summaryrefslogtreecommitdiff
path: root/lib/Target/ARM64/ARM64InstrInfo.td
blob: 268ba4e44db2f16c99e339261d66f0715266b112 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
//===- ARM64InstrInfo.td - Describe the ARM64 Instructions -*- tablegen -*-===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// ARM64 Instruction definitions.
//
//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//
// ARM Instruction Predicate Definitions.
//
def HasFPARMv8       : Predicate<"Subtarget->hasFPARMv8()">,
                               AssemblerPredicate<"FeatureFPARMv8", "fp-armv8">;
def HasNEON          : Predicate<"Subtarget->hasNEON()">,
                                 AssemblerPredicate<"FeatureNEON", "neon">;
def HasCrypto        : Predicate<"Subtarget->hasCrypto()">,
                                 AssemblerPredicate<"FeatureCrypto", "crypto">;
def HasCRC           : Predicate<"Subtarget->hasCRC()">,
                                 AssemblerPredicate<"FeatureCRC", "crc">;
def IsLE             : Predicate<"Subtarget->isLittleEndian()">;
def IsBE             : Predicate<"!Subtarget->isLittleEndian()">;

//===----------------------------------------------------------------------===//
// ARM64-specific DAG Nodes.
//

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

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

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

def SDT_ARM64Brcond  : SDTypeProfile<0, 3,
                                     [SDTCisVT<0, OtherVT>, SDTCisVT<1, i32>,
                                      SDTCisVT<2, i32>]>;
def SDT_ARM64cbz : SDTypeProfile<0, 2, [SDTCisInt<0>, SDTCisVT<1, OtherVT>]>;
def SDT_ARM64tbz : SDTypeProfile<0, 3, [SDTCisVT<0, i64>, SDTCisVT<1, i64>,
                                        SDTCisVT<2, OtherVT>]>;


def SDT_ARM64CSel  : SDTypeProfile<1, 4,
                                   [SDTCisSameAs<0, 1>,
                                    SDTCisSameAs<0, 2>,
                                    SDTCisInt<3>,
                                    SDTCisVT<4, i32>]>;
def SDT_ARM64FCmp   : SDTypeProfile<0, 2,
                                   [SDTCisFP<0>,
                                    SDTCisSameAs<0, 1>]>;
def SDT_ARM64Dup   : SDTypeProfile<1, 1, [SDTCisVec<0>]>;
def SDT_ARM64DupLane   : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisInt<2>]>;
def SDT_ARM64Zip   : SDTypeProfile<1, 2, [SDTCisVec<0>,
                                          SDTCisSameAs<0, 1>,
                                          SDTCisSameAs<0, 2>]>;
def SDT_ARM64MOVIedit : SDTypeProfile<1, 1, [SDTCisInt<1>]>;
def SDT_ARM64MOVIshift : SDTypeProfile<1, 2, [SDTCisInt<1>, SDTCisInt<2>]>;
def SDT_ARM64vecimm : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                           SDTCisInt<2>, SDTCisInt<3>]>;
def SDT_ARM64UnaryVec: SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisSameAs<0,1>]>;
def SDT_ARM64ExtVec: SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                          SDTCisSameAs<0,2>, SDTCisInt<3>]>;
def SDT_ARM64vshift : SDTypeProfile<1, 2, [SDTCisSameAs<0,1>, SDTCisInt<2>]>;

def SDT_ARM64unvec : SDTypeProfile<1, 1, [SDTCisVec<0>, SDTCisSameAs<0,1>]>;
def SDT_ARM64fcmpz : SDTypeProfile<1, 1, []>;
def SDT_ARM64fcmp  : SDTypeProfile<1, 2, [SDTCisSameAs<1,2>]>;
def SDT_ARM64binvec : SDTypeProfile<1, 2, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                           SDTCisSameAs<0,2>]>;
def SDT_ARM64trivec : SDTypeProfile<1, 3, [SDTCisVec<0>, SDTCisSameAs<0,1>,
                                           SDTCisSameAs<0,2>,
                                           SDTCisSameAs<0,3>]>;
def SDT_ARM64TCRET : SDTypeProfile<0, 2, [SDTCisPtrTy<0>]>;
def SDT_ARM64PREFETCH : SDTypeProfile<0, 2, [SDTCisVT<0, i32>, SDTCisPtrTy<1>]>;

def SDT_ARM64ITOF  : SDTypeProfile<1, 1, [SDTCisFP<0>, SDTCisSameAs<0,1>]>;

def SDT_ARM64TLSDescCall : SDTypeProfile<0, -2, [SDTCisPtrTy<0>,
                                                 SDTCisPtrTy<1>]>;
def SDT_ARM64WrapperLarge : SDTypeProfile<1, 4,
                                        [SDTCisVT<0, i64>, SDTCisVT<1, i32>,
                                         SDTCisSameAs<1, 2>, SDTCisSameAs<1, 3>,
                                         SDTCisSameAs<1, 4>]>;


// Node definitions.
def ARM64adrp          : SDNode<"ARM64ISD::ADRP", SDTIntUnaryOp, []>;
def ARM64addlow        : SDNode<"ARM64ISD::ADDlow", SDTIntBinOp, []>;
def ARM64LOADgot       : SDNode<"ARM64ISD::LOADgot", SDTIntUnaryOp>;
def ARM64callseq_start : SDNode<"ISD::CALLSEQ_START",
                                SDCallSeqStart<[ SDTCisVT<0, i32> ]>,
                                [SDNPHasChain, SDNPOutGlue]>;
def ARM64callseq_end   : SDNode<"ISD::CALLSEQ_END",
                                SDCallSeqEnd<[ SDTCisVT<0, i32>,
                                               SDTCisVT<1, i32> ]>,
                                [SDNPHasChain, SDNPOptInGlue, SDNPOutGlue]>;
def ARM64call          : SDNode<"ARM64ISD::CALL",
                                SDTypeProfile<0, -1, [SDTCisPtrTy<0>]>,
                                [SDNPHasChain, SDNPOptInGlue, SDNPOutGlue,
                                 SDNPVariadic]>;
def ARM64brcond        : SDNode<"ARM64ISD::BRCOND", SDT_ARM64Brcond,
                                [SDNPHasChain]>;
def ARM64cbz           : SDNode<"ARM64ISD::CBZ", SDT_ARM64cbz,
                                [SDNPHasChain]>;
def ARM64cbnz           : SDNode<"ARM64ISD::CBNZ", SDT_ARM64cbz,
                                [SDNPHasChain]>;
def ARM64tbz           : SDNode<"ARM64ISD::TBZ", SDT_ARM64tbz,
                                [SDNPHasChain]>;
def ARM64tbnz           : SDNode<"ARM64ISD::TBNZ", SDT_ARM64tbz,
                                [SDNPHasChain]>;


def ARM64csel          : SDNode<"ARM64ISD::CSEL", SDT_ARM64CSel>;
def ARM64csinv         : SDNode<"ARM64ISD::CSINV", SDT_ARM64CSel>;
def ARM64csneg         : SDNode<"ARM64ISD::CSNEG", SDT_ARM64CSel>;
def ARM64csinc         : SDNode<"ARM64ISD::CSINC", SDT_ARM64CSel>;
def ARM64retflag       : SDNode<"ARM64ISD::RET_FLAG", SDTNone,
                                [SDNPHasChain, SDNPOptInGlue, SDNPVariadic]>;
def ARM64adc       : SDNode<"ARM64ISD::ADC",  SDTBinaryArithWithFlagsIn >;
def ARM64sbc       : SDNode<"ARM64ISD::SBC",  SDTBinaryArithWithFlagsIn>;
def ARM64add_flag  : SDNode<"ARM64ISD::ADDS",  SDTBinaryArithWithFlagsOut,
                            [SDNPCommutative]>;
def ARM64sub_flag  : SDNode<"ARM64ISD::SUBS",  SDTBinaryArithWithFlagsOut>;
def ARM64and_flag  : SDNode<"ARM64ISD::ANDS",  SDTBinaryArithWithFlagsOut,
                            [SDNPCommutative]>;
def ARM64adc_flag  : SDNode<"ARM64ISD::ADCS",  SDTBinaryArithWithFlagsInOut>;
def ARM64sbc_flag  : SDNode<"ARM64ISD::SBCS",  SDTBinaryArithWithFlagsInOut>;

def ARM64threadpointer : SDNode<"ARM64ISD::THREAD_POINTER", SDTPtrLeaf>;

def ARM64fcmp      : SDNode<"ARM64ISD::FCMP", SDT_ARM64FCmp>;

def ARM64fmax      : SDNode<"ARM64ISD::FMAX", SDTFPBinOp>;
def ARM64fmin      : SDNode<"ARM64ISD::FMIN", SDTFPBinOp>;

def ARM64dup       : SDNode<"ARM64ISD::DUP", SDT_ARM64Dup>;
def ARM64duplane8  : SDNode<"ARM64ISD::DUPLANE8", SDT_ARM64DupLane>;
def ARM64duplane16 : SDNode<"ARM64ISD::DUPLANE16", SDT_ARM64DupLane>;
def ARM64duplane32 : SDNode<"ARM64ISD::DUPLANE32", SDT_ARM64DupLane>;
def ARM64duplane64 : SDNode<"ARM64ISD::DUPLANE64", SDT_ARM64DupLane>;

def ARM64zip1      : SDNode<"ARM64ISD::ZIP1", SDT_ARM64Zip>;
def ARM64zip2      : SDNode<"ARM64ISD::ZIP2", SDT_ARM64Zip>;
def ARM64uzp1      : SDNode<"ARM64ISD::UZP1", SDT_ARM64Zip>;
def ARM64uzp2      : SDNode<"ARM64ISD::UZP2", SDT_ARM64Zip>;
def ARM64trn1      : SDNode<"ARM64ISD::TRN1", SDT_ARM64Zip>;
def ARM64trn2      : SDNode<"ARM64ISD::TRN2", SDT_ARM64Zip>;

def ARM64movi_edit : SDNode<"ARM64ISD::MOVIedit", SDT_ARM64MOVIedit>;
def ARM64movi_shift : SDNode<"ARM64ISD::MOVIshift", SDT_ARM64MOVIshift>;
def ARM64movi_msl : SDNode<"ARM64ISD::MOVImsl", SDT_ARM64MOVIshift>;
def ARM64mvni_shift : SDNode<"ARM64ISD::MVNIshift", SDT_ARM64MOVIshift>;
def ARM64mvni_msl : SDNode<"ARM64ISD::MVNImsl", SDT_ARM64MOVIshift>;
def ARM64movi : SDNode<"ARM64ISD::MOVI", SDT_ARM64MOVIedit>;
def ARM64fmov : SDNode<"ARM64ISD::FMOV", SDT_ARM64MOVIedit>;

def ARM64rev16 : SDNode<"ARM64ISD::REV16", SDT_ARM64UnaryVec>;
def ARM64rev32 : SDNode<"ARM64ISD::REV32", SDT_ARM64UnaryVec>;
def ARM64rev64 : SDNode<"ARM64ISD::REV64", SDT_ARM64UnaryVec>;
def ARM64ext : SDNode<"ARM64ISD::EXT", SDT_ARM64ExtVec>;

def ARM64vashr : SDNode<"ARM64ISD::VASHR", SDT_ARM64vshift>;
def ARM64vlshr : SDNode<"ARM64ISD::VLSHR", SDT_ARM64vshift>;
def ARM64vshl : SDNode<"ARM64ISD::VSHL", SDT_ARM64vshift>;
def ARM64sqshli : SDNode<"ARM64ISD::SQSHL_I", SDT_ARM64vshift>;
def ARM64uqshli : SDNode<"ARM64ISD::UQSHL_I", SDT_ARM64vshift>;
def ARM64sqshlui : SDNode<"ARM64ISD::SQSHLU_I", SDT_ARM64vshift>;
def ARM64srshri : SDNode<"ARM64ISD::SRSHR_I", SDT_ARM64vshift>;
def ARM64urshri : SDNode<"ARM64ISD::URSHR_I", SDT_ARM64vshift>;

def ARM64not: SDNode<"ARM64ISD::NOT", SDT_ARM64unvec>;
def ARM64bit: SDNode<"ARM64ISD::BIT", SDT_ARM64trivec>;
def ARM64bsl: SDNode<"ARM64ISD::BSL", SDT_ARM64trivec>;

def ARM64cmeq: SDNode<"ARM64ISD::CMEQ", SDT_ARM64binvec>;
def ARM64cmge: SDNode<"ARM64ISD::CMGE", SDT_ARM64binvec>;
def ARM64cmgt: SDNode<"ARM64ISD::CMGT", SDT_ARM64binvec>;
def ARM64cmhi: SDNode<"ARM64ISD::CMHI", SDT_ARM64binvec>;
def ARM64cmhs: SDNode<"ARM64ISD::CMHS", SDT_ARM64binvec>;

def ARM64fcmeq: SDNode<"ARM64ISD::FCMEQ", SDT_ARM64fcmp>;
def ARM64fcmge: SDNode<"ARM64ISD::FCMGE", SDT_ARM64fcmp>;
def ARM64fcmgt: SDNode<"ARM64ISD::FCMGT", SDT_ARM64fcmp>;

def ARM64cmeqz: SDNode<"ARM64ISD::CMEQz", SDT_ARM64unvec>;
def ARM64cmgez: SDNode<"ARM64ISD::CMGEz", SDT_ARM64unvec>;
def ARM64cmgtz: SDNode<"ARM64ISD::CMGTz", SDT_ARM64unvec>;
def ARM64cmlez: SDNode<"ARM64ISD::CMLEz", SDT_ARM64unvec>;
def ARM64cmltz: SDNode<"ARM64ISD::CMLTz", SDT_ARM64unvec>;
def ARM64cmtst : PatFrag<(ops node:$LHS, node:$RHS),
                         (ARM64not (ARM64cmeqz (and node:$LHS, node:$RHS)))>;

def ARM64fcmeqz: SDNode<"ARM64ISD::FCMEQz", SDT_ARM64fcmpz>;
def ARM64fcmgez: SDNode<"ARM64ISD::FCMGEz", SDT_ARM64fcmpz>;
def ARM64fcmgtz: SDNode<"ARM64ISD::FCMGTz", SDT_ARM64fcmpz>;
def ARM64fcmlez: SDNode<"ARM64ISD::FCMLEz", SDT_ARM64fcmpz>;
def ARM64fcmltz: SDNode<"ARM64ISD::FCMLTz", SDT_ARM64fcmpz>;

def ARM64bici: SDNode<"ARM64ISD::BICi", SDT_ARM64vecimm>;
def ARM64orri: SDNode<"ARM64ISD::ORRi", SDT_ARM64vecimm>;

def ARM64neg : SDNode<"ARM64ISD::NEG", SDT_ARM64unvec>;

def ARM64tcret: SDNode<"ARM64ISD::TC_RETURN", SDT_ARM64TCRET,
                  [SDNPHasChain,  SDNPOptInGlue, SDNPVariadic]>;

def ARM64Prefetch        : SDNode<"ARM64ISD::PREFETCH", SDT_ARM64PREFETCH,
                               [SDNPHasChain, SDNPSideEffect]>;

def ARM64sitof: SDNode<"ARM64ISD::SITOF", SDT_ARM64ITOF>;
def ARM64uitof: SDNode<"ARM64ISD::UITOF", SDT_ARM64ITOF>;

def ARM64tlsdesc_call : SDNode<"ARM64ISD::TLSDESC_CALL", SDT_ARM64TLSDescCall,
                               [SDNPInGlue, SDNPOutGlue, SDNPHasChain,
                                SDNPVariadic]>;

def ARM64WrapperLarge : SDNode<"ARM64ISD::WrapperLarge", SDT_ARM64WrapperLarge>;


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

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

// ARM64 Instruction Predicate Definitions.
//
def HasZCZ    : Predicate<"Subtarget->hasZeroCycleZeroing()">;
def NoZCZ     : Predicate<"!Subtarget->hasZeroCycleZeroing()">;
def IsDarwin  : Predicate<"Subtarget->isTargetDarwin()">;
def IsNotDarwin: Predicate<"!Subtarget->isTargetDarwin()">;
def ForCodeSize   : Predicate<"ForCodeSize">;
def NotForCodeSize   : Predicate<"!ForCodeSize">;

include "ARM64InstrFormats.td"

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

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

let Defs = [SP], Uses = [SP], hasSideEffects = 1, isCodeGenOnly = 1 in {
def ADJCALLSTACKDOWN : Pseudo<(outs), (ins i32imm:$amt),
                              [(ARM64callseq_start timm:$amt)]>;
def ADJCALLSTACKUP : Pseudo<(outs), (ins i32imm:$amt1, i32imm:$amt2),
                            [(ARM64callseq_end timm:$amt1, timm:$amt2)]>;
} // Defs = [SP], Uses = [SP], hasSideEffects = 1, isCodeGenOnly = 1

let isReMaterializable = 1, isCodeGenOnly = 1 in {
// FIXME: The following pseudo instructions are only needed because remat
// cannot handle multiple instructions.  When that changes, they can be
// removed, along with the ARM64Wrapper node.

let AddedComplexity = 10 in
def LOADgot : Pseudo<(outs GPR64:$dst), (ins i64imm:$addr),
                     [(set GPR64:$dst, (ARM64LOADgot tglobaladdr:$addr))]>,
              Sched<[WriteLDAdr]>;

// The MOVaddr instruction should match only when the add is not folded
// into a load or store address.
def MOVaddr
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (ARM64addlow (ARM64adrp tglobaladdr:$hi),
                                            tglobaladdr:$low))]>,
      Sched<[WriteAdrAdr]>;
def MOVaddrJT
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (ARM64addlow (ARM64adrp tjumptable:$hi),
                                             tjumptable:$low))]>,
      Sched<[WriteAdrAdr]>;
def MOVaddrCP
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (ARM64addlow (ARM64adrp tconstpool:$hi),
                                             tconstpool:$low))]>,
      Sched<[WriteAdrAdr]>;
def MOVaddrBA
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (ARM64addlow (ARM64adrp tblockaddress:$hi),
                                             tblockaddress:$low))]>,
      Sched<[WriteAdrAdr]>;
def MOVaddrTLS
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (ARM64addlow (ARM64adrp tglobaltlsaddr:$hi),
                                            tglobaltlsaddr:$low))]>,
      Sched<[WriteAdrAdr]>;
def MOVaddrEXT
    : Pseudo<(outs GPR64:$dst), (ins i64imm:$hi, i64imm:$low),
             [(set GPR64:$dst, (ARM64addlow (ARM64adrp texternalsym:$hi),
                                            texternalsym:$low))]>,
      Sched<[WriteAdrAdr]>;

} // isReMaterializable, isCodeGenOnly

def : Pat<(ARM64LOADgot tglobaltlsaddr:$addr),
          (LOADgot tglobaltlsaddr:$addr)>;

def : Pat<(ARM64LOADgot texternalsym:$addr),
          (LOADgot texternalsym:$addr)>;

def : Pat<(ARM64LOADgot tconstpool:$addr),
          (LOADgot tconstpool:$addr)>;

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

def HINT  : HintI<"hint">;
def : InstAlias<"nop",  (HINT 0b000)>;
def : InstAlias<"yield",(HINT 0b001)>;
def : InstAlias<"wfe",  (HINT 0b010)>;
def : InstAlias<"wfi",  (HINT 0b011)>;
def : InstAlias<"sev",  (HINT 0b100)>;
def : InstAlias<"sevl", (HINT 0b101)>;

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

def DMB   : CRmSystemI<barrier_op, 0b101, "dmb">;
def DSB   : CRmSystemI<barrier_op, 0b100, "dsb">;
def ISB   : CRmSystemI<barrier_op, 0b110, "isb">;
def : InstAlias<"clrex", (CLREX 0xf)>;
def : InstAlias<"isb", (ISB 0xf)>;

def MRS    : MRSI;
def MSR    : MSRI;
def MSRpstate: MSRpstateI;

// The thread pointer (on Linux, at least, where this has been implemented) is
// TPIDR_EL0.
def : Pat<(ARM64threadpointer), (MRS 0xde82)>;

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

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

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

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

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

// First group of aliases covers an implicit "lsl #0".
def : InstAlias<"movk $dst, $imm", (MOVKWi GPR32:$dst, imm0_65535:$imm, 0)>;
def : InstAlias<"movk $dst, $imm", (MOVKXi GPR64:$dst, imm0_65535:$imm, 0)>;
def : InstAlias<"movn $dst, $imm", (MOVNWi GPR32:$dst, imm0_65535:$imm, 0)>;
def : InstAlias<"movn $dst, $imm", (MOVNXi GPR64:$dst, imm0_65535:$imm, 0)>;
def : InstAlias<"movz $dst, $imm", (MOVZWi GPR32:$dst, imm0_65535:$imm, 0)>;
def : InstAlias<"movz $dst, $imm", (MOVZXi GPR64:$dst, imm0_65535:$imm, 0)>;

// Next, we have various ELF relocations with the ":XYZ_g0:sym" syntax.
def : InstAlias<"movz $Rd, $sym", (MOVZXi GPR64:$Rd, movz_symbol_g3:$sym, 48)>;
def : InstAlias<"movz $Rd, $sym", (MOVZXi GPR64:$Rd, movz_symbol_g2:$sym, 32)>;
def : InstAlias<"movz $Rd, $sym", (MOVZXi GPR64:$Rd, movz_symbol_g1:$sym, 16)>;
def : InstAlias<"movz $Rd, $sym", (MOVZXi GPR64:$Rd, movz_symbol_g0:$sym, 0)>;

def : InstAlias<"movn $Rd, $sym", (MOVNXi GPR64:$Rd, movz_symbol_g3:$sym, 48)>;
def : InstAlias<"movn $Rd, $sym", (MOVNXi GPR64:$Rd, movz_symbol_g2:$sym, 32)>;
def : InstAlias<"movn $Rd, $sym", (MOVNXi GPR64:$Rd, movz_symbol_g1:$sym, 16)>;
def : InstAlias<"movn $Rd, $sym", (MOVNXi GPR64:$Rd, movz_symbol_g0:$sym, 0)>;

def : InstAlias<"movk $Rd, $sym", (MOVKXi GPR64:$Rd, movk_symbol_g3:$sym, 48)>;
def : InstAlias<"movk $Rd, $sym", (MOVKXi GPR64:$Rd, movk_symbol_g2:$sym, 32)>;
def : InstAlias<"movk $Rd, $sym", (MOVKXi GPR64:$Rd, movk_symbol_g1:$sym, 16)>;
def : InstAlias<"movk $Rd, $sym", (MOVKXi GPR64:$Rd, movk_symbol_g0:$sym, 0)>;

def : InstAlias<"movz $Rd, $sym", (MOVZWi GPR32:$Rd, movz_symbol_g1:$sym, 16)>;
def : InstAlias<"movz $Rd, $sym", (MOVZWi GPR32:$Rd, movz_symbol_g0:$sym, 0)>;

def : InstAlias<"movn $Rd, $sym", (MOVNWi GPR32:$Rd, movz_symbol_g1:$sym, 16)>;
def : InstAlias<"movn $Rd, $sym", (MOVNWi GPR32:$Rd, movz_symbol_g0:$sym, 0)>;

def : InstAlias<"movk $Rd, $sym", (MOVKWi GPR32:$Rd, movk_symbol_g1:$sym, 16)>;
def : InstAlias<"movk $Rd, $sym", (MOVKWi GPR32:$Rd, movk_symbol_g0:$sym, 0)>;

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

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

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

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

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

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

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

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

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

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

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

def : Pat<(i64 i64imm_32bit:$src),
          (SUBREG_TO_REG (i64 0), (MOVi32imm (trunc_imm imm:$src)), sub_32)>;

// Deal with the various forms of (ELF) large addressing with MOVZ/MOVK
// sequences.
def : Pat<(ARM64WrapperLarge tglobaladdr:$g3, tglobaladdr:$g2,
                             tglobaladdr:$g1, tglobaladdr:$g0),
          (MOVKXi (MOVKXi (MOVKXi (MOVZXi tglobaladdr:$g3, 48),
                                  tglobaladdr:$g2, 32),
                          tglobaladdr:$g1, 16),
                  tglobaladdr:$g0, 0)>;

def : Pat<(ARM64WrapperLarge tblockaddress:$g3, tblockaddress:$g2,
                             tblockaddress:$g1, tblockaddress:$g0),
          (MOVKXi (MOVKXi (MOVKXi (MOVZXi tblockaddress:$g3, 48),
                                  tblockaddress:$g2, 32),
                          tblockaddress:$g1, 16),
                  tblockaddress:$g0, 0)>;

def : Pat<(ARM64WrapperLarge tconstpool:$g3, tconstpool:$g2,
                             tconstpool:$g1, tconstpool:$g0),
          (MOVKXi (MOVKXi (MOVKXi (MOVZXi tconstpool:$g3, 48),
                                  tconstpool:$g2, 32),
                          tconstpool:$g1, 16),
                  tconstpool:$g0, 0)>;

def : Pat<(ARM64WrapperLarge tjumptable:$g3, tjumptable:$g2,
                             tjumptable:$g1, tjumptable:$g0),
          (MOVKXi (MOVKXi (MOVKXi (MOVZXi tjumptable:$g3, 48),
                                  tjumptable:$g2, 32),
                          tjumptable:$g1, 16),
                  tjumptable:$g0, 0)>;


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

// Add/subtract with carry.
defm ADC : AddSubCarry<0, "adc", "adcs", ARM64adc, ARM64adc_flag>;
defm SBC : AddSubCarry<1, "sbc", "sbcs", ARM64sbc, ARM64sbc_flag>;

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

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

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

defm ADDS : AddSubS<0, "adds", ARM64add_flag, "cmn">;
defm SUBS : AddSubS<1, "subs", ARM64sub_flag, "cmp">;

// Use SUBS instead of SUB to enable CSE between SUBS and SUB.
def : Pat<(sub GPR32sp:$Rn, addsub_shifted_imm32:$imm),
          (SUBSWri GPR32sp:$Rn, addsub_shifted_imm32:$imm)>;
def : Pat<(sub GPR64sp:$Rn, addsub_shifted_imm64:$imm),
          (SUBSXri GPR64sp:$Rn, addsub_shifted_imm64:$imm)>;
def : Pat<(sub GPR32:$Rn, GPR32:$Rm),
          (SUBSWrr GPR32:$Rn, GPR32:$Rm)>;
def : Pat<(sub GPR64:$Rn, GPR64:$Rm),
          (SUBSXrr GPR64:$Rn, GPR64:$Rm)>;
def : Pat<(sub GPR32:$Rn, arith_shifted_reg32:$Rm),
          (SUBSWrs GPR32:$Rn, arith_shifted_reg32:$Rm)>;
def : Pat<(sub GPR64:$Rn, arith_shifted_reg64:$Rm),
          (SUBSXrs GPR64:$Rn, arith_shifted_reg64:$Rm)>;
def : Pat<(sub GPR32sp:$R2, arith_extended_reg32<i32>:$R3),
          (SUBSWrx GPR32sp:$R2, arith_extended_reg32<i32>:$R3)>;
def : Pat<(sub GPR64sp:$R2, arith_extended_reg32to64<i64>:$R3),
          (SUBSXrx GPR64sp:$R2, arith_extended_reg32to64<i64>:$R3)>;

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

// FIXME: TableGen can very nearly handle printing all of these, we should make
// it work properly.
def : InstAlias<"neg $dst, $src", (SUBWrs GPR32:$dst, WZR, GPR32:$src, 0)>;
def : InstAlias<"neg $dst, $src", (SUBXrs GPR64:$dst, XZR, GPR64:$src, 0)>;
def : InstAlias<"neg $dst, $src, $shift",
                (SUBWrs GPR32:$dst, WZR, GPR32:$src, arith_shift32:$shift)>;
def : InstAlias<"neg $dst, $src, $shift",
                (SUBXrs GPR64:$dst, XZR, GPR64:$src, arith_shift64:$shift)>;

