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
|
From fd37da0d586c331b0008fbfd653a9659344fe76f Mon Sep 17 00:00:00 2001
From: Mike Pall <mike>
Date: Wed, 26 Jul 2017 09:52:19 +0200
Subject: [PATCH] PPC: Add soft-float support to interpreter.
Contributed by Djordje Kovacevic and Stefan Pejic from RT-RK.com.
Sponsored by Cisco Systems, Inc.
---
src/host/buildvm_asm.c | 2 +-
src/lj_arch.h | 29 +-
src/lj_ccall.c | 38 +-
src/lj_ccall.h | 4 +-
src/lj_ccallback.c | 30 +-
src/lj_frame.h | 2 +-
src/lj_ircall.h | 2 +-
src/vm_ppc.dasc | 1249 +++++++++++++++++++++++++++++++++-------
8 files changed, 1101 insertions(+), 255 deletions(-)
--- a/src/host/buildvm_asm.c
+++ b/src/host/buildvm_asm.c
@@ -338,7 +338,7 @@ void emit_asm(BuildCtx *ctx)
#if !(LJ_TARGET_PS3 || LJ_TARGET_PSVITA)
fprintf(ctx->fp, "\t.section .note.GNU-stack,\"\"," ELFASM_PX "progbits\n");
#endif
-#if LJ_TARGET_PPC && !LJ_TARGET_PS3
+#if LJ_TARGET_PPC && !LJ_TARGET_PS3 && !LJ_ABI_SOFTFP
/* Hard-float ABI. */
fprintf(ctx->fp, "\t.gnu_attribute 4, 1\n");
#endif
--- a/src/lj_arch.h
+++ b/src/lj_arch.h
@@ -254,6 +254,29 @@
#else
#define LJ_ARCH_BITS 32
#define LJ_ARCH_NAME "ppc"
+
+#if !defined(LJ_ARCH_HASFPU)
+#if defined(_SOFT_FLOAT) || defined(_SOFT_DOUBLE)
+#define LJ_ARCH_HASFPU 0
+#else
+#define LJ_ARCH_HASFPU 1
+#endif
+#endif
+
+#if !defined(LJ_ABI_SOFTFP)
+#if defined(_SOFT_FLOAT) || defined(_SOFT_DOUBLE)
+#define LJ_ABI_SOFTFP 1
+#else
+#define LJ_ABI_SOFTFP 0
+#endif
+#endif
+#endif
+
+#if LJ_ABI_SOFTFP
+#define LJ_ARCH_NOJIT 1 /* NYI */
+#define LJ_ARCH_NUMMODE LJ_NUMMODE_DUAL
+#else
+#define LJ_ARCH_NUMMODE LJ_NUMMODE_DUAL_SINGLE
#endif
#define LJ_TARGET_PPC 1
@@ -262,7 +285,6 @@
#define LJ_TARGET_MASKSHIFT 0
#define LJ_TARGET_MASKROT 1
#define LJ_TARGET_UNIFYROT 1 /* Want only IR_BROL. */
-#define LJ_ARCH_NUMMODE LJ_NUMMODE_DUAL_SINGLE
#if LJ_TARGET_CONSOLE
#define LJ_ARCH_PPC32ON64 1
@@ -415,16 +437,13 @@
#error "No support for ILP32 model on ARM64"
#endif
#elif LJ_TARGET_PPC
-#if defined(_SOFT_FLOAT) || defined(_SOFT_DOUBLE)
-#error "No support for PowerPC CPUs without double-precision FPU"
-#endif
#if !LJ_ARCH_PPC64 && LJ_ARCH_ENDIAN == LUAJIT_LE
#error "No support for little-endian PPC32"
#endif
#if LJ_ARCH_PPC64
#error "No support for PowerPC 64 bit mode (yet)"
#endif
-#ifdef __NO_FPRS__
+#if defined(__NO_FPRS__) && !defined(_SOFT_FLOAT)
#error "No support for PPC/e500 anymore (use LuaJIT 2.0)"
#endif
#elif LJ_TARGET_MIPS32
--- a/src/lj_ccall.c
+++ b/src/lj_ccall.c
@@ -387,6 +387,24 @@
#define CCALL_HANDLE_COMPLEXARG \
/* Pass complex by value in 2 or 4 GPRs. */
+#define CCALL_HANDLE_GPR \
+ /* Try to pass argument in GPRs. */ \
+ if (n > 1) { \
+ lua_assert(n == 2 || n == 4); /* int64_t or complex (float). */ \
+ if (ctype_isinteger(d->info) || ctype_isfp(d->info)) \
+ ngpr = (ngpr + 1u) & ~1u; /* Align int64_t to regpair. */ \
+ else if (ngpr + n > maxgpr) \
+ ngpr = maxgpr; /* Prevent reordering. */ \
+ } \
+ if (ngpr + n <= maxgpr) { \
+ dp = &cc->gpr[ngpr]; \
+ ngpr += n; \
+ goto done; \
+ } \
+
+#if LJ_ABI_SOFTFP
+#define CCALL_HANDLE_REGARG CCALL_HANDLE_GPR
+#else
#define CCALL_HANDLE_REGARG \
if (isfp) { /* Try to pass argument in FPRs. */ \
if (nfpr + 1 <= CCALL_NARG_FPR) { \
@@ -395,24 +413,16 @@
d = ctype_get(cts, CTID_DOUBLE); /* FPRs always hold doubles. */ \
goto done; \
} \
- } else { /* Try to pass argument in GPRs. */ \
- if (n > 1) { \
- lua_assert(n == 2 || n == 4); /* int64_t or complex (float). */ \
- if (ctype_isinteger(d->info)) \
- ngpr = (ngpr + 1u) & ~1u; /* Align int64_t to regpair. */ \
- else if (ngpr + n > maxgpr) \
- ngpr = maxgpr; /* Prevent reordering. */ \
- } \
- if (ngpr + n <= maxgpr) { \
- dp = &cc->gpr[ngpr]; \
- ngpr += n; \
- goto done; \
- } \
+ } else { \
+ CCALL_HANDLE_GPR \
}
+#endif
+#if !LJ_ABI_SOFTFP
#define CCALL_HANDLE_RET \
if (ctype_isfp(ctr->info) && ctr->size == sizeof(float)) \
ctr = ctype_get(cts, CTID_DOUBLE); /* FPRs always hold doubles. */
+#endif
#elif LJ_TARGET_MIPS32
/* -- MIPS o32 calling conventions ---------------------------------------- */
@@ -1080,7 +1090,7 @@ static int ccall_set_args(lua_State *L,
}
if (fid) lj_err_caller(L, LJ_ERR_FFI_NUMARG); /* Too few arguments. */
-#if LJ_TARGET_X64 || LJ_TARGET_PPC
+#if LJ_TARGET_X64 || (LJ_TARGET_PPC && !LJ_ABI_SOFTFP)
cc->nfpr = nfpr; /* Required for vararg functions. */
#endif
cc->nsp = nsp;
--- a/src/lj_ccall.h
+++ b/src/lj_ccall.h
@@ -86,9 +86,9 @@ typedef union FPRArg {
#elif LJ_TARGET_PPC
#define CCALL_NARG_GPR 8
-#define CCALL_NARG_FPR 8
+#define CCALL_NARG_FPR (LJ_ABI_SOFTFP ? 0 : 8)
#define CCALL_NRET_GPR 4 /* For complex double. */
-#define CCALL_NRET_FPR 1
+#define CCALL_NRET_FPR (LJ_ABI_SOFTFP ? 0 : 1)
#define CCALL_SPS_EXTRA 4
#define CCALL_SPS_FREE 0
--- a/src/lj_ccallback.c
+++ b/src/lj_ccallback.c
@@ -419,6 +419,23 @@ void lj_ccallback_mcode_free(CTState *ct
#elif LJ_TARGET_PPC
+#define CALLBACK_HANDLE_GPR \
+ if (n > 1) { \
+ lua_assert(((LJ_ABI_SOFTFP && ctype_isnum(cta->info)) || /* double. */ \
+ ctype_isinteger(cta->info)) && n == 2); /* int64_t. */ \
+ ngpr = (ngpr + 1u) & ~1u; /* Align int64_t to regpair. */ \
+ } \
+ if (ngpr + n <= maxgpr) { \
+ sp = &cts->cb.gpr[ngpr]; \
+ ngpr += n; \
+ goto done; \
+ }
+
+#if LJ_ABI_SOFTFP
+#define CALLBACK_HANDLE_REGARG \
+ CALLBACK_HANDLE_GPR \
+ UNUSED(isfp);
+#else
#define CALLBACK_HANDLE_REGARG \
if (isfp) { \
if (nfpr + 1 <= CCALL_NARG_FPR) { \
@@ -427,20 +444,15 @@ void lj_ccallback_mcode_free(CTState *ct
goto done; \
} \
} else { /* Try to pass argument in GPRs. */ \
- if (n > 1) { \
- lua_assert(ctype_isinteger(cta->info) && n == 2); /* int64_t. */ \
- ngpr = (ngpr + 1u) & ~1u; /* Align int64_t to regpair. */ \
- } \
- if (ngpr + n <= maxgpr) { \
- sp = &cts->cb.gpr[ngpr]; \
- ngpr += n; \
- goto done; \
- } \
+ CALLBACK_HANDLE_GPR \
}
+#endif
+#if !LJ_ABI_SOFTFP
#define CALLBACK_HANDLE_RET \
if (ctype_isfp(ctr->info) && ctr->size == sizeof(float)) \
*(double *)dp = *(float *)dp; /* FPRs always hold doubles. */
+#endif
#elif LJ_TARGET_MIPS32
--- a/src/lj_frame.h
+++ b/src/lj_frame.h
@@ -226,7 +226,7 @@ enum { LJ_CONT_TAILCALL, LJ_CONT_FFI_CAL
#define CFRAME_OFS_L 36
#define CFRAME_OFS_PC 32
#define CFRAME_OFS_MULTRES 28
-#define CFRAME_SIZE 272
+#define CFRAME_SIZE (LJ_ARCH_HASFPU ? 272 : 128)
#define CFRAME_SHIFT_MULTRES 3
#endif
#elif LJ_TARGET_MIPS32
--- a/src/lj_ircall.h
+++ b/src/lj_ircall.h
@@ -272,7 +272,7 @@ LJ_DATA const CCallInfo lj_ir_callinfo[I
#define fp64_f2l __aeabi_f2lz
#define fp64_f2ul __aeabi_f2ulz
#endif
-#elif LJ_TARGET_MIPS
+#elif LJ_TARGET_MIPS || LJ_TARGET_PPC
#define softfp_add __adddf3
#define softfp_sub __subdf3
#define softfp_mul __muldf3
--- a/src/vm_ppc.dasc
+++ b/src/vm_ppc.dasc
@@ -103,6 +103,18 @@
|// Fixed register assignments for the interpreter.
|// Don't use: r1 = sp, r2 and r13 = reserved (TOC, TLS or SDATA)
|
+|.macro .FPU, a, b
+|.if FPU
+| a, b
+|.endif
+|.endmacro
+|
+|.macro .FPU, a, b, c
+|.if FPU
+| a, b, c
+|.endif
+|.endmacro
+|
|// The following must be C callee-save (but BASE is often refetched).
|.define BASE, r14 // Base of current Lua stack frame.
|.define KBASE, r15 // Constants of current Lua function.
@@ -116,8 +128,10 @@
|.define TISNUM, r22
|.define TISNIL, r23
|.define ZERO, r24
+|.if FPU
|.define TOBIT, f30 // 2^52 + 2^51.
|.define TONUM, f31 // 2^52 + 2^51 + 2^31.
+|.endif
|
|// The following temporaries are not saved across C calls, except for RA.
|.define RA, r20 // Callee-save.
@@ -133,6 +147,7 @@
|
|// Saved temporaries.
|.define SAVE0, r21
+|.define SAVE1, r25
|
|// Calling conventions.
|.define CARG1, r3
@@ -141,8 +156,10 @@
|.define CARG4, r6 // Overlaps TMP3.
|.define CARG5, r7 // Overlaps INS.
|
+|.if FPU
|.define FARG1, f1
|.define FARG2, f2
+|.endif
|
|.define CRET1, r3
|.define CRET2, r4
@@ -213,10 +230,16 @@
|.endif
|.else
|
+|.if FPU
|.define SAVE_LR, 276(sp)
|.define CFRAME_SPACE, 272 // Delta for sp.
|// Back chain for sp: 272(sp) <-- sp entering interpreter
|.define SAVE_FPR_, 128 // .. 128+18*8: 64 bit FPR saves.
+|.else
+|.define SAVE_LR, 132(sp)
+|.define CFRAME_SPACE, 128 // Delta for sp.
+|// Back chain for sp: 128(sp) <-- sp entering interpreter
+|.endif
|.define SAVE_GPR_, 56 // .. 56+18*4: 32 bit GPR saves.
|.define SAVE_CR, 52(sp) // 32 bit CR save.
|.define SAVE_ERRF, 48(sp) // 32 bit C frame info.
