aboutsummaryrefslogtreecommitdiffstats
path: root/lib/Target/Mips/MipsISelLowering.cpp
blob: eb0e8aefabaf5696734a0bfe7ff07cce527d7d1c (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
//===-- MipsISelLowering.cpp - Mips DAG Lowering Implementation -----------===//
//
//                     The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// This file defines the interfaces that Mips uses to lower LLVM code into a
// selection DAG.
//
//===----------------------------------------------------------------------===//

#define DEBUG_TYPE "mips-lower"
#include "MipsISelLowering.h"
#include "MipsMachineFunction.h"
#include "MipsTargetMachine.h"
#include "MipsTargetObjectFile.h"
#include "MipsSubtarget.h"
#include "InstPrinter/MipsInstPrinter.h"
#include "MCTargetDesc/MipsBaseInfo.h"
#include "llvm/DerivedTypes.h"
#include "llvm/Function.h"
#include "llvm/GlobalVariable.h"
#include "llvm/Intrinsics.h"
#include "llvm/CallingConv.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/ValueTypes.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/ErrorHandling.h"
using namespace llvm;

// If I is a shifted mask, set the size (Size) and the first bit of the
// mask (Pos), and return true.
// For example, if I is 0x003ff800, (Pos, Size) = (11, 11).
static bool IsShiftedMask(uint64_t I, uint64_t &Pos, uint64_t &Size) {
  if (!isShiftedMask_64(I))
     return false;

  Size = CountPopulation_64(I);
  Pos = CountTrailingZeros_64(I);
  return true;
}

static SDValue GetGlobalReg(SelectionDAG &DAG, EVT Ty) {
  MipsFunctionInfo *FI = DAG.getMachineFunction().getInfo<MipsFunctionInfo>();
  return DAG.getRegister(FI->getGlobalBaseReg(), Ty);
}

const char *MipsTargetLowering::getTargetNodeName(unsigned Opcode) const {
  switch (Opcode) {
  case MipsISD::JmpLink:           return "MipsISD::JmpLink";
  case MipsISD::Hi:                return "MipsISD::Hi";
  case MipsISD::Lo:                return "MipsISD::Lo";
  case MipsISD::GPRel:             return "MipsISD::GPRel";
  case MipsISD::ThreadPointer:     return "MipsISD::ThreadPointer";
  case MipsISD::Ret:               return "MipsISD::Ret";
  case MipsISD::FPBrcond:          return "MipsISD::FPBrcond";
  case MipsISD::FPCmp:             return "MipsISD::FPCmp";
  case MipsISD::CMovFP_T:          return "MipsISD::CMovFP_T";
  case MipsISD::CMovFP_F:          return "MipsISD::CMovFP_F";
  case MipsISD::FPRound:           return "MipsISD::FPRound";
  case MipsISD::MAdd:              return "MipsISD::MAdd";
  case MipsISD::MAddu:             return "MipsISD::MAddu";
  case MipsISD::MSub:              return "MipsISD::MSub";
  case MipsISD::MSubu:             return "MipsISD::MSubu";
  case MipsISD::DivRem:            return "MipsISD::DivRem";
  case MipsISD::DivRemU:           return "MipsISD::DivRemU";
  case MipsISD::BuildPairF64:      return "MipsISD::BuildPairF64";
  case MipsISD::ExtractElementF64: return "MipsISD::ExtractElementF64";
  case MipsISD::Wrapper:           return "MipsISD::Wrapper";
  case MipsISD::DynAlloc:          return "MipsISD::DynAlloc";
  case MipsISD::Sync:              return "MipsISD::Sync";
  case MipsISD::Ext:               return "MipsISD::Ext";
  case MipsISD::Ins:               return "MipsISD::Ins";
  default:                         return NULL;
  }
}

MipsTargetLowering::
MipsTargetLowering(MipsTargetMachine &TM)
  : TargetLowering(TM, new MipsTargetObjectFile()),
    Subtarget(&TM.getSubtarget<MipsSubtarget>()),
    HasMips64(Subtarget->hasMips64()), IsN64(Subtarget->isABI_N64()),
    IsO32(Subtarget->isABI_O32()) {

  // Mips does not have i1 type, so use i32 for
  // setcc operations results (slt, sgt, ...).
  setBooleanContents(ZeroOrOneBooleanContent);
  setBooleanVectorContents(ZeroOrOneBooleanContent); // FIXME: Is this correct?

  // Set up the register classes
  addRegisterClass(MVT::i32, Mips::CPURegsRegisterClass);

  if (HasMips64)
    addRegisterClass(MVT::i64, Mips::CPU64RegsRegisterClass);

  if (!TM.Options.UseSoftFloat) {
    addRegisterClass(MVT::f32, Mips::FGR32RegisterClass);

    // When dealing with single precision only, use libcalls
    if (!Subtarget->isSingleFloat()) {
      if (HasMips64)
        addRegisterClass(MVT::f64, Mips::FGR64RegisterClass);
      else
        addRegisterClass(MVT::f64, Mips::AFGR64RegisterClass);
    }
  }

  // Load extented operations for i1 types must be promoted
  setLoadExtAction(ISD::EXTLOAD,  MVT::i1,  Promote);
  setLoadExtAction(ISD::ZEXTLOAD, MVT::i1,  Promote);
  setLoadExtAction(ISD::SEXTLOAD, MVT::i1,  Promote);

  // MIPS doesn't have extending float->double load/store
  setLoadExtAction(ISD::EXTLOAD, MVT::f32, Expand);
  setTruncStoreAction(MVT::f64, MVT::f32, Expand);

  // Used by legalize types to correctly generate the setcc result.
  // Without this, every float setcc comes with a AND/OR with the result,
  // we don't want this, since the fpcmp result goes to a flag register,
  // which is used implicitly by brcond and select operations.
  AddPromotedToType(ISD::SETCC, MVT::i1, MVT::i32);

  // Mips Custom Operations
  setOperationAction(ISD::GlobalAddress,      MVT::i32,   Custom);
  setOperationAction(ISD::BlockAddress,       MVT::i32,   Custom);
  setOperationAction(ISD::GlobalTLSAddress,   MVT::i32,   Custom);
  setOperationAction(ISD::JumpTable,          MVT::i32,   Custom);
  setOperationAction(ISD::ConstantPool,       MVT::i32,   Custom);
  setOperationAction(ISD::SELECT,             MVT::f32,   Custom);
  setOperationAction(ISD::SELECT,             MVT::f64,   Custom);
  setOperationAction(ISD::SELECT,             MVT::i32,   Custom);
  setOperationAction(ISD::SETCC,              MVT::f32,   Custom);
  setOperationAction(ISD::SETCC,              MVT::f64,   Custom);
  setOperationAction(ISD::BRCOND,             MVT::Other, Custom);
  setOperationAction(ISD::DYNAMIC_STACKALLOC, MVT::i32,   Custom);
  setOperationAction(ISD::VASTART,            MVT::Other, Custom);
  setOperationAction(ISD::FCOPYSIGN,          MVT::f32,   Custom);
  setOperationAction(ISD::FCOPYSIGN,          MVT::f64,   Custom);
  setOperationAction(ISD::MEMBARRIER,         MVT::Other, Custom);
  setOperationAction(ISD::ATOMIC_FENCE,       MVT::Other, Custom);

  if (HasMips64) {
    setOperationAction(ISD::GlobalAddress,      MVT::i64,   Custom);
    setOperationAction(ISD::BlockAddress,       MVT::i64,   Custom);
    setOperationAction(ISD::GlobalTLSAddress,   MVT::i64,   Custom);
    setOperationAction(ISD::JumpTable,          MVT::i64,   Custom);
    setOperationAction(ISD::ConstantPool,       MVT::i64,   Custom);
    setOperationAction(ISD::SELECT,             MVT::i64,   Custom);
    setOperationAction(ISD::DYNAMIC_STACKALLOC, MVT::i64,   Custom);
  }

  setOperationAction(ISD::SDIV, MVT::i32, Expand);
  setOperationAction(ISD::SREM, MVT::i32, Expand);
  setOperationAction(ISD::UDIV, MVT::i32, Expand);
  setOperationAction(ISD::UREM, MVT::i32, Expand);
  setOperationAction(ISD::SDIV, MVT::i64, Expand);
  setOperationAction(ISD::SREM, MVT::i64, Expand);
  setOperationAction(ISD::UDIV, MVT::i64, Expand);
  setOperationAction(ISD::UREM, MVT::i64, Expand);

  // Operations not directly supported by Mips.
  setOperationAction(ISD::BR_JT,             MVT::Other, Expand);
  setOperationAction(ISD::BR_CC,             MVT::Other, Expand);
  setOperationAction(ISD::SELECT_CC,         MVT::Other, Expand);
  setOperationAction(ISD::UINT_TO_FP,        MVT::i32,   Expand);
  setOperationAction(ISD::UINT_TO_FP,        MVT::i64,   Expand);
  setOperationAction(ISD::FP_TO_UINT,        MVT::i32,   Expand);
  setOperationAction(ISD::FP_TO_UINT,        MVT::i64,   Expand);
  setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::i1,    Expand);
  setOperationAction(ISD::CTPOP,             MVT::i32,   Expand);
  setOperationAction(ISD::CTPOP,             MVT::i64,   Expand);
  setOperationAction(ISD::CTTZ,              MVT::i32,   Expand);
  setOperationAction(ISD::CTTZ,              MVT::i64,   Expand);
  setOperationAction(ISD::CTTZ_ZERO_UNDEF,   MVT::i32,   Expand);
  setOperationAction(ISD::CTTZ_ZERO_UNDEF,   MVT::i64,   Expand);
  setOperationAction(ISD::CTLZ_ZERO_UNDEF,   MVT::i32,   Expand);
  setOperationAction(ISD::CTLZ_ZERO_UNDEF,   MVT::i64,   Expand);
  setOperationAction(ISD::ROTL,              MVT::i32,   Expand);
  setOperationAction(ISD::ROTL,              MVT::i64,   Expand);

  if (!Subtarget->hasMips32r2())
    setOperationAction(ISD::ROTR, MVT::i32,   Expand);

  if (!Subtarget->hasMips64r2())
    setOperationAction(ISD::ROTR, MVT::i64,   Expand);

  setOperationAction(ISD::SHL_PARTS,         MVT::i32,   Expand);
  setOperationAction(ISD::SRA_PARTS,         MVT::i32,   Expand);
  setOperationAction(ISD::SRL_PARTS,         MVT::i32,   Expand);
  setOperationAction(ISD::FSIN,              MVT::f32,   Expand);
  setOperationAction(ISD::FSIN,              MVT::f64,   Expand);
  setOperationAction(ISD::FCOS,              MVT::f32,   Expand);
  setOperationAction(ISD::FCOS,              MVT::f64,   Expand);
  setOperationAction(ISD::FPOWI,             MVT::f32,   Expand);
  setOperationAction(ISD::FPOW,              MVT::f32,   Expand);
  setOperationAction(ISD::FPOW,              MVT::f64,   Expand);
  setOperationAction(ISD::FLOG,              MVT::f32,   Expand);
  setOperationAction(ISD::FLOG2,             MVT::f32,   Expand);
  setOperationAction(ISD::FLOG10,            MVT::f32,   Expand);
  setOperationAction(ISD::FEXP,              MVT::f32,   Expand);
  setOperationAction(ISD::FMA,               MVT::f32,   Expand);
  setOperationAction(ISD::FMA,               MVT::f64,   Expand);

  setOperationAction(ISD::EXCEPTIONADDR,     MVT::i32, Expand);
  setOperationAction(ISD::EXCEPTIONADDR,     MVT::i64, Expand);
  setOperationAction(ISD::EHSELECTION,       MVT::i32, Expand);
  setOperationAction(ISD::EHSELECTION,       MVT::i64, Expand);

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

  // Use the default for now
  setOperationAction(ISD::STACKSAVE,         MVT::Other, Expand);
  setOperationAction(ISD::STACKRESTORE,      MVT::Other, Expand);

  setOperationAction(ISD::ATOMIC_LOAD,       MVT::i32,    Expand);
  setOperationAction(ISD::ATOMIC_LOAD,       MVT::i64,    Expand);
  setOperationAction(ISD::ATOMIC_STORE,      MVT::i32,    Expand);
  setOperationAction(ISD::ATOMIC_STORE,      MVT::i64,    Expand);

  setInsertFencesForAtomic(true);

  if (Subtarget->isSingleFloat())
    setOperationAction(ISD::SELECT_CC, MVT::f64, Expand);

  if (!Subtarget->hasSEInReg()) {
    setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::i8,  Expand);
    setOperationAction(ISD::SIGN_EXTEND_INREG, MVT::i16, Expand);
  }

  if (!Subtarget->hasBitCount()) {
    setOperationAction(ISD::CTLZ, MVT::i32, Expand);
    setOperationAction(ISD::CTLZ, MVT::i64, Expand);
  }

  if (!Subtarget->hasSwap()) {
    setOperationAction(ISD::BSWAP, MVT::i32, Expand);
    setOperationAction(ISD::BSWAP, MVT::i64, Expand);
  }

  setTargetDAGCombine(ISD::ADDE);
  setTargetDAGCombine(ISD::SUBE);
  setTargetDAGCombine(ISD::SDIVREM);
  setTargetDAGCombine(ISD::UDIVREM);
  setTargetDAGCombine(ISD::SELECT);
  setTargetDAGCombine(ISD::AND);
  setTargetDAGCombine(ISD::OR);

  setMinFunctionAlignment(HasMips64 ? 3 : 2);

  setStackPointerRegisterToSaveRestore(IsN64 ? Mips::SP_64 : Mips::SP);
  computeRegisterProperties();

  setExceptionPointerRegister(IsN64 ? Mips::A0_64 : Mips::A0);
  setExceptionSelectorRegister(IsN64 ? Mips::A1_64 : Mips::A1);
}

bool MipsTargetLowering::allowsUnalignedMemoryAccesses(EVT VT) const {
  MVT::SimpleValueType SVT = VT.getSimpleVT().SimpleTy;

  switch (SVT) {
  case MVT::i64:
  case MVT::i32:
  case MVT::i16:
    return true;
  case MVT::f32:
    return Subtarget->hasMips32r2Or64();
  default:
    return false;
  }
}

EVT MipsTargetLowering::getSetCCResultType(EVT VT) const {
  return MVT::i32;
}

// SelectMadd -
// Transforms a subgraph in CurDAG if the following pattern is found:
//  (addc multLo, Lo0), (adde multHi, Hi0),
// where,
//  multHi/Lo: product of multiplication
//  Lo0: initial value of Lo register
//  Hi0: initial value of Hi register
// Return true if pattern matching was successful.
static bool SelectMadd(SDNode* ADDENode, SelectionDAG* CurDAG) {
  // ADDENode's second operand must be a flag output of an ADDC node in order
  // for the matching to be successful.
  SDNode* ADDCNode = ADDENode->getOperand(2).getNode();

  if (ADDCNode->getOpcode() != ISD::ADDC)
    return false;

  SDValue MultHi = ADDENode->getOperand(0);
  SDValue MultLo = ADDCNode->getOperand(0);
  SDNode* MultNode = MultHi.getNode();
  unsigned MultOpc = MultHi.getOpcode();

  // MultHi and MultLo must be generated by the same node,
  if (MultLo.getNode() != MultNode)
    return false;

  // and it must be a multiplication.
  if (MultOpc != ISD::SMUL_LOHI && MultOpc != ISD::UMUL_LOHI)
    return false;

  // MultLo amd MultHi must be the first and second output of MultNode
  // respectively.
  if (MultHi.getResNo() != 1 || MultLo.getResNo() != 0)
    return false;

  // Transform this to a MADD only if ADDENode and ADDCNode are the only users
  // of the values of MultNode, in which case MultNode will be removed in later
  // phases.
  // If there exist users other than ADDENode or ADDCNode, this function returns
  // here, which will result in MultNode being mapped to a single MULT
  // instruction node rather than a pair of MULT and MADD instructions being
  // produced.
  if (!MultHi.hasOneUse() || !MultLo.hasOneUse())
    return false;

  SDValue Chain = CurDAG->getEntryNode();
  DebugLoc dl = ADDENode->getDebugLoc();

  // create MipsMAdd(u) node
  MultOpc = MultOpc == ISD::UMUL_LOHI ? MipsISD::MAddu : MipsISD::MAdd;

  SDValue MAdd = CurDAG->getNode(MultOpc, dl, MVT::Glue,
                                 MultNode->getOperand(0),// Factor 0
                                 MultNode->getOperand(1),// Factor 1
                                 ADDCNode->getOperand(1),// Lo0
                                 ADDENode->getOperand(1));// Hi0

  // create CopyFromReg nodes
  SDValue CopyFromLo = CurDAG->getCopyFromReg(Chain, dl, Mips::LO, MVT::i32,
                                              MAdd);
  SDValue CopyFromHi = CurDAG->getCopyFromReg(CopyFromLo.getValue(1), dl,
                                              Mips::HI, MVT::i32,
                                              CopyFromLo.getValue(2));

  // replace uses of adde and addc here
  if (!SDValue(ADDCNode, 0).use_empty())
    CurDAG->ReplaceAllUsesOfValueWith(SDValue(ADDCNode, 0), CopyFromLo);

  if (!SDValue(ADDENode, 0).use_empty())
    CurDAG->ReplaceAllUsesOfValueWith(SDValue(ADDENode, 0), CopyFromHi);

  return true;
}

// SelectMsub -
// Transforms a subgraph in CurDAG if the following pattern is found:
//  (addc Lo0, multLo), (sube Hi0, multHi),
// where,
//  multHi/Lo: product of multiplication
//  Lo0: initial value of Lo register
//  Hi0: initial value of Hi register
// Return true if pattern matching was successful.
static bool SelectMsub(SDNode* SUBENode, SelectionDAG* CurDAG) {
  // SUBENode's second operand must be a flag output of an SUBC node in order
  // for the matching to be successful.
  SDNode* SUBCNode = SUBENode->getOperand(2).getNode();

  if (SUBCNode->getOpcode() != ISD::SUBC)
    return false;