// Because of the immediate format for add/sub-imm instructions, the
// expression (add x, -1) must be transformed to (SUB{W,X}ri x, 1).
//  These patterns capture that transformation.
let AddedComplexity = 1 in {
def : Pat<(ARM64add_flag GPR32:$Rn, neg_addsub_shifted_imm32:$imm),
          (SUBSWri GPR32:$Rn, neg_addsub_shifted_imm32:$imm)>;
def : Pat<(ARM64add_flag GPR64:$Rn, neg_addsub_shifted_imm64:$imm),
          (SUBSXri GPR64:$Rn, neg_addsub_shifted_imm64:$imm)>;
def : Pat<(ARM64sub_flag GPR32:$Rn, neg_addsub_shifted_imm32:$imm),
          (ADDSWri GPR32:$Rn, neg_addsub_shifted_imm32:$imm)>;
def : Pat<(ARM64sub_flag GPR64:$Rn, neg_addsub_shifted_imm64:$imm),
          (ADDSXri GPR64:$Rn, neg_addsub_shifted_imm64:$imm)>;
}

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

// Unsigned/Signed divide
defm UDIV : Div<0, "udiv", udiv>;
defm SDIV : Div<1, "sdiv", sdiv>;
let isCodeGenOnly = 1 in {
defm UDIV_Int : Div<0, "udiv", int_arm64_udiv>;
defm SDIV_Int : Div<1, "sdiv", int_arm64_sdiv>;
}

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

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

// Multiply-add
let AddedComplexity = 7 in {
defm MADD : MulAccum<0, "madd", add>;
defm MSUB : MulAccum<1, "msub", sub>;

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

def : Pat<(i32 (ineg (mul GPR32:$Rn, GPR32:$Rm))),
          (MSUBWrrr GPR32:$Rn, GPR32:$Rm, WZR)>;
def : Pat<(i64 (ineg (mul GPR64:$Rn, GPR64:$Rm))),
          (MSUBXrrr GPR64:$Rn, GPR64:$Rm, XZR)>;
} // AddedComplexity = 7

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

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

def : Pat<(i64 (ineg (mul (sext GPR32:$Rn), (sext GPR32:$Rm)))),
          (SMSUBLrrr GPR32:$Rn, GPR32:$Rm, XZR)>;
def : Pat<(i64 (ineg (mul (zext GPR32:$Rn), (zext GPR32:$Rm)))),
          (UMSUBLrrr GPR32:$Rn, GPR32:$Rm, XZR)>;
} // AddedComplexity = 5

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

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

// CRC32
def CRC32Brr : BaseCRC32<0, 0b00, 0, GPR32, int_arm64_crc32b, "crc32b">;
def CRC32Hrr : BaseCRC32<0, 0b01, 0, GPR32, int_arm64_crc32h, "crc32h">;
def CRC32Wrr : BaseCRC32<0, 0b10, 0, GPR32, int_arm64_crc32w, "crc32w">;
def CRC32Xrr : BaseCRC32<1, 0b11, 0, GPR64, int_arm64_crc32x, "crc32x">;

def CRC32CBrr : BaseCRC32<0, 0b00, 1, GPR32, int_arm64_crc32cb, "crc32cb">;
def CRC32CHrr : BaseCRC32<0, 0b01, 1, GPR32, int_arm64_crc32ch, "crc32ch">;
def CRC32CWrr : BaseCRC32<0, 0b10, 1, GPR32, int_arm64_crc32cw, "crc32cw">;
def CRC32CXrr : BaseCRC32<1, 0b11, 1, GPR64, int_arm64_crc32cx, "crc32cx">;


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

// (immediate)
defm ANDS : LogicalImmS<0b11, "ands", ARM64and_flag>;
defm AND  : LogicalImm<0b00, "and", and>;
defm EOR  : LogicalImm<0b10, "eor", xor>;
defm ORR  : LogicalImm<0b01, "orr", or>;

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


// (register)
defm ANDS : LogicalRegS<0b11, 0, "ands", ARM64and_flag>;
defm BICS : LogicalRegS<0b11, 1, "bics",
                        BinOpFrag<(ARM64and_flag node:$LHS, (not node:$RHS))>>;
defm AND  : LogicalReg<0b00, 0, "and", and>;
defm BIC  : LogicalReg<0b00, 1, "bic",
                       BinOpFrag<(and node:$LHS, (not node:$RHS))>>;
defm EON  : LogicalReg<0b10, 1, "eon",
                       BinOpFrag<(xor node:$LHS, (not node:$RHS))>>;
defm EOR  : LogicalReg<0b10, 0, "eor", xor>;
defm ORN  : LogicalReg<0b01, 1, "orn",
                       BinOpFrag<(or node:$LHS, (not node:$RHS))>>;
defm ORR  : LogicalReg<0b01, 0, "orr", or>;

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

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

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

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

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

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

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


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

defm CLS    : OneOperandData<0b101, "cls">;
defm CLZ    : OneOperandData<0b100, "clz", ctlz>;
defm RBIT   : OneOperandData<0b000, "rbit">;
def  REV16Wr : OneWRegData<0b001, "rev16",
                                  UnOpFrag<(rotr (bswap node:$LHS), (i64 16))>>;
def  REV16Xr : OneXRegData<0b001, "rev16", null_frag>;

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

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

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

//===----------------------------------------------------------------------===//
// Bitfield immediate extraction instruction.
//===----------------------------------------------------------------------===//
let neverHasSideEffects = 1 in
defm EXTR : ExtractImm<"extr">;
def : InstAlias<"ror $dst, $src, $shift",
            (EXTRWrri GPR32:$dst, GPR32:$src, GPR32:$src, imm0_31:$shift)>;
def : InstAlias<"ror $dst, $src, $shift",
            (EXTRXrri GPR64:$dst, GPR64:$src, GPR64:$src, imm0_63:$shift)>;

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

//===----------------------------------------------------------------------===//
// Other bitfield immediate instructions.
//===----------------------------------------------------------------------===//
let neverHasSideEffects = 1 in {
defm BFM  : BitfieldImmWith2RegArgs<0b01, "bfm">;
defm SBFM : BitfieldImm<0b00, "sbfm">;
defm UBFM : BitfieldImm<0b10, "ubfm">;
}

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

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

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

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

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

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

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

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

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

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

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

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

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

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

//===----------------------------------------------------------------------===//
// Conditionally set flags instructions.
//===----------------------------------------------------------------------===//
defm CCMN : CondSetFlagsImm<0, "ccmn">;
defm CCMP : CondSetFlagsImm<1, "ccmp">;

defm CCMN : CondSetFlagsReg<0, "ccmn">;
defm CCMP : CondSetFlagsReg<1, "ccmp">;

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

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

def : Pat<(ARM64csinv GPR32:$tval, GPR32:$fval, (i32 imm:$cc), NZCV),
          (CSINVWr GPR32:$tval, GPR32:$fval, (i32 imm:$cc))>;
def : Pat<(ARM64csinv GPR64:$tval, GPR64:$fval, (i32 imm:$cc), NZCV),
          (CSINVXr GPR64:$tval, GPR64:$fval, (i32 imm:$cc))>;
def : Pat<(ARM64csneg GPR32:$tval, GPR32:$fval, (i32 imm:$cc), NZCV),
          (CSNEGWr GPR32:$tval, GPR32:$fval, (i32 imm:$cc))>;
def : Pat<(ARM64csneg GPR64:$tval, GPR64:$fval, (i32 imm:$cc), NZCV),
          (CSNEGXr GPR64:$tval, GPR64:$fval, (i32 imm:$cc))>;
def : Pat<(ARM64csinc GPR32:$tval, GPR32:$fval, (i32 imm:$cc), NZCV),
          (CSINCWr GPR32:$tval, GPR32:$fval, (i32 imm:$cc))>;
def : Pat<(ARM64csinc GPR64:$tval, GPR64:$fval, (i32 imm:$cc), NZCV),
          (CSINCXr GPR64:$tval, GPR64:$fval, (i32 imm:$cc))>;

def : Pat<(ARM64csel (i32 0), (i32 1), (i32 imm:$cc), NZCV),
          (CSINCWr WZR, WZR, (i32 imm:$cc))>;
def : Pat<(ARM64csel (i64 0), (i64 1), (i32 imm:$cc), NZCV),
          (CSINCXr XZR, XZR, (i32 imm:$cc))>;
def : Pat<(ARM64csel (i32 0), (i32 -1), (i32 imm:$cc), NZCV),
          (CSINVWr WZR, WZR, (i32 imm:$cc))>;
def : Pat<(ARM64csel (i64 0), (i64 -1), (i32 imm:$cc), NZCV),
          (CSINVXr XZR, XZR, (i32 imm:$cc))>;

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

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

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

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

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

//===----------------------------------------------------------------------===//
// PC-relative instructions.
//===----------------------------------------------------------------------===//
let isReMaterializable = 1 in {
let neverHasSideEffects = 1, mayStore = 0, mayLoad = 0 in {
def ADR  : ADRI<0, "adr", adrlabel, []>;
} // neverHasSideEffects = 1

def ADRP : ADRI<1, "adrp", adrplabel,
                [(set GPR64:$Xd, (ARM64adrp tglobaladdr:$label))]>;
} // isReMaterializable = 1

// page address of a constant pool entry, block address
def : Pat<(ARM64adrp tconstpool:$cp), (ADRP tconstpool:$cp)>;
def : Pat<(ARM64adrp tblockaddress:$cp), (ADRP tblockaddress:$cp)>;

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

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

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

let isCall = 1, Defs = [LR], Uses = [SP] in {
def BLR : BranchReg<0b0001, "blr", [(ARM64call GPR64:$Rn)]>;
} // isCall

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

// Create a separate pseudo-instruction for codegen to use so that we don't
// flag lr as used in every function. It'll be restored before the RET by the
// epilogue if it's legitimately used.
def RET_ReallyLR : Pseudo<(outs), (ins), [(ARM64retflag)]> {
  let isTerminator = 1;
  let isBarrier = 1;
  let isReturn = 1;
}

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

// Pseudo-instruction representing a BLR with attached TLSDESC relocation. It
// gets expanded to two MCInsts during lowering.
let isCall = 1, Defs = [LR] in
def TLSDESC_BLR
    : Pseudo<(outs), (ins GPR64:$dest, i64imm:$sym),
             [(ARM64tlsdesc_call GPR64:$dest, tglobaltlsaddr:$sym)]>;

def : Pat<(ARM64tlsdesc_call GPR64:$dest, texternalsym:$sym),
          (TLSDESC_BLR GPR64:$dest, texternalsym:$sym)>;
//===----------------------------------------------------------------------===//
// Conditional branch (immediate) instruction.
//===----------------------------------------------------------------------===//
def Bcc : BranchCond;

//===----------------------------------------------------------------------===//
// Compare-and-branch instructions.
//===----------------------------------------------------------------------===//
defm CBZ  : CmpBranch<0, "cbz", ARM64cbz>;
defm CBNZ : CmpBranch<1, "cbnz", ARM64cbnz>;

//===----------------------------------------------------------------------===//
// Test-bit-and-branch instructions.
//===----------------------------------------------------------------------===//
def TBZ  : TestBranch<0, "tbz", ARM64tbz>;
def TBNZ : TestBranch<1, "tbnz", ARM64tbnz>;

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

let isCall = 1, Defs = [LR], Uses = [SP] in {
def BL : CallImm<1, "bl", [(ARM64call tglobaladdr:$addr)]>;
} // isCall
def : Pat<(ARM64call texternalsym:$func), (BL texternalsym:$func)>;

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

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

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

// Pair (indexed, offset)
def LDPWi : LoadPairOffset<0b00, 0, GPR32, am_indexed32simm7, "ldp">;
def LDPXi : LoadPairOffset<0b10, 0, GPR64, am_indexed64simm7, "ldp">;
def LDPSi : LoadPairOffset<0b00, 1, FPR32, am_indexed32simm7, "ldp">;
def LDPDi : LoadPairOffset<0b01, 1, FPR64, am_indexed64simm7, "ldp">;
def LDPQi : LoadPairOffset<0b10, 1, FPR128, am_indexed128simm7, "ldp">;

def LDPSWi : LoadPairOffset<0b01, 0, GPR64, am_indexed32simm7, "ldpsw">;

// Pair (pre-indexed)
def LDPWpre : LoadPairPreIdx<0b00, 0, GPR32, am_indexed32simm7_wb, "ldp">;
def LDPXpre : LoadPairPreIdx<0b10, 0, GPR64, am_indexed64simm7_wb, "ldp">;
def LDPSpre : LoadPairPreIdx<0b00, 1, FPR32, am_indexed32simm7_wb, "ldp">;
def LDPDpre : LoadPairPreIdx<0b01, 1, FPR64, am_indexed64simm7_wb, "ldp">;
def LDPQpre : LoadPairPreIdx<0b10, 1, FPR128, am_indexed128simm7_wb, "ldp">;

def LDPSWpre : LoadPairPreIdx<0b01, 0, GPR64, am_indexed32simm7_wb, "ldpsw">;

// Pair (post-indexed)
def LDPWpost : LoadPairPostIdx<0b00, 0, GPR32, simm7s4, "ldp">;
def LDPXpost : LoadPairPostIdx<0b10, 0, GPR64, simm7s8, "ldp">;
def LDPSpost : LoadPairPostIdx<0b00, 1, FPR32, simm7s4, "ldp">;
def LDPDpost : LoadPairPostIdx<0b01, 1, FPR64, simm7s8, "ldp">;
def LDPQpost : LoadPairPostIdx<0b10, 1, FPR128, simm7s16, "ldp">;

def LDPSWpost : LoadPairPostIdx<0b01, 0, GPR64, simm7s4, "ldpsw">;


// Pair (no allocate)
def LDNPWi : LoadPairNoAlloc<0b00, 0, GPR32, am_indexed32simm7, "ldnp">;
def LDNPXi : LoadPairNoAlloc<0b10, 0, GPR64, am_indexed64simm7, "ldnp">;
def LDNPSi : LoadPairNoAlloc<0b00, 1, FPR32, am_indexed32simm7, "ldnp">;
def LDNPDi : LoadPairNoAlloc<0b01, 1, FPR64, am_indexed64simm7, "ldnp">;
def LDNPQi : LoadPairNoAlloc<0b10, 1, FPR128, am_indexed128simm7, "ldnp">;

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

let AddedComplexity = 10 in {
// Integer
def LDRBBro : Load8RO<0b00,  0, 0b01, GPR32, "ldrb",
                      [(set GPR32:$Rt, (zextloadi8 ro_indexed8:$addr))]>;
def LDRHHro : Load16RO<0b01, 0, 0b01, GPR32, "ldrh",
                      [(set GPR32:$Rt, (zextloadi16 ro_indexed16:$addr))]>;
def LDRWro  : Load32RO<0b10,   0, 0b01, GPR32, "ldr",
                      [(set GPR32:$Rt, (load ro_indexed32:$addr))]>;
def LDRXro  : Load64RO<0b11,   0, 0b01, GPR64, "ldr",
                      [(set GPR64:$Rt, (load ro_indexed64:$addr))]>;

// Floating-point
def LDRBro : Load8RO<0b00,   1, 0b01, FPR8,   "ldr",
                      [(set FPR8:$Rt, (load ro_indexed8:$addr))]>;
def LDRHro : Load16RO<0b01,  1, 0b01, FPR16,  "ldr",
                      [(set (f16 FPR16:$Rt), (load ro_indexed16:$addr))]>;
def LDRSro : Load32RO<0b10,    1, 0b01, FPR32,  "ldr",
                      [(set (f32 FPR32:$Rt), (load ro_indexed32:$addr))]>;
def LDRDro : Load64RO<0b11,    1, 0b01, FPR64,  "ldr",
                      [(set (f64 FPR64:$Rt), (load ro_indexed64:$addr))]>;
def LDRQro : Load128RO<0b00,    1, 0b11, FPR128, "ldr", []> {
  let mayLoad = 1;
}

// For regular load, we do not have any alignment requirement.
// Thus, it is safe to directly map the vector loads with interesting
// addressing modes.
// FIXME: We could do the same for bitconvert to floating point vectors.
def : Pat <(v8i8 (scalar_to_vector (i32 (extloadi8 ro_indexed8:$addr)))),
           (INSERT_SUBREG (v8i8 (IMPLICIT_DEF)),
                          (LDRBro ro_indexed8:$addr), bsub)>;
def : Pat <(v16i8 (scalar_to_vector (i32 (extloadi8 ro_indexed8:$addr)))),
           (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
                          (LDRBro ro_indexed8:$addr), bsub)>;
def : Pat <(v4i16 (scalar_to_vector (i32 (extloadi16 ro_indexed16:$addr)))),
           (INSERT_SUBREG (v4i16 (IMPLICIT_DEF)),
                          (LDRHro ro_indexed16:$addr), hsub)>;
def : Pat <(v8i16 (scalar_to_vector (i32 (extloadi16 ro_indexed16:$addr)))),
           (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)),
                          (LDRHro ro_indexed16:$addr), hsub)>;
def : Pat <(v2i32 (scalar_to_vector (i32 (load ro_indexed32:$addr)))),
           (INSERT_SUBREG (v2i32 (IMPLICIT_DEF)),
                          (LDRSro ro_indexed32:$addr), ssub)>;
def : Pat <(v4i32 (scalar_to_vector (i32 (load ro_indexed32:$addr)))),
           (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)),
                          (LDRSro ro_indexed32:$addr), ssub)>;
def : Pat <(v1i64 (scalar_to_vector (i64 (load ro_indexed64:$addr)))),
           (LDRDro ro_indexed64:$addr)>;
def : Pat <(v2i64 (scalar_to_vector (i64 (load ro_indexed64:$addr)))),
           (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)),
                          (LDRDro ro_indexed64:$addr), dsub)>;

// Match all load 64 bits width whose type is compatible with FPR64
let Predicates = [IsLE] in {
  // We must do vector loads with LD1 in big-endian.
  def : Pat<(v2f32 (load ro_indexed64:$addr)), (LDRDro ro_indexed64:$addr)>;
  def : Pat<(v8i8  (load ro_indexed64:$addr)), (LDRDro ro_indexed64:$addr)>;
  def : Pat<(v4i16 (load ro_indexed64:$addr)), (LDRDro ro_indexed64:$addr)>;
  def : Pat<(v2i32 (load ro_indexed64:$addr)), (LDRDro ro_indexed64:$addr)>;
}
def : Pat<(v1f64 (load ro_indexed64:$addr)), (LDRDro ro_indexed64:$addr)>;
def : Pat<(v1i64 (load ro_indexed64:$addr)), (LDRDro ro_indexed64:$addr)>;

// Match all load 128 bits width whose type is compatible with FPR128
let Predicates = [IsLE] in {
  // We must do vector loads with LD1 in big-endian.
  def : Pat<(v4f32 (load ro_indexed128:$addr)), (LDRQro ro_indexed128:$addr)>;
  def : Pat<(v2f64 (load ro_indexed128:$addr)), (LDRQro ro_indexed128:$addr)>;
  def : Pat<(v16i8 (load ro_indexed128:$addr)), (LDRQro ro_indexed128:$addr)>;
  def : Pat<(v8i16 (load ro_indexed128:$addr)), (LDRQro ro_indexed128:$addr)>;
  def : Pat<(v4i32 (load ro_indexed128:$addr)), (LDRQro ro_indexed128:$addr)>;
  def : Pat<(v2i64 (load ro_indexed128:$addr)), (LDRQro ro_indexed128:$addr)>;
}
def : Pat<(f128  (load ro_indexed128:$addr)), (LDRQro ro_indexed128:$addr)>;

// Load sign-extended half-word
def LDRSHWro : Load16RO<0b01, 0, 0b11, GPR32, "ldrsh",
                      [(set GPR32:$Rt, (sextloadi16 ro_indexed16:$addr))]>;
def LDRSHXro : Load16RO<0b01, 0, 0b10, GPR64, "ldrsh",
                      [(set GPR64:$Rt, (sextloadi16 ro_indexed16:$addr))]>;

// Load sign-extended byte
def LDRSBWro : Load8RO<0b00, 0, 0b11, GPR32, "ldrsb",
                      [(set GPR32:$Rt, (sextloadi8 ro_indexed8:$addr))]>;
def LDRSBXro : Load8RO<0b00, 0, 0b10, GPR64, "ldrsb",
                      [(set GPR64:$Rt, (sextloadi8 ro_indexed8:$addr))]>;

// Load sign-extended word
def LDRSWro  : Load32RO<0b10, 0, 0b10, GPR64, "ldrsw",
                      [(set GPR64:$Rt, (sextloadi32 ro_indexed32:$addr))]>;

// Pre-fetch.
def PRFMro : PrefetchRO<0b11, 0, 0b10, "prfm",
                        [(ARM64Prefetch imm:$Rt, ro_indexed64:$addr)]>;

// zextload -> i64
def : Pat<(i64 (zextloadi8 ro_indexed8:$addr)),
    (SUBREG_TO_REG (i64 0), (LDRBBro ro_indexed8:$addr), sub_32)>;
def : Pat<(i64 (zextloadi16 ro_indexed16:$addr)),
    (SUBREG_TO_REG (i64 0), (LDRHHro ro_indexed16:$addr), sub_32)>;
def : Pat<(i64 (zextloadi32 ro_indexed32:$addr)),
    (SUBREG_TO_REG (i64 0), (LDRWro ro_indexed32:$addr), sub_32)>;

// zextloadi1 -> zextloadi8
def : Pat<(i32 (zextloadi1 ro_indexed8:$addr)), (LDRBBro ro_indexed8:$addr)>;
def : Pat<(i64 (zextloadi1 ro_indexed8:$addr)),
    (SUBREG_TO_REG (i64 0), (LDRBBro ro_indexed8:$addr), sub_32)>;

// extload -> zextload
def : Pat<(i32 (extloadi16 ro_indexed16:$addr)), (LDRHHro ro_indexed16:$addr)>;
def : Pat<(i32 (extloadi8 ro_indexed8:$addr)), (LDRBBro ro_indexed8:$addr)>;
def : Pat<(i32 (extloadi1 ro_indexed8:$addr)), (LDRBBro ro_indexed8:$addr)>;
def : Pat<(i64 (extloadi32 ro_indexed32:$addr)),
    (SUBREG_TO_REG (i64 0), (LDRWro ro_indexed32:$addr), sub_32)>;
def : Pat<(i64 (extloadi16 ro_indexed16:$addr)),
    (SUBREG_TO_REG (i64 0), (LDRHHro ro_indexed16:$addr), sub_32)>;
def : Pat<(i64 (extloadi8 ro_indexed8:$addr)),
    (SUBREG_TO_REG (i64 0), (LDRBBro ro_indexed8:$addr), sub_32)>;
def : Pat<(i64 (extloadi1 ro_indexed8:$addr)),
    (SUBREG_TO_REG (i64 0), (LDRBBro ro_indexed8:$addr), sub_32)>;

} // AddedComplexity = 10

//---
// (unsigned immediate)
//---
def LDRXui : LoadUI<0b11, 0, 0b01, GPR64, am_indexed64, "ldr",
                    [(set GPR64:$Rt, (load am_indexed64:$addr))]>;
def LDRWui : LoadUI<0b10, 0, 0b01, GPR32, am_indexed32, "ldr",
                    [(set GPR32:$Rt, (load am_indexed32:$addr))]>;
def LDRBui : LoadUI<0b00, 1, 0b01, FPR8, am_indexed8, "ldr",
                    [(set FPR8:$Rt, (load am_indexed8:$addr))]>;
def LDRHui : LoadUI<0b01, 1, 0b01, FPR16, am_indexed16, "ldr",
                    [(set (f16 FPR16:$Rt), (load am_indexed16:$addr))]>;
def LDRSui : LoadUI<0b10, 1, 0b01, FPR32, am_indexed32, "ldr",
                    [(set (f32 FPR32:$Rt), (load am_indexed32:$addr))]>;
def LDRDui : LoadUI<0b11, 1, 0b01, FPR64, am_indexed64, "ldr",
                    [(set (f64 FPR64:$Rt), (load am_indexed64:$addr))]>;
def LDRQui : LoadUI<0b00, 1, 0b11, FPR128, am_indexed128, "ldr",
                    [(set (f128 FPR128:$Rt), (load am_indexed128:$addr))]>;

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

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

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

def LDRHHui : LoadUI<0b01, 0, 0b01, GPR32, am_indexed16, "ldrh",
                     [(set GPR32:$Rt, (zextloadi16 am_indexed16:$addr))]>;
def LDRBBui : LoadUI<0b00, 0, 0b01, GPR32, am_indexed8, "ldrb",
                     [(set GPR32:$Rt, (zextloadi8 am_indexed8:$addr))]>;
// zextload -> i64
def : Pat<(i64 (zextloadi8 am_indexed8:$addr)),
    (SUBREG_TO_REG (i64 0), (LDRBBui am_indexed8:$addr), sub_32)>;
def : Pat<(i64 (zextloadi16 am_indexed16:$addr)),
    (SUBREG_TO_REG (i64 0), (LDRHHui am_indexed16:$addr), sub_32)>;

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

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

// load sign-extended half-word
def LDRSHWui : LoadUI<0b01, 0, 0b11, GPR32, am_indexed16, "ldrsh",
                      [(set GPR32:$Rt, (sextloadi16 am_indexed16:$addr))]>;
def LDRSHXui : LoadUI<0b01, 0, 0b10, GPR64, am_indexed16, "ldrsh",
                      [(set GPR64:$Rt, (sextloadi16 am_indexed16:$addr))]>;

// load sign-extended byte
def LDRSBWui : LoadUI<0b00, 0, 0b11, GPR32, am_indexed8, "ldrsb",
                      [(set GPR32:$Rt, (sextloadi8 am_indexed8:$addr))]>;
def LDRSBXui : LoadUI<0b00, 0, 0b10, GPR64, am_indexed8, "ldrsb",
                      [(set GPR64:$Rt, (sextloadi8 am_indexed8:$addr))]>;

// load sign-extended word
def LDRSWui  : LoadUI<0b10, 0, 0b10, GPR64, am_indexed32, "ldrsw",
                      [(set GPR64:$Rt, (sextloadi32 am_indexed32:$addr))]>;

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

// Pre-fetch.
def PRFMui : PrefetchUI<0b11, 0, 0b10, "prfm",
                        [(ARM64Prefetch imm:$Rt, am_indexed64:$addr)]>;

//---
// (literal)
def LDRWl : LoadLiteral<0b00, 0, GPR32, "ldr">;
def LDRXl : LoadLiteral<0b01, 0, GPR64, "ldr">;
def LDRSl : LoadLiteral<0b00, 1, FPR32, "ldr">;
def LDRDl : LoadLiteral<0b01, 1, FPR64, "ldr">;
def LDRQl : LoadLiteral<0b10, 1, FPR128, "ldr">;

// load sign-extended word
def LDRSWl : LoadLiteral<0b10, 0, GPR64, "ldrsw">;

// prefetch
def PRFMl : PrefetchLiteral<0b11, 0, "prfm", []>;
//                   [(ARM64Prefetch imm:$Rt, tglobaladdr:$label)]>;

//---
// (unscaled immediate)
def LDURXi : LoadUnscaled<0b11, 0, 0b01, GPR64, am_unscaled64, "ldur",
                          [(set GPR64:$Rt, (load am_unscaled64:$addr))]>;
def LDURWi : LoadUnscaled<0b10, 0, 0b01, GPR32, am_unscaled32, "ldur",
                          [(set GPR32:$Rt, (load am_unscaled32:$addr))]>;
def LDURBi : LoadUnscaled<0b00, 1, 0b01, FPR8,  am_unscaled8, "ldur",
                          [(set FPR8:$Rt, (load am_unscaled8:$addr))]>;
def LDURHi : LoadUnscaled<0b01, 1, 0b01, FPR16, am_unscaled16, "ldur",
                          [(set (f16 FPR16:$Rt), (load am_unscaled16:$addr))]>;
def LDURSi : LoadUnscaled<0b10, 1, 0b01, FPR32, am_unscaled32, "ldur",
                          [(set (f32 FPR32:$Rt), (load am_unscaled32:$addr))]>;
def LDURDi : LoadUnscaled<0b11, 1, 0b01, FPR64, am_unscaled64, "ldur",
                          [(set (f64 FPR64:$Rt), (load am_unscaled64:$addr))]>;
def LDURQi : LoadUnscaled<0b00, 1, 0b11, FPR128, am_unscaled128, "ldur",
                          [(set (f128 FPR128:$Rt), (load am_unscaled128:$addr))]>;

def LDURHHi
    : LoadUnscaled<0b01, 0, 0b01, GPR32, am_unscaled16, "ldurh",
                   [(set GPR32:$Rt, (zextloadi16 am_unscaled16:$addr))]>;
def LDURBBi
    : LoadUnscaled<0b00, 0, 0b01, GPR32, am_unscaled8, "ldurb",
                   [(set GPR32:$Rt, (zextloadi8 am_unscaled8:$addr))]>;

