DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (3865bf230c49)

VCS Links

Line Code
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
/*
 * jidctfst.c
 *
 * Copyright (C) 1994-1998, Thomas G. Lane.
 * This file is part of the Independent JPEG Group's software.
 * For conditions of distribution and use, see the accompanying README file.
 *
 * This file contains a fast, not so accurate integer implementation of the
 * inverse DCT (Discrete Cosine Transform).  In the IJG code, this routine
 * must also perform dequantization of the input coefficients.
 *
 * A 2-D IDCT can be done by 1-D IDCT on each column followed by 1-D IDCT
 * on each row (or vice versa, but it's more convenient to emit a row at
 * a time).  Direct algorithms are also available, but they are much more
 * complex and seem not to be any faster when reduced to code.
 *
 * This implementation is based on Arai, Agui, and Nakajima's algorithm for
 * scaled DCT.  Their original paper (Trans. IEICE E-71(11):1095) is in
 * Japanese, but the algorithm is described in the Pennebaker & Mitchell
 * JPEG textbook (see REFERENCES section in file README).  The following code
 * is based directly on figure 4-8 in P&M.
 * While an 8-point DCT cannot be done in less than 11 multiplies, it is
 * possible to arrange the computation so that many of the multiplies are
 * simple scalings of the final outputs.  These multiplies can then be
 * folded into the multiplications or divisions by the JPEG quantization
 * table entries.  The AA&N method leaves only 5 multiplies and 29 adds
 * to be done in the DCT itself.
 * The primary disadvantage of this method is that with fixed-point math,
 * accuracy is lost due to imprecise representation of the scaled
 * quantization values.  The smaller the quantization table entry, the less
 * precise the scaled value, so this implementation does worse with high-
 * quality-setting files than with low-quality ones.
 */

#define JPEG_INTERNALS
#include "jinclude.h"
#include "jpeglib.h"
#include "jdct.h"		/* Private declarations for DCT subsystem */


#ifdef DCT_IFAST_SUPPORTED


/*
 * This module is specialized to the case DCTSIZE = 8.
 */

#if DCTSIZE != 8
  Sorry, this code only copes with 8x8 DCTs. /* deliberate syntax err */
#endif


/* Scaling decisions are generally the same as in the LL&M algorithm;
 * see jidctint.c for more details.  However, we choose to descale
 * (right shift) multiplication products as soon as they are formed,
 * rather than carrying additional fractional bits into subsequent additions.
 * This compromises accuracy slightly, but it lets us save a few shifts.
 * More importantly, 16-bit arithmetic is then adequate (for 8-bit samples)
 * everywhere except in the multiplications proper; this saves a good deal
 * of work on 16-bit-int machines.
 *
 * The dequantized coefficients are not integers because the AA&N scaling
 * factors have been incorporated.  We represent them scaled up by PASS1_BITS,
 * so that the first and second IDCT rounds have the same input scaling.
 * For 8-bit JSAMPLEs, we choose IFAST_SCALE_BITS = PASS1_BITS so as to
 * avoid a descaling shift; this compromises accuracy rather drastically
 * for small quantization table entries, but it saves a lot of shifts.
 * For 12-bit JSAMPLEs, there's no hope of using 16x16 multiplies anyway,
 * so we use a much larger scaling factor to preserve accuracy.
 *
 * A final compromise is to represent the multiplicative constants to only
 * 8 fractional bits, rather than 13.  This saves some shifting work on some
 * machines, and may also reduce the cost of multiplication (since there
 * are fewer one-bits in the constants).
 */

#if BITS_IN_JSAMPLE == 8
#define CONST_BITS  8
#define PASS1_BITS  2
#else
#define CONST_BITS  8
#define PASS1_BITS  1		/* lose a little precision to avoid overflow */
#endif

/* Some C compilers fail to reduce "FIX(constant)" at compile time, thus
 * causing a lot of useless floating-point operations at run time.
 * To get around this we use the following pre-calculated constants.
 * If you change CONST_BITS you may want to add appropriate values.
 * (With a reasonable C compiler, you can just rely on the FIX() macro...)
 */

#if CONST_BITS == 8
#define FIX_1_082392200  ((INT32)  277)		/* FIX(1.082392200) */
#define FIX_1_414213562  ((INT32)  362)		/* FIX(1.414213562) */
#define FIX_1_847759065  ((INT32)  473)		/* FIX(1.847759065) */
#define FIX_2_613125930  ((INT32)  669)		/* FIX(2.613125930) */
#else
#define FIX_1_082392200  FIX(1.082392200)
#define FIX_1_414213562  FIX(1.414213562)
#define FIX_1_847759065  FIX(1.847759065)
#define FIX_2_613125930  FIX(2.613125930)
#endif


/* We can gain a little more speed, with a further compromise in accuracy,
 * by omitting the addition in a descaling shift.  This yields an incorrectly
 * rounded result half the time...
 */

#ifndef USE_ACCURATE_ROUNDING
#undef DESCALE
#define DESCALE(x,n)  RIGHT_SHIFT(x, n)
#endif