@@ -226,16 +249,25 @@
|.define SAVE_PC, 32(sp)
|.define SAVE_MULTRES, 28(sp)
|.define UNUSED1, 24(sp)
+|.if FPU
|.define TMPD_LO, 20(sp)
|.define TMPD_HI, 16(sp)
|.define TONUM_LO, 12(sp)
|.define TONUM_HI, 8(sp)
+|.else
+|.define SFSAVE_4, 20(sp)
+|.define SFSAVE_3, 16(sp)
+|.define SFSAVE_2, 12(sp)
+|.define SFSAVE_1, 8(sp)
+|.endif
|// Next frame lr: 4(sp)
|// Back chain for sp: 0(sp) <-- sp while in interpreter
|
+|.if FPU
|.define TMPD_BLO, 23(sp)
|.define TMPD, TMPD_HI
|.define TONUM_D, TONUM_HI
+|.endif
|
|.endif
|
@@ -245,7 +277,7 @@
|.else
| stw r..reg, SAVE_GPR_+(reg-14)*4(sp)
|.endif
-| stfd f..reg, SAVE_FPR_+(reg-14)*8(sp)
+| .FPU stfd f..reg, SAVE_FPR_+(reg-14)*8(sp)
|.endmacro
|.macro rest_, reg
|.if GPR64
@@ -253,7 +285,7 @@
|.else
| lwz r..reg, SAVE_GPR_+(reg-14)*4(sp)
|.endif
-| lfd f..reg, SAVE_FPR_+(reg-14)*8(sp)
+| .FPU lfd f..reg, SAVE_FPR_+(reg-14)*8(sp)
|.endmacro
|
|.macro saveregs
@@ -323,6 +355,7 @@
|// Trap for not-yet-implemented parts.
|.macro NYI; tw 4, sp, sp; .endmacro
|
+|.if FPU
|// int/FP conversions.
|.macro tonum_i, freg, reg
| xoris reg, reg, 0x8000
@@ -346,6 +379,7 @@
|.macro toint, reg, freg
| toint reg, freg, freg
|.endmacro
+|.endif
|
|//-----------------------------------------------------------------------
|
@@ -533,9 +567,19 @@ static void build_subroutines(BuildCtx *
| beq >2
|1:
| addic. TMP1, TMP1, -8
+ |.if FPU
| lfd f0, 0(RA)
+ |.else
+ | lwz CARG1, 0(RA)
+ | lwz CARG2, 4(RA)
+ |.endif
| addi RA, RA, 8
+ |.if FPU
| stfd f0, 0(BASE)
+ |.else
+ | stw CARG1, 0(BASE)
+ | stw CARG2, 4(BASE)
+ |.endif
| addi BASE, BASE, 8
| bney <1
|
@@ -613,23 +657,23 @@ static void build_subroutines(BuildCtx *
| .toc ld TOCREG, SAVE_TOC
| li TISNUM, LJ_TISNUM // Setup type comparison constants.
| lp BASE, L->base
- | lus TMP3, 0x59c0 // TOBIT = 2^52 + 2^51 (float).
+ | .FPU lus TMP3, 0x59c0 // TOBIT = 2^52 + 2^51 (float).
| lwz DISPATCH, L->glref // Setup pointer to dispatch table.
| li ZERO, 0
- | stw TMP3, TMPD
+ | .FPU stw TMP3, TMPD
| li TMP1, LJ_TFALSE
- | ori TMP3, TMP3, 0x0004 // TONUM = 2^52 + 2^51 + 2^31 (float).
+ | .FPU ori TMP3, TMP3, 0x0004 // TONUM = 2^52 + 2^51 + 2^31 (float).
| li TISNIL, LJ_TNIL
| li_vmstate INTERP
- | lfs TOBIT, TMPD
+ | .FPU lfs TOBIT, TMPD
| lwz PC, FRAME_PC(BASE) // Fetch PC of previous frame.
| la RA, -8(BASE) // Results start at BASE-8.
- | stw TMP3, TMPD
+ | .FPU stw TMP3, TMPD
| addi DISPATCH, DISPATCH, GG_G2DISP
| stw TMP1, 0(RA) // Prepend false to error message.
| li RD, 16 // 2 results: false + error message.
| st_vmstate
- | lfs TONUM, TMPD
+ | .FPU lfs TONUM, TMPD
| b ->vm_returnc
|
|//-----------------------------------------------------------------------
@@ -690,22 +734,22 @@ static void build_subroutines(BuildCtx *
| li TISNUM, LJ_TISNUM // Setup type comparison constants.
| lp TMP1, L->top
| lwz PC, FRAME_PC(BASE)
- | lus TMP3, 0x59c0 // TOBIT = 2^52 + 2^51 (float).
+ | .FPU lus TMP3, 0x59c0 // TOBIT = 2^52 + 2^51 (float).
| stb CARG3, L->status
- | stw TMP3, TMPD
- | ori TMP3, TMP3, 0x0004 // TONUM = 2^52 + 2^51 + 2^31 (float).
- | lfs TOBIT, TMPD
+ | .FPU stw TMP3, TMPD
+ | .FPU ori TMP3, TMP3, 0x0004 // TONUM = 2^52 + 2^51 + 2^31 (float).
+ | .FPU lfs TOBIT, TMPD
| sub RD, TMP1, BASE
- | stw TMP3, TMPD
- | lus TMP0, 0x4338 // Hiword of 2^52 + 2^51 (double)
+ | .FPU stw TMP3, TMPD
+ | .FPU lus TMP0, 0x4338 // Hiword of 2^52 + 2^51 (double)
| addi RD, RD, 8
- | stw TMP0, TONUM_HI
+ | .FPU stw TMP0, TONUM_HI
| li_vmstate INTERP
| li ZERO, 0
| st_vmstate
| andix. TMP0, PC, FRAME_TYPE
| mr MULTRES, RD
- | lfs TONUM, TMPD
+ | .FPU lfs TONUM, TMPD
| li TISNIL, LJ_TNIL
| beq ->BC_RET_Z
| b ->vm_return
@@ -739,19 +783,19 @@ static void build_subroutines(BuildCtx *
| lp TMP2, L->base // TMP2 = old base (used in vmeta_call).
| li TISNUM, LJ_TISNUM // Setup type comparison constants.
| lp TMP1, L->top
- | lus TMP3, 0x59c0 // TOBIT = 2^52 + 2^51 (float).
+ | .FPU lus TMP3, 0x59c0 // TOBIT = 2^52 + 2^51 (float).
| add PC, PC, BASE
- | stw TMP3, TMPD
+ | .FPU stw TMP3, TMPD
| li ZERO, 0
- | ori TMP3, TMP3, 0x0004 // TONUM = 2^52 + 2^51 + 2^31 (float).
- | lfs TOBIT, TMPD
+ | .FPU ori TMP3, TMP3, 0x0004 // TONUM = 2^52 + 2^51 + 2^31 (float).
+ | .FPU lfs TOBIT, TMPD
| sub PC, PC, TMP2 // PC = frame delta + frame type
- | stw TMP3, TMPD
- | lus TMP0, 0x4338 // Hiword of 2^52 + 2^51 (double)
+ | .FPU stw TMP3, TMPD
+ | .FPU lus TMP0, 0x4338 // Hiword of 2^52 + 2^51 (double)
| sub NARGS8:RC, TMP1, BASE
- | stw TMP0, TONUM_HI
+ | .FPU stw TMP0, TONUM_HI
| li_vmstate INTERP
- | lfs TONUM, TMPD
+ | .FPU lfs TONUM, TMPD
| li TISNIL, LJ_TNIL
| st_vmstate
|
@@ -839,15 +883,30 @@ static void build_subroutines(BuildCtx *
| lwz INS, -4(PC)
| subi CARG2, RB, 16
| decode_RB8 SAVE0, INS
+ |.if FPU
| lfd f0, 0(RA)
+ |.else
+ | lwz TMP2, 0(RA)
+ | lwz TMP3, 4(RA)
+ |.endif
| add TMP1, BASE, SAVE0
| stp BASE, L->base
| cmplw TMP1, CARG2
| sub CARG3, CARG2, TMP1
| decode_RA8 RA, INS
+ |.if FPU
| stfd f0, 0(CARG2)
+ |.else
+ | stw TMP2, 0(CARG2)
+ | stw TMP3, 4(CARG2)
+ |.endif
| bney ->BC_CAT_Z
+ |.if FPU
| stfdx f0, BASE, RA
+ |.else
+ | stwux TMP2, RA, BASE
+ | stw TMP3, 4(RA)
+ |.endif
| b ->cont_nop
|
|//-- Table indexing metamethods -----------------------------------------
@@ -900,9 +959,19 @@ static void build_subroutines(BuildCtx *
| // Returns TValue * (finished) or NULL (metamethod).
| cmplwi CRET1, 0
| beq >3
+ |.if FPU
| lfd f0, 0(CRET1)
+ |.else
+ | lwz TMP0, 0(CRET1)
+ | lwz TMP1, 4(CRET1)
+ |.endif
| ins_next1
+ |.if FPU
| stfdx f0, BASE, RA
+ |.else
+ | stwux TMP0, RA, BASE
+ | stw TMP1, 4(RA)
+ |.endif
| ins_next2
|
|3: // Call __index metamethod.
@@ -920,7 +989,12 @@ static void build_subroutines(BuildCtx *
| // Returns cTValue * or NULL.
| cmplwi CRET1, 0
| beq >1
+ |.if FPU
| lfd f14, 0(CRET1)
+ |.else
+ | lwz SAVE0, 0(CRET1)
+ | lwz SAVE1, 4(CRET1)
+ |.endif
| b ->BC_TGETR_Z
|1:
| stwx TISNIL, BASE, RA
@@ -975,11 +1049,21 @@ static void build_subroutines(BuildCtx *
| bl extern lj_meta_tset // (lua_State *L, TValue *o, TValue *k)
| // Returns TValue * (finished) or NULL (metamethod).
| cmplwi CRET1, 0
+ |.if FPU
| lfdx f0, BASE, RA
+ |.else
+ | lwzux TMP2, RA, BASE
+ | lwz TMP3, 4(RA)
+ |.endif
| beq >3
| // NOBARRIER: lj_meta_tset ensures the table is not black.
| ins_next1
+ |.if FPU
| stfd f0, 0(CRET1)
+ |.else
+ | stw TMP2, 0(CRET1)
+ | stw TMP3, 4(CRET1)
+ |.endif
| ins_next2
|
|3: // Call __newindex metamethod.
@@ -990,7 +1074,12 @@ static void build_subroutines(BuildCtx *
| add PC, TMP1, BASE
| lwz LFUNC:RB, FRAME_FUNC(BASE) // Guaranteed to be a function here.
| li NARGS8:RC, 24 // 3 args for func(t, k, v)
+ |.if FPU
| stfd f0, 16(BASE) // Copy value to third argument.
+ |.else
+ | stw TMP2, 16(BASE)
+ | stw TMP3, 20(BASE)
+ |.endif
| b ->vm_call_dispatch_f
|
|->vmeta_tsetr:
@@ -998,7 +1087,12 @@ static void build_subroutines(BuildCtx *
| stw PC, SAVE_PC
| bl extern lj_tab_setinth // (lua_State *L, GCtab *t, int32_t key)
| // Returns TValue *.
+ |.if FPU
| stfd f14, 0(CRET1)
+ |.else
+ | stw SAVE0, 0(CRET1)
+ | stw SAVE1, 4(CRET1)
+ |.endif
| b ->cont_nop
|
|//-- Comparison metamethods ---------------------------------------------
@@ -1037,9 +1131,19 @@ static void build_subroutines(BuildCtx *
|
|->cont_ra: // RA = resultptr
| lwz INS, -4(PC)
+ |.if FPU
| lfd f0, 0(RA)
+ |.else
+ | lwz CARG1, 0(RA)
+ | lwz CARG2, 4(RA)
+ |.endif
| decode_RA8 TMP1, INS
+ |.if FPU
| stfdx f0, BASE, TMP1
+ |.else
+ | stwux CARG1, TMP1, BASE
+ | stw CARG2, 4(TMP1)
+ |.endif
| b ->cont_nop
|
|->cont_condt: // RA = resultptr
@@ -1245,22 +1349,32 @@ static void build_subroutines(BuildCtx *
|.macro .ffunc_n, name
|->ff_ .. name:
| cmplwi NARGS8:RC, 8
- | lwz CARG3, 0(BASE)
+ | lwz CARG1, 0(BASE)
+ |.if FPU
| lfd FARG1, 0(BASE)
+ |.else
+ | lwz CARG2, 4(BASE)
+ |.endif
| blt ->fff_fallback
- | checknum CARG3; bge ->fff_fallback
+ | checknum CARG1; bge ->fff_fallback
|.endmacro
|
|.macro .ffunc_nn, name
|->ff_ .. name:
| cmplwi NARGS8:RC, 16
- | lwz CARG3, 0(BASE)
+ | lwz CARG1, 0(BASE)
+ |.if FPU
| lfd FARG1, 0(BASE)
- | lwz CARG4, 8(BASE)
+ | lwz CARG3, 8(BASE)
| lfd FARG2, 8(BASE)
+ |.else
+ | lwz CARG2, 4(BASE)
+ | lwz CARG3, 8(BASE)
+ | lwz CARG4, 12(BASE)
+ |.endif
| blt ->fff_fallback
+ | checknum CARG1; bge ->fff_fallback
| checknum CARG3; bge ->fff_fallback
- | checknum CARG4; bge ->fff_fallback
|.endmacro
|
|// Inlined GC threshold check. Caveat: uses TMP0 and TMP1.