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

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

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


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

// Define new assembler match classes as we want to only match these when
// the don't otherwise match the scaled addressing mode for LDR/STR. Don't
// associate a DiagnosticType either, as we want the diagnostic for the
// canonical form (the scaled operand) to take precedence.
def MemoryUnscaledFB8Operand : AsmOperandClass {
  let Name = "MemoryUnscaledFB8";
  let RenderMethod = "addMemoryUnscaledOperands";
}
def MemoryUnscaledFB16Operand : AsmOperandClass {
  let Name = "MemoryUnscaledFB16";
  let RenderMethod = "addMemoryUnscaledOperands";
}
def MemoryUnscaledFB32Operand : AsmOperandClass {
  let Name = "MemoryUnscaledFB32";
  let RenderMethod = "addMemoryUnscaledOperands";
}
def MemoryUnscaledFB64Operand : AsmOperandClass {
  let Name = "MemoryUnscaledFB64";
  let RenderMethod = "addMemoryUnscaledOperands";
}
def MemoryUnscaledFB128Operand : AsmOperandClass {
  let Name = "MemoryUnscaledFB128";
  let RenderMethod = "addMemoryUnscaledOperands";
}
def am_unscaled_fb8 : Operand<i64> {
  let ParserMatchClass = MemoryUnscaledFB8Operand;
  let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
}
def am_unscaled_fb16 : Operand<i64> {
  let ParserMatchClass = MemoryUnscaledFB16Operand;
  let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
}
def am_unscaled_fb32 : Operand<i64> {
  let ParserMatchClass = MemoryUnscaledFB32Operand;
  let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
}
def am_unscaled_fb64 : Operand<i64> {
  let ParserMatchClass = MemoryUnscaledFB64Operand;
  let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
}
def am_unscaled_fb128 : Operand<i64> {
  let ParserMatchClass = MemoryUnscaledFB128Operand;
  let MIOperandInfo = (ops GPR64sp:$base, i64imm:$offset);
}
def : InstAlias<"ldr $Rt, $addr", (LDURXi GPR64:$Rt, am_unscaled_fb64:$addr)>;
def : InstAlias<"ldr $Rt, $addr", (LDURWi GPR32:$Rt, am_unscaled_fb32:$addr)>;
def : InstAlias<"ldr $Rt, $addr", (LDURBi FPR8:$Rt, am_unscaled_fb8:$addr)>;
def : InstAlias<"ldr $Rt, $addr", (LDURHi FPR16:$Rt, am_unscaled_fb16:$addr)>;
def : InstAlias<"ldr $Rt, $addr", (LDURSi FPR32:$Rt, am_unscaled_fb32:$addr)>;
def : InstAlias<"ldr $Rt, $addr", (LDURDi FPR64:$Rt, am_unscaled_fb64:$addr)>;
def : InstAlias<"ldr $Rt, $addr", (LDURQi FPR128:$Rt, am_unscaled_fb128:$addr)>;

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

// load sign-extended half-word
def LDURSHWi
    : LoadUnscaled<0b01, 0, 0b11, GPR32, am_unscaled16, "ldursh",
                   [(set GPR32:$Rt, (sextloadi16 am_unscaled16:$addr))]>;
def LDURSHXi
    : LoadUnscaled<0b01, 0, 0b10, GPR64, am_unscaled16, "ldursh",
                   [(set GPR64:$Rt, (sextloadi16 am_unscaled16:$addr))]>;

// load sign-extended byte
def LDURSBWi
    : LoadUnscaled<0b00, 0, 0b11, GPR32, am_unscaled8, "ldursb",
                   [(set GPR32:$Rt, (sextloadi8 am_unscaled8:$addr))]>;
def LDURSBXi
    : LoadUnscaled<0b00, 0, 0b10, GPR64, am_unscaled8, "ldursb",
                   [(set GPR64:$Rt, (sextloadi8 am_unscaled8:$addr))]>;

// load sign-extended word
def LDURSWi
    : LoadUnscaled<0b10, 0, 0b10, GPR64, am_unscaled32, "ldursw",
                   [(set GPR64:$Rt, (sextloadi32 am_unscaled32:$addr))]>;

// zero and sign extending aliases from generic LDR* mnemonics to LDUR*.
def : InstAlias<"ldrb $Rt, $addr", (LDURBBi GPR32:$Rt, am_unscaled_fb8:$addr)>;
def : InstAlias<"ldrh $Rt, $addr", (LDURHHi GPR32:$Rt, am_unscaled_fb16:$addr)>;
def : InstAlias<"ldrsb $Rt, $addr", (LDURSBWi GPR32:$Rt, am_unscaled_fb8:$addr)>;
def : InstAlias<"ldrsb $Rt, $addr", (LDURSBXi GPR64:$Rt, am_unscaled_fb8:$addr)>;
def : InstAlias<"ldrsh $Rt, $addr", (LDURSHWi GPR32:$Rt, am_unscaled_fb16:$addr)>;
def : InstAlias<"ldrsh $Rt, $addr", (LDURSHXi GPR64:$Rt, am_unscaled_fb16:$addr)>;
def : InstAlias<"ldrsw $Rt, $addr", (LDURSWi GPR64:$Rt, am_unscaled_fb32:$addr)>;

// Pre-fetch.
def PRFUMi : PrefetchUnscaled<0b11, 0, 0b10, "prfum",
                               [(ARM64Prefetch imm:$Rt, am_unscaled64:$addr)]>;

//---
// (unscaled immediate, unprivileged)
def LDTRXi : LoadUnprivileged<0b11, 0, 0b01, GPR64, "ldtr">;
def LDTRWi : LoadUnprivileged<0b10, 0, 0b01, GPR32, "ldtr">;

def LDTRHi : LoadUnprivileged<0b01, 0, 0b01, GPR32, "ldtrh">;
def LDTRBi : LoadUnprivileged<0b00, 0, 0b01, GPR32, "ldtrb">;

// load sign-extended half-word
def LDTRSHWi : LoadUnprivileged<0b01, 0, 0b11, GPR32, "ldtrsh">;
def LDTRSHXi : LoadUnprivileged<0b01, 0, 0b10, GPR64, "ldtrsh">;

// load sign-extended byte
def LDTRSBWi : LoadUnprivileged<0b00, 0, 0b11, GPR32, "ldtrsb">;
def LDTRSBXi : LoadUnprivileged<0b00, 0, 0b10, GPR64, "ldtrsb">;

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

//---
// (immediate pre-indexed)
def LDRWpre : LoadPreIdx<0b10, 0, 0b01, GPR32, "ldr">;
def LDRXpre : LoadPreIdx<0b11, 0, 0b01, GPR64, "ldr">;
def LDRBpre : LoadPreIdx<0b00, 1, 0b01, FPR8,  "ldr">;
def LDRHpre : LoadPreIdx<0b01, 1, 0b01, FPR16, "ldr">;
def LDRSpre : LoadPreIdx<0b10, 1, 0b01, FPR32, "ldr">;
def LDRDpre : LoadPreIdx<0b11, 1, 0b01, FPR64, "ldr">;
def LDRQpre : LoadPreIdx<0b00, 1, 0b11, FPR128, "ldr">;

// load sign-extended half-word
def LDRSHWpre : LoadPreIdx<0b01, 0, 0b11, GPR32, "ldrsh">;
def LDRSHXpre : LoadPreIdx<0b01, 0, 0b10, GPR64, "ldrsh">;

// load sign-extended byte
def LDRSBWpre : LoadPreIdx<0b00, 0, 0b11, GPR32, "ldrsb">;
def LDRSBXpre : LoadPreIdx<0b00, 0, 0b10, GPR64, "ldrsb">;

// load zero-extended byte
def LDRBBpre : LoadPreIdx<0b00, 0, 0b01, GPR32, "ldrb">;
def LDRHHpre : LoadPreIdx<0b01, 0, 0b01, GPR32, "ldrh">;

// load sign-extended word
def LDRSWpre : LoadPreIdx<0b10, 0, 0b10, GPR64, "ldrsw">;

// ISel pseudos and patterns. See expanded comment on LoadPreIdxPseudo.
def LDRQpre_isel  : LoadPreIdxPseudo<FPR128>;
def LDRDpre_isel  : LoadPreIdxPseudo<FPR64>;
def LDRSpre_isel  : LoadPreIdxPseudo<FPR32>;
def LDRXpre_isel  : LoadPreIdxPseudo<GPR64>;
def LDRWpre_isel  : LoadPreIdxPseudo<GPR32>;
def LDRHHpre_isel : LoadPreIdxPseudo<GPR32>;
def LDRBBpre_isel : LoadPreIdxPseudo<GPR32>;

def LDRSWpre_isel : LoadPreIdxPseudo<GPR64>;
def LDRSHWpre_isel : LoadPreIdxPseudo<GPR32>;
def LDRSHXpre_isel : LoadPreIdxPseudo<GPR64>;
def LDRSBWpre_isel : LoadPreIdxPseudo<GPR32>;
def LDRSBXpre_isel : LoadPreIdxPseudo<GPR64>;

//---
// (immediate post-indexed)
def LDRWpost : LoadPostIdx<0b10, 0, 0b01, GPR32, "ldr">;
def LDRXpost : LoadPostIdx<0b11, 0, 0b01, GPR64, "ldr">;
def LDRBpost : LoadPostIdx<0b00, 1, 0b01, FPR8,  "ldr">;
def LDRHpost : LoadPostIdx<0b01, 1, 0b01, FPR16, "ldr">;
def LDRSpost : LoadPostIdx<0b10, 1, 0b01, FPR32, "ldr">;
def LDRDpost : LoadPostIdx<0b11, 1, 0b01, FPR64, "ldr">;
def LDRQpost : LoadPostIdx<0b00, 1, 0b11, FPR128, "ldr">;

// load sign-extended half-word
def LDRSHWpost : LoadPostIdx<0b01, 0, 0b11, GPR32, "ldrsh">;
def LDRSHXpost : LoadPostIdx<0b01, 0, 0b10, GPR64, "ldrsh">;

// load sign-extended byte
def LDRSBWpost : LoadPostIdx<0b00, 0, 0b11, GPR32, "ldrsb">;
def LDRSBXpost : LoadPostIdx<0b00, 0, 0b10, GPR64, "ldrsb">;

// load zero-extended byte
def LDRBBpost : LoadPostIdx<0b00, 0, 0b01, GPR32, "ldrb">;
def LDRHHpost : LoadPostIdx<0b01, 0, 0b01, GPR32, "ldrh">;

// load sign-extended word
def LDRSWpost : LoadPostIdx<0b10, 0, 0b10, GPR64, "ldrsw">;

// ISel pseudos and patterns. See expanded comment on LoadPostIdxPseudo.
def LDRQpost_isel  : LoadPostIdxPseudo<FPR128>;
def LDRDpost_isel  : LoadPostIdxPseudo<FPR64>;
def LDRSpost_isel  : LoadPostIdxPseudo<FPR32>;
def LDRXpost_isel  : LoadPostIdxPseudo<GPR64>;
def LDRWpost_isel  : LoadPostIdxPseudo<GPR32>;
def LDRHHpost_isel : LoadPostIdxPseudo<GPR32>;
def LDRBBpost_isel : LoadPostIdxPseudo<GPR32>;

def LDRSWpost_isel : LoadPostIdxPseudo<GPR64>;
def LDRSHWpost_isel : LoadPostIdxPseudo<GPR32>;
def LDRSHXpost_isel : LoadPostIdxPseudo<GPR64>;
def LDRSBWpost_isel : LoadPostIdxPseudo<GPR32>;
def LDRSBXpost_isel : LoadPostIdxPseudo<GPR64>;

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

// Pair (indexed, offset)
// FIXME: Use dedicated range-checked addressing mode operand here.
def STPWi : StorePairOffset<0b00, 0, GPR32, am_indexed32simm7, "stp">;
def STPXi : StorePairOffset<0b10, 0, GPR64, am_indexed64simm7, "stp">;
def STPSi : StorePairOffset<0b00, 1, FPR32, am_indexed32simm7, "stp">;
def STPDi : StorePairOffset<0b01, 1, FPR64, am_indexed64simm7, "stp">;
def STPQi : StorePairOffset<0b10, 1, FPR128, am_indexed128simm7, "stp">;

// Pair (pre-indexed)
def STPWpre : StorePairPreIdx<0b00, 0, GPR32, am_indexed32simm7_wb, "stp">;
def STPXpre : StorePairPreIdx<0b10, 0, GPR64, am_indexed64simm7_wb, "stp">;
def STPSpre : StorePairPreIdx<0b00, 1, FPR32, am_indexed32simm7_wb, "stp">;
def STPDpre : StorePairPreIdx<0b01, 1, FPR64, am_indexed64simm7_wb, "stp">;
def STPQpre : StorePairPreIdx<0b10, 1, FPR128, am_indexed128simm7_wb, "stp">;

// Pair (pre-indexed)
def STPWpost : StorePairPostIdx<0b00, 0, GPR32, simm7s4, "stp">;
def STPXpost : StorePairPostIdx<0b10, 0, GPR64, simm7s8, "stp">;
def STPSpost : StorePairPostIdx<0b00, 1, FPR32, simm7s4, "stp">;
def STPDpost : StorePairPostIdx<0b01, 1, FPR64, simm7s8, "stp">;
def STPQpost : StorePairPostIdx<0b10, 1, FPR128, simm7s16, "stp">;

// Pair (no allocate)
def STNPWi : StorePairNoAlloc<0b00, 0, GPR32, am_indexed32simm7, "stnp">;
def STNPXi : StorePairNoAlloc<0b10, 0, GPR64, am_indexed64simm7, "stnp">;
def STNPSi : StorePairNoAlloc<0b00, 1, FPR32, am_indexed32simm7, "stnp">;
def STNPDi : StorePairNoAlloc<0b01, 1, FPR64, am_indexed64simm7, "stnp">;
def STNPQi : StorePairNoAlloc<0b10, 1, FPR128, am_indexed128simm7, "stnp">;

//---
// (Register offset)

let AddedComplexity = 10 in {

// Integer
def STRHHro : Store16RO<0b01, 0, 0b00, GPR32, "strh",
                            [(truncstorei16 GPR32:$Rt, ro_indexed16:$addr)]>;
def STRBBro : Store8RO<0b00,  0, 0b00, GPR32, "strb",
                            [(truncstorei8 GPR32:$Rt, ro_indexed8:$addr)]>;
def STRWro  : Store32RO<0b10,   0, 0b00, GPR32, "str",
                            [(store GPR32:$Rt, ro_indexed32:$addr)]>;
def STRXro  : Store64RO<0b11,   0, 0b00, GPR64, "str",
                            [(store GPR64:$Rt, ro_indexed64:$addr)]>;

// truncstore i64
def : Pat<(truncstorei8 GPR64:$Rt, ro_indexed8:$addr),
           (STRBBro (EXTRACT_SUBREG GPR64:$Rt, sub_32), ro_indexed8:$addr)>;
def : Pat<(truncstorei16 GPR64:$Rt, ro_indexed16:$addr),
           (STRHHro (EXTRACT_SUBREG GPR64:$Rt, sub_32), ro_indexed16:$addr)>;
def : Pat<(truncstorei32 GPR64:$Rt, ro_indexed32:$addr),
           (STRWro (EXTRACT_SUBREG GPR64:$Rt, sub_32), ro_indexed32:$addr)>;


// Floating-point
def STRBro : Store8RO<0b00,  1, 0b00, FPR8,  "str",
                            [(store FPR8:$Rt, ro_indexed8:$addr)]>;
def STRHro : Store16RO<0b01, 1, 0b00, FPR16, "str",
                            [(store (f16 FPR16:$Rt), ro_indexed16:$addr)]>;
def STRSro : Store32RO<0b10,   1, 0b00, FPR32, "str",
                            [(store (f32 FPR32:$Rt), ro_indexed32:$addr)]>;
def STRDro : Store64RO<0b11,   1, 0b00, FPR64, "str",
                            [(store (f64 FPR64:$Rt), ro_indexed64:$addr)]>;
def STRQro : Store128RO<0b00,   1, 0b10, FPR128, "str", []> {
  let mayStore = 1;
}

// Match all store 64 bits width whose type is compatible with FPR64
let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  def : Pat<(store (v2f32 FPR64:$Rn), ro_indexed64:$addr),
            (STRDro FPR64:$Rn, ro_indexed64:$addr)>;
  def : Pat<(store (v8i8 FPR64:$Rn), ro_indexed64:$addr),
            (STRDro FPR64:$Rn, ro_indexed64:$addr)>;
  def : Pat<(store (v4i16 FPR64:$Rn), ro_indexed64:$addr),
            (STRDro FPR64:$Rn, ro_indexed64:$addr)>;
  def : Pat<(store (v2i32 FPR64:$Rn), ro_indexed64:$addr),
            (STRDro FPR64:$Rn, ro_indexed64:$addr)>;
}
def : Pat<(store (v1f64 FPR64:$Rn), ro_indexed64:$addr),
          (STRDro FPR64:$Rn, ro_indexed64:$addr)>;
def : Pat<(store (v1i64 FPR64:$Rn), ro_indexed64:$addr),
          (STRDro FPR64:$Rn, ro_indexed64:$addr)>;

// Match all store 128 bits width whose type is compatible with FPR128
let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  def : Pat<(store (v4f32 FPR128:$Rn), ro_indexed128:$addr),
            (STRQro FPR128:$Rn, ro_indexed128:$addr)>;
  def : Pat<(store (v2f64 FPR128:$Rn), ro_indexed128:$addr),
            (STRQro FPR128:$Rn, ro_indexed128:$addr)>;
  def : Pat<(store (v16i8 FPR128:$Rn), ro_indexed128:$addr),
            (STRQro FPR128:$Rn, ro_indexed128:$addr)>;
  def : Pat<(store (v8i16 FPR128:$Rn), ro_indexed128:$addr),
            (STRQro FPR128:$Rn, ro_indexed128:$addr)>;
  def : Pat<(store (v4i32 FPR128:$Rn), ro_indexed128:$addr),
            (STRQro FPR128:$Rn, ro_indexed128:$addr)>;
  def : Pat<(store (v2i64 FPR128:$Rn), ro_indexed128:$addr),
            (STRQro FPR128:$Rn, ro_indexed128:$addr)>;
}
def : Pat<(store (f128 FPR128:$Rn),  ro_indexed128:$addr),
          (STRQro FPR128:$Rn, ro_indexed128:$addr)>;

//---
// (unsigned immediate)
def STRXui : StoreUI<0b11, 0, 0b00, GPR64, am_indexed64, "str",
                     [(store GPR64:$Rt, am_indexed64:$addr)]>;
def STRWui : StoreUI<0b10, 0, 0b00, GPR32, am_indexed32, "str",
                     [(store GPR32:$Rt, am_indexed32:$addr)]>;
def STRBui : StoreUI<0b00, 1, 0b00, FPR8, am_indexed8, "str",
                     [(store FPR8:$Rt, am_indexed8:$addr)]>;
def STRHui : StoreUI<0b01, 1, 0b00, FPR16, am_indexed16, "str",
                     [(store (f16 FPR16:$Rt), am_indexed16:$addr)]>;
def STRSui : StoreUI<0b10, 1, 0b00, FPR32, am_indexed32, "str",
                     [(store (f32 FPR32:$Rt), am_indexed32:$addr)]>;
def STRDui : StoreUI<0b11, 1, 0b00, FPR64, am_indexed64, "str",
                     [(store (f64 FPR64:$Rt), am_indexed64:$addr)]>;
def STRQui : StoreUI<0b00, 1, 0b10, FPR128, am_indexed128, "str", []> {
  let mayStore = 1;
}

// Match all store 64 bits width whose type is compatible with FPR64
let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  def : Pat<(store (v2f32 FPR64:$Rn), am_indexed64:$addr),
            (STRDui FPR64:$Rn, am_indexed64:$addr)>;
  def : Pat<(store (v8i8 FPR64:$Rn), am_indexed64:$addr),
            (STRDui FPR64:$Rn, am_indexed64:$addr)>;
  def : Pat<(store (v4i16 FPR64:$Rn), am_indexed64:$addr),
            (STRDui FPR64:$Rn, am_indexed64:$addr)>;
  def : Pat<(store (v2i32 FPR64:$Rn), am_indexed64:$addr),
            (STRDui FPR64:$Rn, am_indexed64:$addr)>;
}
def : Pat<(store (v1f64 FPR64:$Rn), am_indexed64:$addr),
          (STRDui FPR64:$Rn, am_indexed64:$addr)>;
def : Pat<(store (v1i64 FPR64:$Rn), am_indexed64:$addr),
          (STRDui FPR64:$Rn, am_indexed64:$addr)>;

// Match all store 128 bits width whose type is compatible with FPR128
let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  def : Pat<(store (v4f32 FPR128:$Rn), am_indexed128:$addr),
            (STRQui FPR128:$Rn, am_indexed128:$addr)>;
  def : Pat<(store (v2f64 FPR128:$Rn), am_indexed128:$addr),
            (STRQui FPR128:$Rn, am_indexed128:$addr)>;
  def : Pat<(store (v16i8 FPR128:$Rn), am_indexed128:$addr),
            (STRQui FPR128:$Rn, am_indexed128:$addr)>;
  def : Pat<(store (v8i16 FPR128:$Rn), am_indexed128:$addr),
            (STRQui FPR128:$Rn, am_indexed128:$addr)>;
  def : Pat<(store (v4i32 FPR128:$Rn), am_indexed128:$addr),
            (STRQui FPR128:$Rn, am_indexed128:$addr)>;
  def : Pat<(store (v2i64 FPR128:$Rn), am_indexed128:$addr),
            (STRQui FPR128:$Rn, am_indexed128:$addr)>;
}
def : Pat<(store (f128  FPR128:$Rn), am_indexed128:$addr),
          (STRQui FPR128:$Rn, am_indexed128:$addr)>;

def STRHHui : StoreUI<0b01, 0, 0b00, GPR32, am_indexed16, "strh",
                      [(truncstorei16 GPR32:$Rt, am_indexed16:$addr)]>;
def STRBBui : StoreUI<0b00, 0, 0b00, GPR32, am_indexed8,  "strb",
                      [(truncstorei8 GPR32:$Rt, am_indexed8:$addr)]>;

// truncstore i64
def : Pat<(truncstorei32 GPR64:$Rt, am_indexed32:$addr),
  (STRWui (EXTRACT_SUBREG GPR64:$Rt, sub_32), am_indexed32:$addr)>;
def : Pat<(truncstorei16 GPR64:$Rt, am_indexed16:$addr),
  (STRHHui (EXTRACT_SUBREG GPR64:$Rt, sub_32), am_indexed16:$addr)>;
def : Pat<(truncstorei8 GPR64:$Rt, am_indexed8:$addr),
  (STRBBui (EXTRACT_SUBREG GPR64:$Rt, sub_32), am_indexed8:$addr)>;

} // AddedComplexity = 10

//---
// (unscaled immediate)
def STURXi : StoreUnscaled<0b11, 0, 0b00, GPR64, am_unscaled64, "stur",
                           [(store GPR64:$Rt, am_unscaled64:$addr)]>;
def STURWi : StoreUnscaled<0b10, 0, 0b00, GPR32, am_unscaled32, "stur",
                           [(store GPR32:$Rt, am_unscaled32:$addr)]>;
def STURBi : StoreUnscaled<0b00, 1, 0b00, FPR8,  am_unscaled8, "stur",
                           [(store FPR8:$Rt, am_unscaled8:$addr)]>;
def STURHi : StoreUnscaled<0b01, 1, 0b00, FPR16, am_unscaled16, "stur",
                           [(store (f16 FPR16:$Rt), am_unscaled16:$addr)]>;
def STURSi : StoreUnscaled<0b10, 1, 0b00, FPR32, am_unscaled32, "stur",
                           [(store (f32 FPR32:$Rt), am_unscaled32:$addr)]>;
def STURDi : StoreUnscaled<0b11, 1, 0b00, FPR64, am_unscaled64, "stur",
                           [(store (f64 FPR64:$Rt), am_unscaled64:$addr)]>;
def STURQi : StoreUnscaled<0b00, 1, 0b10, FPR128, am_unscaled128, "stur",
                           [(store (f128 FPR128:$Rt), am_unscaled128:$addr)]>;
def STURHHi : StoreUnscaled<0b01, 0, 0b00, GPR32, am_unscaled16, "sturh",
                            [(truncstorei16 GPR32:$Rt, am_unscaled16:$addr)]>;
def STURBBi : StoreUnscaled<0b00, 0, 0b00, GPR32, am_unscaled8, "sturb",
                            [(truncstorei8 GPR32:$Rt, am_unscaled8:$addr)]>;

// Match all store 64 bits width whose type is compatible with FPR64
let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  def : Pat<(store (v2f32 FPR64:$Rn), am_unscaled64:$addr),
            (STURDi FPR64:$Rn, am_unscaled64:$addr)>;
  def : Pat<(store (v8i8 FPR64:$Rn), am_unscaled64:$addr),
            (STURDi FPR64:$Rn, am_unscaled64:$addr)>;
  def : Pat<(store (v4i16 FPR64:$Rn), am_unscaled64:$addr),
            (STURDi FPR64:$Rn, am_unscaled64:$addr)>;
  def : Pat<(store (v2i32 FPR64:$Rn), am_unscaled64:$addr),
            (STURDi FPR64:$Rn, am_unscaled64:$addr)>;
}
def : Pat<(store (v1f64 FPR64:$Rn), am_unscaled64:$addr),
          (STURDi FPR64:$Rn, am_unscaled64:$addr)>;
def : Pat<(store (v1i64 FPR64:$Rn), am_unscaled64:$addr),
          (STURDi FPR64:$Rn, am_unscaled64:$addr)>;

// Match all store 128 bits width whose type is compatible with FPR128
let Predicates = [IsLE] in {
  // We must use ST1 to store vectors in big-endian.
  def : Pat<(store (v4f32 FPR128:$Rn), am_unscaled128:$addr),
            (STURQi FPR128:$Rn, am_unscaled128:$addr)>;
  def : Pat<(store (v2f64 FPR128:$Rn), am_unscaled128:$addr),
            (STURQi FPR128:$Rn, am_unscaled128:$addr)>;
  def : Pat<(store (v16i8 FPR128:$Rn), am_unscaled128:$addr),
            (STURQi FPR128:$Rn, am_unscaled128:$addr)>;
  def : Pat<(store (v8i16 FPR128:$Rn), am_unscaled128:$addr),
            (STURQi FPR128:$Rn, am_unscaled128:$addr)>;
  def : Pat<(store (v4i32 FPR128:$Rn), am_unscaled128:$addr),
            (STURQi FPR128:$Rn, am_unscaled128:$addr)>;
  def : Pat<(store (v2i64 FPR128:$Rn), am_unscaled128:$addr),
            (STURQi FPR128:$Rn, am_unscaled128:$addr)>;
  def : Pat<(store (v2f64 FPR128:$Rn), am_unscaled128:$addr),
            (STURQi FPR128:$Rn, am_unscaled128:$addr)>;
}

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

//---
// STR mnemonics fall back to STUR for negative or unaligned offsets.
def : InstAlias<"str $Rt, $addr", (STURXi GPR64:$Rt, am_unscaled_fb64:$addr)>;
def : InstAlias<"str $Rt, $addr", (STURWi GPR32:$Rt, am_unscaled_fb32:$addr)>;
def : InstAlias<"str $Rt, $addr", (STURBi FPR8:$Rt, am_unscaled_fb8:$addr)>;
def : InstAlias<"str $Rt, $addr", (STURHi FPR16:$Rt, am_unscaled_fb16:$addr)>;
def : InstAlias<"str $Rt, $addr", (STURSi FPR32:$Rt, am_unscaled_fb32:$addr)>;
def : InstAlias<"str $Rt, $addr", (STURDi FPR64:$Rt, am_unscaled_fb64:$addr)>;
def : InstAlias<"str $Rt, $addr", (STURQi FPR128:$Rt, am_unscaled_fb128:$addr)>;

def : InstAlias<"strb $Rt, $addr", (STURBBi GPR32:$Rt, am_unscaled_fb8:$addr)>;
def : InstAlias<"strh $Rt, $addr", (STURHHi GPR32:$Rt, am_unscaled_fb16:$addr)>;

