1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893
|
/* Copyright (C) 1994, 1995, 1997, 1998, 1999, 2000, 2001, 2002, 2003,
2004, 2005, 2006
Free Software Foundation, Inc.
This file is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 2, or (at your option) any
later version.
In addition to the permissions in the GNU General Public License, the
Free Software Foundation gives you unlimited permission to link the
compiled version of this file into combinations with other programs,
and to distribute those combinations without any restriction coming
from the use of this file. (The General Public License restrictions
do apply in other respects; for example, they cover modification of
the file, and distribution when not linked into a combine
executable.)
This file is distributed in the hope that it will be useful, but
WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; see the file COPYING. If not, write to
the Free Software Foundation, 51 Franklin Street, Fifth Floor,
Boston, MA 02110-1301, USA. */
!! libgcc routines for the Renesas / SuperH SH CPUs.
!! Contributed by Steve Chamberlain.
!! sac@cygnus.com
!! ashiftrt_r4_x, ___ashrsi3, ___ashlsi3, ___lshrsi3 routines
!! recoded in assembly by Toshiyasu Morita
!! tm@netcom.com
/* SH2 optimizations for ___ashrsi3, ___ashlsi3, ___lshrsi3 and
ELF local label prefixes by J"orn Rennecke
amylaar@cygnus.com */
#include "lib1funcs.h"
#if ! __SH5__
#ifdef L_ashiftrt
.global GLOBAL(ashiftrt_r4_0)
.global GLOBAL(ashiftrt_r4_1)
.global GLOBAL(ashiftrt_r4_2)
.global GLOBAL(ashiftrt_r4_3)
.global GLOBAL(ashiftrt_r4_4)
.global GLOBAL(ashiftrt_r4_5)
.global GLOBAL(ashiftrt_r4_6)
.global GLOBAL(ashiftrt_r4_7)
.global GLOBAL(ashiftrt_r4_8)
.global GLOBAL(ashiftrt_r4_9)
.global GLOBAL(ashiftrt_r4_10)
.global GLOBAL(ashiftrt_r4_11)
.global GLOBAL(ashiftrt_r4_12)
.global GLOBAL(ashiftrt_r4_13)
.global GLOBAL(ashiftrt_r4_14)
.global GLOBAL(ashiftrt_r4_15)
.global GLOBAL(ashiftrt_r4_16)
.global GLOBAL(ashiftrt_r4_17)
.global GLOBAL(ashiftrt_r4_18)
.global GLOBAL(ashiftrt_r4_19)
.global GLOBAL(ashiftrt_r4_20)
.global GLOBAL(ashiftrt_r4_21)
.global GLOBAL(ashiftrt_r4_22)
.global GLOBAL(ashiftrt_r4_23)
.global GLOBAL(ashiftrt_r4_24)
.global GLOBAL(ashiftrt_r4_25)
.global GLOBAL(ashiftrt_r4_26)
.global GLOBAL(ashiftrt_r4_27)
.global GLOBAL(ashiftrt_r4_28)
.global GLOBAL(ashiftrt_r4_29)
.global GLOBAL(ashiftrt_r4_30)
.global GLOBAL(ashiftrt_r4_31)
.global GLOBAL(ashiftrt_r4_32)
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_0))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_1))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_2))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_3))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_4))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_5))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_6))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_7))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_8))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_9))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_10))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_11))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_12))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_13))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_14))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_15))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_16))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_17))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_18))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_19))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_20))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_21))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_22))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_23))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_24))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_25))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_26))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_27))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_28))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_29))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_30))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_31))
HIDDEN_FUNC(GLOBAL(ashiftrt_r4_32))
.align 1
GLOBAL(ashiftrt_r4_32):
GLOBAL(ashiftrt_r4_31):
rotcl r4
rts
subc r4,r4
GLOBAL(ashiftrt_r4_30):
shar r4
GLOBAL(ashiftrt_r4_29):
shar r4
GLOBAL(ashiftrt_r4_28):
shar r4
GLOBAL(ashiftrt_r4_27):
shar r4
GLOBAL(ashiftrt_r4_26):
shar r4
GLOBAL(ashiftrt_r4_25):
shar r4
GLOBAL(ashiftrt_r4_24):
shlr16 r4
shlr8 r4
rts
exts.b r4,r4
GLOBAL(ashiftrt_r4_23):
shar r4
GLOBAL(ashiftrt_r4_22):
shar r4
GLOBAL(ashiftrt_r4_21):
shar r4
GLOBAL(ashiftrt_r4_20):
shar r4
GLOBAL(ashiftrt_r4_19):
shar r4
GLOBAL(ashiftrt_r4_18):
shar r4
GLOBAL(ashiftrt_r4_17):
shar r4
GLOBAL(ashiftrt_r4_16):
shlr16 r4
rts
exts.w r4,r4
GLOBAL(ashiftrt_r4_15):
shar r4
GLOBAL(ashiftrt_r4_14):
shar r4
GLOBAL(ashiftrt_r4_13):
shar r4
GLOBAL(ashiftrt_r4_12):
shar r4
GLOBAL(ashiftrt_r4_11):
shar r4
GLOBAL(ashiftrt_r4_10):
shar r4
GLOBAL(ashiftrt_r4_9):
shar r4
GLOBAL(ashiftrt_r4_8):
shar r4
GLOBAL(ashiftrt_r4_7):
shar r4
GLOBAL(ashiftrt_r4_6):
shar r4
GLOBAL(ashiftrt_r4_5):
shar r4
GLOBAL(ashiftrt_r4_4):
shar r4
GLOBAL(ashiftrt_r4_3):
shar r4
GLOBAL(ashiftrt_r4_2):
shar r4
GLOBAL(ashiftrt_r4_1):
rts
shar r4
GLOBAL(ashiftrt_r4_0):
rts
nop
ENDFUNC(GLOBAL(ashiftrt_r4_0))
ENDFUNC(GLOBAL(ashiftrt_r4_1))
ENDFUNC(GLOBAL(ashiftrt_r4_2))
ENDFUNC(GLOBAL(ashiftrt_r4_3))
ENDFUNC(GLOBAL(ashiftrt_r4_4))
ENDFUNC(GLOBAL(ashiftrt_r4_5))
ENDFUNC(GLOBAL(ashiftrt_r4_6))
ENDFUNC(GLOBAL(ashiftrt_r4_7))
ENDFUNC(GLOBAL(ashiftrt_r4_8))
ENDFUNC(GLOBAL(ashiftrt_r4_9))
ENDFUNC(GLOBAL(ashiftrt_r4_10))
ENDFUNC(GLOBAL(ashiftrt_r4_11))
ENDFUNC(GLOBAL(ashiftrt_r4_12))
ENDFUNC(GLOBAL(ashiftrt_r4_13))
ENDFUNC(GLOBAL(ashiftrt_r4_14))
ENDFUNC(GLOBAL(ashiftrt_r4_15))
ENDFUNC(GLOBAL(ashiftrt_r4_16))
ENDFUNC(GLOBAL(ashiftrt_r4_17))
ENDFUNC(GLOBAL(ashiftrt_r4_18))
ENDFUNC(GLOBAL(ashiftrt_r4_19))
ENDFUNC(GLOBAL(ashiftrt_r4_20))
ENDFUNC(GLOBAL(ashiftrt_r4_21))
ENDFUNC(GLOBAL(ashiftrt_r4_22))
ENDFUNC(GLOBAL(ashiftrt_r4_23))
ENDFUNC(GLOBAL(ashiftrt_r4_24))
ENDFUNC(GLOBAL(ashiftrt_r4_25))
ENDFUNC(GLOBAL(ashiftrt_r4_26))
ENDFUNC(GLOBAL(ashiftrt_r4_27))
ENDFUNC(GLOBAL(ashiftrt_r4_28))
ENDFUNC(GLOBAL(ashiftrt_r4_29))
ENDFUNC(GLOBAL(ashiftrt_r4_30))
ENDFUNC(GLOBAL(ashiftrt_r4_31))
ENDFUNC(GLOBAL(ashiftrt_r4_32))
#endif
#ifdef L_ashiftrt_n
!
! GLOBAL(ashrsi3)
!
! Entry:
!
! r4: Value to shift
! r5: Shifts
!
! Exit:
!
! r0: Result
!
! Destroys:
!
! (none)
!
.global GLOBAL(ashrsi3)
HIDDEN_FUNC(GLOBAL(ashrsi3))
.align 2
GLOBAL(ashrsi3):
mov #31,r0
and r0,r5
mova LOCAL(ashrsi3_table),r0
mov.b @(r0,r5),r5
#ifdef __sh1__
add r5,r0
jmp @r0
#else
braf r5
#endif
mov r4,r0
.align 2
LOCAL(ashrsi3_table):
.byte LOCAL(ashrsi3_0)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_1)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_2)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_3)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_4)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_5)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_6)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_7)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_8)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_9)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_10)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_11)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_12)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_13)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_14)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_15)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_16)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_17)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_18)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_19)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_20)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_21)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_22)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_23)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_24)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_25)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_26)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_27)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_28)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_29)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_30)-LOCAL(ashrsi3_table)
.byte LOCAL(ashrsi3_31)-LOCAL(ashrsi3_table)
LOCAL(ashrsi3_31):
rotcl r0
rts
subc r0,r0
LOCAL(ashrsi3_30):
shar r0
LOCAL(ashrsi3_29):
shar r0
LOCAL(ashrsi3_28):
shar r0
LOCAL(ashrsi3_27):
shar r0
LOCAL(ashrsi3_26):
shar r0
LOCAL(ashrsi3_25):
shar r0
LOCAL(ashrsi3_24):
shlr16 r0
shlr8 r0
rts
exts.b r0,r0
LOCAL(ashrsi3_23):
shar r0
LOCAL(ashrsi3_22):
shar r0
LOCAL(ashrsi3_21):
shar r0
LOCAL(ashrsi3_20):
shar r0
LOCAL(ashrsi3_19):
shar r0
LOCAL(ashrsi3_18):
shar r0
LOCAL(ashrsi3_17):
shar r0
LOCAL(ashrsi3_16):
shlr16 r0
rts
exts.w r0,r0
LOCAL(ashrsi3_15):
shar r0
LOCAL(ashrsi3_14):
shar r0
LOCAL(ashrsi3_13):
shar r0
LOCAL(ashrsi3_12):
shar r0
LOCAL(ashrsi3_11):
shar r0
LOCAL(ashrsi3_10):
shar r0
LOCAL(ashrsi3_9):
shar r0
LOCAL(ashrsi3_8):
shar r0
LOCAL(ashrsi3_7):
shar r0
LOCAL(ashrsi3_6):
shar r0
LOCAL(ashrsi3_5):
shar r0
LOCAL(ashrsi3_4):
shar r0
LOCAL(ashrsi3_3):
shar r0
LOCAL(ashrsi3_2):
shar r0
LOCAL(ashrsi3_1):
rts
shar r0
LOCAL(ashrsi3_0):
rts
nop
ENDFUNC(GLOBAL(ashrsi3))
#endif
#ifdef L_ashiftlt
!
! GLOBAL(ashlsi3)
!
! Entry:
!
! r4: Value to shift
! r5: Shifts
!
! Exit:
!
! r0: Result
!
! Destroys:
!
! (none)
!
.global GLOBAL(ashlsi3)
HIDDEN_FUNC(GLOBAL(ashlsi3))
.align 2
GLOBAL(ashlsi3):
mov #31,r0
and r0,r5
mova LOCAL(ashlsi3_table),r0
mov.b @(r0,r5),r5
#ifdef __sh1__
add r5,r0
jmp @r0
#else
braf r5
#endif
mov r4,r0
.align 2
LOCAL(ashlsi3_table):
.byte LOCAL(ashlsi3_0)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_1)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_2)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_3)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_4)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_5)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_6)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_7)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_8)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_9)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_10)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_11)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_12)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_13)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_14)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_15)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_16)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_17)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_18)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_19)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_20)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_21)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_22)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_23)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_24)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_25)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_26)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_27)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_28)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_29)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_30)-LOCAL(ashlsi3_table)
.byte LOCAL(ashlsi3_31)-LOCAL(ashlsi3_table)
LOCAL(ashlsi3_6):
shll2 r0
LOCAL(ashlsi3_4):
shll2 r0
LOCAL(ashlsi3_2):
rts
shll2 r0
LOCAL(ashlsi3_7):
shll2 r0
LOCAL(ashlsi3_5):
shll2 r0
LOCAL(ashlsi3_3):
shll2 r0
LOCAL(ashlsi3_1):
rts
shll r0
LOCAL(ashlsi3_14):
shll2 r0
LOCAL(ashlsi3_12):
shll2 r0
LOCAL(ashlsi3_10):
shll2 r0
LOCAL(ashlsi3_8):
rts
shll8 r0
LOCAL(ashlsi3_15):
shll2 r0
LOCAL(ashlsi3_13):
shll2 r0
LOCAL(ashlsi3_11):
shll2 r0
LOCAL(ashlsi3_9):
shll8 r0
rts
shll r0
LOCAL(ashlsi3_22):
shll2 r0
LOCAL(ashlsi3_20):
shll2 r0
LOCAL(ashlsi3_18):
shll2 r0
LOCAL(ashlsi3_16):
rts
shll16 r0
LOCAL(ashlsi3_23):
shll2 r0
LOCAL(ashlsi3_21):
shll2 r0
LOCAL(ashlsi3_19):
shll2 r0
LOCAL(ashlsi3_17):
shll16 r0
rts
shll r0
LOCAL(ashlsi3_30):
shll2 r0
LOCAL(ashlsi3_28):
shll2 r0
LOCAL(ashlsi3_26):
shll2 r0
LOCAL(ashlsi3_24):
shll16 r0
rts
shll8 r0
LOCAL(ashlsi3_31):
shll2 r0
LOCAL(ashlsi3_29):
shll2 r0
LOCAL(ashlsi3_27):
shll2 r0
LOCAL(ashlsi3_25):
shll16 r0
shll8 r0
rts
shll r0
LOCAL(ashlsi3_0):
rts
nop
ENDFUNC(GLOBAL(ashlsi3))
#endif
#ifdef L_lshiftrt
!
! GLOBAL(lshrsi3)
!
! Entry:
!
! r4: Value to shift
! r5: Shifts
!