/* Multiply a DCTELEM variable by an INT32 constant, and immediately
 * descale to yield a DCTELEM result.
 */

#define MULTIPLY(var,const)  ((DCTELEM) DESCALE((var) * (const), CONST_BITS))


/* Dequantize a coefficient by multiplying it by the multiplier-table
 * entry; produce a DCTELEM result.  For 8-bit data a 16x16->16
 * multiplication will do.  For 12-bit data, the multiplier table is
 * declared INT32, so a 32-bit multiply will be used.
 */

#if BITS_IN_JSAMPLE == 8
#define DEQUANTIZE(coef,quantval)  (((IFAST_MULT_TYPE) (coef)) * (quantval))
#else
#define DEQUANTIZE(coef,quantval)  \
	DESCALE((coef)*(quantval), IFAST_SCALE_BITS-PASS1_BITS)
#endif


/* Like DESCALE, but applies to a DCTELEM and produces an int.
 * We assume that int right shift is unsigned if INT32 right shift is.
 */

#ifdef RIGHT_SHIFT_IS_UNSIGNED
#define ISHIFT_TEMPS	DCTELEM ishift_temp;
#if BITS_IN_JSAMPLE == 8
#define DCTELEMBITS  16		/* DCTELEM may be 16 or 32 bits */
#else
#define DCTELEMBITS  32		/* DCTELEM must be 32 bits */
#endif
#define IRIGHT_SHIFT(x,shft)  \
    ((ishift_temp = (x)) < 0 ? \
     (ishift_temp >> (shft)) | ((~((DCTELEM) 0)) << (DCTELEMBITS-(shft))) : \
     (ishift_temp >> (shft)))
#else
#define ISHIFT_TEMPS
#define IRIGHT_SHIFT(x,shft)	((x) >> (shft))
#endif

#ifdef USE_ACCURATE_ROUNDING
#define IDESCALE(x,n)  ((int) IRIGHT_SHIFT((x) + (1 << ((n)-1)), n))
#else
#define IDESCALE(x,n)  ((int) IRIGHT_SHIFT(x, n))
#endif

#ifdef HAVE_MMX_INTEL_MNEMONICS
__inline GLOBAL(void)
jpeg_idct_ifast_mmx (j_decompress_ptr cinfo, jpeg_component_info * compptr,
		 JCOEFPTR coef_block,
		 JSAMPARRAY output_buf, JDIMENSION output_col);
__inline GLOBAL(void)
jpeg_idct_ifast_orig (j_decompress_ptr cinfo, jpeg_component_info * compptr,
		 JCOEFPTR coef_block,
		 JSAMPARRAY output_buf, JDIMENSION output_col);
#endif

GLOBAL(void)
jpeg_idct_ifast(j_decompress_ptr cinfo, jpeg_component_info * compptr,
		 JCOEFPTR coef_block,
		 JSAMPARRAY output_buf, JDIMENSION output_col);


#ifdef HAVE_MMX_INTEL_MNEMONICS
GLOBAL(void)
jpeg_idct_ifast (j_decompress_ptr cinfo, jpeg_component_info * compptr,
		 JCOEFPTR coef_block,
		 JSAMPARRAY output_buf, JDIMENSION output_col)
{
if (MMXAvailable)
	jpeg_idct_ifast_mmx(cinfo, compptr, coef_block, output_buf, output_col);
else
	jpeg_idct_ifast_orig(cinfo, compptr, coef_block, output_buf, output_col);
}
#else

/*
 * Perform dequantization and inverse DCT on one block of coefficients.
 */

GLOBAL (void)
jpeg_idct_ifast (j_decompress_ptr cinfo, jpeg_component_info * compptr,
		 JCOEFPTR coef_block,
		 JSAMPARRAY output_buf, JDIMENSION output_col)
{
  DCTELEM tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
  DCTELEM tmp10, tmp11, tmp12, tmp13;
  DCTELEM z5, z10, z11, z12, z13;
  JCOEFPTR inptr;
  IFAST_MULT_TYPE * quantptr;
  int * wsptr;
  JSAMPROW outptr;
  JSAMPLE *range_limit = IDCT_range_limit(cinfo);
  int ctr;
  int workspace[DCTSIZE2];	/* buffers data between passes */
  SHIFT_TEMPS			/* for DESCALE */
  ISHIFT_TEMPS			/* for IDESCALE */

  /* Pass 1: process columns from input, store into work array. */

  inptr = coef_block;
  quantptr = (IFAST_MULT_TYPE *) compptr->dct_table;
  wsptr = workspace;
  for (ctr = DCTSIZE; ctr > 0; ctr--) {
    /* Due to quantization, we will usually find that many of the input
     * coefficients are zero, especially the AC terms.  We can exploit this
     * by short-circuiting the IDCT calculation for any column in which all
     * the AC terms are zero.  In that case each output is equal to the
     * DC coefficient (with scale factor as needed).
     * With typical images and quantization tables, half or more of the
     * column DCT calculations can be simplified this way.
     */
    