//---
// (unscaled immediate, unprivileged)
def STTRWi : StoreUnprivileged<0b10, 0, 0b00, GPR32, "sttr">;
def STTRXi : StoreUnprivileged<0b11, 0, 0b00, GPR64, "sttr">;

def STTRHi : StoreUnprivileged<0b01, 0, 0b00, GPR32, "sttrh">;
def STTRBi : StoreUnprivileged<0b00, 0, 0b00, GPR32, "sttrb">;

//---
// (immediate pre-indexed)
def STRWpre : StorePreIdx<0b10, 0, 0b00, GPR32, "str">;
def STRXpre : StorePreIdx<0b11, 0, 0b00, GPR64, "str">;
def STRBpre : StorePreIdx<0b00, 1, 0b00, FPR8,  "str">;
def STRHpre : StorePreIdx<0b01, 1, 0b00, FPR16, "str">;
def STRSpre : StorePreIdx<0b10, 1, 0b00, FPR32, "str">;
def STRDpre : StorePreIdx<0b11, 1, 0b00, FPR64, "str">;
def STRQpre : StorePreIdx<0b00, 1, 0b10, FPR128, "str">;

def STRBBpre : StorePreIdx<0b00, 0, 0b00, GPR32, "strb">;
def STRHHpre : StorePreIdx<0b01, 0, 0b00, GPR32, "strh">;

// ISel pseudos and patterns. See expanded comment on StorePreIdxPseudo.
defm STRQpre : StorePreIdxPseudo<FPR128, f128, pre_store>;
defm STRDpre : StorePreIdxPseudo<FPR64, f64, pre_store>;
defm STRSpre : StorePreIdxPseudo<FPR32, f32, pre_store>;
defm STRXpre : StorePreIdxPseudo<GPR64, i64, pre_store>;
defm STRWpre : StorePreIdxPseudo<GPR32, i32, pre_store>;
defm STRHHpre : StorePreIdxPseudo<GPR32, i32, pre_truncsti16>;
defm STRBBpre : StorePreIdxPseudo<GPR32, i32, pre_truncsti8>;
// truncstore i64
def : Pat<(pre_truncsti32 GPR64:$Rt, am_noindex:$addr, simm9:$off),
  (STRWpre_isel (EXTRACT_SUBREG GPR64:$Rt, sub_32), am_noindex:$addr,
                  simm9:$off)>;
def : Pat<(pre_truncsti16 GPR64:$Rt, am_noindex:$addr, simm9:$off),
  (STRHHpre_isel (EXTRACT_SUBREG GPR64:$Rt, sub_32), am_noindex:$addr,
                  simm9:$off)>;
def : Pat<(pre_truncsti8 GPR64:$Rt, am_noindex:$addr, simm9:$off),
  (STRBBpre_isel (EXTRACT_SUBREG GPR64:$Rt, sub_32), am_noindex:$addr,
                  simm9:$off)>;

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

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

//---
// (immediate post-indexed)
def STRWpost : StorePostIdx<0b10, 0, 0b00, GPR32, "str">;
def STRXpost : StorePostIdx<0b11, 0, 0b00, GPR64, "str">;
def STRBpost : StorePostIdx<0b00, 1, 0b00, FPR8,  "str">;
def STRHpost : StorePostIdx<0b01, 1, 0b00, FPR16, "str">;
def STRSpost : StorePostIdx<0b10, 1, 0b00, FPR32, "str">;
def STRDpost : StorePostIdx<0b11, 1, 0b00, FPR64, "str">;
def STRQpost : StorePostIdx<0b00, 1, 0b10, FPR128, "str">;

def STRBBpost : StorePostIdx<0b00, 0, 0b00, GPR32, "strb">;
def STRHHpost : StorePostIdx<0b01, 0, 0b00, GPR32, "strh">;

// ISel pseudos and patterns. See expanded comment on StorePostIdxPseudo.
defm STRQpost : StorePostIdxPseudo<FPR128, f128, post_store, STRQpost>;
defm STRDpost : StorePostIdxPseudo<FPR64, f64, post_store, STRDpost>;
defm STRSpost : StorePostIdxPseudo<FPR32, f32, post_store, STRSpost>;
defm STRXpost : StorePostIdxPseudo<GPR64, i64, post_store, STRXpost>;
defm STRWpost : StorePostIdxPseudo<GPR32, i32, post_store, STRWpost>;
defm STRHHpost : StorePostIdxPseudo<GPR32, i32, post_truncsti16, STRHHpost>;
defm STRBBpost : StorePostIdxPseudo<GPR32, i32, post_truncsti8, STRBBpost>;
// truncstore i64
def : Pat<(post_truncsti32 GPR64:$Rt, am_noindex:$addr, simm9:$off),
  (STRWpost_isel (EXTRACT_SUBREG GPR64:$Rt, sub_32), am_noindex:$addr,
                  simm9:$off)>;
def : Pat<(post_truncsti16 GPR64:$Rt, am_noindex:$addr, simm9:$off),
  (STRHHpost_isel (EXTRACT_SUBREG GPR64:$Rt, sub_32), am_noindex:$addr,
                  simm9:$off)>;
def : Pat<(post_truncsti8 GPR64:$Rt, am_noindex:$addr, simm9:$off),
  (STRBBpost_isel (EXTRACT_SUBREG GPR64:$Rt, sub_32), am_noindex:$addr,
                  simm9:$off)>;

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

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

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

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

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

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

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

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

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

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

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

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

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

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

defm FCVTAS : FPToIntegerUnscaled<0b00, 0b100, "fcvtas", int_arm64_neon_fcvtas>;
defm FCVTAU : FPToIntegerUnscaled<0b00, 0b101, "fcvtau", int_arm64_neon_fcvtau>;
defm FCVTMS : FPToIntegerUnscaled<0b10, 0b000, "fcvtms", int_arm64_neon_fcvtms>;
defm FCVTMU : FPToIntegerUnscaled<0b10, 0b001, "fcvtmu", int_arm64_neon_fcvtmu>;
defm FCVTNS : FPToIntegerUnscaled<0b00, 0b000, "fcvtns", int_arm64_neon_fcvtns>;
defm FCVTNU : FPToIntegerUnscaled<0b00, 0b001, "fcvtnu", int_arm64_neon_fcvtnu>;
defm FCVTPS : FPToIntegerUnscaled<0b01, 0b000, "fcvtps", int_arm64_neon_fcvtps>;
defm FCVTPU : FPToIntegerUnscaled<0b01, 0b001, "fcvtpu", int_arm64_neon_fcvtpu>;
defm FCVTZS : FPToIntegerUnscaled<0b11, 0b000, "fcvtzs", fp_to_sint>;
defm FCVTZU : FPToIntegerUnscaled<0b11, 0b001, "fcvtzu", fp_to_uint>;
defm FCVTZS : FPToIntegerScaled<0b11, 0b000, "fcvtzs", fp_to_sint>;
defm FCVTZU : FPToIntegerScaled<0b11, 0b001, "fcvtzu", fp_to_uint>;
let isCodeGenOnly = 1 in {
defm FCVTZS_Int : FPToIntegerUnscaled<0b11, 0b000, "fcvtzs", int_arm64_neon_fcvtzs>;
defm FCVTZU_Int : FPToIntegerUnscaled<0b11, 0b001, "fcvtzu", int_arm64_neon_fcvtzu>;
defm FCVTZS_Int : FPToIntegerScaled<0b11, 0b000, "fcvtzs", int_arm64_neon_fcvtzs>;
defm FCVTZU_Int : FPToIntegerScaled<0b11, 0b001, "fcvtzu", int_arm64_neon_fcvtzu>;
}

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

defm SCVTF : IntegerToFP<0, "scvtf", sint_to_fp>;
defm UCVTF : IntegerToFP<1, "ucvtf", uint_to_fp>;

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

defm FMOV : UnscaledConversion<"fmov">;

def : Pat<(f32 (fpimm0)), (FMOVWSr WZR)>, Requires<[NoZCZ]>;
def : Pat<(f64 (fpimm0)), (FMOVXDr XZR)>, Requires<[NoZCZ]>;

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

defm FCVT : FPConversion<"fcvt">;

def : Pat<(f32_to_f16 FPR32:$Rn),
          (i32 (COPY_TO_REGCLASS
                   (f32 (SUBREG_TO_REG (i32 0), (FCVTHSr FPR32:$Rn), hsub)),
                   GPR32))>;

def FCVTSHpseudo : Pseudo<(outs FPR32:$Rd), (ins FPR32:$Rn),
                          [(set (f32 FPR32:$Rd), (f16_to_f32 i32:$Rn))]>;

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

defm FABS   : SingleOperandFPData<0b0001, "fabs", fabs>;
defm FMOV   : SingleOperandFPData<0b0000, "fmov">;
defm FNEG   : SingleOperandFPData<0b0010, "fneg", fneg>;
defm FRINTA : SingleOperandFPData<0b1100, "frinta", frnd>;
defm FRINTI : SingleOperandFPData<0b1111, "frinti", fnearbyint>;
defm FRINTM : SingleOperandFPData<0b1010, "frintm", ffloor>;
defm FRINTN : SingleOperandFPData<0b1000, "frintn", int_arm64_neon_frintn>;
defm FRINTP : SingleOperandFPData<0b1001, "frintp", fceil>;

def : Pat<(v1f64 (int_arm64_neon_frintn (v1f64 FPR64:$Rn))),
          (FRINTNDr FPR64:$Rn)>;

// FRINTX is inserted to set the flags as required by FENV_ACCESS ON behavior
// in the C spec. Setting hasSideEffects ensures it is not DCE'd.
// <rdar://problem/13715968>
// TODO: We should really model the FPSR flags correctly. This is really ugly.
let hasSideEffects = 1 in {
defm FRINTX : SingleOperandFPData<0b1110, "frintx", frint>;
}

defm FRINTZ : SingleOperandFPData<0b1011, "frintz", ftrunc>;

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

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

defm FADD   : TwoOperandFPData<0b0010, "fadd", fadd>;
let SchedRW = [WriteFDiv] in {
defm FDIV   : TwoOperandFPData<0b0001, "fdiv", fdiv>;
}
defm FMAXNM : TwoOperandFPData<0b0110, "fmaxnm", int_arm64_neon_fmaxnm>;
defm FMAX   : TwoOperandFPData<0b0100, "fmax", ARM64fmax>;
defm FMINNM : TwoOperandFPData<0b0111, "fminnm", int_arm64_neon_fminnm>;
defm FMIN   : TwoOperandFPData<0b0101, "fmin", ARM64fmin>;
let SchedRW = [WriteFMul] in {
defm FMUL   : TwoOperandFPData<0b0000, "fmul", fmul>;
defm FNMUL  : TwoOperandFPDataNeg<0b1000, "fnmul", fmul>;
}
defm FSUB   : TwoOperandFPData<0b0011, "fsub", fsub>;

def : Pat<(v1f64 (ARM64fmax (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
          (FMAXDrr FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(v1f64 (ARM64fmin (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
          (FMINDrr FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(v1f64 (int_arm64_neon_fmaxnm (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
          (FMAXNMDrr FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(v1f64 (int_arm64_neon_fminnm (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
          (FMINNMDrr FPR64:$Rn, FPR64:$Rm)>;

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

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

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

// N.b. FMSUB etc have the accumulator at the *end* of (outs), unlike
// the NEON variant.
def : Pat<(f32 (fma (fneg FPR32:$Rn), FPR32:$Rm, FPR32:$Ra)),
          (FMSUBSrrr FPR32:$Rn, FPR32:$Rm, FPR32:$Ra)>;

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

// We handled -(a + b*c) for FNMADD above, now it's time for "(-a) + (-b)*c" and
// "(-a) + b*(-c)".
def : Pat<(f32 (fma (fneg FPR32:$Rn), FPR32:$Rm, (fneg FPR32:$Ra))),
          (FNMADDSrrr FPR32:$Rn, FPR32:$Rm, FPR32:$Ra)>;

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

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

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

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

defm FCMPE : FPComparison<1, "fcmpe">;
defm FCMP  : FPComparison<0, "fcmp", ARM64fcmp>;

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

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

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

defm FCSEL : FPCondSelect<"fcsel">;

// CSEL instructions providing f128 types need to be handled by a
// pseudo-instruction since the eventual code will need to introduce basic
// blocks and control flow.
def F128CSEL : Pseudo<(outs FPR128:$Rd),
                      (ins FPR128:$Rn, FPR128:$Rm, ccode:$cond),
                      [(set (f128 FPR128:$Rd),
                            (ARM64csel FPR128:$Rn, FPR128:$Rm,
                                       (i32 imm:$cond), NZCV))]> {
  let Uses = [NZCV];
  let usesCustomInserter = 1;
}


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

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

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

defm ABS    : SIMDTwoVectorBHSD<0, 0b01011, "abs", int_arm64_neon_abs>;
defm CLS    : SIMDTwoVectorBHS<0, 0b00100, "cls", int_arm64_neon_cls>;
defm CLZ    : SIMDTwoVectorBHS<1, 0b00100, "clz", ctlz>;
defm CMEQ   : SIMDCmpTwoVector<0, 0b01001, "cmeq", ARM64cmeqz>;
defm CMGE   : SIMDCmpTwoVector<1, 0b01000, "cmge", ARM64cmgez>;
defm CMGT   : SIMDCmpTwoVector<0, 0b01000, "cmgt", ARM64cmgtz>;
defm CMLE   : SIMDCmpTwoVector<1, 0b01001, "cmle", ARM64cmlez>;
defm CMLT   : SIMDCmpTwoVector<0, 0b01010, "cmlt", ARM64cmltz>;
defm CNT    : SIMDTwoVectorB<0, 0b00, 0b00101, "cnt", ctpop>;
defm FABS   : SIMDTwoVectorFP<0, 1, 0b01111, "fabs", fabs>;

defm FCMEQ  : SIMDFPCmpTwoVector<0, 1, 0b01101, "fcmeq", ARM64fcmeqz>;
defm FCMGE  : SIMDFPCmpTwoVector<1, 1, 0b01100, "fcmge", ARM64fcmgez>;
defm FCMGT  : SIMDFPCmpTwoVector<0, 1, 0b01100, "fcmgt", ARM64fcmgtz>;
defm FCMLE  : SIMDFPCmpTwoVector<1, 1, 0b01101, "fcmle", ARM64fcmlez>;
defm FCMLT  : SIMDFPCmpTwoVector<0, 1, 0b01110, "fcmlt", ARM64fcmltz>;
defm FCVTAS : SIMDTwoVectorFPToInt<0,0,0b11100, "fcvtas",int_arm64_neon_fcvtas>;
defm FCVTAU : SIMDTwoVectorFPToInt<1,0,0b11100, "fcvtau",int_arm64_neon_fcvtau>;
defm FCVTL  : SIMDFPWidenTwoVector<0, 0, 0b10111, "fcvtl">;
def : Pat<(v4f32 (int_arm64_neon_vcvthf2fp (v4i16 V64:$Rn))),
          (FCVTLv4i16 V64:$Rn)>;
def : Pat<(v4f32 (int_arm64_neon_vcvthf2fp (extract_subvector (v8i16 V128:$Rn),
                                                              (i64 4)))),
          (FCVTLv8i16 V128:$Rn)>;
def : Pat<(v2f64 (fextend (v2f32 V64:$Rn))), (FCVTLv2i32 V64:$Rn)>;
def : Pat<(v2f64 (fextend (v2f32 (extract_subvector (v4f32 V128:$Rn),
                                                    (i64 2))))),
          (FCVTLv4i32 V128:$Rn)>;

defm FCVTMS : SIMDTwoVectorFPToInt<0,0,0b11011, "fcvtms",int_arm64_neon_fcvtms>;
defm FCVTMU : SIMDTwoVectorFPToInt<1,0,0b11011, "fcvtmu",int_arm64_neon_fcvtmu>;
defm FCVTNS : SIMDTwoVectorFPToInt<0,0,0b11010, "fcvtns",int_arm64_neon_fcvtns>;
defm FCVTNU : SIMDTwoVectorFPToInt<1,0,0b11010, "fcvtnu",int_arm64_neon_fcvtnu>;
defm FCVTN  : SIMDFPNarrowTwoVector<0, 0, 0b10110, "fcvtn">;
def : Pat<(v4i16 (int_arm64_neon_vcvtfp2hf (v4f32 V128:$Rn))),
          (FCVTNv4i16 V128:$Rn)>;
def : Pat<(concat_vectors V64:$Rd,
                          (v4i16 (int_arm64_neon_vcvtfp2hf (v4f32 V128:$Rn)))),
          (FCVTNv8i16 (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub), V128:$Rn)>;
def : Pat<(v2f32 (fround (v2f64 V128:$Rn))), (FCVTNv2i32 V128:$Rn)>;
def : Pat<(concat_vectors V64:$Rd, (v2f32 (fround (v2f64 V128:$Rn)))),
          (FCVTNv4i32 (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub), V128:$Rn)>;
defm FCVTPS : SIMDTwoVectorFPToInt<0,1,0b11010, "fcvtps",int_arm64_neon_fcvtps>;
defm FCVTPU : SIMDTwoVectorFPToInt<1,1,0b11010, "fcvtpu",int_arm64_neon_fcvtpu>;
defm FCVTXN : SIMDFPInexactCvtTwoVector<1, 0, 0b10110, "fcvtxn",
                                        int_arm64_neon_fcvtxn>;
defm FCVTZS : SIMDTwoVectorFPToInt<0, 1, 0b11011, "fcvtzs", fp_to_sint>;
defm FCVTZU : SIMDTwoVectorFPToInt<1, 1, 0b11011, "fcvtzu", fp_to_uint>;
let isCodeGenOnly = 1 in {
defm FCVTZS_Int : SIMDTwoVectorFPToInt<0, 1, 0b11011, "fcvtzs",
                                       int_arm64_neon_fcvtzs>;
defm FCVTZU_Int : SIMDTwoVectorFPToInt<1, 1, 0b11011, "fcvtzu",
                                       int_arm64_neon_fcvtzu>;
}
defm FNEG   : SIMDTwoVectorFP<1, 1, 0b01111, "fneg", fneg>;
defm FRECPE : SIMDTwoVectorFP<0, 1, 0b11101, "frecpe", int_arm64_neon_frecpe>;
defm FRINTA : SIMDTwoVectorFP<1, 0, 0b11000, "frinta", frnd>;
defm FRINTI : SIMDTwoVectorFP<1, 1, 0b11001, "frinti", fnearbyint>;
defm FRINTM : SIMDTwoVectorFP<0, 0, 0b11001, "frintm", ffloor>;
defm FRINTN : SIMDTwoVectorFP<0, 0, 0b11000, "frintn", int_arm64_neon_frintn>;
defm FRINTP : SIMDTwoVectorFP<0, 1, 0b11000, "frintp", fceil>;
defm FRINTX : SIMDTwoVectorFP<1, 0, 0b11001, "frintx", frint>;
defm FRINTZ : SIMDTwoVectorFP<0, 1, 0b11001, "frintz", ftrunc>;
defm FRSQRTE: SIMDTwoVectorFP<1, 1, 0b11101, "frsqrte", int_arm64_neon_frsqrte>;
defm FSQRT  : SIMDTwoVectorFP<1, 1, 0b11111, "fsqrt", fsqrt>;
defm NEG    : SIMDTwoVectorBHSD<1, 0b01011, "neg",
                               UnOpFrag<(sub immAllZerosV, node:$LHS)> >;
defm NOT    : SIMDTwoVectorB<1, 0b00, 0b00101, "not", vnot>;
// Aliases for MVN -> NOT.
def : InstAlias<"mvn.8b $Vd, $Vn", (NOTv8i8 V64:$Vd, V64:$Vn)>;
def : InstAlias<"mvn.16b $Vd, $Vn", (NOTv16i8 V128:$Vd, V128:$Vn)>;
def : InstAlias<"mvn $Vd.8b, $Vn.8b", (NOTv8i8 V64:$Vd, V64:$Vn)>;
def : InstAlias<"mvn $Vd.16b, $Vn.16b", (NOTv16i8 V128:$Vd, V128:$Vn)>;

def : Pat<(ARM64neg (v8i8  V64:$Rn)),  (NEGv8i8  V64:$Rn)>;
def : Pat<(ARM64neg (v16i8 V128:$Rn)), (NEGv16i8 V128:$Rn)>;
def : Pat<(ARM64neg (v4i16 V64:$Rn)),  (NEGv4i16 V64:$Rn)>;
def : Pat<(ARM64neg (v8i16 V128:$Rn)), (NEGv8i16 V128:$Rn)>;
def : Pat<(ARM64neg (v2i32 V64:$Rn)),  (NEGv2i32 V64:$Rn)>;
def : Pat<(ARM64neg (v4i32 V128:$Rn)), (NEGv4i32 V128:$Rn)>;
def : Pat<(ARM64neg (v2i64 V128:$Rn)), (NEGv2i64 V128:$Rn)>;

def : Pat<(ARM64not (v8i8 V64:$Rn)),   (NOTv8i8  V64:$Rn)>;
def : Pat<(ARM64not (v16i8 V128:$Rn)), (NOTv16i8 V128:$Rn)>;
def : Pat<(ARM64not (v4i16 V64:$Rn)),  (NOTv8i8  V64:$Rn)>;
def : Pat<(ARM64not (v8i16 V128:$Rn)), (NOTv16i8 V128:$Rn)>;
def : Pat<(ARM64not (v2i32 V64:$Rn)),  (NOTv8i8  V64:$Rn)>;
def : Pat<(ARM64not (v1i64 V64:$Rn)),  (NOTv8i8  V64:$Rn)>;
def : Pat<(ARM64not (v4i32 V128:$Rn)), (NOTv16i8 V128:$Rn)>;
def : Pat<(ARM64not (v2i64 V128:$Rn)), (NOTv16i8 V128:$Rn)>;

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

defm RBIT   : SIMDTwoVectorB<1, 0b01, 0b00101, "rbit", int_arm64_neon_rbit>;
defm REV16  : SIMDTwoVectorB<0, 0b00, 0b00001, "rev16", ARM64rev16>;
defm REV32  : SIMDTwoVectorBH<1, 0b00000, "rev32", ARM64rev32>;
defm REV64  : SIMDTwoVectorBHS<0, 0b00000, "rev64", ARM64rev64>;
defm SADALP : SIMDLongTwoVectorTied<0, 0b00110, "sadalp",
       BinOpFrag<(add node:$LHS, (int_arm64_neon_saddlp node:$RHS))> >;
defm SADDLP : SIMDLongTwoVector<0, 0b00010, "saddlp", int_arm64_neon_saddlp>;
defm SCVTF  : SIMDTwoVectorIntToFP<0, 0, 0b11101, "scvtf", sint_to_fp>;
defm SHLL   : SIMDVectorLShiftLongBySizeBHS;
defm SQABS  : SIMDTwoVectorBHSD<0, 0b00111, "sqabs", int_arm64_neon_sqabs>;
defm SQNEG  : SIMDTwoVectorBHSD<1, 0b00111, "sqneg", int_arm64_neon_sqneg>;
defm SQXTN  : SIMDMixedTwoVector<0, 0b10100, "sqxtn", int_arm64_neon_sqxtn>;
defm SQXTUN : SIMDMixedTwoVector<1, 0b10010, "sqxtun", int_arm64_neon_sqxtun>;
defm SUQADD : SIMDTwoVectorBHSDTied<0, 0b00011, "suqadd",int_arm64_neon_suqadd>;
defm UADALP : SIMDLongTwoVectorTied<1, 0b00110, "uadalp",
       BinOpFrag<(add node:$LHS, (int_arm64_neon_uaddlp node:$RHS))> >;
defm UADDLP : SIMDLongTwoVector<1, 0b00010, "uaddlp",
                    int_arm64_neon_uaddlp>;
defm UCVTF  : SIMDTwoVectorIntToFP<1, 0, 0b11101, "ucvtf", uint_to_fp>;
defm UQXTN  : SIMDMixedTwoVector<1, 0b10100, "uqxtn", int_arm64_neon_uqxtn>;
defm URECPE : SIMDTwoVectorS<0, 1, 0b11100, "urecpe", int_arm64_neon_urecpe>;
defm URSQRTE: SIMDTwoVectorS<1, 1, 0b11100, "ursqrte", int_arm64_neon_ursqrte>;
defm USQADD : SIMDTwoVectorBHSDTied<1, 0b00011, "usqadd",int_arm64_neon_usqadd>;
defm XTN    : SIMDMixedTwoVector<0, 0b10010, "xtn", trunc>;

def : Pat<(v2f32 (ARM64rev64 V64:$Rn)), (REV64v2i32 V64:$Rn)>;
def : Pat<(v4f32 (ARM64rev64 V128:$Rn)), (REV64v4i32 V128:$Rn)>;

// Patterns for vector long shift (by element width). These need to match all
// three of zext, sext and anyext so it's easier to pull the patterns out of the
// definition.
multiclass SIMDVectorLShiftLongBySizeBHSPats<SDPatternOperator ext> {
  def : Pat<(ARM64vshl (v8i16 (ext (v8i8 V64:$Rn))), (i32 8)),
            (SHLLv8i8 V64:$Rn)>;
  def : Pat<(ARM64vshl (v8i16 (ext (extract_high_v16i8 V128:$Rn))), (i32 8)),
            (SHLLv16i8 V128:$Rn)>;
  def : Pat<(ARM64vshl (v4i32 (ext (v4i16 V64:$Rn))), (i32 16)),
            (SHLLv4i16 V64:$Rn)>;
  def : Pat<(ARM64vshl (v4i32 (ext (extract_high_v8i16 V128:$Rn))), (i32 16)),
            (SHLLv8i16 V128:$Rn)>;
  def : Pat<(ARM64vshl (v2i64 (ext (v2i32 V64:$Rn))), (i32 32)),
            (SHLLv2i32 V64:$Rn)>;
  def : Pat<(ARM64vshl (v2i64 (ext (extract_high_v4i32 V128:$Rn))), (i32 32)),
            (SHLLv4i32 V128:$Rn)>;
}

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

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

defm ADD     : SIMDThreeSameVector<0, 0b10000, "add", add>;
defm ADDP    : SIMDThreeSameVector<0, 0b10111, "addp", int_arm64_neon_addp>;
defm CMEQ    : SIMDThreeSameVector<1, 0b10001, "cmeq", ARM64cmeq>;
defm CMGE    : SIMDThreeSameVector<0, 0b00111, "cmge", ARM64cmge>;
defm CMGT    : SIMDThreeSameVector<0, 0b00110, "cmgt", ARM64cmgt>;
defm CMHI    : SIMDThreeSameVector<1, 0b00110, "cmhi", ARM64cmhi>;
defm CMHS    : SIMDThreeSameVector<1, 0b00111, "cmhs", ARM64cmhs>;
defm CMTST   : SIMDThreeSameVector<0, 0b10001, "cmtst", ARM64cmtst>;
defm FABD    : SIMDThreeSameVectorFP<1,1,0b11010,"fabd", int_arm64_neon_fabd>;
defm FACGE   : SIMDThreeSameVectorFPCmp<1,0,0b11101,"facge",int_arm64_neon_facge>;
defm FACGT   : SIMDThreeSameVectorFPCmp<1,1,0b11101,"facgt",int_arm64_neon_facgt>;
defm FADDP   : SIMDThreeSameVectorFP<1,0,0b11010,"faddp",int_arm64_neon_addp>;
defm FADD    : SIMDThreeSameVectorFP<0,0,0b11010,"fadd", fadd>;
defm FCMEQ   : SIMDThreeSameVectorFPCmp<0, 0, 0b11100, "fcmeq", ARM64fcmeq>;
defm FCMGE   : SIMDThreeSameVectorFPCmp<1, 0, 0b11100, "fcmge", ARM64fcmge>;
defm FCMGT   : SIMDThreeSameVectorFPCmp<1, 1, 0b11100, "fcmgt", ARM64fcmgt>;
defm FDIV    : SIMDThreeSameVectorFP<1,0,0b11111,"fdiv", fdiv>;
defm FMAXNMP : SIMDThreeSameVectorFP<1,0,0b11000,"fmaxnmp", int_arm64_neon_fmaxnmp>;
defm FMAXNM  : SIMDThreeSameVectorFP<0,0,0b11000,"fmaxnm", int_arm64_neon_fmaxnm>;
defm FMAXP   : SIMDThreeSameVectorFP<1,0,0b11110,"fmaxp", int_arm64_neon_fmaxp>;
defm FMAX    : SIMDThreeSameVectorFP<0,0,0b11110,"fmax", ARM64fmax>;
defm FMINNMP : SIMDThreeSameVectorFP<1,1,0b11000,"fminnmp", int_arm64_neon_fminnmp>;
defm FMINNM  : SIMDThreeSameVectorFP<0,1,0b11000,"fminnm", int_arm64_neon_fminnm>;
defm FMINP   : SIMDThreeSameVectorFP<1,1,0b11110,"fminp", int_arm64_neon_fminp>;
defm FMIN    : SIMDThreeSameVectorFP<0,1,0b11110,"fmin", ARM64fmin>;