! Exit:
!
! r0: Result
!
! Destroys:
!
! (none)
!
.global GLOBAL(lshrsi3)
HIDDEN_FUNC(GLOBAL(lshrsi3))
.align 2
GLOBAL(lshrsi3):
mov #31,r0
and r0,r5
mova LOCAL(lshrsi3_table),r0
mov.b @(r0,r5),r5
#ifdef __sh1__
add r5,r0
jmp @r0
#else
braf r5
#endif
mov r4,r0
.align 2
LOCAL(lshrsi3_table):
.byte LOCAL(lshrsi3_0)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_1)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_2)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_3)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_4)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_5)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_6)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_7)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_8)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_9)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_10)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_11)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_12)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_13)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_14)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_15)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_16)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_17)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_18)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_19)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_20)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_21)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_22)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_23)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_24)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_25)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_26)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_27)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_28)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_29)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_30)-LOCAL(lshrsi3_table)
.byte LOCAL(lshrsi3_31)-LOCAL(lshrsi3_table)
LOCAL(lshrsi3_6):
shlr2 r0
LOCAL(lshrsi3_4):
shlr2 r0
LOCAL(lshrsi3_2):
rts
shlr2 r0
LOCAL(lshrsi3_7):
shlr2 r0
LOCAL(lshrsi3_5):
shlr2 r0
LOCAL(lshrsi3_3):
shlr2 r0
LOCAL(lshrsi3_1):
rts
shlr r0
LOCAL(lshrsi3_14):
shlr2 r0
LOCAL(lshrsi3_12):
shlr2 r0
LOCAL(lshrsi3_10):
shlr2 r0
LOCAL(lshrsi3_8):
rts
shlr8 r0
LOCAL(lshrsi3_15):
shlr2 r0
LOCAL(lshrsi3_13):
shlr2 r0
LOCAL(lshrsi3_11):
shlr2 r0
LOCAL(lshrsi3_9):
shlr8 r0
rts
shlr r0
LOCAL(lshrsi3_22):
shlr2 r0
LOCAL(lshrsi3_20):
shlr2 r0
LOCAL(lshrsi3_18):
shlr2 r0
LOCAL(lshrsi3_16):
rts
shlr16 r0
LOCAL(lshrsi3_23):
shlr2 r0
LOCAL(lshrsi3_21):
shlr2 r0
LOCAL(lshrsi3_19):
shlr2 r0
LOCAL(lshrsi3_17):
shlr16 r0
rts
shlr r0
LOCAL(lshrsi3_30):
shlr2 r0
LOCAL(lshrsi3_28):
shlr2 r0
LOCAL(lshrsi3_26):
shlr2 r0
LOCAL(lshrsi3_24):
shlr16 r0
rts
shlr8 r0
LOCAL(lshrsi3_31):
shlr2 r0
LOCAL(lshrsi3_29):
shlr2 r0
LOCAL(lshrsi3_27):
shlr2 r0
LOCAL(lshrsi3_25):
shlr16 r0
shlr8 r0
rts
shlr r0
LOCAL(lshrsi3_0):
rts
nop
ENDFUNC(GLOBAL(lshrsi3))
#endif
#ifdef L_movmem
.text
.balign 4
.global GLOBAL(movmem)
HIDDEN_FUNC(GLOBAL(movmem))
HIDDEN_ALIAS(movstr,movmem)
/* This would be a lot simpler if r6 contained the byte count
minus 64, and we wouldn't be called here for a byte count of 64. */
GLOBAL(movmem):
sts.l pr,@-r15
shll2 r6
bsr GLOBAL(movmemSI52+2)
mov.l @(48,r5),r0
.balign 4
LOCAL(movmem_loop): /* Reached with rts */
mov.l @(60,r5),r0
add #-64,r6
mov.l r0,@(60,r4)
tst r6,r6
mov.l @(56,r5),r0
bt LOCAL(movmem_done)
mov.l r0,@(56,r4)
cmp/pl r6
mov.l @(52,r5),r0
add #64,r5
mov.l r0,@(52,r4)
add #64,r4
bt GLOBAL(movmemSI52)
! done all the large groups, do the remainder
! jump to movmem+
mova GLOBAL(movmemSI4)+4,r0
add r6,r0
jmp @r0
LOCAL(movmem_done): ! share slot insn, works out aligned.
lds.l @r15+,pr
mov.l r0,@(56,r4)
mov.l @(52,r5),r0
rts
mov.l r0,@(52,r4)
.balign 4
! ??? We need aliases movstr* for movmem* for the older libraries. These
! aliases will be removed at the some point in the future.
.global GLOBAL(movmemSI64)
HIDDEN_FUNC(GLOBAL(movmemSI64))
HIDDEN_ALIAS(movstrSI64,movmemSI64)
GLOBAL(movmemSI64):
mov.l @(60,r5),r0
mov.l r0,@(60,r4)
.global GLOBAL(movmemSI60)
HIDDEN_FUNC(GLOBAL(movmemSI60))
HIDDEN_ALIAS(movstrSI60,movmemSI60)
GLOBAL(movmemSI60):
mov.l @(56,r5),r0
mov.l r0,@(56,r4)
.global GLOBAL(movmemSI56)
HIDDEN_FUNC(GLOBAL(movmemSI56))
HIDDEN_ALIAS(movstrSI56,movmemSI56)
GLOBAL(movmemSI56):
mov.l @(52,r5),r0
mov.l r0,@(52,r4)
.global GLOBAL(movmemSI52)
HIDDEN_FUNC(GLOBAL(movmemSI52))
HIDDEN_ALIAS(movstrSI52,movmemSI52)
GLOBAL(movmemSI52):
mov.l @(48,r5),r0
mov.l r0,@(48,r4)
.global GLOBAL(movmemSI48)
HIDDEN_FUNC(GLOBAL(movmemSI48))
HIDDEN_ALIAS(movstrSI48,movmemSI48)
GLOBAL(movmemSI48):
mov.l @(44,r5),r0
mov.l r0,@(44,r4)
.global GLOBAL(movmemSI44)
HIDDEN_FUNC(GLOBAL(movmemSI44))
HIDDEN_ALIAS(movstrSI44,movmemSI44)
GLOBAL(movmemSI44):
mov.l @(40,r5),r0
mov.l r0,@(40,r4)
.global GLOBAL(movmemSI40)
HIDDEN_FUNC(GLOBAL(movmemSI40))
HIDDEN_ALIAS(movstrSI40,movmemSI40)
GLOBAL(movmemSI40):
mov.l @(36,r5),r0
mov.l r0,@(36,r4)
.global GLOBAL(movmemSI36)
HIDDEN_FUNC(GLOBAL(movmemSI36))
HIDDEN_ALIAS(movstrSI36,movmemSI36)
GLOBAL(movmemSI36):
mov.l @(32,r5),r0
mov.l r0,@(32,r4)
.global GLOBAL(movmemSI32)
HIDDEN_FUNC(GLOBAL(movmemSI32))
HIDDEN_ALIAS(movstrSI32,movmemSI32)
GLOBAL(movmemSI32):
mov.l @(28,r5),r0
mov.l r0,@(28,r4)
.global GLOBAL(movmemSI28)
HIDDEN_FUNC(GLOBAL(movmemSI28))
HIDDEN_ALIAS(movstrSI28,movmemSI28)
GLOBAL(movmemSI28):
mov.l @(24,r5),r0
mov.l r0,@(24,r4)
.global GLOBAL(movmemSI24)
HIDDEN_FUNC(GLOBAL(movmemSI24))
HIDDEN_ALIAS(movstrSI24,movmemSI24)
GLOBAL(movmemSI24):
mov.l @(20,r5),r0
mov.l r0,@(20,r4)
.global GLOBAL(movmemSI20)
HIDDEN_FUNC(GLOBAL(movmemSI20))
HIDDEN_ALIAS(movstrSI20,movmemSI20)
GLOBAL(movmemSI20):
mov.l @(16,r5),r0
mov.l r0,@(16,r4)
.global GLOBAL(movmemSI16)
HIDDEN_FUNC(GLOBAL(movmemSI16))
HIDDEN_ALIAS(movstrSI16,movmemSI16)
GLOBAL(movmemSI16):
mov.l @(12,r5),r0
mov.l r0,@(12,r4)
.global GLOBAL(movmemSI12)
HIDDEN_FUNC(GLOBAL(movmemSI12))
HIDDEN_ALIAS(movstrSI12,movmemSI12)
GLOBAL(movmemSI12):
mov.l @(8,r5),r0
mov.l r0,@(8,r4)
.global GLOBAL(movmemSI8)
HIDDEN_FUNC(GLOBAL(movmemSI8))
HIDDEN_ALIAS(movstrSI8,movmemSI8)
GLOBAL(movmemSI8):
mov.l @(4,r5),r0
mov.l r0,@(4,r4)
.global GLOBAL(movmemSI4)
HIDDEN_FUNC(GLOBAL(movmemSI4))
HIDDEN_ALIAS(movstrSI4,movmemSI4)
GLOBAL(movmemSI4):
mov.l @(0,r5),r0
rts
mov.l r0,@(0,r4)
ENDFUNC(GLOBAL(movmemSI64))
ENDFUNC(GLOBAL(movmemSI60))
ENDFUNC(GLOBAL(movmemSI56))
ENDFUNC(GLOBAL(movmemSI52))
ENDFUNC(GLOBAL(movmemSI48))
ENDFUNC(GLOBAL(movmemSI44))
ENDFUNC(GLOBAL(movmemSI40))
ENDFUNC(GLOBAL(movmemSI36))
ENDFUNC(GLOBAL(movmemSI32))
ENDFUNC(GLOBAL(movmemSI28))
ENDFUNC(GLOBAL(movmemSI24))
ENDFUNC(GLOBAL(movmemSI20))
ENDFUNC(GLOBAL(movmemSI16))
ENDFUNC(GLOBAL(movmemSI12))
ENDFUNC(GLOBAL(movmemSI8))
ENDFUNC(GLOBAL(movmemSI4))
ENDFUNC(GLOBAL(movmem))
#endif
#ifdef L_movmem_i4
.text
.global GLOBAL(movmem_i4_even)
.global GLOBAL(movmem_i4_odd)
.global GLOBAL(movmemSI12_i4)
HIDDEN_FUNC(GLOBAL(movmem_i4_even))
HIDDEN_FUNC(GLOBAL(movmem_i4_odd))
HIDDEN_FUNC(GLOBAL(movmemSI12_i4))
HIDDEN_ALIAS(movstr_i4_even,movmem_i4_even)
HIDDEN_ALIAS(movstr_i4_odd,movmem_i4_odd)
HIDDEN_ALIAS(movstrSI12_i4,movmemSI12_i4)
.p2align 5
L_movmem_2mod4_end:
mov.l r0,@(16,r4)
rts
mov.l r1,@(20,r4)
.p2align 2
GLOBAL(movmem_i4_even):
mov.l @r5+,r0
bra L_movmem_start_even
mov.l @r5+,r1
GLOBAL(movmem_i4_odd):
mov.l @r5+,r1
add #-4,r4
mov.l @r5+,r2
mov.l @r5+,r3
mov.l r1,@(4,r4)
mov.l r2,@(8,r4)
L_movmem_loop:
mov.l r3,@(12,r4)
dt r6
mov.l @r5+,r0
bt/s L_movmem_2mod4_end
mov.l @r5+,r1
add #16,r4
L_movmem_start_even:
mov.l @r5+,r2
mov.l @r5+,r3
mov.l r0,@r4
dt r6
mov.l r1,@(4,r4)
bf/s L_movmem_loop
mov.l r2,@(8,r4)
rts
mov.l r3,@(12,r4)
ENDFUNC(GLOBAL(movmem_i4_even))
ENDFUNC(GLOBAL(movmem_i4_odd))
.p2align 4
GLOBAL(movmemSI12_i4):
mov.l @r5,r0
mov.l @(4,r5),r1
mov.l @(8,r5),r2
mov.l r0,@r4
mov.l r1,@(4,r4)
rts
mov.l r2,@(8,r4)
ENDFUNC(GLOBAL(movmemSI12_i4))
#endif
#ifdef L_mulsi3
.global GLOBAL(mulsi3)
HIDDEN_FUNC(GLOBAL(mulsi3))
! r4 = aabb
! r5 = ccdd
! r0 = aabb*ccdd via partial products
!
! if aa == 0 and cc = 0
! r0 = bb*dd
!
! else
! aa = bb*dd + (aa*dd*65536) + (cc*bb*65536)
!
GLOBAL(mulsi3):
mulu.w r4,r5 ! multiply the lsws macl=bb*dd
mov r5,r3 ! r3 = ccdd
swap.w r4,r2 ! r2 = bbaa
xtrct r2,r3 ! r3 = aacc
tst r3,r3 ! msws zero ?
bf hiset
rts ! yes - then we have the answer
sts macl,r0
hiset: sts macl,r0 ! r0 = bb*dd
mulu.w r2,r5 ! brewing macl = aa*dd
sts macl,r1
mulu.w r3,r4 ! brewing macl = cc*bb
sts macl,r2
add r1,r2
shll16 r2
rts
add r2,r0
ENDFUNC(GLOBAL(mulsi3))
#endif
#endif /* ! __SH5__ */
#ifdef L_sdivsi3_i4
.title "SH DIVIDE"
!! 4 byte integer Divide code for the Renesas SH
#ifdef __SH4__
!! args in r4 and r5, result in fpul, clobber dr0, dr2
.global GLOBAL(sdivsi3_i4)
HIDDEN_FUNC(GLOBAL(sdivsi3_i4))
GLOBAL(sdivsi3_i4):
lds r4,fpul
float fpul,dr0
lds r5,fpul
float fpul,dr2
fdiv dr2,dr0
rts
ftrc dr0,fpul
ENDFUNC(GLOBAL(sdivsi3_i4))
#elif defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__) || (defined (__SH5__) && ! defined __SH4_NOFPU__)
!! args in r4 and r5, result in fpul, clobber r2, dr0, dr2
#if ! __SH5__ || __SH5__ == 32
#if __SH5__
.mode SHcompact
#endif
.global GLOBAL(sdivsi3_i4)
HIDDEN_FUNC(GLOBAL(sdivsi3_i4))
GLOBAL(sdivsi3_i4):
sts.l fpscr,@-r15
mov #8,r2
swap.w r2,r2
lds r2,fpscr
lds r4,fpul
float fpul,dr0
lds r5,fpul
float fpul,dr2
fdiv dr2,dr0
ftrc dr0,fpul
rts
lds.l @r15+,fpscr
ENDFUNC(GLOBAL(sdivsi3_i4))
#endif /* ! __SH5__ || __SH5__ == 32 */
#endif /* ! __SH4__ */
#endif
#ifdef L_sdivsi3
/* __SH4_SINGLE_ONLY__ keeps this part for link compatibility with
sh2e/sh3e code. */
#if (! defined(__SH4__) && ! defined (__SH4_SINGLE__)) || defined (__linux__)
!!