@@ -1281,14 +1395,21 @@ static void build_subroutines(BuildCtx *
| bge cr1, ->fff_fallback
| stw CARG3, 0(RA)
| addi RD, NARGS8:RC, 8 // Compute (nresults+1)*8.
+ | addi TMP1, BASE, 8
+ | add TMP2, RA, NARGS8:RC
| stw CARG1, 4(RA)
| beq ->fff_res // Done if exactly 1 argument.
- | li TMP1, 8
- | subi RC, RC, 8
|1:
- | cmplw TMP1, RC
- | lfdx f0, BASE, TMP1
- | stfdx f0, RA, TMP1
+ | cmplw TMP1, TMP2
+ |.if FPU
+ | lfd f0, 0(TMP1)
+ | stfd f0, 0(TMP1)
+ |.else
+ | lwz CARG1, 0(TMP1)
+ | lwz CARG2, 4(TMP1)
+ | stw CARG1, -8(TMP1)
+ | stw CARG2, -4(TMP1)
+ |.endif
| addi TMP1, TMP1, 8
| bney <1
| b ->fff_res
@@ -1303,8 +1424,14 @@ static void build_subroutines(BuildCtx *
| orc TMP1, TMP2, TMP0
| addi TMP1, TMP1, ~LJ_TISNUM+1
| slwi TMP1, TMP1, 3
+ |.if FPU
| la TMP2, CFUNC:RB->upvalue
| lfdx FARG1, TMP2, TMP1
+ |.else
+ | add TMP1, CFUNC:RB, TMP1
+ | lwz CARG1, CFUNC:TMP1->upvalue[0].u32.hi
+ | lwz CARG2, CFUNC:TMP1->upvalue[0].u32.lo
+ |.endif
| b ->fff_resn
|
|//-- Base library: getters and setters ---------------------------------
@@ -1382,7 +1509,12 @@ static void build_subroutines(BuildCtx *
| mr CARG1, L
| bl extern lj_tab_get // (lua_State *L, GCtab *t, cTValue *key)
| // Returns cTValue *.
+ |.if FPU
| lfd FARG1, 0(CRET1)
+ |.else
+ | lwz CARG2, 4(CRET1)
+ | lwz CARG1, 0(CRET1) // Caveat: CARG1 == CRET1.
+ |.endif
| b ->fff_resn
|
|//-- Base library: conversions ------------------------------------------
@@ -1391,7 +1523,11 @@ static void build_subroutines(BuildCtx *
| // Only handles the number case inline (without a base argument).
| cmplwi NARGS8:RC, 8
| lwz CARG1, 0(BASE)
+ |.if FPU
| lfd FARG1, 0(BASE)
+ |.else
+ | lwz CARG2, 4(BASE)
+ |.endif
| bne ->fff_fallback // Exactly one argument.
| checknum CARG1; bgt ->fff_fallback
| b ->fff_resn
@@ -1442,12 +1578,23 @@ static void build_subroutines(BuildCtx *
| cmplwi CRET1, 0
| li CARG3, LJ_TNIL
| beq ->fff_restv // End of traversal: return nil.
- | lfd f0, 8(BASE) // Copy key and value to results.
| la RA, -8(BASE)
+ |.if FPU
+ | lfd f0, 8(BASE) // Copy key and value to results.
| lfd f1, 16(BASE)
| stfd f0, 0(RA)
- | li RD, (2+1)*8
| stfd f1, 8(RA)
+ |.else
+ | lwz CARG1, 8(BASE)
+ | lwz CARG2, 12(BASE)
+ | lwz CARG3, 16(BASE)
+ | lwz CARG4, 20(BASE)
+ | stw CARG1, 0(RA)
+ | stw CARG2, 4(RA)
+ | stw CARG3, 8(RA)
+ | stw CARG4, 12(RA)
+ |.endif
+ | li RD, (2+1)*8
| b ->fff_res
|
|.ffunc_1 pairs
@@ -1456,17 +1603,32 @@ static void build_subroutines(BuildCtx *
| bne ->fff_fallback
#if LJ_52
| lwz TAB:TMP2, TAB:CARG1->metatable
+ |.if FPU
| lfd f0, CFUNC:RB->upvalue[0]
+ |.else
+ | lwz TMP0, CFUNC:RB->upvalue[0].u32.hi
+ | lwz TMP1, CFUNC:RB->upvalue[0].u32.lo
+ |.endif
| cmplwi TAB:TMP2, 0
| la RA, -8(BASE)
| bne ->fff_fallback
#else
+ |.if FPU
| lfd f0, CFUNC:RB->upvalue[0]
+ |.else
+ | lwz TMP0, CFUNC:RB->upvalue[0].u32.hi
+ | lwz TMP1, CFUNC:RB->upvalue[0].u32.lo
+ |.endif
| la RA, -8(BASE)
#endif
| stw TISNIL, 8(BASE)
| li RD, (3+1)*8
+ |.if FPU
| stfd f0, 0(RA)
+ |.else
+ | stw TMP0, 0(RA)
+ | stw TMP1, 4(RA)
+ |.endif
| b ->fff_res
|
|.ffunc ipairs_aux
@@ -1512,14 +1674,24 @@ static void build_subroutines(BuildCtx *
| stfd FARG2, 0(RA)
|.endif
| ble >2 // Not in array part?
+ |.if FPU
| lwzx TMP2, TMP1, TMP3
| lfdx f0, TMP1, TMP3
+ |.else
+ | lwzux TMP2, TMP1, TMP3
+ | lwz TMP3, 4(TMP1)
+ |.endif
|1:
| checknil TMP2
| li RD, (0+1)*8
| beq ->fff_res // End of iteration, return 0 results.
| li RD, (2+1)*8
+ |.if FPU
| stfd f0, 8(RA)
+ |.else
+ | stw TMP2, 8(RA)
+ | stw TMP3, 12(RA)
+ |.endif
| b ->fff_res
|2: // Check for empty hash part first. Otherwise call C function.
| lwz TMP0, TAB:CARG1->hmask
@@ -1533,7 +1705,11 @@ static void build_subroutines(BuildCtx *
| li RD, (0+1)*8
| beq ->fff_res
| lwz TMP2, 0(CRET1)
+ |.if FPU
| lfd f0, 0(CRET1)
+ |.else
+ | lwz TMP3, 4(CRET1)
+ |.endif
| b <1
|
|.ffunc_1 ipairs
@@ -1542,12 +1718,22 @@ static void build_subroutines(BuildCtx *
| bne ->fff_fallback
#if LJ_52
| lwz TAB:TMP2, TAB:CARG1->metatable
+ |.if FPU
| lfd f0, CFUNC:RB->upvalue[0]
+ |.else
+ | lwz TMP0, CFUNC:RB->upvalue[0].u32.hi
+ | lwz TMP1, CFUNC:RB->upvalue[0].u32.lo
+ |.endif
| cmplwi TAB:TMP2, 0
| la RA, -8(BASE)
| bne ->fff_fallback
#else
+ |.if FPU
| lfd f0, CFUNC:RB->upvalue[0]
+ |.else
+ | lwz TMP0, CFUNC:RB->upvalue[0].u32.hi
+ | lwz TMP1, CFUNC:RB->upvalue[0].u32.lo
+ |.endif
| la RA, -8(BASE)
#endif
|.if DUALNUM
@@ -1557,7 +1743,12 @@ static void build_subroutines(BuildCtx *
|.endif
| stw ZERO, 12(BASE)
| li RD, (3+1)*8
+ |.if FPU
| stfd f0, 0(RA)
+ |.else
+ | stw TMP0, 0(RA)
+ | stw TMP1, 4(RA)
+ |.endif
| b ->fff_res
|
|//-- Base library: catch errors ----------------------------------------
@@ -1576,19 +1767,32 @@ static void build_subroutines(BuildCtx *
|
|.ffunc xpcall
| cmplwi NARGS8:RC, 16
- | lwz CARG4, 8(BASE)
+ | lwz CARG3, 8(BASE)
+ |.if FPU
| lfd FARG2, 8(BASE)
| lfd FARG1, 0(BASE)
+ |.else
+ | lwz CARG1, 0(BASE)
+ | lwz CARG2, 4(BASE)
+ | lwz CARG4, 12(BASE)
+ |.endif
| blt ->fff_fallback
| lbz TMP1, DISPATCH_GL(hookmask)(DISPATCH)
| mr TMP2, BASE
- | checkfunc CARG4; bne ->fff_fallback // Traceback must be a function.
+ | checkfunc CARG3; bne ->fff_fallback // Traceback must be a function.
| la BASE, 16(BASE)
| // Remember active hook before pcall.
| rlwinm TMP1, TMP1, 32-HOOK_ACTIVE_SHIFT, 31, 31
+ |.if FPU
| stfd FARG2, 0(TMP2) // Swap function and traceback.
- | subi NARGS8:RC, NARGS8:RC, 16
| stfd FARG1, 8(TMP2)
+ |.else
+ | stw CARG3, 0(TMP2)
+ | stw CARG4, 4(TMP2)
+ | stw CARG1, 8(TMP2)
+ | stw CARG2, 12(TMP2)
+ |.endif
+ | subi NARGS8:RC, NARGS8:RC, 16
| addi PC, TMP1, 16+FRAME_PCALL
| b ->vm_call_dispatch
|
@@ -1631,9 +1835,21 @@ static void build_subroutines(BuildCtx *
| stp BASE, L->top
|2: // Move args to coroutine.
| cmpw TMP1, NARGS8:RC
+ |.if FPU
| lfdx f0, BASE, TMP1
+ |.else
+ | add CARG3, BASE, TMP1
+ | lwz TMP2, 0(CARG3)
+ | lwz TMP3, 4(CARG3)
+ |.endif
| beq >3
+ |.if FPU
| stfdx f0, CARG2, TMP1
+ |.else
+ | add CARG3, CARG2, TMP1
+ | stw TMP2, 0(CARG3)
+ | stw TMP3, 4(CARG3)
+ |.endif
| addi TMP1, TMP1, 8
| b <2
|3:
@@ -1664,8 +1880,17 @@ static void build_subroutines(BuildCtx *
| stp TMP2, L:SAVE0->top // Clear coroutine stack.
|5: // Move results from coroutine.
| cmplw TMP1, TMP3
+ |.if FPU
| lfdx f0, TMP2, TMP1
| stfdx f0, BASE, TMP1
+ |.else
+ | add CARG3, TMP2, TMP1
+ | lwz CARG1, 0(CARG3)
+ | lwz CARG2, 4(CARG3)
+ | add CARG3, BASE, TMP1
+ | stw CARG1, 0(CARG3)
+ | stw CARG2, 4(CARG3)
+ |.endif
| addi TMP1, TMP1, 8
| bne <5
|6:
@@ -1690,12 +1915,22 @@ static void build_subroutines(BuildCtx *
| andix. TMP0, PC, FRAME_TYPE
| la TMP3, -8(TMP3)
| li TMP1, LJ_TFALSE
+ |.if FPU
| lfd f0, 0(TMP3)
+ |.else
+ | lwz CARG1, 0(TMP3)
+ | lwz CARG2, 4(TMP3)
+ |.endif
| stp TMP3, L:SAVE0->top // Remove error from coroutine stack.
| li RD, (2+1)*8
| stw TMP1, -8(BASE) // Prepend false to results.
| la RA, -8(BASE)
+ |.if FPU
| stfd f0, 0(BASE) // Copy error message.
+ |.else
+ | stw CARG1, 0(BASE) // Copy error message.
+ | stw CARG2, 4(BASE)
+ |.endif
| b <7
|.else
| mr CARG1, L
@@ -1874,7 +2109,12 @@ static void build_subroutines(BuildCtx *
| lus CARG1, 0x8000 // -(2^31).
| beqy ->fff_resi
|5:
+ |.if FPU
| lfd FARG1, 0(BASE)
+ |.else
+ | lwz CARG1, 0(BASE)
+ | lwz CARG2, 4(BASE)
+ |.endif
| blex func
| b ->fff_resn
|.endmacro
@@ -1898,10 +2138,14 @@ static void build_subroutines(BuildCtx *
|
|.ffunc math_log
| cmplwi NARGS8:RC, 8
- | lwz CARG3, 0(BASE)
- | lfd FARG1, 0(BASE)
+ | lwz CARG1, 0(BASE)
| bne ->fff_fallback // Need exactly 1 argument.