// NOTE: The operands of the PatFrag are reordered on FMLA/FMLS because the
// instruction expects the addend first, while the fma intrinsic puts it last.
defm FMLA     : SIMDThreeSameVectorFPTied<0, 0, 0b11001, "fmla",
            TriOpFrag<(fma node:$RHS, node:$MHS, node:$LHS)> >;
defm FMLS     : SIMDThreeSameVectorFPTied<0, 1, 0b11001, "fmls",
            TriOpFrag<(fma node:$MHS, (fneg node:$RHS), node:$LHS)> >;

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

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

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

defm FMULX    : SIMDThreeSameVectorFP<0,0,0b11011,"fmulx", int_arm64_neon_fmulx>;
defm FMUL     : SIMDThreeSameVectorFP<1,0,0b11011,"fmul", fmul>;
defm FRECPS   : SIMDThreeSameVectorFP<0,0,0b11111,"frecps", int_arm64_neon_frecps>;
defm FRSQRTS  : SIMDThreeSameVectorFP<0,1,0b11111,"frsqrts", int_arm64_neon_frsqrts>;
defm FSUB     : SIMDThreeSameVectorFP<0,1,0b11010,"fsub", fsub>;
defm MLA      : SIMDThreeSameVectorBHSTied<0, 0b10010, "mla",
                      TriOpFrag<(add node:$LHS, (mul node:$MHS, node:$RHS))> >;
defm MLS      : SIMDThreeSameVectorBHSTied<1, 0b10010, "mls",
                      TriOpFrag<(sub node:$LHS, (mul node:$MHS, node:$RHS))> >;
defm MUL      : SIMDThreeSameVectorBHS<0, 0b10011, "mul", mul>;
defm PMUL     : SIMDThreeSameVectorB<1, 0b10011, "pmul", int_arm64_neon_pmul>;
defm SABA     : SIMDThreeSameVectorBHSTied<0, 0b01111, "saba",
      TriOpFrag<(add node:$LHS, (int_arm64_neon_sabd node:$MHS, node:$RHS))> >;
defm SABD     : SIMDThreeSameVectorBHS<0,0b01110,"sabd", int_arm64_neon_sabd>;
defm SHADD    : SIMDThreeSameVectorBHS<0,0b00000,"shadd", int_arm64_neon_shadd>;
defm SHSUB    : SIMDThreeSameVectorBHS<0,0b00100,"shsub", int_arm64_neon_shsub>;
defm SMAXP    : SIMDThreeSameVectorBHS<0,0b10100,"smaxp", int_arm64_neon_smaxp>;
defm SMAX     : SIMDThreeSameVectorBHS<0,0b01100,"smax", int_arm64_neon_smax>;
defm SMINP    : SIMDThreeSameVectorBHS<0,0b10101,"sminp", int_arm64_neon_sminp>;
defm SMIN     : SIMDThreeSameVectorBHS<0,0b01101,"smin", int_arm64_neon_smin>;
defm SQADD    : SIMDThreeSameVector<0,0b00001,"sqadd", int_arm64_neon_sqadd>;
defm SQDMULH  : SIMDThreeSameVectorHS<0,0b10110,"sqdmulh",int_arm64_neon_sqdmulh>;
defm SQRDMULH : SIMDThreeSameVectorHS<1,0b10110,"sqrdmulh",int_arm64_neon_sqrdmulh>;
defm SQRSHL   : SIMDThreeSameVector<0,0b01011,"sqrshl", int_arm64_neon_sqrshl>;
defm SQSHL    : SIMDThreeSameVector<0,0b01001,"sqshl", int_arm64_neon_sqshl>;
defm SQSUB    : SIMDThreeSameVector<0,0b00101,"sqsub", int_arm64_neon_sqsub>;
defm SRHADD   : SIMDThreeSameVectorBHS<0,0b00010,"srhadd",int_arm64_neon_srhadd>;
defm SRSHL    : SIMDThreeSameVector<0,0b01010,"srshl", int_arm64_neon_srshl>;
defm SSHL     : SIMDThreeSameVector<0,0b01000,"sshl", int_arm64_neon_sshl>;
defm SUB      : SIMDThreeSameVector<1,0b10000,"sub", sub>;
defm UABA     : SIMDThreeSameVectorBHSTied<1, 0b01111, "uaba",
      TriOpFrag<(add node:$LHS, (int_arm64_neon_uabd node:$MHS, node:$RHS))> >;
defm UABD     : SIMDThreeSameVectorBHS<1,0b01110,"uabd", int_arm64_neon_uabd>;
defm UHADD    : SIMDThreeSameVectorBHS<1,0b00000,"uhadd", int_arm64_neon_uhadd>;
defm UHSUB    : SIMDThreeSameVectorBHS<1,0b00100,"uhsub", int_arm64_neon_uhsub>;
defm UMAXP    : SIMDThreeSameVectorBHS<1,0b10100,"umaxp", int_arm64_neon_umaxp>;
defm UMAX     : SIMDThreeSameVectorBHS<1,0b01100,"umax", int_arm64_neon_umax>;
defm UMINP    : SIMDThreeSameVectorBHS<1,0b10101,"uminp", int_arm64_neon_uminp>;
defm UMIN     : SIMDThreeSameVectorBHS<1,0b01101,"umin", int_arm64_neon_umin>;
defm UQADD    : SIMDThreeSameVector<1,0b00001,"uqadd", int_arm64_neon_uqadd>;
defm UQRSHL   : SIMDThreeSameVector<1,0b01011,"uqrshl", int_arm64_neon_uqrshl>;
defm UQSHL    : SIMDThreeSameVector<1,0b01001,"uqshl", int_arm64_neon_uqshl>;
defm UQSUB    : SIMDThreeSameVector<1,0b00101,"uqsub", int_arm64_neon_uqsub>;
defm URHADD   : SIMDThreeSameVectorBHS<1,0b00010,"urhadd", int_arm64_neon_urhadd>;
defm URSHL    : SIMDThreeSameVector<1,0b01010,"urshl", int_arm64_neon_urshl>;
defm USHL     : SIMDThreeSameVector<1,0b01000,"ushl", int_arm64_neon_ushl>;

defm AND : SIMDLogicalThreeVector<0, 0b00, "and", and>;
defm BIC : SIMDLogicalThreeVector<0, 0b01, "bic",
                                  BinOpFrag<(and node:$LHS, (vnot node:$RHS))> >;
defm BIF : SIMDLogicalThreeVector<1, 0b11, "bif">;
defm BIT : SIMDLogicalThreeVectorTied<1, 0b10, "bit", ARM64bit>;
defm BSL : SIMDLogicalThreeVectorTied<1, 0b01, "bsl",
    TriOpFrag<(or (and node:$LHS, node:$MHS), (and (vnot node:$LHS), node:$RHS))>>;
defm EOR : SIMDLogicalThreeVector<1, 0b00, "eor", xor>;
defm ORN : SIMDLogicalThreeVector<0, 0b11, "orn",
                                  BinOpFrag<(or node:$LHS, (vnot node:$RHS))> >;
defm ORR : SIMDLogicalThreeVector<0, 0b10, "orr", or>;

def : Pat<(ARM64bsl (v8i8 V64:$Rd), V64:$Rn, V64:$Rm),
          (BSLv8i8 V64:$Rd, V64:$Rn, V64:$Rm)>;
def : Pat<(ARM64bsl (v4i16 V64:$Rd), V64:$Rn, V64:$Rm),
          (BSLv8i8 V64:$Rd, V64:$Rn, V64:$Rm)>;
def : Pat<(ARM64bsl (v2i32 V64:$Rd), V64:$Rn, V64:$Rm),
          (BSLv8i8 V64:$Rd, V64:$Rn, V64:$Rm)>;
def : Pat<(ARM64bsl (v1i64 V64:$Rd), V64:$Rn, V64:$Rm),
          (BSLv8i8 V64:$Rd, V64:$Rn, V64:$Rm)>;

def : Pat<(ARM64bsl (v16i8 V128:$Rd), V128:$Rn, V128:$Rm),
          (BSLv16i8 V128:$Rd, V128:$Rn, V128:$Rm)>;
def : Pat<(ARM64bsl (v8i16 V128:$Rd), V128:$Rn, V128:$Rm),
          (BSLv16i8 V128:$Rd, V128:$Rn, V128:$Rm)>;
def : Pat<(ARM64bsl (v4i32 V128:$Rd), V128:$Rn, V128:$Rm),
          (BSLv16i8 V128:$Rd, V128:$Rn, V128:$Rm)>;
def : Pat<(ARM64bsl (v2i64 V128:$Rd), V128:$Rn, V128:$Rm),
          (BSLv16i8 V128:$Rd, V128:$Rn, V128:$Rm)>;

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

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

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

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

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

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

def : InstAlias<"{fcmle\t$dst.2s, $src1.2s, $src2.2s" #
                "|fcmle.2s\t$dst, $src1, $src2}",
                (FCMGEv2f32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{fcmle\t$dst.4s, $src1.4s, $src2.4s" #
                "|fcmle.4s\t$dst, $src1, $src2}",
                (FCMGEv4f32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{fcmle\t$dst.2d, $src1.2d, $src2.2d" #
                "|fcmle.2d\t$dst, $src1, $src2}",
                (FCMGEv2f64 V128:$dst, V128:$src2, V128:$src1), 0>;

def : InstAlias<"{fcmlt\t$dst.2s, $src1.2s, $src2.2s" #
                "|fcmlt.2s\t$dst, $src1, $src2}",
                (FCMGTv2f32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{fcmlt\t$dst.4s, $src1.4s, $src2.4s" #
                "|fcmlt.4s\t$dst, $src1, $src2}",
                (FCMGTv4f32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{fcmlt\t$dst.2d, $src1.2d, $src2.2d" #
                "|fcmlt.2d\t$dst, $src1, $src2}",
                (FCMGTv2f64 V128:$dst, V128:$src2, V128:$src1), 0>;

def : InstAlias<"{facle\t$dst.2s, $src1.2s, $src2.2s" #
                "|facle.2s\t$dst, $src1, $src2}",
                (FACGEv2f32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{facle\t$dst.4s, $src1.4s, $src2.4s" #
                "|facle.4s\t$dst, $src1, $src2}",
                (FACGEv4f32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{facle\t$dst.2d, $src1.2d, $src2.2d" #
                "|facle.2d\t$dst, $src1, $src2}",
                (FACGEv2f64 V128:$dst, V128:$src2, V128:$src1), 0>;

def : InstAlias<"{faclt\t$dst.2s, $src1.2s, $src2.2s" #
                "|faclt.2s\t$dst, $src1, $src2}",
                (FACGTv2f32 V64:$dst, V64:$src2, V64:$src1), 0>;
def : InstAlias<"{faclt\t$dst.4s, $src1.4s, $src2.4s" #
                "|faclt.4s\t$dst, $src1, $src2}",
                (FACGTv4f32 V128:$dst, V128:$src2, V128:$src1), 0>;
def : InstAlias<"{faclt\t$dst.2d, $src1.2d, $src2.2d" #
                "|faclt.2d\t$dst, $src1, $src2}",
                (FACGTv2f64 V128:$dst, V128:$src2, V128:$src1), 0>;

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

defm ADD      : SIMDThreeScalarD<0, 0b10000, "add", add>;
defm CMEQ     : SIMDThreeScalarD<1, 0b10001, "cmeq", ARM64cmeq>;
defm CMGE     : SIMDThreeScalarD<0, 0b00111, "cmge", ARM64cmge>;
defm CMGT     : SIMDThreeScalarD<0, 0b00110, "cmgt", ARM64cmgt>;
defm CMHI     : SIMDThreeScalarD<1, 0b00110, "cmhi", ARM64cmhi>;
defm CMHS     : SIMDThreeScalarD<1, 0b00111, "cmhs", ARM64cmhs>;
defm CMTST    : SIMDThreeScalarD<0, 0b10001, "cmtst", ARM64cmtst>;
defm FABD     : SIMDThreeScalarSD<1, 1, 0b11010, "fabd", int_arm64_sisd_fabd>;
def : Pat<(v1f64 (int_arm64_neon_fabd (v1f64 FPR64:$Rn), (v1f64 FPR64:$Rm))),
          (FABD64 FPR64:$Rn, FPR64:$Rm)>;
defm FACGE    : SIMDThreeScalarFPCmp<1, 0, 0b11101, "facge",
                                     int_arm64_neon_facge>;
defm FACGT    : SIMDThreeScalarFPCmp<1, 1, 0b11101, "facgt",
                                     int_arm64_neon_facgt>;
defm FCMEQ    : SIMDThreeScalarFPCmp<0, 0, 0b11100, "fcmeq", ARM64fcmeq>;
defm FCMGE    : SIMDThreeScalarFPCmp<1, 0, 0b11100, "fcmge", ARM64fcmge>;
defm FCMGT    : SIMDThreeScalarFPCmp<1, 1, 0b11100, "fcmgt", ARM64fcmgt>;
defm FMULX    : SIMDThreeScalarSD<0, 0, 0b11011, "fmulx", int_arm64_neon_fmulx>;
defm FRECPS   : SIMDThreeScalarSD<0, 0, 0b11111, "frecps", int_arm64_neon_frecps>;
defm FRSQRTS  : SIMDThreeScalarSD<0, 1, 0b11111, "frsqrts", int_arm64_neon_frsqrts>;
defm SQADD    : SIMDThreeScalarBHSD<0, 0b00001, "sqadd", int_arm64_neon_sqadd>;
defm SQDMULH  : SIMDThreeScalarHS<  0, 0b10110, "sqdmulh", int_arm64_neon_sqdmulh>;
defm SQRDMULH : SIMDThreeScalarHS<  1, 0b10110, "sqrdmulh", int_arm64_neon_sqrdmulh>;
defm SQRSHL   : SIMDThreeScalarBHSD<0, 0b01011, "sqrshl",int_arm64_neon_sqrshl>;
defm SQSHL    : SIMDThreeScalarBHSD<0, 0b01001, "sqshl", int_arm64_neon_sqshl>;
defm SQSUB    : SIMDThreeScalarBHSD<0, 0b00101, "sqsub", int_arm64_neon_sqsub>;
defm SRSHL    : SIMDThreeScalarD<   0, 0b01010, "srshl", int_arm64_neon_srshl>;
defm SSHL     : SIMDThreeScalarD<   0, 0b01000, "sshl", int_arm64_neon_sshl>;
defm SUB      : SIMDThreeScalarD<   1, 0b10000, "sub", sub>;
defm UQADD    : SIMDThreeScalarBHSD<1, 0b00001, "uqadd", int_arm64_neon_uqadd>;
defm UQRSHL   : SIMDThreeScalarBHSD<1, 0b01011, "uqrshl",int_arm64_neon_uqrshl>;
defm UQSHL    : SIMDThreeScalarBHSD<1, 0b01001, "uqshl", int_arm64_neon_uqshl>;
defm UQSUB    : SIMDThreeScalarBHSD<1, 0b00101, "uqsub", int_arm64_neon_uqsub>;
defm URSHL    : SIMDThreeScalarD<   1, 0b01010, "urshl", int_arm64_neon_urshl>;
defm USHL     : SIMDThreeScalarD<   1, 0b01000, "ushl", int_arm64_neon_ushl>;

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

//===----------------------------------------------------------------------===//
// Advanced SIMD three scalar instructions (mixed operands).
//===----------------------------------------------------------------------===//
defm SQDMULL  : SIMDThreeScalarMixedHS<0, 0b11010, "sqdmull",
                                       int_arm64_neon_sqdmulls_scalar>;
defm SQDMLAL  : SIMDThreeScalarMixedTiedHS<0, 0b10010, "sqdmlal">;
defm SQDMLSL  : SIMDThreeScalarMixedTiedHS<0, 0b10110, "sqdmlsl">;

def : Pat<(i64 (int_arm64_neon_sqadd (i64 FPR64:$Rd),
                   (i64 (int_arm64_neon_sqdmulls_scalar (i32 FPR32:$Rn),
                                                        (i32 FPR32:$Rm))))),
          (SQDMLALi32 FPR64:$Rd, FPR32:$Rn, FPR32:$Rm)>;
def : Pat<(i64 (int_arm64_neon_sqsub (i64 FPR64:$Rd),
                   (i64 (int_arm64_neon_sqdmulls_scalar (i32 FPR32:$Rn),
                                                        (i32 FPR32:$Rm))))),
          (SQDMLSLi32 FPR64:$Rd, FPR32:$Rn, FPR32:$Rm)>;

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

defm ABS    : SIMDTwoScalarD<    0, 0b01011, "abs", int_arm64_neon_abs>;
defm CMEQ   : SIMDCmpTwoScalarD< 0, 0b01001, "cmeq", ARM64cmeqz>;
defm CMGE   : SIMDCmpTwoScalarD< 1, 0b01000, "cmge", ARM64cmgez>;
defm CMGT   : SIMDCmpTwoScalarD< 0, 0b01000, "cmgt", ARM64cmgtz>;
defm CMLE   : SIMDCmpTwoScalarD< 1, 0b01001, "cmle", ARM64cmlez>;
defm CMLT   : SIMDCmpTwoScalarD< 0, 0b01010, "cmlt", ARM64cmltz>;
defm FCMEQ  : SIMDCmpTwoScalarSD<0, 1, 0b01101, "fcmeq", ARM64fcmeqz>;
defm FCMGE  : SIMDCmpTwoScalarSD<1, 1, 0b01100, "fcmge", ARM64fcmgez>;
defm FCMGT  : SIMDCmpTwoScalarSD<0, 1, 0b01100, "fcmgt", ARM64fcmgtz>;
defm FCMLE  : SIMDCmpTwoScalarSD<1, 1, 0b01101, "fcmle", ARM64fcmlez>;
defm FCMLT  : SIMDCmpTwoScalarSD<0, 1, 0b01110, "fcmlt", ARM64fcmltz>;
defm FCVTAS : SIMDTwoScalarSD<   0, 0, 0b11100, "fcvtas">;
defm FCVTAU : SIMDTwoScalarSD<   1, 0, 0b11100, "fcvtau">;
defm FCVTMS : SIMDTwoScalarSD<   0, 0, 0b11011, "fcvtms">;
defm FCVTMU : SIMDTwoScalarSD<   1, 0, 0b11011, "fcvtmu">;
defm FCVTNS : SIMDTwoScalarSD<   0, 0, 0b11010, "fcvtns">;
defm FCVTNU : SIMDTwoScalarSD<   1, 0, 0b11010, "fcvtnu">;
defm FCVTPS : SIMDTwoScalarSD<   0, 1, 0b11010, "fcvtps">;
defm FCVTPU : SIMDTwoScalarSD<   1, 1, 0b11010, "fcvtpu">;
def  FCVTXNv1i64 : SIMDInexactCvtTwoScalar<0b10110, "fcvtxn">;
defm FCVTZS : SIMDTwoScalarSD<   0, 1, 0b11011, "fcvtzs">;
defm FCVTZU : SIMDTwoScalarSD<   1, 1, 0b11011, "fcvtzu">;
defm FRECPE : SIMDTwoScalarSD<   0, 1, 0b11101, "frecpe">;
defm FRECPX : SIMDTwoScalarSD<   0, 1, 0b11111, "frecpx">;
defm FRSQRTE : SIMDTwoScalarSD<  1, 1, 0b11101, "frsqrte">;
defm NEG    : SIMDTwoScalarD<    1, 0b01011, "neg",
                                 UnOpFrag<(sub immAllZerosV, node:$LHS)> >;
defm SCVTF  : SIMDTwoScalarCVTSD<   0, 0, 0b11101, "scvtf", ARM64sitof>;
defm SQABS  : SIMDTwoScalarBHSD< 0, 0b00111, "sqabs", int_arm64_neon_sqabs>;
defm SQNEG  : SIMDTwoScalarBHSD< 1, 0b00111, "sqneg", int_arm64_neon_sqneg>;
defm SQXTN  : SIMDTwoScalarMixedBHS< 0, 0b10100, "sqxtn", int_arm64_neon_scalar_sqxtn>;
defm SQXTUN : SIMDTwoScalarMixedBHS< 1, 0b10010, "sqxtun", int_arm64_neon_scalar_sqxtun>;
defm SUQADD : SIMDTwoScalarBHSDTied< 0, 0b00011, "suqadd",
                                     int_arm64_neon_suqadd>;
defm UCVTF  : SIMDTwoScalarCVTSD<   1, 0, 0b11101, "ucvtf", ARM64uitof>;
defm UQXTN  : SIMDTwoScalarMixedBHS<1, 0b10100, "uqxtn", int_arm64_neon_scalar_uqxtn>;
defm USQADD : SIMDTwoScalarBHSDTied< 1, 0b00011, "usqadd",
                                    int_arm64_neon_usqadd>;

def : Pat<(ARM64neg (v1i64 V64:$Rn)), (NEGv1i64 V64:$Rn)>;

def : Pat<(v1i64 (int_arm64_neon_fcvtas (v1f64 FPR64:$Rn))),
          (FCVTASv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_arm64_neon_fcvtau (v1f64 FPR64:$Rn))),
          (FCVTAUv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_arm64_neon_fcvtms (v1f64 FPR64:$Rn))),
          (FCVTMSv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_arm64_neon_fcvtmu (v1f64 FPR64:$Rn))),
          (FCVTMUv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_arm64_neon_fcvtns (v1f64 FPR64:$Rn))),
          (FCVTNSv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_arm64_neon_fcvtnu (v1f64 FPR64:$Rn))),
          (FCVTNUv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_arm64_neon_fcvtps (v1f64 FPR64:$Rn))),
          (FCVTPSv1i64 FPR64:$Rn)>;
def : Pat<(v1i64 (int_arm64_neon_fcvtpu (v1f64 FPR64:$Rn))),
          (FCVTPUv1i64 FPR64:$Rn)>;

def : Pat<(f32 (int_arm64_neon_frecpe (f32 FPR32:$Rn))),
          (FRECPEv1i32 FPR32:$Rn)>;
def : Pat<(f64 (int_arm64_neon_frecpe (f64 FPR64:$Rn))),
          (FRECPEv1i64 FPR64:$Rn)>;
def : Pat<(v1f64 (int_arm64_neon_frecpe (v1f64 FPR64:$Rn))),
          (FRECPEv1i64 FPR64:$Rn)>;

def : Pat<(f32 (int_arm64_neon_frecpx (f32 FPR32:$Rn))),
          (FRECPXv1i32 FPR32:$Rn)>;
def : Pat<(f64 (int_arm64_neon_frecpx (f64 FPR64:$Rn))),
          (FRECPXv1i64 FPR64:$Rn)>;

def : Pat<(f32 (int_arm64_neon_frsqrte (f32 FPR32:$Rn))),
          (FRSQRTEv1i32 FPR32:$Rn)>;
def : Pat<(f64 (int_arm64_neon_frsqrte (f64 FPR64:$Rn))),
          (FRSQRTEv1i64 FPR64:$Rn)>;
def : Pat<(v1f64 (int_arm64_neon_frsqrte (v1f64 FPR64:$Rn))),
          (FRSQRTEv1i64 FPR64:$Rn)>;

// If an integer is about to be converted to a floating point value,
// just load it on the floating point unit.
// Here are the patterns for 8 and 16-bits to float.
// 8-bits -> float.
def : Pat <(f32 (uint_to_fp (i32 (zextloadi8 ro_indexed8:$addr)))),
           (UCVTFv1i32 (INSERT_SUBREG (f32 (IMPLICIT_DEF)),
                          (LDRBro ro_indexed8:$addr), bsub))>;
def : Pat <(f32 (uint_to_fp (i32 (zextloadi8 am_indexed8:$addr)))),
           (UCVTFv1i32 (INSERT_SUBREG (f32 (IMPLICIT_DEF)),
                          (LDRBui am_indexed8:$addr), bsub))>;
def : Pat <(f32 (uint_to_fp (i32 (zextloadi8 am_unscaled8:$addr)))),
           (UCVTFv1i32 (INSERT_SUBREG (f32 (IMPLICIT_DEF)),
                          (LDURBi am_unscaled8:$addr), bsub))>;
// 16-bits -> float.
def : Pat <(f32 (uint_to_fp (i32 (zextloadi16 ro_indexed16:$addr)))),
           (UCVTFv1i32 (INSERT_SUBREG (f32 (IMPLICIT_DEF)),
                          (LDRHro ro_indexed16:$addr), hsub))>;
def : Pat <(f32 (uint_to_fp (i32 (zextloadi16 am_indexed16:$addr)))),
           (UCVTFv1i32 (INSERT_SUBREG (f32 (IMPLICIT_DEF)),
                          (LDRHui am_indexed16:$addr), hsub))>;
def : Pat <(f32 (uint_to_fp (i32 (zextloadi16 am_unscaled16:$addr)))),
           (UCVTFv1i32 (INSERT_SUBREG (f32 (IMPLICIT_DEF)),
                          (LDURHi am_unscaled16:$addr), hsub))>;
// 32-bits are handled in target specific dag combine:
// performIntToFpCombine.
// 64-bits integer to 32-bits floating point, not possible with
// UCVTF on floating point registers (both source and destination
// must have the same size).

// Here are the patterns for 8, 16, 32, and 64-bits to double.
// 8-bits -> double.
def : Pat <(f64 (uint_to_fp (i32 (zextloadi8 ro_indexed8:$addr)))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDRBro ro_indexed8:$addr), bsub))>;
def : Pat <(f64 (uint_to_fp (i32 (zextloadi8 am_indexed8:$addr)))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDRBui am_indexed8:$addr), bsub))>;
def : Pat <(f64 (uint_to_fp (i32 (zextloadi8 am_unscaled8:$addr)))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDURBi am_unscaled8:$addr), bsub))>;
// 16-bits -> double.
def : Pat <(f64 (uint_to_fp (i32 (zextloadi16 ro_indexed16:$addr)))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDRHro ro_indexed16:$addr), hsub))>;
def : Pat <(f64 (uint_to_fp (i32 (zextloadi16 am_indexed16:$addr)))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDRHui am_indexed16:$addr), hsub))>;
def : Pat <(f64 (uint_to_fp (i32 (zextloadi16 am_unscaled16:$addr)))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDURHi am_unscaled16:$addr), hsub))>;
// 32-bits -> double.
def : Pat <(f64 (uint_to_fp (i32 (load ro_indexed32:$addr)))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDRSro ro_indexed32:$addr), ssub))>;
def : Pat <(f64 (uint_to_fp (i32 (load am_indexed32:$addr)))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDRSui am_indexed32:$addr), ssub))>;
def : Pat <(f64 (uint_to_fp (i32 (load am_unscaled32:$addr)))),
           (UCVTFv1i64 (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                          (LDURSi am_unscaled32:$addr), ssub))>;
// 64-bits -> double are handled in target specific dag combine:
// performIntToFpCombine.