!! Steve Chamberlain
!! sac@cygnus.com
!!
!!
!! args in r4 and r5, result in r0 clobber r1, r2, r3, and t bit
.global GLOBAL(sdivsi3)
#if __SHMEDIA__
#if __SH5__ == 32
.section .text..SHmedia32,"ax"
#else
.text
#endif
.align 2
#if 0
/* The assembly code that follows is a hand-optimized version of the C
code that follows. Note that the registers that are modified are
exactly those listed as clobbered in the patterns divsi3_i1 and
divsi3_i1_media.
int __sdivsi3 (i, j)
int i, j;
{
register unsigned long long r18 asm ("r18");
register unsigned long long r19 asm ("r19");
register unsigned long long r0 asm ("r0") = 0;
register unsigned long long r1 asm ("r1") = 1;
register int r2 asm ("r2") = i >> 31;
register int r3 asm ("r3") = j >> 31;
r2 = r2 ? r2 : r1;
r3 = r3 ? r3 : r1;
r18 = i * r2;
r19 = j * r3;
r2 *= r3;
r19 <<= 31;
r1 <<= 31;
do
if (r18 >= r19)
r0 |= r1, r18 -= r19;
while (r19 >>= 1, r1 >>= 1);
return r2 * (int)r0;
}
*/
GLOBAL(sdivsi3):
pt/l LOCAL(sdivsi3_dontadd), tr2
pt/l LOCAL(sdivsi3_loop), tr1
ptabs/l r18, tr0
movi 0, r0
movi 1, r1
shari.l r4, 31, r2
shari.l r5, 31, r3
cmveq r2, r1, r2
cmveq r3, r1, r3
muls.l r4, r2, r18
muls.l r5, r3, r19
muls.l r2, r3, r2
shlli r19, 31, r19
shlli r1, 31, r1
LOCAL(sdivsi3_loop):
bgtu r19, r18, tr2
or r0, r1, r0
sub r18, r19, r18
LOCAL(sdivsi3_dontadd):
shlri r1, 1, r1
shlri r19, 1, r19
bnei r1, 0, tr1
muls.l r0, r2, r0
add.l r0, r63, r0
blink tr0, r63
#elif 0 /* ! 0 */
// inputs: r4,r5
// clobbered: r1,r2,r3,r18,r19,r20,r21,r25,tr0
// result in r0
GLOBAL(sdivsi3):
// can create absolute value without extra latency,
// but dependent on proper sign extension of inputs:
// shari.l r5,31,r2
// xor r5,r2,r20
// sub r20,r2,r20 // r20 is now absolute value of r5, zero-extended.
shari.l r5,31,r2
ori r2,1,r2
muls.l r5,r2,r20 // r20 is now absolute value of r5, zero-extended.
movi 0xffffffffffffbb0c,r19 // shift count eqiv 76
shari.l r4,31,r3
nsb r20,r0
shlld r20,r0,r25
shlri r25,48,r25
sub r19,r25,r1
mmulfx.w r1,r1,r2
mshflo.w r1,r63,r1
// If r4 was to be used in-place instead of r21, could use this sequence
// to compute absolute:
// sub r63,r4,r19 // compute absolute value of r4
// shlri r4,32,r3 // into lower 32 bit of r4, keeping
// mcmv r19,r3,r4 // the sign in the upper 32 bits intact.
ori r3,1,r3
mmulfx.w r25,r2,r2
sub r19,r0,r0
muls.l r4,r3,r21
msub.w r1,r2,r2
addi r2,-2,r1
mulu.l r21,r1,r19
mmulfx.w r2,r2,r2
shlli r1,15,r1
shlrd r19,r0,r19
mulu.l r19,r20,r3
mmacnfx.wl r25,r2,r1
ptabs r18,tr0
sub r21,r3,r25
mulu.l r25,r1,r2
addi r0,14,r0
xor r4,r5,r18
shlrd r2,r0,r2
mulu.l r2,r20,r3
add r19,r2,r19
shari.l r18,31,r18
sub r25,r3,r25
mulu.l r25,r1,r2
sub r25,r20,r25
add r19,r18,r19
shlrd r2,r0,r2
mulu.l r2,r20,r3
addi r25,1,r25
add r19,r2,r19
cmpgt r25,r3,r25
add.l r19,r25,r0
xor r0,r18,r0
blink tr0,r63
#else /* ! 0 && ! 0 */
// inputs: r4,r5
// clobbered: r1,r18,r19,r20,r21,r25,tr0
// result in r0
HIDDEN_FUNC(GLOBAL(sdivsi3_2))
#ifndef __pic__
FUNC(GLOBAL(sdivsi3))
GLOBAL(sdivsi3): /* this is the shcompact entry point */
// The special SHmedia entry point sdivsi3_1 prevents accidental linking
// with the SHcompact implementation, which clobbers tr1 / tr2.
.global GLOBAL(sdivsi3_1)
GLOBAL(sdivsi3_1):
.global GLOBAL(div_table_internal)
movi (GLOBAL(div_table_internal) >> 16) & 65535, r20
shori GLOBAL(div_table_internal) & 65535, r20
#endif
.global GLOBAL(sdivsi3_2)
// div_table in r20
// clobbered: r1,r18,r19,r21,r25,tr0
GLOBAL(sdivsi3_2):
nsb r5, r1
shlld r5, r1, r25 // normalize; [-2 ..1, 1..2) in s2.62
shari r25, 58, r21 // extract 5(6) bit index (s2.4 with hole -1..1)
ldx.ub r20, r21, r19 // u0.8
shari r25, 32, r25 // normalize to s2.30
shlli r21, 1, r21
muls.l r25, r19, r19 // s2.38
ldx.w r20, r21, r21 // s2.14
ptabs r18, tr0
shari r19, 24, r19 // truncate to s2.14
sub r21, r19, r19 // some 11 bit inverse in s1.14
muls.l r19, r19, r21 // u0.28
sub r63, r1, r1
addi r1, 92, r1
muls.l r25, r21, r18 // s2.58
shlli r19, 45, r19 // multiply by two and convert to s2.58
/* bubble */
sub r19, r18, r18
shari r18, 28, r18 // some 22 bit inverse in s1.30
muls.l r18, r25, r0 // s2.60
muls.l r18, r4, r25 // s32.30
/* bubble */
shari r0, 16, r19 // s-16.44
muls.l r19, r18, r19 // s-16.74
shari r25, 63, r0
shari r4, 14, r18 // s19.-14
shari r19, 30, r19 // s-16.44
muls.l r19, r18, r19 // s15.30
xor r21, r0, r21 // You could also use the constant 1 << 27.
add r21, r25, r21
sub r21, r19, r21
shard r21, r1, r21
sub r21, r0, r0
blink tr0, r63
#ifndef __pic__
ENDFUNC(GLOBAL(sdivsi3))
#endif
ENDFUNC(GLOBAL(sdivsi3_2))
#endif
#elif defined __SHMEDIA__
/* m5compact-nofpu */
// clobbered: r18,r19,r20,r21,r25,tr0,tr1,tr2
.mode SHmedia
.section .text..SHmedia32,"ax"
.align 2
FUNC(GLOBAL(sdivsi3))
GLOBAL(sdivsi3):
pt/l LOCAL(sdivsi3_dontsub), tr0
pt/l LOCAL(sdivsi3_loop), tr1
ptabs/l r18,tr2
shari.l r4,31,r18
shari.l r5,31,r19
xor r4,r18,r20
xor r5,r19,r21
sub.l r20,r18,r20
sub.l r21,r19,r21
xor r18,r19,r19
shlli r21,32,r25
addi r25,-1,r21
addz.l r20,r63,r20
LOCAL(sdivsi3_loop):
shlli r20,1,r20
bgeu/u r21,r20,tr0
sub r20,r21,r20
LOCAL(sdivsi3_dontsub):
addi.l r25,-1,r25
bnei r25,-32,tr1
xor r20,r19,r20
sub.l r20,r19,r0
blink tr2,r63
ENDFUNC(GLOBAL(sdivsi3))
#else /* ! __SHMEDIA__ */
FUNC(GLOBAL(sdivsi3))
GLOBAL(sdivsi3):
mov r4,r1
mov r5,r0
tst r0,r0
bt div0
mov #0,r2
div0s r2,r1
subc r3,r3
subc r2,r1
div0s r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
div1 r0,r3
rotcl r1
addc r2,r1
rts
mov r1,r0
div0: rts
mov #0,r0
ENDFUNC(GLOBAL(sdivsi3))
#endif /* ! __SHMEDIA__ */
#endif /* ! __SH4__ */
#endif
#ifdef L_udivsi3_i4
.title "SH DIVIDE"
!! 4 byte integer Divide code for the Renesas SH
#ifdef __SH4__
!! args in r4 and r5, result in fpul, clobber r0, r1, r4, r5, dr0, dr2, dr4,
!! and t bit
.global GLOBAL(udivsi3_i4)
HIDDEN_FUNC(GLOBAL(udivsi3_i4))
GLOBAL(udivsi3_i4):
mov #1,r1
cmp/hi r1,r5
bf trivial
rotr r1
xor r1,r4
lds r4,fpul
mova L1,r0
#ifdef FMOVD_WORKS
fmov.d @r0+,dr4
#else
fmov.s @r0+,DR40
fmov.s @r0,DR41
#endif
float fpul,dr0
xor r1,r5
lds r5,fpul
float fpul,dr2
fadd dr4,dr0
fadd dr4,dr2
fdiv dr2,dr0
rts
ftrc dr0,fpul
trivial:
rts
lds r4,fpul
.align 2
#ifdef FMOVD_WORKS
.align 3 ! make double below 8 byte aligned.
#endif
L1:
.double 2147483648
ENDFUNC(GLOBAL(udivsi3_i4))
#elif defined (__SH5__) && ! defined (__SH4_NOFPU__)
#if ! __SH5__ || __SH5__ == 32
!! args in r4 and r5, result in fpul, clobber r20, r21, dr0, fr33
.mode SHmedia
.global GLOBAL(udivsi3_i4)
HIDDEN_FUNC(GLOBAL(udivsi3_i4))
GLOBAL(udivsi3_i4):
addz.l r4,r63,r20
addz.l r5,r63,r21
fmov.qd r20,dr0
fmov.qd r21,dr32
ptabs r18,tr0
float.qd dr0,dr0
float.qd dr32,dr32
fdiv.d dr0,dr32,dr0
ftrc.dq dr0,dr32
fmov.s fr33,fr32
blink tr0,r63
ENDFUNC(GLOBAL(udivsi3_i4))
#endif /* ! __SH5__ || __SH5__ == 32 */
#elif defined(__SH4_SINGLE__) || defined(__SH4_SINGLE_ONLY__)
!! args in r4 and r5, result in fpul, clobber r0, r1, r4, r5, dr0, dr2, dr4
.global GLOBAL(udivsi3_i4)
HIDDEN_FUNC(GLOBAL(udivsi3_i4))
GLOBAL(udivsi3_i4):
mov #1,r1
cmp/hi r1,r5
bf trivial
sts.l fpscr,@-r15
mova L1,r0
lds.l @r0+,fpscr
rotr r1
xor r1,r4
lds r4,fpul
#ifdef FMOVD_WORKS
fmov.d @r0+,dr4
#else
fmov.s @r0+,DR40
fmov.s @r0,DR41
#endif
float fpul,dr0
xor r1,r5
lds r5,fpul
float fpul,dr2
fadd dr4,dr0
fadd dr4,dr2
fdiv dr2,dr0
ftrc dr0,fpul
rts
lds.l @r15+,fpscr
#ifdef FMOVD_WORKS
.align 3 ! make double below 8 byte aligned.
