aboutsummaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
blob: a1e3e326a97afd11c22373137e75d4a1673b3565 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
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
//===-- RISCVISelLowering.cpp - RISCV DAG Lowering Implementation  --------===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
// This file defines the interfaces that RISCV uses to lower LLVM code into a
// selection DAG.
//
//===----------------------------------------------------------------------===//

#include "RISCVISelLowering.h"
#include "RISCV.h"
#include "RISCVMachineFunctionInfo.h"
#include "RISCVRegisterInfo.h"
#include "RISCVSubtarget.h"
#include "RISCVTargetMachine.h"
#include "Utils/RISCVMatInt.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/Statistic.h"
#include "llvm/CodeGen/CallingConvLower.h"
#include "llvm/CodeGen/MachineFrameInfo.h"
#include "llvm/CodeGen/MachineFunction.h"
#include "llvm/CodeGen/MachineInstrBuilder.h"
#include "llvm/CodeGen/MachineRegisterInfo.h"
#include "llvm/CodeGen/SelectionDAGISel.h"
#include "llvm/CodeGen/TargetLoweringObjectFileImpl.h"
#include "llvm/CodeGen/ValueTypes.h"
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/DiagnosticPrinter.h"
#include "llvm/IR/IntrinsicsRISCV.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/raw_ostream.h"

using namespace llvm;

#define DEBUG_TYPE "riscv-lower"

STATISTIC(NumTailCalls, "Number of tail calls");

RISCVTargetLowering::RISCVTargetLowering(const TargetMachine &TM,
                                         const RISCVSubtarget &STI)
    : TargetLowering(TM), Subtarget(STI) {

  if (Subtarget.isRV32E())
    report_fatal_error("Codegen not yet implemented for RV32E");

  RISCVABI::ABI ABI = Subtarget.getTargetABI();
  assert(ABI != RISCVABI::ABI_Unknown && "Improperly initialised target ABI");

  if ((ABI == RISCVABI::ABI_ILP32F || ABI == RISCVABI::ABI_LP64F) &&
      !Subtarget.hasStdExtF()) {
    errs() << "Hard-float 'f' ABI can't be used for a target that "
                "doesn't support the F instruction set extension (ignoring "
                          "target-abi)\n";
    ABI = Subtarget.is64Bit() ? RISCVABI::ABI_LP64 : RISCVABI::ABI_ILP32;
  } else if ((ABI == RISCVABI::ABI_ILP32D || ABI == RISCVABI::ABI_LP64D) &&
             !Subtarget.hasStdExtD()) {
    errs() << "Hard-float 'd' ABI can't be used for a target that "
              "doesn't support the D instruction set extension (ignoring "
              "target-abi)\n";
    ABI = Subtarget.is64Bit() ? RISCVABI::ABI_LP64 : RISCVABI::ABI_ILP32;
  }

  switch (ABI) {
  default:
    report_fatal_error("Don't know how to lower this ABI");
  case RISCVABI::ABI_ILP32:
  case RISCVABI::ABI_ILP32F:
  case RISCVABI::ABI_ILP32D:
  case RISCVABI::ABI_LP64:
  case RISCVABI::ABI_LP64F:
  case RISCVABI::ABI_LP64D:
    break;
  }

  MVT XLenVT = Subtarget.getXLenVT();

  // Set up the register classes.
  addRegisterClass(XLenVT, &RISCV::GPRRegClass);

  if (Subtarget.hasStdExtF())
    addRegisterClass(MVT::f32, &RISCV::FPR32RegClass);
  if (Subtarget.hasStdExtD())
    addRegisterClass(MVT::f64, &RISCV::FPR64RegClass);

  // Compute derived properties from the register classes.
  computeRegisterProperties(STI.getRegisterInfo());

  setStackPointerRegisterToSaveRestore(RISCV::X2);

  for (auto N : {ISD::EXTLOAD, ISD::SEXTLOAD, ISD::ZEXTLOAD})
    setLoadExtAction(N, XLenVT, MVT::i1, Promote);

  // TODO: add all necessary setOperationAction calls.
  setOperationAction(ISD::DYNAMIC_STACKALLOC, XLenVT, Expand);

  setOperationAction(ISD::BR_JT, MVT::Other, Expand);
  setOperationAction(ISD::BR_CC, XLenVT, Expand);
  setOperationAction(ISD::SELECT, XLenVT, Custom);
  setOperationAction(ISD::SELECT_CC, XLenVT, Expand);

  setOperationAction(ISD::STACKSAVE, MVT::Other, Expand);
  setOperationAction(ISD::STACKRESTORE, MVT::Other, Expand);

  setOperationAction(ISD::VASTART, MVT::Other, Custom);
  setOperationAction(ISD::VAARG, MVT::Other, Expand);
  setOperationAction(ISD::VACOPY, MVT::Other, Expand);
  setOperationAction(ISD::VAEND, MVT::Other, Expand);

  for (auto VT : {MVT::i1, MVT::i8, MVT::i16})
    setOperationAction(ISD::SIGN_EXTEND_INREG, VT, Expand);

  if (Subtarget.is64Bit()) {
    setOperationAction(ISD::ADD, MVT::i32, Custom);
    setOperationAction(ISD::SUB, MVT::i32, Custom);
    setOperationAction(ISD::SHL, MVT::i32, Custom);
    setOperationAction(ISD::SRA, MVT::i32, Custom);
    setOperationAction(ISD::SRL, MVT::i32, Custom);
  }

  if (!Subtarget.hasStdExtM()) {
    setOperationAction(ISD::MUL, XLenVT, Expand);
    setOperationAction(ISD::MULHS, XLenVT, Expand);
    setOperationAction(ISD::MULHU, XLenVT, Expand);
    setOperationAction(ISD::SDIV, XLenVT, Expand);
    setOperationAction(ISD::UDIV, XLenVT, Expand);
    setOperationAction(ISD::SREM, XLenVT, Expand);
    setOperationAction(ISD::UREM, XLenVT, Expand);
  }

  if (Subtarget.is64Bit() && Subtarget.hasStdExtM()) {
    setOperationAction(ISD::MUL, MVT::i32, Custom);
    setOperationAction(ISD::SDIV, MVT::i32, Custom);
    setOperationAction(ISD::UDIV, MVT::i32, Custom);
    setOperationAction(ISD::UREM, MVT::i32, Custom);
  }

  setOperationAction(ISD::SDIVREM, XLenVT, Expand);
  setOperationAction(ISD::UDIVREM, XLenVT, Expand);
  setOperationAction(ISD::SMUL_LOHI, XLenVT, Expand);
  setOperationAction(ISD::UMUL_LOHI, XLenVT, Expand);

  setOperationAction(ISD::SHL_PARTS, XLenVT, Custom);
  setOperationAction(ISD::SRL_PARTS, XLenVT, Custom);
  setOperationAction(ISD::SRA_PARTS, XLenVT, Custom);

  setOperationAction(ISD::ROTL, XLenVT, Expand);
  setOperationAction(ISD::ROTR, XLenVT, Expand);
  setOperationAction(ISD::BSWAP, XLenVT, Expand);
  setOperationAction(ISD::CTTZ, XLenVT, Expand);
  setOperationAction(ISD::CTLZ, XLenVT, Expand);
  setOperationAction(ISD::CTPOP, XLenVT, Expand);

  ISD::CondCode FPCCToExtend[] = {
      ISD::SETOGT, ISD::SETOGE, ISD::SETONE, ISD::SETUEQ, ISD::SETUGT,
      ISD::SETUGE, ISD::SETULT, ISD::SETULE, ISD::SETUNE, ISD::SETGT,
      ISD::SETGE,  ISD::SETNE};

  ISD::NodeType FPOpToExtend[] = {
      ISD::FSIN, ISD::FCOS, ISD::FSINCOS, ISD::FPOW, ISD::FREM, ISD::FP16_TO_FP,
      ISD::FP_TO_FP16};

  if (Subtarget.hasStdExtF()) {
    setOperationAction(ISD::FMINNUM, MVT::f32, Legal);
    setOperationAction(ISD::FMAXNUM, MVT::f32, Legal);
    for (auto CC : FPCCToExtend)
      setCondCodeAction(CC, MVT::f32, Expand);
    setOperationAction(ISD::SELECT_CC, MVT::f32, Expand);
    setOperationAction(ISD::SELECT, MVT::f32, Custom);
    setOperationAction(ISD::BR_CC, MVT::f32, Expand);
    for (auto Op : FPOpToExtend)
      setOperationAction(Op, MVT::f32, Expand);
    setLoadExtAction(ISD::EXTLOAD, MVT::f32, MVT::f16, Expand);
    setTruncStoreAction(MVT::f32, MVT::f16, Expand);
  }

  if (Subtarget.hasStdExtF() && Subtarget.is64Bit())
    setOperationAction(ISD::BITCAST, MVT::i32, Custom);

  if (Subtarget.hasStdExtD()) {
    setOperationAction(ISD::FMINNUM, MVT::f64, Legal);
    setOperationAction(ISD::FMAXNUM, MVT::f64, Legal);
    for (auto CC : FPCCToExtend)
      setCondCodeAction(CC, MVT::f64, Expand);
    setOperationAction(ISD::SELECT_CC, MVT::f64, Expand);
    setOperationAction(ISD::SELECT, MVT::f64, Custom);
    setOperationAction(ISD::BR_CC, MVT::f64, Expand);
    setLoadExtAction(ISD::EXTLOAD, MVT::f64, MVT::f32, Expand);
    setTruncStoreAction(MVT::f64, MVT::f32, Expand);
    for (auto Op : FPOpToExtend)
      setOperationAction(Op, MVT::f64, Expand);
    setLoadExtAction(ISD::EXTLOAD, MVT::f64, MVT::f16, Expand);
    setTruncStoreAction(MVT::f64, MVT::f16, Expand);
  }

  if (Subtarget.is64Bit() &&
      !(Subtarget.hasStdExtD() || Subtarget.hasStdExtF())) {
    setOperationAction(ISD::FP_TO_UINT, MVT::i32, Custom);
    setOperationAction(ISD::FP_TO_SINT, MVT::i32, Custom);
    setOperationAction(ISD::STRICT_FP_TO_UINT, MVT::i32, Custom);
    setOperationAction(ISD::STRICT_FP_TO_SINT, MVT::i32, Custom);
  }

  setOperationAction(ISD::GlobalAddress, XLenVT, Custom);
  setOperationAction(ISD::BlockAddress, XLenVT, Custom);
  setOperationAction(ISD::ConstantPool, XLenVT, Custom);

  setOperationAction(ISD::GlobalTLSAddress, XLenVT, Custom);

  // TODO: On M-mode only targets, the cycle[h] CSR may not be present.
  // Unfortunately this can't be determined just from the ISA naming string.
  setOperationAction(ISD::READCYCLECOUNTER, MVT::i64,
                     Subtarget.is64Bit() ? Legal : Custom);

  setOperationAction(ISD::TRAP, MVT::Other, Legal);
  setOperationAction(ISD::DEBUGTRAP, MVT::Other, Legal);

  if (Subtarget.hasStdExtA()) {
    setMaxAtomicSizeInBitsSupported(Subtarget.getXLen());
    setMinCmpXchgSizeInBits(32);
  } else {
    setMaxAtomicSizeInBitsSupported(0);
  }

  setBooleanContents(ZeroOrOneBooleanContent);

  // Function alignments.
  const Align FunctionAlignment(Subtarget.hasStdExtC() ? 2 : 4);
  setMinFunctionAlignment(FunctionAlignment);
  setPrefFunctionAlignment(FunctionAlignment);

  // Effectively disable jump table generation.
  setMinimumJumpTableEntries(INT_MAX);
}

EVT RISCVTargetLowering::getSetCCResultType(const DataLayout &DL, LLVMContext &,
                                            EVT VT) const {
  if (!VT.isVector())
    return getPointerTy(DL);
  return VT.changeVectorElementTypeToInteger();
}

bool RISCVTargetLowering::getTgtMemIntrinsic(IntrinsicInfo &Info,
                                             const CallInst &I,
                                             MachineFunction &MF,
                                             unsigned Intrinsic) const {
  switch (Intrinsic) {
  default:
    return false;
  case Intrinsic::riscv_masked_atomicrmw_xchg_i32:
  case Intrinsic::riscv_masked_atomicrmw_add_i32:
  case Intrinsic::riscv_masked_atomicrmw_sub_i32:
  case Intrinsic::riscv_masked_atomicrmw_nand_i32:
  case Intrinsic::riscv_masked_atomicrmw_max_i32:
  case Intrinsic::riscv_masked_atomicrmw_min_i32:
  case Intrinsic::riscv_masked_atomicrmw_umax_i32:
  case Intrinsic::riscv_masked_atomicrmw_umin_i32:
  case Intrinsic::riscv_masked_cmpxchg_i32:
    PointerType *PtrTy = cast<PointerType>(I.getArgOperand(0)->getType());
    Info.opc = ISD::INTRINSIC_W_CHAIN;
    Info.memVT = MVT::getVT(PtrTy->getElementType());
    Info.ptrVal = I.getArgOperand(0);
    Info.offset = 0;
    Info.align = Align(4);
    Info.flags = MachineMemOperand::MOLoad | MachineMemOperand::MOStore |
                 MachineMemOperand::MOVolatile;
    return true;
  }
}

bool RISCVTargetLowering::isLegalAddressingMode(const DataLayout &DL,
                                                const AddrMode &AM, Type *Ty,
                                                unsigned AS,
                                                Instruction *I) const {
  // No global is ever allowed as a base.
  if (AM.BaseGV)
    return false;

  // Require a 12-bit signed offset.
  if (!isInt<12>(AM.BaseOffs))
    return false;

  switch (AM.Scale) {
  case 0: // "r+i" or just "i", depending on HasBaseReg.
    break;
  case 1:
    if (!AM.HasBaseReg) // allow "r+i".
      break;
    return false; // disallow "r+r" or "r+r+i".
  default:
    return false;
  }

  return true;
}

bool RISCVTargetLowering::isLegalICmpImmediate(int64_t Imm) const {
  return isInt<12>(Imm);
}

bool RISCVTargetLowering::isLegalAddImmediate(int64_t Imm) const {
  return isInt<12>(Imm);
}

// On RV32, 64-bit integers are split into their high and low parts and held
// in two different registers, so the trunc is free since the low register can
// just be used.
bool RISCVTargetLowering::isTruncateFree(Type *SrcTy, Type *DstTy) const {
  if (Subtarget.is64Bit() || !SrcTy->isIntegerTy() || !DstTy->isIntegerTy())
    return false;
  unsigned SrcBits = SrcTy->getPrimitiveSizeInBits();
  unsigned DestBits = DstTy->getPrimitiveSizeInBits();
  return (SrcBits == 64 && DestBits == 32);
}

bool RISCVTargetLowering::isTruncateFree(EVT SrcVT, EVT DstVT) const {
  if (Subtarget.is64Bit() || SrcVT.isVector() || DstVT.isVector() ||
      !SrcVT.isInteger() || !DstVT.isInteger())
    return false;
  unsigned SrcBits = SrcVT.getSizeInBits();
  unsigned DestBits = DstVT.getSizeInBits();
  return (SrcBits == 64 && DestBits == 32);
}

bool RISCVTargetLowering::isZExtFree(SDValue Val, EVT VT2) const {
  // Zexts are free if they can be combined with a load.
  if (auto *LD = dyn_cast<LoadSDNode>(Val)) {
    EVT MemVT = LD->getMemoryVT();
    if ((MemVT == MVT::i8 || MemVT == MVT::i16 ||
         (Subtarget.is64Bit() && MemVT == MVT::i32)) &&
        (LD->getExtensionType() == ISD::NON_EXTLOAD ||
         LD->getExtensionType() == ISD::ZEXTLOAD))
      return true;
  }

  return TargetLowering::isZExtFree(Val, VT2);
}

bool RISCVTargetLowering::isSExtCheaperThanZExt(EVT SrcVT, EVT DstVT) const {
  return Subtarget.is64Bit() && SrcVT == MVT::i32 && DstVT == MVT::i64;
}

bool RISCVTargetLowering::hasBitPreservingFPLogic(EVT VT) const {
  return (VT == MVT::f32 && Subtarget.hasStdExtF()) ||
         (VT == MVT::f64 && Subtarget.hasStdExtD());
}

// Changes the condition code and swaps operands if necessary, so the SetCC
// operation matches one of the comparisons supported directly in the RISC-V
// ISA.
static void normaliseSetCC(SDValue &LHS, SDValue &RHS, ISD::CondCode &CC) {
  switch (CC) {
  default:
    break;
  case ISD::SETGT:
  case ISD::SETLE:
  case ISD::SETUGT:
  case ISD::SETULE:
    CC = ISD::getSetCCSwappedOperands(CC);
    std::swap(LHS, RHS);
    break;
  }
}

// Return the RISC-V branch opcode that matches the given DAG integer
// condition code. The CondCode must be one of those supported by the RISC-V
// ISA (see normaliseSetCC).
static unsigned getBranchOpcodeForIntCondCode(ISD::CondCode CC) {
  switch (CC) {
  default:
    llvm_unreachable("Unsupported CondCode");
  case ISD::SETEQ:
    return RISCV::BEQ;
  case ISD::SETNE:
    return RISCV::BNE;
  case ISD::SETLT:
    return RISCV::BLT;
  case ISD::SETGE:
    return RISCV::BGE;
  case ISD::SETULT:
    return RISCV::BLTU;
  case ISD::SETUGE:
    return RISCV::BGEU;
  }
}