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

defm ADDHN  : SIMDNarrowThreeVectorBHS<0,0b0100,"addhn", int_arm64_neon_addhn>;
defm SUBHN  : SIMDNarrowThreeVectorBHS<0,0b0110,"subhn", int_arm64_neon_subhn>;
defm RADDHN : SIMDNarrowThreeVectorBHS<1,0b0100,"raddhn",int_arm64_neon_raddhn>;
defm RSUBHN : SIMDNarrowThreeVectorBHS<1,0b0110,"rsubhn",int_arm64_neon_rsubhn>;
defm PMULL  : SIMDDifferentThreeVectorBD<0,0b1110,"pmull",int_arm64_neon_pmull>;
defm SABAL  : SIMDLongThreeVectorTiedBHSabal<0,0b0101,"sabal",
                                             int_arm64_neon_sabd>;
defm SABDL   : SIMDLongThreeVectorBHSabdl<0, 0b0111, "sabdl",
                                          int_arm64_neon_sabd>;
defm SADDL   : SIMDLongThreeVectorBHS<   0, 0b0000, "saddl",
            BinOpFrag<(add (sext node:$LHS), (sext node:$RHS))>>;
defm SADDW   : SIMDWideThreeVectorBHS<   0, 0b0001, "saddw",
                 BinOpFrag<(add node:$LHS, (sext node:$RHS))>>;
defm SMLAL   : SIMDLongThreeVectorTiedBHS<0, 0b1000, "smlal",
    TriOpFrag<(add node:$LHS, (int_arm64_neon_smull node:$MHS, node:$RHS))>>;
defm SMLSL   : SIMDLongThreeVectorTiedBHS<0, 0b1010, "smlsl",
    TriOpFrag<(sub node:$LHS, (int_arm64_neon_smull node:$MHS, node:$RHS))>>;
defm SMULL   : SIMDLongThreeVectorBHS<0, 0b1100, "smull", int_arm64_neon_smull>;
defm SQDMLAL : SIMDLongThreeVectorSQDMLXTiedHS<0, 0b1001, "sqdmlal",
                                               int_arm64_neon_sqadd>;
defm SQDMLSL : SIMDLongThreeVectorSQDMLXTiedHS<0, 0b1011, "sqdmlsl",
                                               int_arm64_neon_sqsub>;
defm SQDMULL : SIMDLongThreeVectorHS<0, 0b1101, "sqdmull",
                                     int_arm64_neon_sqdmull>;
defm SSUBL   : SIMDLongThreeVectorBHS<0, 0b0010, "ssubl",
                 BinOpFrag<(sub (sext node:$LHS), (sext node:$RHS))>>;
defm SSUBW   : SIMDWideThreeVectorBHS<0, 0b0011, "ssubw",
                 BinOpFrag<(sub node:$LHS, (sext node:$RHS))>>;
defm UABAL   : SIMDLongThreeVectorTiedBHSabal<1, 0b0101, "uabal",
                                              int_arm64_neon_uabd>;
defm UABDL   : SIMDLongThreeVectorBHSabdl<1, 0b0111, "uabdl",
                                          int_arm64_neon_uabd>;
defm UADDL   : SIMDLongThreeVectorBHS<1, 0b0000, "uaddl",
                 BinOpFrag<(add (zext node:$LHS), (zext node:$RHS))>>;
defm UADDW   : SIMDWideThreeVectorBHS<1, 0b0001, "uaddw",
                 BinOpFrag<(add node:$LHS, (zext node:$RHS))>>;
defm UMLAL   : SIMDLongThreeVectorTiedBHS<1, 0b1000, "umlal",
    TriOpFrag<(add node:$LHS, (int_arm64_neon_umull node:$MHS, node:$RHS))>>;
defm UMLSL   : SIMDLongThreeVectorTiedBHS<1, 0b1010, "umlsl",
    TriOpFrag<(sub node:$LHS, (int_arm64_neon_umull node:$MHS, node:$RHS))>>;
defm UMULL   : SIMDLongThreeVectorBHS<1, 0b1100, "umull", int_arm64_neon_umull>;
defm USUBL   : SIMDLongThreeVectorBHS<1, 0b0010, "usubl",
                 BinOpFrag<(sub (zext node:$LHS), (zext node:$RHS))>>;
defm USUBW   : SIMDWideThreeVectorBHS<   1, 0b0011, "usubw",
                 BinOpFrag<(sub node:$LHS, (zext node:$RHS))>>;

// Patterns for 64-bit pmull
def : Pat<(int_arm64_neon_pmull64 V64:$Rn, V64:$Rm),
          (PMULLv1i64 V64:$Rn, V64:$Rm)>;
def : Pat<(int_arm64_neon_pmull64 (vector_extract (v2i64 V128:$Rn), (i64 1)),
                                  (vector_extract (v2i64 V128:$Rm), (i64 1))),
          (PMULLv2i64 V128:$Rn, V128:$Rm)>;

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

// ADDHN
def : Pat<(v8i8 (trunc (v8i16 (ARM64vlshr (add V128:$Rn, V128:$Rm), (i32 8))))),
          (ADDHNv8i16_v8i8 V128:$Rn, V128:$Rm)>;
def : Pat<(v4i16 (trunc (v4i32 (ARM64vlshr (add V128:$Rn, V128:$Rm),
                                           (i32 16))))),
          (ADDHNv4i32_v4i16 V128:$Rn, V128:$Rm)>;
def : Pat<(v2i32 (trunc (v2i64 (ARM64vlshr (add V128:$Rn, V128:$Rm),
                                           (i32 32))))),
          (ADDHNv2i64_v2i32 V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v8i8 V64:$Rd),
                          (trunc (v8i16 (ARM64vlshr (add V128:$Rn, V128:$Rm),
                                                    (i32 8))))),
          (ADDHNv8i16_v16i8 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v4i16 V64:$Rd),
                          (trunc (v4i32 (ARM64vlshr (add V128:$Rn, V128:$Rm),
                                                    (i32 16))))),
          (ADDHNv4i32_v8i16 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v2i32 V64:$Rd),
                          (trunc (v2i64 (ARM64vlshr (add V128:$Rn, V128:$Rm),
                                                    (i32 32))))),
          (ADDHNv2i64_v4i32 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;

// SUBHN
def : Pat<(v8i8 (trunc (v8i16 (ARM64vlshr (sub V128:$Rn, V128:$Rm), (i32 8))))),
          (SUBHNv8i16_v8i8 V128:$Rn, V128:$Rm)>;
def : Pat<(v4i16 (trunc (v4i32 (ARM64vlshr (sub V128:$Rn, V128:$Rm),
                                           (i32 16))))),
          (SUBHNv4i32_v4i16 V128:$Rn, V128:$Rm)>;
def : Pat<(v2i32 (trunc (v2i64 (ARM64vlshr (sub V128:$Rn, V128:$Rm),
                                           (i32 32))))),
          (SUBHNv2i64_v2i32 V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v8i8 V64:$Rd),
                          (trunc (v8i16 (ARM64vlshr (sub V128:$Rn, V128:$Rm),
                                                    (i32 8))))),
          (SUBHNv8i16_v16i8 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v4i16 V64:$Rd),
                          (trunc (v4i32 (ARM64vlshr (sub V128:$Rn, V128:$Rm),
                                                    (i32 16))))),
          (SUBHNv4i32_v8i16 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;
def : Pat<(concat_vectors (v2i32 V64:$Rd),
                          (trunc (v2i64 (ARM64vlshr (sub V128:$Rn, V128:$Rm),
                                                    (i32 32))))),
          (SUBHNv2i64_v4i32 (SUBREG_TO_REG (i32 0), V64:$Rd, dsub),
                            V128:$Rn, V128:$Rm)>;

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

defm EXT : SIMDBitwiseExtract<"ext">;

def : Pat<(v4i16 (ARM64ext V64:$Rn, V64:$Rm, (i32 imm:$imm))),
          (EXTv8i8 V64:$Rn, V64:$Rm, imm:$imm)>;
def : Pat<(v8i16 (ARM64ext V128:$Rn, V128:$Rm, (i32 imm:$imm))),
          (EXTv16i8 V128:$Rn, V128:$Rm, imm:$imm)>;
def : Pat<(v2i32 (ARM64ext V64:$Rn, V64:$Rm, (i32 imm:$imm))),
          (EXTv8i8 V64:$Rn, V64:$Rm, imm:$imm)>;
def : Pat<(v2f32 (ARM64ext V64:$Rn, V64:$Rm, (i32 imm:$imm))),
          (EXTv8i8 V64:$Rn, V64:$Rm, imm:$imm)>;
def : Pat<(v4i32 (ARM64ext V128:$Rn, V128:$Rm, (i32 imm:$imm))),
          (EXTv16i8 V128:$Rn, V128:$Rm, imm:$imm)>;
def : Pat<(v4f32 (ARM64ext V128:$Rn, V128:$Rm, (i32 imm:$imm))),
          (EXTv16i8 V128:$Rn, V128:$Rm, imm:$imm)>;
def : Pat<(v2i64 (ARM64ext V128:$Rn, V128:$Rm, (i32 imm:$imm))),
          (EXTv16i8 V128:$Rn, V128:$Rm, imm:$imm)>;
def : Pat<(v2f64 (ARM64ext V128:$Rn, V128:$Rm, (i32 imm:$imm))),
          (EXTv16i8 V128:$Rn, V128:$Rm, imm:$imm)>;

// We use EXT to handle extract_subvector to copy the upper 64-bits of a
// 128-bit vector.
def : Pat<(v8i8  (extract_subvector V128:$Rn, (i64 8))),
          (EXTRACT_SUBREG (EXTv16i8 V128:$Rn, V128:$Rn, 8), dsub)>;
def : Pat<(v4i16 (extract_subvector V128:$Rn, (i64 4))),
          (EXTRACT_SUBREG (EXTv16i8 V128:$Rn, V128:$Rn, 8), dsub)>;
def : Pat<(v2i32 (extract_subvector V128:$Rn, (i64 2))),
          (EXTRACT_SUBREG (EXTv16i8 V128:$Rn, V128:$Rn, 8), dsub)>;
def : Pat<(v1i64 (extract_subvector V128:$Rn, (i64 1))),
          (EXTRACT_SUBREG (EXTv16i8 V128:$Rn, V128:$Rn, 8), dsub)>;
def : Pat<(v2f32 (extract_subvector V128:$Rn, (i64 2))),
          (EXTRACT_SUBREG (EXTv16i8 V128:$Rn, V128:$Rn, 8), dsub)>;
def : Pat<(v1f64 (extract_subvector V128:$Rn, (i64 1))),
          (EXTRACT_SUBREG (EXTv16i8 V128:$Rn, V128:$Rn, 8), dsub)>;


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

defm TRN1 : SIMDZipVector<0b010, "trn1", ARM64trn1>;
defm TRN2 : SIMDZipVector<0b110, "trn2", ARM64trn2>;
defm UZP1 : SIMDZipVector<0b001, "uzp1", ARM64uzp1>;
defm UZP2 : SIMDZipVector<0b101, "uzp2", ARM64uzp2>;
defm ZIP1 : SIMDZipVector<0b011, "zip1", ARM64zip1>;
defm ZIP2 : SIMDZipVector<0b111, "zip2", ARM64zip2>;

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

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

def : Pat<(v8i8 (int_arm64_neon_tbl1 (v16i8 VecListOne128:$Rn), (v8i8 V64:$Ri))),
          (TBLv8i8One VecListOne128:$Rn, V64:$Ri)>;
def : Pat<(v16i8 (int_arm64_neon_tbl1 (v16i8 V128:$Ri), (v16i8 V128:$Rn))),
          (TBLv16i8One V128:$Ri, V128:$Rn)>;

def : Pat<(v8i8 (int_arm64_neon_tbx1 (v8i8 V64:$Rd),
                  (v16i8 VecListOne128:$Rn), (v8i8 V64:$Ri))),
          (TBXv8i8One V64:$Rd, VecListOne128:$Rn, V64:$Ri)>;
def : Pat<(v16i8 (int_arm64_neon_tbx1 (v16i8 V128:$Rd),
                   (v16i8 V128:$Ri), (v16i8 V128:$Rn))),
          (TBXv16i8One V128:$Rd, V128:$Ri, V128:$Rn)>;


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

defm CPY : SIMDScalarCPY<"cpy">;

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

defm ADDP    : SIMDPairwiseScalarD<0, 0b11011, "addp">;
defm FADDP   : SIMDPairwiseScalarSD<1, 0, 0b01101, "faddp">;
defm FMAXNMP : SIMDPairwiseScalarSD<1, 0, 0b01100, "fmaxnmp">;
defm FMAXP   : SIMDPairwiseScalarSD<1, 0, 0b01111, "fmaxp">;
defm FMINNMP : SIMDPairwiseScalarSD<1, 1, 0b01100, "fminnmp">;
defm FMINP   : SIMDPairwiseScalarSD<1, 1, 0b01111, "fminp">;
def : Pat<(i64 (int_arm64_neon_saddv (v2i64 V128:$Rn))),
          (ADDPv2i64p V128:$Rn)>;
def : Pat<(i64 (int_arm64_neon_uaddv (v2i64 V128:$Rn))),
          (ADDPv2i64p V128:$Rn)>;
def : Pat<(f32 (int_arm64_neon_faddv (v2f32 V64:$Rn))),
          (FADDPv2i32p V64:$Rn)>;
def : Pat<(f32 (int_arm64_neon_faddv (v4f32 V128:$Rn))),
          (FADDPv2i32p (EXTRACT_SUBREG (FADDPv4f32 V128:$Rn, V128:$Rn), dsub))>;
def : Pat<(f64 (int_arm64_neon_faddv (v2f64 V128:$Rn))),
          (FADDPv2i64p V128:$Rn)>;
def : Pat<(f32 (int_arm64_neon_fmaxnmv (v2f32 V64:$Rn))),
          (FMAXNMPv2i32p V64:$Rn)>;
def : Pat<(f64 (int_arm64_neon_fmaxnmv (v2f64 V128:$Rn))),
          (FMAXNMPv2i64p V128:$Rn)>;
def : Pat<(f32 (int_arm64_neon_fmaxv (v2f32 V64:$Rn))),
          (FMAXPv2i32p V64:$Rn)>;
def : Pat<(f64 (int_arm64_neon_fmaxv (v2f64 V128:$Rn))),
          (FMAXPv2i64p V128:$Rn)>;
def : Pat<(f32 (int_arm64_neon_fminnmv (v2f32 V64:$Rn))),
          (FMINNMPv2i32p V64:$Rn)>;
def : Pat<(f64 (int_arm64_neon_fminnmv (v2f64 V128:$Rn))),
          (FMINNMPv2i64p V128:$Rn)>;
def : Pat<(f32 (int_arm64_neon_fminv (v2f32 V64:$Rn))),
          (FMINPv2i32p V64:$Rn)>;
def : Pat<(f64 (int_arm64_neon_fminv (v2f64 V128:$Rn))),
          (FMINPv2i64p V128:$Rn)>;

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

def DUPv8i8gpr  : SIMDDupFromMain<0, 0b00001, ".8b", v8i8, V64, GPR32>;
def DUPv16i8gpr : SIMDDupFromMain<1, 0b00001, ".16b", v16i8, V128, GPR32>;
def DUPv4i16gpr : SIMDDupFromMain<0, 0b00010, ".4h", v4i16, V64, GPR32>;
def DUPv8i16gpr : SIMDDupFromMain<1, 0b00010, ".8h", v8i16, V128, GPR32>;
def DUPv2i32gpr : SIMDDupFromMain<0, 0b00100, ".2s", v2i32, V64, GPR32>;
def DUPv4i32gpr : SIMDDupFromMain<1, 0b00100, ".4s", v4i32, V128, GPR32>;
def DUPv2i64gpr : SIMDDupFromMain<1, 0b01000, ".2d", v2i64, V128, GPR64>;

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

def : Pat<(v2f32 (ARM64dup (f32 FPR32:$Rn))),
          (v2f32 (DUPv2i32lane
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR32:$Rn, ssub),
            (i64 0)))>;
def : Pat<(v4f32 (ARM64dup (f32 FPR32:$Rn))),
          (v4f32 (DUPv4i32lane
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR32:$Rn, ssub),
            (i64 0)))>;
def : Pat<(v2f64 (ARM64dup (f64 FPR64:$Rn))),
          (v2f64 (DUPv2i64lane
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR64:$Rn, dsub),
            (i64 0)))>;

def : Pat<(v2f32 (ARM64duplane32 (v4f32 V128:$Rn), VectorIndexS:$imm)),
          (DUPv2i32lane V128:$Rn, VectorIndexS:$imm)>;
def : Pat<(v4f32 (ARM64duplane32 (v4f32 V128:$Rn), VectorIndexS:$imm)),
         (DUPv4i32lane V128:$Rn, VectorIndexS:$imm)>;
def : Pat<(v2f64 (ARM64duplane64 (v2f64 V128:$Rn), VectorIndexD:$imm)),
          (DUPv2i64lane V128:$Rn, VectorIndexD:$imm)>;

// If there's an (ARM64dup (vector_extract ...) ...), we can use a duplane
// instruction even if the types don't match: we just have to remap the lane
// carefully. N.b. this trick only applies to truncations.
def VecIndex_x2 : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(2 * N->getZExtValue(), MVT::i64);
}]>;
def VecIndex_x4 : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(4 * N->getZExtValue(), MVT::i64);
}]>;
def VecIndex_x8 : SDNodeXForm<imm, [{
  return CurDAG->getTargetConstant(8 * N->getZExtValue(), MVT::i64);
}]>;

multiclass DUPWithTruncPats<ValueType ResVT, ValueType Src64VT,
                            ValueType Src128VT, ValueType ScalVT,
                            Instruction DUP, SDNodeXForm IdxXFORM> {
  def : Pat<(ResVT (ARM64dup (ScalVT (vector_extract (Src128VT V128:$Rn),
                                                     imm:$idx)))),
            (DUP V128:$Rn, (IdxXFORM imm:$idx))>;

  def : Pat<(ResVT (ARM64dup (ScalVT (vector_extract (Src64VT V64:$Rn),
                                                     imm:$idx)))),
            (DUP (SUBREG_TO_REG (i64 0), V64:$Rn, dsub), (IdxXFORM imm:$idx))>;
}

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

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

multiclass DUPWithTrunci64Pats<ValueType ResVT, Instruction DUP,
                               SDNodeXForm IdxXFORM> {
  def : Pat<(ResVT (ARM64dup (i32 (trunc (vector_extract (v2i64 V128:$Rn),
                                                         imm:$idx))))),
            (DUP V128:$Rn, (IdxXFORM imm:$idx))>;

  def : Pat<(ResVT (ARM64dup (i32 (trunc (vector_extract (v1i64 V64:$Rn),
                                                         imm:$idx))))),
            (DUP (SUBREG_TO_REG (i64 0), V64:$Rn, dsub), (IdxXFORM imm:$idx))>;
}

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

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

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

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

// Extracting i8 or i16 elements will have the zero-extend transformed to
// an 'and' mask by type legalization since neither i8 nor i16 are legal types
// for ARM64. Match these patterns here since UMOV already zeroes out the high
// bits of the destination register.
def : Pat<(and (vector_extract (v16i8 V128:$Rn), VectorIndexB:$idx),
               (i32 0xff)),
          (i32 (UMOVvi8 V128:$Rn, VectorIndexB:$idx))>;
def : Pat<(and (vector_extract (v8i16 V128:$Rn), VectorIndexH:$idx),
               (i32 0xffff)),
          (i32 (UMOVvi16 V128:$Rn, VectorIndexH:$idx))>;

defm INS : SIMDIns;

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

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

def : Pat<(v2i32 (scalar_to_vector (i32 FPR32:$Rn))),
            (v2i32 (INSERT_SUBREG (v2i32 (IMPLICIT_DEF)),
                                  (i32 FPR32:$Rn), ssub))>;
def : Pat<(v4i32 (scalar_to_vector (i32 FPR32:$Rn))),
            (v4i32 (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)),
                                  (i32 FPR32:$Rn), ssub))>;
def : Pat<(v2i64 (scalar_to_vector (i64 FPR64:$Rn))),
            (v2i64 (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)),
                                  (i64 FPR64:$Rn), dsub))>;

def : Pat<(v4f32 (scalar_to_vector (f32 FPR32:$Rn))),
          (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), FPR32:$Rn, ssub)>;
def : Pat<(v2f32 (scalar_to_vector (f32 FPR32:$Rn))),
          (INSERT_SUBREG (v2f32 (IMPLICIT_DEF)), FPR32:$Rn, ssub)>;
def : Pat<(v2f64 (scalar_to_vector (f64 FPR64:$Rn))),
          (INSERT_SUBREG (v2f64 (IMPLICIT_DEF)), FPR64:$Rn, dsub)>;

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

// Copy an element at a constant index in one vector into a constant indexed
// element of another.
// FIXME refactor to a shared class/dev parameterized on vector type, vector
// index type and INS extension
def : Pat<(v16i8 (int_arm64_neon_vcopy_lane
                   (v16i8 V128:$Vd), VectorIndexB:$idx, (v16i8 V128:$Vs),
                   VectorIndexB:$idx2)),
          (v16i8 (INSvi8lane
                   V128:$Vd, VectorIndexB:$idx, V128:$Vs, VectorIndexB:$idx2)
          )>;
def : Pat<(v8i16 (int_arm64_neon_vcopy_lane
                   (v8i16 V128:$Vd), VectorIndexH:$idx, (v8i16 V128:$Vs),
                   VectorIndexH:$idx2)),
          (v8i16 (INSvi16lane
                   V128:$Vd, VectorIndexH:$idx, V128:$Vs, VectorIndexH:$idx2)
          )>;
def : Pat<(v4i32 (int_arm64_neon_vcopy_lane
                   (v4i32 V128:$Vd), VectorIndexS:$idx, (v4i32 V128:$Vs),
                   VectorIndexS:$idx2)),
          (v4i32 (INSvi32lane
                   V128:$Vd, VectorIndexS:$idx, V128:$Vs, VectorIndexS:$idx2)
          )>;
def : Pat<(v2i64 (int_arm64_neon_vcopy_lane
                   (v2i64 V128:$Vd), VectorIndexD:$idx, (v2i64 V128:$Vs),
                   VectorIndexD:$idx2)),
          (v2i64 (INSvi64lane
                   V128:$Vd, VectorIndexD:$idx, V128:$Vs, VectorIndexD:$idx2)
          )>;

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

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

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

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

defm : Neon_INS_elt_pattern<v4f32, v2f32, f32, INSvi32lane>;
defm : Neon_INS_elt_pattern<v2f64, v1f64, f64, INSvi64lane>;
defm : Neon_INS_elt_pattern<v16i8, v8i8,  i32, INSvi8lane>;
defm : Neon_INS_elt_pattern<v8i16, v4i16, i32, INSvi16lane>;
defm : Neon_INS_elt_pattern<v4i32, v2i32, i32, INSvi32lane>;
defm : Neon_INS_elt_pattern<v2i64, v1i64, i64, INSvi32lane>;


// Floating point vector extractions are codegen'd as either a sequence of
// subregister extractions, possibly fed by an INS if the lane number is
// anything other than zero.
def : Pat<(vector_extract (v2f64 V128:$Rn), 0),
          (f64 (EXTRACT_SUBREG V128:$Rn, dsub))>;
def : Pat<(vector_extract (v4f32 V128:$Rn), 0),
          (f32 (EXTRACT_SUBREG V128:$Rn, ssub))>;
def : Pat<(vector_extract (v2f64 V128:$Rn), VectorIndexD:$idx),
          (f64 (EXTRACT_SUBREG
            (INSvi64lane (v2f64 (IMPLICIT_DEF)), 0,
                         V128:$Rn, VectorIndexD:$idx),
            dsub))>;
def : Pat<(vector_extract (v4f32 V128:$Rn), VectorIndexS:$idx),
          (f32 (EXTRACT_SUBREG
            (INSvi32lane (v4f32 (IMPLICIT_DEF)), 0,
                         V128:$Rn, VectorIndexS:$idx),
            ssub))>;

// All concat_vectors operations are canonicalised to act on i64 vectors for
// ARM64. In the general case we need an instruction, which had just as well be
// INS.
class ConcatPat<ValueType DstTy, ValueType SrcTy>
  : Pat<(DstTy (concat_vectors (SrcTy V64:$Rd), V64:$Rn)),
        (INSvi64lane (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub), 1,
                     (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rn, dsub), 0)>;

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

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

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

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

defm ADDV    : SIMDAcrossLanesBHS<0, 0b11011, "addv">;
defm SMAXV   : SIMDAcrossLanesBHS<0, 0b01010, "smaxv">;
defm SMINV   : SIMDAcrossLanesBHS<0, 0b11010, "sminv">;
defm UMAXV   : SIMDAcrossLanesBHS<1, 0b01010, "umaxv">;
defm UMINV   : SIMDAcrossLanesBHS<1, 0b11010, "uminv">;
defm SADDLV  : SIMDAcrossLanesHSD<0, 0b00011, "saddlv">;
defm UADDLV  : SIMDAcrossLanesHSD<1, 0b00011, "uaddlv">;
defm FMAXNMV : SIMDAcrossLanesS<0b01100, 0, "fmaxnmv", int_arm64_neon_fmaxnmv>;
defm FMAXV   : SIMDAcrossLanesS<0b01111, 0, "fmaxv", int_arm64_neon_fmaxv>;
defm FMINNMV : SIMDAcrossLanesS<0b01100, 1, "fminnmv", int_arm64_neon_fminnmv>;
defm FMINV   : SIMDAcrossLanesS<0b01111, 1, "fminv", int_arm64_neon_fminv>;

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

def : Pat<(i32 (intOp (v4i32 V128:$Rn))),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
           (!cast<Instruction>(!strconcat(baseOpc, "v4i32v")) V128:$Rn), ssub),
          ssub))>;
}

multiclass SIMDAcrossLanesUnsignedIntrinsic<string baseOpc, Intrinsic intOp> {
// If there is a masking operation keeping only what has been actually
// generated, consume it.
  def : Pat<(i32 (and (i32 (intOp (v8i8 V64:$Rn))), maski8_or_more)),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v8i8v")) V64:$Rn), bsub),
          ssub))>;
  def : Pat<(i32 (intOp (v8i8 V64:$Rn))),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v8i8v")) V64:$Rn), bsub),
          ssub))>;
// If there is a masking operation keeping only what has been actually
// generated, consume it.
def : Pat<(i32 (and (i32 (intOp (v16i8 V128:$Rn))), maski8_or_more)),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v16i8v")) V128:$Rn), bsub),
          ssub))>;
def : Pat<(i32 (intOp (v16i8 V128:$Rn))),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v16i8v")) V128:$Rn), bsub),
          ssub))>;

// If there is a masking operation keeping only what has been actually
// generated, consume it.
def : Pat<(i32 (and (i32 (intOp (v4i16 V64:$Rn))), maski16_or_more)),
          (i32 (EXTRACT_SUBREG
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
              (!cast<Instruction>(!strconcat(baseOpc, "v4i16v")) V64:$Rn), hsub),
            ssub))>;
def : Pat<(i32 (intOp (v4i16 V64:$Rn))),
          (i32 (EXTRACT_SUBREG
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
              (!cast<Instruction>(!strconcat(baseOpc, "v4i16v")) V64:$Rn), hsub),
            ssub))>;
// If there is a masking operation keeping only what has been actually
// generated, consume it.
def : Pat<(i32 (and (i32 (intOp (v8i16 V128:$Rn))), maski16_or_more)),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v8i16v")) V128:$Rn), hsub),
          ssub))>;
def : Pat<(i32 (intOp (v8i16 V128:$Rn))),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v8i16v")) V128:$Rn), hsub),
          ssub))>;

def : Pat<(i32 (intOp (v4i32 V128:$Rn))),
        (i32 (EXTRACT_SUBREG
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
            (!cast<Instruction>(!strconcat(baseOpc, "v4i32v")) V128:$Rn), ssub),
          ssub))>;

}

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

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

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

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

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

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

defm : SIMDAcrossLanesSignedIntrinsic<"ADDV",  int_arm64_neon_saddv>;
// vaddv_[su]32 is special; -> ADDP Vd.2S,Vn.2S,Vm.2S; return Vd.s[0];Vn==Vm
def : Pat<(i32 (int_arm64_neon_saddv (v2i32 V64:$Rn))),
          (EXTRACT_SUBREG (ADDPv2i32 V64:$Rn, V64:$Rn), ssub)>;

defm : SIMDAcrossLanesUnsignedIntrinsic<"ADDV",  int_arm64_neon_uaddv>;
// vaddv_[su]32 is special; -> ADDP Vd.2S,Vn.2S,Vm.2S; return Vd.s[0];Vn==Vm
def : Pat<(i32 (int_arm64_neon_uaddv (v2i32 V64:$Rn))),
          (EXTRACT_SUBREG (ADDPv2i32 V64:$Rn, V64:$Rn), ssub)>;

defm : SIMDAcrossLanesSignedIntrinsic<"SMAXV", int_arm64_neon_smaxv>;
def : Pat<(i32 (int_arm64_neon_smaxv (v2i32 V64:$Rn))),
           (EXTRACT_SUBREG (SMAXPv2i32 V64:$Rn, V64:$Rn), ssub)>;

defm : SIMDAcrossLanesSignedIntrinsic<"SMINV", int_arm64_neon_sminv>;
def : Pat<(i32 (int_arm64_neon_sminv (v2i32 V64:$Rn))),
           (EXTRACT_SUBREG (SMINPv2i32 V64:$Rn, V64:$Rn), ssub)>;

defm : SIMDAcrossLanesUnsignedIntrinsic<"UMAXV", int_arm64_neon_umaxv>;
def : Pat<(i32 (int_arm64_neon_umaxv (v2i32 V64:$Rn))),
           (EXTRACT_SUBREG (UMAXPv2i32 V64:$Rn, V64:$Rn), ssub)>;

defm : SIMDAcrossLanesUnsignedIntrinsic<"UMINV", int_arm64_neon_uminv>;
def : Pat<(i32 (int_arm64_neon_uminv (v2i32 V64:$Rn))),
           (EXTRACT_SUBREG (UMINPv2i32 V64:$Rn, V64:$Rn), ssub)>;

defm : SIMDAcrossLanesSignedLongIntrinsic<"SADDLV", int_arm64_neon_saddlv>;
defm : SIMDAcrossLanesUnsignedLongIntrinsic<"UADDLV", int_arm64_neon_uaddlv>;