#endif
trivial:
rts
lds r4,fpul
.align 2
L1:
#ifndef FMOVD_WORKS
.long 0x80000
#else
.long 0x180000
#endif
.double 2147483648
ENDFUNC(GLOBAL(udivsi3_i4))
#endif /* ! __SH4__ */
#endif
#ifdef L_udivsi3
/* __SH4_SINGLE_ONLY__ keeps this part for link compatibility with
sh2e/sh3e code. */
#if (! defined(__SH4__) && ! defined (__SH4_SINGLE__)) || defined (__linux__)
!! args in r4 and r5, result in r0, clobbers r4, pr, and t bit
.global GLOBAL(udivsi3)
HIDDEN_FUNC(GLOBAL(udivsi3))
#if __SHMEDIA__
#if __SH5__ == 32
.section .text..SHmedia32,"ax"
#else
.text
#endif
.align 2
#if 0
/* The assembly code that follows is a hand-optimized version of the C
code that follows. Note that the registers that are modified are
exactly those listed as clobbered in the patterns udivsi3_i1 and
udivsi3_i1_media.
unsigned
__udivsi3 (i, j)
unsigned i, j;
{
register unsigned long long r0 asm ("r0") = 0;
register unsigned long long r18 asm ("r18") = 1;
register unsigned long long r4 asm ("r4") = i;
register unsigned long long r19 asm ("r19") = j;
r19 <<= 31;
r18 <<= 31;
do
if (r4 >= r19)
r0 |= r18, r4 -= r19;
while (r19 >>= 1, r18 >>= 1);
return r0;
}
*/
GLOBAL(udivsi3):
pt/l LOCAL(udivsi3_dontadd), tr2
pt/l LOCAL(udivsi3_loop), tr1
ptabs/l r18, tr0
movi 0, r0
movi 1, r18
addz.l r5, r63, r19
addz.l r4, r63, r4
shlli r19, 31, r19
shlli r18, 31, r18
LOCAL(udivsi3_loop):
bgtu r19, r4, tr2
or r0, r18, r0
sub r4, r19, r4
LOCAL(udivsi3_dontadd):
shlri r18, 1, r18
shlri r19, 1, r19
bnei r18, 0, tr1
blink tr0, r63
#else
GLOBAL(udivsi3):
// inputs: r4,r5
// clobbered: r18,r19,r20,r21,r22,r25,tr0
// result in r0.
addz.l r5,r63,r22
nsb r22,r0
shlld r22,r0,r25
shlri r25,48,r25
movi 0xffffffffffffbb0c,r20 // shift count eqiv 76
sub r20,r25,r21
mmulfx.w r21,r21,r19
mshflo.w r21,r63,r21
ptabs r18,tr0
mmulfx.w r25,r19,r19
sub r20,r0,r0
/* bubble */
msub.w r21,r19,r19
addi r19,-2,r21 /* It would be nice for scheduling to do this add to r21
before the msub.w, but we need a different value for
r19 to keep errors under control. */
mulu.l r4,r21,r18
mmulfx.w r19,r19,r19
shlli r21,15,r21
shlrd r18,r0,r18
mulu.l r18,r22,r20
mmacnfx.wl r25,r19,r21
/* bubble */
sub r4,r20,r25
mulu.l r25,r21,r19
addi r0,14,r0
/* bubble */
shlrd r19,r0,r19
mulu.l r19,r22,r20
add r18,r19,r18
/* bubble */
sub.l r25,r20,r25
mulu.l r25,r21,r19
addz.l r25,r63,r25
sub r25,r22,r25
shlrd r19,r0,r19
mulu.l r19,r22,r20
addi r25,1,r25
add r18,r19,r18
cmpgt r25,r20,r25
add.l r18,r25,r0
blink tr0,r63
#endif
#elif defined (__SHMEDIA__)
/* m5compact-nofpu - more emphasis on code size than on speed, but don't
ignore speed altogether - div1 needs 9 cycles, subc 7 and rotcl 4.
So use a short shmedia loop. */
// clobbered: r20,r21,r25,tr0,tr1,tr2
.mode SHmedia
.section .text..SHmedia32,"ax"
.align 2
GLOBAL(udivsi3):
pt/l LOCAL(udivsi3_dontsub), tr0
pt/l LOCAL(udivsi3_loop), tr1
ptabs/l r18,tr2
shlli r5,32,r25
addi r25,-1,r21
addz.l r4,r63,r20
LOCAL(udivsi3_loop):
shlli r20,1,r20
bgeu/u r21,r20,tr0
sub r20,r21,r20
LOCAL(udivsi3_dontsub):
addi.l r25,-1,r25
bnei r25,-32,tr1
add.l r20,r63,r0
blink tr2,r63
#else /* ! defined (__SHMEDIA__) */
LOCAL(div8):
div1 r5,r4
LOCAL(div7):
div1 r5,r4; div1 r5,r4; div1 r5,r4
div1 r5,r4; div1 r5,r4; div1 r5,r4; rts; div1 r5,r4
LOCAL(divx4):
div1 r5,r4; rotcl r0
div1 r5,r4; rotcl r0
div1 r5,r4; rotcl r0
rts; div1 r5,r4
GLOBAL(udivsi3):
sts.l pr,@-r15
extu.w r5,r0
cmp/eq r5,r0
#ifdef __sh1__
bf LOCAL(large_divisor)
#else
bf/s LOCAL(large_divisor)
#endif
div0u
swap.w r4,r0
shlr16 r4
bsr LOCAL(div8)
shll16 r5
bsr LOCAL(div7)
div1 r5,r4
xtrct r4,r0
xtrct r0,r4
bsr LOCAL(div8)
swap.w r4,r4
bsr LOCAL(div7)
div1 r5,r4
lds.l @r15+,pr
xtrct r4,r0
swap.w r0,r0
rotcl r0
rts
shlr16 r5
LOCAL(large_divisor):
#ifdef __sh1__
div0u
#endif
mov #0,r0
xtrct r4,r0
xtrct r0,r4
bsr LOCAL(divx4)
rotcl r0
bsr LOCAL(divx4)
rotcl r0
bsr LOCAL(divx4)
rotcl r0
bsr LOCAL(divx4)
rotcl r0
lds.l @r15+,pr
rts
rotcl r0
ENDFUNC(GLOBAL(udivsi3))
#endif /* ! __SHMEDIA__ */
#endif /* __SH4__ */
#endif /* L_udivsi3 */
#ifdef L_udivdi3
#ifdef __SHMEDIA__
.mode SHmedia
.section .text..SHmedia32,"ax"
.align 2
.global GLOBAL(udivdi3)
FUNC(GLOBAL(udivdi3))
GLOBAL(udivdi3):
HIDDEN_ALIAS(udivdi3_internal,udivdi3)
shlri r3,1,r4
nsb r4,r22
shlld r3,r22,r6
shlri r6,49,r5
movi 0xffffffffffffbaf1,r21 /* .l shift count 17. */
sub r21,r5,r1
mmulfx.w r1,r1,r4
mshflo.w r1,r63,r1
sub r63,r22,r20 // r63 == 64 % 64
mmulfx.w r5,r4,r4
pta LOCAL(large_divisor),tr0
addi r20,32,r9
msub.w r1,r4,r1
madd.w r1,r1,r1
mmulfx.w r1,r1,r4
shlri r6,32,r7
bgt/u r9,r63,tr0 // large_divisor
mmulfx.w r5,r4,r4
shlri r2,32+14,r19
addi r22,-31,r0
msub.w r1,r4,r1
mulu.l r1,r7,r4
addi r1,-3,r5
mulu.l r5,r19,r5
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
the case may be, %0000000000000000 000.11111111111, still */
muls.l r1,r4,r4 /* leaving at least one sign bit. */
mulu.l r5,r3,r8
mshalds.l r1,r21,r1
shari r4,26,r4
shlld r8,r0,r8
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
sub r2,r8,r2
/* Can do second step of 64 : 32 div now, using r1 and the rest in r2. */
shlri r2,22,r21
mulu.l r21,r1,r21
shlld r5,r0,r8
addi r20,30-22,r0
shlrd r21,r0,r21
mulu.l r21,r3,r5
add r8,r21,r8
mcmpgt.l r21,r63,r21 // See Note 1
addi r20,30,r0
mshfhi.l r63,r21,r21
sub r2,r5,r2
andc r2,r21,r2
/* small divisor: need a third divide step */
mulu.l r2,r1,r7
ptabs r18,tr0
addi r2,1,r2
shlrd r7,r0,r7
mulu.l r7,r3,r5
add r8,r7,r8
sub r2,r3,r2
cmpgt r2,r5,r5
add r8,r5,r2
/* could test r3 here to check for divide by zero. */
blink tr0,r63
LOCAL(large_divisor):
mmulfx.w r5,r4,r4
shlrd r2,r9,r25
shlri r25,32,r8
msub.w r1,r4,r1
mulu.l r1,r7,r4
addi r1,-3,r5
mulu.l r5,r8,r5
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
the case may be, %0000000000000000 000.11111111111, still */
muls.l r1,r4,r4 /* leaving at least one sign bit. */
shlri r5,14-1,r8
mulu.l r8,r7,r5
mshalds.l r1,r21,r1
shari r4,26,r4
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
sub r25,r5,r25
/* Can do second step of 64 : 32 div now, using r1 and the rest in r25. */
shlri r25,22,r21
mulu.l r21,r1,r21
pta LOCAL(no_lo_adj),tr0
addi r22,32,r0
shlri r21,40,r21
mulu.l r21,r7,r5
add r8,r21,r8
shlld r2,r0,r2
sub r25,r5,r25
bgtu/u r7,r25,tr0 // no_lo_adj
addi r8,1,r8
sub r25,r7,r25
LOCAL(no_lo_adj):
mextr4 r2,r25,r2
/* large_divisor: only needs a few adjustments. */
mulu.l r8,r6,r5
ptabs r18,tr0
/* bubble */
cmpgtu r5,r2,r5
sub r8,r5,r2
blink tr0,r63
ENDFUNC(GLOBAL(udivdi3))
/* Note 1: To shift the result of the second divide stage so that the result
always fits into 32 bits, yet we still reduce the rest sufficiently
would require a lot of instructions to do the shifts just right. Using
the full 64 bit shift result to multiply with the divisor would require
four extra instructions for the upper 32 bits (shift / mulu / shift / sub).
Fortunately, if the upper 32 bits of the shift result are nonzero, we
know that the rest after taking this partial result into account will
fit into 32 bits. So we just clear the upper 32 bits of the rest if the
upper 32 bits of the partial result are nonzero. */
#endif /* __SHMEDIA__ */
#endif /* L_udivdi3 */
#ifdef L_divdi3
#ifdef __SHMEDIA__
.mode SHmedia
.section .text..SHmedia32,"ax"
.align 2
.global GLOBAL(divdi3)
FUNC(GLOBAL(divdi3))
GLOBAL(divdi3):
pta GLOBAL(udivdi3_internal),tr0
shari r2,63,r22
shari r3,63,r23
xor r2,r22,r2
xor r3,r23,r3
sub r2,r22,r2
sub r3,r23,r3
beq/u r22,r23,tr0
ptabs r18,tr1
blink tr0,r18
sub r63,r2,r2
blink tr1,r63
ENDFUNC(GLOBAL(divdi3))
#endif /* __SHMEDIA__ */
#endif /* L_divdi3 */
#ifdef L_umoddi3
#ifdef __SHMEDIA__
.mode SHmedia
.section .text..SHmedia32,"ax"
.align 2
.global GLOBAL(umoddi3)
FUNC(GLOBAL(umoddi3))
GLOBAL(umoddi3):
HIDDEN_ALIAS(umoddi3_internal,umoddi3)
shlri r3,1,r4
nsb r4,r22
shlld r3,r22,r6
shlri r6,49,r5
movi 0xffffffffffffbaf1,r21 /* .l shift count 17. */
sub r21,r5,r1
mmulfx.w r1,r1,r4
mshflo.w r1,r63,r1
sub r63,r22,r20 // r63 == 64 % 64
mmulfx.w r5,r4,r4
pta LOCAL(large_divisor),tr0
addi r20,32,r9
msub.w r1,r4,r1
madd.w r1,r1,r1
mmulfx.w r1,r1,r4
shlri r6,32,r7
bgt/u r9,r63,tr0 // large_divisor
mmulfx.w r5,r4,r4
shlri r2,32+14,r19
addi r22,-31,r0
msub.w r1,r4,r1
mulu.l r1,r7,r4
addi r1,-3,r5
mulu.l r5,r19,r5
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
the case may be, %0000000000000000 000.11111111111, still */
muls.l r1,r4,r4 /* leaving at least one sign bit. */
mulu.l r5,r3,r5
mshalds.l r1,r21,r1
shari r4,26,r4
shlld r5,r0,r5
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
sub r2,r5,r2
/* Can do second step of 64 : 32 div now, using r1 and the rest in r2. */
shlri r2,22,r21
mulu.l r21,r1,r21
addi r20,30-22,r0
/* bubble */ /* could test r3 here to check for divide by zero. */
shlrd r21,r0,r21
mulu.l r21,r3,r5
mcmpgt.l r21,r63,r21 // See Note 1
addi r20,30,r0
mshfhi.l r63,r21,r21
sub r2,r5,r2
andc r2,r21,r2
/* small divisor: need a third divide step */
mulu.l r2,r1,r7
ptabs r18,tr0
sub r2,r3,r8 /* re-use r8 here for rest - r3 */
shlrd r7,r0,r7
mulu.l r7,r3,r5
/* bubble */
addi r8,1,r7
cmpgt r7,r5,r7
cmvne r7,r8,r2
sub r2,r5,r2
blink tr0,r63
LOCAL(large_divisor):
mmulfx.w r5,r4,r4
shlrd r2,r9,r25
shlri r25,32,r8
msub.w r1,r4,r1
mulu.l r1,r7,r4
addi r1,-3,r5
mulu.l r5,r8,r5
sub r63,r4,r4 // Negate to make sure r1 ends up <= 1/r2
shlri r4,2,r4 /* chop off leading %0000000000000000 001.00000000000 - or, as
the case may be, %0000000000000000 000.11111111111, still */
muls.l r1,r4,r4 /* leaving at least one sign bit. */
shlri r5,14-1,r8
mulu.l r8,r7,r5
mshalds.l r1,r21,r1
shari r4,26,r4
add r1,r4,r1 // 31 bit unsigned reciprocal now in r1 (msb equiv. 0.5)
sub r25,r5,r25
/* Can do second step of 64 : 32 div now, using r1 and the rest in r25. */
shlri r25,22,r21
mulu.l r21,r1,r21
pta LOCAL(no_lo_adj),tr0
addi r22,32,r0
shlri r21,40,r21
mulu.l r21,r7,r5
add r8,r21,r8
shlld r2,r0,r2
sub r25,r5,r25
bgtu/u r7,r25,tr0 // no_lo_adj
addi r8,1,r8
sub r25,r7,r25
LOCAL(no_lo_adj):
mextr4 r2,r25,r2
/* large_divisor: only needs a few adjustments. */
mulu.l r8,r6,r5
ptabs r18,tr0
add r2,r6,r7
cmpgtu r5,r2,r8
cmvne r8,r7,r2
sub r2,r5,r2
shlrd r2,r22,r2
blink tr0,r63
ENDFUNC(GLOBAL(umoddi3))
/* Note 1: To shift the result of the second divide stage so that the result
always fits into 32 bits, yet we still reduce the rest sufficiently
would require a lot of instructions to do the shifts just right. Using
the full 64 bit shift result to multiply with the divisor would require
four extra instructions for the upper 32 bits (shift / mulu / shift / sub).