SDValue RISCVTargetLowering::LowerOperation(SDValue Op,
                                            SelectionDAG &DAG) const {
  switch (Op.getOpcode()) {
  default:
    report_fatal_error("unimplemented operand");
  case ISD::GlobalAddress:
    return lowerGlobalAddress(Op, DAG);
  case ISD::BlockAddress:
    return lowerBlockAddress(Op, DAG);
  case ISD::ConstantPool:
    return lowerConstantPool(Op, DAG);
  case ISD::GlobalTLSAddress:
    return lowerGlobalTLSAddress(Op, DAG);
  case ISD::SELECT:
    return lowerSELECT(Op, DAG);
  case ISD::VASTART:
    return lowerVASTART(Op, DAG);
  case ISD::FRAMEADDR:
    return lowerFRAMEADDR(Op, DAG);
  case ISD::RETURNADDR:
    return lowerRETURNADDR(Op, DAG);
  case ISD::SHL_PARTS:
    return lowerShiftLeftParts(Op, DAG);
  case ISD::SRA_PARTS:
    return lowerShiftRightParts(Op, DAG, true);
  case ISD::SRL_PARTS:
    return lowerShiftRightParts(Op, DAG, false);
  case ISD::BITCAST: {
    assert(Subtarget.is64Bit() && Subtarget.hasStdExtF() &&
           "Unexpected custom legalisation");
    SDLoc DL(Op);
    SDValue Op0 = Op.getOperand(0);
    if (Op.getValueType() != MVT::f32 || Op0.getValueType() != MVT::i32)
      return SDValue();
    SDValue NewOp0 = DAG.getNode(ISD::ANY_EXTEND, DL, MVT::i64, Op0);
    SDValue FPConv = DAG.getNode(RISCVISD::FMV_W_X_RV64, DL, MVT::f32, NewOp0);
    return FPConv;
  }
  }
}

static SDValue getTargetNode(GlobalAddressSDNode *N, SDLoc DL, EVT Ty,
                             SelectionDAG &DAG, unsigned Flags) {
  return DAG.getTargetGlobalAddress(N->getGlobal(), DL, Ty, 0, Flags);
}

static SDValue getTargetNode(BlockAddressSDNode *N, SDLoc DL, EVT Ty,
                             SelectionDAG &DAG, unsigned Flags) {
  return DAG.getTargetBlockAddress(N->getBlockAddress(), Ty, N->getOffset(),
                                   Flags);
}

static SDValue getTargetNode(ConstantPoolSDNode *N, SDLoc DL, EVT Ty,
                             SelectionDAG &DAG, unsigned Flags) {
  return DAG.getTargetConstantPool(N->getConstVal(), Ty, N->getAlignment(),
                                   N->getOffset(), Flags);
}

template <class NodeTy>
SDValue RISCVTargetLowering::getAddr(NodeTy *N, SelectionDAG &DAG,
                                     bool IsLocal) const {
  SDLoc DL(N);
  EVT Ty = getPointerTy(DAG.getDataLayout());

  if (isPositionIndependent()) {
    SDValue Addr = getTargetNode(N, DL, Ty, DAG, 0);
    if (IsLocal)
      // Use PC-relative addressing to access the symbol. This generates the
      // pattern (PseudoLLA sym), which expands to (addi (auipc %pcrel_hi(sym))
      // %pcrel_lo(auipc)).
      return SDValue(DAG.getMachineNode(RISCV::PseudoLLA, DL, Ty, Addr), 0);

    // Use PC-relative addressing to access the GOT for this symbol, then load
    // the address from the GOT. This generates the pattern (PseudoLA sym),
    // which expands to (ld (addi (auipc %got_pcrel_hi(sym)) %pcrel_lo(auipc))).
    return SDValue(DAG.getMachineNode(RISCV::PseudoLA, DL, Ty, Addr), 0);
  }

  switch (getTargetMachine().getCodeModel()) {
  default:
    report_fatal_error("Unsupported code model for lowering");
  case CodeModel::Small: {
    // Generate a sequence for accessing addresses within the first 2 GiB of
    // address space. This generates the pattern (addi (lui %hi(sym)) %lo(sym)).
    SDValue AddrHi = getTargetNode(N, DL, Ty, DAG, RISCVII::MO_HI);
    SDValue AddrLo = getTargetNode(N, DL, Ty, DAG, RISCVII::MO_LO);
    SDValue MNHi = SDValue(DAG.getMachineNode(RISCV::LUI, DL, Ty, AddrHi), 0);
    return SDValue(DAG.getMachineNode(RISCV::ADDI, DL, Ty, MNHi, AddrLo), 0);
  }
  case CodeModel::Medium: {
    // Generate a sequence for accessing addresses within any 2GiB range within
    // the address space. This generates the pattern (PseudoLLA sym), which
    // expands to (addi (auipc %pcrel_hi(sym)) %pcrel_lo(auipc)).
    SDValue Addr = getTargetNode(N, DL, Ty, DAG, 0);
    return SDValue(DAG.getMachineNode(RISCV::PseudoLLA, DL, Ty, Addr), 0);
  }
  }
}

SDValue RISCVTargetLowering::lowerGlobalAddress(SDValue Op,
                                                SelectionDAG &DAG) const {
  SDLoc DL(Op);
  EVT Ty = Op.getValueType();
  GlobalAddressSDNode *N = cast<GlobalAddressSDNode>(Op);
  int64_t Offset = N->getOffset();
  MVT XLenVT = Subtarget.getXLenVT();

  const GlobalValue *GV = N->getGlobal();
  bool IsLocal = getTargetMachine().shouldAssumeDSOLocal(*GV->getParent(), GV);
  SDValue Addr = getAddr(N, DAG, IsLocal);

  // In order to maximise the opportunity for common subexpression elimination,
  // emit a separate ADD node for the global address offset instead of folding
  // it in the global address node. Later peephole optimisations may choose to
  // fold it back in when profitable.
  if (Offset != 0)
    return DAG.getNode(ISD::ADD, DL, Ty, Addr,
                       DAG.getConstant(Offset, DL, XLenVT));
  return Addr;
}

SDValue RISCVTargetLowering::lowerBlockAddress(SDValue Op,
                                               SelectionDAG &DAG) const {
  BlockAddressSDNode *N = cast<BlockAddressSDNode>(Op);

  return getAddr(N, DAG);
}

SDValue RISCVTargetLowering::lowerConstantPool(SDValue Op,
                                               SelectionDAG &DAG) const {
  ConstantPoolSDNode *N = cast<ConstantPoolSDNode>(Op);

  return getAddr(N, DAG);
}

SDValue RISCVTargetLowering::getStaticTLSAddr(GlobalAddressSDNode *N,
                                              SelectionDAG &DAG,
                                              bool UseGOT) const {
  SDLoc DL(N);
  EVT Ty = getPointerTy(DAG.getDataLayout());
  const GlobalValue *GV = N->getGlobal();
  MVT XLenVT = Subtarget.getXLenVT();

  if (UseGOT) {
    // Use PC-relative addressing to access the GOT for this TLS symbol, then
    // load the address from the GOT and add the thread pointer. This generates
    // the pattern (PseudoLA_TLS_IE sym), which expands to
    // (ld (auipc %tls_ie_pcrel_hi(sym)) %pcrel_lo(auipc)).
    SDValue Addr = DAG.getTargetGlobalAddress(GV, DL, Ty, 0, 0);
    SDValue Load =
        SDValue(DAG.getMachineNode(RISCV::PseudoLA_TLS_IE, DL, Ty, Addr), 0);

    // Add the thread pointer.
    SDValue TPReg = DAG.getRegister(RISCV::X4, XLenVT);
    return DAG.getNode(ISD::ADD, DL, Ty, Load, TPReg);
  }

  // Generate a sequence for accessing the address relative to the thread
  // pointer, with the appropriate adjustment for the thread pointer offset.
  // This generates the pattern
  // (add (add_tprel (lui %tprel_hi(sym)) tp %tprel_add(sym)) %tprel_lo(sym))
  SDValue AddrHi =
      DAG.getTargetGlobalAddress(GV, DL, Ty, 0, RISCVII::MO_TPREL_HI);
  SDValue AddrAdd =
      DAG.getTargetGlobalAddress(GV, DL, Ty, 0, RISCVII::MO_TPREL_ADD);
  SDValue AddrLo =
      DAG.getTargetGlobalAddress(GV, DL, Ty, 0, RISCVII::MO_TPREL_LO);

  SDValue MNHi = SDValue(DAG.getMachineNode(RISCV::LUI, DL, Ty, AddrHi), 0);
  SDValue TPReg = DAG.getRegister(RISCV::X4, XLenVT);
  SDValue MNAdd = SDValue(
      DAG.getMachineNode(RISCV::PseudoAddTPRel, DL, Ty, MNHi, TPReg, AddrAdd),
      0);
  return SDValue(DAG.getMachineNode(RISCV::ADDI, DL, Ty, MNAdd, AddrLo), 0);
}

SDValue RISCVTargetLowering::getDynamicTLSAddr(GlobalAddressSDNode *N,
                                               SelectionDAG &DAG) const {
  SDLoc DL(N);
  EVT Ty = getPointerTy(DAG.getDataLayout());
  IntegerType *CallTy = Type::getIntNTy(*DAG.getContext(), Ty.getSizeInBits());
  const GlobalValue *GV = N->getGlobal();

  // Use a PC-relative addressing mode to access the global dynamic GOT address.
  // This generates the pattern (PseudoLA_TLS_GD sym), which expands to
  // (addi (auipc %tls_gd_pcrel_hi(sym)) %pcrel_lo(auipc)).
  SDValue Addr = DAG.getTargetGlobalAddress(GV, DL, Ty, 0, 0);
  SDValue Load =
      SDValue(DAG.getMachineNode(RISCV::PseudoLA_TLS_GD, DL, Ty, Addr), 0);

  // Prepare argument list to generate call.
  ArgListTy Args;
  ArgListEntry Entry;
  Entry.Node = Load;
  Entry.Ty = CallTy;
  Args.push_back(Entry);

  // Setup call to __tls_get_addr.
  TargetLowering::CallLoweringInfo CLI(DAG);
  CLI.setDebugLoc(DL)
      .setChain(DAG.getEntryNode())
      .setLibCallee(CallingConv::C, CallTy,
                    DAG.getExternalSymbol("__tls_get_addr", Ty),
                    std::move(Args));

  return LowerCallTo(CLI).first;
}

SDValue RISCVTargetLowering::lowerGlobalTLSAddress(SDValue Op,
                                                   SelectionDAG &DAG) const {
  SDLoc DL(Op);
  EVT Ty = Op.getValueType();
  GlobalAddressSDNode *N = cast<GlobalAddressSDNode>(Op);
  int64_t Offset = N->getOffset();
  MVT XLenVT = Subtarget.getXLenVT();

  TLSModel::Model Model = getTargetMachine().getTLSModel(N->getGlobal());

  SDValue Addr;
  switch (Model) {
  case TLSModel::LocalExec:
    Addr = getStaticTLSAddr(N, DAG, /*UseGOT=*/false);
    break;
  case TLSModel::InitialExec:
    Addr = getStaticTLSAddr(N, DAG, /*UseGOT=*/true);
    break;
  case TLSModel::LocalDynamic:
  case TLSModel::GeneralDynamic:
    Addr = getDynamicTLSAddr(N, DAG);
    break;
  }

  // In order to maximise the opportunity for common subexpression elimination,
  // emit a separate ADD node for the global address offset instead of folding
  // it in the global address node. Later peephole optimisations may choose to
  // fold it back in when profitable.
  if (Offset != 0)
    return DAG.getNode(ISD::ADD, DL, Ty, Addr,
                       DAG.getConstant(Offset, DL, XLenVT));
  return Addr;
}

SDValue RISCVTargetLowering::lowerSELECT(SDValue Op, SelectionDAG &DAG) const {
  SDValue CondV = Op.getOperand(0);
  SDValue TrueV = Op.getOperand(1);
  SDValue FalseV = Op.getOperand(2);
  SDLoc DL(Op);
  MVT XLenVT = Subtarget.getXLenVT();

  // If the result type is XLenVT and CondV is the output of a SETCC node
  // which also operated on XLenVT inputs, then merge the SETCC node into the
  // lowered RISCVISD::SELECT_CC to take advantage of the integer
  // compare+branch instructions. i.e.:
  // (select (setcc lhs, rhs, cc), truev, falsev)
  // -> (riscvisd::select_cc lhs, rhs, cc, truev, falsev)
  if (Op.getSimpleValueType() == XLenVT && CondV.getOpcode() == ISD::SETCC &&
      CondV.getOperand(0).getSimpleValueType() == XLenVT) {
    SDValue LHS = CondV.getOperand(0);
    SDValue RHS = CondV.getOperand(1);
    auto CC = cast<CondCodeSDNode>(CondV.getOperand(2));
    ISD::CondCode CCVal = CC->get();

    normaliseSetCC(LHS, RHS, CCVal);

    SDValue TargetCC = DAG.getConstant(CCVal, DL, XLenVT);
    SDVTList VTs = DAG.getVTList(Op.getValueType(), MVT::Glue);
    SDValue Ops[] = {LHS, RHS, TargetCC, TrueV, FalseV};
    return DAG.getNode(RISCVISD::SELECT_CC, DL, VTs, Ops);
  }

  // Otherwise:
  // (select condv, truev, falsev)
  // -> (riscvisd::select_cc condv, zero, setne, truev, falsev)
  SDValue Zero = DAG.getConstant(0, DL, XLenVT);
  SDValue SetNE = DAG.getConstant(ISD::SETNE, DL, XLenVT);

  SDVTList VTs = DAG.getVTList(Op.getValueType(), MVT::Glue);
  SDValue Ops[] = {CondV, Zero, SetNE, TrueV, FalseV};

  return DAG.getNode(RISCVISD::SELECT_CC, DL, VTs, Ops);
}

SDValue RISCVTargetLowering::lowerVASTART(SDValue Op, SelectionDAG &DAG) const {
  MachineFunction &MF = DAG.getMachineFunction();
  RISCVMachineFunctionInfo *FuncInfo = MF.getInfo<RISCVMachineFunctionInfo>();

  SDLoc DL(Op);
  SDValue FI = DAG.getFrameIndex(FuncInfo->getVarArgsFrameIndex(),
                                 getPointerTy(MF.getDataLayout()));

  // vastart just stores the address of the VarArgsFrameIndex slot into the
  // memory location argument.
  const Value *SV = cast<SrcValueSDNode>(Op.getOperand(2))->getValue();
  return DAG.getStore(Op.getOperand(0), DL, FI, Op.getOperand(1),
                      MachinePointerInfo(SV));
}

SDValue RISCVTargetLowering::lowerFRAMEADDR(SDValue Op,
                                            SelectionDAG &DAG) const {
  const RISCVRegisterInfo &RI = *Subtarget.getRegisterInfo();
  MachineFunction &MF = DAG.getMachineFunction();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  MFI.setFrameAddressIsTaken(true);
  Register FrameReg = RI.getFrameRegister(MF);
  int XLenInBytes = Subtarget.getXLen() / 8;

  EVT VT = Op.getValueType();
  SDLoc DL(Op);
  SDValue FrameAddr = DAG.getCopyFromReg(DAG.getEntryNode(), DL, FrameReg, VT);
  unsigned Depth = cast<ConstantSDNode>(Op.getOperand(0))->getZExtValue();
  while (Depth--) {
    int Offset = -(XLenInBytes * 2);
    SDValue Ptr = DAG.getNode(ISD::ADD, DL, VT, FrameAddr,
                              DAG.getIntPtrConstant(Offset, DL));
    FrameAddr =
        DAG.getLoad(VT, DL, DAG.getEntryNode(), Ptr, MachinePointerInfo());
  }
  return FrameAddr;
}

SDValue RISCVTargetLowering::lowerRETURNADDR(SDValue Op,
                                             SelectionDAG &DAG) const {
  const RISCVRegisterInfo &RI = *Subtarget.getRegisterInfo();
  MachineFunction &MF = DAG.getMachineFunction();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  MFI.setReturnAddressIsTaken(true);
  MVT XLenVT = Subtarget.getXLenVT();
  int XLenInBytes = Subtarget.getXLen() / 8;

  if (verifyReturnAddressArgumentIsConstant(Op, DAG))
    return SDValue();

  EVT VT = Op.getValueType();
  SDLoc DL(Op);
  unsigned Depth = cast<ConstantSDNode>(Op.getOperand(0))->getZExtValue();
  if (Depth) {
    int Off = -XLenInBytes;
    SDValue FrameAddr = lowerFRAMEADDR(Op, DAG);
    SDValue Offset = DAG.getConstant(Off, DL, VT);
    return DAG.getLoad(VT, DL, DAG.getEntryNode(),
                       DAG.getNode(ISD::ADD, DL, VT, FrameAddr, Offset),
                       MachinePointerInfo());
  }

  // Return the value of the return address register, marking it an implicit
  // live-in.
  Register Reg = MF.addLiveIn(RI.getRARegister(), getRegClassFor(XLenVT));
  return DAG.getCopyFromReg(DAG.getEntryNode(), DL, Reg, XLenVT);
}

SDValue RISCVTargetLowering::lowerShiftLeftParts(SDValue Op,
                                                 SelectionDAG &DAG) const {
  SDLoc DL(Op);
  SDValue Lo = Op.getOperand(0);
  SDValue Hi = Op.getOperand(1);
  SDValue Shamt = Op.getOperand(2);
  EVT VT = Lo.getValueType();