- | checknum CARG3; bge ->fff_fallback
+ | checknum CARG1; bge ->fff_fallback
+ |.if FPU
+ | lfd FARG1, 0(BASE)
+ |.else
+ | lwz CARG2, 4(BASE)
+ |.endif
| blex log
| b ->fff_resn
|
@@ -1923,17 +2167,24 @@ static void build_subroutines(BuildCtx *
|.if DUALNUM
|.ffunc math_ldexp
| cmplwi NARGS8:RC, 16
- | lwz CARG3, 0(BASE)
+ | lwz TMP0, 0(BASE)
+ |.if FPU
| lfd FARG1, 0(BASE)
- | lwz CARG4, 8(BASE)
+ |.else
+ | lwz CARG1, 0(BASE)
+ | lwz CARG2, 4(BASE)
+ |.endif
+ | lwz TMP1, 8(BASE)
|.if GPR64
| lwz CARG2, 12(BASE)
- |.else
+ |.elif FPU
| lwz CARG1, 12(BASE)
+ |.else
+ | lwz CARG3, 12(BASE)
|.endif
| blt ->fff_fallback
- | checknum CARG3; bge ->fff_fallback
- | checknum CARG4; bne ->fff_fallback
+ | checknum TMP0; bge ->fff_fallback
+ | checknum TMP1; bne ->fff_fallback
|.else
|.ffunc_nn math_ldexp
|.if GPR64
@@ -1948,8 +2199,10 @@ static void build_subroutines(BuildCtx *
|.ffunc_n math_frexp
|.if GPR64
| la CARG2, DISPATCH_GL(tmptv)(DISPATCH)
- |.else
+ |.elif FPU
| la CARG1, DISPATCH_GL(tmptv)(DISPATCH)
+ |.else
+ | la CARG3, DISPATCH_GL(tmptv)(DISPATCH)
|.endif
| lwz PC, FRAME_PC(BASE)
| blex frexp
@@ -1958,7 +2211,12 @@ static void build_subroutines(BuildCtx *
|.if not DUALNUM
| tonum_i FARG2, TMP1
|.endif
+ |.if FPU
| stfd FARG1, 0(RA)
+ |.else
+ | stw CRET1, 0(RA)
+ | stw CRET2, 4(RA)
+ |.endif
| li RD, (2+1)*8
|.if DUALNUM
| stw TISNUM, 8(RA)
@@ -1971,13 +2229,20 @@ static void build_subroutines(BuildCtx *
|.ffunc_n math_modf
|.if GPR64
| la CARG2, -8(BASE)
- |.else
+ |.elif FPU
| la CARG1, -8(BASE)
+ |.else
+ | la CARG3, -8(BASE)
|.endif
| lwz PC, FRAME_PC(BASE)
| blex modf
| la RA, -8(BASE)
+ |.if FPU
| stfd FARG1, 0(BASE)
+ |.else
+ | stw CRET1, 0(BASE)
+ | stw CRET2, 4(BASE)
+ |.endif
| li RD, (2+1)*8
| b ->fff_res
|
@@ -1985,13 +2250,13 @@ static void build_subroutines(BuildCtx *
|.if DUALNUM
| .ffunc_1 name
| checknum CARG3
- | addi TMP1, BASE, 8
- | add TMP2, BASE, NARGS8:RC
+ | addi SAVE0, BASE, 8
+ | add SAVE1, BASE, NARGS8:RC
| bne >4
|1: // Handle integers.
- | lwz CARG4, 0(TMP1)
- | cmplw cr1, TMP1, TMP2
- | lwz CARG2, 4(TMP1)
+ | lwz CARG4, 0(SAVE0)
+ | cmplw cr1, SAVE0, SAVE1
+ | lwz CARG2, 4(SAVE0)
| bge cr1, ->fff_resi
| checknum CARG4
| xoris TMP0, CARG1, 0x8000
@@ -2008,36 +2273,76 @@ static void build_subroutines(BuildCtx *
|.if GPR64
| rldicl CARG1, CARG1, 0, 32
|.endif
- | addi TMP1, TMP1, 8
+ | addi SAVE0, SAVE0, 8
| b <1
|3:
| bge ->fff_fallback
| // Convert intermediate result to number and continue below.
+ |.if FPU
| tonum_i FARG1, CARG1
- | lfd FARG2, 0(TMP1)
+ | lfd FARG2, 0(SAVE0)
+ |.else
+ | mr CARG2, CARG1
+ | bl ->vm_sfi2d_1
+ | lwz CARG3, 0(SAVE0)
+ | lwz CARG4, 4(SAVE0)
+ |.endif
| b >6
|4:
+ |.if FPU
| lfd FARG1, 0(BASE)
+ |.else
+ | lwz CARG1, 0(BASE)
+ | lwz CARG2, 4(BASE)
+ |.endif
| bge ->fff_fallback
|5: // Handle numbers.
- | lwz CARG4, 0(TMP1)
- | cmplw cr1, TMP1, TMP2
- | lfd FARG2, 0(TMP1)
+ | lwz CARG3, 0(SAVE0)
+ | cmplw cr1, SAVE0, SAVE1
+ |.if FPU
+ | lfd FARG2, 0(SAVE0)
+ |.else
+ | lwz CARG4, 4(SAVE0)
+ |.endif
| bge cr1, ->fff_resn
- | checknum CARG4; bge >7
+ | checknum CARG3; bge >7
|6:
+ | addi SAVE0, SAVE0, 8
+ |.if FPU
| fsub f0, FARG1, FARG2
- | addi TMP1, TMP1, 8
|.if ismax
| fsel FARG1, f0, FARG1, FARG2
|.else
| fsel FARG1, f0, FARG2, FARG1
|.endif
+ |.else
+ | stw CARG1, SFSAVE_1
+ | stw CARG2, SFSAVE_2
+ | stw CARG3, SFSAVE_3
+ | stw CARG4, SFSAVE_4
+ | blex __ledf2
+ | cmpwi CRET1, 0
+ |.if ismax
+ | blt >8
+ |.else
+ | bge >8
+ |.endif
+ | lwz CARG1, SFSAVE_1
+ | lwz CARG2, SFSAVE_2
+ | b <5
+ |8:
+ | lwz CARG1, SFSAVE_3
+ | lwz CARG2, SFSAVE_4
+ |.endif
| b <5
|7: // Convert integer to number and continue above.
- | lwz CARG2, 4(TMP1)
+ | lwz CARG3, 4(SAVE0)
| bne ->fff_fallback
- | tonum_i FARG2, CARG2
+ |.if FPU
+ | tonum_i FARG2, CARG3
+ |.else
+ | bl ->vm_sfi2d_2
+ |.endif
| b <6
|.else
| .ffunc_n name
@@ -2237,28 +2542,37 @@ static void build_subroutines(BuildCtx *
|
|.macro .ffunc_bit_op, name, ins
| .ffunc_bit name
- | addi TMP1, BASE, 8
- | add TMP2, BASE, NARGS8:RC
+ | addi SAVE0, BASE, 8
+ | add SAVE1, BASE, NARGS8:RC
|1:
- | lwz CARG4, 0(TMP1)
- | cmplw cr1, TMP1, TMP2
+ | lwz CARG4, 0(SAVE0)
+ | cmplw cr1, SAVE0, SAVE1
|.if DUALNUM
- | lwz CARG2, 4(TMP1)
+ | lwz CARG2, 4(SAVE0)
|.else
- | lfd FARG1, 0(TMP1)
+ | lfd FARG1, 0(SAVE0)
|.endif
| bgey cr1, ->fff_resi
| checknum CARG4
|.if DUALNUM
+ |.if FPU
| bnel ->fff_bitop_fb
|.else
+ | beq >3
+ | stw CARG1, SFSAVE_1
+ | bl ->fff_bitop_fb
+ | mr CARG2, CARG1
+ | lwz CARG1, SFSAVE_1
+ |3:
+ |.endif
+ |.else
| fadd FARG1, FARG1, TOBIT
| bge ->fff_fallback
| stfd FARG1, TMPD
| lwz CARG2, TMPD_LO
|.endif
| ins CARG1, CARG1, CARG2
- | addi TMP1, TMP1, 8
+ | addi SAVE0, SAVE0, 8
| b <1
|.endmacro
|
@@ -2280,7 +2594,14 @@ static void build_subroutines(BuildCtx *
|.macro .ffunc_bit_sh, name, ins, shmod
|.if DUALNUM
| .ffunc_2 bit_..name
+ |.if FPU
| checknum CARG3; bnel ->fff_tobit_fb
+ |.else
+ | checknum CARG3; beq >1
+ | bl ->fff_tobit_fb
+ | lwz CARG2, 12(BASE) // Conversion polluted CARG2.
+ |1:
+ |.endif
| // Note: no inline conversion from number for 2nd argument!
| checknum CARG4; bne ->fff_fallback
|.else
@@ -2317,27 +2638,77 @@ static void build_subroutines(BuildCtx *
|->fff_resn:
| lwz PC, FRAME_PC(BASE)
| la RA, -8(BASE)
+ |.if FPU
| stfd FARG1, -8(BASE)
+ |.else
+ | stw CARG1, -8(BASE)
+ | stw CARG2, -4(BASE)
+ |.endif
| b ->fff_res1
|
|// Fallback FP number to bit conversion.
|->fff_tobit_fb:
|.if DUALNUM
+ |.if FPU
| lfd FARG1, 0(BASE)
| bgt ->fff_fallback
| fadd FARG1, FARG1, TOBIT
| stfd FARG1, TMPD
| lwz CARG1, TMPD_LO
| blr
+ |.else
+ | bgt ->fff_fallback
+ | mr CARG2, CARG1
+ | mr CARG1, CARG3
+ |// Modifies: CARG1, CARG2, TMP0, TMP1, TMP2.
+ |->vm_tobit:
+ | slwi TMP2, CARG1, 1
+ | addis TMP2, TMP2, 0x0020
+ | cmpwi TMP2, 0
+ | bge >2
+ | li TMP1, 0x3e0
+ | srawi TMP2, TMP2, 21
+ | not TMP1, TMP1
+ | sub. TMP2, TMP1, TMP2
+ | cmpwi cr7, CARG1, 0
+ | blt >1
+ | slwi TMP1, CARG1, 11
+ | srwi TMP0, CARG2, 21
+ | oris TMP1, TMP1, 0x8000
+ | or TMP1, TMP1, TMP0
+ | srw CARG1, TMP1, TMP2
+ | bclr 4, 28 // Return if cr7[lt] == 0, no hint.
+ | neg CARG1, CARG1
+ | blr
+ |1:
+ | addi TMP2, TMP2, 21
+ | srw TMP1, CARG2, TMP2
+ | slwi CARG2, CARG1, 12
+ | subfic TMP2, TMP2, 20
+ | slw TMP0, CARG2, TMP2
+ | or CARG1, TMP1, TMP0
+ | bclr 4, 28 // Return if cr7[lt] == 0, no hint.
+ | neg CARG1, CARG1
+ | blr
+ |2:
+ | li CARG1, 0
+ | blr
+ |.endif
|.endif
|->fff_bitop_fb:
|.if DUALNUM
- | lfd FARG1, 0(TMP1)
+ |.if FPU
+ | lfd FARG1, 0(SAVE0)
| bgt ->fff_fallback
| fadd FARG1, FARG1, TOBIT
| stfd FARG1, TMPD
| lwz CARG2, TMPD_LO
| blr
+ |.else
+ | bgt ->fff_fallback
+ | mr CARG1, CARG4
+ | b ->vm_tobit
+ |.endif
|.endif
|
|//-----------------------------------------------------------------------
@@ -2530,10 +2901,21 @@ static void build_subroutines(BuildCtx *
| decode_RA8 RC, INS // Call base.
| beq >2
|1: // Move results down.
+ |.if FPU
| lfd f0, 0(RA)
+ |.else
+ | lwz CARG1, 0(RA)
+ | lwz CARG2, 4(RA)
+ |.endif
| addic. TMP1, TMP1, -8
| addi RA, RA, 8
+ |.if FPU
| stfdx f0, BASE, RC
+ |.else
+ | add CARG3, BASE, RC
+ | stw CARG1, 0(CARG3)
+ | stw CARG2, 4(CARG3)
+ |.endif
| addi RC, RC, 8
| bne <1
|2:
@@ -2586,10 +2968,12 @@ static void build_subroutines(BuildCtx *
|//-----------------------------------------------------------------------
|
|.macro savex_, a, b, c, d
+ |.if FPU
| stfd f..a, 16+a*8(sp)
| stfd f..b, 16+b*8(sp)
| stfd f..c, 16+c*8(sp)
| stfd f..d, 16+d*8(sp)
+ |.endif
|.endmacro
|
|->vm_exit_handler:
@@ -2661,16 +3045,16 @@ static void build_subroutines(BuildCtx *
| lwz KBASE, PC2PROTO(k)(TMP1)
| // Setup type comparison constants.
| li TISNUM, LJ_TISNUM
- | lus TMP3, 0x59c0 // TOBIT = 2^52 + 2^51 (float).
- | stw TMP3, TMPD
+ | .FPU lus TMP3, 0x59c0 // TOBIT = 2^52 + 2^51 (float).
+ | .FPU stw TMP3, TMPD
| li ZERO, 0
- | ori TMP3, TMP3, 0x0004 // TONUM = 2^52 + 2^51 + 2^31 (float).
- | lfs TOBIT, TMPD
- | stw TMP3, TMPD
- | lus TMP0, 0x4338 // Hiword of 2^52 + 2^51 (double)
+ | .FPU ori TMP3, TMP3, 0x0004 // TONUM = 2^52 + 2^51 + 2^31 (float).
+ | .FPU lfs TOBIT, TMPD
+ | .FPU stw TMP3, TMPD
+ | .FPU lus TMP0, 0x4338 // Hiword of 2^52 + 2^51 (double)
| li TISNIL, LJ_TNIL
- | stw TMP0, TONUM_HI
- | lfs TONUM, TMPD
+ | .FPU stw TMP0, TONUM_HI
+ | .FPU lfs TONUM, TMPD
| // Modified copy of ins_next which handles function header dispatch, too.
| lwz INS, 0(PC)
| addi PC, PC, 4
@@ -2715,7 +3099,35 @@ static void build_subroutines(BuildCtx *
|//-- Math helper functions ----------------------------------------------
|//-----------------------------------------------------------------------
|
- |// NYI: Use internal implementations of floor, ceil, trunc.
+ |// NYI: Use internal implementations of floor, ceil, trunc, sfcmp.