  SDValue MultHi = SUBENode->getOperand(1);
  SDValue MultLo = SUBCNode->getOperand(1);
  SDNode* MultNode = MultHi.getNode();
  unsigned MultOpc = MultHi.getOpcode();

  // MultHi and MultLo must be generated by the same node,
  if (MultLo.getNode() != MultNode)
    return false;

  // and it must be a multiplication.
  if (MultOpc != ISD::SMUL_LOHI && MultOpc != ISD::UMUL_LOHI)
    return false;

  // MultLo amd MultHi must be the first and second output of MultNode
  // respectively.
  if (MultHi.getResNo() != 1 || MultLo.getResNo() != 0)
    return false;

  // Transform this to a MSUB only if SUBENode and SUBCNode are the only users
  // of the values of MultNode, in which case MultNode will be removed in later
  // phases.
  // If there exist users other than SUBENode or SUBCNode, this function returns
  // here, which will result in MultNode being mapped to a single MULT
  // instruction node rather than a pair of MULT and MSUB instructions being
  // produced.
  if (!MultHi.hasOneUse() || !MultLo.hasOneUse())
    return false;

  SDValue Chain = CurDAG->getEntryNode();
  DebugLoc dl = SUBENode->getDebugLoc();

  // create MipsSub(u) node
  MultOpc = MultOpc == ISD::UMUL_LOHI ? MipsISD::MSubu : MipsISD::MSub;

  SDValue MSub = CurDAG->getNode(MultOpc, dl, MVT::Glue,
                                 MultNode->getOperand(0),// Factor 0
                                 MultNode->getOperand(1),// Factor 1
                                 SUBCNode->getOperand(0),// Lo0
                                 SUBENode->getOperand(0));// Hi0

  // create CopyFromReg nodes
  SDValue CopyFromLo = CurDAG->getCopyFromReg(Chain, dl, Mips::LO, MVT::i32,
                                              MSub);
  SDValue CopyFromHi = CurDAG->getCopyFromReg(CopyFromLo.getValue(1), dl,
                                              Mips::HI, MVT::i32,
                                              CopyFromLo.getValue(2));

  // replace uses of sube and subc here
  if (!SDValue(SUBCNode, 0).use_empty())
    CurDAG->ReplaceAllUsesOfValueWith(SDValue(SUBCNode, 0), CopyFromLo);

  if (!SDValue(SUBENode, 0).use_empty())
    CurDAG->ReplaceAllUsesOfValueWith(SDValue(SUBENode, 0), CopyFromHi);

  return true;
}

static SDValue PerformADDECombine(SDNode *N, SelectionDAG& DAG,
                                  TargetLowering::DAGCombinerInfo &DCI,
                                  const MipsSubtarget* Subtarget) {
  if (DCI.isBeforeLegalize())
    return SDValue();

  if (Subtarget->hasMips32() && N->getValueType(0) == MVT::i32 &&
      SelectMadd(N, &DAG))
    return SDValue(N, 0);

  return SDValue();
}

static SDValue PerformSUBECombine(SDNode *N, SelectionDAG& DAG,
                                  TargetLowering::DAGCombinerInfo &DCI,
                                  const MipsSubtarget* Subtarget) {
  if (DCI.isBeforeLegalize())
    return SDValue();

  if (Subtarget->hasMips32() && N->getValueType(0) == MVT::i32 &&
      SelectMsub(N, &DAG))
    return SDValue(N, 0);

  return SDValue();
}

static SDValue PerformDivRemCombine(SDNode *N, SelectionDAG& DAG,
                                    TargetLowering::DAGCombinerInfo &DCI,
                                    const MipsSubtarget* Subtarget) {
  if (DCI.isBeforeLegalizeOps())
    return SDValue();

  EVT Ty = N->getValueType(0);
  unsigned LO = (Ty == MVT::i32) ? Mips::LO : Mips::LO64;
  unsigned HI = (Ty == MVT::i32) ? Mips::HI : Mips::HI64;
  unsigned opc = N->getOpcode() == ISD::SDIVREM ? MipsISD::DivRem :
                                                  MipsISD::DivRemU;
  DebugLoc dl = N->getDebugLoc();

  SDValue DivRem = DAG.getNode(opc, dl, MVT::Glue,
                               N->getOperand(0), N->getOperand(1));
  SDValue InChain = DAG.getEntryNode();
  SDValue InGlue = DivRem;

  // insert MFLO
  if (N->hasAnyUseOfValue(0)) {
    SDValue CopyFromLo = DAG.getCopyFromReg(InChain, dl, LO, Ty,
                                            InGlue);
    DAG.ReplaceAllUsesOfValueWith(SDValue(N, 0), CopyFromLo);
    InChain = CopyFromLo.getValue(1);
    InGlue = CopyFromLo.getValue(2);
  }

  // insert MFHI
  if (N->hasAnyUseOfValue(1)) {
    SDValue CopyFromHi = DAG.getCopyFromReg(InChain, dl,
                                            HI, Ty, InGlue);
    DAG.ReplaceAllUsesOfValueWith(SDValue(N, 1), CopyFromHi);
  }

  return SDValue();
}

static Mips::CondCode FPCondCCodeToFCC(ISD::CondCode CC) {
  switch (CC) {
  default: llvm_unreachable("Unknown fp condition code!");
  case ISD::SETEQ:
  case ISD::SETOEQ: return Mips::FCOND_OEQ;
  case ISD::SETUNE: return Mips::FCOND_UNE;
  case ISD::SETLT:
  case ISD::SETOLT: return Mips::FCOND_OLT;
  case ISD::SETGT:
  case ISD::SETOGT: return Mips::FCOND_OGT;
  case ISD::SETLE:
  case ISD::SETOLE: return Mips::FCOND_OLE;
  case ISD::SETGE:
  case ISD::SETOGE: return Mips::FCOND_OGE;
  case ISD::SETULT: return Mips::FCOND_ULT;
  case ISD::SETULE: return Mips::FCOND_ULE;
  case ISD::SETUGT: return Mips::FCOND_UGT;
  case ISD::SETUGE: return Mips::FCOND_UGE;
  case ISD::SETUO:  return Mips::FCOND_UN;
  case ISD::SETO:   return Mips::FCOND_OR;
  case ISD::SETNE:
  case ISD::SETONE: return Mips::FCOND_ONE;
  case ISD::SETUEQ: return Mips::FCOND_UEQ;
  }
}


// Returns true if condition code has to be inverted.
static bool InvertFPCondCode(Mips::CondCode CC) {
  if (CC >= Mips::FCOND_F && CC <= Mips::FCOND_NGT)
    return false;

  assert((CC >= Mips::FCOND_T && CC <= Mips::FCOND_GT) &&
         "Illegal Condition Code");

  return true;
}

// Creates and returns an FPCmp node from a setcc node.
// Returns Op if setcc is not a floating point comparison.
static SDValue CreateFPCmp(SelectionDAG& DAG, const SDValue& Op) {
  // must be a SETCC node
  if (Op.getOpcode() != ISD::SETCC)
    return Op;

  SDValue LHS = Op.getOperand(0);

  if (!LHS.getValueType().isFloatingPoint())
    return Op;

  SDValue RHS = Op.getOperand(1);
  DebugLoc dl = Op.getDebugLoc();

  // Assume the 3rd operand is a CondCodeSDNode. Add code to check the type of
  // node if necessary.
  ISD::CondCode CC = cast<CondCodeSDNode>(Op.getOperand(2))->get();

  return DAG.getNode(MipsISD::FPCmp, dl, MVT::Glue, LHS, RHS,
                     DAG.getConstant(FPCondCCodeToFCC(CC), MVT::i32));
}

// Creates and returns a CMovFPT/F node.
static SDValue CreateCMovFP(SelectionDAG& DAG, SDValue Cond, SDValue True,
                            SDValue False, DebugLoc DL) {
  bool invert = InvertFPCondCode((Mips::CondCode)
                                 cast<ConstantSDNode>(Cond.getOperand(2))
                                 ->getSExtValue());

  return DAG.getNode((invert ? MipsISD::CMovFP_F : MipsISD::CMovFP_T), DL,
                     True.getValueType(), True, False, Cond);
}

static SDValue PerformSELECTCombine(SDNode *N, SelectionDAG& DAG,
                                    TargetLowering::DAGCombinerInfo &DCI,
                                    const MipsSubtarget* Subtarget) {
  if (DCI.isBeforeLegalizeOps())
    return SDValue();

  SDValue SetCC = N->getOperand(0);

  if ((SetCC.getOpcode() != ISD::SETCC) ||
      !SetCC.getOperand(0).getValueType().isInteger())
    return SDValue();

  SDValue False = N->getOperand(2);
  EVT FalseTy = False.getValueType();

  if (!FalseTy.isInteger())
    return SDValue();

  ConstantSDNode *CN = dyn_cast<ConstantSDNode>(False);

  if (!CN || CN->getZExtValue())
    return SDValue();

  const DebugLoc DL = N->getDebugLoc();
  ISD::CondCode CC = cast<CondCodeSDNode>(SetCC.getOperand(2))->get();
  SDValue True = N->getOperand(1);
  
  SetCC = DAG.getSetCC(DL, SetCC.getValueType(), SetCC.getOperand(0),
                       SetCC.getOperand(1), ISD::getSetCCInverse(CC, true));
  
  return DAG.getNode(ISD::SELECT, DL, FalseTy, SetCC, False, True);
}

static SDValue PerformANDCombine(SDNode *N, SelectionDAG& DAG,
                                 TargetLowering::DAGCombinerInfo &DCI,
                                 const MipsSubtarget* Subtarget) {
  // Pattern match EXT.
  //  $dst = and ((sra or srl) $src , pos), (2**size - 1)
  //  => ext $dst, $src, size, pos
  if (DCI.isBeforeLegalizeOps() || !Subtarget->hasMips32r2())
    return SDValue();

  SDValue ShiftRight = N->getOperand(0), Mask = N->getOperand(1);
  unsigned ShiftRightOpc = ShiftRight.getOpcode();

  // Op's first operand must be a shift right.
  if (ShiftRightOpc != ISD::SRA && ShiftRightOpc != ISD::SRL)
    return SDValue();

  // The second operand of the shift must be an immediate.
  ConstantSDNode *CN;
  if (!(CN = dyn_cast<ConstantSDNode>(ShiftRight.getOperand(1))))
    return SDValue();

  uint64_t Pos = CN->getZExtValue();
  uint64_t SMPos, SMSize;

  // Op's second operand must be a shifted mask.
  if (!(CN = dyn_cast<ConstantSDNode>(Mask)) ||
      !IsShiftedMask(CN->getZExtValue(), SMPos, SMSize))
    return SDValue();

  // Return if the shifted mask does not start at bit 0 or the sum of its size
  // and Pos exceeds the word's size.
  EVT ValTy = N->getValueType(0);
  if (SMPos != 0 || Pos + SMSize > ValTy.getSizeInBits())
    return SDValue();

  return DAG.getNode(MipsISD::Ext, N->getDebugLoc(), ValTy,
                     ShiftRight.getOperand(0), DAG.getConstant(Pos, MVT::i32),
                     DAG.getConstant(SMSize, MVT::i32));
}

static SDValue PerformORCombine(SDNode *N, SelectionDAG& DAG,
                                TargetLowering::DAGCombinerInfo &DCI,
                                const MipsSubtarget* Subtarget) {
  // Pattern match INS.
  //  $dst = or (and $src1 , mask0), (and (shl $src, pos), mask1),
  //  where mask1 = (2**size - 1) << pos, mask0 = ~mask1
  //  => ins $dst, $src, size, pos, $src1
  if (DCI.isBeforeLegalizeOps() || !Subtarget->hasMips32r2())
    return SDValue();

  SDValue And0 = N->getOperand(0), And1 = N->getOperand(1);
  uint64_t SMPos0, SMSize0, SMPos1, SMSize1;
  ConstantSDNode *CN;

  // See if Op's first operand matches (and $src1 , mask0).
  if (And0.getOpcode() != ISD::AND)
    return SDValue();

  if (!(CN = dyn_cast<ConstantSDNode>(And0.getOperand(1))) ||
      !IsShiftedMask(~CN->getSExtValue(), SMPos0, SMSize0))
    return SDValue();

  // See if Op's second operand matches (and (shl $src, pos), mask1).
  if (And1.getOpcode() != ISD::AND)
    return SDValue();

  if (!(CN = dyn_cast<ConstantSDNode>(And1.getOperand(1))) ||
      !IsShiftedMask(CN->getZExtValue(), SMPos1, SMSize1))
    return SDValue();

  // The shift masks must have the same position and size.
  if (SMPos0 != SMPos1 || SMSize0 != SMSize1)
    return SDValue();

  SDValue Shl = And1.getOperand(0);
  if (Shl.getOpcode() != ISD::SHL)
    return SDValue();

  if (!(CN = dyn_cast<ConstantSDNode>(Shl.getOperand(1))))
    return SDValue();

  unsigned Shamt = CN->getZExtValue();

  // Return if the shift amount and the first bit position of mask are not the
  // same.
  EVT ValTy = N->getValueType(0);
  if ((Shamt != SMPos0) || (SMPos0 + SMSize0 > ValTy.getSizeInBits()))
    return SDValue();

  return DAG.getNode(MipsISD::Ins, N->getDebugLoc(), ValTy, Shl.getOperand(0),
                     DAG.getConstant(SMPos0, MVT::i32),
                     DAG.getConstant(SMSize0, MVT::i32), And0.getOperand(0));
}

SDValue  MipsTargetLowering::PerformDAGCombine(SDNode *N, DAGCombinerInfo &DCI)
  const {
  SelectionDAG &DAG = DCI.DAG;
  unsigned opc = N->getOpcode();

  switch (opc) {
  default: break;
  case ISD::ADDE:
    return PerformADDECombine(N, DAG, DCI, Subtarget);
  case ISD::SUBE:
    return PerformSUBECombine(N, DAG, DCI, Subtarget);
  case ISD::SDIVREM:
  case ISD::UDIVREM:
    return PerformDivRemCombine(N, DAG, DCI, Subtarget);
  case ISD::SELECT:
    return PerformSELECTCombine(N, DAG, DCI, Subtarget);  
  case ISD::AND:
    return PerformANDCombine(N, DAG, DCI, Subtarget);
  case ISD::OR:
    return PerformORCombine(N, DAG, DCI, Subtarget);
  }

  return SDValue();
}

SDValue MipsTargetLowering::
LowerOperation(SDValue Op, SelectionDAG &DAG) const
{
  switch (Op.getOpcode())
  {
    case ISD::BRCOND:             return LowerBRCOND(Op, DAG);
    case ISD::ConstantPool:       return LowerConstantPool(Op, DAG);
    case ISD::DYNAMIC_STACKALLOC: return LowerDYNAMIC_STACKALLOC(Op, DAG);
    case ISD::GlobalAddress:      return LowerGlobalAddress(Op, DAG);
    case ISD::BlockAddress:       return LowerBlockAddress(Op, DAG);
    case ISD::GlobalTLSAddress:   return LowerGlobalTLSAddress(Op, DAG);
    case ISD::JumpTable:          return LowerJumpTable(Op, DAG);
    case ISD::SELECT:             return LowerSELECT(Op, DAG);
    case ISD::SETCC:              return LowerSETCC(Op, DAG);
    case ISD::VASTART:            return LowerVASTART(Op, DAG);
    case ISD::FCOPYSIGN:          return LowerFCOPYSIGN(Op, DAG);
    case ISD::FRAMEADDR:          return LowerFRAMEADDR(Op, DAG);
    case ISD::MEMBARRIER:         return LowerMEMBARRIER(Op, DAG);
    case ISD::ATOMIC_FENCE:       return LowerATOMIC_FENCE(Op, DAG);
  }
  return SDValue();
}

//===----------------------------------------------------------------------===//
//  Lower helper functions
//===----------------------------------------------------------------------===//

// AddLiveIn - This helper function adds the specified physical register to the
// MachineFunction as a live in value.  It also creates a corresponding
// virtual register for it.
static unsigned
AddLiveIn(MachineFunction &MF, unsigned PReg, const TargetRegisterClass *RC)
{
  assert(RC->contains(PReg) && "Not the correct regclass!");
  unsigned VReg = MF.getRegInfo().createVirtualRegister(RC);
  MF.getRegInfo().addLiveIn(PReg, VReg);
  return VReg;
}

// Get fp branch code (not opcode) from condition code.
static Mips::FPBranchCode GetFPBranchCodeFromCond(Mips::CondCode CC) {
  if (CC >= Mips::FCOND_F && CC <= Mips::FCOND_NGT)
    return Mips::BRANCH_T;

  assert((CC >= Mips::FCOND_T && CC <= Mips::FCOND_GT) &&
         "Invalid CondCode.");

  return Mips::BRANCH_F;
}

/*
static MachineBasicBlock* ExpandCondMov(MachineInstr *MI, MachineBasicBlock *BB,
                                        DebugLoc dl,
                                        const MipsSubtarget* Subtarget,
                                        const TargetInstrInfo *TII,
                                        bool isFPCmp, unsigned Opc) {
  // There is no need to expand CMov instructions if target has
  // conditional moves.
  if (Subtarget->hasCondMov())
    return BB;