  // if Shamt-XLEN < 0: // Shamt < XLEN
  //   Lo = Lo << Shamt
  //   Hi = (Hi << Shamt) | ((Lo >>u 1) >>u (XLEN-1 - Shamt))
  // else:
  //   Lo = 0
  //   Hi = Lo << (Shamt-XLEN)

  SDValue Zero = DAG.getConstant(0, DL, VT);
  SDValue One = DAG.getConstant(1, DL, VT);
  SDValue MinusXLen = DAG.getConstant(-(int)Subtarget.getXLen(), DL, VT);
  SDValue XLenMinus1 = DAG.getConstant(Subtarget.getXLen() - 1, DL, VT);
  SDValue ShamtMinusXLen = DAG.getNode(ISD::ADD, DL, VT, Shamt, MinusXLen);
  SDValue XLenMinus1Shamt = DAG.getNode(ISD::SUB, DL, VT, XLenMinus1, Shamt);

  SDValue LoTrue = DAG.getNode(ISD::SHL, DL, VT, Lo, Shamt);
  SDValue ShiftRight1Lo = DAG.getNode(ISD::SRL, DL, VT, Lo, One);
  SDValue ShiftRightLo =
      DAG.getNode(ISD::SRL, DL, VT, ShiftRight1Lo, XLenMinus1Shamt);
  SDValue ShiftLeftHi = DAG.getNode(ISD::SHL, DL, VT, Hi, Shamt);
  SDValue HiTrue = DAG.getNode(ISD::OR, DL, VT, ShiftLeftHi, ShiftRightLo);
  SDValue HiFalse = DAG.getNode(ISD::SHL, DL, VT, Lo, ShamtMinusXLen);

  SDValue CC = DAG.getSetCC(DL, VT, ShamtMinusXLen, Zero, ISD::SETLT);

  Lo = DAG.getNode(ISD::SELECT, DL, VT, CC, LoTrue, Zero);
  Hi = DAG.getNode(ISD::SELECT, DL, VT, CC, HiTrue, HiFalse);

  SDValue Parts[2] = {Lo, Hi};
  return DAG.getMergeValues(Parts, DL);
}

SDValue RISCVTargetLowering::lowerShiftRightParts(SDValue Op, SelectionDAG &DAG,
                                                  bool IsSRA) const {
  SDLoc DL(Op);
  SDValue Lo = Op.getOperand(0);
  SDValue Hi = Op.getOperand(1);
  SDValue Shamt = Op.getOperand(2);
  EVT VT = Lo.getValueType();

  // SRA expansion:
  //   if Shamt-XLEN < 0: // Shamt < XLEN
  //     Lo = (Lo >>u Shamt) | ((Hi << 1) << (XLEN-1 - Shamt))
  //     Hi = Hi >>s Shamt
  //   else:
  //     Lo = Hi >>s (Shamt-XLEN);
  //     Hi = Hi >>s (XLEN-1)
  //
  // SRL expansion:
  //   if Shamt-XLEN < 0: // Shamt < XLEN
  //     Lo = (Lo >>u Shamt) | ((Hi << 1) << (XLEN-1 - Shamt))
  //     Hi = Hi >>u Shamt
  //   else:
  //     Lo = Hi >>u (Shamt-XLEN);
  //     Hi = 0;

  unsigned ShiftRightOp = IsSRA ? ISD::SRA : ISD::SRL;

  SDValue Zero = DAG.getConstant(0, DL, VT);
  SDValue One = DAG.getConstant(1, DL, VT);
  SDValue MinusXLen = DAG.getConstant(-(int)Subtarget.getXLen(), DL, VT);
  SDValue XLenMinus1 = DAG.getConstant(Subtarget.getXLen() - 1, DL, VT);
  SDValue ShamtMinusXLen = DAG.getNode(ISD::ADD, DL, VT, Shamt, MinusXLen);
  SDValue XLenMinus1Shamt = DAG.getNode(ISD::SUB, DL, VT, XLenMinus1, Shamt);

  SDValue ShiftRightLo = DAG.getNode(ISD::SRL, DL, VT, Lo, Shamt);
  SDValue ShiftLeftHi1 = DAG.getNode(ISD::SHL, DL, VT, Hi, One);
  SDValue ShiftLeftHi =
      DAG.getNode(ISD::SHL, DL, VT, ShiftLeftHi1, XLenMinus1Shamt);
  SDValue LoTrue = DAG.getNode(ISD::OR, DL, VT, ShiftRightLo, ShiftLeftHi);
  SDValue HiTrue = DAG.getNode(ShiftRightOp, DL, VT, Hi, Shamt);
  SDValue LoFalse = DAG.getNode(ShiftRightOp, DL, VT, Hi, ShamtMinusXLen);
  SDValue HiFalse =
      IsSRA ? DAG.getNode(ISD::SRA, DL, VT, Hi, XLenMinus1) : Zero;

  SDValue CC = DAG.getSetCC(DL, VT, ShamtMinusXLen, Zero, ISD::SETLT);

  Lo = DAG.getNode(ISD::SELECT, DL, VT, CC, LoTrue, LoFalse);
  Hi = DAG.getNode(ISD::SELECT, DL, VT, CC, HiTrue, HiFalse);

  SDValue Parts[2] = {Lo, Hi};
  return DAG.getMergeValues(Parts, DL);
}

// Returns the opcode of the target-specific SDNode that implements the 32-bit
// form of the given Opcode.
static RISCVISD::NodeType getRISCVWOpcode(unsigned Opcode) {
  switch (Opcode) {
  default:
    llvm_unreachable("Unexpected opcode");
  case ISD::SHL:
    return RISCVISD::SLLW;
  case ISD::SRA:
    return RISCVISD::SRAW;
  case ISD::SRL:
    return RISCVISD::SRLW;
  case ISD::SDIV:
    return RISCVISD::DIVW;
  case ISD::UDIV:
    return RISCVISD::DIVUW;
  case ISD::UREM:
    return RISCVISD::REMUW;
  }
}

// Converts the given 32-bit operation to a target-specific SelectionDAG node.
// Because i32 isn't a legal type for RV64, these operations would otherwise
// be promoted to i64, making it difficult to select the SLLW/DIVUW/.../*W
// later one because the fact the operation was originally of type i32 is
// lost.
static SDValue customLegalizeToWOp(SDNode *N, SelectionDAG &DAG) {
  SDLoc DL(N);
  RISCVISD::NodeType WOpcode = getRISCVWOpcode(N->getOpcode());
  SDValue NewOp0 = DAG.getNode(ISD::ANY_EXTEND, DL, MVT::i64, N->getOperand(0));
  SDValue NewOp1 = DAG.getNode(ISD::ANY_EXTEND, DL, MVT::i64, N->getOperand(1));
  SDValue NewRes = DAG.getNode(WOpcode, DL, MVT::i64, NewOp0, NewOp1);
  // ReplaceNodeResults requires we maintain the same type for the return value.
  return DAG.getNode(ISD::TRUNCATE, DL, MVT::i32, NewRes);
}

// Converts the given 32-bit operation to a i64 operation with signed extension
// semantic to reduce the signed extension instructions.
static SDValue customLegalizeToWOpWithSExt(SDNode *N, SelectionDAG &DAG) {
  SDLoc DL(N);
  SDValue NewOp0 = DAG.getNode(ISD::ANY_EXTEND, DL, MVT::i64, N->getOperand(0));
  SDValue NewOp1 = DAG.getNode(ISD::ANY_EXTEND, DL, MVT::i64, N->getOperand(1));
  SDValue NewWOp = DAG.getNode(N->getOpcode(), DL, MVT::i64, NewOp0, NewOp1);
  SDValue NewRes = DAG.getNode(ISD::SIGN_EXTEND_INREG, DL, MVT::i64, NewWOp,
                               DAG.getValueType(MVT::i32));
  return DAG.getNode(ISD::TRUNCATE, DL, MVT::i32, NewRes);
}

void RISCVTargetLowering::ReplaceNodeResults(SDNode *N,
                                             SmallVectorImpl<SDValue> &Results,
                                             SelectionDAG &DAG) const {
  SDLoc DL(N);
  switch (N->getOpcode()) {
  default:
    llvm_unreachable("Don't know how to custom type legalize this operation!");
  case ISD::STRICT_FP_TO_SINT:
  case ISD::STRICT_FP_TO_UINT:
  case ISD::FP_TO_SINT:
  case ISD::FP_TO_UINT: {
    bool IsStrict = N->isStrictFPOpcode();
    assert(N->getValueType(0) == MVT::i32 && Subtarget.is64Bit() &&
           "Unexpected custom legalisation");
    SDValue Op0 = IsStrict ? N->getOperand(1) : N->getOperand(0);
    RTLIB::Libcall LC;
    if (N->getOpcode() == ISD::FP_TO_SINT ||
        N->getOpcode() == ISD::STRICT_FP_TO_SINT)
      LC = RTLIB::getFPTOSINT(Op0.getValueType(), N->getValueType(0));
    else
      LC = RTLIB::getFPTOUINT(Op0.getValueType(), N->getValueType(0));
    MakeLibCallOptions CallOptions;
    EVT OpVT = Op0.getValueType();
    CallOptions.setTypeListBeforeSoften(OpVT, N->getValueType(0), true);
    SDValue Chain = IsStrict ? N->getOperand(0) : SDValue();
    SDValue Result;
    std::tie(Result, Chain) =
        makeLibCall(DAG, LC, N->getValueType(0), Op0, CallOptions, DL, Chain);
    Results.push_back(Result);
    if (IsStrict)
      Results.push_back(Chain);
    break;
  }
  case ISD::READCYCLECOUNTER: {
    assert(!Subtarget.is64Bit() &&
           "READCYCLECOUNTER only has custom type legalization on riscv32");

    SDVTList VTs = DAG.getVTList(MVT::i32, MVT::i32, MVT::Other);
    SDValue RCW =
        DAG.getNode(RISCVISD::READ_CYCLE_WIDE, DL, VTs, N->getOperand(0));

    Results.push_back(RCW);
    Results.push_back(RCW.getValue(1));
    Results.push_back(RCW.getValue(2));
    break;
  }
  case ISD::ADD:
  case ISD::SUB:
  case ISD::MUL:
    assert(N->getValueType(0) == MVT::i32 && Subtarget.is64Bit() &&
           "Unexpected custom legalisation");
    if (N->getOperand(1).getOpcode() == ISD::Constant)
      return;
    Results.push_back(customLegalizeToWOpWithSExt(N, DAG));
    break;
  case ISD::SHL:
  case ISD::SRA:
  case ISD::SRL:
    assert(N->getValueType(0) == MVT::i32 && Subtarget.is64Bit() &&
           "Unexpected custom legalisation");
    if (N->getOperand(1).getOpcode() == ISD::Constant)
      return;
    Results.push_back(customLegalizeToWOp(N, DAG));
    break;
  case ISD::SDIV:
  case ISD::UDIV:
  case ISD::UREM:
    assert(N->getValueType(0) == MVT::i32 && Subtarget.is64Bit() &&
           Subtarget.hasStdExtM() && "Unexpected custom legalisation");
    if (N->getOperand(0).getOpcode() == ISD::Constant ||
        N->getOperand(1).getOpcode() == ISD::Constant)
      return;
    Results.push_back(customLegalizeToWOp(N, DAG));
    break;
  case ISD::BITCAST: {
    assert(N->getValueType(0) == MVT::i32 && Subtarget.is64Bit() &&
           Subtarget.hasStdExtF() && "Unexpected custom legalisation");
    SDLoc DL(N);
    SDValue Op0 = N->getOperand(0);
    if (Op0.getValueType() != MVT::f32)
      return;
    SDValue FPConv =
        DAG.getNode(RISCVISD::FMV_X_ANYEXTW_RV64, DL, MVT::i64, Op0);
    Results.push_back(DAG.getNode(ISD::TRUNCATE, DL, MVT::i32, FPConv));
    break;
  }
  }
}

SDValue RISCVTargetLowering::PerformDAGCombine(SDNode *N,
                                               DAGCombinerInfo &DCI) const {
  SelectionDAG &DAG = DCI.DAG;

  switch (N->getOpcode()) {
  default:
    break;
  case RISCVISD::SplitF64: {
    SDValue Op0 = N->getOperand(0);
    // If the input to SplitF64 is just BuildPairF64 then the operation is
    // redundant. Instead, use BuildPairF64's operands directly.
    if (Op0->getOpcode() == RISCVISD::BuildPairF64)
      return DCI.CombineTo(N, Op0.getOperand(0), Op0.getOperand(1));

    SDLoc DL(N);

    // It's cheaper to materialise two 32-bit integers than to load a double
    // from the constant pool and transfer it to integer registers through the
    // stack.
    if (ConstantFPSDNode *C = dyn_cast<ConstantFPSDNode>(Op0)) {
      APInt V = C->getValueAPF().bitcastToAPInt();
      SDValue Lo = DAG.getConstant(V.trunc(32), DL, MVT::i32);
      SDValue Hi = DAG.getConstant(V.lshr(32).trunc(32), DL, MVT::i32);
      return DCI.CombineTo(N, Lo, Hi);
    }

    // This is a target-specific version of a DAGCombine performed in
    // DAGCombiner::visitBITCAST. It performs the equivalent of:
    // fold (bitconvert (fneg x)) -> (xor (bitconvert x), signbit)
    // fold (bitconvert (fabs x)) -> (and (bitconvert x), (not signbit))
    if (!(Op0.getOpcode() == ISD::FNEG || Op0.getOpcode() == ISD::FABS) ||
        !Op0.getNode()->hasOneUse())
      break;
    SDValue NewSplitF64 =
        DAG.getNode(RISCVISD::SplitF64, DL, DAG.getVTList(MVT::i32, MVT::i32),
                    Op0.getOperand(0));
    SDValue Lo = NewSplitF64.getValue(0);
    SDValue Hi = NewSplitF64.getValue(1);
    APInt SignBit = APInt::getSignMask(32);
    if (Op0.getOpcode() == ISD::FNEG) {
      SDValue NewHi = DAG.getNode(ISD::XOR, DL, MVT::i32, Hi,
                                  DAG.getConstant(SignBit, DL, MVT::i32));
      return DCI.CombineTo(N, Lo, NewHi);
    }
    assert(Op0.getOpcode() == ISD::FABS);
    SDValue NewHi = DAG.getNode(ISD::AND, DL, MVT::i32, Hi,
                                DAG.getConstant(~SignBit, DL, MVT::i32));
    return DCI.CombineTo(N, Lo, NewHi);
  }
  case RISCVISD::SLLW:
  case RISCVISD::SRAW:
  case RISCVISD::SRLW: {
    // Only the lower 32 bits of LHS and lower 5 bits of RHS are read.
    SDValue LHS = N->getOperand(0);
    SDValue RHS = N->getOperand(1);
    APInt LHSMask = APInt::getLowBitsSet(LHS.getValueSizeInBits(), 32);
    APInt RHSMask = APInt::getLowBitsSet(RHS.getValueSizeInBits(), 5);
    if ((SimplifyDemandedBits(N->getOperand(0), LHSMask, DCI)) ||
        (SimplifyDemandedBits(N->getOperand(1), RHSMask, DCI)))
      return SDValue();
    break;
  }
  case RISCVISD::FMV_X_ANYEXTW_RV64: {
    SDLoc DL(N);
    SDValue Op0 = N->getOperand(0);
    // If the input to FMV_X_ANYEXTW_RV64 is just FMV_W_X_RV64 then the
    // conversion is unnecessary and can be replaced with an ANY_EXTEND
    // of the FMV_W_X_RV64 operand.
    if (Op0->getOpcode() == RISCVISD::FMV_W_X_RV64) {
      SDValue AExtOp =
          DAG.getNode(ISD::ANY_EXTEND, DL, MVT::i64, Op0.getOperand(0));
      return DCI.CombineTo(N, AExtOp);
    }

    // This is a target-specific version of a DAGCombine performed in
    // DAGCombiner::visitBITCAST. It performs the equivalent of:
    // fold (bitconvert (fneg x)) -> (xor (bitconvert x), signbit)
    // fold (bitconvert (fabs x)) -> (and (bitconvert x), (not signbit))
    if (!(Op0.getOpcode() == ISD::FNEG || Op0.getOpcode() == ISD::FABS) ||
        !Op0.getNode()->hasOneUse())
      break;
    SDValue NewFMV = DAG.getNode(RISCVISD::FMV_X_ANYEXTW_RV64, DL, MVT::i64,
                                 Op0.getOperand(0));
    APInt SignBit = APInt::getSignMask(32).sext(64);
    if (Op0.getOpcode() == ISD::FNEG) {
      return DCI.CombineTo(N,
                           DAG.getNode(ISD::XOR, DL, MVT::i64, NewFMV,
                                       DAG.getConstant(SignBit, DL, MVT::i64)));
    }
    assert(Op0.getOpcode() == ISD::FABS);
    return DCI.CombineTo(N,
                         DAG.getNode(ISD::AND, DL, MVT::i64, NewFMV,
                                     DAG.getConstant(~SignBit, DL, MVT::i64)));
  }
  }

  return SDValue();
}

bool RISCVTargetLowering::isDesirableToCommuteWithShift(
    const SDNode *N, CombineLevel Level) const {
  // The following folds are only desirable if `(OP _, c1 << c2)` can be
  // materialised in fewer instructions than `(OP _, c1)`:
  //
  //   (shl (add x, c1), c2) -> (add (shl x, c2), c1 << c2)
  //   (shl (or x, c1), c2) -> (or (shl x, c2), c1 << c2)
  SDValue N0 = N->getOperand(0);
  EVT Ty = N0.getValueType();
  if (Ty.isScalarInteger() &&
      (N0.getOpcode() == ISD::ADD || N0.getOpcode() == ISD::OR)) {
    auto *C1 = dyn_cast<ConstantSDNode>(N0->getOperand(1));
    auto *C2 = dyn_cast<ConstantSDNode>(N->getOperand(1));
    if (C1 && C2) {
      APInt C1Int = C1->getAPIntValue();
      APInt ShiftedC1Int = C1Int << C2->getAPIntValue();