// The vaddlv_s32 intrinsic gets mapped to SADDLP.
def : Pat<(i64 (int_arm64_neon_saddlv (v2i32 V64:$Rn))),
          (i64 (EXTRACT_SUBREG
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
              (SADDLPv2i32_v1i64 V64:$Rn), dsub),
            dsub))>;
// The vaddlv_u32 intrinsic gets mapped to UADDLP.
def : Pat<(i64 (int_arm64_neon_uaddlv (v2i32 V64:$Rn))),
          (i64 (EXTRACT_SUBREG
            (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)),
              (UADDLPv2i32_v1i64 V64:$Rn), dsub),
            dsub))>;

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

// AdvSIMD BIC
defm BIC : SIMDModifiedImmVectorShiftTied<1, 0b11, 0b01, "bic", ARM64bici>;
// AdvSIMD ORR
defm ORR : SIMDModifiedImmVectorShiftTied<0, 0b11, 0b01, "orr", ARM64orri>;

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

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

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

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

// AdvSIMD FMOV
def FMOVv2f64_ns : SIMDModifiedImmVectorNoShift<1, 1, 0b1111, V128, fpimm8,
                                              "fmov", ".2d",
                       [(set (v2f64 V128:$Rd), (ARM64fmov imm0_255:$imm8))]>;
def FMOVv2f32_ns : SIMDModifiedImmVectorNoShift<0, 0, 0b1111, V64,  fpimm8,
                                              "fmov", ".2s",
                       [(set (v2f32 V64:$Rd), (ARM64fmov imm0_255:$imm8))]>;
def FMOVv4f32_ns : SIMDModifiedImmVectorNoShift<1, 0, 0b1111, V128, fpimm8,
                                              "fmov", ".4s",
                       [(set (v4f32 V128:$Rd), (ARM64fmov imm0_255:$imm8))]>;

// AdvSIMD MOVI

// EDIT byte mask: scalar
let isReMaterializable = 1, isAsCheapAsAMove = 1 in
def MOVID      : SIMDModifiedImmScalarNoShift<0, 1, 0b1110, "movi",
                    [(set FPR64:$Rd, simdimmtype10:$imm8)]>;
// The movi_edit node has the immediate value already encoded, so we use
// a plain imm0_255 here.
def : Pat<(f64 (ARM64movi_edit imm0_255:$shift)),
          (MOVID imm0_255:$shift)>;

def : Pat<(v1i64 immAllZerosV), (MOVID (i32 0))>;
def : Pat<(v2i32 immAllZerosV), (MOVID (i32 0))>;
def : Pat<(v4i16 immAllZerosV), (MOVID (i32 0))>;
def : Pat<(v8i8  immAllZerosV), (MOVID (i32 0))>;

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

// EDIT byte mask: 2d

// The movi_edit node has the immediate value already encoded, so we use
// a plain imm0_255 in the pattern
let isReMaterializable = 1, isAsCheapAsAMove = 1 in
def MOVIv2d_ns   : SIMDModifiedImmVectorNoShift<1, 1, 0b1110, V128,
                                                simdimmtype10,
                                                "movi", ".2d",
                   [(set (v2i64 V128:$Rd), (ARM64movi_edit imm0_255:$imm8))]>;


// Use movi.2d to materialize 0.0 if the HW does zero-cycle zeroing.
// Complexity is added to break a tie with a plain MOVI.
let AddedComplexity = 1 in {
def : Pat<(f32   fpimm0),
          (f32 (EXTRACT_SUBREG (v2i64 (MOVIv2d_ns (i32 0))), ssub))>,
      Requires<[HasZCZ]>;
def : Pat<(f64   fpimm0),
          (f64 (EXTRACT_SUBREG (v2i64 (MOVIv2d_ns (i32 0))), dsub))>,
      Requires<[HasZCZ]>;
}

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

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

def : Pat<(v2f64 (ARM64dup (f64 fpimm0))), (MOVIv2d_ns (i32 0))>;
def : Pat<(v4f32 (ARM64dup (f32 fpimm0))), (MOVIv2d_ns (i32 0))>;

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

// FIXME: these should be canonical but the TableGen alias printer can't cope
// with syntax variants.
def : InstAlias<"movi $Vd.4h, $imm", (MOVIv4i16 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"movi $Vd.8h, $imm", (MOVIv8i16 V128:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"movi $Vd.2s, $imm", (MOVIv2i32 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"movi $Vd.4s, $imm", (MOVIv4i32 V128:$Vd, imm0_255:$imm, 0), 0>;

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

def : Pat<(v2i32 (ARM64movi_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MOVIv2i32 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v4i32 (ARM64movi_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MOVIv4i32 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v4i16 (ARM64movi_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MOVIv4i16 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v8i16 (ARM64movi_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MOVIv8i16 imm0_255:$imm8, imm:$shift)>;

// EDIT per word: 2s & 4s with MSL shifter
def MOVIv2s_msl  : SIMDModifiedImmMoveMSL<0, 0, {1,1,0,?}, V64, "movi", ".2s",
                      [(set (v2i32 V64:$Rd),
                            (ARM64movi_msl imm0_255:$imm8, (i32 imm:$shift)))]>;
def MOVIv4s_msl  : SIMDModifiedImmMoveMSL<1, 0, {1,1,0,?}, V128, "movi", ".4s",
                      [(set (v4i32 V128:$Rd),
                            (ARM64movi_msl imm0_255:$imm8, (i32 imm:$shift)))]>;

// Per byte: 8b & 16b
def MOVIv8b_ns   : SIMDModifiedImmVectorNoShift<0, 0, 0b1110, V64,  imm0_255,
                                                 "movi", ".8b",
                       [(set (v8i8 V64:$Rd), (ARM64movi imm0_255:$imm8))]>;
def MOVIv16b_ns  : SIMDModifiedImmVectorNoShift<1, 0, 0b1110, V128, imm0_255,
                                                 "movi", ".16b",
                       [(set (v16i8 V128:$Rd), (ARM64movi imm0_255:$imm8))]>;

// AdvSIMD MVNI

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

// FIXME: these should be canonical, but TableGen can't do aliases & syntax
// variants together.
def : InstAlias<"mvni $Vd.4h, $imm", (MVNIv4i16 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni $Vd.8h, $imm", (MVNIv8i16 V128:$Vd, imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni $Vd.2s, $imm", (MVNIv2i32 V64:$Vd,  imm0_255:$imm, 0), 0>;
def : InstAlias<"mvni $Vd.4s, $imm", (MVNIv4i32 V128:$Vd, imm0_255:$imm, 0), 0>;

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

def : Pat<(v2i32 (ARM64mvni_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MVNIv2i32 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v4i32 (ARM64mvni_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MVNIv4i32 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v4i16 (ARM64mvni_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MVNIv4i16 imm0_255:$imm8, imm:$shift)>;
def : Pat<(v8i16 (ARM64mvni_shift imm0_255:$imm8, (i32 imm:$shift))),
          (MVNIv8i16 imm0_255:$imm8, imm:$shift)>;

// EDIT per word: 2s & 4s with MSL shifter
def MVNIv2s_msl   : SIMDModifiedImmMoveMSL<0, 1, {1,1,0,?}, V64, "mvni", ".2s",
                      [(set (v2i32 V64:$Rd),
                            (ARM64mvni_msl imm0_255:$imm8, (i32 imm:$shift)))]>;
def MVNIv4s_msl   : SIMDModifiedImmMoveMSL<1, 1, {1,1,0,?}, V128, "mvni", ".4s",
                      [(set (v4i32 V128:$Rd),
                            (ARM64mvni_msl imm0_255:$imm8, (i32 imm:$shift)))]>;

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

let neverHasSideEffects = 1 in {
  defm FMLA  : SIMDFPIndexedSDTied<0, 0b0001, "fmla">;
  defm FMLS  : SIMDFPIndexedSDTied<0, 0b0101, "fmls">;
}

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

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

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

multiclass FMLSIndexedAfterNegPatterns<SDPatternOperator OpNode> {
  // 3 variants for the .2s version: DUPLANE from 128-bit, DUPLANE from 64-bit
  // and DUP scalar.
  def : Pat<(v2f32 (OpNode (v2f32 V64:$Rd), (v2f32 V64:$Rn),
                           (ARM64duplane32 (v4f32 (fneg V128:$Rm)),
                                           VectorIndexS:$idx))),
            (FMLSv2i32_indexed V64:$Rd, V64:$Rn, V128:$Rm, VectorIndexS:$idx)>;
  def : Pat<(v2f32 (OpNode (v2f32 V64:$Rd), (v2f32 V64:$Rn),
                           (v2f32 (ARM64duplane32
                                      (v4f32 (insert_subvector undef,
                                                 (v2f32 (fneg V64:$Rm)),
                                                 (i32 0))),
                                      VectorIndexS:$idx)))),
            (FMLSv2i32_indexed V64:$Rd, V64:$Rn,
                               (SUBREG_TO_REG (i32 0), V64:$Rm, dsub),
                               VectorIndexS:$idx)>;
  def : Pat<(v2f32 (OpNode (v2f32 V64:$Rd), (v2f32 V64:$Rn),
                           (ARM64dup (f32 (fneg FPR32Op:$Rm))))),
            (FMLSv2i32_indexed V64:$Rd, V64:$Rn,
                (SUBREG_TO_REG (i32 0), FPR32Op:$Rm, ssub), (i64 0))>;

  // 3 variants for the .4s version: DUPLANE from 128-bit, DUPLANE from 64-bit
  // and DUP scalar.
  def : Pat<(v4f32 (OpNode (v4f32 V128:$Rd), (v4f32 V128:$Rn),
                           (ARM64duplane32 (v4f32 (fneg V128:$Rm)),
                                           VectorIndexS:$idx))),
            (FMLSv4i32_indexed V128:$Rd, V128:$Rn, V128:$Rm,
                               VectorIndexS:$idx)>;
  def : Pat<(v4f32 (OpNode (v4f32 V128:$Rd), (v4f32 V128:$Rn),
                           (v4f32 (ARM64duplane32
                                      (v4f32 (insert_subvector undef,
                                                 (v2f32 (fneg V64:$Rm)),
                                                 (i32 0))),
                                      VectorIndexS:$idx)))),
            (FMLSv4i32_indexed V128:$Rd, V128:$Rn,
                               (SUBREG_TO_REG (i32 0), V64:$Rm, dsub),
                               VectorIndexS:$idx)>;
  def : Pat<(v4f32 (OpNode (v4f32 V128:$Rd), (v4f32 V128:$Rn),
                           (ARM64dup (f32 (fneg FPR32Op:$Rm))))),
            (FMLSv4i32_indexed V128:$Rd, V128:$Rn,
                (SUBREG_TO_REG (i32 0), FPR32Op:$Rm, ssub), (i64 0))>;

  // 2 variants for the .2d version: DUPLANE from 128-bit, and DUP scalar
  // (DUPLANE from 64-bit would be trivial).
  def : Pat<(v2f64 (OpNode (v2f64 V128:$Rd), (v2f64 V128:$Rn),
                           (ARM64duplane64 (v2f64 (fneg V128:$Rm)),
                                           VectorIndexD:$idx))),
            (FMLSv2i64_indexed
                V128:$Rd, V128:$Rn, V128:$Rm, VectorIndexS:$idx)>;
  def : Pat<(v2f64 (OpNode (v2f64 V128:$Rd), (v2f64 V128:$Rn),
                           (ARM64dup (f64 (fneg FPR64Op:$Rm))))),
            (FMLSv2i64_indexed V128:$Rd, V128:$Rn,
                (SUBREG_TO_REG (i32 0), FPR64Op:$Rm, dsub), (i64 0))>;

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

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

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

defm FMULX : SIMDFPIndexedSD<1, 0b1001, "fmulx", int_arm64_neon_fmulx>;
defm FMUL  : SIMDFPIndexedSD<0, 0b1001, "fmul", fmul>;

def : Pat<(v2f32 (fmul V64:$Rn, (ARM64dup (f32 FPR32:$Rm)))),
          (FMULv2i32_indexed V64:$Rn,
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR32:$Rm, ssub),
            (i64 0))>;
def : Pat<(v4f32 (fmul V128:$Rn, (ARM64dup (f32 FPR32:$Rm)))),
          (FMULv4i32_indexed V128:$Rn,
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR32:$Rm, ssub),
            (i64 0))>;
def : Pat<(v2f64 (fmul V128:$Rn, (ARM64dup (f64 FPR64:$Rm)))),
          (FMULv2i64_indexed V128:$Rn,
            (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR64:$Rm, dsub),
            (i64 0))>;

defm SQDMULH : SIMDIndexedHS<0, 0b1100, "sqdmulh", int_arm64_neon_sqdmulh>;
defm SQRDMULH : SIMDIndexedHS<0, 0b1101, "sqrdmulh", int_arm64_neon_sqrdmulh>;
defm MLA   : SIMDVectorIndexedHSTied<1, 0b0000, "mla",
              TriOpFrag<(add node:$LHS, (mul node:$MHS, node:$RHS))>>;
defm MLS   : SIMDVectorIndexedHSTied<1, 0b0100, "mls",
              TriOpFrag<(sub node:$LHS, (mul node:$MHS, node:$RHS))>>;
defm MUL   : SIMDVectorIndexedHS<0, 0b1000, "mul", mul>;
defm SMLAL : SIMDVectorIndexedLongSDTied<0, 0b0010, "smlal",
    TriOpFrag<(add node:$LHS, (int_arm64_neon_smull node:$MHS, node:$RHS))>>;
defm SMLSL : SIMDVectorIndexedLongSDTied<0, 0b0110, "smlsl",
    TriOpFrag<(sub node:$LHS, (int_arm64_neon_smull node:$MHS, node:$RHS))>>;
defm SMULL : SIMDVectorIndexedLongSD<0, 0b1010, "smull",
                int_arm64_neon_smull>;
defm SQDMLAL : SIMDIndexedLongSQDMLXSDTied<0, 0b0011, "sqdmlal",
                                           int_arm64_neon_sqadd>;
defm SQDMLSL : SIMDIndexedLongSQDMLXSDTied<0, 0b0111, "sqdmlsl",
                                           int_arm64_neon_sqsub>;
defm SQDMULL : SIMDIndexedLongSD<0, 0b1011, "sqdmull", int_arm64_neon_sqdmull>;
defm UMLAL   : SIMDVectorIndexedLongSDTied<1, 0b0010, "umlal",
    TriOpFrag<(add node:$LHS, (int_arm64_neon_umull node:$MHS, node:$RHS))>>;
defm UMLSL   : SIMDVectorIndexedLongSDTied<1, 0b0110, "umlsl",
    TriOpFrag<(sub node:$LHS, (int_arm64_neon_umull node:$MHS, node:$RHS))>>;
defm UMULL   : SIMDVectorIndexedLongSD<1, 0b1010, "umull",
                int_arm64_neon_umull>;

// A scalar sqdmull with the second operand being a vector lane can be
// handled directly with the indexed instruction encoding.
def : Pat<(int_arm64_neon_sqdmulls_scalar (i32 FPR32:$Rn),
                                          (vector_extract (v4i32 V128:$Vm),
                                                           VectorIndexS:$idx)),
          (SQDMULLv1i64_indexed FPR32:$Rn, V128:$Vm, VectorIndexS:$idx)>;

//----------------------------------------------------------------------------
// AdvSIMD scalar shift instructions
//----------------------------------------------------------------------------
defm FCVTZS : SIMDScalarRShiftSD<0, 0b11111, "fcvtzs">;
defm FCVTZU : SIMDScalarRShiftSD<1, 0b11111, "fcvtzu">;
defm SCVTF  : SIMDScalarRShiftSD<0, 0b11100, "scvtf">;
defm UCVTF  : SIMDScalarRShiftSD<1, 0b11100, "ucvtf">;
// Codegen patterns for the above. We don't put these directly on the
// instructions because TableGen's type inference can't handle the truth.
// Having the same base pattern for fp <--> int totally freaks it out.
def : Pat<(int_arm64_neon_vcvtfp2fxs FPR32:$Rn, vecshiftR32:$imm),
          (FCVTZSs FPR32:$Rn, vecshiftR32:$imm)>;
def : Pat<(int_arm64_neon_vcvtfp2fxu FPR32:$Rn, vecshiftR32:$imm),
          (FCVTZUs FPR32:$Rn, vecshiftR32:$imm)>;
def : Pat<(i64 (int_arm64_neon_vcvtfp2fxs (f64 FPR64:$Rn), vecshiftR64:$imm)),
          (FCVTZSd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(i64 (int_arm64_neon_vcvtfp2fxu (f64 FPR64:$Rn), vecshiftR64:$imm)),
          (FCVTZUd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(v1i64 (int_arm64_neon_vcvtfp2fxs (v1f64 FPR64:$Rn),
                                            vecshiftR64:$imm)),
          (FCVTZSd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(v1i64 (int_arm64_neon_vcvtfp2fxu (v1f64 FPR64:$Rn),
                                            vecshiftR64:$imm)),
          (FCVTZUd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(int_arm64_neon_vcvtfxs2fp FPR32:$Rn, vecshiftR32:$imm),
          (SCVTFs FPR32:$Rn, vecshiftR32:$imm)>;
def : Pat<(int_arm64_neon_vcvtfxu2fp FPR32:$Rn, vecshiftR32:$imm),
          (UCVTFs FPR32:$Rn, vecshiftR32:$imm)>;
def : Pat<(f64 (int_arm64_neon_vcvtfxs2fp (i64 FPR64:$Rn), vecshiftR64:$imm)),
          (SCVTFd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(f64 (int_arm64_neon_vcvtfxu2fp (i64 FPR64:$Rn), vecshiftR64:$imm)),
          (UCVTFd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(v1f64 (int_arm64_neon_vcvtfxs2fp (v1i64 FPR64:$Rn),
                                            vecshiftR64:$imm)),
          (SCVTFd FPR64:$Rn, vecshiftR64:$imm)>;
def : Pat<(v1f64 (int_arm64_neon_vcvtfxu2fp (v1i64 FPR64:$Rn),
                                            vecshiftR64:$imm)),
          (UCVTFd FPR64:$Rn, vecshiftR64:$imm)>;

defm SHL      : SIMDScalarLShiftD<   0, 0b01010, "shl", ARM64vshl>;
defm SLI      : SIMDScalarLShiftDTied<1, 0b01010, "sli">;
defm SQRSHRN  : SIMDScalarRShiftBHS< 0, 0b10011, "sqrshrn",
                                     int_arm64_neon_sqrshrn>;
defm SQRSHRUN : SIMDScalarRShiftBHS< 1, 0b10001, "sqrshrun",
                                     int_arm64_neon_sqrshrun>;
defm SQSHLU   : SIMDScalarLShiftBHSD<1, 0b01100, "sqshlu", ARM64sqshlui>;
defm SQSHL    : SIMDScalarLShiftBHSD<0, 0b01110, "sqshl", ARM64sqshli>;
defm SQSHRN   : SIMDScalarRShiftBHS< 0, 0b10010, "sqshrn",
                                     int_arm64_neon_sqshrn>;
defm SQSHRUN  : SIMDScalarRShiftBHS< 1, 0b10000, "sqshrun",
                                     int_arm64_neon_sqshrun>;
defm SRI      : SIMDScalarRShiftDTied<   1, 0b01000, "sri">;
defm SRSHR    : SIMDScalarRShiftD<   0, 0b00100, "srshr", ARM64srshri>;
defm SRSRA    : SIMDScalarRShiftDTied<   0, 0b00110, "srsra",
    TriOpFrag<(add node:$LHS,
                   (ARM64srshri node:$MHS, node:$RHS))>>;
defm SSHR     : SIMDScalarRShiftD<   0, 0b00000, "sshr", ARM64vashr>;
defm SSRA     : SIMDScalarRShiftDTied<   0, 0b00010, "ssra",
    TriOpFrag<(add node:$LHS,
                   (ARM64vashr node:$MHS, node:$RHS))>>;
defm UQRSHRN  : SIMDScalarRShiftBHS< 1, 0b10011, "uqrshrn",
                                     int_arm64_neon_uqrshrn>;
defm UQSHL    : SIMDScalarLShiftBHSD<1, 0b01110, "uqshl", ARM64uqshli>;
defm UQSHRN   : SIMDScalarRShiftBHS< 1, 0b10010, "uqshrn",
                                     int_arm64_neon_uqshrn>;
defm URSHR    : SIMDScalarRShiftD<   1, 0b00100, "urshr", ARM64urshri>;
defm URSRA    : SIMDScalarRShiftDTied<   1, 0b00110, "ursra",
    TriOpFrag<(add node:$LHS,
                   (ARM64urshri node:$MHS, node:$RHS))>>;
defm USHR     : SIMDScalarRShiftD<   1, 0b00000, "ushr", ARM64vlshr>;
defm USRA     : SIMDScalarRShiftDTied<   1, 0b00010, "usra",
    TriOpFrag<(add node:$LHS,
                   (ARM64vlshr node:$MHS, node:$RHS))>>;

//----------------------------------------------------------------------------
// AdvSIMD vector shift instructions
//----------------------------------------------------------------------------
defm FCVTZS:SIMDVectorRShiftSD<0, 0b11111, "fcvtzs", int_arm64_neon_vcvtfp2fxs>;
defm FCVTZU:SIMDVectorRShiftSD<1, 0b11111, "fcvtzu", int_arm64_neon_vcvtfp2fxu>;
defm SCVTF: SIMDVectorRShiftSDToFP<0, 0b11100, "scvtf",
                                   int_arm64_neon_vcvtfxs2fp>;
defm RSHRN   : SIMDVectorRShiftNarrowBHS<0, 0b10001, "rshrn",
                                         int_arm64_neon_rshrn>;
defm SHL     : SIMDVectorLShiftBHSD<0, 0b01010, "shl", ARM64vshl>;
defm SHRN    : SIMDVectorRShiftNarrowBHS<0, 0b10000, "shrn",
                          BinOpFrag<(trunc (ARM64vashr node:$LHS, node:$RHS))>>;
defm SLI     : SIMDVectorLShiftBHSDTied<1, 0b01010, "sli", int_arm64_neon_vsli>;
def : Pat<(v1i64 (int_arm64_neon_vsli (v1i64 FPR64:$Rd), (v1i64 FPR64:$Rn),
                                      (i32 vecshiftL64:$imm))),
          (SLId FPR64:$Rd, FPR64:$Rn, vecshiftL64:$imm)>;
defm SQRSHRN : SIMDVectorRShiftNarrowBHS<0, 0b10011, "sqrshrn",
                                         int_arm64_neon_sqrshrn>;
defm SQRSHRUN: SIMDVectorRShiftNarrowBHS<1, 0b10001, "sqrshrun",
                                         int_arm64_neon_sqrshrun>;
defm SQSHLU : SIMDVectorLShiftBHSD<1, 0b01100, "sqshlu", ARM64sqshlui>;
defm SQSHL  : SIMDVectorLShiftBHSD<0, 0b01110, "sqshl", ARM64sqshli>;
defm SQSHRN  : SIMDVectorRShiftNarrowBHS<0, 0b10010, "sqshrn",
                                         int_arm64_neon_sqshrn>;
defm SQSHRUN : SIMDVectorRShiftNarrowBHS<1, 0b10000, "sqshrun",
                                         int_arm64_neon_sqshrun>;
defm SRI     : SIMDVectorRShiftBHSDTied<1, 0b01000, "sri", int_arm64_neon_vsri>;
def : Pat<(v1i64 (int_arm64_neon_vsri (v1i64 FPR64:$Rd), (v1i64 FPR64:$Rn),
                                      (i32 vecshiftR64:$imm))),
          (SRId FPR64:$Rd, FPR64:$Rn, vecshiftR64:$imm)>;
defm SRSHR   : SIMDVectorRShiftBHSD<0, 0b00100, "srshr", ARM64srshri>;
defm SRSRA   : SIMDVectorRShiftBHSDTied<0, 0b00110, "srsra",
                 TriOpFrag<(add node:$LHS,
                                (ARM64srshri node:$MHS, node:$RHS))> >;
defm SSHLL   : SIMDVectorLShiftLongBHSD<0, 0b10100, "sshll",
                BinOpFrag<(ARM64vshl (sext node:$LHS), node:$RHS)>>;

defm SSHR    : SIMDVectorRShiftBHSD<0, 0b00000, "sshr", ARM64vashr>;
defm SSRA    : SIMDVectorRShiftBHSDTied<0, 0b00010, "ssra",
                TriOpFrag<(add node:$LHS, (ARM64vashr node:$MHS, node:$RHS))>>;
defm UCVTF   : SIMDVectorRShiftSDToFP<1, 0b11100, "ucvtf",
                        int_arm64_neon_vcvtfxu2fp>;
defm UQRSHRN : SIMDVectorRShiftNarrowBHS<1, 0b10011, "uqrshrn",
                                         int_arm64_neon_uqrshrn>;
defm UQSHL   : SIMDVectorLShiftBHSD<1, 0b01110, "uqshl", ARM64uqshli>;
defm UQSHRN  : SIMDVectorRShiftNarrowBHS<1, 0b10010, "uqshrn",
                                         int_arm64_neon_uqshrn>;
defm URSHR   : SIMDVectorRShiftBHSD<1, 0b00100, "urshr", ARM64urshri>;
defm URSRA   : SIMDVectorRShiftBHSDTied<1, 0b00110, "ursra",
                TriOpFrag<(add node:$LHS,
                               (ARM64urshri node:$MHS, node:$RHS))> >;
defm USHLL   : SIMDVectorLShiftLongBHSD<1, 0b10100, "ushll",
                BinOpFrag<(ARM64vshl (zext node:$LHS), node:$RHS)>>;
defm USHR    : SIMDVectorRShiftBHSD<1, 0b00000, "ushr", ARM64vlshr>;
defm USRA    : SIMDVectorRShiftBHSDTied<1, 0b00010, "usra",
                TriOpFrag<(add node:$LHS, (ARM64vlshr node:$MHS, node:$RHS))> >;

// SHRN patterns for when a logical right shift was used instead of arithmetic
// (the immediate guarantees no sign bits actually end up in the result so it
// doesn't matter).
def : Pat<(v8i8 (trunc (ARM64vlshr (v8i16 V128:$Rn), vecshiftR16Narrow:$imm))),
          (SHRNv8i8_shift V128:$Rn, vecshiftR16Narrow:$imm)>;
def : Pat<(v4i16 (trunc (ARM64vlshr (v4i32 V128:$Rn), vecshiftR32Narrow:$imm))),
          (SHRNv4i16_shift V128:$Rn, vecshiftR32Narrow:$imm)>;
def : Pat<(v2i32 (trunc (ARM64vlshr (v2i64 V128:$Rn), vecshiftR64Narrow:$imm))),
          (SHRNv2i32_shift V128:$Rn, vecshiftR64Narrow:$imm)>;

def : Pat<(v16i8 (concat_vectors (v8i8 V64:$Rd),
                                 (trunc (ARM64vlshr (v8i16 V128:$Rn),
                                                    vecshiftR16Narrow:$imm)))),
          (SHRNv16i8_shift (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
                           V128:$Rn, vecshiftR16Narrow:$imm)>;
def : Pat<(v8i16 (concat_vectors (v4i16 V64:$Rd),
                                 (trunc (ARM64vlshr (v4i32 V128:$Rn),
                                                    vecshiftR32Narrow:$imm)))),
          (SHRNv8i16_shift (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
                           V128:$Rn, vecshiftR32Narrow:$imm)>;
def : Pat<(v4i32 (concat_vectors (v2i32 V64:$Rd),
                                 (trunc (ARM64vlshr (v2i64 V128:$Rn),
                                                    vecshiftR64Narrow:$imm)))),
          (SHRNv4i32_shift (INSERT_SUBREG (IMPLICIT_DEF), V64:$Rd, dsub),
                           V128:$Rn, vecshiftR32Narrow:$imm)>;

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

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

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

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

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

// If an integer is about to be converted to a floating point value,
// just load it on the floating point unit.
// These patterns are more complex because floating point loads do not
// support sign extension.
// The sign extension has to be explicitly added and is only supported for
// one step: byte-to-half, half-to-word, word-to-doubleword.
// SCVTF GPR -> FPR is 9 cycles.
// SCVTF FPR -> FPR is 4 cyclces.
// (sign extension with lengthen) SXTL FPR -> FPR is 2 cycles.
// Therefore, we can do 2 sign extensions and one SCVTF FPR -> FPR
// and still being faster.
// However, this is not good for code size.
// 8-bits -> float. 2 sizes step-up.
def : Pat <(f32 (sint_to_fp (i32 (sextloadi8 ro_indexed8:$addr)))),
           (SCVTFv1i32 (f32 (EXTRACT_SUBREG
                              (SSHLLv4i16_shift
                                (f64
                                  (EXTRACT_SUBREG
                                    (SSHLLv8i8_shift
                                      (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                                  (LDRBro ro_indexed8:$addr),
                                                  bsub),
                                     0),
                                   dsub)),
                               0),
                           ssub)))>, Requires<[NotForCodeSize]>;
def : Pat <(f32 (sint_to_fp (i32 (sextloadi8 am_indexed8:$addr)))),
           (SCVTFv1i32 (f32 (EXTRACT_SUBREG
                              (SSHLLv4i16_shift
                                (f64
                                  (EXTRACT_SUBREG
                                    (SSHLLv8i8_shift
                                      (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                                  (LDRBui am_indexed8:$addr),
                                                  bsub),
                                     0),
                                   dsub)),
                               0),
                           ssub)))>, Requires<[NotForCodeSize]>;
def : Pat <(f32 (sint_to_fp (i32 (sextloadi8 am_unscaled8:$addr)))),
           (SCVTFv1i32 (f32 (EXTRACT_SUBREG
                              (SSHLLv4i16_shift
                                (f64
                                  (EXTRACT_SUBREG
                                    (SSHLLv8i8_shift
                                      (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                                  (LDURBi am_unscaled8:$addr),
                                                  bsub),
                                     0),
                                   dsub)),
                               0),
                           ssub)))>, Requires<[NotForCodeSize]>;
// 16-bits -> float. 1 size step-up.
def : Pat <(f32 (sint_to_fp (i32 (sextloadi16 ro_indexed16:$addr)))),
           (SCVTFv1i32 (f32 (EXTRACT_SUBREG
                              (SSHLLv4i16_shift
                                (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                               (LDRHro ro_indexed16:$addr),
                                               hsub),
                               0),
                           ssub)))>, Requires<[NotForCodeSize]>;
def : Pat <(f32 (sint_to_fp (i32 (sextloadi16 am_indexed16:$addr)))),
           (SCVTFv1i32 (f32 (EXTRACT_SUBREG
                              (SSHLLv4i16_shift
                                (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                               (LDRHui am_indexed16:$addr),
                                               hsub),
                               0),
                           ssub)))>, Requires<[NotForCodeSize]>;
def : Pat <(f32 (sint_to_fp (i32 (sextloadi16 am_unscaled16:$addr)))),
           (SCVTFv1i32 (f32 (EXTRACT_SUBREG
                              (SSHLLv4i16_shift
                                (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                               (LDURHi am_unscaled16:$addr),
                                               hsub),
                               0),
                           ssub)))>, Requires<[NotForCodeSize]>;
// 32-bits to 32-bits are handled in target specific dag combine:
// performIntToFpCombine.
// 64-bits integer to 32-bits floating point, not possible with
// SCVTF on floating point registers (both source and destination
// must have the same size).