  // To "insert" a SELECT_CC instruction, we actually have to insert the
  // diamond control-flow pattern.  The incoming instruction knows the
  // destination vreg to set, the condition code register to branch on, the
  // true/false values to select between, and a branch opcode to use.
  const BasicBlock *LLVM_BB = BB->getBasicBlock();
  MachineFunction::iterator It = BB;
  ++It;

  //  thisMBB:
  //  ...
  //   TrueVal = ...
  //   setcc r1, r2, r3
  //   bNE   r1, r0, copy1MBB
  //   fallthrough --> copy0MBB
  MachineBasicBlock *thisMBB  = BB;
  MachineFunction *F = BB->getParent();
  MachineBasicBlock *copy0MBB = F->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *sinkMBB  = F->CreateMachineBasicBlock(LLVM_BB);
  F->insert(It, copy0MBB);
  F->insert(It, sinkMBB);

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

  // Next, add the true and fallthrough blocks as its successors.
  BB->addSuccessor(copy0MBB);
  BB->addSuccessor(sinkMBB);

  // Emit the right instruction according to the type of the operands compared
  if (isFPCmp)
    BuildMI(BB, dl, TII->get(Opc)).addMBB(sinkMBB);
  else
    BuildMI(BB, dl, TII->get(Opc)).addReg(MI->getOperand(2).getReg())
      .addReg(Mips::ZERO).addMBB(sinkMBB);

  //  copy0MBB:
  //   %FalseValue = ...
  //   # fallthrough to sinkMBB
  BB = copy0MBB;

  // Update machine-CFG edges
  BB->addSuccessor(sinkMBB);

  //  sinkMBB:
  //   %Result = phi [ %TrueValue, thisMBB ], [ %FalseValue, copy0MBB ]
  //  ...
  BB = sinkMBB;

  if (isFPCmp)
    BuildMI(*BB, BB->begin(), dl,
            TII->get(Mips::PHI), MI->getOperand(0).getReg())
      .addReg(MI->getOperand(2).getReg()).addMBB(thisMBB)
      .addReg(MI->getOperand(1).getReg()).addMBB(copy0MBB);
  else
    BuildMI(*BB, BB->begin(), dl,
            TII->get(Mips::PHI), MI->getOperand(0).getReg())
      .addReg(MI->getOperand(3).getReg()).addMBB(thisMBB)
      .addReg(MI->getOperand(1).getReg()).addMBB(copy0MBB);

  MI->eraseFromParent();   // The pseudo instruction is gone now.
  return BB;
}
*/
MachineBasicBlock *
MipsTargetLowering::EmitInstrWithCustomInserter(MachineInstr *MI,
                                                MachineBasicBlock *BB) const {
  switch (MI->getOpcode()) {
  default: llvm_unreachable("Unexpected instr type to insert");
  case Mips::ATOMIC_LOAD_ADD_I8:
  case Mips::ATOMIC_LOAD_ADD_I8_P8:
    return EmitAtomicBinaryPartword(MI, BB, 1, Mips::ADDu);
  case Mips::ATOMIC_LOAD_ADD_I16:
  case Mips::ATOMIC_LOAD_ADD_I16_P8:
    return EmitAtomicBinaryPartword(MI, BB, 2, Mips::ADDu);
  case Mips::ATOMIC_LOAD_ADD_I32:
  case Mips::ATOMIC_LOAD_ADD_I32_P8:
    return EmitAtomicBinary(MI, BB, 4, Mips::ADDu);
  case Mips::ATOMIC_LOAD_ADD_I64:
  case Mips::ATOMIC_LOAD_ADD_I64_P8:
    return EmitAtomicBinary(MI, BB, 8, Mips::DADDu);

  case Mips::ATOMIC_LOAD_AND_I8:
  case Mips::ATOMIC_LOAD_AND_I8_P8:
    return EmitAtomicBinaryPartword(MI, BB, 1, Mips::AND);
  case Mips::ATOMIC_LOAD_AND_I16:
  case Mips::ATOMIC_LOAD_AND_I16_P8:
    return EmitAtomicBinaryPartword(MI, BB, 2, Mips::AND);
  case Mips::ATOMIC_LOAD_AND_I32:
  case Mips::ATOMIC_LOAD_AND_I32_P8:
    return EmitAtomicBinary(MI, BB, 4, Mips::AND);
  case Mips::ATOMIC_LOAD_AND_I64:
  case Mips::ATOMIC_LOAD_AND_I64_P8:
    return EmitAtomicBinary(MI, BB, 8, Mips::AND64);

  case Mips::ATOMIC_LOAD_OR_I8:
  case Mips::ATOMIC_LOAD_OR_I8_P8:
    return EmitAtomicBinaryPartword(MI, BB, 1, Mips::OR);
  case Mips::ATOMIC_LOAD_OR_I16:
  case Mips::ATOMIC_LOAD_OR_I16_P8:
    return EmitAtomicBinaryPartword(MI, BB, 2, Mips::OR);
  case Mips::ATOMIC_LOAD_OR_I32:
  case Mips::ATOMIC_LOAD_OR_I32_P8:
    return EmitAtomicBinary(MI, BB, 4, Mips::OR);
  case Mips::ATOMIC_LOAD_OR_I64:
  case Mips::ATOMIC_LOAD_OR_I64_P8:
    return EmitAtomicBinary(MI, BB, 8, Mips::OR64);

  case Mips::ATOMIC_LOAD_XOR_I8:
  case Mips::ATOMIC_LOAD_XOR_I8_P8:
    return EmitAtomicBinaryPartword(MI, BB, 1, Mips::XOR);
  case Mips::ATOMIC_LOAD_XOR_I16:
  case Mips::ATOMIC_LOAD_XOR_I16_P8:
    return EmitAtomicBinaryPartword(MI, BB, 2, Mips::XOR);
  case Mips::ATOMIC_LOAD_XOR_I32:
  case Mips::ATOMIC_LOAD_XOR_I32_P8:
    return EmitAtomicBinary(MI, BB, 4, Mips::XOR);
  case Mips::ATOMIC_LOAD_XOR_I64:
  case Mips::ATOMIC_LOAD_XOR_I64_P8:
    return EmitAtomicBinary(MI, BB, 8, Mips::XOR64);

  case Mips::ATOMIC_LOAD_NAND_I8:
  case Mips::ATOMIC_LOAD_NAND_I8_P8:
    return EmitAtomicBinaryPartword(MI, BB, 1, 0, true);
  case Mips::ATOMIC_LOAD_NAND_I16:
  case Mips::ATOMIC_LOAD_NAND_I16_P8:
    return EmitAtomicBinaryPartword(MI, BB, 2, 0, true);
  case Mips::ATOMIC_LOAD_NAND_I32:
  case Mips::ATOMIC_LOAD_NAND_I32_P8:
    return EmitAtomicBinary(MI, BB, 4, 0, true);
  case Mips::ATOMIC_LOAD_NAND_I64:
  case Mips::ATOMIC_LOAD_NAND_I64_P8:
    return EmitAtomicBinary(MI, BB, 8, 0, true);

  case Mips::ATOMIC_LOAD_SUB_I8:
  case Mips::ATOMIC_LOAD_SUB_I8_P8:
    return EmitAtomicBinaryPartword(MI, BB, 1, Mips::SUBu);
  case Mips::ATOMIC_LOAD_SUB_I16:
  case Mips::ATOMIC_LOAD_SUB_I16_P8:
    return EmitAtomicBinaryPartword(MI, BB, 2, Mips::SUBu);
  case Mips::ATOMIC_LOAD_SUB_I32:
  case Mips::ATOMIC_LOAD_SUB_I32_P8:
    return EmitAtomicBinary(MI, BB, 4, Mips::SUBu);
  case Mips::ATOMIC_LOAD_SUB_I64:
  case Mips::ATOMIC_LOAD_SUB_I64_P8:
    return EmitAtomicBinary(MI, BB, 8, Mips::DSUBu);

  case Mips::ATOMIC_SWAP_I8:
  case Mips::ATOMIC_SWAP_I8_P8:
    return EmitAtomicBinaryPartword(MI, BB, 1, 0);
  case Mips::ATOMIC_SWAP_I16:
  case Mips::ATOMIC_SWAP_I16_P8:
    return EmitAtomicBinaryPartword(MI, BB, 2, 0);
  case Mips::ATOMIC_SWAP_I32:
  case Mips::ATOMIC_SWAP_I32_P8:
    return EmitAtomicBinary(MI, BB, 4, 0);
  case Mips::ATOMIC_SWAP_I64:
  case Mips::ATOMIC_SWAP_I64_P8:
    return EmitAtomicBinary(MI, BB, 8, 0);

  case Mips::ATOMIC_CMP_SWAP_I8:
  case Mips::ATOMIC_CMP_SWAP_I8_P8:
    return EmitAtomicCmpSwapPartword(MI, BB, 1);
  case Mips::ATOMIC_CMP_SWAP_I16:
  case Mips::ATOMIC_CMP_SWAP_I16_P8:
    return EmitAtomicCmpSwapPartword(MI, BB, 2);
  case Mips::ATOMIC_CMP_SWAP_I32:
  case Mips::ATOMIC_CMP_SWAP_I32_P8:
    return EmitAtomicCmpSwap(MI, BB, 4);
  case Mips::ATOMIC_CMP_SWAP_I64:
  case Mips::ATOMIC_CMP_SWAP_I64_P8:
    return EmitAtomicCmpSwap(MI, BB, 8);
  }
}

// This function also handles Mips::ATOMIC_SWAP_I32 (when BinOpcode == 0), and
// Mips::ATOMIC_LOAD_NAND_I32 (when Nand == true)
MachineBasicBlock *
MipsTargetLowering::EmitAtomicBinary(MachineInstr *MI, MachineBasicBlock *BB,
                                     unsigned Size, unsigned BinOpcode,
                                     bool Nand) const {
  assert((Size == 4 || Size == 8) && "Unsupported size for EmitAtomicBinary.");

  MachineFunction *MF = BB->getParent();
  MachineRegisterInfo &RegInfo = MF->getRegInfo();
  const TargetRegisterClass *RC = getRegClassFor(MVT::getIntegerVT(Size * 8));
  const TargetInstrInfo *TII = getTargetMachine().getInstrInfo();
  DebugLoc dl = MI->getDebugLoc();
  unsigned LL, SC, AND, NOR, ZERO, BEQ;

  if (Size == 4) {
    LL = IsN64 ? Mips::LL_P8 : Mips::LL;
    SC = IsN64 ? Mips::SC_P8 : Mips::SC;
    AND = Mips::AND;
    NOR = Mips::NOR;
    ZERO = Mips::ZERO;
    BEQ = Mips::BEQ;
  }
  else {
    LL = IsN64 ? Mips::LLD_P8 : Mips::LLD;
    SC = IsN64 ? Mips::SCD_P8 : Mips::SCD;
    AND = Mips::AND64;
    NOR = Mips::NOR64;
    ZERO = Mips::ZERO_64;
    BEQ = Mips::BEQ64;
  }

  unsigned OldVal = MI->getOperand(0).getReg();
  unsigned Ptr = MI->getOperand(1).getReg();
  unsigned Incr = MI->getOperand(2).getReg();

  unsigned StoreVal = RegInfo.createVirtualRegister(RC);
  unsigned AndRes = RegInfo.createVirtualRegister(RC);
  unsigned Success = RegInfo.createVirtualRegister(RC);

  // insert new blocks after the current block
  const BasicBlock *LLVM_BB = BB->getBasicBlock();
  MachineBasicBlock *loopMBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *exitMBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineFunction::iterator It = BB;
  ++It;
  MF->insert(It, loopMBB);
  MF->insert(It, exitMBB);

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

  //  thisMBB:
  //    ...
  //    fallthrough --> loopMBB
  BB->addSuccessor(loopMBB);
  loopMBB->addSuccessor(loopMBB);
  loopMBB->addSuccessor(exitMBB);

  //  loopMBB:
  //    ll oldval, 0(ptr)
  //    <binop> storeval, oldval, incr
  //    sc success, storeval, 0(ptr)
  //    beq success, $0, loopMBB
  BB = loopMBB;
  BuildMI(BB, dl, TII->get(LL), OldVal).addReg(Ptr).addImm(0);
  if (Nand) {
    //  and andres, oldval, incr
    //  nor storeval, $0, andres
    BuildMI(BB, dl, TII->get(AND), AndRes).addReg(OldVal).addReg(Incr);
    BuildMI(BB, dl, TII->get(NOR), StoreVal).addReg(ZERO).addReg(AndRes);
  } else if (BinOpcode) {
    //  <binop> storeval, oldval, incr
    BuildMI(BB, dl, TII->get(BinOpcode), StoreVal).addReg(OldVal).addReg(Incr);
  } else {
    StoreVal = Incr;
  }
  BuildMI(BB, dl, TII->get(SC), Success).addReg(StoreVal).addReg(Ptr).addImm(0);
  BuildMI(BB, dl, TII->get(BEQ)).addReg(Success).addReg(ZERO).addMBB(loopMBB);

  MI->eraseFromParent();   // The instruction is gone now.

  return exitMBB;
}

MachineBasicBlock *
MipsTargetLowering::EmitAtomicBinaryPartword(MachineInstr *MI,
                                             MachineBasicBlock *BB,
                                             unsigned Size, unsigned BinOpcode,
                                             bool Nand) const {
  assert((Size == 1 || Size == 2) &&
      "Unsupported size for EmitAtomicBinaryPartial.");

  MachineFunction *MF = BB->getParent();
  MachineRegisterInfo &RegInfo = MF->getRegInfo();
  const TargetRegisterClass *RC = getRegClassFor(MVT::i32);
  const TargetInstrInfo *TII = getTargetMachine().getInstrInfo();
  DebugLoc dl = MI->getDebugLoc();
  unsigned LL = IsN64 ? Mips::LL_P8 : Mips::LL;
  unsigned SC = IsN64 ? Mips::SC_P8 : Mips::SC;

  unsigned Dest = MI->getOperand(0).getReg();
  unsigned Ptr = MI->getOperand(1).getReg();
  unsigned Incr = MI->getOperand(2).getReg();

  unsigned AlignedAddr = RegInfo.createVirtualRegister(RC);
  unsigned ShiftAmt = RegInfo.createVirtualRegister(RC);
  unsigned Mask = RegInfo.createVirtualRegister(RC);
  unsigned Mask2 = RegInfo.createVirtualRegister(RC);
  unsigned NewVal = RegInfo.createVirtualRegister(RC);
  unsigned OldVal = RegInfo.createVirtualRegister(RC);
  unsigned Incr2 = RegInfo.createVirtualRegister(RC);
  unsigned MaskLSB2 = RegInfo.createVirtualRegister(RC);
  unsigned PtrLSB2 = RegInfo.createVirtualRegister(RC);
  unsigned MaskUpper = RegInfo.createVirtualRegister(RC);
  unsigned AndRes = RegInfo.createVirtualRegister(RC);
  unsigned BinOpRes = RegInfo.createVirtualRegister(RC);
  unsigned MaskedOldVal0 = RegInfo.createVirtualRegister(RC);
  unsigned StoreVal = RegInfo.createVirtualRegister(RC);
  unsigned MaskedOldVal1 = RegInfo.createVirtualRegister(RC);
  unsigned SrlRes = RegInfo.createVirtualRegister(RC);
  unsigned SllRes = RegInfo.createVirtualRegister(RC);
  unsigned Success = RegInfo.createVirtualRegister(RC);

  // insert new blocks after the current block
  const BasicBlock *LLVM_BB = BB->getBasicBlock();
  MachineBasicBlock *loopMBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *sinkMBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *exitMBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineFunction::iterator It = BB;
  ++It;
  MF->insert(It, loopMBB);
  MF->insert(It, sinkMBB);
  MF->insert(It, exitMBB);

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

  BB->addSuccessor(loopMBB);
  loopMBB->addSuccessor(loopMBB);
  loopMBB->addSuccessor(sinkMBB);
  sinkMBB->addSuccessor(exitMBB);

  //  thisMBB:
  //    addiu   masklsb2,$0,-4                # 0xfffffffc
  //    and     alignedaddr,ptr,masklsb2
  //    andi    ptrlsb2,ptr,3
  //    sll     shiftamt,ptrlsb2,3
  //    ori     maskupper,$0,255               # 0xff
  //    sll     mask,maskupper,shiftamt
  //    nor     mask2,$0,mask
  //    sll     incr2,incr,shiftamt

  int64_t MaskImm = (Size == 1) ? 255 : 65535;
  BuildMI(BB, dl, TII->get(Mips::ADDiu), MaskLSB2)
    .addReg(Mips::ZERO).addImm(-4);
  BuildMI(BB, dl, TII->get(Mips::AND), AlignedAddr)
    .addReg(Ptr).addReg(MaskLSB2);
  BuildMI(BB, dl, TII->get(Mips::ANDi), PtrLSB2).addReg(Ptr).addImm(3);
  BuildMI(BB, dl, TII->get(Mips::SLL), ShiftAmt).addReg(PtrLSB2).addImm(3);
  BuildMI(BB, dl, TII->get(Mips::ORi), MaskUpper)
    .addReg(Mips::ZERO).addImm(MaskImm);
  BuildMI(BB, dl, TII->get(Mips::SLLV), Mask)
    .addReg(ShiftAmt).addReg(MaskUpper);
  BuildMI(BB, dl, TII->get(Mips::NOR), Mask2).addReg(Mips::ZERO).addReg(Mask);
  BuildMI(BB, dl, TII->get(Mips::SLLV), Incr2).addReg(ShiftAmt).addReg(Incr);