      // We can materialise `c1 << c2` into an add immediate, so it's "free",
      // and the combine should happen, to potentially allow further combines
      // later.
      if (ShiftedC1Int.getMinSignedBits() <= 64 &&
          isLegalAddImmediate(ShiftedC1Int.getSExtValue()))
        return true;

      // We can materialise `c1` in an add immediate, so it's "free", and the
      // combine should be prevented.
      if (C1Int.getMinSignedBits() <= 64 &&
          isLegalAddImmediate(C1Int.getSExtValue()))
        return false;

      // Neither constant will fit into an immediate, so find materialisation
      // costs.
      int C1Cost = RISCVMatInt::getIntMatCost(C1Int, Ty.getSizeInBits(),
                                              Subtarget.is64Bit());
      int ShiftedC1Cost = RISCVMatInt::getIntMatCost(
          ShiftedC1Int, Ty.getSizeInBits(), Subtarget.is64Bit());

      // Materialising `c1` is cheaper than materialising `c1 << c2`, so the
      // combine should be prevented.
      if (C1Cost < ShiftedC1Cost)
        return false;
    }
  }
  return true;
}

unsigned RISCVTargetLowering::ComputeNumSignBitsForTargetNode(
    SDValue Op, const APInt &DemandedElts, const SelectionDAG &DAG,
    unsigned Depth) const {
  switch (Op.getOpcode()) {
  default:
    break;
  case RISCVISD::SLLW:
  case RISCVISD::SRAW:
  case RISCVISD::SRLW:
  case RISCVISD::DIVW:
  case RISCVISD::DIVUW:
  case RISCVISD::REMUW:
    // TODO: As the result is sign-extended, this is conservatively correct. A
    // more precise answer could be calculated for SRAW depending on known
    // bits in the shift amount.
    return 33;
  }

  return 1;
}

static MachineBasicBlock *emitReadCycleWidePseudo(MachineInstr &MI,
                                                  MachineBasicBlock *BB) {
  assert(MI.getOpcode() == RISCV::ReadCycleWide && "Unexpected instruction");

  // To read the 64-bit cycle CSR on a 32-bit target, we read the two halves.
  // Should the count have wrapped while it was being read, we need to try
  // again.
  // ...
  // read:
  // rdcycleh x3 # load high word of cycle
  // rdcycle  x2 # load low word of cycle
  // rdcycleh x4 # load high word of cycle
  // bne x3, x4, read # check if high word reads match, otherwise try again
  // ...

  MachineFunction &MF = *BB->getParent();
  const BasicBlock *LLVM_BB = BB->getBasicBlock();
  MachineFunction::iterator It = ++BB->getIterator();

  MachineBasicBlock *LoopMBB = MF.CreateMachineBasicBlock(LLVM_BB);
  MF.insert(It, LoopMBB);

  MachineBasicBlock *DoneMBB = MF.CreateMachineBasicBlock(LLVM_BB);
  MF.insert(It, DoneMBB);

  // Transfer the remainder of BB and its successor edges to DoneMBB.
  DoneMBB->splice(DoneMBB->begin(), BB,
                  std::next(MachineBasicBlock::iterator(MI)), BB->end());
  DoneMBB->transferSuccessorsAndUpdatePHIs(BB);

  BB->addSuccessor(LoopMBB);

  MachineRegisterInfo &RegInfo = MF.getRegInfo();
  Register ReadAgainReg = RegInfo.createVirtualRegister(&RISCV::GPRRegClass);
  Register LoReg = MI.getOperand(0).getReg();
  Register HiReg = MI.getOperand(1).getReg();
  DebugLoc DL = MI.getDebugLoc();

  const TargetInstrInfo *TII = MF.getSubtarget().getInstrInfo();
  BuildMI(LoopMBB, DL, TII->get(RISCV::CSRRS), HiReg)
      .addImm(RISCVSysReg::lookupSysRegByName("CYCLEH")->Encoding)
      .addReg(RISCV::X0);
  BuildMI(LoopMBB, DL, TII->get(RISCV::CSRRS), LoReg)
      .addImm(RISCVSysReg::lookupSysRegByName("CYCLE")->Encoding)
      .addReg(RISCV::X0);
  BuildMI(LoopMBB, DL, TII->get(RISCV::CSRRS), ReadAgainReg)
      .addImm(RISCVSysReg::lookupSysRegByName("CYCLEH")->Encoding)
      .addReg(RISCV::X0);

  BuildMI(LoopMBB, DL, TII->get(RISCV::BNE))
      .addReg(HiReg)
      .addReg(ReadAgainReg)
      .addMBB(LoopMBB);

  LoopMBB->addSuccessor(LoopMBB);
  LoopMBB->addSuccessor(DoneMBB);

  MI.eraseFromParent();

  return DoneMBB;
}

static MachineBasicBlock *emitSplitF64Pseudo(MachineInstr &MI,
                                             MachineBasicBlock *BB) {
  assert(MI.getOpcode() == RISCV::SplitF64Pseudo && "Unexpected instruction");

  MachineFunction &MF = *BB->getParent();
  DebugLoc DL = MI.getDebugLoc();
  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
  const TargetRegisterInfo *RI = MF.getSubtarget().getRegisterInfo();
  Register LoReg = MI.getOperand(0).getReg();
  Register HiReg = MI.getOperand(1).getReg();
  Register SrcReg = MI.getOperand(2).getReg();
  const TargetRegisterClass *SrcRC = &RISCV::FPR64RegClass;
  int FI = MF.getInfo<RISCVMachineFunctionInfo>()->getMoveF64FrameIndex();

  TII.storeRegToStackSlot(*BB, MI, SrcReg, MI.getOperand(2).isKill(), FI, SrcRC,
                          RI);
  MachineMemOperand *MMO =
      MF.getMachineMemOperand(MachinePointerInfo::getFixedStack(MF, FI),
                              MachineMemOperand::MOLoad, 8, 8);
  BuildMI(*BB, MI, DL, TII.get(RISCV::LW), LoReg)
      .addFrameIndex(FI)
      .addImm(0)
      .addMemOperand(MMO);
  BuildMI(*BB, MI, DL, TII.get(RISCV::LW), HiReg)
      .addFrameIndex(FI)
      .addImm(4)
      .addMemOperand(MMO);
  MI.eraseFromParent(); // The pseudo instruction is gone now.
  return BB;
}

static MachineBasicBlock *emitBuildPairF64Pseudo(MachineInstr &MI,
                                                 MachineBasicBlock *BB) {
  assert(MI.getOpcode() == RISCV::BuildPairF64Pseudo &&
         "Unexpected instruction");

  MachineFunction &MF = *BB->getParent();
  DebugLoc DL = MI.getDebugLoc();
  const TargetInstrInfo &TII = *MF.getSubtarget().getInstrInfo();
  const TargetRegisterInfo *RI = MF.getSubtarget().getRegisterInfo();
  Register DstReg = MI.getOperand(0).getReg();
  Register LoReg = MI.getOperand(1).getReg();
  Register HiReg = MI.getOperand(2).getReg();
  const TargetRegisterClass *DstRC = &RISCV::FPR64RegClass;
  int FI = MF.getInfo<RISCVMachineFunctionInfo>()->getMoveF64FrameIndex();

  MachineMemOperand *MMO =
      MF.getMachineMemOperand(MachinePointerInfo::getFixedStack(MF, FI),
                              MachineMemOperand::MOStore, 8, 8);
  BuildMI(*BB, MI, DL, TII.get(RISCV::SW))
      .addReg(LoReg, getKillRegState(MI.getOperand(1).isKill()))
      .addFrameIndex(FI)
      .addImm(0)
      .addMemOperand(MMO);
  BuildMI(*BB, MI, DL, TII.get(RISCV::SW))
      .addReg(HiReg, getKillRegState(MI.getOperand(2).isKill()))
      .addFrameIndex(FI)
      .addImm(4)
      .addMemOperand(MMO);
  TII.loadRegFromStackSlot(*BB, MI, DstReg, FI, DstRC, RI);
  MI.eraseFromParent(); // The pseudo instruction is gone now.
  return BB;
}

static bool isSelectPseudo(MachineInstr &MI) {
  switch (MI.getOpcode()) {
  default:
    return false;
  case RISCV::Select_GPR_Using_CC_GPR:
  case RISCV::Select_FPR32_Using_CC_GPR:
  case RISCV::Select_FPR64_Using_CC_GPR:
    return true;
  }
}

static MachineBasicBlock *emitSelectPseudo(MachineInstr &MI,
                                           MachineBasicBlock *BB) {
  // To "insert" Select_* instructions, we actually have to insert the triangle
  // control-flow pattern.  The incoming instructions know the destination vreg
  // to set, the condition code register to branch on, the true/false values to
  // select between, and the condcode to use to select the appropriate branch.
  //
  // We produce the following control flow:
  //     HeadMBB
  //     |  \
  //     |  IfFalseMBB
  //     | /
  //    TailMBB
  //
  // When we find a sequence of selects we attempt to optimize their emission
  // by sharing the control flow. Currently we only handle cases where we have
  // multiple selects with the exact same condition (same LHS, RHS and CC).
  // The selects may be interleaved with other instructions if the other
  // instructions meet some requirements we deem safe:
  // - They are debug instructions. Otherwise,
  // - They do not have side-effects, do not access memory and their inputs do
  //   not depend on the results of the select pseudo-instructions.
  // The TrueV/FalseV operands of the selects cannot depend on the result of
  // previous selects in the sequence.
  // These conditions could be further relaxed. See the X86 target for a
  // related approach and more information.
  Register LHS = MI.getOperand(1).getReg();
  Register RHS = MI.getOperand(2).getReg();
  auto CC = static_cast<ISD::CondCode>(MI.getOperand(3).getImm());

  SmallVector<MachineInstr *, 4> SelectDebugValues;
  SmallSet<Register, 4> SelectDests;
  SelectDests.insert(MI.getOperand(0).getReg());

  MachineInstr *LastSelectPseudo = &MI;

  for (auto E = BB->end(), SequenceMBBI = MachineBasicBlock::iterator(MI);
       SequenceMBBI != E; ++SequenceMBBI) {
    if (SequenceMBBI->isDebugInstr())
      continue;
    else if (isSelectPseudo(*SequenceMBBI)) {
      if (SequenceMBBI->getOperand(1).getReg() != LHS ||
          SequenceMBBI->getOperand(2).getReg() != RHS ||
          SequenceMBBI->getOperand(3).getImm() != CC ||
          SelectDests.count(SequenceMBBI->getOperand(4).getReg()) ||
          SelectDests.count(SequenceMBBI->getOperand(5).getReg()))
        break;
      LastSelectPseudo = &*SequenceMBBI;
      SequenceMBBI->collectDebugValues(SelectDebugValues);
      SelectDests.insert(SequenceMBBI->getOperand(0).getReg());
    } else {
      if (SequenceMBBI->hasUnmodeledSideEffects() ||
          SequenceMBBI->mayLoadOrStore())
        break;
      if (llvm::any_of(SequenceMBBI->operands(), [&](MachineOperand &MO) {
            return MO.isReg() && MO.isUse() && SelectDests.count(MO.getReg());
          }))
        break;
    }
  }

  const TargetInstrInfo &TII = *BB->getParent()->getSubtarget().getInstrInfo();
  const BasicBlock *LLVM_BB = BB->getBasicBlock();
  DebugLoc DL = MI.getDebugLoc();
  MachineFunction::iterator I = ++BB->getIterator();

  MachineBasicBlock *HeadMBB = BB;
  MachineFunction *F = BB->getParent();
  MachineBasicBlock *TailMBB = F->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *IfFalseMBB = F->CreateMachineBasicBlock(LLVM_BB);

  F->insert(I, IfFalseMBB);
  F->insert(I, TailMBB);

  // Transfer debug instructions associated with the selects to TailMBB.
  for (MachineInstr *DebugInstr : SelectDebugValues) {
    TailMBB->push_back(DebugInstr->removeFromParent());
  }

  // Move all instructions after the sequence to TailMBB.
  TailMBB->splice(TailMBB->end(), HeadMBB,
                  std::next(LastSelectPseudo->getIterator()), HeadMBB->end());
  // Update machine-CFG edges by transferring all successors of the current
  // block to the new block which will contain the Phi nodes for the selects.
  TailMBB->transferSuccessorsAndUpdatePHIs(HeadMBB);
  // Set the successors for HeadMBB.
  HeadMBB->addSuccessor(IfFalseMBB);
  HeadMBB->addSuccessor(TailMBB);

  // Insert appropriate branch.
  unsigned Opcode = getBranchOpcodeForIntCondCode(CC);

  BuildMI(HeadMBB, DL, TII.get(Opcode))
    .addReg(LHS)
    .addReg(RHS)
    .addMBB(TailMBB);

  // IfFalseMBB just falls through to TailMBB.
  IfFalseMBB->addSuccessor(TailMBB);

  // Create PHIs for all of the select pseudo-instructions.
  auto SelectMBBI = MI.getIterator();
  auto SelectEnd = std::next(LastSelectPseudo->getIterator());
  auto InsertionPoint = TailMBB->begin();
  while (SelectMBBI != SelectEnd) {
    auto Next = std::next(SelectMBBI);
    if (isSelectPseudo(*SelectMBBI)) {
      // %Result = phi [ %TrueValue, HeadMBB ], [ %FalseValue, IfFalseMBB ]
      BuildMI(*TailMBB, InsertionPoint, SelectMBBI->getDebugLoc(),
              TII.get(RISCV::PHI), SelectMBBI->getOperand(0).getReg())
          .addReg(SelectMBBI->getOperand(4).getReg())
          .addMBB(HeadMBB)
          .addReg(SelectMBBI->getOperand(5).getReg())
          .addMBB(IfFalseMBB);
      SelectMBBI->eraseFromParent();
    }
    SelectMBBI = Next;
  }

  F->getProperties().reset(MachineFunctionProperties::Property::NoPHIs);
  return TailMBB;
}

MachineBasicBlock *
RISCVTargetLowering::EmitInstrWithCustomInserter(MachineInstr &MI,
                                                 MachineBasicBlock *BB) const {
  switch (MI.getOpcode()) {
  default:
    llvm_unreachable("Unexpected instr type to insert");
  case RISCV::ReadCycleWide:
    assert(!Subtarget.is64Bit() &&
           "ReadCycleWrite is only to be used on riscv32");
    return emitReadCycleWidePseudo(MI, BB);
  case RISCV::Select_GPR_Using_CC_GPR:
  case RISCV::Select_FPR32_Using_CC_GPR:
  case RISCV::Select_FPR64_Using_CC_GPR:
    return emitSelectPseudo(MI, BB);
  case RISCV::BuildPairF64Pseudo:
    return emitBuildPairF64Pseudo(MI, BB);
  case RISCV::SplitF64Pseudo:
    return emitSplitF64Pseudo(MI, BB);
  }
}

// Calling Convention Implementation.
// The expectations for frontend ABI lowering vary from target to target.
// Ideally, an LLVM frontend would be able to avoid worrying about many ABI
// details, but this is a longer term goal. For now, we simply try to keep the
// role of the frontend as simple and well-defined as possible. The rules can
// be summarised as:
// * Never split up large scalar arguments. We handle them here.
// * If a hardfloat calling convention is being used, and the struct may be
// passed in a pair of registers (fp+fp, int+fp), and both registers are
// available, then pass as two separate arguments. If either the GPRs or FPRs
// are exhausted, then pass according to the rule below.
// * If a struct could never be passed in registers or directly in a stack
// slot (as it is larger than 2*XLEN and the floating point rules don't
// apply), then pass it using a pointer with the byval attribute.
// * If a struct is less than 2*XLEN, then coerce to either a two-element
// word-sized array or a 2*XLEN scalar (depending on alignment).
// * The frontend can determine whether a struct is returned by reference or
// not based on its size and fields. If it will be returned by reference, the
// frontend must modify the prototype so a pointer with the sret annotation is
// passed as the first argument. This is not necessary for large scalar
// returns.
// * Struct return values and varargs should be coerced to structs containing
// register-size fields in the same situations they would be for fixed
// arguments.

static const MCPhysReg ArgGPRs[] = {
  RISCV::X10, RISCV::X11, RISCV::X12, RISCV::X13,
  RISCV::X14, RISCV::X15, RISCV::X16, RISCV::X17
};
static const MCPhysReg ArgFPR32s[] = {
  RISCV::F10_F, RISCV::F11_F, RISCV::F12_F, RISCV::F13_F,
  RISCV::F14_F, RISCV::F15_F, RISCV::F16_F, RISCV::F17_F
};
static const MCPhysReg ArgFPR64s[] = {
  RISCV::F10_D, RISCV::F11_D, RISCV::F12_D, RISCV::F13_D,
  RISCV::F14_D, RISCV::F15_D, RISCV::F16_D, RISCV::F17_D
};