    if (inptr[DCTSIZE*1] == 0 && inptr[DCTSIZE*2] == 0 &&
	inptr[DCTSIZE*3] == 0 && inptr[DCTSIZE*4] == 0 &&
	inptr[DCTSIZE*5] == 0 && inptr[DCTSIZE*6] == 0 &&
	inptr[DCTSIZE*7] == 0) {
      /* AC terms all zero */
      int dcval = (int) DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);

      wsptr[DCTSIZE*0] = dcval;
      wsptr[DCTSIZE*1] = dcval;
      wsptr[DCTSIZE*2] = dcval;
      wsptr[DCTSIZE*3] = dcval;
      wsptr[DCTSIZE*4] = dcval;
      wsptr[DCTSIZE*5] = dcval;
      wsptr[DCTSIZE*6] = dcval;
      wsptr[DCTSIZE*7] = dcval;
      
      inptr++;			/* advance pointers to next column */
      quantptr++;
      wsptr++;
      continue;
    }
    
    /* Even part */

    tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);
    tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]);
    tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]);
    tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]);

    tmp10 = tmp0 + tmp2;	/* phase 3 */
    tmp11 = tmp0 - tmp2;

    tmp13 = tmp1 + tmp3;	/* phases 5-3 */
    tmp12 = MULTIPLY(tmp1 - tmp3, FIX_1_414213562) - tmp13; /* 2*c4 */

    tmp0 = tmp10 + tmp13;	/* phase 2 */
    tmp3 = tmp10 - tmp13;
    tmp1 = tmp11 + tmp12;
    tmp2 = tmp11 - tmp12;
    
    /* Odd part */

    tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]);
    tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]);
    tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]);
    tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]);

    z13 = tmp6 + tmp5;		/* phase 6 */
    z10 = tmp6 - tmp5;
    z11 = tmp4 + tmp7;
    z12 = tmp4 - tmp7;

    tmp7 = z11 + z13;		/* phase 5 */
    tmp11 = MULTIPLY(z11 - z13, FIX_1_414213562); /* 2*c4 */

    z5 = MULTIPLY(z10 + z12, FIX_1_847759065); /* 2*c2 */
    tmp10 = MULTIPLY(z12, FIX_1_082392200) - z5; /* 2*(c2-c6) */
    tmp12 = MULTIPLY(z10, - FIX_2_613125930) + z5; /* -2*(c2+c6) */

    tmp6 = tmp12 - tmp7;	/* phase 2 */
    tmp5 = tmp11 - tmp6;
    tmp4 = tmp10 + tmp5;

    wsptr[DCTSIZE*0] = (int) (tmp0 + tmp7);
    wsptr[DCTSIZE*7] = (int) (tmp0 - tmp7);
    wsptr[DCTSIZE*1] = (int) (tmp1 + tmp6);
    wsptr[DCTSIZE*6] = (int) (tmp1 - tmp6);
    wsptr[DCTSIZE*2] = (int) (tmp2 + tmp5);
    wsptr[DCTSIZE*5] = (int) (tmp2 - tmp5);
    wsptr[DCTSIZE*4] = (int) (tmp3 + tmp4);
    wsptr[DCTSIZE*3] = (int) (tmp3 - tmp4);

    inptr++;			/* advance pointers to next column */
    quantptr++;
    wsptr++;
  }
  
  /* Pass 2: process rows from work array, store into output array. */
  /* Note that we must descale the results by a factor of 8 == 2**3, */
  /* and also undo the PASS1_BITS scaling. */

  wsptr = workspace;
  for (ctr = 0; ctr < DCTSIZE; ctr++) {
    outptr = output_buf[ctr] + output_col;
    /* Rows of zeroes can be exploited in the same way as we did with columns.
     * However, the column calculation has created many nonzero AC terms, so
     * the simplification applies less often (typically 5% to 10% of the time).
     * On machines with very fast multiplication, it's possible that the
     * test takes more time than it's worth.  In that case this section
     * may be commented out.
     */
    
#ifndef NO_ZERO_ROW_TEST
    if (wsptr[1] == 0 && wsptr[2] == 0 && wsptr[3] == 0 && wsptr[4] == 0 &&
	wsptr[5] == 0 && wsptr[6] == 0 && wsptr[7] == 0) {
      /* AC terms all zero */
      JSAMPLE dcval = range_limit[IDESCALE(wsptr[0], PASS1_BITS+3)
				  & RANGE_MASK];
      
      outptr[0] = dcval;
      outptr[1] = dcval;
      outptr[2] = dcval;
      outptr[3] = dcval;
      outptr[4] = dcval;
      outptr[5] = dcval;
      outptr[6] = dcval;
      outptr[7] = dcval;

      wsptr += DCTSIZE;		/* advance pointer to next row */
      continue;
    }
#endif
    
    /* Even part */

    tmp10 = ((DCTELEM) wsptr[0] + (DCTELEM) wsptr[4]);
    tmp11 = ((DCTELEM) wsptr[0] - (DCTELEM) wsptr[4]);

    tmp13 = ((DCTELEM) wsptr[2] + (DCTELEM) wsptr[6]);
    tmp12 = MULTIPLY((DCTELEM) wsptr[2] - (DCTELEM) wsptr[6], FIX_1_414213562)
	    - tmp13;

    tmp0 = tmp10 + tmp13;
    tmp3 = tmp10 - tmp13;
    tmp1 = tmp11 + tmp12;
    tmp2 = tmp11 - tmp12;