  // atomic.load.binop
  // loopMBB:
  //   ll      oldval,0(alignedaddr)
  //   binop   binopres,oldval,incr2
  //   and     newval,binopres,mask
  //   and     maskedoldval0,oldval,mask2
  //   or      storeval,maskedoldval0,newval
  //   sc      success,storeval,0(alignedaddr)
  //   beq     success,$0,loopMBB

  // atomic.swap
  // loopMBB:
  //   ll      oldval,0(alignedaddr)
  //   and     newval,incr2,mask
  //   and     maskedoldval0,oldval,mask2
  //   or      storeval,maskedoldval0,newval
  //   sc      success,storeval,0(alignedaddr)
  //   beq     success,$0,loopMBB

  BB = loopMBB;
  BuildMI(BB, dl, TII->get(LL), OldVal).addReg(AlignedAddr).addImm(0);
  if (Nand) {
    //  and andres, oldval, incr2
    //  nor binopres, $0, andres
    //  and newval, binopres, mask
    BuildMI(BB, dl, TII->get(Mips::AND), AndRes).addReg(OldVal).addReg(Incr2);
    BuildMI(BB, dl, TII->get(Mips::NOR), BinOpRes)
      .addReg(Mips::ZERO).addReg(AndRes);
    BuildMI(BB, dl, TII->get(Mips::AND), NewVal).addReg(BinOpRes).addReg(Mask);
  } else if (BinOpcode) {
    //  <binop> binopres, oldval, incr2
    //  and newval, binopres, mask
    BuildMI(BB, dl, TII->get(BinOpcode), BinOpRes).addReg(OldVal).addReg(Incr2);
    BuildMI(BB, dl, TII->get(Mips::AND), NewVal).addReg(BinOpRes).addReg(Mask);
  } else {// atomic.swap
    //  and newval, incr2, mask
    BuildMI(BB, dl, TII->get(Mips::AND), NewVal).addReg(Incr2).addReg(Mask);
  }

  BuildMI(BB, dl, TII->get(Mips::AND), MaskedOldVal0)
    .addReg(OldVal).addReg(Mask2);
  BuildMI(BB, dl, TII->get(Mips::OR), StoreVal)
    .addReg(MaskedOldVal0).addReg(NewVal);
  BuildMI(BB, dl, TII->get(SC), Success)
    .addReg(StoreVal).addReg(AlignedAddr).addImm(0);
  BuildMI(BB, dl, TII->get(Mips::BEQ))
    .addReg(Success).addReg(Mips::ZERO).addMBB(loopMBB);

  //  sinkMBB:
  //    and     maskedoldval1,oldval,mask
  //    srl     srlres,maskedoldval1,shiftamt
  //    sll     sllres,srlres,24
  //    sra     dest,sllres,24
  BB = sinkMBB;
  int64_t ShiftImm = (Size == 1) ? 24 : 16;

  BuildMI(BB, dl, TII->get(Mips::AND), MaskedOldVal1)
    .addReg(OldVal).addReg(Mask);
  BuildMI(BB, dl, TII->get(Mips::SRLV), SrlRes)
      .addReg(ShiftAmt).addReg(MaskedOldVal1);
  BuildMI(BB, dl, TII->get(Mips::SLL), SllRes)
      .addReg(SrlRes).addImm(ShiftImm);
  BuildMI(BB, dl, TII->get(Mips::SRA), Dest)
      .addReg(SllRes).addImm(ShiftImm);

  MI->eraseFromParent();   // The instruction is gone now.

  return exitMBB;
}

MachineBasicBlock *
MipsTargetLowering::EmitAtomicCmpSwap(MachineInstr *MI,
                                      MachineBasicBlock *BB,
                                      unsigned Size) const {
  assert((Size == 4 || Size == 8) && "Unsupported size for EmitAtomicCmpSwap.");

  MachineFunction *MF = BB->getParent();
  MachineRegisterInfo &RegInfo = MF->getRegInfo();
  const TargetRegisterClass *RC = getRegClassFor(MVT::getIntegerVT(Size * 8));
  const TargetInstrInfo *TII = getTargetMachine().getInstrInfo();
  DebugLoc dl = MI->getDebugLoc();
  unsigned LL, SC, ZERO, BNE, BEQ;

  if (Size == 4) {
    LL = IsN64 ? Mips::LL_P8 : Mips::LL;
    SC = IsN64 ? Mips::SC_P8 : Mips::SC;
    ZERO = Mips::ZERO;
    BNE = Mips::BNE;
    BEQ = Mips::BEQ;
  }
  else {
    LL = IsN64 ? Mips::LLD_P8 : Mips::LLD;
    SC = IsN64 ? Mips::SCD_P8 : Mips::SCD;
    ZERO = Mips::ZERO_64;
    BNE = Mips::BNE64;
    BEQ = Mips::BEQ64;
  }

  unsigned Dest    = MI->getOperand(0).getReg();
  unsigned Ptr     = MI->getOperand(1).getReg();
  unsigned OldVal  = MI->getOperand(2).getReg();
  unsigned NewVal  = MI->getOperand(3).getReg();

  unsigned Success = RegInfo.createVirtualRegister(RC);

  // insert new blocks after the current block
  const BasicBlock *LLVM_BB = BB->getBasicBlock();
  MachineBasicBlock *loop1MBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *loop2MBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *exitMBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineFunction::iterator It = BB;
  ++It;
  MF->insert(It, loop1MBB);
  MF->insert(It, loop2MBB);
  MF->insert(It, exitMBB);

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

  //  thisMBB:
  //    ...
  //    fallthrough --> loop1MBB
  BB->addSuccessor(loop1MBB);
  loop1MBB->addSuccessor(exitMBB);
  loop1MBB->addSuccessor(loop2MBB);
  loop2MBB->addSuccessor(loop1MBB);
  loop2MBB->addSuccessor(exitMBB);

  // loop1MBB:
  //   ll dest, 0(ptr)
  //   bne dest, oldval, exitMBB
  BB = loop1MBB;
  BuildMI(BB, dl, TII->get(LL), Dest).addReg(Ptr).addImm(0);
  BuildMI(BB, dl, TII->get(BNE))
    .addReg(Dest).addReg(OldVal).addMBB(exitMBB);

  // loop2MBB:
  //   sc success, newval, 0(ptr)
  //   beq success, $0, loop1MBB
  BB = loop2MBB;
  BuildMI(BB, dl, TII->get(SC), Success)
    .addReg(NewVal).addReg(Ptr).addImm(0);
  BuildMI(BB, dl, TII->get(BEQ))
    .addReg(Success).addReg(ZERO).addMBB(loop1MBB);

  MI->eraseFromParent();   // The instruction is gone now.

  return exitMBB;
}

MachineBasicBlock *
MipsTargetLowering::EmitAtomicCmpSwapPartword(MachineInstr *MI,
                                              MachineBasicBlock *BB,
                                              unsigned Size) const {
  assert((Size == 1 || Size == 2) &&
      "Unsupported size for EmitAtomicCmpSwapPartial.");

  MachineFunction *MF = BB->getParent();
  MachineRegisterInfo &RegInfo = MF->getRegInfo();
  const TargetRegisterClass *RC = getRegClassFor(MVT::i32);
  const TargetInstrInfo *TII = getTargetMachine().getInstrInfo();
  DebugLoc dl = MI->getDebugLoc();
  unsigned LL = IsN64 ? Mips::LL_P8 : Mips::LL;
  unsigned SC = IsN64 ? Mips::SC_P8 : Mips::SC;

  unsigned Dest    = MI->getOperand(0).getReg();
  unsigned Ptr     = MI->getOperand(1).getReg();
  unsigned CmpVal  = MI->getOperand(2).getReg();
  unsigned NewVal  = MI->getOperand(3).getReg();

  unsigned AlignedAddr = RegInfo.createVirtualRegister(RC);
  unsigned ShiftAmt = RegInfo.createVirtualRegister(RC);
  unsigned Mask = RegInfo.createVirtualRegister(RC);
  unsigned Mask2 = RegInfo.createVirtualRegister(RC);
  unsigned ShiftedCmpVal = RegInfo.createVirtualRegister(RC);
  unsigned OldVal = RegInfo.createVirtualRegister(RC);
  unsigned MaskedOldVal0 = RegInfo.createVirtualRegister(RC);
  unsigned ShiftedNewVal = RegInfo.createVirtualRegister(RC);
  unsigned MaskLSB2 = RegInfo.createVirtualRegister(RC);
  unsigned PtrLSB2 = RegInfo.createVirtualRegister(RC);
  unsigned MaskUpper = RegInfo.createVirtualRegister(RC);
  unsigned MaskedCmpVal = RegInfo.createVirtualRegister(RC);
  unsigned MaskedNewVal = RegInfo.createVirtualRegister(RC);
  unsigned MaskedOldVal1 = RegInfo.createVirtualRegister(RC);
  unsigned StoreVal = RegInfo.createVirtualRegister(RC);
  unsigned SrlRes = RegInfo.createVirtualRegister(RC);
  unsigned SllRes = RegInfo.createVirtualRegister(RC);
  unsigned Success = RegInfo.createVirtualRegister(RC);

  // insert new blocks after the current block
  const BasicBlock *LLVM_BB = BB->getBasicBlock();
  MachineBasicBlock *loop1MBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *loop2MBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *sinkMBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineBasicBlock *exitMBB = MF->CreateMachineBasicBlock(LLVM_BB);
  MachineFunction::iterator It = BB;
  ++It;
  MF->insert(It, loop1MBB);
  MF->insert(It, loop2MBB);
  MF->insert(It, sinkMBB);
  MF->insert(It, exitMBB);

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

  BB->addSuccessor(loop1MBB);
  loop1MBB->addSuccessor(sinkMBB);
  loop1MBB->addSuccessor(loop2MBB);
  loop2MBB->addSuccessor(loop1MBB);
  loop2MBB->addSuccessor(sinkMBB);
  sinkMBB->addSuccessor(exitMBB);

  // FIXME: computation of newval2 can be moved to loop2MBB.
  //  thisMBB:
  //    addiu   masklsb2,$0,-4                # 0xfffffffc
  //    and     alignedaddr,ptr,masklsb2
  //    andi    ptrlsb2,ptr,3
  //    sll     shiftamt,ptrlsb2,3
  //    ori     maskupper,$0,255               # 0xff
  //    sll     mask,maskupper,shiftamt
  //    nor     mask2,$0,mask
  //    andi    maskedcmpval,cmpval,255
  //    sll     shiftedcmpval,maskedcmpval,shiftamt
  //    andi    maskednewval,newval,255
  //    sll     shiftednewval,maskednewval,shiftamt
  int64_t MaskImm = (Size == 1) ? 255 : 65535;
  BuildMI(BB, dl, TII->get(Mips::ADDiu), MaskLSB2)
    .addReg(Mips::ZERO).addImm(-4);
  BuildMI(BB, dl, TII->get(Mips::AND), AlignedAddr)
    .addReg(Ptr).addReg(MaskLSB2);
  BuildMI(BB, dl, TII->get(Mips::ANDi), PtrLSB2).addReg(Ptr).addImm(3);
  BuildMI(BB, dl, TII->get(Mips::SLL), ShiftAmt).addReg(PtrLSB2).addImm(3);
  BuildMI(BB, dl, TII->get(Mips::ORi), MaskUpper)
    .addReg(Mips::ZERO).addImm(MaskImm);
  BuildMI(BB, dl, TII->get(Mips::SLLV), Mask)
    .addReg(ShiftAmt).addReg(MaskUpper);
  BuildMI(BB, dl, TII->get(Mips::NOR), Mask2).addReg(Mips::ZERO).addReg(Mask);
  BuildMI(BB, dl, TII->get(Mips::ANDi), MaskedCmpVal)
    .addReg(CmpVal).addImm(MaskImm);
  BuildMI(BB, dl, TII->get(Mips::SLLV), ShiftedCmpVal)
    .addReg(ShiftAmt).addReg(MaskedCmpVal);
  BuildMI(BB, dl, TII->get(Mips::ANDi), MaskedNewVal)
    .addReg(NewVal).addImm(MaskImm);
  BuildMI(BB, dl, TII->get(Mips::SLLV), ShiftedNewVal)
    .addReg(ShiftAmt).addReg(MaskedNewVal);

  //  loop1MBB:
  //    ll      oldval,0(alginedaddr)
  //    and     maskedoldval0,oldval,mask
  //    bne     maskedoldval0,shiftedcmpval,sinkMBB
  BB = loop1MBB;
  BuildMI(BB, dl, TII->get(LL), OldVal).addReg(AlignedAddr).addImm(0);
  BuildMI(BB, dl, TII->get(Mips::AND), MaskedOldVal0)
    .addReg(OldVal).addReg(Mask);
  BuildMI(BB, dl, TII->get(Mips::BNE))
    .addReg(MaskedOldVal0).addReg(ShiftedCmpVal).addMBB(sinkMBB);

  //  loop2MBB:
  //    and     maskedoldval1,oldval,mask2
  //    or      storeval,maskedoldval1,shiftednewval
  //    sc      success,storeval,0(alignedaddr)
  //    beq     success,$0,loop1MBB
  BB = loop2MBB;
  BuildMI(BB, dl, TII->get(Mips::AND), MaskedOldVal1)
    .addReg(OldVal).addReg(Mask2);
  BuildMI(BB, dl, TII->get(Mips::OR), StoreVal)
    .addReg(MaskedOldVal1).addReg(ShiftedNewVal);
  BuildMI(BB, dl, TII->get(SC), Success)
      .addReg(StoreVal).addReg(AlignedAddr).addImm(0);
  BuildMI(BB, dl, TII->get(Mips::BEQ))
      .addReg(Success).addReg(Mips::ZERO).addMBB(loop1MBB);

  //  sinkMBB:
  //    srl     srlres,maskedoldval0,shiftamt
  //    sll     sllres,srlres,24
  //    sra     dest,sllres,24
  BB = sinkMBB;
  int64_t ShiftImm = (Size == 1) ? 24 : 16;

  BuildMI(BB, dl, TII->get(Mips::SRLV), SrlRes)
      .addReg(ShiftAmt).addReg(MaskedOldVal0);
  BuildMI(BB, dl, TII->get(Mips::SLL), SllRes)
      .addReg(SrlRes).addImm(ShiftImm);
  BuildMI(BB, dl, TII->get(Mips::SRA), Dest)
      .addReg(SllRes).addImm(ShiftImm);

  MI->eraseFromParent();   // The instruction is gone now.

  return exitMBB;
}

//===----------------------------------------------------------------------===//
//  Misc Lower Operation implementation
//===----------------------------------------------------------------------===//
SDValue MipsTargetLowering::
LowerDYNAMIC_STACKALLOC(SDValue Op, SelectionDAG &DAG) const
{
  MachineFunction &MF = DAG.getMachineFunction();
  MipsFunctionInfo *MipsFI = MF.getInfo<MipsFunctionInfo>();
  unsigned SP = IsN64 ? Mips::SP_64 : Mips::SP;

  assert(getTargetMachine().getFrameLowering()->getStackAlignment() >=
         cast<ConstantSDNode>(Op.getOperand(2).getNode())->getZExtValue() &&
         "Cannot lower if the alignment of the allocated space is larger than \
          that of the stack.");

  SDValue Chain = Op.getOperand(0);
  SDValue Size = Op.getOperand(1);
  DebugLoc dl = Op.getDebugLoc();

  // Get a reference from Mips stack pointer
  SDValue StackPointer = DAG.getCopyFromReg(Chain, dl, SP, getPointerTy());

  // Subtract the dynamic size from the actual stack size to
  // obtain the new stack size.
  SDValue Sub = DAG.getNode(ISD::SUB, dl, getPointerTy(), StackPointer, Size);

  // The Sub result contains the new stack start address, so it
  // must be placed in the stack pointer register.
  Chain = DAG.getCopyToReg(StackPointer.getValue(1), dl, SP, Sub, SDValue());

  // This node always has two return values: a new stack pointer
  // value and a chain
  SDVTList VTLs = DAG.getVTList(getPointerTy(), MVT::Other);
  SDValue Ptr = DAG.getFrameIndex(MipsFI->getDynAllocFI(), getPointerTy());
  SDValue Ops[] = { Chain, Ptr, Chain.getValue(1) };

  return DAG.getNode(MipsISD::DynAlloc, dl, VTLs, Ops, 3);
}

SDValue MipsTargetLowering::
LowerBRCOND(SDValue Op, SelectionDAG &DAG) const
{
  // The first operand is the chain, the second is the condition, the third is
  // the block to branch to if the condition is true.
  SDValue Chain = Op.getOperand(0);
  SDValue Dest = Op.getOperand(2);
  DebugLoc dl = Op.getDebugLoc();

  SDValue CondRes = CreateFPCmp(DAG, Op.getOperand(1));

  // Return if flag is not set by a floating point comparison.
  if (CondRes.getOpcode() != MipsISD::FPCmp)
    return Op;

  SDValue CCNode  = CondRes.getOperand(2);
  Mips::CondCode CC =
    (Mips::CondCode)cast<ConstantSDNode>(CCNode)->getZExtValue();
  SDValue BrCode = DAG.getConstant(GetFPBranchCodeFromCond(CC), MVT::i32);

  return DAG.getNode(MipsISD::FPBrcond, dl, Op.getValueType(), Chain, BrCode,
                     Dest, CondRes);
}

SDValue MipsTargetLowering::
LowerSELECT(SDValue Op, SelectionDAG &DAG) const
{
  SDValue Cond = CreateFPCmp(DAG, Op.getOperand(0));

  // Return if flag is not set by a floating point comparison.
  if (Cond.getOpcode() != MipsISD::FPCmp)
    return Op;

  return CreateCMovFP(DAG, Cond, Op.getOperand(1), Op.getOperand(2),
                      Op.getDebugLoc());
}

