  let KeyCol = ["1"];
  let ValueCols = [["1"]];
}

def getMUBUFNoLdsInst : InstrMapping {
  let FilterClass = "MUBUFLdsTable";
  let RowFields = ["OpName"];
  let ColFields = ["IsLds"];
  let KeyCol = ["1"];
  let ValueCols = [["0"]];
}

// Maps an atomic opcode to its version with a return value.
def getAtomicRetOp : InstrMapping {
  let FilterClass = "AtomicNoRet";
  let RowFields = ["NoRetOp"];
  let ColFields = ["IsRet"];
  let KeyCol = ["0"];
  let ValueCols = [["1"]];
}

// Maps an atomic opcode to its returnless version.
def getAtomicNoRetOp : InstrMapping {
  let FilterClass = "AtomicNoRet";
  let RowFields = ["NoRetOp"];
  let ColFields = ["IsRet"];
  let KeyCol = ["1"];
  let ValueCols = [["0"]];
}

// Maps a GLOBAL to its SADDR form.
def getGlobalSaddrOp : InstrMapping {
  let FilterClass = "GlobalSaddrTable";
  let RowFields = ["SaddrOp"];
  let ColFields = ["IsSaddr"];
  let KeyCol = ["0"];
  let ValueCols = [["1"]];
}

// Maps a v_cmpx opcode with sdst to opcode without sdst.
def getVCMPXNoSDstOp : InstrMapping {
  let FilterClass = "VCMPXNoSDstTable";
  let RowFields = ["NoSDstOp"];
  let ColFields = ["HasSDst"];
  let KeyCol = ["1"];
  let ValueCols = [["0"]];
}

// Maps a SOPP to a SOPP with S_NOP
def getSOPPWithRelaxation : InstrMapping {
  let FilterClass = "Base_SOPP";
  let RowFields = ["AsmString"];
  let ColFields = ["Size"];
  let KeyCol = ["4"];
  let ValueCols = [["8"]];
}

include "SIInstructions.td"

include "DSInstructions.td"
include "MIMGInstructions.td"