Fortunately, if the upper 32 bits of the shift result are nonzero, we
know that the rest after taking this partial result into account will
fit into 32 bits. So we just clear the upper 32 bits of the rest if the
upper 32 bits of the partial result are nonzero. */
#endif /* __SHMEDIA__ */
#endif /* L_umoddi3 */
#ifdef L_moddi3
#ifdef __SHMEDIA__
.mode SHmedia
.section .text..SHmedia32,"ax"
.align 2
.global GLOBAL(moddi3)
FUNC(GLOBAL(moddi3))
GLOBAL(moddi3):
pta GLOBAL(umoddi3_internal),tr0
shari r2,63,r22
shari r3,63,r23
xor r2,r22,r2
xor r3,r23,r3
sub r2,r22,r2
sub r3,r23,r3
beq/u r22,r63,tr0
ptabs r18,tr1
blink tr0,r18
sub r63,r2,r2
blink tr1,r63
ENDFUNC(GLOBAL(moddi3))
#endif /* __SHMEDIA__ */
#endif /* L_moddi3 */
#ifdef L_set_fpscr
#if !defined (__SH2A_NOFPU__)
#if defined (__SH2E__) || defined (__SH2A__) || defined (__SH3E__) || defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || __SH5__ == 32
#ifdef __SH5__
.mode SHcompact
#endif
.global GLOBAL(set_fpscr)
HIDDEN_FUNC(GLOBAL(set_fpscr))
GLOBAL(set_fpscr):
lds r4,fpscr
#ifdef __PIC__
mov.l r12,@-r15
mova LOCAL(set_fpscr_L0),r0
mov.l LOCAL(set_fpscr_L0),r12
add r0,r12
mov.l LOCAL(set_fpscr_L1),r0
mov.l @(r0,r12),r1
mov.l @r15+,r12
#else
mov.l LOCAL(set_fpscr_L1),r1
#endif
swap.w r4,r0
or #24,r0
#ifndef FMOVD_WORKS
xor #16,r0
#endif
#if defined(__SH4__) || defined (__SH2A_DOUBLE__)
swap.w r0,r3
mov.l r3,@(4,r1)
#else /* defined (__SH2E__) || defined(__SH3E__) || defined(__SH4_SINGLE*__) */
swap.w r0,r2
mov.l r2,@r1
#endif
#ifndef FMOVD_WORKS
xor #8,r0
#else
xor #24,r0
#endif
#if defined(__SH4__) || defined (__SH2A_DOUBLE__)
swap.w r0,r2
rts
mov.l r2,@r1
#else /* defined(__SH2E__) || defined(__SH3E__) || defined(__SH4_SINGLE*__) */
swap.w r0,r3
rts
mov.l r3,@(4,r1)
#endif
.align 2
#ifdef __PIC__
LOCAL(set_fpscr_L0):
.long _GLOBAL_OFFSET_TABLE_
LOCAL(set_fpscr_L1):
.long GLOBAL(fpscr_values@GOT)
#else
LOCAL(set_fpscr_L1):
.long GLOBAL(fpscr_values)
#endif
ENDFUNC(GLOBAL(set_fpscr))
#ifndef NO_FPSCR_VALUES
#ifdef __ELF__
.comm GLOBAL(fpscr_values),8,4
#else
.comm GLOBAL(fpscr_values),8
#endif /* ELF */
#endif /* NO_FPSCR_VALUES */
#endif /* SH2E / SH3E / SH4 */
#endif /* __SH2A_NOFPU__ */
#endif /* L_set_fpscr */
#ifdef L_ic_invalidate
#if __SH5__ == 32
.mode SHmedia
.section .text..SHmedia32,"ax"
.align 2
.global GLOBAL(init_trampoline)
HIDDEN_FUNC(GLOBAL(init_trampoline))
GLOBAL(init_trampoline):
st.l r0,8,r2
#ifdef __LITTLE_ENDIAN__
movi 9,r20
shori 0x402b,r20
shori 0xd101,r20
shori 0xd002,r20
#else
movi 0xffffffffffffd002,r20
shori 0xd101,r20
shori 0x402b,r20
shori 9,r20
#endif
st.q r0,0,r20
st.l r0,12,r3
ENDFUNC(GLOBAL(init_trampoline))
.global GLOBAL(ic_invalidate)
HIDDEN_FUNC(GLOBAL(ic_invalidate))
GLOBAL(ic_invalidate):
ocbwb r0,0
synco
icbi r0, 0
ptabs r18, tr0
synci
blink tr0, r63
ENDFUNC(GLOBAL(ic_invalidate))
#elif defined(__SH4A__)
.global GLOBAL(ic_invalidate)
HIDDEN_FUNC(GLOBAL(ic_invalidate))
GLOBAL(ic_invalidate):
ocbwb @r4
synco
rts
icbi @r4
ENDFUNC(GLOBAL(ic_invalidate))
#elif defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || (defined(__SH4_NOFPU__) && !defined(__SH5__))
/* For system code, we use ic_invalidate_line_i, but user code
needs a different mechanism. A kernel call is generally not
available, and it would also be slow. Different SH4 variants use
different sizes and associativities of the Icache. We use a small
bit of dispatch code that can be put hidden in every shared object,
which calls the actual processor-specific invalidation code in a
separate module.
Or if you have operating system support, the OS could mmap the
procesor-specific code from a single page, since it is highly
repetitive. */
.global GLOBAL(ic_invalidate)
HIDDEN_FUNC(GLOBAL(ic_invalidate))
GLOBAL(ic_invalidate):
mov.l 0f,r1
#ifdef __pic__
mova 0f,r0
mov.l 1f,r2
add r1,r0
mov.l @(r0,r2),r1
#endif
ocbwb @r4
mov.l @(8,r1),r0
sub r1,r4
and r4,r0
add r1,r0
jmp @r0
mov.l @(4,r1),r0
#ifndef __pic__
0: .long GLOBAL(ic_invalidate_array)
#else /* __pic__ */
.global GLOBAL(ic_invalidate_array)
/* ??? Why won't the assembler allow to add these two constants? */
0: .long _GLOBAL_OFFSET_TABLE_
1: .long GLOBAL(ic_invalidate_array)@GOT
ENDFUNC(GLOBAL(ic_invalidate))
#endif /* __pic__ */
#endif /* SH4 */
#endif /* L_ic_invalidate */
#ifdef L_ic_invalidate_array
#if defined(__SH4A__) || (defined (__FORCE_SH4A__) && (defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || (defined(__SH4_NOFPU__) && !defined(__SH5__))))
.global GLOBAL(ic_invalidate_array)
/* This is needed when an SH4 dso with trampolines is used on SH4A. */
.global GLOBAL(ic_invalidate_array)
FUNC(GLOBAL(ic_invalidate_array))
GLOBAL(ic_invalidate_array):
add r1,r4
synco
rts
icbi @r4
.long 0
ENDFUNC(GLOBAL(ic_invalidate_array))
#elif defined(__SH4_SINGLE__) || defined(__SH4__) || defined(__SH4_SINGLE_ONLY__) || (defined(__SH4_NOFPU__) && !defined(__SH5__))
.global GLOBAL(ic_invalidate_array)
.p2align 5
FUNC(GLOBAL(ic_invalidate_array))
/* This must be aligned to the beginning of a cache line. */
GLOBAL(ic_invalidate_array):
#ifndef WAYS
#define WAYS 4
#define WAY_SIZE 0x4000
#endif
#if WAYS == 1
.rept WAY_SIZE * WAYS / 32
rts
nop
.rept 7
.long WAY_SIZE - 32
.endr
.endr
#elif WAYS <= 6
.rept WAY_SIZE * WAYS / 32
braf r0
add #-8,r0
.long WAY_SIZE + 8
.long WAY_SIZE - 32
.rept WAYS-2
braf r0
nop
.endr
.rept 7 - WAYS
rts
nop
.endr
.endr
#else /* WAYS > 6 */
/* This variant needs two different pages for mmap-ing. */
.rept WAYS-1
.rept WAY_SIZE / 32
braf r0
nop
.long WAY_SIZE
.rept 6
.long WAY_SIZE - 32
.endr
.endr
.endr
.rept WAY_SIZE / 32
rts
.rept 15
nop
.endr
.endr
#endif /* WAYS */
ENDFUNC(GLOBAL(ic_invalidate_array))
#endif /* SH4 */
#endif /* L_ic_invalidate_array */
#if defined (__SH5__) && __SH5__ == 32
#ifdef L_shcompact_call_trampoline
.section .rodata
.align 1
LOCAL(ct_main_table):
.word LOCAL(ct_r2_fp) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r2_ld) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r2_pop) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r3_fp) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r3_ld) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r3_pop) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r4_fp) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r4_ld) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r4_pop) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r5_fp) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r5_ld) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r5_pop) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r6_fph) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r6_fpl) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r6_ld) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r6_pop) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r7_fph) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r7_fpl) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r7_ld) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r7_pop) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r8_fph) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r8_fpl) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r8_ld) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r8_pop) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r9_fph) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r9_fpl) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r9_ld) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r9_pop) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_pop_seq) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_pop_seq) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_r9_pop) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_ret_wide) - datalabel LOCAL(ct_main_label)
.word LOCAL(ct_call_func) - datalabel LOCAL(ct_main_label)
.mode SHmedia
.section .text..SHmedia32, "ax"
.align 2
/* This function loads 64-bit general-purpose registers from the
stack, from a memory address contained in them or from an FP
register, according to a cookie passed in r1. Its execution
time is linear on the number of registers that actually have
to be copied. See sh.h for details on the actual bit pattern.
The function to be called is passed in r0. If a 32-bit return
value is expected, the actual function will be tail-called,
otherwise the return address will be stored in r10 (that the
caller should expect to be clobbered) and the return value
will be expanded into r2/r3 upon return. */
.global GLOBAL(GCC_shcompact_call_trampoline)
FUNC(GLOBAL(GCC_shcompact_call_trampoline))
GLOBAL(GCC_shcompact_call_trampoline):
ptabs/l r0, tr0 /* Prepare to call the actual function. */
movi ((datalabel LOCAL(ct_main_table) - 31 * 2) >> 16) & 65535, r0
pt/l LOCAL(ct_loop), tr1
addz.l r1, r63, r1
shori ((datalabel LOCAL(ct_main_table) - 31 * 2)) & 65535, r0
LOCAL(ct_loop):
nsb r1, r28
shlli r28, 1, r29
ldx.w r0, r29, r30
LOCAL(ct_main_label):
ptrel/l r30, tr2
blink tr2, r63
LOCAL(ct_r2_fp): /* Copy r2 from an FP register. */
/* It must be dr0, so just do it. */
fmov.dq dr0, r2
movi 7, r30
shlli r30, 29, r31
andc r1, r31, r1
blink tr1, r63
LOCAL(ct_r3_fp): /* Copy r3 from an FP register. */
/* It is either dr0 or dr2. */
movi 7, r30
shlri r1, 26, r32
shlli r30, 26, r31
andc r1, r31, r1
fmov.dq dr0, r3
beqi/l r32, 4, tr1
fmov.dq dr2, r3
blink tr1, r63
LOCAL(ct_r4_fp): /* Copy r4 from an FP register. */
shlri r1, 23 - 3, r34
andi r34, 3 << 3, r33
addi r33, LOCAL(ct_r4_fp_copy) - datalabel LOCAL(ct_r4_fp_base), r32
LOCAL(ct_r4_fp_base):
ptrel/l r32, tr2
movi 7, r30
shlli r30, 23, r31
andc r1, r31, r1
blink tr2, r63
LOCAL(ct_r4_fp_copy):
fmov.dq dr0, r4
blink tr1, r63
fmov.dq dr2, r4
blink tr1, r63
fmov.dq dr4, r4
blink tr1, r63