// Pass a 2*XLEN argument that has been split into two XLEN values through
// registers or the stack as necessary.
static bool CC_RISCVAssign2XLen(unsigned XLen, CCState &State, CCValAssign VA1,
                                ISD::ArgFlagsTy ArgFlags1, unsigned ValNo2,
                                MVT ValVT2, MVT LocVT2,
                                ISD::ArgFlagsTy ArgFlags2) {
  unsigned XLenInBytes = XLen / 8;
  if (Register Reg = State.AllocateReg(ArgGPRs)) {
    // At least one half can be passed via register.
    State.addLoc(CCValAssign::getReg(VA1.getValNo(), VA1.getValVT(), Reg,
                                     VA1.getLocVT(), CCValAssign::Full));
  } else {
    // Both halves must be passed on the stack, with proper alignment.
    unsigned StackAlign = std::max(XLenInBytes, ArgFlags1.getOrigAlign());
    State.addLoc(
        CCValAssign::getMem(VA1.getValNo(), VA1.getValVT(),
                            State.AllocateStack(XLenInBytes, StackAlign),
                            VA1.getLocVT(), CCValAssign::Full));
    State.addLoc(CCValAssign::getMem(
        ValNo2, ValVT2, State.AllocateStack(XLenInBytes, XLenInBytes), LocVT2,
        CCValAssign::Full));
    return false;
  }

  if (Register Reg = State.AllocateReg(ArgGPRs)) {
    // The second half can also be passed via register.
    State.addLoc(
        CCValAssign::getReg(ValNo2, ValVT2, Reg, LocVT2, CCValAssign::Full));
  } else {
    // The second half is passed via the stack, without additional alignment.
    State.addLoc(CCValAssign::getMem(
        ValNo2, ValVT2, State.AllocateStack(XLenInBytes, XLenInBytes), LocVT2,
        CCValAssign::Full));
  }

  return false;
}

// Implements the RISC-V calling convention. Returns true upon failure.
static bool CC_RISCV(const DataLayout &DL, RISCVABI::ABI ABI, unsigned ValNo,
                     MVT ValVT, MVT LocVT, CCValAssign::LocInfo LocInfo,
                     ISD::ArgFlagsTy ArgFlags, CCState &State, bool IsFixed,
                     bool IsRet, Type *OrigTy) {
  unsigned XLen = DL.getLargestLegalIntTypeSizeInBits();
  assert(XLen == 32 || XLen == 64);
  MVT XLenVT = XLen == 32 ? MVT::i32 : MVT::i64;

  // Any return value split in to more than two values can't be returned
  // directly.
  if (IsRet && ValNo > 1)
    return true;

  // UseGPRForF32 if targeting one of the soft-float ABIs, if passing a
  // variadic argument, or if no F32 argument registers are available.
  bool UseGPRForF32 = true;
  // UseGPRForF64 if targeting soft-float ABIs or an FLEN=32 ABI, if passing a
  // variadic argument, or if no F64 argument registers are available.
  bool UseGPRForF64 = true;

  switch (ABI) {
  default:
    llvm_unreachable("Unexpected ABI");
  case RISCVABI::ABI_ILP32:
  case RISCVABI::ABI_LP64:
    break;
  case RISCVABI::ABI_ILP32F:
  case RISCVABI::ABI_LP64F:
    UseGPRForF32 = !IsFixed;
    break;
  case RISCVABI::ABI_ILP32D:
  case RISCVABI::ABI_LP64D:
    UseGPRForF32 = !IsFixed;
    UseGPRForF64 = !IsFixed;
    break;
  }

  if (State.getFirstUnallocated(ArgFPR32s) == array_lengthof(ArgFPR32s))
    UseGPRForF32 = true;
  if (State.getFirstUnallocated(ArgFPR64s) == array_lengthof(ArgFPR64s))
    UseGPRForF64 = true;

  // From this point on, rely on UseGPRForF32, UseGPRForF64 and similar local
  // variables rather than directly checking against the target ABI.

  if (UseGPRForF32 && ValVT == MVT::f32) {
    LocVT = XLenVT;
    LocInfo = CCValAssign::BCvt;
  } else if (UseGPRForF64 && XLen == 64 && ValVT == MVT::f64) {
    LocVT = MVT::i64;
    LocInfo = CCValAssign::BCvt;
  }

  // If this is a variadic argument, the RISC-V calling convention requires
  // that it is assigned an 'even' or 'aligned' register if it has 8-byte
  // alignment (RV32) or 16-byte alignment (RV64). An aligned register should
  // be used regardless of whether the original argument was split during
  // legalisation or not. The argument will not be passed by registers if the
  // original type is larger than 2*XLEN, so the register alignment rule does
  // not apply.
  unsigned TwoXLenInBytes = (2 * XLen) / 8;
  if (!IsFixed && ArgFlags.getOrigAlign() == TwoXLenInBytes &&
      DL.getTypeAllocSize(OrigTy) == TwoXLenInBytes) {
    unsigned RegIdx = State.getFirstUnallocated(ArgGPRs);
    // Skip 'odd' register if necessary.
    if (RegIdx != array_lengthof(ArgGPRs) && RegIdx % 2 == 1)
      State.AllocateReg(ArgGPRs);
  }

  SmallVectorImpl<CCValAssign> &PendingLocs = State.getPendingLocs();
  SmallVectorImpl<ISD::ArgFlagsTy> &PendingArgFlags =
      State.getPendingArgFlags();

  assert(PendingLocs.size() == PendingArgFlags.size() &&
         "PendingLocs and PendingArgFlags out of sync");

  // Handle passing f64 on RV32D with a soft float ABI or when floating point
  // registers are exhausted.
  if (UseGPRForF64 && XLen == 32 && ValVT == MVT::f64) {
    assert(!ArgFlags.isSplit() && PendingLocs.empty() &&
           "Can't lower f64 if it is split");
    // Depending on available argument GPRS, f64 may be passed in a pair of
    // GPRs, split between a GPR and the stack, or passed completely on the
    // stack. LowerCall/LowerFormalArguments/LowerReturn must recognise these
    // cases.
    Register Reg = State.AllocateReg(ArgGPRs);
    LocVT = MVT::i32;
    if (!Reg) {
      unsigned StackOffset = State.AllocateStack(8, 8);
      State.addLoc(
          CCValAssign::getMem(ValNo, ValVT, StackOffset, LocVT, LocInfo));
      return false;
    }
    if (!State.AllocateReg(ArgGPRs))
      State.AllocateStack(4, 4);
    State.addLoc(CCValAssign::getReg(ValNo, ValVT, Reg, LocVT, LocInfo));
    return false;
  }

  // Split arguments might be passed indirectly, so keep track of the pending
  // values.
  if (ArgFlags.isSplit() || !PendingLocs.empty()) {
    LocVT = XLenVT;
    LocInfo = CCValAssign::Indirect;
    PendingLocs.push_back(
        CCValAssign::getPending(ValNo, ValVT, LocVT, LocInfo));
    PendingArgFlags.push_back(ArgFlags);
    if (!ArgFlags.isSplitEnd()) {
      return false;
    }
  }

  // If the split argument only had two elements, it should be passed directly
  // in registers or on the stack.
  if (ArgFlags.isSplitEnd() && PendingLocs.size() <= 2) {
    assert(PendingLocs.size() == 2 && "Unexpected PendingLocs.size()");
    // Apply the normal calling convention rules to the first half of the
    // split argument.
    CCValAssign VA = PendingLocs[0];
    ISD::ArgFlagsTy AF = PendingArgFlags[0];
    PendingLocs.clear();
    PendingArgFlags.clear();
    return CC_RISCVAssign2XLen(XLen, State, VA, AF, ValNo, ValVT, LocVT,
                               ArgFlags);
  }

  // Allocate to a register if possible, or else a stack slot.
  Register Reg;
  if (ValVT == MVT::f32 && !UseGPRForF32)
    Reg = State.AllocateReg(ArgFPR32s, ArgFPR64s);
  else if (ValVT == MVT::f64 && !UseGPRForF64)
    Reg = State.AllocateReg(ArgFPR64s, ArgFPR32s);
  else
    Reg = State.AllocateReg(ArgGPRs);
  unsigned StackOffset = Reg ? 0 : State.AllocateStack(XLen / 8, XLen / 8);

  // If we reach this point and PendingLocs is non-empty, we must be at the
  // end of a split argument that must be passed indirectly.
  if (!PendingLocs.empty()) {
    assert(ArgFlags.isSplitEnd() && "Expected ArgFlags.isSplitEnd()");
    assert(PendingLocs.size() > 2 && "Unexpected PendingLocs.size()");

    for (auto &It : PendingLocs) {
      if (Reg)
        It.convertToReg(Reg);
      else
        It.convertToMem(StackOffset);
      State.addLoc(It);
    }
    PendingLocs.clear();
    PendingArgFlags.clear();
    return false;
  }

  assert((!UseGPRForF32 || !UseGPRForF64 || LocVT == XLenVT) &&
         "Expected an XLenVT at this stage");

  if (Reg) {
    State.addLoc(CCValAssign::getReg(ValNo, ValVT, Reg, LocVT, LocInfo));
    return false;
  }

  // When an f32 or f64 is passed on the stack, no bit-conversion is needed.
  if (ValVT == MVT::f32 || ValVT == MVT::f64) {
    LocVT = ValVT;
    LocInfo = CCValAssign::Full;
  }
  State.addLoc(CCValAssign::getMem(ValNo, ValVT, StackOffset, LocVT, LocInfo));
  return false;
}

void RISCVTargetLowering::analyzeInputArgs(
    MachineFunction &MF, CCState &CCInfo,
    const SmallVectorImpl<ISD::InputArg> &Ins, bool IsRet) const {
  unsigned NumArgs = Ins.size();
  FunctionType *FType = MF.getFunction().getFunctionType();

  for (unsigned i = 0; i != NumArgs; ++i) {
    MVT ArgVT = Ins[i].VT;
    ISD::ArgFlagsTy ArgFlags = Ins[i].Flags;

    Type *ArgTy = nullptr;
    if (IsRet)
      ArgTy = FType->getReturnType();
    else if (Ins[i].isOrigArg())
      ArgTy = FType->getParamType(Ins[i].getOrigArgIndex());

    RISCVABI::ABI ABI = MF.getSubtarget<RISCVSubtarget>().getTargetABI();
    if (CC_RISCV(MF.getDataLayout(), ABI, i, ArgVT, ArgVT, CCValAssign::Full,
                 ArgFlags, CCInfo, /*IsRet=*/true, IsRet, ArgTy)) {
      LLVM_DEBUG(dbgs() << "InputArg #" << i << " has unhandled type "
                        << EVT(ArgVT).getEVTString() << '\n');
      llvm_unreachable(nullptr);
    }
  }
}

void RISCVTargetLowering::analyzeOutputArgs(
    MachineFunction &MF, CCState &CCInfo,
    const SmallVectorImpl<ISD::OutputArg> &Outs, bool IsRet,
    CallLoweringInfo *CLI) const {
  unsigned NumArgs = Outs.size();

  for (unsigned i = 0; i != NumArgs; i++) {
    MVT ArgVT = Outs[i].VT;
    ISD::ArgFlagsTy ArgFlags = Outs[i].Flags;
    Type *OrigTy = CLI ? CLI->getArgs()[Outs[i].OrigArgIndex].Ty : nullptr;

    RISCVABI::ABI ABI = MF.getSubtarget<RISCVSubtarget>().getTargetABI();
    if (CC_RISCV(MF.getDataLayout(), ABI, i, ArgVT, ArgVT, CCValAssign::Full,
                 ArgFlags, CCInfo, Outs[i].IsFixed, IsRet, OrigTy)) {
      LLVM_DEBUG(dbgs() << "OutputArg #" << i << " has unhandled type "
                        << EVT(ArgVT).getEVTString() << "\n");
      llvm_unreachable(nullptr);
    }
  }
}

// Convert Val to a ValVT. Should not be called for CCValAssign::Indirect
// values.
static SDValue convertLocVTToValVT(SelectionDAG &DAG, SDValue Val,
                                   const CCValAssign &VA, const SDLoc &DL) {
  switch (VA.getLocInfo()) {
  default:
    llvm_unreachable("Unexpected CCValAssign::LocInfo");
  case CCValAssign::Full:
    break;
  case CCValAssign::BCvt:
    if (VA.getLocVT() == MVT::i64 && VA.getValVT() == MVT::f32) {
      Val = DAG.getNode(RISCVISD::FMV_W_X_RV64, DL, MVT::f32, Val);
      break;
    }
    Val = DAG.getNode(ISD::BITCAST, DL, VA.getValVT(), Val);
    break;
  }
  return Val;
}

// The caller is responsible for loading the full value if the argument is
// passed with CCValAssign::Indirect.
static SDValue unpackFromRegLoc(SelectionDAG &DAG, SDValue Chain,
                                const CCValAssign &VA, const SDLoc &DL) {
  MachineFunction &MF = DAG.getMachineFunction();
  MachineRegisterInfo &RegInfo = MF.getRegInfo();
  EVT LocVT = VA.getLocVT();
  SDValue Val;
  const TargetRegisterClass *RC;

  switch (LocVT.getSimpleVT().SimpleTy) {
  default:
    llvm_unreachable("Unexpected register type");
  case MVT::i32:
  case MVT::i64:
    RC = &RISCV::GPRRegClass;
    break;
  case MVT::f32:
    RC = &RISCV::FPR32RegClass;
    break;
  case MVT::f64:
    RC = &RISCV::FPR64RegClass;
    break;
  }

  Register VReg = RegInfo.createVirtualRegister(RC);
  RegInfo.addLiveIn(VA.getLocReg(), VReg);
  Val = DAG.getCopyFromReg(Chain, DL, VReg, LocVT);

  if (VA.getLocInfo() == CCValAssign::Indirect)
    return Val;

  return convertLocVTToValVT(DAG, Val, VA, DL);
}

static SDValue convertValVTToLocVT(SelectionDAG &DAG, SDValue Val,
                                   const CCValAssign &VA, const SDLoc &DL) {
  EVT LocVT = VA.getLocVT();

  switch (VA.getLocInfo()) {
  default:
    llvm_unreachable("Unexpected CCValAssign::LocInfo");
  case CCValAssign::Full:
    break;
  case CCValAssign::BCvt:
    if (VA.getLocVT() == MVT::i64 && VA.getValVT() == MVT::f32) {
      Val = DAG.getNode(RISCVISD::FMV_X_ANYEXTW_RV64, DL, MVT::i64, Val);
      break;
    }
    Val = DAG.getNode(ISD::BITCAST, DL, LocVT, Val);
    break;
  }
  return Val;
}

// The caller is responsible for loading the full value if the argument is
// passed with CCValAssign::Indirect.
static SDValue unpackFromMemLoc(SelectionDAG &DAG, SDValue Chain,
                                const CCValAssign &VA, const SDLoc &DL) {
  MachineFunction &MF = DAG.getMachineFunction();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  EVT LocVT = VA.getLocVT();
  EVT ValVT = VA.getValVT();
  EVT PtrVT = MVT::getIntegerVT(DAG.getDataLayout().getPointerSizeInBits(0));
  int FI = MFI.CreateFixedObject(ValVT.getSizeInBits() / 8,
                                 VA.getLocMemOffset(), /*Immutable=*/true);
  SDValue FIN = DAG.getFrameIndex(FI, PtrVT);
  SDValue Val;

  ISD::LoadExtType ExtType;
  switch (VA.getLocInfo()) {
  default:
    llvm_unreachable("Unexpected CCValAssign::LocInfo");
  case CCValAssign::Full:
  case CCValAssign::Indirect:
  case CCValAssign::BCvt:
    ExtType = ISD::NON_EXTLOAD;
    break;
  }
  Val = DAG.getExtLoad(
      ExtType, DL, LocVT, Chain, FIN,
      MachinePointerInfo::getFixedStack(DAG.getMachineFunction(), FI), ValVT);
  return Val;
}

static SDValue unpackF64OnRV32DSoftABI(SelectionDAG &DAG, SDValue Chain,
                                       const CCValAssign &VA, const SDLoc &DL) {
  assert(VA.getLocVT() == MVT::i32 && VA.getValVT() == MVT::f64 &&
         "Unexpected VA");
  MachineFunction &MF = DAG.getMachineFunction();
  MachineFrameInfo &MFI = MF.getFrameInfo();
  MachineRegisterInfo &RegInfo = MF.getRegInfo();

  if (VA.isMemLoc()) {
    // f64 is passed on the stack.
    int FI = MFI.CreateFixedObject(8, VA.getLocMemOffset(), /*Immutable=*/true);
    SDValue FIN = DAG.getFrameIndex(FI, MVT::i32);
    return DAG.getLoad(MVT::f64, DL, Chain, FIN,
                       MachinePointerInfo::getFixedStack(MF, FI));
  }

  assert(VA.isRegLoc() && "Expected register VA assignment");

  Register LoVReg = RegInfo.createVirtualRegister(&RISCV::GPRRegClass);
  RegInfo.addLiveIn(VA.getLocReg(), LoVReg);
  SDValue Lo = DAG.getCopyFromReg(Chain, DL, LoVReg, MVT::i32);
  SDValue Hi;
  if (VA.getLocReg() == RISCV::X17) {
    // Second half of f64 is passed on the stack.
    int FI = MFI.CreateFixedObject(4, 0, /*Immutable=*/true);
    SDValue FIN = DAG.getFrameIndex(FI, MVT::i32);
    Hi = DAG.getLoad(MVT::i32, DL, Chain, FIN,
                     MachinePointerInfo::getFixedStack(MF, FI));
  } else {
    // Second half of f64 is passed in another GPR.
    Register HiVReg = RegInfo.createVirtualRegister(&RISCV::GPRRegClass);
    RegInfo.addLiveIn(VA.getLocReg() + 1, HiVReg);
    Hi = DAG.getCopyFromReg(Chain, DL, HiVReg, MVT::i32);
  }
  return DAG.getNode(RISCVISD::BuildPairF64, DL, MVT::f64, Lo, Hi);
}