+ |
+ |.macro sfi2d, AHI, ALO
+ |.if not FPU
+ | mr. AHI, ALO
+ | bclr 12, 2 // Handle zero first.
+ | srawi TMP0, ALO, 31
+ | xor TMP1, ALO, TMP0
+ | sub TMP1, TMP1, TMP0 // Absolute value in TMP1.
+ | cntlzw AHI, TMP1
+ | andix. TMP0, TMP0, 0x800 // Mask sign bit.
+ | slw TMP1, TMP1, AHI // Align mantissa left with leading 1.
+ | subfic AHI, AHI, 0x3ff+31-1 // Exponent -1 in AHI.
+ | slwi ALO, TMP1, 21
+ | or AHI, AHI, TMP0 // Sign | Exponent.
+ | srwi TMP1, TMP1, 11
+ | slwi AHI, AHI, 20 // Align left.
+ | add AHI, AHI, TMP1 // Add mantissa, increment exponent.
+ | blr
+ |.endif
+ |.endmacro
+ |
+ |// Input: CARG2. Output: CARG1, CARG2. Temporaries: TMP0, TMP1.
+ |->vm_sfi2d_1:
+ | sfi2d CARG1, CARG2
+ |
+ |// Input: CARG4. Output: CARG3, CARG4. Temporaries: TMP0, TMP1.
+ |->vm_sfi2d_2:
+ | sfi2d CARG3, CARG4
|
|->vm_modi:
| divwo. TMP0, CARG1, CARG2
@@ -2783,21 +3195,21 @@ static void build_subroutines(BuildCtx *
| addi DISPATCH, r12, GG_G2DISP
| stw r11, CTSTATE->cb.slot
| stw r3, CTSTATE->cb.gpr[0]
- | stfd f1, CTSTATE->cb.fpr[0]
+ | .FPU stfd f1, CTSTATE->cb.fpr[0]
| stw r4, CTSTATE->cb.gpr[1]
- | stfd f2, CTSTATE->cb.fpr[1]
+ | .FPU stfd f2, CTSTATE->cb.fpr[1]
| stw r5, CTSTATE->cb.gpr[2]
- | stfd f3, CTSTATE->cb.fpr[2]
+ | .FPU stfd f3, CTSTATE->cb.fpr[2]
| stw r6, CTSTATE->cb.gpr[3]
- | stfd f4, CTSTATE->cb.fpr[3]
+ | .FPU stfd f4, CTSTATE->cb.fpr[3]
| stw r7, CTSTATE->cb.gpr[4]
- | stfd f5, CTSTATE->cb.fpr[4]
+ | .FPU stfd f5, CTSTATE->cb.fpr[4]
| stw r8, CTSTATE->cb.gpr[5]
- | stfd f6, CTSTATE->cb.fpr[5]
+ | .FPU stfd f6, CTSTATE->cb.fpr[5]
| stw r9, CTSTATE->cb.gpr[6]
- | stfd f7, CTSTATE->cb.fpr[6]
+ | .FPU stfd f7, CTSTATE->cb.fpr[6]
| stw r10, CTSTATE->cb.gpr[7]
- | stfd f8, CTSTATE->cb.fpr[7]
+ | .FPU stfd f8, CTSTATE->cb.fpr[7]
| addi TMP0, sp, CFRAME_SPACE+8
| stw TMP0, CTSTATE->cb.stack
| mr CARG1, CTSTATE
@@ -2808,21 +3220,21 @@ static void build_subroutines(BuildCtx *
| lp BASE, L:CRET1->base
| li TISNUM, LJ_TISNUM // Setup type comparison constants.
| lp RC, L:CRET1->top
- | lus TMP3, 0x59c0 // TOBIT = 2^52 + 2^51 (float).
+ | .FPU lus TMP3, 0x59c0 // TOBIT = 2^52 + 2^51 (float).
| li ZERO, 0
| mr L, CRET1
- | stw TMP3, TMPD
- | lus TMP0, 0x4338 // Hiword of 2^52 + 2^51 (double)
+ | .FPU stw TMP3, TMPD
+ | .FPU lus TMP0, 0x4338 // Hiword of 2^52 + 2^51 (double)
| lwz LFUNC:RB, FRAME_FUNC(BASE)
- | ori TMP3, TMP3, 0x0004 // TONUM = 2^52 + 2^51 + 2^31 (float).
- | stw TMP0, TONUM_HI
+ | .FPU ori TMP3, TMP3, 0x0004 // TONUM = 2^52 + 2^51 + 2^31 (float).
+ | .FPU stw TMP0, TONUM_HI
| li TISNIL, LJ_TNIL
| li_vmstate INTERP
- | lfs TOBIT, TMPD
- | stw TMP3, TMPD
+ | .FPU lfs TOBIT, TMPD
+ | .FPU stw TMP3, TMPD
| sub RC, RC, BASE
| st_vmstate
- | lfs TONUM, TMPD
+ | .FPU lfs TONUM, TMPD
| ins_callt
|.endif
|
@@ -2836,7 +3248,7 @@ static void build_subroutines(BuildCtx *
| mr CARG2, RA
| bl extern lj_ccallback_leave // (CTState *cts, TValue *o)
| lwz CRET1, CTSTATE->cb.gpr[0]
- | lfd FARG1, CTSTATE->cb.fpr[0]
+ | .FPU lfd FARG1, CTSTATE->cb.fpr[0]
| lwz CRET2, CTSTATE->cb.gpr[1]
| b ->vm_leave_unw
|.endif
@@ -2870,14 +3282,14 @@ static void build_subroutines(BuildCtx *
| bge <1
|2:
| bney cr1, >3
- | lfd f1, CCSTATE->fpr[0]
- | lfd f2, CCSTATE->fpr[1]
- | lfd f3, CCSTATE->fpr[2]
- | lfd f4, CCSTATE->fpr[3]
- | lfd f5, CCSTATE->fpr[4]
- | lfd f6, CCSTATE->fpr[5]
- | lfd f7, CCSTATE->fpr[6]
- | lfd f8, CCSTATE->fpr[7]
+ | .FPU lfd f1, CCSTATE->fpr[0]
+ | .FPU lfd f2, CCSTATE->fpr[1]
+ | .FPU lfd f3, CCSTATE->fpr[2]
+ | .FPU lfd f4, CCSTATE->fpr[3]
+ | .FPU lfd f5, CCSTATE->fpr[4]
+ | .FPU lfd f6, CCSTATE->fpr[5]
+ | .FPU lfd f7, CCSTATE->fpr[6]
+ | .FPU lfd f8, CCSTATE->fpr[7]
|3:
| lp TMP0, CCSTATE->func
| lwz CARG2, CCSTATE->gpr[1]
@@ -2894,7 +3306,7 @@ static void build_subroutines(BuildCtx *
| lwz TMP2, -4(r14)
| lwz TMP0, 4(r14)
| stw CARG1, CCSTATE:TMP1->gpr[0]
- | stfd FARG1, CCSTATE:TMP1->fpr[0]
+ | .FPU stfd FARG1, CCSTATE:TMP1->fpr[0]
| stw CARG2, CCSTATE:TMP1->gpr[1]
| mtlr TMP0
| stw CARG3, CCSTATE:TMP1->gpr[2]
@@ -2923,19 +3335,19 @@ static void build_ins(BuildCtx *ctx, BCO
case BC_ISLT: case BC_ISGE: case BC_ISLE: case BC_ISGT:
| // RA = src1*8, RD = src2*8, JMP with RD = target
|.if DUALNUM
- | lwzux TMP0, RA, BASE
+ | lwzux CARG1, RA, BASE
| addi PC, PC, 4
| lwz CARG2, 4(RA)
- | lwzux TMP1, RD, BASE
+ | lwzux CARG3, RD, BASE
| lwz TMP2, -4(PC)
- | checknum cr0, TMP0
- | lwz CARG3, 4(RD)
+ | checknum cr0, CARG1
+ | lwz CARG4, 4(RD)
| decode_RD4 TMP2, TMP2
- | checknum cr1, TMP1
- | addis TMP2, TMP2, -(BCBIAS_J*4 >> 16)
+ | checknum cr1, CARG3
+ | addis SAVE0, TMP2, -(BCBIAS_J*4 >> 16)
| bne cr0, >7
| bne cr1, >8
- | cmpw CARG2, CARG3
+ | cmpw CARG2, CARG4
if (op == BC_ISLT) {
| bge >2
} else if (op == BC_ISGE) {
@@ -2946,28 +3358,41 @@ static void build_ins(BuildCtx *ctx, BCO
| ble >2
}
|1:
- | add PC, PC, TMP2
+ | add PC, PC, SAVE0
|2:
| ins_next
|
|7: // RA is not an integer.
| bgt cr0, ->vmeta_comp
| // RA is a number.
- | lfd f0, 0(RA)
+ | .FPU lfd f0, 0(RA)
| bgt cr1, ->vmeta_comp
| blt cr1, >4
| // RA is a number, RD is an integer.
- | tonum_i f1, CARG3
+ |.if FPU
+ | tonum_i f1, CARG4
+ |.else
+ | bl ->vm_sfi2d_2
+ |.endif
| b >5
|
|8: // RA is an integer, RD is not an integer.
| bgt cr1, ->vmeta_comp
| // RA is an integer, RD is a number.
+ |.if FPU
| tonum_i f0, CARG2
+ |.else
+ | bl ->vm_sfi2d_1
+ |.endif
|4:
- | lfd f1, 0(RD)
+ | .FPU lfd f1, 0(RD)
|5:
+ |.if FPU
| fcmpu cr0, f0, f1
+ |.else
+ | blex __ledf2
+ | cmpwi CRET1, 0
+ |.endif
if (op == BC_ISLT) {
| bge <2
} else if (op == BC_ISGE) {
@@ -3015,42 +3440,42 @@ static void build_ins(BuildCtx *ctx, BCO
vk = op == BC_ISEQV;
| // RA = src1*8, RD = src2*8, JMP with RD = target
|.if DUALNUM
- | lwzux TMP0, RA, BASE
+ | lwzux CARG1, RA, BASE
| addi PC, PC, 4
| lwz CARG2, 4(RA)
- | lwzux TMP1, RD, BASE
- | checknum cr0, TMP0
- | lwz TMP2, -4(PC)
- | checknum cr1, TMP1
- | decode_RD4 TMP2, TMP2
- | lwz CARG3, 4(RD)
+ | lwzux CARG3, RD, BASE
+ | checknum cr0, CARG1
+ | lwz SAVE0, -4(PC)
+ | checknum cr1, CARG3
+ | decode_RD4 SAVE0, SAVE0
+ | lwz CARG4, 4(RD)
| cror 4*cr7+gt, 4*cr0+gt, 4*cr1+gt
- | addis TMP2, TMP2, -(BCBIAS_J*4 >> 16)
+ | addis SAVE0, SAVE0, -(BCBIAS_J*4 >> 16)
if (vk) {
| ble cr7, ->BC_ISEQN_Z
} else {
| ble cr7, ->BC_ISNEN_Z
}
|.else
- | lwzux TMP0, RA, BASE
- | lwz TMP2, 0(PC)
+ | lwzux CARG1, RA, BASE
+ | lwz SAVE0, 0(PC)
| lfd f0, 0(RA)
| addi PC, PC, 4
- | lwzux TMP1, RD, BASE
- | checknum cr0, TMP0
- | decode_RD4 TMP2, TMP2
+ | lwzux CARG3, RD, BASE
+ | checknum cr0, CARG1
+ | decode_RD4 SAVE0, SAVE0
| lfd f1, 0(RD)
- | checknum cr1, TMP1
- | addis TMP2, TMP2, -(BCBIAS_J*4 >> 16)
+ | checknum cr1, CARG3
+ | addis SAVE0, SAVE0, -(BCBIAS_J*4 >> 16)
| bge cr0, >5
| bge cr1, >5
| fcmpu cr0, f0, f1
if (vk) {
| bne >1
- | add PC, PC, TMP2
+ | add PC, PC, SAVE0
} else {
| beq >1
- | add PC, PC, TMP2
+ | add PC, PC, SAVE0
}
|1:
| ins_next
@@ -3058,36 +3483,36 @@ static void build_ins(BuildCtx *ctx, BCO
|5: // Either or both types are not numbers.
|.if not DUALNUM
| lwz CARG2, 4(RA)
- | lwz CARG3, 4(RD)
+ | lwz CARG4, 4(RD)
|.endif
|.if FFI
- | cmpwi cr7, TMP0, LJ_TCDATA
- | cmpwi cr5, TMP1, LJ_TCDATA
+ | cmpwi cr7, CARG1, LJ_TCDATA
+ | cmpwi cr5, CARG3, LJ_TCDATA
|.endif
- | not TMP3, TMP0
- | cmplw TMP0, TMP1
- | cmplwi cr1, TMP3, ~LJ_TISPRI // Primitive?
+ | not TMP2, CARG1
+ | cmplw CARG1, CARG3
+ | cmplwi cr1, TMP2, ~LJ_TISPRI // Primitive?
|.if FFI
| cror 4*cr7+eq, 4*cr7+eq, 4*cr5+eq
|.endif
- | cmplwi cr6, TMP3, ~LJ_TISTABUD // Table or userdata?