SDValue MipsTargetLowering::LowerSETCC(SDValue Op, SelectionDAG &DAG) const {
  SDValue Cond = CreateFPCmp(DAG, Op);

  assert(Cond.getOpcode() == MipsISD::FPCmp &&
         "Floating point operand expected.");

  SDValue True  = DAG.getConstant(1, MVT::i32);
  SDValue False = DAG.getConstant(0, MVT::i32);

  return CreateCMovFP(DAG, Cond, True, False, Op.getDebugLoc());
}

SDValue MipsTargetLowering::LowerGlobalAddress(SDValue Op,
                                               SelectionDAG &DAG) const {
  // FIXME there isn't actually debug info here
  DebugLoc dl = Op.getDebugLoc();
  const GlobalValue *GV = cast<GlobalAddressSDNode>(Op)->getGlobal();

  if (getTargetMachine().getRelocationModel() != Reloc::PIC_ && !IsN64) {
    SDVTList VTs = DAG.getVTList(MVT::i32);

    MipsTargetObjectFile &TLOF = (MipsTargetObjectFile&)getObjFileLowering();

    // %gp_rel relocation
    if (TLOF.IsGlobalInSmallSection(GV, getTargetMachine())) {
      SDValue GA = DAG.getTargetGlobalAddress(GV, dl, MVT::i32, 0,
                                              MipsII::MO_GPREL);
      SDValue GPRelNode = DAG.getNode(MipsISD::GPRel, dl, VTs, &GA, 1);
      SDValue GOT = DAG.getGLOBAL_OFFSET_TABLE(MVT::i32);
      return DAG.getNode(ISD::ADD, dl, MVT::i32, GOT, GPRelNode);
    }
    // %hi/%lo relocation
    SDValue GAHi = DAG.getTargetGlobalAddress(GV, dl, MVT::i32, 0,
                                              MipsII::MO_ABS_HI);
    SDValue GALo = DAG.getTargetGlobalAddress(GV, dl, MVT::i32, 0,
                                              MipsII::MO_ABS_LO);
    SDValue HiPart = DAG.getNode(MipsISD::Hi, dl, VTs, &GAHi, 1);
    SDValue Lo = DAG.getNode(MipsISD::Lo, dl, MVT::i32, GALo);
    return DAG.getNode(ISD::ADD, dl, MVT::i32, HiPart, Lo);
  }

  EVT ValTy = Op.getValueType();
  bool HasGotOfst = (GV->hasInternalLinkage() ||
                     (GV->hasLocalLinkage() && !isa<Function>(GV)));
  unsigned GotFlag = IsN64 ?
                     (HasGotOfst ? MipsII::MO_GOT_PAGE : MipsII::MO_GOT_DISP) :
                     (HasGotOfst ? MipsII::MO_GOT : MipsII::MO_GOT16);
  SDValue GA = DAG.getTargetGlobalAddress(GV, dl, ValTy, 0, GotFlag);
  GA = DAG.getNode(MipsISD::Wrapper, dl, ValTy, GetGlobalReg(DAG, ValTy), GA);
  SDValue ResNode = DAG.getLoad(ValTy, dl, DAG.getEntryNode(), GA,
                                MachinePointerInfo(), false, false, false, 0);
  // On functions and global targets not internal linked only
  // a load from got/GP is necessary for PIC to work.
  if (!HasGotOfst)
    return ResNode;
  SDValue GALo = DAG.getTargetGlobalAddress(GV, dl, ValTy, 0,
                                            IsN64 ? MipsII::MO_GOT_OFST :
                                                    MipsII::MO_ABS_LO);
  SDValue Lo = DAG.getNode(MipsISD::Lo, dl, ValTy, GALo);
  return DAG.getNode(ISD::ADD, dl, ValTy, ResNode, Lo);
}

SDValue MipsTargetLowering::LowerBlockAddress(SDValue Op,
                                              SelectionDAG &DAG) const {
  const BlockAddress *BA = cast<BlockAddressSDNode>(Op)->getBlockAddress();
  // FIXME there isn't actually debug info here
  DebugLoc dl = Op.getDebugLoc();

  if (getTargetMachine().getRelocationModel() != Reloc::PIC_ && !IsN64) {
    // %hi/%lo relocation
    SDValue BAHi = DAG.getBlockAddress(BA, MVT::i32, true, MipsII::MO_ABS_HI);
    SDValue BALo = DAG.getBlockAddress(BA, MVT::i32, true, MipsII::MO_ABS_LO);
    SDValue Hi = DAG.getNode(MipsISD::Hi, dl, MVT::i32, BAHi);
    SDValue Lo = DAG.getNode(MipsISD::Lo, dl, MVT::i32, BALo);
    return DAG.getNode(ISD::ADD, dl, MVT::i32, Hi, Lo);
  }

  EVT ValTy = Op.getValueType();
  unsigned GOTFlag = IsN64 ? MipsII::MO_GOT_PAGE : MipsII::MO_GOT;
  unsigned OFSTFlag = IsN64 ? MipsII::MO_GOT_OFST : MipsII::MO_ABS_LO;
  SDValue BAGOTOffset = DAG.getBlockAddress(BA, ValTy, true, GOTFlag);
  BAGOTOffset = DAG.getNode(MipsISD::Wrapper, dl, ValTy,
                            GetGlobalReg(DAG, ValTy), BAGOTOffset);
  SDValue BALOOffset = DAG.getBlockAddress(BA, ValTy, true, OFSTFlag);
  SDValue Load = DAG.getLoad(ValTy, dl, DAG.getEntryNode(), BAGOTOffset,
                             MachinePointerInfo(), false, false, false, 0);
  SDValue Lo = DAG.getNode(MipsISD::Lo, dl, ValTy, BALOOffset);
  return DAG.getNode(ISD::ADD, dl, ValTy, Load, Lo);
}

SDValue MipsTargetLowering::
LowerGlobalTLSAddress(SDValue Op, SelectionDAG &DAG) const
{
  // If the relocation model is PIC, use the General Dynamic TLS Model or
  // Local Dynamic TLS model, otherwise use the Initial Exec or
  // Local Exec TLS Model.

  GlobalAddressSDNode *GA = cast<GlobalAddressSDNode>(Op);
  DebugLoc dl = GA->getDebugLoc();
  const GlobalValue *GV = GA->getGlobal();
  EVT PtrVT = getPointerTy();

  if (getTargetMachine().getRelocationModel() == Reloc::PIC_) {
    // General Dynamic TLS Model
    bool LocalDynamic = GV->hasInternalLinkage();
    unsigned Flag = LocalDynamic ? MipsII::MO_TLSLDM :MipsII::MO_TLSGD;
    SDValue TGA = DAG.getTargetGlobalAddress(GV, dl, PtrVT, 0, Flag);
    SDValue Argument = DAG.getNode(MipsISD::Wrapper, dl, PtrVT,
                                   GetGlobalReg(DAG, PtrVT), TGA);
    unsigned PtrSize = PtrVT.getSizeInBits();
    IntegerType *PtrTy = Type::getIntNTy(*DAG.getContext(), PtrSize);

    SDValue TlsGetAddr = DAG.getExternalSymbol("__tls_get_addr", PtrVT);

    ArgListTy Args;
    ArgListEntry Entry;
    Entry.Node = Argument;
    Entry.Ty = PtrTy;
    Args.push_back(Entry);

    std::pair<SDValue, SDValue> CallResult =
      LowerCallTo(DAG.getEntryNode(), PtrTy,
                  false, false, false, false, 0, CallingConv::C,
                  /*isTailCall=*/false, /*doesNotRet=*/false,
                  /*isReturnValueUsed=*/true,
                  TlsGetAddr, Args, DAG, dl);

    SDValue Ret = CallResult.first;

    if (!LocalDynamic)
      return Ret;

    SDValue TGAHi = DAG.getTargetGlobalAddress(GV, dl, PtrVT, 0,
                                               MipsII::MO_DTPREL_HI);
    SDValue Hi = DAG.getNode(MipsISD::Hi, dl, PtrVT, TGAHi);
    SDValue TGALo = DAG.getTargetGlobalAddress(GV, dl, PtrVT, 0,
                                               MipsII::MO_DTPREL_LO);
    SDValue Lo = DAG.getNode(MipsISD::Lo, dl, PtrVT, TGALo);
    SDValue Add = DAG.getNode(ISD::ADD, dl, PtrVT, Hi, Ret);
    return DAG.getNode(ISD::ADD, dl, PtrVT, Add, Lo);
  }

  SDValue Offset;
  if (GV->isDeclaration()) {
    // Initial Exec TLS Model
    SDValue TGA = DAG.getTargetGlobalAddress(GV, dl, PtrVT, 0,
                                             MipsII::MO_GOTTPREL);
    TGA = DAG.getNode(MipsISD::Wrapper, dl, PtrVT, GetGlobalReg(DAG, PtrVT),
                      TGA);
    Offset = DAG.getLoad(PtrVT, dl,
                         DAG.getEntryNode(), TGA, MachinePointerInfo(),
                         false, false, false, 0);
  } else {
    // Local Exec TLS Model
    SDValue TGAHi = DAG.getTargetGlobalAddress(GV, dl, PtrVT, 0,
                                               MipsII::MO_TPREL_HI);
    SDValue TGALo = DAG.getTargetGlobalAddress(GV, dl, PtrVT, 0,
                                               MipsII::MO_TPREL_LO);
    SDValue Hi = DAG.getNode(MipsISD::Hi, dl, PtrVT, TGAHi);
    SDValue Lo = DAG.getNode(MipsISD::Lo, dl, PtrVT, TGALo);
    Offset = DAG.getNode(ISD::ADD, dl, PtrVT, Hi, Lo);
  }

  SDValue ThreadPointer = DAG.getNode(MipsISD::ThreadPointer, dl, PtrVT);
  return DAG.getNode(ISD::ADD, dl, PtrVT, ThreadPointer, Offset);
}

SDValue MipsTargetLowering::
LowerJumpTable(SDValue Op, SelectionDAG &DAG) const
{
  SDValue HiPart, JTI, JTILo;
  // FIXME there isn't actually debug info here
  DebugLoc dl = Op.getDebugLoc();
  bool IsPIC = getTargetMachine().getRelocationModel() == Reloc::PIC_;
  EVT PtrVT = Op.getValueType();
  JumpTableSDNode *JT = cast<JumpTableSDNode>(Op);

  if (!IsPIC && !IsN64) {
    JTI = DAG.getTargetJumpTable(JT->getIndex(), PtrVT, MipsII::MO_ABS_HI);
    HiPart = DAG.getNode(MipsISD::Hi, dl, PtrVT, JTI);
    JTILo = DAG.getTargetJumpTable(JT->getIndex(), PtrVT, MipsII::MO_ABS_LO);
  } else {// Emit Load from Global Pointer
    unsigned GOTFlag = IsN64 ? MipsII::MO_GOT_PAGE : MipsII::MO_GOT;
    unsigned OfstFlag = IsN64 ? MipsII::MO_GOT_OFST : MipsII::MO_ABS_LO;
    JTI = DAG.getTargetJumpTable(JT->getIndex(), PtrVT, GOTFlag);
    JTI = DAG.getNode(MipsISD::Wrapper, dl, PtrVT, GetGlobalReg(DAG, PtrVT),
                      JTI);
    HiPart = DAG.getLoad(PtrVT, dl, DAG.getEntryNode(), JTI,
                         MachinePointerInfo(), false, false, false, 0);
    JTILo = DAG.getTargetJumpTable(JT->getIndex(), PtrVT, OfstFlag);
  }

  SDValue Lo = DAG.getNode(MipsISD::Lo, dl, PtrVT, JTILo);
  return DAG.getNode(ISD::ADD, dl, PtrVT, HiPart, Lo);
}

SDValue MipsTargetLowering::
LowerConstantPool(SDValue Op, SelectionDAG &DAG) const
{
  SDValue ResNode;
  ConstantPoolSDNode *N = cast<ConstantPoolSDNode>(Op);
  const Constant *C = N->getConstVal();
  // FIXME there isn't actually debug info here
  DebugLoc dl = Op.getDebugLoc();

  // gp_rel relocation
  // FIXME: we should reference the constant pool using small data sections,
  // but the asm printer currently doesn't support this feature without
  // hacking it. This feature should come soon so we can uncomment the
  // stuff below.
  //if (IsInSmallSection(C->getType())) {
  //  SDValue GPRelNode = DAG.getNode(MipsISD::GPRel, MVT::i32, CP);
  //  SDValue GOT = DAG.getGLOBAL_OFFSET_TABLE(MVT::i32);
  //  ResNode = DAG.getNode(ISD::ADD, MVT::i32, GOT, GPRelNode);

  if (getTargetMachine().getRelocationModel() != Reloc::PIC_ && !IsN64) {
    SDValue CPHi = DAG.getTargetConstantPool(C, MVT::i32, N->getAlignment(),
                                             N->getOffset(), MipsII::MO_ABS_HI);
    SDValue CPLo = DAG.getTargetConstantPool(C, MVT::i32, N->getAlignment(),
                                             N->getOffset(), MipsII::MO_ABS_LO);
    SDValue HiPart = DAG.getNode(MipsISD::Hi, dl, MVT::i32, CPHi);
    SDValue Lo = DAG.getNode(MipsISD::Lo, dl, MVT::i32, CPLo);
    ResNode = DAG.getNode(ISD::ADD, dl, MVT::i32, HiPart, Lo);
  } else {
    EVT ValTy = Op.getValueType();
    unsigned GOTFlag = IsN64 ? MipsII::MO_GOT_PAGE : MipsII::MO_GOT;
    unsigned OFSTFlag = IsN64 ? MipsII::MO_GOT_OFST : MipsII::MO_ABS_LO;
    SDValue CP = DAG.getTargetConstantPool(C, ValTy, N->getAlignment(),
                                           N->getOffset(), GOTFlag);
    CP = DAG.getNode(MipsISD::Wrapper, dl, ValTy, GetGlobalReg(DAG, ValTy), CP);
    SDValue Load = DAG.getLoad(ValTy, dl, DAG.getEntryNode(), CP,
                               MachinePointerInfo::getConstantPool(), false,
                               false, false, 0);
    SDValue CPLo = DAG.getTargetConstantPool(C, ValTy, N->getAlignment(),
                                             N->getOffset(), OFSTFlag);
    SDValue Lo = DAG.getNode(MipsISD::Lo, dl, ValTy, CPLo);
    ResNode = DAG.getNode(ISD::ADD, dl, ValTy, Load, Lo);
  }

  return ResNode;
}

SDValue MipsTargetLowering::LowerVASTART(SDValue Op, SelectionDAG &DAG) const {
  MachineFunction &MF = DAG.getMachineFunction();
  MipsFunctionInfo *FuncInfo = MF.getInfo<MipsFunctionInfo>();

  DebugLoc dl = Op.getDebugLoc();
  SDValue FI = DAG.getFrameIndex(FuncInfo->getVarArgsFrameIndex(),
                                 getPointerTy());

  // 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), false, false, 0);
}

// Called if the size of integer registers is large enough to hold the whole
// floating point number.
static SDValue LowerFCOPYSIGNLargeIntReg(SDValue Op, SelectionDAG &DAG) {
  // FIXME: Use ext/ins instructions if target architecture is Mips32r2.
  EVT ValTy = Op.getValueType();
  EVT IntValTy = MVT::getIntegerVT(ValTy.getSizeInBits());
  uint64_t Mask = (uint64_t)1 << (ValTy.getSizeInBits() - 1);
  DebugLoc dl = Op.getDebugLoc();
  SDValue Op0 = DAG.getNode(ISD::BITCAST, dl, IntValTy, Op.getOperand(0));
  SDValue Op1 = DAG.getNode(ISD::BITCAST, dl, IntValTy, Op.getOperand(1));
  SDValue And0 = DAG.getNode(ISD::AND, dl, IntValTy, Op0,
                             DAG.getConstant(Mask - 1, IntValTy));
  SDValue And1 = DAG.getNode(ISD::AND, dl, IntValTy, Op1,
                             DAG.getConstant(Mask, IntValTy));
  SDValue Result = DAG.getNode(ISD::OR, dl, IntValTy, And0, And1);
  return DAG.getNode(ISD::BITCAST, dl, ValTy, Result);
}

// Called if the size of integer registers is not large enough to hold the whole
// floating point number (e.g. f64 & 32-bit integer register).
static SDValue
LowerFCOPYSIGNSmallIntReg(SDValue Op, SelectionDAG &DAG, bool isLittle) {
  // FIXME:
  //  Use ext/ins instructions if target architecture is Mips32r2.
  //  Eliminate redundant mfc1 and mtc1 instructions.
  unsigned LoIdx = 0, HiIdx = 1;

  if (!isLittle)
    std::swap(LoIdx, HiIdx);