    /* Odd part */

    z13 = (DCTELEM) wsptr[5] + (DCTELEM) wsptr[3];
    z10 = (DCTELEM) wsptr[5] - (DCTELEM) wsptr[3];
    z11 = (DCTELEM) wsptr[1] + (DCTELEM) wsptr[7];
    z12 = (DCTELEM) wsptr[1] - (DCTELEM) wsptr[7];

    tmp7 = z11 + z13;		/* phase 5 */
    tmp11 = MULTIPLY(z11 - z13, FIX_1_414213562); /* 2*c4 */

    z5 = MULTIPLY(z10 + z12, FIX_1_847759065); /* 2*c2 */
    tmp10 = MULTIPLY(z12, FIX_1_082392200) - z5; /* 2*(c2-c6) */
    tmp12 = MULTIPLY(z10, - FIX_2_613125930) + z5; /* -2*(c2+c6) */

    tmp6 = tmp12 - tmp7;	/* phase 2 */
    tmp5 = tmp11 - tmp6;
    tmp4 = tmp10 + tmp5;

    /* Final output stage: scale down by a factor of 8 and range-limit */

    outptr[0] = range_limit[IDESCALE(tmp0 + tmp7, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[7] = range_limit[IDESCALE(tmp0 - tmp7, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[1] = range_limit[IDESCALE(tmp1 + tmp6, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[6] = range_limit[IDESCALE(tmp1 - tmp6, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[2] = range_limit[IDESCALE(tmp2 + tmp5, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[5] = range_limit[IDESCALE(tmp2 - tmp5, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[4] = range_limit[IDESCALE(tmp3 + tmp4, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[3] = range_limit[IDESCALE(tmp3 - tmp4, PASS1_BITS+3)
			    & RANGE_MASK];

    wsptr += DCTSIZE;		/* advance pointer to next row */
  }
}

#endif

#ifdef HAVE_MMX_INTEL_MNEMONICS


_inline GLOBAL(void)
jpeg_idct_ifast_orig (j_decompress_ptr cinfo, jpeg_component_info * compptr,
		 JCOEFPTR coef_block,
		 JSAMPARRAY output_buf, JDIMENSION output_col)
{
  DCTELEM tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
  DCTELEM tmp10, tmp11, tmp12, tmp13;
  DCTELEM z5, z10, z11, z12, z13;
  JCOEFPTR inptr;
  IFAST_MULT_TYPE * quantptr;
  int * wsptr;
  JSAMPROW outptr;
  JSAMPLE *range_limit = IDCT_range_limit(cinfo);
  int ctr;
  int workspace[DCTSIZE2];	/* buffers data between passes */
  SHIFT_TEMPS			/* for DESCALE */
  ISHIFT_TEMPS			/* for IDESCALE */

  /* Pass 1: process columns from input, store into work array. */

  inptr = coef_block;
  quantptr = (IFAST_MULT_TYPE *) compptr->dct_table;
  wsptr = workspace;
  for (ctr = DCTSIZE; ctr > 0; ctr--) {
    /* Due to quantization, we will usually find that many of the input
     * coefficients are zero, especially the AC terms.  We can exploit this
     * by short-circuiting the IDCT calculation for any column in which all
     * the AC terms are zero.  In that case each output is equal to the
     * DC coefficient (with scale factor as needed).
     * With typical images and quantization tables, half or more of the
     * column DCT calculations can be simplified this way.
     */
    
    if ((inptr[DCTSIZE*1] | inptr[DCTSIZE*2] | inptr[DCTSIZE*3] |
	 inptr[DCTSIZE*4] | inptr[DCTSIZE*5] | inptr[DCTSIZE*6] |
	 inptr[DCTSIZE*7]) == 0) {
      /* AC terms all zero */
      int dcval = (int) DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);

      wsptr[DCTSIZE*0] = dcval;
      wsptr[DCTSIZE*1] = dcval;
      wsptr[DCTSIZE*2] = dcval;
      wsptr[DCTSIZE*3] = dcval;
      wsptr[DCTSIZE*4] = dcval;
      wsptr[DCTSIZE*5] = dcval;
      wsptr[DCTSIZE*6] = dcval;
      wsptr[DCTSIZE*7] = dcval;
      
      inptr++;			/* advance pointers to next column */
      quantptr++;
      wsptr++;
      continue;
    }
    
    /* Even part */

    tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);
    tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]);
    tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]);
    tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]);

    tmp10 = tmp0 + tmp2;	/* phase 3 */
    tmp11 = tmp0 - tmp2;

    tmp13 = tmp1 + tmp3;	/* phases 5-3 */
    tmp12 = MULTIPLY(tmp1 - tmp3, FIX_1_414213562) - tmp13; /* 2*c4 */

    tmp0 = tmp10 + tmp13;	/* phase 2 */
    tmp3 = tmp10 - tmp13;
    tmp1 = tmp11 + tmp12;
    tmp2 = tmp11 - tmp12;
    