// FastCC has less than 1% performance improvement for some particular
// benchmark. But theoretically, it may has benenfit for some cases.
static bool CC_RISCV_FastCC(unsigned ValNo, MVT ValVT, MVT LocVT,
                            CCValAssign::LocInfo LocInfo,
                            ISD::ArgFlagsTy ArgFlags, CCState &State) {

  if (LocVT == MVT::i32 || LocVT == MVT::i64) {
    // X5 and X6 might be used for save-restore libcall.
    static const MCPhysReg GPRList[] = {
        RISCV::X10, RISCV::X11, RISCV::X12, RISCV::X13, RISCV::X14,
        RISCV::X15, RISCV::X16, RISCV::X17, RISCV::X7,  RISCV::X28,
        RISCV::X29, RISCV::X30, RISCV::X31};
    if (unsigned Reg = State.AllocateReg(GPRList)) {
      State.addLoc(CCValAssign::getReg(ValNo, ValVT, Reg, LocVT, LocInfo));
      return false;
    }
  }

  if (LocVT == MVT::f32) {
    static const MCPhysReg FPR32List[] = {
        RISCV::F10_F, RISCV::F11_F, RISCV::F12_F, RISCV::F13_F, RISCV::F14_F,
        RISCV::F15_F, RISCV::F16_F, RISCV::F17_F, RISCV::F0_F,  RISCV::F1_F,
        RISCV::F2_F,  RISCV::F3_F,  RISCV::F4_F,  RISCV::F5_F,  RISCV::F6_F,
        RISCV::F7_F,  RISCV::F28_F, RISCV::F29_F, RISCV::F30_F, RISCV::F31_F};
    if (unsigned Reg = State.AllocateReg(FPR32List)) {
      State.addLoc(CCValAssign::getReg(ValNo, ValVT, Reg, LocVT, LocInfo));
      return false;
    }
  }

  if (LocVT == MVT::f64) {
    static const MCPhysReg FPR64List[] = {
        RISCV::F10_D, RISCV::F11_D, RISCV::F12_D, RISCV::F13_D, RISCV::F14_D,
        RISCV::F15_D, RISCV::F16_D, RISCV::F17_D, RISCV::F0_D,  RISCV::F1_D,
        RISCV::F2_D,  RISCV::F3_D,  RISCV::F4_D,  RISCV::F5_D,  RISCV::F6_D,
        RISCV::F7_D,  RISCV::F28_D, RISCV::F29_D, RISCV::F30_D, RISCV::F31_D};
    if (unsigned Reg = State.AllocateReg(FPR64List)) {
      State.addLoc(CCValAssign::getReg(ValNo, ValVT, Reg, LocVT, LocInfo));
      return false;
    }
  }

  if (LocVT == MVT::i32 || LocVT == MVT::f32) {
    unsigned Offset4 = State.AllocateStack(4, 4);
    State.addLoc(CCValAssign::getMem(ValNo, ValVT, Offset4, LocVT, LocInfo));
    return false;
  }

  if (LocVT == MVT::i64 || LocVT == MVT::f64) {
    unsigned Offset5 = State.AllocateStack(8, 8);
    State.addLoc(CCValAssign::getMem(ValNo, ValVT, Offset5, LocVT, LocInfo));
    return false;
  }

  return true; // CC didn't match.
}

// Transform physical registers into virtual registers.
SDValue RISCVTargetLowering::LowerFormalArguments(
    SDValue Chain, CallingConv::ID CallConv, bool IsVarArg,
    const SmallVectorImpl<ISD::InputArg> &Ins, const SDLoc &DL,
    SelectionDAG &DAG, SmallVectorImpl<SDValue> &InVals) const {

  switch (CallConv) {
  default:
    report_fatal_error("Unsupported calling convention");
  case CallingConv::C:
  case CallingConv::Fast:
    break;
  }

  MachineFunction &MF = DAG.getMachineFunction();

  const Function &Func = MF.getFunction();
  if (Func.hasFnAttribute("interrupt")) {
    if (!Func.arg_empty())
      report_fatal_error(
        "Functions with the interrupt attribute cannot have arguments!");

    StringRef Kind =
      MF.getFunction().getFnAttribute("interrupt").getValueAsString();

    if (!(Kind == "user" || Kind == "supervisor" || Kind == "machine"))
      report_fatal_error(
        "Function interrupt attribute argument not supported!");
  }

  EVT PtrVT = getPointerTy(DAG.getDataLayout());
  MVT XLenVT = Subtarget.getXLenVT();
  unsigned XLenInBytes = Subtarget.getXLen() / 8;
  // Used with vargs to acumulate store chains.
  std::vector<SDValue> OutChains;

  // Assign locations to all of the incoming arguments.
  SmallVector<CCValAssign, 16> ArgLocs;
  CCState CCInfo(CallConv, IsVarArg, MF, ArgLocs, *DAG.getContext());

  if (CallConv == CallingConv::Fast)
    CCInfo.AnalyzeFormalArguments(Ins, CC_RISCV_FastCC);
  else
    analyzeInputArgs(MF, CCInfo, Ins, /*IsRet=*/false);

  for (unsigned i = 0, e = ArgLocs.size(); i != e; ++i) {
    CCValAssign &VA = ArgLocs[i];
    SDValue ArgValue;
    // Passing f64 on RV32D with a soft float ABI must be handled as a special
    // case.
    if (VA.getLocVT() == MVT::i32 && VA.getValVT() == MVT::f64)
      ArgValue = unpackF64OnRV32DSoftABI(DAG, Chain, VA, DL);
    else if (VA.isRegLoc())
      ArgValue = unpackFromRegLoc(DAG, Chain, VA, DL);
    else
      ArgValue = unpackFromMemLoc(DAG, Chain, VA, DL);

    if (VA.getLocInfo() == CCValAssign::Indirect) {
      // If the original argument was split and passed by reference (e.g. i128
      // on RV32), we need to load all parts of it here (using the same
      // address).
      InVals.push_back(DAG.getLoad(VA.getValVT(), DL, Chain, ArgValue,
                                   MachinePointerInfo()));
      unsigned ArgIndex = Ins[i].OrigArgIndex;
      assert(Ins[i].PartOffset == 0);
      while (i + 1 != e && Ins[i + 1].OrigArgIndex == ArgIndex) {
        CCValAssign &PartVA = ArgLocs[i + 1];
        unsigned PartOffset = Ins[i + 1].PartOffset;
        SDValue Address = DAG.getNode(ISD::ADD, DL, PtrVT, ArgValue,
                                      DAG.getIntPtrConstant(PartOffset, DL));
        InVals.push_back(DAG.getLoad(PartVA.getValVT(), DL, Chain, Address,
                                     MachinePointerInfo()));
        ++i;
      }
      continue;
    }
    InVals.push_back(ArgValue);
  }

  if (IsVarArg) {
    ArrayRef<MCPhysReg> ArgRegs = makeArrayRef(ArgGPRs);
    unsigned Idx = CCInfo.getFirstUnallocated(ArgRegs);
    const TargetRegisterClass *RC = &RISCV::GPRRegClass;
    MachineFrameInfo &MFI = MF.getFrameInfo();
    MachineRegisterInfo &RegInfo = MF.getRegInfo();
    RISCVMachineFunctionInfo *RVFI = MF.getInfo<RISCVMachineFunctionInfo>();

    // Offset of the first variable argument from stack pointer, and size of
    // the vararg save area. For now, the varargs save area is either zero or
    // large enough to hold a0-a7.
    int VaArgOffset, VarArgsSaveSize;

    // If all registers are allocated, then all varargs must be passed on the
    // stack and we don't need to save any argregs.
    if (ArgRegs.size() == Idx) {
      VaArgOffset = CCInfo.getNextStackOffset();
      VarArgsSaveSize = 0;
    } else {
      VarArgsSaveSize = XLenInBytes * (ArgRegs.size() - Idx);
      VaArgOffset = -VarArgsSaveSize;
    }

    // Record the frame index of the first variable argument
    // which is a value necessary to VASTART.
    int FI = MFI.CreateFixedObject(XLenInBytes, VaArgOffset, true);
    RVFI->setVarArgsFrameIndex(FI);

    // If saving an odd number of registers then create an extra stack slot to
    // ensure that the frame pointer is 2*XLEN-aligned, which in turn ensures
    // offsets to even-numbered registered remain 2*XLEN-aligned.
    if (Idx % 2) {
      MFI.CreateFixedObject(XLenInBytes, VaArgOffset - (int)XLenInBytes, true);
      VarArgsSaveSize += XLenInBytes;
    }

    // Copy the integer registers that may have been used for passing varargs
    // to the vararg save area.
    for (unsigned I = Idx; I < ArgRegs.size();
         ++I, VaArgOffset += XLenInBytes) {
      const Register Reg = RegInfo.createVirtualRegister(RC);
      RegInfo.addLiveIn(ArgRegs[I], Reg);
      SDValue ArgValue = DAG.getCopyFromReg(Chain, DL, Reg, XLenVT);
      FI = MFI.CreateFixedObject(XLenInBytes, VaArgOffset, true);
      SDValue PtrOff = DAG.getFrameIndex(FI, getPointerTy(DAG.getDataLayout()));
      SDValue Store = DAG.getStore(Chain, DL, ArgValue, PtrOff,
                                   MachinePointerInfo::getFixedStack(MF, FI));
      cast<StoreSDNode>(Store.getNode())
          ->getMemOperand()
          ->setValue((Value *)nullptr);
      OutChains.push_back(Store);
    }
    RVFI->setVarArgsSaveSize(VarArgsSaveSize);
  }

  // All stores are grouped in one node to allow the matching between
  // the size of Ins and InVals. This only happens for vararg functions.
  if (!OutChains.empty()) {
    OutChains.push_back(Chain);
    Chain = DAG.getNode(ISD::TokenFactor, DL, MVT::Other, OutChains);
  }

  return Chain;
}

/// isEligibleForTailCallOptimization - Check whether the call is eligible
/// for tail call optimization.
/// Note: This is modelled after ARM's IsEligibleForTailCallOptimization.
bool RISCVTargetLowering::isEligibleForTailCallOptimization(
    CCState &CCInfo, CallLoweringInfo &CLI, MachineFunction &MF,
    const SmallVector<CCValAssign, 16> &ArgLocs) const {

  auto &Callee = CLI.Callee;
  auto CalleeCC = CLI.CallConv;
  auto &Outs = CLI.Outs;
  auto &Caller = MF.getFunction();
  auto CallerCC = Caller.getCallingConv();

  // Exception-handling functions need a special set of instructions to
  // indicate a return to the hardware. Tail-calling another function would
  // probably break this.
  // TODO: The "interrupt" attribute isn't currently defined by RISC-V. This
  // should be expanded as new function attributes are introduced.
  if (Caller.hasFnAttribute("interrupt"))
    return false;

  // Do not tail call opt if the stack is used to pass parameters.
  if (CCInfo.getNextStackOffset() != 0)
    return false;

  // Do not tail call opt if any parameters need to be passed indirectly.
  // Since long doubles (fp128) and i128 are larger than 2*XLEN, they are
  // passed indirectly. So the address of the value will be passed in a
  // register, or if not available, then the address is put on the stack. In
  // order to pass indirectly, space on the stack often needs to be allocated
  // in order to store the value. In this case the CCInfo.getNextStackOffset()
  // != 0 check is not enough and we need to check if any CCValAssign ArgsLocs
  // are passed CCValAssign::Indirect.
  for (auto &VA : ArgLocs)
    if (VA.getLocInfo() == CCValAssign::Indirect)
      return false;

  // Do not tail call opt if either caller or callee uses struct return
  // semantics.
  auto IsCallerStructRet = Caller.hasStructRetAttr();
  auto IsCalleeStructRet = Outs.empty() ? false : Outs[0].Flags.isSRet();
  if (IsCallerStructRet || IsCalleeStructRet)
    return false;

  // Externally-defined functions with weak linkage should not be
  // tail-called. The behaviour of branch instructions in this situation (as
  // used for tail calls) is implementation-defined, so we cannot rely on the
  // linker replacing the tail call with a return.
  if (GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(Callee)) {
    const GlobalValue *GV = G->getGlobal();
    if (GV->hasExternalWeakLinkage())
      return false;
  }

  // The callee has to preserve all registers the caller needs to preserve.
  const RISCVRegisterInfo *TRI = Subtarget.getRegisterInfo();
  const uint32_t *CallerPreserved = TRI->getCallPreservedMask(MF, CallerCC);
  if (CalleeCC != CallerCC) {
    const uint32_t *CalleePreserved = TRI->getCallPreservedMask(MF, CalleeCC);
    if (!TRI->regmaskSubsetEqual(CallerPreserved, CalleePreserved))
      return false;
  }

  // Byval parameters hand the function a pointer directly into the stack area
  // we want to reuse during a tail call. Working around this *is* possible
  // but less efficient and uglier in LowerCall.
  for (auto &Arg : Outs)
    if (Arg.Flags.isByVal())
      return false;

  return true;
}

// Lower a call to a callseq_start + CALL + callseq_end chain, and add input
// and output parameter nodes.
SDValue RISCVTargetLowering::LowerCall(CallLoweringInfo &CLI,
                                       SmallVectorImpl<SDValue> &InVals) const {
  SelectionDAG &DAG = CLI.DAG;
  SDLoc &DL = CLI.DL;
  SmallVectorImpl<ISD::OutputArg> &Outs = CLI.Outs;
  SmallVectorImpl<SDValue> &OutVals = CLI.OutVals;
  SmallVectorImpl<ISD::InputArg> &Ins = CLI.Ins;
  SDValue Chain = CLI.Chain;
  SDValue Callee = CLI.Callee;
  bool &IsTailCall = CLI.IsTailCall;
  CallingConv::ID CallConv = CLI.CallConv;
  bool IsVarArg = CLI.IsVarArg;
  EVT PtrVT = getPointerTy(DAG.getDataLayout());
  MVT XLenVT = Subtarget.getXLenVT();

  MachineFunction &MF = DAG.getMachineFunction();

  // Analyze the operands of the call, assigning locations to each operand.
  SmallVector<CCValAssign, 16> ArgLocs;
  CCState ArgCCInfo(CallConv, IsVarArg, MF, ArgLocs, *DAG.getContext());

  if (CallConv == CallingConv::Fast)
    ArgCCInfo.AnalyzeCallOperands(Outs, CC_RISCV_FastCC);
  else
    analyzeOutputArgs(MF, ArgCCInfo, Outs, /*IsRet=*/false, &CLI);

  // Check if it's really possible to do a tail call.
  if (IsTailCall)
    IsTailCall = isEligibleForTailCallOptimization(ArgCCInfo, CLI, MF, ArgLocs);

  if (IsTailCall)
    ++NumTailCalls;
  else if (CLI.CS && CLI.CS.isMustTailCall())
    report_fatal_error("failed to perform tail call elimination on a call "
                       "site marked musttail");

  // Get a count of how many bytes are to be pushed on the stack.
  unsigned NumBytes = ArgCCInfo.getNextStackOffset();

  // Create local copies for byval args
  SmallVector<SDValue, 8> ByValArgs;
  for (unsigned i = 0, e = Outs.size(); i != e; ++i) {
    ISD::ArgFlagsTy Flags = Outs[i].Flags;
    if (!Flags.isByVal())
      continue;

    SDValue Arg = OutVals[i];
    unsigned Size = Flags.getByValSize();
    unsigned Align = Flags.getByValAlign();

    int FI = MF.getFrameInfo().CreateStackObject(Size, Align, /*isSS=*/false);
    SDValue FIPtr = DAG.getFrameIndex(FI, getPointerTy(DAG.getDataLayout()));
    SDValue SizeNode = DAG.getConstant(Size, DL, XLenVT);

    Chain = DAG.getMemcpy(Chain, DL, FIPtr, Arg, SizeNode, Align,
                          /*IsVolatile=*/false,
                          /*AlwaysInline=*/false,
                          IsTailCall, MachinePointerInfo(),
                          MachinePointerInfo());
    ByValArgs.push_back(FIPtr);
  }

  if (!IsTailCall)
    Chain = DAG.getCALLSEQ_START(Chain, NumBytes, 0, CLI.DL);

  // Copy argument values to their designated locations.
  SmallVector<std::pair<Register, SDValue>, 8> RegsToPass;
  SmallVector<SDValue, 8> MemOpChains;
  SDValue StackPtr;
  for (unsigned i = 0, j = 0, e = ArgLocs.size(); i != e; ++i) {
    CCValAssign &VA = ArgLocs[i];
    SDValue ArgValue = OutVals[i];
    ISD::ArgFlagsTy Flags = Outs[i].Flags;

    // Handle passing f64 on RV32D with a soft float ABI as a special case.
    bool IsF64OnRV32DSoftABI =
        VA.getLocVT() == MVT::i32 && VA.getValVT() == MVT::f64;
    if (IsF64OnRV32DSoftABI && VA.isRegLoc()) {
      SDValue SplitF64 = DAG.getNode(
          RISCVISD::SplitF64, DL, DAG.getVTList(MVT::i32, MVT::i32), ArgValue);
      SDValue Lo = SplitF64.getValue(0);
      SDValue Hi = SplitF64.getValue(1);

      Register RegLo = VA.getLocReg();
      RegsToPass.push_back(std::make_pair(RegLo, Lo));

      if (RegLo == RISCV::X17) {
        // Second half of f64 is passed on the stack.
        // Work out the address of the stack slot.
        if (!StackPtr.getNode())
          StackPtr = DAG.getCopyFromReg(Chain, DL, RISCV::X2, PtrVT);
        // Emit the store.
        MemOpChains.push_back(
            DAG.getStore(Chain, DL, Hi, StackPtr, MachinePointerInfo()));
      } else {
        // Second half of f64 is passed in another GPR.
        assert(RegLo < RISCV::X31 && "Invalid register pair");
        Register RegHigh = RegLo + 1;
        RegsToPass.push_back(std::make_pair(RegHigh, Hi));
      }
      continue;
    }

    // IsF64OnRV32DSoftABI && VA.isMemLoc() is handled below in the same way
    // as any other MemLoc.