+ | cmplwi cr6, TMP2, ~LJ_TISTABUD // Table or userdata?
|.if FFI
| beq cr7, ->vmeta_equal_cd
|.endif
- | cmplw cr5, CARG2, CARG3
+ | cmplw cr5, CARG2, CARG4
| crandc 4*cr0+gt, 4*cr0+eq, 4*cr1+gt // 2: Same type and primitive.
| crorc 4*cr0+lt, 4*cr5+eq, 4*cr0+eq // 1: Same tv or different type.
| crand 4*cr0+eq, 4*cr0+eq, 4*cr5+eq // 0: Same type and same tv.
- | mr SAVE0, PC
+ | mr SAVE1, PC
| cror 4*cr0+eq, 4*cr0+eq, 4*cr0+gt // 0 or 2.
| cror 4*cr0+lt, 4*cr0+lt, 4*cr0+gt // 1 or 2.
if (vk) {
| bne cr0, >6
- | add PC, PC, TMP2
+ | add PC, PC, SAVE0
|6:
} else {
| beq cr0, >6
- | add PC, PC, TMP2
+ | add PC, PC, SAVE0
|6:
}
|.if DUALNUM
@@ -3102,6 +3527,7 @@ static void build_ins(BuildCtx *ctx, BCO
|
| // Different tables or userdatas. Need to check __eq metamethod.
| // Field metatable must be at same offset for GCtab and GCudata!
+ | mr CARG3, CARG4
| lwz TAB:TMP2, TAB:CARG2->metatable
| li CARG4, 1-vk // ne = 0 or 1.
| cmplwi TAB:TMP2, 0
@@ -3109,7 +3535,7 @@ static void build_ins(BuildCtx *ctx, BCO
| lbz TMP2, TAB:TMP2->nomm
| andix. TMP2, TMP2, 1<<MM_eq
| bne <1 // Or 'no __eq' flag set?
- | mr PC, SAVE0 // Restore old PC.
+ | mr PC, SAVE1 // Restore old PC.
| b ->vmeta_equal // Handle __eq metamethod.
break;
@@ -3150,16 +3576,16 @@ static void build_ins(BuildCtx *ctx, BCO
vk = op == BC_ISEQN;
| // RA = src*8, RD = num_const*8, JMP with RD = target
|.if DUALNUM
- | lwzux TMP0, RA, BASE
+ | lwzux CARG1, RA, BASE
| addi PC, PC, 4
| lwz CARG2, 4(RA)
- | lwzux TMP1, RD, KBASE
- | checknum cr0, TMP0
- | lwz TMP2, -4(PC)
- | checknum cr1, TMP1
- | decode_RD4 TMP2, TMP2
- | lwz CARG3, 4(RD)
- | addis TMP2, TMP2, -(BCBIAS_J*4 >> 16)
+ | lwzux CARG3, RD, KBASE
+ | checknum cr0, CARG1
+ | lwz SAVE0, -4(PC)
+ | checknum cr1, CARG3
+ | decode_RD4 SAVE0, SAVE0
+ | lwz CARG4, 4(RD)
+ | addis SAVE0, SAVE0, -(BCBIAS_J*4 >> 16)
if (vk) {
|->BC_ISEQN_Z:
} else {
@@ -3167,7 +3593,7 @@ static void build_ins(BuildCtx *ctx, BCO
}
| bne cr0, >7
| bne cr1, >8
- | cmpw CARG2, CARG3
+ | cmpw CARG2, CARG4
|4:
|.else
if (vk) {
@@ -3175,20 +3601,20 @@ static void build_ins(BuildCtx *ctx, BCO
} else {
|->BC_ISNEN_Z: // Dummy label.
}
- | lwzx TMP0, BASE, RA
+ | lwzx CARG1, BASE, RA
| addi PC, PC, 4
| lfdx f0, BASE, RA
- | lwz TMP2, -4(PC)
+ | lwz SAVE0, -4(PC)
| lfdx f1, KBASE, RD
- | decode_RD4 TMP2, TMP2
- | checknum TMP0
- | addis TMP2, TMP2, -(BCBIAS_J*4 >> 16)
+ | decode_RD4 SAVE0, SAVE0
+ | checknum CARG1
+ | addis SAVE0, SAVE0, -(BCBIAS_J*4 >> 16)
| bge >3
| fcmpu cr0, f0, f1
|.endif
if (vk) {
| bne >1
- | add PC, PC, TMP2
+ | add PC, PC, SAVE0
|1:
|.if not FFI
|3:
@@ -3199,13 +3625,13 @@ static void build_ins(BuildCtx *ctx, BCO
|.if not FFI
|3:
|.endif
- | add PC, PC, TMP2
+ | add PC, PC, SAVE0
|2:
}
| ins_next
|.if FFI
|3:
- | cmpwi TMP0, LJ_TCDATA
+ | cmpwi CARG1, LJ_TCDATA
| beq ->vmeta_equal_cd
| b <1
|.endif
@@ -3213,18 +3639,31 @@ static void build_ins(BuildCtx *ctx, BCO
|7: // RA is not an integer.
| bge cr0, <3
| // RA is a number.
- | lfd f0, 0(RA)
+ | .FPU lfd f0, 0(RA)
| blt cr1, >1
| // RA is a number, RD is an integer.
- | tonum_i f1, CARG3
+ |.if FPU
+ | tonum_i f1, CARG4
+ |.else
+ | bl ->vm_sfi2d_2
+ |.endif
| b >2
|
|8: // RA is an integer, RD is a number.
+ |.if FPU
| tonum_i f0, CARG2
+ |.else
+ | bl ->vm_sfi2d_1
+ |.endif
|1:
- | lfd f1, 0(RD)
+ | .FPU lfd f1, 0(RD)
|2:
+ |.if FPU
| fcmpu cr0, f0, f1
+ |.else
+ | blex __ledf2
+ | cmpwi CRET1, 0
+ |.endif
| b <4
|.endif
break;
@@ -3279,7 +3718,12 @@ static void build_ins(BuildCtx *ctx, BCO
| add PC, PC, TMP2
} else {
| li TMP1, LJ_TFALSE
+ |.if FPU
| lfdx f0, BASE, RD
+ |.else
+ | lwzux CARG1, RD, BASE
+ | lwz CARG2, 4(RD)
+ |.endif
| cmplw TMP0, TMP1
if (op == BC_ISTC) {
| bge >1
@@ -3288,7 +3732,12 @@ static void build_ins(BuildCtx *ctx, BCO
}
| addis PC, PC, -(BCBIAS_J*4 >> 16)
| decode_RD4 TMP2, INS
+ |.if FPU
| stfdx f0, BASE, RA
+ |.else
+ | stwux CARG1, RA, BASE
+ | stw CARG2, 4(RA)
+ |.endif
| add PC, PC, TMP2
|1:
}
@@ -3323,8 +3772,15 @@ static void build_ins(BuildCtx *ctx, BCO
case BC_MOV:
| // RA = dst*8, RD = src*8
| ins_next1
+ |.if FPU
| lfdx f0, BASE, RD
| stfdx f0, BASE, RA
+ |.else
+ | lwzux TMP0, RD, BASE
+ | lwz TMP1, 4(RD)
+ | stwux TMP0, RA, BASE
+ | stw TMP1, 4(RA)
+ |.endif
| ins_next2
break;
case BC_NOT:
@@ -3426,44 +3882,65 @@ static void build_ins(BuildCtx *ctx, BCO
||vk = ((int)op - BC_ADDVN) / (BC_ADDNV-BC_ADDVN);
||switch (vk) {
||case 0:
- | lwzx TMP1, BASE, RB
+ | lwzx CARG1, BASE, RB
| .if DUALNUM
- | lwzx TMP2, KBASE, RC
+ | lwzx CARG3, KBASE, RC
| .endif
+ | .if FPU
| lfdx f14, BASE, RB
| lfdx f15, KBASE, RC
+ | .else
+ | add TMP1, BASE, RB
+ | add TMP2, KBASE, RC
+ | lwz CARG2, 4(TMP1)
+ | lwz CARG4, 4(TMP2)
+ | .endif
| .if DUALNUM
- | checknum cr0, TMP1
- | checknum cr1, TMP2
+ | checknum cr0, CARG1
+ | checknum cr1, CARG3
| crand 4*cr0+lt, 4*cr0+lt, 4*cr1+lt
| bge ->vmeta_arith_vn
| .else
- | checknum TMP1; bge ->vmeta_arith_vn
+ | checknum CARG1; bge ->vmeta_arith_vn
| .endif
|| break;
||case 1:
- | lwzx TMP1, BASE, RB
+ | lwzx CARG1, BASE, RB
| .if DUALNUM
- | lwzx TMP2, KBASE, RC
+ | lwzx CARG3, KBASE, RC
| .endif
+ | .if FPU
| lfdx f15, BASE, RB
| lfdx f14, KBASE, RC
+ | .else
+ | add TMP1, BASE, RB
+ | add TMP2, KBASE, RC
+ | lwz CARG2, 4(TMP1)
+ | lwz CARG4, 4(TMP2)
+ | .endif
| .if DUALNUM
- | checknum cr0, TMP1
- | checknum cr1, TMP2
+ | checknum cr0, CARG1
+ | checknum cr1, CARG3
| crand 4*cr0+lt, 4*cr0+lt, 4*cr1+lt
| bge ->vmeta_arith_nv
| .else
- | checknum TMP1; bge ->vmeta_arith_nv
+ | checknum CARG1; bge ->vmeta_arith_nv
| .endif
|| break;
||default:
- | lwzx TMP1, BASE, RB
- | lwzx TMP2, BASE, RC
+ | lwzx CARG1, BASE, RB
+ | lwzx CARG3, BASE, RC
+ | .if FPU
| lfdx f14, BASE, RB
| lfdx f15, BASE, RC
- | checknum cr0, TMP1
- | checknum cr1, TMP2
+ | .else
+ | add TMP1, BASE, RB
+ | add TMP2, BASE, RC
+ | lwz CARG2, 4(TMP1)
+ | lwz CARG4, 4(TMP2)
+ | .endif
+ | checknum cr0, CARG1
+ | checknum cr1, CARG3
| crand 4*cr0+lt, 4*cr0+lt, 4*cr1+lt
| bge ->vmeta_arith_vv
|| break;
@@ -3497,48 +3974,78 @@ static void build_ins(BuildCtx *ctx, BCO
| fsub a, b, a // b - floor(b/c)*c
|.endmacro
|
+ |.macro sfpmod
+ |->BC_MODVN_Z:
+ | stw CARG1, SFSAVE_1
+ | stw CARG2, SFSAVE_2
+ | mr SAVE0, CARG3
+ | mr SAVE1, CARG4
+ | blex __divdf3
+ | blex floor
+ | mr CARG3, SAVE0
+ | mr CARG4, SAVE1
+ | blex __muldf3
+ | mr CARG3, CRET1
+ | mr CARG4, CRET2
+ | lwz CARG1, SFSAVE_1
+ | lwz CARG2, SFSAVE_2
+ | blex __subdf3
+ |.endmacro
+ |
|.macro ins_arithfp, fpins
| ins_arithpre
|.if "fpins" == "fpmod_"
| b ->BC_MODVN_Z // Avoid 3 copies. It's slow anyway.
- |.else
+ |.elif FPU
| fpins f0, f14, f15
| ins_next1
| stfdx f0, BASE, RA
| ins_next2
+ |.else
+ | blex __divdf3 // Only soft-float div uses this macro.
+ | ins_next1
+ | stwux CRET1, RA, BASE
+ | stw CRET2, 4(RA)
+ | ins_next2
|.endif
|.endmacro
|
- |.macro ins_arithdn, intins, fpins
+ |.macro ins_arithdn, intins, fpins, fpcall
| // RA = dst*8, RB = src1*8, RC = src2*8 | num_const*8
||vk = ((int)op - BC_ADDVN) / (BC_ADDNV-BC_ADDVN);
||switch (vk) {
||case 0:
- | lwzux TMP1, RB, BASE
- | lwzux TMP2, RC, KBASE
- | lwz CARG1, 4(RB)
- | checknum cr0, TMP1
- | lwz CARG2, 4(RC)
+ | lwzux CARG1, RB, BASE
+ | lwzux CARG3, RC, KBASE
+ | lwz CARG2, 4(RB)
+ | checknum cr0, CARG1
+ | lwz CARG4, 4(RC)
+ | checknum cr1, CARG3
|| break;
||case 1:
- | lwzux TMP1, RB, BASE
- | lwzux TMP2, RC, KBASE
- | lwz CARG2, 4(RB)
- | checknum cr0, TMP1
- | lwz CARG1, 4(RC)
+ | lwzux CARG3, RB, BASE
+ | lwzux CARG1, RC, KBASE
+ | lwz CARG4, 4(RB)
+ | checknum cr0, CARG3
+ | lwz CARG2, 4(RC)
+ | checknum cr1, CARG1
|| break;
||default:
- | lwzux TMP1, RB, BASE
- | lwzux TMP2, RC, BASE
- | lwz CARG1, 4(RB)
- | checknum cr0, TMP1
- | lwz CARG2, 4(RC)
+ | lwzux CARG1, RB, BASE
+ | lwzux CARG3, RC, BASE
+ | lwz CARG2, 4(RB)
+ | checknum cr0, CARG1
+ | lwz CARG4, 4(RC)
+ | checknum cr1, CARG3
|| break;
||}
- | checknum cr1, TMP2
| bne >5
| bne cr1, >5
- | intins CARG1, CARG1, CARG2
+ |.if "intins" == "intmod"
+ | mr CARG1, CARG2
+ | mr CARG2, CARG4
+ |.endif
+ | intins CARG1, CARG2, CARG4
| bso >4
|1:
| ins_next1
@@ -3550,29 +4057,40 @@ static void build_ins(BuildCtx *ctx, BCO
| checkov TMP0, <1 // Ignore unrelated overflow.
| ins_arithfallback b
|5: // FP variant.