    /* Odd part */

    tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]);
    tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]);
    tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]);
    tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]);

    z13 = tmp6 + tmp5;		/* phase 6 */
    z10 = tmp6 - tmp5;
    z11 = tmp4 + tmp7;
    z12 = tmp4 - tmp7;

    tmp7 = z11 + z13;		/* phase 5 */
    tmp11 = MULTIPLY(z11 - z13, FIX_1_414213562); /* 2*c4 */

    z5 = MULTIPLY(z10 + z12, FIX_1_847759065); /* 2*c2 */
    tmp10 = MULTIPLY(z12, FIX_1_082392200) - z5; /* 2*(c2-c6) */
    tmp12 = MULTIPLY(z10, - FIX_2_613125930) + z5; /* -2*(c2+c6) */

    tmp6 = tmp12 - tmp7;	/* phase 2 */
    tmp5 = tmp11 - tmp6;
    tmp4 = tmp10 + tmp5;

    wsptr[DCTSIZE*0] = (int) (tmp0 + tmp7);
    wsptr[DCTSIZE*7] = (int) (tmp0 - tmp7);
    wsptr[DCTSIZE*1] = (int) (tmp1 + tmp6);
    wsptr[DCTSIZE*6] = (int) (tmp1 - tmp6);
    wsptr[DCTSIZE*2] = (int) (tmp2 + tmp5);
    wsptr[DCTSIZE*5] = (int) (tmp2 - tmp5);
    wsptr[DCTSIZE*4] = (int) (tmp3 + tmp4);
    wsptr[DCTSIZE*3] = (int) (tmp3 - tmp4);

    inptr++;			/* advance pointers to next column */
    quantptr++;
    wsptr++;
  }
  
  /* Pass 2: process rows from work array, store into output array. */
  /* Note that we must descale the results by a factor of 8 == 2**3, */
  /* and also undo the PASS1_BITS scaling. */

  wsptr = workspace;
  for (ctr = 0; ctr < DCTSIZE; ctr++) {
    outptr = output_buf[ctr] + output_col;
    /* Rows of zeroes can be exploited in the same way as we did with columns.
     * However, the column calculation has created many nonzero AC terms, so
     * the simplification applies less often (typically 5% to 10% of the time).
     * On machines with very fast multiplication, it's possible that the
     * test takes more time than it's worth.  In that case this section
     * may be commented out.
     */
    
#ifndef NO_ZERO_ROW_TEST
    if ((wsptr[1] | wsptr[2] | wsptr[3] | wsptr[4] | wsptr[5] | wsptr[6] |
	 wsptr[7]) == 0) {
      /* AC terms all zero */
      JSAMPLE dcval = range_limit[IDESCALE(wsptr[0], PASS1_BITS+3)
				  & RANGE_MASK];
      
      outptr[0] = dcval;
      outptr[1] = dcval;
      outptr[2] = dcval;
      outptr[3] = dcval;
      outptr[4] = dcval;
      outptr[5] = dcval;
      outptr[6] = dcval;
      outptr[7] = dcval;

      wsptr += DCTSIZE;		/* advance pointer to next row */
      continue;
    }
#endif
    
    /* Even part */

    tmp10 = ((DCTELEM) wsptr[0] + (DCTELEM) wsptr[4]);
    tmp11 = ((DCTELEM) wsptr[0] - (DCTELEM) wsptr[4]);

    tmp13 = ((DCTELEM) wsptr[2] + (DCTELEM) wsptr[6]);
    tmp12 = MULTIPLY((DCTELEM) wsptr[2] - (DCTELEM) wsptr[6], FIX_1_414213562)
	    - tmp13;

    tmp0 = tmp10 + tmp13;
    tmp3 = tmp10 - tmp13;
    tmp1 = tmp11 + tmp12;
    tmp2 = tmp11 - tmp12;

    /* Odd part */

    z13 = (DCTELEM) wsptr[5] + (DCTELEM) wsptr[3];
    z10 = (DCTELEM) wsptr[5] - (DCTELEM) wsptr[3];
    z11 = (DCTELEM) wsptr[1] + (DCTELEM) wsptr[7];
    z12 = (DCTELEM) wsptr[1] - (DCTELEM) wsptr[7];

    tmp7 = z11 + z13;		/* phase 5 */
    tmp11 = MULTIPLY(z11 - z13, FIX_1_414213562); /* 2*c4 */

    z5 = MULTIPLY(z10 + z12, FIX_1_847759065); /* 2*c2 */
    tmp10 = MULTIPLY(z12, FIX_1_082392200) - z5; /* 2*(c2-c6) */
    tmp12 = MULTIPLY(z10, - FIX_2_613125930) + z5; /* -2*(c2+c6) */

    tmp6 = tmp12 - tmp7;	/* phase 2 */
    tmp5 = tmp11 - tmp6;
    tmp4 = tmp10 + tmp5;