  DebugLoc dl = Op.getDebugLoc();
  SDValue Word0 = DAG.getNode(MipsISD::ExtractElementF64, dl, MVT::i32,
                              Op.getOperand(0),
                              DAG.getConstant(LoIdx, MVT::i32));
  SDValue Hi0 = DAG.getNode(MipsISD::ExtractElementF64, dl, MVT::i32,
                            Op.getOperand(0), DAG.getConstant(HiIdx, MVT::i32));
  SDValue Hi1 = DAG.getNode(MipsISD::ExtractElementF64, dl, MVT::i32,
                            Op.getOperand(1), DAG.getConstant(HiIdx, MVT::i32));
  SDValue And0 = DAG.getNode(ISD::AND, dl, MVT::i32, Hi0,
                             DAG.getConstant(0x7fffffff, MVT::i32));
  SDValue And1 = DAG.getNode(ISD::AND, dl, MVT::i32, Hi1,
                             DAG.getConstant(0x80000000, MVT::i32));
  SDValue Word1 = DAG.getNode(ISD::OR, dl, MVT::i32, And0, And1);

  if (!isLittle)
    std::swap(Word0, Word1);

  return DAG.getNode(MipsISD::BuildPairF64, dl, MVT::f64, Word0, Word1);
}

SDValue
MipsTargetLowering::LowerFCOPYSIGN(SDValue Op, SelectionDAG &DAG) const {
  EVT Ty = Op.getValueType();

  assert(Ty == MVT::f32 || Ty == MVT::f64);

  if (Ty == MVT::f32 || HasMips64)
    return LowerFCOPYSIGNLargeIntReg(Op, DAG);

  return LowerFCOPYSIGNSmallIntReg(Op, DAG, Subtarget->isLittle());
}

SDValue MipsTargetLowering::
LowerFRAMEADDR(SDValue Op, SelectionDAG &DAG) const {
  // check the depth
  assert((cast<ConstantSDNode>(Op.getOperand(0))->getZExtValue() == 0) &&
         "Frame address can only be determined for current frame.");

  MachineFrameInfo *MFI = DAG.getMachineFunction().getFrameInfo();
  MFI->setFrameAddressIsTaken(true);
  EVT VT = Op.getValueType();
  DebugLoc dl = Op.getDebugLoc();
  SDValue FrameAddr = DAG.getCopyFromReg(DAG.getEntryNode(), dl,
                                         IsN64 ? Mips::FP_64 : Mips::FP, VT);
  return FrameAddr;
}

// TODO: set SType according to the desired memory barrier behavior.
SDValue
MipsTargetLowering::LowerMEMBARRIER(SDValue Op, SelectionDAG& DAG) const {
  unsigned SType = 0;
  DebugLoc dl = Op.getDebugLoc();
  return DAG.getNode(MipsISD::Sync, dl, MVT::Other, Op.getOperand(0),
                     DAG.getConstant(SType, MVT::i32));
}

SDValue MipsTargetLowering::LowerATOMIC_FENCE(SDValue Op,
                                              SelectionDAG& DAG) const {
  // FIXME: Need pseudo-fence for 'singlethread' fences
  // FIXME: Set SType for weaker fences where supported/appropriate.
  unsigned SType = 0;
  DebugLoc dl = Op.getDebugLoc();
  return DAG.getNode(MipsISD::Sync, dl, MVT::Other, Op.getOperand(0),
                     DAG.getConstant(SType, MVT::i32));
}

//===----------------------------------------------------------------------===//
//                      Calling Convention Implementation
//===----------------------------------------------------------------------===//

//===----------------------------------------------------------------------===//
// TODO: Implement a generic logic using tblgen that can support this.
// Mips O32 ABI rules:
// ---
// i32 - Passed in A0, A1, A2, A3 and stack
// f32 - Only passed in f32 registers if no int reg has been used yet to hold
//       an argument. Otherwise, passed in A1, A2, A3 and stack.
// f64 - Only passed in two aliased f32 registers if no int reg has been used
//       yet to hold an argument. Otherwise, use A2, A3 and stack. If A1 is
//       not used, it must be shadowed. If only A3 is avaiable, shadow it and
//       go to stack.
//
//  For vararg functions, all arguments are passed in A0, A1, A2, A3 and stack.
//===----------------------------------------------------------------------===//

static bool CC_MipsO32(unsigned ValNo, MVT ValVT,
                       MVT LocVT, CCValAssign::LocInfo LocInfo,
                       ISD::ArgFlagsTy ArgFlags, CCState &State) {

  static const unsigned IntRegsSize=4, FloatRegsSize=2;

  static const uint16_t IntRegs[] = {
      Mips::A0, Mips::A1, Mips::A2, Mips::A3
  };
  static const uint16_t F32Regs[] = {
      Mips::F12, Mips::F14
  };
  static const uint16_t F64Regs[] = {
      Mips::D6, Mips::D7
  };

  // ByVal Args
  if (ArgFlags.isByVal()) {
    State.HandleByVal(ValNo, ValVT, LocVT, LocInfo,
                      1 /*MinSize*/, 4 /*MinAlign*/, ArgFlags);
    unsigned NextReg = (State.getNextStackOffset() + 3) / 4;
    for (unsigned r = State.getFirstUnallocated(IntRegs, IntRegsSize);
         r < std::min(IntRegsSize, NextReg); ++r)
      State.AllocateReg(IntRegs[r]);
    return false;
  }

  // Promote i8 and i16
  if (LocVT == MVT::i8 || LocVT == MVT::i16) {
    LocVT = MVT::i32;
    if (ArgFlags.isSExt())
      LocInfo = CCValAssign::SExt;
    else if (ArgFlags.isZExt())
      LocInfo = CCValAssign::ZExt;
    else
      LocInfo = CCValAssign::AExt;
  }

  unsigned Reg;

  // f32 and f64 are allocated in A0, A1, A2, A3 when either of the following
  // is true: function is vararg, argument is 3rd or higher, there is previous
  // argument which is not f32 or f64.
  bool AllocateFloatsInIntReg = State.isVarArg() || ValNo > 1
      || State.getFirstUnallocated(F32Regs, FloatRegsSize) != ValNo;
  unsigned OrigAlign = ArgFlags.getOrigAlign();
  bool isI64 = (ValVT == MVT::i32 && OrigAlign == 8);

  if (ValVT == MVT::i32 || (ValVT == MVT::f32 && AllocateFloatsInIntReg)) {
    Reg = State.AllocateReg(IntRegs, IntRegsSize);
    // If this is the first part of an i64 arg,
    // the allocated register must be either A0 or A2.
    if (isI64 && (Reg == Mips::A1 || Reg == Mips::A3))
      Reg = State.AllocateReg(IntRegs, IntRegsSize);
    LocVT = MVT::i32;
  } else if (ValVT == MVT::f64 && AllocateFloatsInIntReg) {
    // Allocate int register and shadow next int register. If first
    // available register is Mips::A1 or Mips::A3, shadow it too.
    Reg = State.AllocateReg(IntRegs, IntRegsSize);
    if (Reg == Mips::A1 || Reg == Mips::A3)
      Reg = State.AllocateReg(IntRegs, IntRegsSize);
    State.AllocateReg(IntRegs, IntRegsSize);
    LocVT = MVT::i32;
  } else if (ValVT.isFloatingPoint() && !AllocateFloatsInIntReg) {
    // we are guaranteed to find an available float register
    if (ValVT == MVT::f32) {
      Reg = State.AllocateReg(F32Regs, FloatRegsSize);
      // Shadow int register
      State.AllocateReg(IntRegs, IntRegsSize);
    } else {
      Reg = State.AllocateReg(F64Regs, FloatRegsSize);
      // Shadow int registers
      unsigned Reg2 = State.AllocateReg(IntRegs, IntRegsSize);
      if (Reg2 == Mips::A1 || Reg2 == Mips::A3)
        State.AllocateReg(IntRegs, IntRegsSize);
      State.AllocateReg(IntRegs, IntRegsSize);
    }
  } else
    llvm_unreachable("Cannot handle this ValVT.");

  unsigned SizeInBytes = ValVT.getSizeInBits() >> 3;
  unsigned Offset = State.AllocateStack(SizeInBytes, OrigAlign);

  if (!Reg)
    State.addLoc(CCValAssign::getMem(ValNo, ValVT, Offset, LocVT, LocInfo));
  else
    State.addLoc(CCValAssign::getReg(ValNo, ValVT, Reg, LocVT, LocInfo));

  return false; // CC must always match
}

static const uint16_t Mips64IntRegs[8] =
  {Mips::A0_64, Mips::A1_64, Mips::A2_64, Mips::A3_64,
   Mips::T0_64, Mips::T1_64, Mips::T2_64, Mips::T3_64};
static const uint16_t Mips64DPRegs[8] =
  {Mips::D12_64, Mips::D13_64, Mips::D14_64, Mips::D15_64,
   Mips::D16_64, Mips::D17_64, Mips::D18_64, Mips::D19_64};

static bool CC_Mips64Byval(unsigned ValNo, MVT ValVT, MVT LocVT,
                           CCValAssign::LocInfo LocInfo,
                           ISD::ArgFlagsTy ArgFlags, CCState &State) {
  unsigned Align = std::max(ArgFlags.getByValAlign(), (unsigned)8);
  unsigned Size  = (ArgFlags.getByValSize() + 7) / 8 * 8;
  unsigned FirstIdx = State.getFirstUnallocated(Mips64IntRegs, 8);

  assert(Align <= 16 && "Cannot handle alignments larger than 16.");

  // If byval is 16-byte aligned, the first arg register must be even.
  if ((Align == 16) && (FirstIdx % 2)) {
    State.AllocateReg(Mips64IntRegs[FirstIdx], Mips64DPRegs[FirstIdx]);
    ++FirstIdx;
  }

  // Mark the registers allocated.
  for (unsigned I = FirstIdx; Size && (I < 8); Size -= 8, ++I)
    State.AllocateReg(Mips64IntRegs[I], Mips64DPRegs[I]);

  // Allocate space on caller's stack.
  unsigned Offset = State.AllocateStack(Size, Align);

  if (FirstIdx < 8)
    State.addLoc(CCValAssign::getReg(ValNo, ValVT, Mips64IntRegs[FirstIdx],
                                     LocVT, LocInfo));
  else
    State.addLoc(CCValAssign::getMem(ValNo, ValVT, Offset, LocVT, LocInfo));

  return true;
}

#include "MipsGenCallingConv.inc"

static void
AnalyzeMips64CallOperands(CCState &CCInfo,
                          const SmallVectorImpl<ISD::OutputArg> &Outs) {
  unsigned NumOps = Outs.size();
  for (unsigned i = 0; i != NumOps; ++i) {
    MVT ArgVT = Outs[i].VT;
    ISD::ArgFlagsTy ArgFlags = Outs[i].Flags;
    bool R;

    if (Outs[i].IsFixed)
      R = CC_MipsN(i, ArgVT, ArgVT, CCValAssign::Full, ArgFlags, CCInfo);
    else
      R = CC_MipsN_VarArg(i, ArgVT, ArgVT, CCValAssign::Full, ArgFlags, CCInfo);

    if (R) {
#ifndef NDEBUG
      dbgs() << "Call operand #" << i << " has unhandled type "
             << EVT(ArgVT).getEVTString();
#endif
      llvm_unreachable(0);
    }
  }
}

//===----------------------------------------------------------------------===//
//                  Call Calling Convention Implementation
//===----------------------------------------------------------------------===//

static const unsigned O32IntRegsSize = 4;

static const uint16_t O32IntRegs[] = {
  Mips::A0, Mips::A1, Mips::A2, Mips::A3
};

// Return next O32 integer argument register.
static unsigned getNextIntArgReg(unsigned Reg) {
  assert((Reg == Mips::A0) || (Reg == Mips::A2));
  return (Reg == Mips::A0) ? Mips::A1 : Mips::A3;
}

// Write ByVal Arg to arg registers and stack.
static void
WriteByValArg(SDValue& ByValChain, SDValue Chain, DebugLoc dl,
              SmallVector<std::pair<unsigned, SDValue>, 16>& RegsToPass,
              SmallVector<SDValue, 8>& MemOpChains, int& LastFI,
              MachineFrameInfo *MFI, SelectionDAG &DAG, SDValue Arg,
              const CCValAssign &VA, const ISD::ArgFlagsTy& Flags,
              MVT PtrType, bool isLittle) {
  unsigned LocMemOffset = VA.getLocMemOffset();
  unsigned Offset = 0;
  uint32_t RemainingSize = Flags.getByValSize();
  unsigned ByValAlign = Flags.getByValAlign();

  // Copy the first 4 words of byval arg to registers A0 - A3.
  // FIXME: Use a stricter alignment if it enables better optimization in passes
  //        run later.
  for (; RemainingSize >= 4 && LocMemOffset < 4 * 4;
       Offset += 4, RemainingSize -= 4, LocMemOffset += 4) {
    SDValue LoadPtr = DAG.getNode(ISD::ADD, dl, MVT::i32, Arg,
                                  DAG.getConstant(Offset, MVT::i32));
    SDValue LoadVal = DAG.getLoad(MVT::i32, dl, Chain, LoadPtr,
                                  MachinePointerInfo(), false, false, false,
                                  std::min(ByValAlign, (unsigned )4));
    MemOpChains.push_back(LoadVal.getValue(1));
    unsigned DstReg = O32IntRegs[LocMemOffset / 4];
    RegsToPass.push_back(std::make_pair(DstReg, LoadVal));
  }

  if (RemainingSize == 0)
    return;

  // If there still is a register available for argument passing, write the
  // remaining part of the structure to it using subword loads and shifts.
  if (LocMemOffset < 4 * 4) {
    assert(RemainingSize <= 3 && RemainingSize >= 1 &&
           "There must be one to three bytes remaining.");
    unsigned LoadSize = (RemainingSize == 3 ? 2 : RemainingSize);
    SDValue LoadPtr = DAG.getNode(ISD::ADD, dl, MVT::i32, Arg,
                                  DAG.getConstant(Offset, MVT::i32));
    unsigned Alignment = std::min(ByValAlign, (unsigned )4);
    SDValue LoadVal = DAG.getExtLoad(ISD::ZEXTLOAD, dl, MVT::i32, Chain,
                                     LoadPtr, MachinePointerInfo(),
                                     MVT::getIntegerVT(LoadSize * 8), false,
                                     false, Alignment);
    MemOpChains.push_back(LoadVal.getValue(1));

    // If target is big endian, shift it to the most significant half-word or
    // byte.
    if (!isLittle)
      LoadVal = DAG.getNode(ISD::SHL, dl, MVT::i32, LoadVal,
                            DAG.getConstant(32 - LoadSize * 8, MVT::i32));

    Offset += LoadSize;
    RemainingSize -= LoadSize;

    // Read second subword if necessary.
    if (RemainingSize != 0)  {
      assert(RemainingSize == 1 && "There must be one byte remaining.");
      LoadPtr = DAG.getNode(ISD::ADD, dl, MVT::i32, Arg,
                            DAG.getConstant(Offset, MVT::i32));
      unsigned Alignment = std::min(ByValAlign, (unsigned )2);
      SDValue Subword = DAG.getExtLoad(ISD::ZEXTLOAD, dl, MVT::i32, Chain,
                                       LoadPtr, MachinePointerInfo(),
                                       MVT::i8, false, false, Alignment);
      MemOpChains.push_back(Subword.getValue(1));
      // Insert the loaded byte to LoadVal.
      // FIXME: Use INS if supported by target.
      unsigned ShiftAmt = isLittle ? 16 : 8;
      SDValue Shift = DAG.getNode(ISD::SHL, dl, MVT::i32, Subword,
                                  DAG.getConstant(ShiftAmt, MVT::i32));
      LoadVal = DAG.getNode(ISD::OR, dl, MVT::i32, LoadVal, Shift);
    }

    unsigned DstReg = O32IntRegs[LocMemOffset / 4];
    RegsToPass.push_back(std::make_pair(DstReg, LoadVal));
    return;
  }

  // Create a fixed object on stack at offset LocMemOffset and copy
  // remaining part of byval arg to it using memcpy.
  SDValue Src = DAG.getNode(ISD::ADD, dl, MVT::i32, Arg,
                            DAG.getConstant(Offset, MVT::i32));
  LastFI = MFI->CreateFixedObject(RemainingSize, LocMemOffset, true);
  SDValue Dst = DAG.getFrameIndex(LastFI, PtrType);
  ByValChain = DAG.getMemcpy(ByValChain, dl, Dst, Src,
                             DAG.getConstant(RemainingSize, MVT::i32),
                             std::min(ByValAlign, (unsigned)4),
                             /*isVolatile=*/false, /*AlwaysInline=*/false,
                             MachinePointerInfo(0), MachinePointerInfo(0));
}

// Copy Mips64 byVal arg to registers and stack.
void static
PassByValArg64(SDValue& ByValChain, SDValue Chain, DebugLoc dl,
               SmallVector<std::pair<unsigned, SDValue>, 16>& RegsToPass,
               SmallVector<SDValue, 8>& MemOpChains, int& LastFI,
               MachineFrameInfo *MFI, SelectionDAG &DAG, SDValue Arg,
               const CCValAssign &VA, const ISD::ArgFlagsTy& Flags,
               EVT PtrTy, bool isLittle) {
  unsigned ByValSize = Flags.getByValSize();
  unsigned Alignment = std::min(Flags.getByValAlign(), (unsigned)8);
  bool IsRegLoc = VA.isRegLoc();
  unsigned Offset = 0; // Offset in # of bytes from the beginning of struct.
  unsigned LocMemOffset = 0;
  unsigned MemCpySize = ByValSize;

  if (!IsRegLoc)
    LocMemOffset = VA.getLocMemOffset();
  else {
    const uint16_t *Reg = std::find(Mips64IntRegs, Mips64IntRegs + 8,
                                    VA.getLocReg());
    const uint16_t *RegEnd = Mips64IntRegs + 8;

    // Copy double words to registers.
    for (; (Reg != RegEnd) && (ByValSize >= Offset + 8); ++Reg, Offset += 8) {
      SDValue LoadPtr = DAG.getNode(ISD::ADD, dl, PtrTy, Arg,
                                    DAG.getConstant(Offset, PtrTy));
      SDValue LoadVal = DAG.getLoad(MVT::i64, dl, Chain, LoadPtr,
                                    MachinePointerInfo(), false, false, false,
                                    Alignment);
      MemOpChains.push_back(LoadVal.getValue(1));
      RegsToPass.push_back(std::make_pair(*Reg, LoadVal));
    }