    // Promote the value if needed.
    // For now, only handle fully promoted and indirect arguments.
    if (VA.getLocInfo() == CCValAssign::Indirect) {
      // Store the argument in a stack slot and pass its address.
      SDValue SpillSlot = DAG.CreateStackTemporary(Outs[i].ArgVT);
      int FI = cast<FrameIndexSDNode>(SpillSlot)->getIndex();
      MemOpChains.push_back(
          DAG.getStore(Chain, DL, ArgValue, SpillSlot,
                       MachinePointerInfo::getFixedStack(MF, FI)));
      // If the original argument was split (e.g. i128), we need
      // to store all parts of it here (and pass just one address).
      unsigned ArgIndex = Outs[i].OrigArgIndex;
      assert(Outs[i].PartOffset == 0);
      while (i + 1 != e && Outs[i + 1].OrigArgIndex == ArgIndex) {
        SDValue PartValue = OutVals[i + 1];
        unsigned PartOffset = Outs[i + 1].PartOffset;
        SDValue Address = DAG.getNode(ISD::ADD, DL, PtrVT, SpillSlot,
                                      DAG.getIntPtrConstant(PartOffset, DL));
        MemOpChains.push_back(
            DAG.getStore(Chain, DL, PartValue, Address,
                         MachinePointerInfo::getFixedStack(MF, FI)));
        ++i;
      }
      ArgValue = SpillSlot;
    } else {
      ArgValue = convertValVTToLocVT(DAG, ArgValue, VA, DL);
    }

    // Use local copy if it is a byval arg.
    if (Flags.isByVal())
      ArgValue = ByValArgs[j++];

    if (VA.isRegLoc()) {
      // Queue up the argument copies and emit them at the end.
      RegsToPass.push_back(std::make_pair(VA.getLocReg(), ArgValue));
    } else {
      assert(VA.isMemLoc() && "Argument not register or memory");
      assert(!IsTailCall && "Tail call not allowed if stack is used "
                            "for passing parameters");

      // Work out the address of the stack slot.
      if (!StackPtr.getNode())
        StackPtr = DAG.getCopyFromReg(Chain, DL, RISCV::X2, PtrVT);
      SDValue Address =
          DAG.getNode(ISD::ADD, DL, PtrVT, StackPtr,
                      DAG.getIntPtrConstant(VA.getLocMemOffset(), DL));

      // Emit the store.
      MemOpChains.push_back(
          DAG.getStore(Chain, DL, ArgValue, Address, MachinePointerInfo()));
    }
  }

  // Join the stores, which are independent of one another.
  if (!MemOpChains.empty())
    Chain = DAG.getNode(ISD::TokenFactor, DL, MVT::Other, MemOpChains);

  SDValue Glue;

  // Build a sequence of copy-to-reg nodes, chained and glued together.
  for (auto &Reg : RegsToPass) {
    Chain = DAG.getCopyToReg(Chain, DL, Reg.first, Reg.second, Glue);
    Glue = Chain.getValue(1);
  }

  // Validate that none of the argument registers have been marked as
  // reserved, if so report an error. Do the same for the return address if this
  // is not a tailcall.
  validateCCReservedRegs(RegsToPass, MF);
  if (!IsTailCall &&
      MF.getSubtarget<RISCVSubtarget>().isRegisterReservedByUser(RISCV::X1))
    MF.getFunction().getContext().diagnose(DiagnosticInfoUnsupported{
        MF.getFunction(),
        "Return address register required, but has been reserved."});

  // If the callee is a GlobalAddress/ExternalSymbol node, turn it into a
  // TargetGlobalAddress/TargetExternalSymbol node so that legalize won't
  // split it and then direct call can be matched by PseudoCALL.
  if (GlobalAddressSDNode *S = dyn_cast<GlobalAddressSDNode>(Callee)) {
    const GlobalValue *GV = S->getGlobal();

    unsigned OpFlags = RISCVII::MO_CALL;
    if (!getTargetMachine().shouldAssumeDSOLocal(*GV->getParent(), GV))
      OpFlags = RISCVII::MO_PLT;

    Callee = DAG.getTargetGlobalAddress(GV, DL, PtrVT, 0, OpFlags);
  } else if (ExternalSymbolSDNode *S = dyn_cast<ExternalSymbolSDNode>(Callee)) {
    unsigned OpFlags = RISCVII::MO_CALL;

    if (!getTargetMachine().shouldAssumeDSOLocal(*MF.getFunction().getParent(),
                                                 nullptr))
      OpFlags = RISCVII::MO_PLT;

    Callee = DAG.getTargetExternalSymbol(S->getSymbol(), PtrVT, OpFlags);
  }

  // The first call operand is the chain and the second is the target address.
  SmallVector<SDValue, 8> Ops;
  Ops.push_back(Chain);
  Ops.push_back(Callee);

  // Add argument registers to the end of the list so that they are
  // known live into the call.
  for (auto &Reg : RegsToPass)
    Ops.push_back(DAG.getRegister(Reg.first, Reg.second.getValueType()));

  if (!IsTailCall) {
    // Add a register mask operand representing the call-preserved registers.
    const TargetRegisterInfo *TRI = Subtarget.getRegisterInfo();
    const uint32_t *Mask = TRI->getCallPreservedMask(MF, CallConv);
    assert(Mask && "Missing call preserved mask for calling convention");
    Ops.push_back(DAG.getRegisterMask(Mask));
  }

  // Glue the call to the argument copies, if any.
  if (Glue.getNode())
    Ops.push_back(Glue);

  // Emit the call.
  SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);

  if (IsTailCall) {
    MF.getFrameInfo().setHasTailCall();
    return DAG.getNode(RISCVISD::TAIL, DL, NodeTys, Ops);
  }

  Chain = DAG.getNode(RISCVISD::CALL, DL, NodeTys, Ops);
  Glue = Chain.getValue(1);

  // Mark the end of the call, which is glued to the call itself.
  Chain = DAG.getCALLSEQ_END(Chain,
                             DAG.getConstant(NumBytes, DL, PtrVT, true),
                             DAG.getConstant(0, DL, PtrVT, true),
                             Glue, DL);
  Glue = Chain.getValue(1);

  // Assign locations to each value returned by this call.
  SmallVector<CCValAssign, 16> RVLocs;
  CCState RetCCInfo(CallConv, IsVarArg, MF, RVLocs, *DAG.getContext());
  analyzeInputArgs(MF, RetCCInfo, Ins, /*IsRet=*/true);

  // Copy all of the result registers out of their specified physreg.
  for (auto &VA : RVLocs) {
    // Copy the value out
    SDValue RetValue =
        DAG.getCopyFromReg(Chain, DL, VA.getLocReg(), VA.getLocVT(), Glue);
    // Glue the RetValue to the end of the call sequence
    Chain = RetValue.getValue(1);
    Glue = RetValue.getValue(2);

    if (VA.getLocVT() == MVT::i32 && VA.getValVT() == MVT::f64) {
      assert(VA.getLocReg() == ArgGPRs[0] && "Unexpected reg assignment");
      SDValue RetValue2 =
          DAG.getCopyFromReg(Chain, DL, ArgGPRs[1], MVT::i32, Glue);
      Chain = RetValue2.getValue(1);
      Glue = RetValue2.getValue(2);
      RetValue = DAG.getNode(RISCVISD::BuildPairF64, DL, MVT::f64, RetValue,
                             RetValue2);
    }

    RetValue = convertLocVTToValVT(DAG, RetValue, VA, DL);

    InVals.push_back(RetValue);
  }

  return Chain;
}

bool RISCVTargetLowering::CanLowerReturn(
    CallingConv::ID CallConv, MachineFunction &MF, bool IsVarArg,
    const SmallVectorImpl<ISD::OutputArg> &Outs, LLVMContext &Context) const {
  SmallVector<CCValAssign, 16> RVLocs;
  CCState CCInfo(CallConv, IsVarArg, MF, RVLocs, Context);
  for (unsigned i = 0, e = Outs.size(); i != e; ++i) {
    MVT VT = Outs[i].VT;
    ISD::ArgFlagsTy ArgFlags = Outs[i].Flags;
    RISCVABI::ABI ABI = MF.getSubtarget<RISCVSubtarget>().getTargetABI();
    if (CC_RISCV(MF.getDataLayout(), ABI, i, VT, VT, CCValAssign::Full,
                 ArgFlags, CCInfo, /*IsFixed=*/true, /*IsRet=*/true, nullptr))
      return false;
  }
  return true;
}

SDValue
RISCVTargetLowering::LowerReturn(SDValue Chain, CallingConv::ID CallConv,
                                 bool IsVarArg,
                                 const SmallVectorImpl<ISD::OutputArg> &Outs,
                                 const SmallVectorImpl<SDValue> &OutVals,
                                 const SDLoc &DL, SelectionDAG &DAG) const {
  const MachineFunction &MF = DAG.getMachineFunction();
  const RISCVSubtarget &STI = MF.getSubtarget<RISCVSubtarget>();

  // Stores the assignment of the return value to a location.
  SmallVector<CCValAssign, 16> RVLocs;

  // Info about the registers and stack slot.
  CCState CCInfo(CallConv, IsVarArg, DAG.getMachineFunction(), RVLocs,
                 *DAG.getContext());

  analyzeOutputArgs(DAG.getMachineFunction(), CCInfo, Outs, /*IsRet=*/true,
                    nullptr);

  SDValue Glue;
  SmallVector<SDValue, 4> RetOps(1, Chain);

  // Copy the result values into the output registers.
  for (unsigned i = 0, e = RVLocs.size(); i < e; ++i) {
    SDValue Val = OutVals[i];
    CCValAssign &VA = RVLocs[i];
    assert(VA.isRegLoc() && "Can only return in registers!");

    if (VA.getLocVT() == MVT::i32 && VA.getValVT() == MVT::f64) {
      // Handle returning f64 on RV32D with a soft float ABI.
      assert(VA.isRegLoc() && "Expected return via registers");
      SDValue SplitF64 = DAG.getNode(RISCVISD::SplitF64, DL,
                                     DAG.getVTList(MVT::i32, MVT::i32), Val);
      SDValue Lo = SplitF64.getValue(0);
      SDValue Hi = SplitF64.getValue(1);
      Register RegLo = VA.getLocReg();
      assert(RegLo < RISCV::X31 && "Invalid register pair");
      Register RegHi = RegLo + 1;

      if (STI.isRegisterReservedByUser(RegLo) ||
          STI.isRegisterReservedByUser(RegHi))
        MF.getFunction().getContext().diagnose(DiagnosticInfoUnsupported{
            MF.getFunction(),
            "Return value register required, but has been reserved."});

      Chain = DAG.getCopyToReg(Chain, DL, RegLo, Lo, Glue);
      Glue = Chain.getValue(1);
      RetOps.push_back(DAG.getRegister(RegLo, MVT::i32));
      Chain = DAG.getCopyToReg(Chain, DL, RegHi, Hi, Glue);
      Glue = Chain.getValue(1);
      RetOps.push_back(DAG.getRegister(RegHi, MVT::i32));
    } else {
      // Handle a 'normal' return.
      Val = convertValVTToLocVT(DAG, Val, VA, DL);
      Chain = DAG.getCopyToReg(Chain, DL, VA.getLocReg(), Val, Glue);

      if (STI.isRegisterReservedByUser(VA.getLocReg()))
        MF.getFunction().getContext().diagnose(DiagnosticInfoUnsupported{
            MF.getFunction(),
            "Return value register required, but has been reserved."});

      // Guarantee that all emitted copies are stuck together.
      Glue = Chain.getValue(1);
      RetOps.push_back(DAG.getRegister(VA.getLocReg(), VA.getLocVT()));
    }
  }

  RetOps[0] = Chain; // Update chain.

  // Add the glue node if we have it.
  if (Glue.getNode()) {
    RetOps.push_back(Glue);
  }

  // Interrupt service routines use different return instructions.
  const Function &Func = DAG.getMachineFunction().getFunction();
  if (Func.hasFnAttribute("interrupt")) {
    if (!Func.getReturnType()->isVoidTy())
      report_fatal_error(
          "Functions with the interrupt attribute must have void return type!");

    MachineFunction &MF = DAG.getMachineFunction();
    StringRef Kind =
      MF.getFunction().getFnAttribute("interrupt").getValueAsString();

    unsigned RetOpc;
    if (Kind == "user")
      RetOpc = RISCVISD::URET_FLAG;
    else if (Kind == "supervisor")
      RetOpc = RISCVISD::SRET_FLAG;
    else
      RetOpc = RISCVISD::MRET_FLAG;

    return DAG.getNode(RetOpc, DL, MVT::Other, RetOps);
  }

  return DAG.getNode(RISCVISD::RET_FLAG, DL, MVT::Other, RetOps);
}

void RISCVTargetLowering::validateCCReservedRegs(
    const SmallVectorImpl<std::pair<llvm::Register, llvm::SDValue>> &Regs,
    MachineFunction &MF) const {
  const Function &F = MF.getFunction();
  const RISCVSubtarget &STI = MF.getSubtarget<RISCVSubtarget>();

  if (std::any_of(std::begin(Regs), std::end(Regs), [&STI](auto Reg) {
        return STI.isRegisterReservedByUser(Reg.first);
      }))
    F.getContext().diagnose(DiagnosticInfoUnsupported{
        F, "Argument register required, but has been reserved."});
}

const char *RISCVTargetLowering::getTargetNodeName(unsigned Opcode) const {
  switch ((RISCVISD::NodeType)Opcode) {
  case RISCVISD::FIRST_NUMBER:
    break;
  case RISCVISD::RET_FLAG:
    return "RISCVISD::RET_FLAG";
  case RISCVISD::URET_FLAG:
    return "RISCVISD::URET_FLAG";
  case RISCVISD::SRET_FLAG:
    return "RISCVISD::SRET_FLAG";
  case RISCVISD::MRET_FLAG:
    return "RISCVISD::MRET_FLAG";
  case RISCVISD::CALL:
    return "RISCVISD::CALL";
  case RISCVISD::SELECT_CC:
    return "RISCVISD::SELECT_CC";
  case RISCVISD::BuildPairF64:
    return "RISCVISD::BuildPairF64";
  case RISCVISD::SplitF64:
    return "RISCVISD::SplitF64";
  case RISCVISD::TAIL:
    return "RISCVISD::TAIL";
  case RISCVISD::SLLW:
    return "RISCVISD::SLLW";
  case RISCVISD::SRAW:
    return "RISCVISD::SRAW";
  case RISCVISD::SRLW:
    return "RISCVISD::SRLW";
  case RISCVISD::DIVW:
    return "RISCVISD::DIVW";
  case RISCVISD::DIVUW:
    return "RISCVISD::DIVUW";
  case RISCVISD::REMUW:
    return "RISCVISD::REMUW";
  case RISCVISD::FMV_W_X_RV64:
    return "RISCVISD::FMV_W_X_RV64";
  case RISCVISD::FMV_X_ANYEXTW_RV64:
    return "RISCVISD::FMV_X_ANYEXTW_RV64";
  case RISCVISD::READ_CYCLE_WIDE:
    return "RISCVISD::READ_CYCLE_WIDE";
  }
  return nullptr;
}

/// getConstraintType - Given a constraint letter, return the type of
/// constraint it is for this target.
RISCVTargetLowering::ConstraintType
RISCVTargetLowering::getConstraintType(StringRef Constraint) const {
  if (Constraint.size() == 1) {
    switch (Constraint[0]) {
    default:
      break;
    case 'f':
      return C_RegisterClass;
    case 'I':
    case 'J':
    case 'K':
      return C_Immediate;
    case 'A':
      return C_Memory;
    }
  }
  return TargetLowering::getConstraintType(Constraint);
}

std::pair<unsigned, const TargetRegisterClass *>
RISCVTargetLowering::getRegForInlineAsmConstraint(const TargetRegisterInfo *TRI,
                                                  StringRef Constraint,
                                                  MVT VT) const {
  // First, see if this is a constraint that directly corresponds to a
  // RISCV register class.
  if (Constraint.size() == 1) {
    switch (Constraint[0]) {
    case 'r':
      return std::make_pair(0U, &RISCV::GPRRegClass);
    case 'f':
      if (Subtarget.hasStdExtF() && VT == MVT::f32)
        return std::make_pair(0U, &RISCV::FPR32RegClass);
      if (Subtarget.hasStdExtD() && VT == MVT::f64)
        return std::make_pair(0U, &RISCV::FPR64RegClass);
      break;
    default:
      break;
    }
  }