// Here are the patterns for 8, 16, 32, and 64-bits to double.
// 8-bits -> double. 3 size step-up: give up.
// 16-bits -> double. 2 size step.
def : Pat <(f64 (sint_to_fp (i32 (sextloadi16 ro_indexed16:$addr)))),
           (SCVTFv1i64 (f64 (EXTRACT_SUBREG
                              (SSHLLv2i32_shift
                                 (f64
                                  (EXTRACT_SUBREG
                                    (SSHLLv4i16_shift
                                      (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                                  (LDRHro ro_indexed16:$addr),
                                                  hsub),
                                     0),
                                   dsub)),
                               0),
                             dsub)))>, Requires<[NotForCodeSize]>;
def : Pat <(f64 (sint_to_fp (i32 (sextloadi16 am_indexed16:$addr)))),
           (SCVTFv1i64  (f64 (EXTRACT_SUBREG
                               (SSHLLv2i32_shift
                                 (f64
                                   (EXTRACT_SUBREG
                                     (SSHLLv4i16_shift
                                       (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                                  (LDRHui am_indexed16:$addr),
                                                  hsub),
                                      0),
                                    dsub)),
                                 0),
                              dsub)))>, Requires<[NotForCodeSize]>;
def : Pat <(f64 (sint_to_fp (i32 (sextloadi16 am_unscaled16:$addr)))),
           (SCVTFv1i64 (f64 (EXTRACT_SUBREG
                              (SSHLLv2i32_shift
                                (f64
                                  (EXTRACT_SUBREG
                                    (SSHLLv4i16_shift
                                     (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                                  (LDURHi am_unscaled16:$addr),
                                                  hsub),
                                      0),
                                   dsub)),
                               0),
                             dsub)))>, Requires<[NotForCodeSize]>;
// 32-bits -> double. 1 size step-up.
def : Pat <(f64 (sint_to_fp (i32 (load ro_indexed32:$addr)))),
           (SCVTFv1i64 (f64 (EXTRACT_SUBREG
                              (SSHLLv2i32_shift
                                (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                               (LDRSro ro_indexed32:$addr),
                                               ssub),
                               0),
                             dsub)))>, Requires<[NotForCodeSize]>;
def : Pat <(f64 (sint_to_fp (i32 (load am_indexed32:$addr)))),
           (SCVTFv1i64 (f64 (EXTRACT_SUBREG
                              (SSHLLv2i32_shift
                                (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                               (LDRSui am_indexed32:$addr),
                                               ssub),
                               0),
                             dsub)))>, Requires<[NotForCodeSize]>;
def : Pat <(f64 (sint_to_fp (i32 (load am_unscaled32:$addr)))),
           (SCVTFv1i64 (f64 (EXTRACT_SUBREG
                              (SSHLLv2i32_shift
                                (INSERT_SUBREG (f64 (IMPLICIT_DEF)),
                                               (LDURSi am_unscaled32:$addr),
                                               ssub),
                               0),
                             dsub)))>, Requires<[NotForCodeSize]>;
// 64-bits -> double are handled in target specific dag combine:
// performIntToFpCombine.


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

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

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

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

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

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

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

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

def : Pat<(v8i8 (ARM64dup (i32 (extloadi8 am_simdnoindex:$vaddr)))),
          (LD1Rv8b am_simdnoindex:$vaddr)>;
def : Pat<(v16i8 (ARM64dup (i32 (extloadi8 am_simdnoindex:$vaddr)))),
          (LD1Rv16b am_simdnoindex:$vaddr)>;
def : Pat<(v4i16 (ARM64dup (i32 (extloadi16 am_simdnoindex:$vaddr)))),
          (LD1Rv4h am_simdnoindex:$vaddr)>;
def : Pat<(v8i16 (ARM64dup (i32 (extloadi16 am_simdnoindex:$vaddr)))),
          (LD1Rv8h am_simdnoindex:$vaddr)>;
def : Pat<(v2i32 (ARM64dup (i32 (load am_simdnoindex:$vaddr)))),
          (LD1Rv2s am_simdnoindex:$vaddr)>;
def : Pat<(v4i32 (ARM64dup (i32 (load am_simdnoindex:$vaddr)))),
          (LD1Rv4s am_simdnoindex:$vaddr)>;
def : Pat<(v2i64 (ARM64dup (i64 (load am_simdnoindex:$vaddr)))),
          (LD1Rv2d am_simdnoindex:$vaddr)>;
def : Pat<(v1i64 (ARM64dup (i64 (load am_simdnoindex:$vaddr)))),
          (LD1Rv1d am_simdnoindex:$vaddr)>;
// Grab the floating point version too
def : Pat<(v2f32 (ARM64dup (f32 (load am_simdnoindex:$vaddr)))),
          (LD1Rv2s am_simdnoindex:$vaddr)>;
def : Pat<(v4f32 (ARM64dup (f32 (load am_simdnoindex:$vaddr)))),
          (LD1Rv4s am_simdnoindex:$vaddr)>;
def : Pat<(v2f64 (ARM64dup (f64 (load am_simdnoindex:$vaddr)))),
          (LD1Rv2d am_simdnoindex:$vaddr)>;
def : Pat<(v1f64 (ARM64dup (f64 (load am_simdnoindex:$vaddr)))),
          (LD1Rv1d am_simdnoindex:$vaddr)>;

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

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

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

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


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

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

let AddedComplexity = 8 in
class St1Lane128Pat<SDPatternOperator scalar_store, Operand VecIndex,
                    ValueType VTy, ValueType STy, Instruction ST1>
  : Pat<(scalar_store
             (STy (vector_extract (VTy VecListOne128:$Vt), VecIndex:$idx)),
             am_simdnoindex:$vaddr),
        (ST1 VecListOne128:$Vt, VecIndex:$idx, am_simdnoindex:$vaddr)>;

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

let AddedComplexity = 8 in
class St1Lane64Pat<SDPatternOperator scalar_store, Operand VecIndex,
                   ValueType VTy, ValueType STy, Instruction ST1>
  : Pat<(scalar_store
             (STy (vector_extract (VTy VecListOne64:$Vt), VecIndex:$idx)),
             am_simdnoindex:$vaddr),
        (ST1 (SUBREG_TO_REG (i32 0), VecListOne64:$Vt, dsub),
             VecIndex:$idx, am_simdnoindex:$vaddr)>;

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

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

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

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

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

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

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

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

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

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

def AESErr   : AESTiedInst<0b0100, "aese",   int_arm64_crypto_aese>;
def AESDrr   : AESTiedInst<0b0101, "aesd",   int_arm64_crypto_aesd>;
def AESMCrr  : AESInst<    0b0110, "aesmc",  int_arm64_crypto_aesmc>;
def AESIMCrr : AESInst<    0b0111, "aesimc", int_arm64_crypto_aesimc>;

def SHA1Crrr     : SHATiedInstQSV<0b000, "sha1c",   int_arm64_crypto_sha1c>;
def SHA1Prrr     : SHATiedInstQSV<0b001, "sha1p",   int_arm64_crypto_sha1p>;
def SHA1Mrrr     : SHATiedInstQSV<0b010, "sha1m",   int_arm64_crypto_sha1m>;
def SHA1SU0rrr   : SHATiedInstVVV<0b011, "sha1su0", int_arm64_crypto_sha1su0>;
def SHA256Hrrr   : SHATiedInstQQV<0b100, "sha256h", int_arm64_crypto_sha256h>;
def SHA256H2rrr  : SHATiedInstQQV<0b101, "sha256h2",int_arm64_crypto_sha256h2>;
def SHA256SU1rrr :SHATiedInstVVV<0b110, "sha256su1",int_arm64_crypto_sha256su1>;

def SHA1Hrr     : SHAInstSS<    0b0000, "sha1h",    int_arm64_crypto_sha1h>;
def SHA1SU1rr   : SHATiedInstVV<0b0001, "sha1su1",  int_arm64_crypto_sha1su1>;
def SHA256SU0rr : SHATiedInstVV<0b0010, "sha256su0",int_arm64_crypto_sha256su0>;

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

// Any instruction that defines a 32-bit result leaves the high half of the
// register. Truncate can be lowered to EXTRACT_SUBREG. CopyFromReg may
// be copying from a truncate. But any other 32-bit operation will zero-extend
// up to 64 bits.
// FIXME: X86 also checks for CMOV here. Do we need something similar?
def def32 : PatLeaf<(i32 GPR32:$src), [{
  return N->getOpcode() != ISD::TRUNCATE &&
         N->getOpcode() != TargetOpcode::EXTRACT_SUBREG &&
         N->getOpcode() != ISD::CopyFromReg;
}]>;

// In the case of a 32-bit def that is known to implicitly zero-extend,
// we can use a SUBREG_TO_REG.
def : Pat<(i64 (zext def32:$src)), (SUBREG_TO_REG (i64 0), GPR32:$src, sub_32)>;

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

// When we need to explicitly zero-extend, we use an unsigned bitfield move
// instruction (UBFM) on the enclosing super-reg.
def : Pat<(i64 (zext GPR32:$src)),
 (UBFMXri (INSERT_SUBREG (i64 (IMPLICIT_DEF)), GPR32:$src, sub_32), 0, 31)>;

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

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

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

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

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

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

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

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

// __builtin_trap() uses the BRK instruction on ARM64.
def : Pat<(trap), (BRK 1)>;

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

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

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

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

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

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

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

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

let Predicates = [IsLE] in {
def : Pat<(v8i8  (bitconvert (v1i64 FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (v2i32 FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (v4i16 FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (f64   FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (v2f32 FPR64:$src))), (v8i8  FPR64:$src)>;
def : Pat<(v8i8  (bitconvert (v1f64 FPR64:$src))), (v8i8  FPR64:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v8i8  (bitconvert (v1i64 FPR64:$src))),
                             (v8i8 (REV64v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (v2i32 FPR64:$src))),
                             (v8i8 (REV32v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (v4i16 FPR64:$src))),
                             (v8i8 (REV16v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (f64   FPR64:$src))),
                             (v8i8 (REV64v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (v2f32 FPR64:$src))),
                             (v8i8 (REV32v8i8 FPR64:$src))>;
def : Pat<(v8i8  (bitconvert (v1f64 FPR64:$src))),
                             (v8i8 (REV64v8i8 FPR64:$src))>;
}

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

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

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

let Predicates = [IsLE] in {
def : Pat<(f128 (bitconvert (v2i64 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v4i32 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v8i16 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v2f64 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v4f32 FPR128:$src))), (f128 FPR128:$src)>;
def : Pat<(f128 (bitconvert (v16i8 FPR128:$src))), (f128 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(f128 (bitconvert (v2i64 FPR128:$src))),
                            (f128 (EXTv16i8 FPR128:$src, FPR128:$src, (i32 8)))>;
def : Pat<(f128 (bitconvert (v4i32 FPR128:$src))),
                            (f128 (EXTv16i8 (REV64v4i32 FPR128:$src),
                                            (REV64v4i32 FPR128:$src), (i32 8)))>;
def : Pat<(f128 (bitconvert (v8i16 FPR128:$src))),
                            (f128 (EXTv16i8 (REV64v8i16 FPR128:$src),
                                            (REV64v8i16 FPR128:$src), (i32 8)))>;
def : Pat<(f128 (bitconvert (v2f64 FPR128:$src))),
                            (f128 (EXTv16i8 FPR128:$src, FPR128:$src, (i32 8)))>;
def : Pat<(f128 (bitconvert (v4f32 FPR128:$src))),
                            (f128 (EXTv16i8 (REV64v4i32 FPR128:$src),
                                            (REV64v4i32 FPR128:$src), (i32 8)))>;
def : Pat<(f128 (bitconvert (v16i8 FPR128:$src))),
                            (f128 (EXTv16i8 (REV64v16i8 FPR128:$src),
                                            (REV64v16i8 FPR128:$src), (i32 8)))>;
}

let Predicates = [IsLE] in {
def : Pat<(v2f64 (bitconvert (f128  FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v2f64 (bitconvert (v4i32 FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v2f64 (bitconvert (v8i16 FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v2f64 (bitconvert (v16i8 FPR128:$src))), (v2f64 FPR128:$src)>;
def : Pat<(v2f64 (bitconvert (v4f32 FPR128:$src))), (v2f64 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v2f64 (bitconvert (f128  FPR128:$src))),
                             (v2f64 (EXTv16i8 FPR128:$src,
                                              FPR128:$src, (i32 8)))>;
def : Pat<(v2f64 (bitconvert (v4i32 FPR128:$src))),
                             (v2f64 (REV64v4i32 FPR128:$src))>;
def : Pat<(v2f64 (bitconvert (v8i16 FPR128:$src))),
                             (v2f64 (REV64v8i16 FPR128:$src))>;
def : Pat<(v2f64 (bitconvert (v16i8 FPR128:$src))),
                             (v2f64 (REV64v16i8 FPR128:$src))>;
def : Pat<(v2f64 (bitconvert (v4f32 FPR128:$src))),
                             (v2f64 (REV64v4i32 FPR128:$src))>;
}
def : Pat<(v2f64 (bitconvert (v2i64 FPR128:$src))), (v2f64 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v4f32 (bitconvert (f128  FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v4f32 (bitconvert (v8i16 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v4f32 (bitconvert (v16i8 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v4f32 (bitconvert (v2i64 FPR128:$src))), (v4f32 FPR128:$src)>;
def : Pat<(v4f32 (bitconvert (v2f64 FPR128:$src))), (v4f32 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v4f32 (bitconvert (f128  FPR128:$src))),
                             (v4f32 (EXTv16i8 (REV64v4i32 FPR128:$src),
                                    (REV64v4i32 FPR128:$src), (i32 8)))>;
def : Pat<(v4f32 (bitconvert (v8i16 FPR128:$src))),
                             (v4f32 (REV32v8i16 FPR128:$src))>;
def : Pat<(v4f32 (bitconvert (v16i8 FPR128:$src))),
                             (v4f32 (REV32v16i8 FPR128:$src))>;
def : Pat<(v4f32 (bitconvert (v2i64 FPR128:$src))),
                             (v4f32 (REV64v4i32 FPR128:$src))>;
def : Pat<(v4f32 (bitconvert (v2f64 FPR128:$src))),
                             (v4f32 (REV64v4i32 FPR128:$src))>;
}
def : Pat<(v4f32 (bitconvert (v4i32 FPR128:$src))), (v4f32 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v2i64 (bitconvert (f128  FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2i64 (bitconvert (v4i32 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2i64 (bitconvert (v8i16 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2i64 (bitconvert (v16i8 FPR128:$src))), (v2i64 FPR128:$src)>;
def : Pat<(v2i64 (bitconvert (v4f32 FPR128:$src))), (v2i64 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v2i64 (bitconvert (f128  FPR128:$src))),
                             (v2i64 (EXTv16i8 FPR128:$src,
                                              FPR128:$src, (i32 8)))>;
def : Pat<(v2i64 (bitconvert (v4i32 FPR128:$src))),
                             (v2i64 (REV64v4i32 FPR128:$src))>;
def : Pat<(v2i64 (bitconvert (v8i16 FPR128:$src))),
                             (v2i64 (REV64v8i16 FPR128:$src))>;
def : Pat<(v2i64 (bitconvert (v16i8 FPR128:$src))),
                             (v2i64 (REV64v16i8 FPR128:$src))>;
def : Pat<(v2i64 (bitconvert (v4f32 FPR128:$src))),
                             (v2i64 (REV64v4i32 FPR128:$src))>;
}
def : Pat<(v2i64 (bitconvert (v2f64 FPR128:$src))), (v2i64 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v4i32 (bitconvert (f128  FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4i32 (bitconvert (v2i64 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4i32 (bitconvert (v8i16 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4i32 (bitconvert (v16i8 FPR128:$src))), (v4i32 FPR128:$src)>;
def : Pat<(v4i32 (bitconvert (v2f64 FPR128:$src))), (v4i32 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v4i32 (bitconvert (f128  FPR128:$src))),
                             (v4i32 (EXTv16i8 (REV64v4i32 FPR128:$src),
                                              (REV64v4i32 FPR128:$src),
                                              (i32 8)))>;
def : Pat<(v4i32 (bitconvert (v2i64 FPR128:$src))),
                             (v4i32 (REV64v4i32 FPR128:$src))>;
def : Pat<(v4i32 (bitconvert (v8i16 FPR128:$src))),
                             (v4i32 (REV32v8i16 FPR128:$src))>;
def : Pat<(v4i32 (bitconvert (v16i8 FPR128:$src))),
                             (v4i32 (REV32v16i8 FPR128:$src))>;
def : Pat<(v4i32 (bitconvert (v2f64 FPR128:$src))),
                             (v4i32 (REV64v4i32 FPR128:$src))>;
}
def : Pat<(v4i32 (bitconvert (v4f32 FPR128:$src))), (v4i32 FPR128:$src)>;

let Predicates = [IsLE] in {
def : Pat<(v8i16 (bitconvert (f128  FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v2i64 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v4i32 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v16i8 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v2f64 FPR128:$src))), (v8i16 FPR128:$src)>;
def : Pat<(v8i16 (bitconvert (v4f32 FPR128:$src))), (v8i16 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v8i16 (bitconvert (f128  FPR128:$src))),
                             (v8i16 (EXTv16i8 (REV64v8i16 FPR128:$src),
                                              (REV64v8i16 FPR128:$src),
                                              (i32 8)))>;
def : Pat<(v8i16 (bitconvert (v2i64 FPR128:$src))),
                             (v8i16 (REV64v8i16 FPR128:$src))>;
def : Pat<(v8i16 (bitconvert (v4i32 FPR128:$src))),
                             (v8i16 (REV32v8i16 FPR128:$src))>;
def : Pat<(v8i16 (bitconvert (v16i8 FPR128:$src))),
                             (v8i16 (REV16v16i8 FPR128:$src))>;
def : Pat<(v8i16 (bitconvert (v2f64 FPR128:$src))),
                             (v8i16 (REV64v8i16 FPR128:$src))>;
def : Pat<(v8i16 (bitconvert (v4f32 FPR128:$src))),
                             (v8i16 (REV32v8i16 FPR128:$src))>;
}

let Predicates = [IsLE] in {
def : Pat<(v16i8 (bitconvert (f128  FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v2i64 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v4i32 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v8i16 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v2f64 FPR128:$src))), (v16i8 FPR128:$src)>;
def : Pat<(v16i8 (bitconvert (v4f32 FPR128:$src))), (v16i8 FPR128:$src)>;
}
let Predicates = [IsBE] in {
def : Pat<(v16i8 (bitconvert (f128  FPR128:$src))),
                             (v16i8 (EXTv16i8 (REV64v16i8 FPR128:$src),
                                              (REV64v16i8 FPR128:$src),
                                              (i32 8)))>;
def : Pat<(v16i8 (bitconvert (v2i64 FPR128:$src))),
                             (v16i8 (REV64v16i8 FPR128:$src))>;
def : Pat<(v16i8 (bitconvert (v4i32 FPR128:$src))),
                             (v16i8 (REV32v16i8 FPR128:$src))>;
def : Pat<(v16i8 (bitconvert (v8i16 FPR128:$src))),
                             (v16i8 (REV16v16i8 FPR128:$src))>;
def : Pat<(v16i8 (bitconvert (v2f64 FPR128:$src))),
                             (v16i8 (REV64v16i8 FPR128:$src))>;
def : Pat<(v16i8 (bitconvert (v4f32 FPR128:$src))),
                             (v16i8 (REV32v16i8 FPR128:$src))>;
}

def : Pat<(v8i8 (extract_subvector (v16i8 FPR128:$Rn), (i64 1))),
          (EXTRACT_SUBREG (DUPv2i64lane FPR128:$Rn, 1), dsub)>;
def : Pat<(v4i16 (extract_subvector (v8i16 FPR128:$Rn), (i64 1))),
          (EXTRACT_SUBREG (DUPv2i64lane FPR128:$Rn, 1), dsub)>;
def : Pat<(v2i32 (extract_subvector (v4i32 FPR128:$Rn), (i64 1))),
          (EXTRACT_SUBREG (DUPv2i64lane FPR128:$Rn, 1), dsub)>;
def : Pat<(v1i64 (extract_subvector (v2i64 FPR128:$Rn), (i64 1))),
          (EXTRACT_SUBREG (DUPv2i64lane FPR128:$Rn, 1), dsub)>;

// A 64-bit subvector insert to the first 128-bit vector position
// is a subregister copy that needs no instruction.
def : Pat<(insert_subvector undef, (v1i64 FPR64:$src), (i32 0)),
          (INSERT_SUBREG (v2i64 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
def : Pat<(insert_subvector undef, (v1f64 FPR64:$src), (i32 0)),
          (INSERT_SUBREG (v2f64 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
def : Pat<(insert_subvector undef, (v2i32 FPR64:$src), (i32 0)),
          (INSERT_SUBREG (v4i32 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
def : Pat<(insert_subvector undef, (v2f32 FPR64:$src), (i32 0)),
          (INSERT_SUBREG (v4f32 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
def : Pat<(insert_subvector undef, (v4i16 FPR64:$src), (i32 0)),
          (INSERT_SUBREG (v8i16 (IMPLICIT_DEF)), FPR64:$src, dsub)>;
def : Pat<(insert_subvector undef, (v8i8 FPR64:$src), (i32 0)),
          (INSERT_SUBREG (v16i8 (IMPLICIT_DEF)), FPR64:$src, dsub)>;

// Use pair-wise add instructions when summing up the lanes for v2f64, v2i64
// or v2f32.
def : Pat<(i64 (add (vector_extract (v2i64 FPR128:$Rn), (i64 0)),
                    (vector_extract (v2i64 FPR128:$Rn), (i64 1)))),
           (i64 (ADDPv2i64p (v2i64 FPR128:$Rn)))>;
def : Pat<(f64 (fadd (vector_extract (v2f64 FPR128:$Rn), (i64 0)),
                     (vector_extract (v2f64 FPR128:$Rn), (i64 1)))),
           (f64 (FADDPv2i64p (v2f64 FPR128:$Rn)))>;
    // vector_extract on 64-bit vectors gets promoted to a 128 bit vector,
    // so we match on v4f32 here, not v2f32. This will also catch adding
    // the low two lanes of a true v4f32 vector.
def : Pat<(fadd (vector_extract (v4f32 FPR128:$Rn), (i64 0)),
                (vector_extract (v4f32 FPR128:$Rn), (i64 1))),
          (f32 (FADDPv2i32p (EXTRACT_SUBREG FPR128:$Rn, dsub)))>;

// Scalar 64-bit shifts in FPR64 registers.
def : Pat<(i64 (int_arm64_neon_sshl (i64 FPR64:$Rn), (i64 FPR64:$Rm))),
          (SSHLv1i64 FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(i64 (int_arm64_neon_ushl (i64 FPR64:$Rn), (i64 FPR64:$Rm))),
          (USHLv1i64 FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(i64 (int_arm64_neon_srshl (i64 FPR64:$Rn), (i64 FPR64:$Rm))),
          (SRSHLv1i64 FPR64:$Rn, FPR64:$Rm)>;
def : Pat<(i64 (int_arm64_neon_urshl (i64 FPR64:$Rn), (i64 FPR64:$Rm))),
          (URSHLv1i64 FPR64:$Rn, FPR64:$Rm)>;

// Tail call return handling. These are all compiler pseudo-instructions,
// so no encoding information or anything like that.
let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1, Uses = [SP] in {
  def TCRETURNdi : Pseudo<(outs), (ins i64imm:$dst, i32imm:$FPDiff),[]>;
  def TCRETURNri : Pseudo<(outs), (ins tcGPR64:$dst, i32imm:$FPDiff), []>;
}

def : Pat<(ARM64tcret tcGPR64:$dst, (i32 timm:$FPDiff)),
          (TCRETURNri tcGPR64:$dst, imm:$FPDiff)>;
def : Pat<(ARM64tcret tglobaladdr:$dst, (i32 timm:$FPDiff)),
          (TCRETURNdi texternalsym:$dst, imm:$FPDiff)>;
def : Pat<(ARM64tcret texternalsym:$dst, (i32 timm:$FPDiff)),
          (TCRETURNdi texternalsym:$dst, imm:$FPDiff)>;

include "ARM64InstrAtomics.td"