LOCAL(ct_r5_fp): /* Copy r5 from an FP register. */
shlri r1, 20 - 3, r34
andi r34, 3 << 3, r33
addi r33, LOCAL(ct_r5_fp_copy) - datalabel LOCAL(ct_r5_fp_base), r32
LOCAL(ct_r5_fp_base):
ptrel/l r32, tr2
movi 7, r30
shlli r30, 20, r31
andc r1, r31, r1
blink tr2, r63
LOCAL(ct_r5_fp_copy):
fmov.dq dr0, r5
blink tr1, r63
fmov.dq dr2, r5
blink tr1, r63
fmov.dq dr4, r5
blink tr1, r63
fmov.dq dr6, r5
blink tr1, r63
LOCAL(ct_r6_fph): /* Copy r6 from a high FP register. */
/* It must be dr8. */
fmov.dq dr8, r6
movi 15, r30
shlli r30, 16, r31
andc r1, r31, r1
blink tr1, r63
LOCAL(ct_r6_fpl): /* Copy r6 from a low FP register. */
shlri r1, 16 - 3, r34
andi r34, 3 << 3, r33
addi r33, LOCAL(ct_r6_fp_copy) - datalabel LOCAL(ct_r6_fp_base), r32
LOCAL(ct_r6_fp_base):
ptrel/l r32, tr2
movi 7, r30
shlli r30, 16, r31
andc r1, r31, r1
blink tr2, r63
LOCAL(ct_r6_fp_copy):
fmov.dq dr0, r6
blink tr1, r63
fmov.dq dr2, r6
blink tr1, r63
fmov.dq dr4, r6
blink tr1, r63
fmov.dq dr6, r6
blink tr1, r63
LOCAL(ct_r7_fph): /* Copy r7 from a high FP register. */
/* It is either dr8 or dr10. */
movi 15 << 12, r31
shlri r1, 12, r32
andc r1, r31, r1
fmov.dq dr8, r7
beqi/l r32, 8, tr1
fmov.dq dr10, r7
blink tr1, r63
LOCAL(ct_r7_fpl): /* Copy r7 from a low FP register. */
shlri r1, 12 - 3, r34
andi r34, 3 << 3, r33
addi r33, LOCAL(ct_r7_fp_copy) - datalabel LOCAL(ct_r7_fp_base), r32
LOCAL(ct_r7_fp_base):
ptrel/l r32, tr2
movi 7 << 12, r31
andc r1, r31, r1
blink tr2, r63
LOCAL(ct_r7_fp_copy):
fmov.dq dr0, r7
blink tr1, r63
fmov.dq dr2, r7
blink tr1, r63
fmov.dq dr4, r7
blink tr1, r63
fmov.dq dr6, r7
blink tr1, r63
LOCAL(ct_r8_fph): /* Copy r8 from a high FP register. */
/* It is either dr8 or dr10. */
movi 15 << 8, r31
andi r1, 1 << 8, r32
andc r1, r31, r1
fmov.dq dr8, r8
beq/l r32, r63, tr1
fmov.dq dr10, r8
blink tr1, r63
LOCAL(ct_r8_fpl): /* Copy r8 from a low FP register. */
shlri r1, 8 - 3, r34
andi r34, 3 << 3, r33
addi r33, LOCAL(ct_r8_fp_copy) - datalabel LOCAL(ct_r8_fp_base), r32
LOCAL(ct_r8_fp_base):
ptrel/l r32, tr2
movi 7 << 8, r31
andc r1, r31, r1
blink tr2, r63
LOCAL(ct_r8_fp_copy):
fmov.dq dr0, r8
blink tr1, r63
fmov.dq dr2, r8
blink tr1, r63
fmov.dq dr4, r8
blink tr1, r63
fmov.dq dr6, r8
blink tr1, r63
LOCAL(ct_r9_fph): /* Copy r9 from a high FP register. */
/* It is either dr8 or dr10. */
movi 15 << 4, r31
andi r1, 1 << 4, r32
andc r1, r31, r1
fmov.dq dr8, r9
beq/l r32, r63, tr1
fmov.dq dr10, r9
blink tr1, r63
LOCAL(ct_r9_fpl): /* Copy r9 from a low FP register. */
shlri r1, 4 - 3, r34
andi r34, 3 << 3, r33
addi r33, LOCAL(ct_r9_fp_copy) - datalabel LOCAL(ct_r9_fp_base), r32
LOCAL(ct_r9_fp_base):
ptrel/l r32, tr2
movi 7 << 4, r31
andc r1, r31, r1
blink tr2, r63
LOCAL(ct_r9_fp_copy):
fmov.dq dr0, r9
blink tr1, r63
fmov.dq dr2, r9
blink tr1, r63
fmov.dq dr4, r9
blink tr1, r63
fmov.dq dr6, r9
blink tr1, r63
LOCAL(ct_r2_ld): /* Copy r2 from a memory address. */
pt/l LOCAL(ct_r2_load), tr2
movi 3, r30
shlli r30, 29, r31
and r1, r31, r32
andc r1, r31, r1
beq/l r31, r32, tr2
addi.l r2, 8, r3
ldx.q r2, r63, r2
/* Fall through. */
LOCAL(ct_r3_ld): /* Copy r3 from a memory address. */
pt/l LOCAL(ct_r3_load), tr2
movi 3, r30
shlli r30, 26, r31
and r1, r31, r32
andc r1, r31, r1
beq/l r31, r32, tr2
addi.l r3, 8, r4
ldx.q r3, r63, r3
LOCAL(ct_r4_ld): /* Copy r4 from a memory address. */
pt/l LOCAL(ct_r4_load), tr2
movi 3, r30
shlli r30, 23, r31
and r1, r31, r32
andc r1, r31, r1
beq/l r31, r32, tr2
addi.l r4, 8, r5
ldx.q r4, r63, r4
LOCAL(ct_r5_ld): /* Copy r5 from a memory address. */
pt/l LOCAL(ct_r5_load), tr2
movi 3, r30
shlli r30, 20, r31
and r1, r31, r32
andc r1, r31, r1
beq/l r31, r32, tr2
addi.l r5, 8, r6
ldx.q r5, r63, r5
LOCAL(ct_r6_ld): /* Copy r6 from a memory address. */
pt/l LOCAL(ct_r6_load), tr2
movi 3 << 16, r31
and r1, r31, r32
andc r1, r31, r1
beq/l r31, r32, tr2
addi.l r6, 8, r7
ldx.q r6, r63, r6
LOCAL(ct_r7_ld): /* Copy r7 from a memory address. */
pt/l LOCAL(ct_r7_load), tr2
movi 3 << 12, r31
and r1, r31, r32
andc r1, r31, r1
beq/l r31, r32, tr2
addi.l r7, 8, r8
ldx.q r7, r63, r7
LOCAL(ct_r8_ld): /* Copy r8 from a memory address. */
pt/l LOCAL(ct_r8_load), tr2
movi 3 << 8, r31
and r1, r31, r32
andc r1, r31, r1
beq/l r31, r32, tr2
addi.l r8, 8, r9
ldx.q r8, r63, r8
LOCAL(ct_r9_ld): /* Copy r9 from a memory address. */
pt/l LOCAL(ct_check_tramp), tr2
ldx.q r9, r63, r9
blink tr2, r63
LOCAL(ct_r2_load):
ldx.q r2, r63, r2
blink tr1, r63
LOCAL(ct_r3_load):
ldx.q r3, r63, r3
blink tr1, r63
LOCAL(ct_r4_load):
ldx.q r4, r63, r4
blink tr1, r63
LOCAL(ct_r5_load):
ldx.q r5, r63, r5
blink tr1, r63
LOCAL(ct_r6_load):
ldx.q r6, r63, r6
blink tr1, r63
LOCAL(ct_r7_load):
ldx.q r7, r63, r7
blink tr1, r63
LOCAL(ct_r8_load):
ldx.q r8, r63, r8
blink tr1, r63
LOCAL(ct_r2_pop): /* Pop r2 from the stack. */
movi 1, r30
ldx.q r15, r63, r2
shlli r30, 29, r31
addi.l r15, 8, r15
andc r1, r31, r1
blink tr1, r63
LOCAL(ct_r3_pop): /* Pop r3 from the stack. */
movi 1, r30
ldx.q r15, r63, r3
shlli r30, 26, r31
addi.l r15, 8, r15
andc r1, r31, r1
blink tr1, r63
LOCAL(ct_r4_pop): /* Pop r4 from the stack. */
movi 1, r30
ldx.q r15, r63, r4
shlli r30, 23, r31
addi.l r15, 8, r15
andc r1, r31, r1
blink tr1, r63
LOCAL(ct_r5_pop): /* Pop r5 from the stack. */
movi 1, r30
ldx.q r15, r63, r5
shlli r30, 20, r31
addi.l r15, 8, r15
andc r1, r31, r1
blink tr1, r63
LOCAL(ct_r6_pop): /* Pop r6 from the stack. */
movi 1, r30
ldx.q r15, r63, r6
shlli r30, 16, r31
addi.l r15, 8, r15
andc r1, r31, r1
blink tr1, r63
LOCAL(ct_r7_pop): /* Pop r7 from the stack. */
ldx.q r15, r63, r7
movi 1 << 12, r31
addi.l r15, 8, r15
andc r1, r31, r1
blink tr1, r63
LOCAL(ct_r8_pop): /* Pop r8 from the stack. */
ldx.q r15, r63, r8
movi 1 << 8, r31
addi.l r15, 8, r15
andc r1, r31, r1
blink tr1, r63
LOCAL(ct_pop_seq): /* Pop a sequence of registers off the stack. */
andi r1, 7 << 1, r30
movi (LOCAL(ct_end_of_pop_seq) >> 16) & 65535, r32
shlli r30, 2, r31
shori LOCAL(ct_end_of_pop_seq) & 65535, r32
sub.l r32, r31, r33
ptabs/l r33, tr2
blink tr2, r63
LOCAL(ct_start_of_pop_seq): /* Beginning of pop sequence. */
ldx.q r15, r63, r3
addi.l r15, 8, r15
ldx.q r15, r63, r4
addi.l r15, 8, r15
ldx.q r15, r63, r5
addi.l r15, 8, r15
ldx.q r15, r63, r6
addi.l r15, 8, r15
ldx.q r15, r63, r7
addi.l r15, 8, r15
ldx.q r15, r63, r8
addi.l r15, 8, r15
LOCAL(ct_r9_pop): /* Pop r9 from the stack. */
ldx.q r15, r63, r9
addi.l r15, 8, r15
LOCAL(ct_end_of_pop_seq): /* Label used to compute first pop instruction. */
LOCAL(ct_check_tramp): /* Check whether we need a trampoline. */
pt/u LOCAL(ct_ret_wide), tr2
andi r1, 1, r1
bne/u r1, r63, tr2
LOCAL(ct_call_func): /* Just branch to the function. */
blink tr0, r63
LOCAL(ct_ret_wide): /* Call the function, so that we can unpack its
64-bit return value. */
add.l r18, r63, r10
blink tr0, r18
ptabs r10, tr0
#if __LITTLE_ENDIAN__
shari r2, 32, r3
add.l r2, r63, r2
#else
add.l r2, r63, r3
shari r2, 32, r2
#endif
blink tr0, r63
ENDFUNC(GLOBAL(GCC_shcompact_call_trampoline))
#endif /* L_shcompact_call_trampoline */
#ifdef L_shcompact_return_trampoline
/* This function does the converse of the code in `ret_wide'
above. It is tail-called by SHcompact functions returning
64-bit non-floating-point values, to pack the 32-bit values in
r2 and r3 into r2. */
.mode SHmedia
.section .text..SHmedia32, "ax"
.align 2
.global GLOBAL(GCC_shcompact_return_trampoline)
HIDDEN_FUNC(GLOBAL(GCC_shcompact_return_trampoline))
GLOBAL(GCC_shcompact_return_trampoline):
ptabs/l r18, tr0
#if __LITTLE_ENDIAN__
addz.l r2, r63, r2
shlli r3, 32, r3
#else
addz.l r3, r63, r3
shlli r2, 32, r2
#endif
or r3, r2, r2
blink tr0, r63
ENDFUNC(GLOBAL(GCC_shcompact_return_trampoline))
#endif /* L_shcompact_return_trampoline */
#ifdef L_shcompact_incoming_args
.section .rodata
.align 1
LOCAL(ia_main_table):
.word 1 /* Invalid, just loop */
.word LOCAL(ia_r2_ld) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_r2_push) - datalabel LOCAL(ia_main_label)
.word 1 /* Invalid, just loop */
.word LOCAL(ia_r3_ld) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_r3_push) - datalabel LOCAL(ia_main_label)
.word 1 /* Invalid, just loop */
.word LOCAL(ia_r4_ld) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_r4_push) - datalabel LOCAL(ia_main_label)
.word 1 /* Invalid, just loop */
.word LOCAL(ia_r5_ld) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_r5_push) - datalabel LOCAL(ia_main_label)
.word 1 /* Invalid, just loop */
.word 1 /* Invalid, just loop */
.word LOCAL(ia_r6_ld) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_r6_push) - datalabel LOCAL(ia_main_label)
.word 1 /* Invalid, just loop */
.word 1 /* Invalid, just loop */
.word LOCAL(ia_r7_ld) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_r7_push) - datalabel LOCAL(ia_main_label)
.word 1 /* Invalid, just loop */
.word 1 /* Invalid, just loop */
.word LOCAL(ia_r8_ld) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_r8_push) - datalabel LOCAL(ia_main_label)
.word 1 /* Invalid, just loop */
.word 1 /* Invalid, just loop */
.word LOCAL(ia_r9_ld) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_r9_push) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_push_seq) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_push_seq) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_r9_push) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_return) - datalabel LOCAL(ia_main_label)
.word LOCAL(ia_return) - datalabel LOCAL(ia_main_label)
.mode SHmedia
.section .text..SHmedia32, "ax"
.align 2
/* This function stores 64-bit general-purpose registers back in
the stack, and loads the address in which each register
was stored into itself. The lower 32 bits of r17 hold the address
to begin storing, and the upper 32 bits of r17 hold the cookie.