    /* Final output stage: scale down by a factor of 8 and range-limit */

    outptr[0] = range_limit[IDESCALE(tmp0 + tmp7, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[7] = range_limit[IDESCALE(tmp0 - tmp7, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[1] = range_limit[IDESCALE(tmp1 + tmp6, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[6] = range_limit[IDESCALE(tmp1 - tmp6, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[2] = range_limit[IDESCALE(tmp2 + tmp5, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[5] = range_limit[IDESCALE(tmp2 - tmp5, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[4] = range_limit[IDESCALE(tmp3 + tmp4, PASS1_BITS+3)
			    & RANGE_MASK];
    outptr[3] = range_limit[IDESCALE(tmp3 - tmp4, PASS1_BITS+3)
			    & RANGE_MASK];

    wsptr += DCTSIZE;		/* advance pointer to next row */
  }
}


	static	  __int64 fix_141		= 0x5a825a825a825a82;
	static	  __int64 fix_184n261	= 0xcf04cf04cf04cf04;
	static	  __int64 fix_184		= 0x7641764176417641;
	static	  __int64 fix_n184		= 0x896f896f896f896f;
	static	  __int64 fix_108n184	= 0xcf04cf04cf04cf04;
	static	  __int64 const_0x0080	= 0x0080008000800080;


__inline GLOBAL(void)
jpeg_idct_ifast_mmx (j_decompress_ptr cinfo, jpeg_component_info * compptr,
		 JCOEFPTR inptr,
		 JSAMPARRAY outptr, JDIMENSION output_col)
{

  int16 workspace[DCTSIZE2 + 4];	/* buffers data between passes */
  int16 *wsptr=workspace;
  int16 *quantptr=compptr->dct_table;

  __asm{ 
    
	mov		edi, quantptr
	mov		ebx, inptr
	mov		esi, wsptr
	add		esi, 0x07		;align wsptr to qword
	and		esi, 0xfffffff8	;align wsptr to qword

	mov		eax, esi

    /* Odd part */


	movq		mm1, [ebx + 8*10]		;load inptr[DCTSIZE*5]

	pmullw		mm1, [edi + 8*10]		;tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]);

	movq		mm0, [ebx + 8*6]		;load inptr[DCTSIZE*3]

	pmullw		mm0, [edi + 8*6]		;tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]);

	movq		mm3, [ebx + 8*2]		;load inptr[DCTSIZE*1]
	movq	mm2, mm1					;copy tmp6	/* phase 6 */

	pmullw		mm3, [edi + 8*2]		;tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]);

	movq		mm4, [ebx + 8*14]		;load inptr[DCTSIZE*1]
	paddw	mm1, mm0					;z13 = tmp6 + tmp5;

	pmullw		mm4, [edi + 8*14]	    ;tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]);
	psubw	mm2, mm0					;z10 = tmp6 - tmp5   

	psllw		mm2, 2				;shift z10
	movq		mm0, mm2			;copy z10

	pmulhw		mm2, fix_184n261	;MULTIPLY( z12, FIX_1_847759065); /* 2*c2 */
	movq		mm5, mm3				;copy tmp4

	pmulhw		mm0, fix_n184		;MULTIPLY(z10, -FIX_1_847759065); /* 2*c2 */
	paddw		mm3, mm4				;z11 = tmp4 + tmp7;

	movq		mm6, mm3				;copy z11			/* phase 5 */
	psubw		mm5, mm4				;z12 = tmp4 - tmp7;

	psubw		mm6, mm1				;z11-z13
	psllw		mm5, 2				;shift z12

	movq		mm4, [ebx + 8*12]		;load inptr[DCTSIZE*6], even part
 	movq		mm7, mm5			;copy z12

	pmulhw		mm5, fix_108n184	;MULT(z12, (FIX_1_08-FIX_1_84)) //- z5; /* 2*(c2-c6) */ even part
	paddw		mm3, mm1				;tmp7 = z11 + z13;	


    /* Even part */
	pmulhw		mm7, fix_184		;MULTIPLY(z10,(FIX_1_847759065 - FIX_2_613125930)) //+ z5; /* -2*(c2+c6) */
	psllw		mm6, 2

	movq		mm1, [ebx + 8*4]		;load inptr[DCTSIZE*2]

	pmullw		mm1, [edi + 8*4]		;tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]);
	paddw		mm0, mm5			;tmp10

	pmullw		mm4, [edi + 8*12]		;tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]);
	paddw		mm2, mm7			;tmp12

	pmulhw		mm6, fix_141			;tmp11 = MULTIPLY(z11 - z13, FIX_1_414213562); /* 2*c4 */
	psubw		mm2, mm3		;tmp6 = tmp12 - tmp7

	movq		mm5, mm1				;copy tmp1
	paddw		mm1, mm4				;tmp13= tmp1 + tmp3;	/* phases 5-3 */

	psubw		mm5, mm4				;tmp1-tmp3
	psubw		mm6, mm2		;tmp5 = tmp11 - tmp6;

	movq		[esi+8*0], mm1			;save tmp13 in workspace
	psllw		mm5, 2					;shift tmp1-tmp3
    
	movq		mm7, [ebx + 8*0]		;load inptr[DCTSIZE*0]