    // Return if the struct has been fully copied.
    if (!(MemCpySize = ByValSize - Offset))
      return;

    // If there is an argument register available, copy the remainder of the
    // byval argument with sub-doubleword loads and shifts.
    if (Reg != RegEnd) {
      assert((ByValSize < Offset + 8) &&
             "Size of the remainder should be smaller than 8-byte.");
      SDValue Val;
      for (unsigned LoadSize = 4; Offset < ByValSize; LoadSize /= 2) {
        unsigned RemSize = ByValSize - Offset;

        if (RemSize < LoadSize)
          continue;

        SDValue LoadPtr = DAG.getNode(ISD::ADD, dl, PtrTy, Arg,
                                      DAG.getConstant(Offset, PtrTy));
        SDValue LoadVal =
          DAG.getExtLoad(ISD::ZEXTLOAD, dl, MVT::i64, Chain, LoadPtr,
                         MachinePointerInfo(), MVT::getIntegerVT(LoadSize * 8),
                         false, false, Alignment);
        MemOpChains.push_back(LoadVal.getValue(1));

        // Offset in number of bits from double word boundary.
        unsigned OffsetDW = (Offset % 8) * 8;
        unsigned Shamt = isLittle ? OffsetDW : 64 - (OffsetDW + LoadSize * 8);
        SDValue Shift = DAG.getNode(ISD::SHL, dl, MVT::i64, LoadVal,
                                    DAG.getConstant(Shamt, MVT::i32));

        Val = Val.getNode() ? DAG.getNode(ISD::OR, dl, MVT::i64, Val, Shift) :
                              Shift;
        Offset += LoadSize;
        Alignment = std::min(Alignment, LoadSize);
      }

      RegsToPass.push_back(std::make_pair(*Reg, Val));
      return;
    }
  }

  assert(MemCpySize && "MemCpySize must not be zero.");

  // Create a fixed object on stack at offset LocMemOffset and copy
  // remainder of byval arg to it with memcpy.
  SDValue Src = DAG.getNode(ISD::ADD, dl, PtrTy, Arg,
                            DAG.getConstant(Offset, PtrTy));
  LastFI = MFI->CreateFixedObject(MemCpySize, LocMemOffset, true);
  SDValue Dst = DAG.getFrameIndex(LastFI, PtrTy);
  ByValChain = DAG.getMemcpy(ByValChain, dl, Dst, Src,
                             DAG.getConstant(MemCpySize, PtrTy), Alignment,
                             /*isVolatile=*/false, /*AlwaysInline=*/false,
                             MachinePointerInfo(0), MachinePointerInfo(0));
}

/// LowerCall - functions arguments are copied from virtual regs to
/// (physical regs)/(stack frame), CALLSEQ_START and CALLSEQ_END are emitted.
/// TODO: isTailCall.
SDValue
MipsTargetLowering::LowerCall(SDValue InChain, SDValue Callee,
                              CallingConv::ID CallConv, bool isVarArg,
                              bool doesNotRet, bool &isTailCall,
                              const SmallVectorImpl<ISD::OutputArg> &Outs,
                              const SmallVectorImpl<SDValue> &OutVals,
                              const SmallVectorImpl<ISD::InputArg> &Ins,
                              DebugLoc dl, SelectionDAG &DAG,
                              SmallVectorImpl<SDValue> &InVals) const {
  // MIPs target does not yet support tail call optimization.
  isTailCall = false;

  MachineFunction &MF = DAG.getMachineFunction();
  MachineFrameInfo *MFI = MF.getFrameInfo();
  const TargetFrameLowering *TFL = MF.getTarget().getFrameLowering();
  bool IsPIC = getTargetMachine().getRelocationModel() == Reloc::PIC_;
  MipsFunctionInfo *MipsFI = MF.getInfo<MipsFunctionInfo>();

  // Analyze operands of the call, assigning locations to each operand.
  SmallVector<CCValAssign, 16> ArgLocs;
  CCState CCInfo(CallConv, isVarArg, DAG.getMachineFunction(),
                 getTargetMachine(), ArgLocs, *DAG.getContext());

  if (IsO32)
    CCInfo.AnalyzeCallOperands(Outs, CC_MipsO32);
  else if (HasMips64)
    AnalyzeMips64CallOperands(CCInfo, Outs);
  else
    CCInfo.AnalyzeCallOperands(Outs, CC_Mips);

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

  // Chain is the output chain of the last Load/Store or CopyToReg node.
  // ByValChain is the output chain of the last Memcpy node created for copying
  // byval arguments to the stack.
  SDValue Chain, CallSeqStart, ByValChain;
  SDValue NextStackOffsetVal = DAG.getIntPtrConstant(NextStackOffset, true);
  Chain = CallSeqStart = DAG.getCALLSEQ_START(InChain, NextStackOffsetVal);
  ByValChain = InChain;

  // If this is the first call, create a stack frame object that points to
  // a location to which .cprestore saves $gp.
  if (IsO32 && IsPIC && MipsFI->globalBaseRegFixed() && !MipsFI->getGPFI())
    MipsFI->setGPFI(MFI->CreateFixedObject(4, 0, true));

  // Get the frame index of the stack frame object that points to the location
  // of dynamically allocated area on the stack.
  int DynAllocFI = MipsFI->getDynAllocFI();

  // Update size of the maximum argument space.
  // For O32, a minimum of four words (16 bytes) of argument space is
  // allocated.
  if (IsO32)
    NextStackOffset = std::max(NextStackOffset, (unsigned)16);

  unsigned MaxCallFrameSize = MipsFI->getMaxCallFrameSize();

  if (MaxCallFrameSize < NextStackOffset) {
    MipsFI->setMaxCallFrameSize(NextStackOffset);

    // Set the offsets relative to $sp of the $gp restore slot and dynamically
    // allocated stack space. These offsets must be aligned to a boundary
    // determined by the stack alignment of the ABI.
    unsigned StackAlignment = TFL->getStackAlignment();
    NextStackOffset = (NextStackOffset + StackAlignment - 1) /
                      StackAlignment * StackAlignment;

    if (MipsFI->needGPSaveRestore())
      MFI->setObjectOffset(MipsFI->getGPFI(), NextStackOffset);

    MFI->setObjectOffset(DynAllocFI, NextStackOffset);
  }

  // With EABI is it possible to have 16 args on registers.
  SmallVector<std::pair<unsigned, SDValue>, 16> RegsToPass;
  SmallVector<SDValue, 8> MemOpChains;

  int FirstFI = -MFI->getNumFixedObjects() - 1, LastFI = 0;

  // Walk the register/memloc assignments, inserting copies/loads.
  for (unsigned i = 0, e = ArgLocs.size(); i != e; ++i) {
    SDValue Arg = OutVals[i];
    CCValAssign &VA = ArgLocs[i];
    MVT ValVT = VA.getValVT(), LocVT = VA.getLocVT();
    ISD::ArgFlagsTy Flags = Outs[i].Flags;

    // ByVal Arg.
    if (Flags.isByVal()) {
      assert(Flags.getByValSize() &&
             "ByVal args of size 0 should have been ignored by front-end.");
      if (IsO32)
        WriteByValArg(ByValChain, Chain, dl, RegsToPass, MemOpChains, LastFI,
                      MFI, DAG, Arg, VA, Flags, getPointerTy(),
                      Subtarget->isLittle());
      else
        PassByValArg64(ByValChain, Chain, dl, RegsToPass, MemOpChains, LastFI,
                       MFI, DAG, Arg, VA, Flags, getPointerTy(),
                       Subtarget->isLittle());
      continue;
    }

    // Promote the value if needed.
    switch (VA.getLocInfo()) {
    default: llvm_unreachable("Unknown loc info!");
    case CCValAssign::Full:
      if (VA.isRegLoc()) {
        if ((ValVT == MVT::f32 && LocVT == MVT::i32) ||
            (ValVT == MVT::f64 && LocVT == MVT::i64))
          Arg = DAG.getNode(ISD::BITCAST, dl, LocVT, Arg);
        else if (ValVT == MVT::f64 && LocVT == MVT::i32) {
          SDValue Lo = DAG.getNode(MipsISD::ExtractElementF64, dl, MVT::i32,
                                   Arg, DAG.getConstant(0, MVT::i32));
          SDValue Hi = DAG.getNode(MipsISD::ExtractElementF64, dl, MVT::i32,
                                   Arg, DAG.getConstant(1, MVT::i32));
          if (!Subtarget->isLittle())
            std::swap(Lo, Hi);
          unsigned LocRegLo = VA.getLocReg();
          unsigned LocRegHigh = getNextIntArgReg(LocRegLo);
          RegsToPass.push_back(std::make_pair(LocRegLo, Lo));
          RegsToPass.push_back(std::make_pair(LocRegHigh, Hi));
          continue;
        }
      }
      break;
    case CCValAssign::SExt:
      Arg = DAG.getNode(ISD::SIGN_EXTEND, dl, LocVT, Arg);
      break;
    case CCValAssign::ZExt:
      Arg = DAG.getNode(ISD::ZERO_EXTEND, dl, LocVT, Arg);
      break;
    case CCValAssign::AExt:
      Arg = DAG.getNode(ISD::ANY_EXTEND, dl, LocVT, Arg);
      break;
    }

    // Arguments that can be passed on register must be kept at
    // RegsToPass vector
    if (VA.isRegLoc()) {
      RegsToPass.push_back(std::make_pair(VA.getLocReg(), Arg));
      continue;
    }

    // Register can't get to this point...
    assert(VA.isMemLoc());

    // Create the frame index object for this incoming parameter
    LastFI = MFI->CreateFixedObject(ValVT.getSizeInBits()/8,
                                    VA.getLocMemOffset(), true);
    SDValue PtrOff = DAG.getFrameIndex(LastFI, getPointerTy());

    // emit ISD::STORE whichs stores the
    // parameter value to a stack Location
    MemOpChains.push_back(DAG.getStore(Chain, dl, Arg, PtrOff,
                                       MachinePointerInfo(), false, false, 0));
  }

  // Extend range of indices of frame objects for outgoing arguments that were
  // created during this function call. Skip this step if no such objects were
  // created.
  if (LastFI)
    MipsFI->extendOutArgFIRange(FirstFI, LastFI);

  // If a memcpy has been created to copy a byval arg to a stack, replace the
  // chain input of CallSeqStart with ByValChain.
  if (InChain != ByValChain)
    DAG.UpdateNodeOperands(CallSeqStart.getNode(), ByValChain,
                           NextStackOffsetVal);

  // Transform all store nodes into one single node because all store
  // nodes are independent of each other.
  if (!MemOpChains.empty())
    Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other,
                        &MemOpChains[0], MemOpChains.size());

  // If the callee is a GlobalAddress/ExternalSymbol node (quite common, every
  // direct call is) turn it into a TargetGlobalAddress/TargetExternalSymbol
  // node so that legalize doesn't hack it.
  unsigned char OpFlag;
  bool IsPICCall = (IsN64 || IsPIC); // true if calls are translated to jalr $25
  bool GlobalOrExternal = false;
  SDValue CalleeLo;

  if (GlobalAddressSDNode *G = dyn_cast<GlobalAddressSDNode>(Callee)) {
    if (IsPICCall && G->getGlobal()->hasInternalLinkage()) {
      OpFlag = IsO32 ? MipsII::MO_GOT : MipsII::MO_GOT_PAGE;
      unsigned char LoFlag = IsO32 ? MipsII::MO_ABS_LO : MipsII::MO_GOT_OFST;
      Callee = DAG.getTargetGlobalAddress(G->getGlobal(), dl, getPointerTy(), 0,
                                          OpFlag);
      CalleeLo = DAG.getTargetGlobalAddress(G->getGlobal(), dl, getPointerTy(),
                                            0, LoFlag);
    } else {
      OpFlag = IsPICCall ? MipsII::MO_GOT_CALL : MipsII::MO_NO_FLAG;
      Callee = DAG.getTargetGlobalAddress(G->getGlobal(), dl,
                                          getPointerTy(), 0, OpFlag);
    }

    GlobalOrExternal = true;
  }
  else if (ExternalSymbolSDNode *S = dyn_cast<ExternalSymbolSDNode>(Callee)) {
    if (IsN64 || (!IsO32 && IsPIC))
      OpFlag = MipsII::MO_GOT_DISP;
    else if (!IsPIC) // !N64 && static
      OpFlag = MipsII::MO_NO_FLAG;
    else // O32 & PIC
      OpFlag = MipsII::MO_GOT_CALL;
    Callee = DAG.getTargetExternalSymbol(S->getSymbol(), getPointerTy(),
                                         OpFlag);
    GlobalOrExternal = true;
  }

  SDValue InFlag;

  // Create nodes that load address of callee and copy it to T9
  if (IsPICCall) {
    if (GlobalOrExternal) {
      // Load callee address
      Callee = DAG.getNode(MipsISD::Wrapper, dl, getPointerTy(),
                           GetGlobalReg(DAG, getPointerTy()), Callee);
      SDValue LoadValue = DAG.getLoad(getPointerTy(), dl, DAG.getEntryNode(),
                                      Callee, MachinePointerInfo::getGOT(),
                                      false, false, false, 0);

      // Use GOT+LO if callee has internal linkage.
      if (CalleeLo.getNode()) {
        SDValue Lo = DAG.getNode(MipsISD::Lo, dl, getPointerTy(), CalleeLo);
        Callee = DAG.getNode(ISD::ADD, dl, getPointerTy(), LoadValue, Lo);
      } else
        Callee = LoadValue;
    }
  }

  // T9 should contain the address of the callee function if
  // -reloction-model=pic or it is an indirect call.
  if (IsPICCall || !GlobalOrExternal) {
    // copy to T9
    unsigned T9Reg = IsN64 ? Mips::T9_64 : Mips::T9;
    Chain = DAG.getCopyToReg(Chain, dl, T9Reg, Callee, SDValue(0, 0));
    InFlag = Chain.getValue(1);
    Callee = DAG.getRegister(T9Reg, getPointerTy());
  }

  // Build a sequence of copy-to-reg nodes chained together with token
  // chain and flag operands which copy the outgoing args into registers.
  // The InFlag in necessary since all emitted instructions must be
  // stuck together.
  for (unsigned i = 0, e = RegsToPass.size(); i != e; ++i) {
    Chain = DAG.getCopyToReg(Chain, dl, RegsToPass[i].first,
                             RegsToPass[i].second, InFlag);
    InFlag = Chain.getValue(1);
  }

  // MipsJmpLink = #chain, #target_address, #opt_in_flags...
  //             = Chain, Callee, Reg#1, Reg#2, ...
  //
  // Returns a chain & a flag for retval copy to use.
  SDVTList NodeTys = DAG.getVTList(MVT::Other, MVT::Glue);
  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 (unsigned i = 0, e = RegsToPass.size(); i != e; ++i)
    Ops.push_back(DAG.getRegister(RegsToPass[i].first,
                                  RegsToPass[i].second.getValueType()));

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

  if (InFlag.getNode())
    Ops.push_back(InFlag);

  Chain  = DAG.getNode(MipsISD::JmpLink, dl, NodeTys, &Ops[0], Ops.size());
  InFlag = Chain.getValue(1);

  // Create the CALLSEQ_END node.
  Chain = DAG.getCALLSEQ_END(Chain,
                             DAG.getIntPtrConstant(NextStackOffset, true),
                             DAG.getIntPtrConstant(0, true), InFlag);
  InFlag = Chain.getValue(1);

  // Handle result values, copying them out of physregs into vregs that we
  // return.
  return LowerCallResult(Chain, InFlag, CallConv, isVarArg,
                         Ins, dl, DAG, InVals);
}

/// LowerCallResult - Lower the result values of a call into the
/// appropriate copies out of appropriate physical registers.
SDValue
MipsTargetLowering::LowerCallResult(SDValue Chain, SDValue InFlag,
                                    CallingConv::ID CallConv, bool isVarArg,
                                    const SmallVectorImpl<ISD::InputArg> &Ins,
                                    DebugLoc dl, SelectionDAG &DAG,
                                    SmallVectorImpl<SDValue> &InVals) const {
  // Assign locations to each value returned by this call.
  SmallVector<CCValAssign, 16> RVLocs;
  CCState CCInfo(CallConv, isVarArg, DAG.getMachineFunction(),
		 getTargetMachine(), RVLocs, *DAG.getContext());

  CCInfo.AnalyzeCallResult(Ins, RetCC_Mips);

  // Copy all of the result registers out of their specified physreg.
  for (unsigned i = 0; i != RVLocs.size(); ++i) {
    Chain = DAG.getCopyFromReg(Chain, dl, RVLocs[i].getLocReg(),
                               RVLocs[i].getValVT(), InFlag).getValue(1);
    InFlag = Chain.getValue(2);
    InVals.push_back(Chain.getValue(0));
  }

  return Chain;
}

//===----------------------------------------------------------------------===//
//             Formal Arguments Calling Convention Implementation
//===----------------------------------------------------------------------===//
static void ReadByValArg(MachineFunction &MF, SDValue Chain, DebugLoc dl,
                         std::vector<SDValue>& OutChains,
                         SelectionDAG &DAG, unsigned NumWords, SDValue FIN,
                         const CCValAssign &VA, const ISD::ArgFlagsTy& Flags,
                         const Argument *FuncArg) {
  unsigned LocMem = VA.getLocMemOffset();
  unsigned FirstWord = LocMem / 4;