Its execution time is linear on the
number of registers that actually have to be copied, and it is
optimized for structures larger than 64 bits, as opposed to
individual `long long' arguments. See sh.h for details on the
actual bit pattern. */
.global GLOBAL(GCC_shcompact_incoming_args)
FUNC(GLOBAL(GCC_shcompact_incoming_args))
GLOBAL(GCC_shcompact_incoming_args):
ptabs/l r18, tr0 /* Prepare to return. */
shlri r17, 32, r0 /* Load the cookie. */
movi ((datalabel LOCAL(ia_main_table) - 31 * 2) >> 16) & 65535, r43
pt/l LOCAL(ia_loop), tr1
add.l r17, r63, r17
shori ((datalabel LOCAL(ia_main_table) - 31 * 2)) & 65535, r43
LOCAL(ia_loop):
nsb r0, r36
shlli r36, 1, r37
ldx.w r43, r37, r38
LOCAL(ia_main_label):
ptrel/l r38, tr2
blink tr2, r63
LOCAL(ia_r2_ld): /* Store r2 and load its address. */
movi 3, r38
shlli r38, 29, r39
and r0, r39, r40
andc r0, r39, r0
stx.q r17, r63, r2
add.l r17, r63, r2
addi.l r17, 8, r17
beq/u r39, r40, tr1
LOCAL(ia_r3_ld): /* Store r3 and load its address. */
movi 3, r38
shlli r38, 26, r39
and r0, r39, r40
andc r0, r39, r0
stx.q r17, r63, r3
add.l r17, r63, r3
addi.l r17, 8, r17
beq/u r39, r40, tr1
LOCAL(ia_r4_ld): /* Store r4 and load its address. */
movi 3, r38
shlli r38, 23, r39
and r0, r39, r40
andc r0, r39, r0
stx.q r17, r63, r4
add.l r17, r63, r4
addi.l r17, 8, r17
beq/u r39, r40, tr1
LOCAL(ia_r5_ld): /* Store r5 and load its address. */
movi 3, r38
shlli r38, 20, r39
and r0, r39, r40
andc r0, r39, r0
stx.q r17, r63, r5
add.l r17, r63, r5
addi.l r17, 8, r17
beq/u r39, r40, tr1
LOCAL(ia_r6_ld): /* Store r6 and load its address. */
movi 3, r38
shlli r38, 16, r39
and r0, r39, r40
andc r0, r39, r0
stx.q r17, r63, r6
add.l r17, r63, r6
addi.l r17, 8, r17
beq/u r39, r40, tr1
LOCAL(ia_r7_ld): /* Store r7 and load its address. */
movi 3 << 12, r39
and r0, r39, r40
andc r0, r39, r0
stx.q r17, r63, r7
add.l r17, r63, r7
addi.l r17, 8, r17
beq/u r39, r40, tr1
LOCAL(ia_r8_ld): /* Store r8 and load its address. */
movi 3 << 8, r39
and r0, r39, r40
andc r0, r39, r0
stx.q r17, r63, r8
add.l r17, r63, r8
addi.l r17, 8, r17
beq/u r39, r40, tr1
LOCAL(ia_r9_ld): /* Store r9 and load its address. */
stx.q r17, r63, r9
add.l r17, r63, r9
blink tr0, r63
LOCAL(ia_r2_push): /* Push r2 onto the stack. */
movi 1, r38
shlli r38, 29, r39
andc r0, r39, r0
stx.q r17, r63, r2
addi.l r17, 8, r17
blink tr1, r63
LOCAL(ia_r3_push): /* Push r3 onto the stack. */
movi 1, r38
shlli r38, 26, r39
andc r0, r39, r0
stx.q r17, r63, r3
addi.l r17, 8, r17
blink tr1, r63
LOCAL(ia_r4_push): /* Push r4 onto the stack. */
movi 1, r38
shlli r38, 23, r39
andc r0, r39, r0
stx.q r17, r63, r4
addi.l r17, 8, r17
blink tr1, r63
LOCAL(ia_r5_push): /* Push r5 onto the stack. */
movi 1, r38
shlli r38, 20, r39
andc r0, r39, r0
stx.q r17, r63, r5
addi.l r17, 8, r17
blink tr1, r63
LOCAL(ia_r6_push): /* Push r6 onto the stack. */
movi 1, r38
shlli r38, 16, r39
andc r0, r39, r0
stx.q r17, r63, r6
addi.l r17, 8, r17
blink tr1, r63
LOCAL(ia_r7_push): /* Push r7 onto the stack. */
movi 1 << 12, r39
andc r0, r39, r0
stx.q r17, r63, r7
addi.l r17, 8, r17
blink tr1, r63
LOCAL(ia_r8_push): /* Push r8 onto the stack. */
movi 1 << 8, r39
andc r0, r39, r0
stx.q r17, r63, r8
addi.l r17, 8, r17
blink tr1, r63
LOCAL(ia_push_seq): /* Push a sequence of registers onto the stack. */
andi r0, 7 << 1, r38
movi (LOCAL(ia_end_of_push_seq) >> 16) & 65535, r40
shlli r38, 2, r39
shori LOCAL(ia_end_of_push_seq) & 65535, r40
sub.l r40, r39, r41
ptabs/l r41, tr2
blink tr2, r63
LOCAL(ia_stack_of_push_seq): /* Beginning of push sequence. */
stx.q r17, r63, r3
addi.l r17, 8, r17
stx.q r17, r63, r4
addi.l r17, 8, r17
stx.q r17, r63, r5
addi.l r17, 8, r17
stx.q r17, r63, r6
addi.l r17, 8, r17
stx.q r17, r63, r7
addi.l r17, 8, r17
stx.q r17, r63, r8
addi.l r17, 8, r17
LOCAL(ia_r9_push): /* Push r9 onto the stack. */
stx.q r17, r63, r9
LOCAL(ia_return): /* Return. */
blink tr0, r63
LOCAL(ia_end_of_push_seq): /* Label used to compute the first push instruction. */
ENDFUNC(GLOBAL(GCC_shcompact_incoming_args))
#endif /* L_shcompact_incoming_args */
#endif
#if __SH5__
#ifdef L_nested_trampoline
#if __SH5__ == 32
.section .text..SHmedia32,"ax"
#else
.text
#endif
.align 3 /* It is copied in units of 8 bytes in SHmedia mode. */
.global GLOBAL(GCC_nested_trampoline)
HIDDEN_FUNC(GLOBAL(GCC_nested_trampoline))
GLOBAL(GCC_nested_trampoline):
.mode SHmedia
ptrel/u r63, tr0
gettr tr0, r0
#if __SH5__ == 64
ld.q r0, 24, r1
#else
ld.l r0, 24, r1
#endif
ptabs/l r1, tr1
#if __SH5__ == 64
ld.q r0, 32, r1
#else
ld.l r0, 28, r1
#endif
blink tr1, r63
ENDFUNC(GLOBAL(GCC_nested_trampoline))
#endif /* L_nested_trampoline */
#endif /* __SH5__ */
#if __SH5__ == 32
#ifdef L_push_pop_shmedia_regs
.section .text..SHmedia32,"ax"
.mode SHmedia
.align 2
#ifndef __SH4_NOFPU__
.global GLOBAL(GCC_push_shmedia_regs)
FUNC(GLOBAL(GCC_push_shmedia_regs))
GLOBAL(GCC_push_shmedia_regs):
addi.l r15, -14*8, r15
fst.d r15, 13*8, dr62
fst.d r15, 12*8, dr60
fst.d r15, 11*8, dr58
fst.d r15, 10*8, dr56
fst.d r15, 9*8, dr54
fst.d r15, 8*8, dr52
fst.d r15, 7*8, dr50
fst.d r15, 6*8, dr48
fst.d r15, 5*8, dr46
fst.d r15, 4*8, dr44
fst.d r15, 3*8, dr42
fst.d r15, 2*8, dr40
fst.d r15, 1*8, dr38
fst.d r15, 0*8, dr36
#else /* ! __SH4_NOFPU__ */
.global GLOBAL(GCC_push_shmedia_regs_nofpu)
FUNC(GLOBAL(GCC_push_shmedia_regs_nofpu))
GLOBAL(GCC_push_shmedia_regs_nofpu):
#endif /* ! __SH4_NOFPU__ */
ptabs/l r18, tr0
addi.l r15, -27*8, r15
gettr tr7, r62
gettr tr6, r61
gettr tr5, r60
st.q r15, 26*8, r62
st.q r15, 25*8, r61
st.q r15, 24*8, r60
st.q r15, 23*8, r59
st.q r15, 22*8, r58
st.q r15, 21*8, r57
st.q r15, 20*8, r56
st.q r15, 19*8, r55
st.q r15, 18*8, r54
st.q r15, 17*8, r53
st.q r15, 16*8, r52
st.q r15, 15*8, r51
st.q r15, 14*8, r50
st.q r15, 13*8, r49
st.q r15, 12*8, r48
st.q r15, 11*8, r47
st.q r15, 10*8, r46
st.q r15, 9*8, r45
st.q r15, 8*8, r44
st.q r15, 7*8, r35
st.q r15, 6*8, r34
st.q r15, 5*8, r33
st.q r15, 4*8, r32
st.q r15, 3*8, r31
st.q r15, 2*8, r30
st.q r15, 1*8, r29
st.q r15, 0*8, r28
blink tr0, r63
#ifndef __SH4_NOFPU__
ENDFUNC(GLOBAL(GCC_push_shmedia_regs))
#else
ENDFUNC(GLOBAL(GCC_push_shmedia_regs_nofpu))
#endif
#ifndef __SH4_NOFPU__
.global GLOBAL(GCC_pop_shmedia_regs)
FUNC(GLOBAL(GCC_pop_shmedia_regs))
GLOBAL(GCC_pop_shmedia_regs):
pt .L0, tr1
movi 41*8, r0
fld.d r15, 40*8, dr62
fld.d r15, 39*8, dr60
fld.d r15, 38*8, dr58
fld.d r15, 37*8, dr56
fld.d r15, 36*8, dr54
fld.d r15, 35*8, dr52
fld.d r15, 34*8, dr50
fld.d r15, 33*8, dr48
fld.d r15, 32*8, dr46
fld.d r15, 31*8, dr44
fld.d r15, 30*8, dr42
fld.d r15, 29*8, dr40
fld.d r15, 28*8, dr38
fld.d r15, 27*8, dr36
blink tr1, r63
#else /* ! __SH4_NOFPU__ */
.global GLOBAL(GCC_pop_shmedia_regs_nofpu)
FUNC(GLOBAL(GCC_pop_shmedia_regs_nofpu))
GLOBAL(GCC_pop_shmedia_regs_nofpu):
#endif /* ! __SH4_NOFPU__ */
movi 27*8, r0
.L0:
ptabs r18, tr0
ld.q r15, 26*8, r62
ld.q r15, 25*8, r61
ld.q r15, 24*8, r60
ptabs r62, tr7
ptabs r61, tr6
ptabs r60, tr5
ld.q r15, 23*8, r59
ld.q r15, 22*8, r58
ld.q r15, 21*8, r57
ld.q r15, 20*8, r56
ld.q r15, 19*8, r55
ld.q r15, 18*8, r54
ld.q r15, 17*8, r53
ld.q r15, 16*8, r52
ld.q r15, 15*8, r51
ld.q r15, 14*8, r50
ld.q r15, 13*8, r49
ld.q r15, 12*8, r48
ld.q r15, 11*8, r47
ld.q r15, 10*8, r46
ld.q r15, 9*8, r45
ld.q r15, 8*8, r44
ld.q r15, 7*8, r35
ld.q r15, 6*8, r34
ld.q r15, 5*8, r33
ld.q r15, 4*8, r32
ld.q r15, 3*8, r31
ld.q r15, 2*8, r30
ld.q r15, 1*8, r29
ld.q r15, 0*8, r28
add.l r15, r0, r15
blink tr0, r63
#ifndef __SH4_NOFPU__
ENDFUNC(GLOBAL(GCC_pop_shmedia_regs))
#else
ENDFUNC(GLOBAL(GCC_pop_shmedia_regs_nofpu))
#endif
#endif /* __SH5__ == 32 */
#endif /* L_push_pop_shmedia_regs */
#ifdef L_div_table
#if __SH5__
#if defined(__pic__) && defined(__SHMEDIA__)
.global GLOBAL(sdivsi3)
FUNC(GLOBAL(sdivsi3))
#if __SH5__ == 32
.section .text..SHmedia32,"ax"
#else
.text
#endif
#if 0
/* ??? FIXME: Presumably due to a linker bug, exporting data symbols
in a text section does not work (at least for shared libraries):
the linker sets the LSB of the address as if this was SHmedia code. */
#define TEXT_DATA_BUG
#endif
.align 2
// inputs: r4,r5
// clobbered: r1,r18,r19,r20,r21,r25,tr0
// result in r0
.global GLOBAL(sdivsi3)
GLOBAL(sdivsi3):
#ifdef TEXT_DATA_BUG
ptb datalabel Local_div_table,tr0
#else
ptb GLOBAL(div_table_internal),tr0
#endif
nsb r5, r1
shlld r5, r1, r25 // normalize; [-2 ..1, 1..2) in s2.62
shari r25, 58, r21 // extract 5(6) bit index (s2.4 with hole -1..1)
/* bubble */
gettr tr0,r20
ldx.ub r20, r21, r19 // u0.8
shari r25, 32, r25 // normalize to s2.30
shlli r21, 1, r21
muls.l r25, r19, r19 // s2.38
ldx.w r20, r21, r21 // s2.14
ptabs r18, tr0
shari r19, 24, r19 // truncate to s2.14
sub r21, r19, r19 // some 11 bit inverse in s1.14
muls.l r19, r19, r21 // u0.28
sub r63, r1, r1
addi r1, 92, r1
muls.l r25, r21, r18 // s2.58
shlli r19, 45, r19 // multiply by two and convert to s2.58
/* bubble */
sub r19, r18, r18
shari r18, 28, r18 // some 22 bit inverse in s1.30
muls.l r18, r25, r0 // s2.60
muls.l r18, r4, r25 // s32.30
/* bubble */
shari r0, 16, r19 // s-16.44
muls.l r19, r18, r19 // s-16.74
shari r25, 63, r0
shari r4, 14, r18 // s19.-14
shari r19, 30, r19 // s-16.44
muls.l r19, r18, r19 // s15.30
xor r21, r0, r21 // You could also use the constant 1 << 27.
add r21, r25, r21
sub r21, r19, r21
shard r21, r1, r21
sub r21, r0, r0
blink tr0, r63
ENDFUNC(GLOBAL(sdivsi3))
/* This table has been generated by divtab.c .
Defects for bias -330:
Max defect: 6.081536e-07 at -1.000000e+00
Min defect: 2.849516e-08 at 1.030651e+00
Max 2nd step defect: 9.606539e-12 at -1.000000e+00
Min 2nd step defect: 0.000000e+00 at 0.000000e+00
Defect at 1: 1.238659e-07
Defect at -2: 1.061708e-07 */
#else /* ! __pic__ || ! __SHMEDIA__ */
.section .rodata
#endif /* __pic__ */
#if defined(TEXT_DATA_BUG) && defined(__pic__) && defined(__SHMEDIA__)
.balign 2
.type Local_div_table,@object
.size Local_div_table,128
/* negative division constants */
.word -16638
.word -17135
.word -17737
.word -18433
.word -19103
.word -19751
.word -20583
.word -21383
.word -22343
.word -23353
.word -24407
.word -25582
.word -26863
.word -28382
.word -29965
.word -31800
/* negative division factors */
.byte 66
.byte 70
.byte 75
.byte 81
.byte 87
.byte 93
.byte 101
.byte 109
.byte 119
.byte 130
.byte 142
.byte 156
.byte 172
.byte 192
.byte 214
.byte 241
.skip 16
Local_div_table:
.skip 16
/* positive division factors */
.byte 241
.byte 214
.byte 192
.byte 172
.byte 156
.byte 142
.byte 130
.byte 119
.byte 109
.byte 101
.byte 93
.byte 87
.byte 81
.byte 75
.byte 70
.byte 66
/* positive division constants */
.word 31801
.word 29966
.word 28383
.word 26864
.word 25583
.word 24408
.word 23354
.word 22344
.word 21384
.word 20584
.word 19752
.word 19104
.word 18434
.word 17738
.word 17136
.word 16639
.section .rodata
#endif /* TEXT_DATA_BUG */
.balign 2
.type GLOBAL(div_table),@object
.size GLOBAL(div_table),128
/* negative division constants */
.word -16638
.word -17135
.word -17737
.word -18433
.word -19103
.word -19751
.word -20583
.word -21383
.word -22343
.word -23353
.word -24407
.word -25582
.word -26863
.word -28382
.word -29965
.word -31800
/* negative division factors */
.byte 66
.byte 70
.byte 75
.byte 81
.byte 87
.byte 93
.byte 101
.byte 109
.byte 119
.byte 130
.byte 142
.byte 156
.byte 172
.byte 192
.byte 214
.byte 241
.skip 16
.global GLOBAL(div_table)
GLOBAL(div_table):
HIDDEN_ALIAS(div_table_internal,div_table)
.skip 16
/* positive division factors */
.byte 241
.byte 214
.byte 192
.byte 172
.byte 156
.byte 142
.byte 130
.byte 119
.byte 109
.byte 101
.byte 93
.byte 87
.byte 81
.byte 75
.byte 70
.byte 66
/* positive division constants */
.word 31801
.word 29966
.word 28383
.word 26864
.word 25583
.word 24408
.word 23354
.word 22344
.word 21384
.word 20584
.word 19752
.word 19104
.word 18434
.word 17738
.word 17136
.word 16639
#elif defined (__SH3__) || defined (__SH3E__) || defined (__SH4__) || defined (__SH4_SINGLE__) || defined (__SH4_SINGLE_ONLY__) || defined (__SH4_NOFPU__)
/* This code used shld, thus is not suitable for SH1 / SH2. */
/* Signed / unsigned division without use of FPU, optimized for SH4.