	pmulhw		mm5, fix_141			;MULTIPLY(tmp1 - tmp3, FIX_1_414213562)
	paddw		mm0, mm6		;tmp4 = tmp10 + tmp5;

	pmullw		mm7, [edi + 8*0]		;tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);

	movq		mm4, [ebx + 8*8]		;load inptr[DCTSIZE*4]
	
	pmullw		mm4, [edi + 8*8]		;tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]);
	psubw		mm5, mm1				;tmp12 = MULTIPLY(tmp1 - tmp3, FIX_1_414213562) - tmp13; /* 2*c4 */

	movq		[esi+8*4], mm0		;save tmp4 in workspace
	movq		mm1, mm7			;copy tmp0	/* phase 3 */

	movq		[esi+8*2], mm5		;save tmp12 in workspace
	psubw		mm1, mm4			;tmp11 = tmp0 - tmp2; 

	paddw		mm7, mm4			;tmp10 = tmp0 + tmp2;
    movq		mm5, mm1		;copy tmp11
	
	paddw		mm1, [esi+8*2]	;tmp1 = tmp11 + tmp12;
	movq		mm4, mm7		;copy tmp10		/* phase 2 */

	paddw		mm7, [esi+8*0]	;tmp0 = tmp10 + tmp13;	

	psubw		mm4, [esi+8*0]	;tmp3 = tmp10 - tmp13;
	movq		mm0, mm7		;copy tmp0

	psubw		mm5, [esi+8*2]	;tmp2 = tmp11 - tmp12;
	paddw		mm7, mm3		;wsptr[DCTSIZE*0] = (int) (tmp0 + tmp7);
	
	psubw		mm0, mm3			;wsptr[DCTSIZE*7] = (int) (tmp0 - tmp7);

	movq		[esi + 8*0], mm7	;wsptr[DCTSIZE*0]
	movq		mm3, mm1			;copy tmp1

	movq		[esi + 8*14], mm0	;wsptr[DCTSIZE*7]
	paddw		mm1, mm2			;wsptr[DCTSIZE*1] = (int) (tmp1 + tmp6);

	psubw		mm3, mm2			;wsptr[DCTSIZE*6] = (int) (tmp1 - tmp6);

	movq		[esi + 8*2], mm1	;wsptr[DCTSIZE*1]
	movq		mm1, mm4			;copy tmp3

	movq		[esi + 8*12], mm3	;wsptr[DCTSIZE*6]

	paddw		mm4, [esi+8*4]		;wsptr[DCTSIZE*4] = (int) (tmp3 + tmp4);

	psubw		mm1, [esi+8*4]		;wsptr[DCTSIZE*3] = (int) (tmp3 - tmp4);

	movq		[esi + 8*8], mm4
	movq		mm7, mm5			;copy tmp2

	paddw		mm5, mm6			;wsptr[DCTSIZE*2] = (int) (tmp2 + tmp5)

	movq		[esi+8*6], mm1		;
	psubw		mm7, mm6			;wsptr[DCTSIZE*5] = (int) (tmp2 - tmp5);

	movq		[esi + 8*4], mm5

	movq		[esi + 8*10], mm7



/*****************************************************************/
	add		edi, 8
	add		ebx, 8
	add		esi, 8

/*****************************************************************/




	movq		mm1, [ebx + 8*10]		;load inptr[DCTSIZE*5]

	pmullw		mm1, [edi + 8*10]		;tmp6 = DEQUANTIZE(inptr[DCTSIZE*5], quantptr[DCTSIZE*5]);

	movq		mm0, [ebx + 8*6]		;load inptr[DCTSIZE*3]

	pmullw		mm0, [edi + 8*6]		;tmp5 = DEQUANTIZE(inptr[DCTSIZE*3], quantptr[DCTSIZE*3]);

	movq		mm3, [ebx + 8*2]		;load inptr[DCTSIZE*1]
	movq	mm2, mm1					;copy tmp6	/* phase 6 */

	pmullw		mm3, [edi + 8*2]		;tmp4 = DEQUANTIZE(inptr[DCTSIZE*1], quantptr[DCTSIZE*1]);

	movq		mm4, [ebx + 8*14]		;load inptr[DCTSIZE*1]
	paddw	mm1, mm0					;z13 = tmp6 + tmp5;

	pmullw		mm4, [edi + 8*14]	    ;tmp7 = DEQUANTIZE(inptr[DCTSIZE*7], quantptr[DCTSIZE*7]);
	psubw	mm2, mm0					;z10 = tmp6 - tmp5   

	psllw		mm2, 2				;shift z10
	movq		mm0, mm2			;copy z10

	pmulhw		mm2, fix_184n261	;MULTIPLY( z12, FIX_1_847759065); /* 2*c2 */
	movq		mm5, mm3				;copy tmp4

	pmulhw		mm0, fix_n184		;MULTIPLY(z10, -FIX_1_847759065); /* 2*c2 */
	paddw		mm3, mm4				;z11 = tmp4 + tmp7;

	movq		mm6, mm3				;copy z11			/* phase 5 */
	psubw		mm5, mm4				;z12 = tmp4 - tmp7;

	psubw		mm6, mm1				;z11-z13
	psllw		mm5, 2				;shift z12

	movq		mm4, [ebx + 8*12]		;load inptr[DCTSIZE*6], even part
 	movq		mm7, mm5			;copy z12

	pmulhw		mm5, fix_108n184	;MULT(z12, (FIX_1_08-FIX_1_84)) //- z5; /* 2*(c2-c6) */ even part
	paddw		mm3, mm1				;tmp7 = z11 + z13;	