  // copy register A0 - A3 to frame object
  for (unsigned i = 0; i < NumWords; ++i) {
    unsigned CurWord = FirstWord + i;
    if (CurWord >= O32IntRegsSize)
      break;

    unsigned SrcReg = O32IntRegs[CurWord];
    unsigned Reg = AddLiveIn(MF, SrcReg, Mips::CPURegsRegisterClass);
    SDValue StorePtr = DAG.getNode(ISD::ADD, dl, MVT::i32, FIN,
                                   DAG.getConstant(i * 4, MVT::i32));
    SDValue Store = DAG.getStore(Chain, dl, DAG.getRegister(Reg, MVT::i32),
                                 StorePtr, MachinePointerInfo(FuncArg, i * 4),
                                 false, false, 0);
    OutChains.push_back(Store);
  }
}

// Create frame object on stack and copy registers used for byval passing to it.
static unsigned
CopyMips64ByValRegs(MachineFunction &MF, SDValue Chain, DebugLoc dl,
                    std::vector<SDValue>& OutChains, SelectionDAG &DAG,
                    const CCValAssign &VA, const ISD::ArgFlagsTy& Flags,
                    MachineFrameInfo *MFI, bool IsRegLoc,
                    SmallVectorImpl<SDValue> &InVals, MipsFunctionInfo *MipsFI,
                    EVT PtrTy, const Argument *FuncArg) {
  const uint16_t *Reg = Mips64IntRegs + 8;
  int FOOffset; // Frame object offset from virtual frame pointer.

  if (IsRegLoc) {
    Reg = std::find(Mips64IntRegs, Mips64IntRegs + 8, VA.getLocReg());
    FOOffset = (Reg - Mips64IntRegs) * 8 - 8 * 8;
  }
  else
    FOOffset = VA.getLocMemOffset();

  // Create frame object.
  unsigned NumRegs = (Flags.getByValSize() + 7) / 8;
  unsigned LastFI = MFI->CreateFixedObject(NumRegs * 8, FOOffset, true);
  SDValue FIN = DAG.getFrameIndex(LastFI, PtrTy);
  InVals.push_back(FIN);

  // Copy arg registers.
  for (unsigned I = 0; (Reg != Mips64IntRegs + 8) && (I < NumRegs);
       ++Reg, ++I) {
    unsigned VReg = AddLiveIn(MF, *Reg, Mips::CPU64RegsRegisterClass);
    SDValue StorePtr = DAG.getNode(ISD::ADD, dl, PtrTy, FIN,
                                   DAG.getConstant(I * 8, PtrTy));
    SDValue Store = DAG.getStore(Chain, dl, DAG.getRegister(VReg, MVT::i64),
                                 StorePtr, MachinePointerInfo(FuncArg, I * 8),
                                 false, false, 0);
    OutChains.push_back(Store);
  }

  return LastFI;
}

/// LowerFormalArguments - transform physical registers into virtual registers
/// and generate load operations for arguments places on the stack.
SDValue
MipsTargetLowering::LowerFormalArguments(SDValue Chain,
                                         CallingConv::ID CallConv,
                                         bool isVarArg,
                                      const SmallVectorImpl<ISD::InputArg> &Ins,
                                         DebugLoc dl, SelectionDAG &DAG,
                                         SmallVectorImpl<SDValue> &InVals)
                                          const {
  MachineFunction &MF = DAG.getMachineFunction();
  MachineFrameInfo *MFI = MF.getFrameInfo();
  MipsFunctionInfo *MipsFI = MF.getInfo<MipsFunctionInfo>();

  MipsFI->setVarArgsFrameIndex(0);

  // 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, DAG.getMachineFunction(),
                 getTargetMachine(), ArgLocs, *DAG.getContext());

  if (IsO32)
    CCInfo.AnalyzeFormalArguments(Ins, CC_MipsO32);
  else
    CCInfo.AnalyzeFormalArguments(Ins, CC_Mips);

  Function::const_arg_iterator FuncArg =
    DAG.getMachineFunction().getFunction()->arg_begin();
  int LastFI = 0;// MipsFI->LastInArgFI is 0 at the entry of this function.

  for (unsigned i = 0, e = ArgLocs.size(); i != e; ++i, ++FuncArg) {
    CCValAssign &VA = ArgLocs[i];
    EVT ValVT = VA.getValVT();
    ISD::ArgFlagsTy Flags = Ins[i].Flags;
    bool IsRegLoc = VA.isRegLoc();

    if (Flags.isByVal()) {
      assert(Flags.getByValSize() &&
             "ByVal args of size 0 should have been ignored by front-end.");
      if (IsO32) {
        unsigned NumWords = (Flags.getByValSize() + 3) / 4;
        LastFI = MFI->CreateFixedObject(NumWords * 4, VA.getLocMemOffset(),
                                        true);
        SDValue FIN = DAG.getFrameIndex(LastFI, getPointerTy());
        InVals.push_back(FIN);
        ReadByValArg(MF, Chain, dl, OutChains, DAG, NumWords, FIN, VA, Flags,
                     &*FuncArg);
      } else // N32/64
        LastFI = CopyMips64ByValRegs(MF, Chain, dl, OutChains, DAG, VA, Flags,
                                     MFI, IsRegLoc, InVals, MipsFI,
                                     getPointerTy(), &*FuncArg);
      continue;
    }

    // Arguments stored on registers
    if (IsRegLoc) {
      EVT RegVT = VA.getLocVT();
      unsigned ArgReg = VA.getLocReg();
      const TargetRegisterClass *RC;

      if (RegVT == MVT::i32)
        RC = Mips::CPURegsRegisterClass;
      else if (RegVT == MVT::i64)
        RC = Mips::CPU64RegsRegisterClass;
      else if (RegVT == MVT::f32)
        RC = Mips::FGR32RegisterClass;
      else if (RegVT == MVT::f64)
        RC = HasMips64 ? Mips::FGR64RegisterClass : Mips::AFGR64RegisterClass;
      else
        llvm_unreachable("RegVT not supported by FormalArguments Lowering");

      // Transform the arguments stored on
      // physical registers into virtual ones
      unsigned Reg = AddLiveIn(DAG.getMachineFunction(), ArgReg, RC);
      SDValue ArgValue = DAG.getCopyFromReg(Chain, dl, Reg, RegVT);

      // If this is an 8 or 16-bit value, it has been passed promoted
      // to 32 bits.  Insert an assert[sz]ext to capture this, then
      // truncate to the right size.
      if (VA.getLocInfo() != CCValAssign::Full) {
        unsigned Opcode = 0;
        if (VA.getLocInfo() == CCValAssign::SExt)
          Opcode = ISD::AssertSext;
        else if (VA.getLocInfo() == CCValAssign::ZExt)
          Opcode = ISD::AssertZext;
        if (Opcode)
          ArgValue = DAG.getNode(Opcode, dl, RegVT, ArgValue,
                                 DAG.getValueType(ValVT));
        ArgValue = DAG.getNode(ISD::TRUNCATE, dl, ValVT, ArgValue);
      }

      // Handle floating point arguments passed in integer registers.
      if ((RegVT == MVT::i32 && ValVT == MVT::f32) ||
          (RegVT == MVT::i64 && ValVT == MVT::f64))
        ArgValue = DAG.getNode(ISD::BITCAST, dl, ValVT, ArgValue);
      else if (IsO32 && RegVT == MVT::i32 && ValVT == MVT::f64) {
        unsigned Reg2 = AddLiveIn(DAG.getMachineFunction(),
                                  getNextIntArgReg(ArgReg), RC);
        SDValue ArgValue2 = DAG.getCopyFromReg(Chain, dl, Reg2, RegVT);
        if (!Subtarget->isLittle())
          std::swap(ArgValue, ArgValue2);
        ArgValue = DAG.getNode(MipsISD::BuildPairF64, dl, MVT::f64,
                               ArgValue, ArgValue2);
      }

      InVals.push_back(ArgValue);
    } else { // VA.isRegLoc()

      // sanity check
      assert(VA.isMemLoc());

      // The stack pointer offset is relative to the caller stack frame.
      LastFI = MFI->CreateFixedObject(ValVT.getSizeInBits()/8,
                                      VA.getLocMemOffset(), true);

      // Create load nodes to retrieve arguments from the stack
      SDValue FIN = DAG.getFrameIndex(LastFI, getPointerTy());
      InVals.push_back(DAG.getLoad(ValVT, dl, Chain, FIN,
                                   MachinePointerInfo::getFixedStack(LastFI),
                                   false, false, false, 0));
    }
  }

  // The mips ABIs for returning structs by value requires that we copy
  // the sret argument into $v0 for the return. Save the argument into
  // a virtual register so that we can access it from the return points.
  if (DAG.getMachineFunction().getFunction()->hasStructRetAttr()) {
    unsigned Reg = MipsFI->getSRetReturnReg();
    if (!Reg) {
      Reg = MF.getRegInfo().createVirtualRegister(getRegClassFor(MVT::i32));
      MipsFI->setSRetReturnReg(Reg);
    }
    SDValue Copy = DAG.getCopyToReg(DAG.getEntryNode(), dl, Reg, InVals[0]);
    Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other, Copy, Chain);
  }

  if (isVarArg) {
    unsigned NumOfRegs = IsO32 ? 4 : 8;
    const uint16_t *ArgRegs = IsO32 ? O32IntRegs : Mips64IntRegs;
    unsigned Idx = CCInfo.getFirstUnallocated(ArgRegs, NumOfRegs);
    int FirstRegSlotOffset = IsO32 ? 0 : -64 ; // offset of $a0's slot.
    const TargetRegisterClass *RC
      = IsO32 ? Mips::CPURegsRegisterClass : Mips::CPU64RegsRegisterClass;
    unsigned RegSize = RC->getSize();
    int RegSlotOffset = FirstRegSlotOffset + Idx * RegSize;

    // Offset of the first variable argument from stack pointer.
    int FirstVaArgOffset;

    if (IsO32 || (Idx == NumOfRegs)) {
      FirstVaArgOffset =
        (CCInfo.getNextStackOffset() + RegSize - 1) / RegSize * RegSize;
    } else
      FirstVaArgOffset = RegSlotOffset;

    // Record the frame index of the first variable argument
    // which is a value necessary to VASTART.
    LastFI = MFI->CreateFixedObject(RegSize, FirstVaArgOffset, true);
    MipsFI->setVarArgsFrameIndex(LastFI);

    // Copy the integer registers that have not been used for argument passing
    // to the argument register save area. For O32, the save area is allocated
    // in the caller's stack frame, while for N32/64, it is allocated in the
    // callee's stack frame.
    for (int StackOffset = RegSlotOffset;
         Idx < NumOfRegs; ++Idx, StackOffset += RegSize) {
      unsigned Reg = AddLiveIn(DAG.getMachineFunction(), ArgRegs[Idx], RC);
      SDValue ArgValue = DAG.getCopyFromReg(Chain, dl, Reg,
                                            MVT::getIntegerVT(RegSize * 8));
      LastFI = MFI->CreateFixedObject(RegSize, StackOffset, true);
      SDValue PtrOff = DAG.getFrameIndex(LastFI, getPointerTy());
      OutChains.push_back(DAG.getStore(Chain, dl, ArgValue, PtrOff,
                                       MachinePointerInfo(), false, false, 0));
    }
  }

  MipsFI->setLastInArgFI(LastFI);

  // All stores are grouped in one node to allow the matching between
  // the size of Ins and InVals. This only happens when on varg functions
  if (!OutChains.empty()) {
    OutChains.push_back(Chain);
    Chain = DAG.getNode(ISD::TokenFactor, dl, MVT::Other,
                        &OutChains[0], OutChains.size());
  }

  return Chain;
}

//===----------------------------------------------------------------------===//
//               Return Value Calling Convention Implementation
//===----------------------------------------------------------------------===//

SDValue
MipsTargetLowering::LowerReturn(SDValue Chain,
                                CallingConv::ID CallConv, bool isVarArg,
                                const SmallVectorImpl<ISD::OutputArg> &Outs,
                                const SmallVectorImpl<SDValue> &OutVals,
                                DebugLoc dl, SelectionDAG &DAG) const {

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

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

  // Analize return values.
  CCInfo.AnalyzeReturn(Outs, RetCC_Mips);

  // If this is the first return lowered for this function, add
  // the regs to the liveout set for the function.
  if (DAG.getMachineFunction().getRegInfo().liveout_empty()) {
    for (unsigned i = 0; i != RVLocs.size(); ++i)
      if (RVLocs[i].isRegLoc())
        DAG.getMachineFunction().getRegInfo().addLiveOut(RVLocs[i].getLocReg());
  }

  SDValue Flag;

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

    Chain = DAG.getCopyToReg(Chain, dl, VA.getLocReg(), OutVals[i], Flag);

    // guarantee that all emitted copies are
    // stuck together, avoiding something bad
    Flag = Chain.getValue(1);
  }

  // The mips ABIs for returning structs by value requires that we copy
  // the sret argument into $v0 for the return. We saved the argument into
  // a virtual register in the entry block, so now we copy the value out
  // and into $v0.
  if (DAG.getMachineFunction().getFunction()->hasStructRetAttr()) {
    MachineFunction &MF      = DAG.getMachineFunction();
    MipsFunctionInfo *MipsFI = MF.getInfo<MipsFunctionInfo>();
    unsigned Reg = MipsFI->getSRetReturnReg();

    if (!Reg)
      llvm_unreachable("sret virtual register not created in the entry block");
    SDValue Val = DAG.getCopyFromReg(Chain, dl, Reg, getPointerTy());

    Chain = DAG.getCopyToReg(Chain, dl, Mips::V0, Val, Flag);
    Flag = Chain.getValue(1);
  }

  // Return on Mips is always a "jr $ra"
  if (Flag.getNode())
    return DAG.getNode(MipsISD::Ret, dl, MVT::Other,
                       Chain, DAG.getRegister(Mips::RA, MVT::i32), Flag);
  else // Return Void
    return DAG.getNode(MipsISD::Ret, dl, MVT::Other,
                       Chain, DAG.getRegister(Mips::RA, MVT::i32));
}

//===----------------------------------------------------------------------===//
//                           Mips Inline Assembly Support
//===----------------------------------------------------------------------===//

/// getConstraintType - Given a constraint letter, return the type of
/// constraint it is for this target.
MipsTargetLowering::ConstraintType MipsTargetLowering::
getConstraintType(const std::string &Constraint) const
{
  // Mips specific constrainy
  // GCC config/mips/constraints.md
  //
  // 'd' : An address register. Equivalent to r
  //       unless generating MIPS16 code.
  // 'y' : Equivalent to r; retained for
  //       backwards compatibility.
  // 'f' : Floating Point registers.
  if (Constraint.size() == 1) {
    switch (Constraint[0]) {
      default : break;
      case 'd':
      case 'y':
      case 'f':
        return C_RegisterClass;
    }
  }
  return TargetLowering::getConstraintType(Constraint);
}

/// Examine constraint type and operand type and determine a weight value.
/// This object must already have been set up with the operand type
/// and the current alternative constraint selected.
TargetLowering::ConstraintWeight
MipsTargetLowering::getSingleConstraintMatchWeight(
    AsmOperandInfo &info, const char *constraint) const {
  ConstraintWeight weight = CW_Invalid;
  Value *CallOperandVal = info.CallOperandVal;
    // If we don't have a value, we can't do a match,
    // but allow it at the lowest weight.
  if (CallOperandVal == NULL)
    return CW_Default;
  Type *type = CallOperandVal->getType();
  // Look at the constraint type.
  switch (*constraint) {
  default:
    weight = TargetLowering::getSingleConstraintMatchWeight(info, constraint);
    break;
  case 'd':
  case 'y':
    if (type->isIntegerTy())
      weight = CW_Register;
    break;
  case 'f':
    if (type->isFloatTy())
      weight = CW_Register;
    break;
  }
  return weight;
}

/// Given a register class constraint, like 'r', if this corresponds directly
/// to an LLVM register class, return a register of 0 and the register class
/// pointer.
std::pair<unsigned, const TargetRegisterClass*> MipsTargetLowering::
getRegForInlineAsmConstraint(const std::string &Constraint, EVT VT) const
{
  if (Constraint.size() == 1) {
    switch (Constraint[0]) {
    case 'd': // Address register. Same as 'r' unless generating MIPS16 code.
    case 'y': // Same as 'r'. Exists for compatibility.
    case 'r':
      if (VT == MVT::i32)
        return std::make_pair(0U, Mips::CPURegsRegisterClass);
      assert(VT == MVT::i64 && "Unexpected type.");
      return std::make_pair(0U, Mips::CPU64RegsRegisterClass);
    case 'f':
      if (VT == MVT::f32)
        return std::make_pair(0U, Mips::FGR32RegisterClass);
      if ((VT == MVT::f64) && (!Subtarget->isSingleFloat())) {
        if (Subtarget->isFP64bit())
          return std::make_pair(0U, Mips::FGR64RegisterClass);
        else
          return std::make_pair(0U, Mips::AFGR64RegisterClass);
      }
    }
  }
  return TargetLowering::getRegForInlineAsmConstraint(Constraint, VT);
}

bool
MipsTargetLowering::isOffsetFoldingLegal(const GlobalAddressSDNode *GA) const {
  // The Mips target isn't yet aware of offsets.
  return false;
}

bool MipsTargetLowering::isFPImmLegal(const APFloat &Imm, EVT VT) const {
  if (VT != MVT::f32 && VT != MVT::f64)
    return false;
  if (Imm.isNegZero())
    return false;
  return Imm.isZero();
}

unsigned MipsTargetLowering::getJumpTableEncoding() const {
  if (IsN64)
    return MachineJumpTableInfo::EK_GPRel64BlockAddress;

  return TargetLowering::getJumpTableEncoding();
}