  // Clang will correctly decode the usage of register name aliases into their
  // official names. However, other frontends like `rustc` do not. This allows
  // users of these frontends to use the ABI names for registers in LLVM-style
  // register constraints.
  Register XRegFromAlias = StringSwitch<Register>(Constraint.lower())
                               .Case("{zero}", RISCV::X0)
                               .Case("{ra}", RISCV::X1)
                               .Case("{sp}", RISCV::X2)
                               .Case("{gp}", RISCV::X3)
                               .Case("{tp}", RISCV::X4)
                               .Case("{t0}", RISCV::X5)
                               .Case("{t1}", RISCV::X6)
                               .Case("{t2}", RISCV::X7)
                               .Cases("{s0}", "{fp}", RISCV::X8)
                               .Case("{s1}", RISCV::X9)
                               .Case("{a0}", RISCV::X10)
                               .Case("{a1}", RISCV::X11)
                               .Case("{a2}", RISCV::X12)
                               .Case("{a3}", RISCV::X13)
                               .Case("{a4}", RISCV::X14)
                               .Case("{a5}", RISCV::X15)
                               .Case("{a6}", RISCV::X16)
                               .Case("{a7}", RISCV::X17)
                               .Case("{s2}", RISCV::X18)
                               .Case("{s3}", RISCV::X19)
                               .Case("{s4}", RISCV::X20)
                               .Case("{s5}", RISCV::X21)
                               .Case("{s6}", RISCV::X22)
                               .Case("{s7}", RISCV::X23)
                               .Case("{s8}", RISCV::X24)
                               .Case("{s9}", RISCV::X25)
                               .Case("{s10}", RISCV::X26)
                               .Case("{s11}", RISCV::X27)
                               .Case("{t3}", RISCV::X28)
                               .Case("{t4}", RISCV::X29)
                               .Case("{t5}", RISCV::X30)
                               .Case("{t6}", RISCV::X31)
                               .Default(RISCV::NoRegister);
  if (XRegFromAlias != RISCV::NoRegister)
    return std::make_pair(XRegFromAlias, &RISCV::GPRRegClass);

  // Since TargetLowering::getRegForInlineAsmConstraint uses the name of the
  // TableGen record rather than the AsmName to choose registers for InlineAsm
  // constraints, plus we want to match those names to the widest floating point
  // register type available, manually select floating point registers here.
  //
  // The second case is the ABI name of the register, so that frontends can also
  // use the ABI names in register constraint lists.
  if (Subtarget.hasStdExtF() || Subtarget.hasStdExtD()) {
    std::pair<Register, Register> FReg =
        StringSwitch<std::pair<Register, Register>>(Constraint.lower())
            .Cases("{f0}", "{ft0}", {RISCV::F0_F, RISCV::F0_D})
            .Cases("{f1}", "{ft1}", {RISCV::F1_F, RISCV::F1_D})
            .Cases("{f2}", "{ft2}", {RISCV::F2_F, RISCV::F2_D})
            .Cases("{f3}", "{ft3}", {RISCV::F3_F, RISCV::F3_D})
            .Cases("{f4}", "{ft4}", {RISCV::F4_F, RISCV::F4_D})
            .Cases("{f5}", "{ft5}", {RISCV::F5_F, RISCV::F5_D})
            .Cases("{f6}", "{ft6}", {RISCV::F6_F, RISCV::F6_D})
            .Cases("{f7}", "{ft7}", {RISCV::F7_F, RISCV::F7_D})
            .Cases("{f8}", "{fs0}", {RISCV::F8_F, RISCV::F8_D})
            .Cases("{f9}", "{fs1}", {RISCV::F9_F, RISCV::F9_D})
            .Cases("{f10}", "{fa0}", {RISCV::F10_F, RISCV::F10_D})
            .Cases("{f11}", "{fa1}", {RISCV::F11_F, RISCV::F11_D})
            .Cases("{f12}", "{fa2}", {RISCV::F12_F, RISCV::F12_D})
            .Cases("{f13}", "{fa3}", {RISCV::F13_F, RISCV::F13_D})
            .Cases("{f14}", "{fa4}", {RISCV::F14_F, RISCV::F14_D})
            .Cases("{f15}", "{fa5}", {RISCV::F15_F, RISCV::F15_D})
            .Cases("{f16}", "{fa6}", {RISCV::F16_F, RISCV::F16_D})
            .Cases("{f17}", "{fa7}", {RISCV::F17_F, RISCV::F17_D})
            .Cases("{f18}", "{fs2}", {RISCV::F18_F, RISCV::F18_D})
            .Cases("{f19}", "{fs3}", {RISCV::F19_F, RISCV::F19_D})
            .Cases("{f20}", "{fs4}", {RISCV::F20_F, RISCV::F20_D})
            .Cases("{f21}", "{fs5}", {RISCV::F21_F, RISCV::F21_D})
            .Cases("{f22}", "{fs6}", {RISCV::F22_F, RISCV::F22_D})
            .Cases("{f23}", "{fs7}", {RISCV::F23_F, RISCV::F23_D})
            .Cases("{f24}", "{fs8}", {RISCV::F24_F, RISCV::F24_D})
            .Cases("{f25}", "{fs9}", {RISCV::F25_F, RISCV::F25_D})
            .Cases("{f26}", "{fs10}", {RISCV::F26_F, RISCV::F26_D})
            .Cases("{f27}", "{fs11}", {RISCV::F27_F, RISCV::F27_D})
            .Cases("{f28}", "{ft8}", {RISCV::F28_F, RISCV::F28_D})
            .Cases("{f29}", "{ft9}", {RISCV::F29_F, RISCV::F29_D})
            .Cases("{f30}", "{ft10}", {RISCV::F30_F, RISCV::F30_D})
            .Cases("{f31}", "{ft11}", {RISCV::F31_F, RISCV::F31_D})
            .Default({RISCV::NoRegister, RISCV::NoRegister});
    if (FReg.first != RISCV::NoRegister)
      return Subtarget.hasStdExtD()
                 ? std::make_pair(FReg.second, &RISCV::FPR64RegClass)
                 : std::make_pair(FReg.first, &RISCV::FPR32RegClass);
  }

  return TargetLowering::getRegForInlineAsmConstraint(TRI, Constraint, VT);
}

unsigned
RISCVTargetLowering::getInlineAsmMemConstraint(StringRef ConstraintCode) const {
  // Currently only support length 1 constraints.
  if (ConstraintCode.size() == 1) {
    switch (ConstraintCode[0]) {
    case 'A':
      return InlineAsm::Constraint_A;
    default:
      break;
    }
  }

  return TargetLowering::getInlineAsmMemConstraint(ConstraintCode);
}

void RISCVTargetLowering::LowerAsmOperandForConstraint(
    SDValue Op, std::string &Constraint, std::vector<SDValue> &Ops,
    SelectionDAG &DAG) const {
  // Currently only support length 1 constraints.
  if (Constraint.length() == 1) {
    switch (Constraint[0]) {
    case 'I':
      // Validate & create a 12-bit signed immediate operand.
      if (auto *C = dyn_cast<ConstantSDNode>(Op)) {
        uint64_t CVal = C->getSExtValue();
        if (isInt<12>(CVal))
          Ops.push_back(
              DAG.getTargetConstant(CVal, SDLoc(Op), Subtarget.getXLenVT()));
      }
      return;
    case 'J':
      // Validate & create an integer zero operand.
      if (auto *C = dyn_cast<ConstantSDNode>(Op))
        if (C->getZExtValue() == 0)
          Ops.push_back(
              DAG.getTargetConstant(0, SDLoc(Op), Subtarget.getXLenVT()));
      return;
    case 'K':
      // Validate & create a 5-bit unsigned immediate operand.
      if (auto *C = dyn_cast<ConstantSDNode>(Op)) {
        uint64_t CVal = C->getZExtValue();
        if (isUInt<5>(CVal))
          Ops.push_back(
              DAG.getTargetConstant(CVal, SDLoc(Op), Subtarget.getXLenVT()));
      }
      return;
    default:
      break;
    }
  }
  TargetLowering::LowerAsmOperandForConstraint(Op, Constraint, Ops, DAG);
}

Instruction *RISCVTargetLowering::emitLeadingFence(IRBuilder<> &Builder,
                                                   Instruction *Inst,
                                                   AtomicOrdering Ord) const {
  if (isa<LoadInst>(Inst) && Ord == AtomicOrdering::SequentiallyConsistent)
    return Builder.CreateFence(Ord);
  if (isa<StoreInst>(Inst) && isReleaseOrStronger(Ord))
    return Builder.CreateFence(AtomicOrdering::Release);
  return nullptr;
}

Instruction *RISCVTargetLowering::emitTrailingFence(IRBuilder<> &Builder,
                                                    Instruction *Inst,
                                                    AtomicOrdering Ord) const {
  if (isa<LoadInst>(Inst) && isAcquireOrStronger(Ord))
    return Builder.CreateFence(AtomicOrdering::Acquire);
  return nullptr;
}

TargetLowering::AtomicExpansionKind
RISCVTargetLowering::shouldExpandAtomicRMWInIR(AtomicRMWInst *AI) const {
  // atomicrmw {fadd,fsub} must be expanded to use compare-exchange, as floating
  // point operations can't be used in an lr/sc sequence without breaking the
  // forward-progress guarantee.
  if (AI->isFloatingPointOperation())
    return AtomicExpansionKind::CmpXChg;

  unsigned Size = AI->getType()->getPrimitiveSizeInBits();
  if (Size == 8 || Size == 16)
    return AtomicExpansionKind::MaskedIntrinsic;
  return AtomicExpansionKind::None;
}

static Intrinsic::ID
getIntrinsicForMaskedAtomicRMWBinOp(unsigned XLen, AtomicRMWInst::BinOp BinOp) {
  if (XLen == 32) {
    switch (BinOp) {
    default:
      llvm_unreachable("Unexpected AtomicRMW BinOp");
    case AtomicRMWInst::Xchg:
      return Intrinsic::riscv_masked_atomicrmw_xchg_i32;
    case AtomicRMWInst::Add:
      return Intrinsic::riscv_masked_atomicrmw_add_i32;
    case AtomicRMWInst::Sub:
      return Intrinsic::riscv_masked_atomicrmw_sub_i32;
    case AtomicRMWInst::Nand:
      return Intrinsic::riscv_masked_atomicrmw_nand_i32;
    case AtomicRMWInst::Max:
      return Intrinsic::riscv_masked_atomicrmw_max_i32;
    case AtomicRMWInst::Min:
      return Intrinsic::riscv_masked_atomicrmw_min_i32;
    case AtomicRMWInst::UMax:
      return Intrinsic::riscv_masked_atomicrmw_umax_i32;
    case AtomicRMWInst::UMin:
      return Intrinsic::riscv_masked_atomicrmw_umin_i32;
    }
  }

  if (XLen == 64) {
    switch (BinOp) {
    default:
      llvm_unreachable("Unexpected AtomicRMW BinOp");
    case AtomicRMWInst::Xchg:
      return Intrinsic::riscv_masked_atomicrmw_xchg_i64;
    case AtomicRMWInst::Add:
      return Intrinsic::riscv_masked_atomicrmw_add_i64;
    case AtomicRMWInst::Sub:
      return Intrinsic::riscv_masked_atomicrmw_sub_i64;
    case AtomicRMWInst::Nand:
      return Intrinsic::riscv_masked_atomicrmw_nand_i64;
    case AtomicRMWInst::Max:
      return Intrinsic::riscv_masked_atomicrmw_max_i64;
    case AtomicRMWInst::Min:
      return Intrinsic::riscv_masked_atomicrmw_min_i64;
    case AtomicRMWInst::UMax:
      return Intrinsic::riscv_masked_atomicrmw_umax_i64;
    case AtomicRMWInst::UMin:
      return Intrinsic::riscv_masked_atomicrmw_umin_i64;
    }
  }

  llvm_unreachable("Unexpected XLen\n");
}

Value *RISCVTargetLowering::emitMaskedAtomicRMWIntrinsic(
    IRBuilder<> &Builder, AtomicRMWInst *AI, Value *AlignedAddr, Value *Incr,
    Value *Mask, Value *ShiftAmt, AtomicOrdering Ord) const {
  unsigned XLen = Subtarget.getXLen();
  Value *Ordering =
      Builder.getIntN(XLen, static_cast<uint64_t>(AI->getOrdering()));
  Type *Tys[] = {AlignedAddr->getType()};
  Function *LrwOpScwLoop = Intrinsic::getDeclaration(
      AI->getModule(),
      getIntrinsicForMaskedAtomicRMWBinOp(XLen, AI->getOperation()), Tys);

  if (XLen == 64) {
    Incr = Builder.CreateSExt(Incr, Builder.getInt64Ty());
    Mask = Builder.CreateSExt(Mask, Builder.getInt64Ty());
    ShiftAmt = Builder.CreateSExt(ShiftAmt, Builder.getInt64Ty());
  }

  Value *Result;

  // Must pass the shift amount needed to sign extend the loaded value prior
  // to performing a signed comparison for min/max. ShiftAmt is the number of
  // bits to shift the value into position. Pass XLen-ShiftAmt-ValWidth, which
  // is the number of bits to left+right shift the value in order to
  // sign-extend.
  if (AI->getOperation() == AtomicRMWInst::Min ||
      AI->getOperation() == AtomicRMWInst::Max) {
    const DataLayout &DL = AI->getModule()->getDataLayout();
    unsigned ValWidth =
        DL.getTypeStoreSizeInBits(AI->getValOperand()->getType());
    Value *SextShamt =
        Builder.CreateSub(Builder.getIntN(XLen, XLen - ValWidth), ShiftAmt);
    Result = Builder.CreateCall(LrwOpScwLoop,
                                {AlignedAddr, Incr, Mask, SextShamt, Ordering});
  } else {
    Result =
        Builder.CreateCall(LrwOpScwLoop, {AlignedAddr, Incr, Mask, Ordering});
  }

  if (XLen == 64)
    Result = Builder.CreateTrunc(Result, Builder.getInt32Ty());
  return Result;
}

TargetLowering::AtomicExpansionKind
RISCVTargetLowering::shouldExpandAtomicCmpXchgInIR(
    AtomicCmpXchgInst *CI) const {
  unsigned Size = CI->getCompareOperand()->getType()->getPrimitiveSizeInBits();
  if (Size == 8 || Size == 16)
    return AtomicExpansionKind::MaskedIntrinsic;
  return AtomicExpansionKind::None;
}

Value *RISCVTargetLowering::emitMaskedAtomicCmpXchgIntrinsic(
    IRBuilder<> &Builder, AtomicCmpXchgInst *CI, Value *AlignedAddr,
    Value *CmpVal, Value *NewVal, Value *Mask, AtomicOrdering Ord) const {
  unsigned XLen = Subtarget.getXLen();
  Value *Ordering = Builder.getIntN(XLen, static_cast<uint64_t>(Ord));
  Intrinsic::ID CmpXchgIntrID = Intrinsic::riscv_masked_cmpxchg_i32;
  if (XLen == 64) {
    CmpVal = Builder.CreateSExt(CmpVal, Builder.getInt64Ty());
    NewVal = Builder.CreateSExt(NewVal, Builder.getInt64Ty());
    Mask = Builder.CreateSExt(Mask, Builder.getInt64Ty());
    CmpXchgIntrID = Intrinsic::riscv_masked_cmpxchg_i64;
  }
  Type *Tys[] = {AlignedAddr->getType()};
  Function *MaskedCmpXchg =
      Intrinsic::getDeclaration(CI->getModule(), CmpXchgIntrID, Tys);
  Value *Result = Builder.CreateCall(
      MaskedCmpXchg, {AlignedAddr, CmpVal, NewVal, Mask, Ordering});
  if (XLen == 64)
    Result = Builder.CreateTrunc(Result, Builder.getInt32Ty());
  return Result;
}

unsigned RISCVTargetLowering::getExceptionPointerRegister(
    const Constant *PersonalityFn) const {
  return RISCV::X10;
}

unsigned RISCVTargetLowering::getExceptionSelectorRegister(
    const Constant *PersonalityFn) const {
  return RISCV::X11;
}

bool RISCVTargetLowering::shouldExtendTypeInLibCall(EVT Type) const {
  // Return false to suppress the unnecessary extensions if the LibCall
  // arguments or return value is f32 type for LP64 ABI.
  RISCVABI::ABI ABI = Subtarget.getTargetABI();
  if (ABI == RISCVABI::ABI_LP64 && (Type == MVT::f32))
    return false;

  return true;
}

#define GET_REGISTER_MATCHER
#include "RISCVGenAsmMatcher.inc"

Register
RISCVTargetLowering::getRegisterByName(const char *RegName, LLT VT,
                                       const MachineFunction &MF) const {
  Register Reg = MatchRegisterAltName(RegName);
  if (Reg == RISCV::NoRegister)
    Reg = MatchRegisterName(RegName);
  if (Reg == RISCV::NoRegister)
    report_fatal_error(
        Twine("Invalid register name \"" + StringRef(RegName) + "\"."));
  BitVector ReservedRegs = Subtarget.getRegisterInfo()->getReservedRegs(MF);
  if (!ReservedRegs.test(Reg) && !Subtarget.isRegisterReservedByUser(Reg))
    report_fatal_error(Twine("Trying to obtain non-reserved register \"" +
                             StringRef(RegName) + "\"."));
  return Reg;
}