+ |.if FPU
||if (vk == 1) {
| lfd f15, 0(RB)
- | crand 4*cr0+lt, 4*cr0+lt, 4*cr1+lt
| lfd f14, 0(RC)
||} else {
| lfd f14, 0(RB)
- | crand 4*cr0+lt, 4*cr0+lt, 4*cr1+lt
| lfd f15, 0(RC)
||}
+ |.endif
+ | crand 4*cr0+lt, 4*cr0+lt, 4*cr1+lt
| ins_arithfallback bge
|.if "fpins" == "fpmod_"
| b ->BC_MODVN_Z // Avoid 3 copies. It's slow anyway.
|.else
+ |.if FPU
| fpins f0, f14, f15
- | ins_next1
| stfdx f0, BASE, RA
+ |.else
+ |.if "fpcall" == "sfpmod"
+ | sfpmod
+ |.else
+ | blex fpcall
+ |.endif
+ | stwux CRET1, RA, BASE
+ | stw CRET2, 4(RA)
+ |.endif
+ | ins_next1
| b <2
|.endif
|.endmacro
|
- |.macro ins_arith, intins, fpins
+ |.macro ins_arith, intins, fpins, fpcall
|.if DUALNUM
- | ins_arithdn intins, fpins
+ | ins_arithdn intins, fpins, fpcall
|.else
| ins_arithfp fpins
|.endif
@@ -3587,9 +4105,9 @@ static void build_ins(BuildCtx *ctx, BCO
| addo. TMP0, TMP0, TMP3
| add y, a, b
|.endmacro
- | ins_arith addo32., fadd
+ | ins_arith addo32., fadd, __adddf3
|.else
- | ins_arith addo., fadd
+ | ins_arith addo., fadd, __adddf3
|.endif
break;
case BC_SUBVN: case BC_SUBNV: case BC_SUBVV:
@@ -3601,36 +4119,48 @@ static void build_ins(BuildCtx *ctx, BCO
| subo. TMP0, TMP0, TMP3
| sub y, a, b
|.endmacro
- | ins_arith subo32., fsub
+ | ins_arith subo32., fsub, __subdf3
|.else
- | ins_arith subo., fsub
+ | ins_arith subo., fsub, __subdf3
|.endif
break;
case BC_MULVN: case BC_MULNV: case BC_MULVV:
- | ins_arith mullwo., fmul
+ | ins_arith mullwo., fmul, __muldf3
break;
case BC_DIVVN: case BC_DIVNV: case BC_DIVVV:
| ins_arithfp fdiv
break;
case BC_MODVN:
- | ins_arith intmod, fpmod
+ | ins_arith intmod, fpmod, sfpmod
break;
case BC_MODNV: case BC_MODVV:
- | ins_arith intmod, fpmod_
+ | ins_arith intmod, fpmod_, sfpmod
break;
case BC_POW:
| // NYI: (partial) integer arithmetic.
- | lwzx TMP1, BASE, RB
+ | lwzx CARG1, BASE, RB
+ | lwzx CARG3, BASE, RC
+ |.if FPU
| lfdx FARG1, BASE, RB
- | lwzx TMP2, BASE, RC
| lfdx FARG2, BASE, RC
- | checknum cr0, TMP1
- | checknum cr1, TMP2
+ |.else
+ | add TMP1, BASE, RB
+ | add TMP2, BASE, RC
+ | lwz CARG2, 4(TMP1)
+ | lwz CARG4, 4(TMP2)
+ |.endif
+ | checknum cr0, CARG1
+ | checknum cr1, CARG3
| crand 4*cr0+lt, 4*cr0+lt, 4*cr1+lt
| bge ->vmeta_arith_vv
| blex pow
| ins_next1
+ |.if FPU
| stfdx FARG1, BASE, RA
+ |.else
+ | stwux CARG1, RA, BASE
+ | stw CARG2, 4(RA)
+ |.endif
| ins_next2
break;
@@ -3650,8 +4180,15 @@ static void build_ins(BuildCtx *ctx, BCO
| lp BASE, L->base
| bne ->vmeta_binop
| ins_next1
+ |.if FPU
| lfdx f0, BASE, SAVE0 // Copy result from RB to RA.
| stfdx f0, BASE, RA
+ |.else
+ | lwzux TMP0, SAVE0, BASE
+ | lwz TMP1, 4(SAVE0)
+ | stwux TMP0, RA, BASE
+ | stw TMP1, 4(RA)
+ |.endif
| ins_next2
break;
@@ -3714,8 +4251,15 @@ static void build_ins(BuildCtx *ctx, BCO
case BC_KNUM:
| // RA = dst*8, RD = num_const*8
| ins_next1
+ |.if FPU
| lfdx f0, KBASE, RD
| stfdx f0, BASE, RA
+ |.else
+ | lwzux TMP0, RD, KBASE
+ | lwz TMP1, 4(RD)
+ | stwux TMP0, RA, BASE
+ | stw TMP1, 4(RA)
+ |.endif
| ins_next2
break;
case BC_KPRI:
@@ -3748,8 +4292,15 @@ static void build_ins(BuildCtx *ctx, BCO
| lwzx UPVAL:RB, LFUNC:RB, RD
| ins_next1
| lwz TMP1, UPVAL:RB->v
+ |.if FPU
| lfd f0, 0(TMP1)
| stfdx f0, BASE, RA
+ |.else
+ | lwz TMP2, 0(TMP1)
+ | lwz TMP3, 4(TMP1)
+ | stwux TMP2, RA, BASE
+ | stw TMP3, 4(RA)
+ |.endif
| ins_next2
break;
case BC_USETV:
@@ -3757,14 +4308,24 @@ static void build_ins(BuildCtx *ctx, BCO
| lwz LFUNC:RB, FRAME_FUNC(BASE)
| srwi RA, RA, 1
| addi RA, RA, offsetof(GCfuncL, uvptr)
+ |.if FPU
| lfdux f0, RD, BASE
+ |.else
+ | lwzux CARG1, RD, BASE
+ | lwz CARG3, 4(RD)
+ |.endif
| lwzx UPVAL:RB, LFUNC:RB, RA
| lbz TMP3, UPVAL:RB->marked
| lwz CARG2, UPVAL:RB->v
| andix. TMP3, TMP3, LJ_GC_BLACK // isblack(uv)
| lbz TMP0, UPVAL:RB->closed
| lwz TMP2, 0(RD)
+ |.if FPU
| stfd f0, 0(CARG2)
+ |.else
+ | stw CARG1, 0(CARG2)
+ | stw CARG3, 4(CARG2)
+ |.endif
| cmplwi cr1, TMP0, 0
| lwz TMP1, 4(RD)
| cror 4*cr0+eq, 4*cr0+eq, 4*cr1+eq
@@ -3820,11 +4381,21 @@ static void build_ins(BuildCtx *ctx, BCO
| lwz LFUNC:RB, FRAME_FUNC(BASE)
| srwi RA, RA, 1
| addi RA, RA, offsetof(GCfuncL, uvptr)
+ |.if FPU
| lfdx f0, KBASE, RD
+ |.else
+ | lwzux TMP2, RD, KBASE
+ | lwz TMP3, 4(RD)
+ |.endif
| lwzx UPVAL:RB, LFUNC:RB, RA
| ins_next1
| lwz TMP1, UPVAL:RB->v
+ |.if FPU
| stfd f0, 0(TMP1)
+ |.else
+ | stw TMP2, 0(TMP1)
+ | stw TMP3, 4(TMP1)
+ |.endif
| ins_next2
break;
case BC_USETP:
@@ -3972,11 +4543,21 @@ static void build_ins(BuildCtx *ctx, BCO
|.endif
| ble ->vmeta_tgetv // Integer key and in array part?
| lwzx TMP0, TMP1, TMP2
+ |.if FPU
| lfdx f14, TMP1, TMP2
+ |.else
+ | lwzux SAVE0, TMP1, TMP2
+ | lwz SAVE1, 4(TMP1)
+ |.endif
| checknil TMP0; beq >2
|1:
| ins_next1
+ |.if FPU
| stfdx f14, BASE, RA
+ |.else
+ | stwux SAVE0, RA, BASE
+ | stw SAVE1, 4(RA)
+ |.endif
| ins_next2
|
|2: // Check for __index if table value is nil.
@@ -4052,12 +4633,22 @@ static void build_ins(BuildCtx *ctx, BCO
| lwz TMP1, TAB:RB->asize
| lwz TMP2, TAB:RB->array
| cmplw TMP0, TMP1; bge ->vmeta_tgetb
+ |.if FPU
| lwzx TMP1, TMP2, RC
| lfdx f0, TMP2, RC
+ |.else
+ | lwzux TMP1, TMP2, RC
+ | lwz TMP3, 4(TMP2)
+ |.endif
| checknil TMP1; beq >5
|1:
| ins_next1
+ |.if FPU
| stfdx f0, BASE, RA
+ |.else
+ | stwux TMP1, RA, BASE
+ | stw TMP3, 4(RA)
+ |.endif
| ins_next2
|
|5: // Check for __index if table value is nil.
@@ -4087,10 +4678,20 @@ static void build_ins(BuildCtx *ctx, BCO
| cmplw TMP0, CARG2
| slwi TMP2, CARG2, 3
| ble ->vmeta_tgetr // In array part?
+ |.if FPU
| lfdx f14, TMP1, TMP2
+ |.else
+ | lwzux SAVE0, TMP2, TMP1
+ | lwz SAVE1, 4(TMP2)
+ |.endif
|->BC_TGETR_Z:
| ins_next1
+ |.if FPU
| stfdx f14, BASE, RA
+ |.else
+ | stwux SAVE0, RA, BASE
+ | stw SAVE1, 4(RA)
+ |.endif
| ins_next2
break;
@@ -4131,11 +4732,22 @@ static void build_ins(BuildCtx *ctx, BCO
| ble ->vmeta_tsetv // Integer key and in array part?
| lwzx TMP2, TMP1, TMP0
| lbz TMP3, TAB:RB->marked
+ |.if FPU
| lfdx f14, BASE, RA
+ |.else
+ | add SAVE1, BASE, RA
+ | lwz SAVE0, 0(SAVE1)
+ | lwz SAVE1, 4(SAVE1)
+ |.endif
| checknil TMP2; beq >3
|1:
| andix. TMP2, TMP3, LJ_GC_BLACK // isblack(table)
+ |.if FPU
| stfdx f14, TMP1, TMP0
+ |.else
+ | stwux SAVE0, TMP1, TMP0
+ | stw SAVE1, 4(TMP1)
+ |.endif
| bne >7
|2:
| ins_next
@@ -4176,7 +4788,13 @@ static void build_ins(BuildCtx *ctx, BCO
| lwz NODE:TMP2, TAB:RB->node
| stb ZERO, TAB:RB->nomm // Clear metamethod cache.
| and TMP1, TMP1, TMP0 // idx = str->hash & tab->hmask
+ |.if FPU
| lfdx f14, BASE, RA
+ |.else
+ | add CARG2, BASE, RA
+ | lwz SAVE0, 0(CARG2)
+ | lwz SAVE1, 4(CARG2)
+ |.endif
| slwi TMP0, TMP1, 5
| slwi TMP1, TMP1, 3
| sub TMP1, TMP0, TMP1
@@ -4192,7 +4810,12 @@ static void build_ins(BuildCtx *ctx, BCO
| checknil CARG2; beq >4 // Key found, but nil value?
|2:
| andix. TMP0, TMP3, LJ_GC_BLACK // isblack(table)
+ |.if FPU
| stfd f14, NODE:TMP2->val
+ |.else
+ | stw SAVE0, NODE:TMP2->val.u32.hi
+ | stw SAVE1, NODE:TMP2->val.u32.lo
+ |.endif
| bne >7
|3:
| ins_next
@@ -4231,7 +4854,12 @@ static void build_ins(BuildCtx *ctx, BCO
| bl extern lj_tab_newkey // (lua_State *L, GCtab *t, TValue *k)
| // Returns TValue *.
| lp BASE, L->base
+ |.if FPU
| stfd f14, 0(CRET1)
+ |.else
+ | stw SAVE0, 0(CRET1)
+ | stw SAVE1, 4(CRET1)
+ |.endif
| b <3 // No 2nd write barrier needed.
|
|7: // Possible table write barrier for the value. Skip valiswhite check.