Uses a lookup table for divisors in the range -128 .. +128, and
div1 with case distinction for larger divisors in three more ranges.
The code is lumped together with the table to allow the use of mova. */
#ifdef __LITTLE_ENDIAN__
#define L_LSB 0
#define L_LSWMSB 1
#define L_MSWLSB 2
#else
#define L_LSB 3
#define L_LSWMSB 2
#define L_MSWLSB 1
#endif
.balign 4
.global GLOBAL(udivsi3_i4i)
FUNC(GLOBAL(udivsi3_i4i))
GLOBAL(udivsi3_i4i):
mov.w LOCAL(c128_w), r1
div0u
mov r4,r0
shlr8 r0
cmp/hi r1,r5
extu.w r5,r1
bf LOCAL(udiv_le128)
cmp/eq r5,r1
bf LOCAL(udiv_ge64k)
shlr r0
mov r5,r1
shll16 r5
mov.l r4,@-r15
div1 r5,r0
mov.l r1,@-r15
div1 r5,r0
div1 r5,r0
bra LOCAL(udiv_25)
div1 r5,r0
LOCAL(div_le128):
mova LOCAL(div_table_ix),r0
bra LOCAL(div_le128_2)
mov.b @(r0,r5),r1
LOCAL(udiv_le128):
mov.l r4,@-r15
mova LOCAL(div_table_ix),r0
mov.b @(r0,r5),r1
mov.l r5,@-r15
LOCAL(div_le128_2):
mova LOCAL(div_table_inv),r0
mov.l @(r0,r1),r1
mov r5,r0
tst #0xfe,r0
mova LOCAL(div_table_clz),r0
dmulu.l r1,r4
mov.b @(r0,r5),r1
bt/s LOCAL(div_by_1)
mov r4,r0
mov.l @r15+,r5
sts mach,r0
/* clrt */
addc r4,r0
mov.l @r15+,r4
rotcr r0
rts
shld r1,r0
LOCAL(div_by_1_neg):
neg r4,r0
LOCAL(div_by_1):
mov.l @r15+,r5
rts
mov.l @r15+,r4
LOCAL(div_ge64k):
bt/s LOCAL(div_r8)
div0u
shll8 r5
bra LOCAL(div_ge64k_2)
div1 r5,r0
LOCAL(udiv_ge64k):
cmp/hi r0,r5
mov r5,r1
bt LOCAL(udiv_r8)
shll8 r5
mov.l r4,@-r15
div1 r5,r0
mov.l r1,@-r15
LOCAL(div_ge64k_2):
div1 r5,r0
mov.l LOCAL(zero_l),r1
.rept 4
div1 r5,r0
.endr
mov.l r1,@-r15
div1 r5,r0
mov.w LOCAL(m256_w),r1
div1 r5,r0
mov.b r0,@(L_LSWMSB,r15)
xor r4,r0
and r1,r0
bra LOCAL(div_ge64k_end)
xor r4,r0
LOCAL(div_r8):
shll16 r4
bra LOCAL(div_r8_2)
shll8 r4
LOCAL(udiv_r8):
mov.l r4,@-r15
shll16 r4
clrt
shll8 r4
mov.l r5,@-r15
LOCAL(div_r8_2):
rotcl r4
mov r0,r1
div1 r5,r1
mov r4,r0
rotcl r0
mov r5,r4
div1 r5,r1
.rept 5
rotcl r0; div1 r5,r1
.endr
rotcl r0
mov.l @r15+,r5
div1 r4,r1
mov.l @r15+,r4
rts
rotcl r0
ENDFUNC(GLOBAL(udivsi3_i4i))
.global GLOBAL(sdivsi3_i4i)
FUNC(GLOBAL(sdivsi3_i4i))
/* This is link-compatible with a GLOBAL(sdivsi3) call,
but we effectively clobber only r1. */
GLOBAL(sdivsi3_i4i):
mov.l r4,@-r15
cmp/pz r5
mov.w LOCAL(c128_w), r1
bt/s LOCAL(pos_divisor)
cmp/pz r4
mov.l r5,@-r15
neg r5,r5
bt/s LOCAL(neg_result)
cmp/hi r1,r5
neg r4,r4
LOCAL(pos_result):
extu.w r5,r0
bf LOCAL(div_le128)
cmp/eq r5,r0
mov r4,r0
shlr8 r0
bf/s LOCAL(div_ge64k)
cmp/hi r0,r5
div0u
shll16 r5
div1 r5,r0
div1 r5,r0
div1 r5,r0
LOCAL(udiv_25):
mov.l LOCAL(zero_l),r1
div1 r5,r0
div1 r5,r0
mov.l r1,@-r15
.rept 3
div1 r5,r0
.endr
mov.b r0,@(L_MSWLSB,r15)
xtrct r4,r0
swap.w r0,r0
.rept 8
div1 r5,r0
.endr
mov.b r0,@(L_LSWMSB,r15)
LOCAL(div_ge64k_end):
.rept 8
div1 r5,r0
.endr
mov.l @r15+,r4 ! zero-extension and swap using LS unit.
extu.b r0,r0
mov.l @r15+,r5
or r4,r0
mov.l @r15+,r4
rts
rotcl r0
LOCAL(div_le128_neg):
tst #0xfe,r0
mova LOCAL(div_table_ix),r0
mov.b @(r0,r5),r1
mova LOCAL(div_table_inv),r0
bt/s LOCAL(div_by_1_neg)
mov.l @(r0,r1),r1
mova LOCAL(div_table_clz),r0
dmulu.l r1,r4
mov.b @(r0,r5),r1
mov.l @r15+,r5
sts mach,r0
/* clrt */
addc r4,r0
mov.l @r15+,r4
rotcr r0
shld r1,r0
rts
neg r0,r0
LOCAL(pos_divisor):
mov.l r5,@-r15
bt/s LOCAL(pos_result)
cmp/hi r1,r5
neg r4,r4
LOCAL(neg_result):
extu.w r5,r0
bf LOCAL(div_le128_neg)
cmp/eq r5,r0
mov r4,r0
shlr8 r0
bf/s LOCAL(div_ge64k_neg)
cmp/hi r0,r5
div0u
mov.l LOCAL(zero_l),r1
shll16 r5
div1 r5,r0
mov.l r1,@-r15
.rept 7
div1 r5,r0
.endr
mov.b r0,@(L_MSWLSB,r15)
xtrct r4,r0
swap.w r0,r0
.rept 8
div1 r5,r0
.endr
mov.b r0,@(L_LSWMSB,r15)
LOCAL(div_ge64k_neg_end):
.rept 8
div1 r5,r0
.endr
mov.l @r15+,r4 ! zero-extension and swap using LS unit.
extu.b r0,r1
mov.l @r15+,r5
or r4,r1
LOCAL(div_r8_neg_end):
mov.l @r15+,r4
rotcl r1
rts
neg r1,r0
LOCAL(div_ge64k_neg):
bt/s LOCAL(div_r8_neg)
div0u
shll8 r5
mov.l LOCAL(zero_l),r1
.rept 6
div1 r5,r0
.endr
mov.l r1,@-r15
div1 r5,r0
mov.w LOCAL(m256_w),r1
div1 r5,r0
mov.b r0,@(L_LSWMSB,r15)
xor r4,r0
and r1,r0
bra LOCAL(div_ge64k_neg_end)
xor r4,r0
LOCAL(c128_w):
.word 128
LOCAL(div_r8_neg):
clrt
shll16 r4
mov r4,r1
shll8 r1
mov r5,r4
.rept 7
rotcl r1; div1 r5,r0
.endr
mov.l @r15+,r5
rotcl r1
bra LOCAL(div_r8_neg_end)
div1 r4,r0
LOCAL(m256_w):
.word 0xff00
/* This table has been generated by divtab-sh4.c. */
.balign 4
LOCAL(div_table_clz):
.byte 0
.byte 1
.byte 0
.byte -1
.byte -1
.byte -2
.byte -2
.byte -2
.byte -2
.byte -3
.byte -3
.byte -3
.byte -3
.byte -3
.byte -3
.byte -3
.byte -3
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -4
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -5
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
.byte -6
/* Lookup table translating positive divisor to index into table of
normalized inverse. N.B. the '0' entry is also the last entry of the
previous table, and causes an unaligned access for division by zero. */
LOCAL(div_table_ix):
.byte -6
.byte -128
.byte -128
.byte 0
.byte -128
.byte -64
.byte 0
.byte 64
.byte -128
.byte -96
.byte -64
.byte -32
.byte 0
.byte 32
.byte 64
.byte 96
.byte -128
.byte -112
.byte -96
.byte -80
.byte -64
.byte -48
.byte -32
.byte -16
.byte 0
.byte 16
.byte 32
.byte 48
.byte 64
.byte 80
.byte 96
.byte 112
.byte -128
.byte -120
.byte -112
.byte -104
.byte -96
.byte -88
.byte -80
.byte -72
.byte -64
.byte -56
.byte -48
.byte -40
.byte -32
.byte -24
.byte -16
.byte -8
.byte 0
.byte 8
.byte 16
.byte 24
.byte 32
.byte 40
.byte 48
.byte 56
.byte 64
.byte 72
.byte 80
.byte 88
.byte 96
.byte 104
.byte 112
.byte 120
.byte -128
.byte -124
.byte -120
.byte -116
.byte -112
.byte -108
.byte -104
.byte -100
.byte -96
.byte -92
.byte -88
.byte -84
.byte -80
.byte -76
.byte -72
.byte -68
.byte -64
.byte -60
.byte -56
.byte -52
.byte -48
.byte -44
.byte -40
.byte -36
.byte -32
.byte -28
.byte -24
.byte -20
.byte -16
.byte -12
.byte -8
.byte -4
.byte 0
.byte 4
.byte 8
.byte 12
.byte 16
.byte 20
.byte 24
.byte 28
.byte 32
.byte 36
.byte 40
.byte 44
.byte 48
.byte 52
.byte 56
.byte 60
.byte 64
.byte 68
.byte 72
.byte 76
.byte 80
.byte 84
.byte 88
.byte 92
.byte 96
.byte 100
.byte 104
.byte 108
.byte 112
.byte 116
.byte 120
.byte 124
.byte -128
/* 1/64 .. 1/127, normalized. There is an implicit leading 1 in bit 32. */
.balign 4
LOCAL(zero_l):
.long 0x0
.long 0xF81F81F9
.long 0xF07C1F08
.long 0xE9131AC0
.long 0xE1E1E1E2
.long 0xDAE6076C
.long 0xD41D41D5
.long 0xCD856891
.long 0xC71C71C8
.long 0xC0E07039
.long 0xBACF914D
.long 0xB4E81B4F
.long 0xAF286BCB
.long 0xA98EF607
.long 0xA41A41A5
.long 0x9EC8E952
.long 0x9999999A
.long 0x948B0FCE
.long 0x8F9C18FA
.long 0x8ACB90F7
.long 0x86186187
.long 0x81818182
.long 0x7D05F418
.long 0x78A4C818
.long 0x745D1746
.long 0x702E05C1
.long 0x6C16C16D
.long 0x68168169
.long 0x642C8591
.long 0x60581606
.long 0x5C9882BA
.long 0x58ED2309
LOCAL(div_table_inv):
.long 0x55555556
.long 0x51D07EAF
.long 0x4E5E0A73
.long 0x4AFD6A06
.long 0x47AE147B
.long 0x446F8657
.long 0x41414142
.long 0x3E22CBCF
.long 0x3B13B13C
.long 0x38138139
.long 0x3521CFB3
.long 0x323E34A3
.long 0x2F684BDB
.long 0x2C9FB4D9
.long 0x29E4129F
.long 0x27350B89
.long 0x24924925
.long 0x21FB7813
.long 0x1F7047DD
.long 0x1CF06ADB
.long 0x1A7B9612
.long 0x18118119
.long 0x15B1E5F8
.long 0x135C8114
.long 0x11111112
.long 0xECF56BF
.long 0xC9714FC
.long 0xA6810A7
.long 0x8421085
.long 0x624DD30
.long 0x4104105
.long 0x2040811
/* maximum error: 0.987342 scaled: 0.921875*/
ENDFUNC(GLOBAL(sdivsi3_i4i))
#endif /* SH3 / SH4 */
#endif /* L_div_table */
#ifdef L_udiv_qrnnd_16
#if !__SHMEDIA__
HIDDEN_FUNC(GLOBAL(udiv_qrnnd_16))
/* r0: rn r1: qn */ /* r0: n1 r4: n0 r5: d r6: d1 */ /* r2: __m */
/* n1 < d, but n1 might be larger than d1. */
.global GLOBAL(udiv_qrnnd_16)
.balign 8
GLOBAL(udiv_qrnnd_16):
div0u
cmp/hi r6,r0
bt .Lots
.rept 16
div1 r6,r0
.endr
extu.w r0,r1
bt 0f
add r6,r0
0: rotcl r1
mulu.w r1,r5
xtrct r4,r0
swap.w r0,r0
sts macl,r2
cmp/hs r2,r0
sub r2,r0
bt 0f
addc r5,r0
add #-1,r1
bt 0f
1: add #-1,r1
rts
add r5,r0
.balign 8
.Lots:
sub r5,r0
swap.w r4,r1
xtrct r0,r1
clrt
mov r1,r0
addc r5,r0
mov #-1,r1
SL1(bf, 1b,
shlr16 r1)
0: rts
nop
ENDFUNC(GLOBAL(udiv_qrnnd_16))
#endif /* !__SHMEDIA__ */
#endif /* L_udiv_qrnnd_16 */
|