@@ -4248,13 +4876,24 @@ static void build_ins(BuildCtx *ctx, BCO
| lwz TMP2, TAB:RB->array
| lbz TMP3, TAB:RB->marked
| cmplw TMP0, TMP1
+ |.if FPU
| lfdx f14, BASE, RA
+ |.else
+ | add CARG2, BASE, RA
+ | lwz SAVE0, 0(CARG2)
+ | lwz SAVE1, 4(CARG2)
+ |.endif
| bge ->vmeta_tsetb
| lwzx TMP1, TMP2, RC
| checknil TMP1; beq >5
|1:
| andix. TMP0, TMP3, LJ_GC_BLACK // isblack(table)
+ |.if FPU
| stfdx f14, TMP2, RC
+ |.else
+ | stwux SAVE0, RC, TMP2
+ | stw SAVE1, 4(RC)
+ |.endif
| bne >7
|2:
| ins_next
@@ -4294,10 +4933,20 @@ static void build_ins(BuildCtx *ctx, BCO
|2:
| cmplw TMP0, CARG3
| slwi TMP2, CARG3, 3
+ |.if FPU
| lfdx f14, BASE, RA
+ |.else
+ | lwzux SAVE0, RA, BASE
+ | lwz SAVE1, 4(RA)
+ |.endif
| ble ->vmeta_tsetr // In array part?
| ins_next1
+ |.if FPU
| stfdx f14, TMP1, TMP2
+ |.else
+ | stwux SAVE0, TMP1, TMP2
+ | stw SAVE1, 4(TMP1)
+ |.endif
| ins_next2
|
|7: // Possible table write barrier for the value. Skip valiswhite check.
@@ -4327,10 +4976,20 @@ static void build_ins(BuildCtx *ctx, BCO
| add TMP1, TMP1, TMP0
| andix. TMP0, TMP3, LJ_GC_BLACK // isblack(table)
|3: // Copy result slots to table.
+ |.if FPU
| lfd f0, 0(RA)
+ |.else
+ | lwz SAVE0, 0(RA)
+ | lwz SAVE1, 4(RA)
+ |.endif
| addi RA, RA, 8
| cmpw cr1, RA, TMP2
+ |.if FPU
| stfd f0, 0(TMP1)
+ |.else
+ | stw SAVE0, 0(TMP1)
+ | stw SAVE1, 4(TMP1)
+ |.endif
| addi TMP1, TMP1, 8
| blt cr1, <3
| bne >7
@@ -4397,9 +5056,20 @@ static void build_ins(BuildCtx *ctx, BCO
| beq cr1, >3
|2:
| addi TMP3, TMP2, 8
+ |.if FPU
| lfdx f0, RA, TMP2
+ |.else
+ | add CARG3, RA, TMP2
+ | lwz CARG1, 0(CARG3)
+ | lwz CARG2, 4(CARG3)
+ |.endif
| cmplw cr1, TMP3, NARGS8:RC
+ |.if FPU
| stfdx f0, BASE, TMP2
+ |.else
+ | stwux CARG1, TMP2, BASE
+ | stw CARG2, 4(TMP2)
+ |.endif
| mr TMP2, TMP3
| bne cr1, <2
|3:
@@ -4432,14 +5102,28 @@ static void build_ins(BuildCtx *ctx, BCO
| add BASE, BASE, RA
| lwz TMP1, -24(BASE)
| lwz LFUNC:RB, -20(BASE)
+ |.if FPU
| lfd f1, -8(BASE)
| lfd f0, -16(BASE)
+ |.else
+ | lwz CARG1, -8(BASE)
+ | lwz CARG2, -4(BASE)
+ | lwz CARG3, -16(BASE)
+ | lwz CARG4, -12(BASE)
+ |.endif
| stw TMP1, 0(BASE) // Copy callable.
| stw LFUNC:RB, 4(BASE)
| checkfunc TMP1
- | stfd f1, 16(BASE) // Copy control var.
| li NARGS8:RC, 16 // Iterators get 2 arguments.
+ |.if FPU
+ | stfd f1, 16(BASE) // Copy control var.
| stfdu f0, 8(BASE) // Copy state.
+ |.else
+ | stw CARG1, 16(BASE) // Copy control var.
+ | stw CARG2, 20(BASE)
+ | stwu CARG3, 8(BASE) // Copy state.
+ | stw CARG4, 4(BASE)
+ |.endif
| bne ->vmeta_call
| ins_call
break;
@@ -4460,7 +5144,12 @@ static void build_ins(BuildCtx *ctx, BCO
| slwi TMP3, RC, 3
| bge >5 // Index points after array part?
| lwzx TMP2, TMP1, TMP3
+ |.if FPU
| lfdx f0, TMP1, TMP3
+ |.else
+ | lwzux CARG1, TMP3, TMP1
+ | lwz CARG2, 4(TMP3)
+ |.endif
| checknil TMP2
| lwz INS, -4(PC)
| beq >4
@@ -4472,7 +5161,12 @@ static void build_ins(BuildCtx *ctx, BCO
|.endif
| addi RC, RC, 1
| addis TMP3, PC, -(BCBIAS_J*4 >> 16)
+ |.if FPU
| stfd f0, 8(RA)
+ |.else
+ | stw CARG1, 8(RA)
+ | stw CARG2, 12(RA)
+ |.endif
| decode_RD4 TMP1, INS
| stw RC, -4(RA) // Update control var.
| add PC, TMP1, TMP3
@@ -4497,17 +5191,38 @@ static void build_ins(BuildCtx *ctx, BCO
| slwi RB, RC, 3
| sub TMP3, TMP3, RB
| lwzx RB, TMP2, TMP3
+ |.if FPU
| lfdx f0, TMP2, TMP3
+ |.else
+ | add CARG3, TMP2, TMP3
+ | lwz CARG1, 0(CARG3)
+ | lwz CARG2, 4(CARG3)
+ |.endif
| add NODE:TMP3, TMP2, TMP3
| checknil RB
| lwz INS, -4(PC)
| beq >7
+ |.if FPU
| lfd f1, NODE:TMP3->key
+ |.else
+ | lwz CARG3, NODE:TMP3->key.u32.hi
+ | lwz CARG4, NODE:TMP3->key.u32.lo
+ |.endif
| addis TMP2, PC, -(BCBIAS_J*4 >> 16)
+ |.if FPU
| stfd f0, 8(RA)
+ |.else
+ | stw CARG1, 8(RA)
+ | stw CARG2, 12(RA)
+ |.endif
| add RC, RC, TMP0
| decode_RD4 TMP1, INS
+ |.if FPU
| stfd f1, 0(RA)
+ |.else
+ | stw CARG3, 0(RA)
+ | stw CARG4, 4(RA)
+ |.endif
| addi RC, RC, 1
| add PC, TMP1, TMP2
| stw RC, -4(RA) // Update control var.
@@ -4573,9 +5288,19 @@ static void build_ins(BuildCtx *ctx, BCO
| subi TMP2, TMP2, 16
| ble >2 // No vararg slots?
|1: // Copy vararg slots to destination slots.
+ |.if FPU
| lfd f0, 0(RC)
+ |.else
+ | lwz CARG1, 0(RC)
+ | lwz CARG2, 4(RC)
+ |.endif
| addi RC, RC, 8
+ |.if FPU
| stfd f0, 0(RA)
+ |.else
+ | stw CARG1, 0(RA)
+ | stw CARG2, 4(RA)
+ |.endif
| cmplw RA, TMP2
| cmplw cr1, RC, TMP3
| bge >3 // All destination slots filled?
@@ -4598,9 +5323,19 @@ static void build_ins(BuildCtx *ctx, BCO
| addi MULTRES, TMP1, 8
| bgt >7
|6:
+ |.if FPU
| lfd f0, 0(RC)
+ |.else
+ | lwz CARG1, 0(RC)
+ | lwz CARG2, 4(RC)
+ |.endif
| addi RC, RC, 8
+ |.if FPU
| stfd f0, 0(RA)
+ |.else
+ | stw CARG1, 0(RA)
+ | stw CARG2, 4(RA)
+ |.endif
| cmplw RC, TMP3
| addi RA, RA, 8
| blt <6 // More vararg slots?
@@ -4651,14 +5386,38 @@ static void build_ins(BuildCtx *ctx, BCO
| li TMP1, 0
|2:
| addi TMP3, TMP1, 8
+ |.if FPU
| lfdx f0, RA, TMP1
+ |.else
+ | add CARG3, RA, TMP1
+ | lwz CARG1, 0(CARG3)
+ | lwz CARG2, 4(CARG3)
+ |.endif
| cmpw TMP3, RC
+ |.if FPU
| stfdx f0, TMP2, TMP1
+ |.else
+ | add CARG3, TMP2, TMP1
+ | stw CARG1, 0(CARG3)
+ | stw CARG2, 4(CARG3)
+ |.endif
| beq >3
| addi TMP1, TMP3, 8
+ |.if FPU
| lfdx f1, RA, TMP3
+ |.else
+ | add CARG3, RA, TMP3
+ | lwz CARG1, 0(CARG3)
+ | lwz CARG2, 4(CARG3)
+ |.endif
| cmpw TMP1, RC
+ |.if FPU
| stfdx f1, TMP2, TMP3
+ |.else
+ | add CARG3, TMP2, TMP3
+ | stw CARG1, 0(CARG3)
+ | stw CARG2, 4(CARG3)
+ |.endif
| bne <2
|3:
|5:
@@ -4700,8 +5459,15 @@ static void build_ins(BuildCtx *ctx, BCO
| subi TMP2, BASE, 8
| decode_RB8 RB, INS
if (op == BC_RET1) {
+ |.if FPU
| lfd f0, 0(RA)
| stfd f0, 0(TMP2)
+ |.else
+ | lwz CARG1, 0(RA)
+ | lwz CARG2, 4(RA)
+ | stw CARG1, 0(TMP2)
+ | stw CARG2, 4(TMP2)
+ |.endif
}
|5:
| cmplw RB, RD
@@ -4762,11 +5528,11 @@ static void build_ins(BuildCtx *ctx, BCO
|4:
| stw CARG1, FORL_IDX*8+4(RA)
} else {
- | lwz TMP3, FORL_STEP*8(RA)
+ | lwz SAVE0, FORL_STEP*8(RA)
| lwz CARG3, FORL_STEP*8+4(RA)
| lwz TMP2, FORL_STOP*8(RA)
| lwz CARG2, FORL_STOP*8+4(RA)
- | cmplw cr7, TMP3, TISNUM
+ | cmplw cr7, SAVE0, TISNUM
| cmplw cr1, TMP2, TISNUM
| crand 4*cr0+eq, 4*cr0+eq, 4*cr7+eq
| crand 4*cr0+eq, 4*cr0+eq, 4*cr1+eq
@@ -4809,41 +5575,80 @@ static void build_ins(BuildCtx *ctx, BCO
if (vk) {
|.if DUALNUM
|9: // FP loop.
+ |.if FPU
| lfd f1, FORL_IDX*8(RA)
|.else
+ | lwz CARG1, FORL_IDX*8(RA)
+ | lwz CARG2, FORL_IDX*8+4(RA)
+ |.endif
+ |.else
| lfdux f1, RA, BASE
|.endif
+ |.if FPU
| lfd f3, FORL_STEP*8(RA)
| lfd f2, FORL_STOP*8(RA)
- | lwz TMP3, FORL_STEP*8(RA)
| fadd f1, f1, f3
| stfd f1, FORL_IDX*8(RA)
+ |.else
+ | lwz CARG3, FORL_STEP*8(RA)
+ | lwz CARG4, FORL_STEP*8+4(RA)
+ | mr SAVE1, RD
+ | blex __adddf3
+ | mr RD, SAVE1
+ | stw CRET1, FORL_IDX*8(RA)
+ | stw CRET2, FORL_IDX*8+4(RA)
+ | lwz CARG3, FORL_STOP*8(RA)
+ | lwz CARG4, FORL_STOP*8+4(RA)
+ |.endif
+ | lwz SAVE0, FORL_STEP*8(RA)
} else {
|.if DUALNUM
|9: // FP loop.
|.else
| lwzux TMP1, RA, BASE
- | lwz TMP3, FORL_STEP*8(RA)
+ | lwz SAVE0, FORL_STEP*8(RA)
| lwz TMP2, FORL_STOP*8(RA)
| cmplw cr0, TMP1, TISNUM
- | cmplw cr7, TMP3, TISNUM
+ | cmplw cr7, SAVE0, TISNUM
| cmplw cr1, TMP2, TISNUM
|.endif
+ |.if FPU
| lfd f1, FORL_IDX*8(RA)
+ |.else
+ | lwz CARG1, FORL_IDX*8(RA)
+ | lwz CARG2, FORL_IDX*8+4(RA)
+ |.endif
| crand 4*cr0+lt, 4*cr0+lt, 4*cr7+lt
| crand 4*cr0+lt, 4*cr0+lt, 4*cr1+lt
+ |.if FPU
| lfd f2, FORL_STOP*8(RA)
+ |.else
+ | lwz CARG3, FORL_STOP*8(RA)
+ | lwz CARG4, FORL_STOP*8+4(RA)
+ |.endif
| bge ->vmeta_for
}
- | cmpwi cr6, TMP3, 0
+ | cmpwi cr6, SAVE0, 0
if (op != BC_JFORL) {
| srwi RD, RD, 1
}
+ |.if FPU
| stfd f1, FORL_EXT*8(RA)
+ |.else
+ | stw CARG1, FORL_EXT*8(RA)
+ | stw CARG2, FORL_EXT*8+4(RA)
+ |.endif
if (op != BC_JFORL) {
| add RD, PC, RD
}
+ |.if FPU
| fcmpu cr0, f1, f2
+ |.else
+ | mr SAVE1, RD
+ | blex __ledf2
+ | cmpwi CRET1, 0
+ | mr RD, SAVE1
+ |.endif
if (op == BC_JFORI) {
| addis PC, RD, -(BCBIAS_J*4 >> 16)
}
|