    /* Even part */
	pmulhw		mm7, fix_184		;MULTIPLY(z10,(FIX_1_847759065 - FIX_2_613125930)) //+ z5; /* -2*(c2+c6) */
	psllw		mm6, 2

	movq		mm1, [ebx + 8*4]		;load inptr[DCTSIZE*2]

	pmullw		mm1, [edi + 8*4]		;tmp1 = DEQUANTIZE(inptr[DCTSIZE*2], quantptr[DCTSIZE*2]);
	paddw		mm0, mm5			;tmp10

	pmullw		mm4, [edi + 8*12]		;tmp3 = DEQUANTIZE(inptr[DCTSIZE*6], quantptr[DCTSIZE*6]);
	paddw		mm2, mm7			;tmp12

	pmulhw		mm6, fix_141			;tmp11 = MULTIPLY(z11 - z13, FIX_1_414213562); /* 2*c4 */
	psubw		mm2, mm3		;tmp6 = tmp12 - tmp7

	movq		mm5, mm1				;copy tmp1
	paddw		mm1, mm4				;tmp13= tmp1 + tmp3;	/* phases 5-3 */

	psubw		mm5, mm4				;tmp1-tmp3
	psubw		mm6, mm2		;tmp5 = tmp11 - tmp6;

	movq		[esi+8*0], mm1			;save tmp13 in workspace
	psllw		mm5, 2					;shift tmp1-tmp3
    
	movq		mm7, [ebx + 8*0]		;load inptr[DCTSIZE*0]
	paddw		mm0, mm6		;tmp4 = tmp10 + tmp5;

	pmulhw		mm5, fix_141			;MULTIPLY(tmp1 - tmp3, FIX_1_414213562)

	pmullw		mm7, [edi + 8*0]		;tmp0 = DEQUANTIZE(inptr[DCTSIZE*0], quantptr[DCTSIZE*0]);

	movq		mm4, [ebx + 8*8]		;load inptr[DCTSIZE*4]
	
	pmullw		mm4, [edi + 8*8]		;tmp2 = DEQUANTIZE(inptr[DCTSIZE*4], quantptr[DCTSIZE*4]);
	psubw		mm5, mm1				;tmp12 = MULTIPLY(tmp1 - tmp3, FIX_1_414213562) - tmp13; /* 2*c4 */

	movq		[esi+8*4], mm0		;save tmp4 in workspace
	movq		mm1, mm7			;copy tmp0	/* phase 3 */

	movq		[esi+8*2], mm5		;save tmp12 in workspace
	psubw		mm1, mm4			;tmp11 = tmp0 - tmp2; 

	paddw		mm7, mm4			;tmp10 = tmp0 + tmp2;
    movq		mm5, mm1		;copy tmp11
	
	paddw		mm1, [esi+8*2]	;tmp1 = tmp11 + tmp12;
	movq		mm4, mm7		;copy tmp10		/* phase 2 */

	paddw		mm7, [esi+8*0]	;tmp0 = tmp10 + tmp13;	

	psubw		mm4, [esi+8*0]	;tmp3 = tmp10 - tmp13;
	movq		mm0, mm7		;copy tmp0

	psubw		mm5, [esi+8*2]	;tmp2 = tmp11 - tmp12;
	paddw		mm7, mm3		;wsptr[DCTSIZE*0] = (int) (tmp0 + tmp7);
	
	psubw		mm0, mm3			;wsptr[DCTSIZE*7] = (int) (tmp0 - tmp7);

	movq		[esi + 8*0], mm7	;wsptr[DCTSIZE*0]
	movq		mm3, mm1			;copy tmp1

	movq		[esi + 8*14], mm0	;wsptr[DCTSIZE*7]
	paddw		mm1, mm2			;wsptr[DCTSIZE*1] = (int) (tmp1 + tmp6);

	psubw		mm3, mm2			;wsptr[DCTSIZE*6] = (int) (tmp1 - tmp6);

	movq		[esi + 8*2], mm1	;wsptr[DCTSIZE*1]
	movq		mm1, mm4			;copy tmp3

	movq		[esi + 8*12], mm3	;wsptr[DCTSIZE*6]

	paddw		mm4, [esi+8*4]		;wsptr[DCTSIZE*4] = (int) (tmp3 + tmp4);

	psubw		mm1, [esi+8*4]		;wsptr[DCTSIZE*3] = (int) (tmp3 - tmp4);

	movq		[esi + 8*8], mm4
	movq		mm7, mm5			;copy tmp2

	paddw		mm5, mm6			;wsptr[DCTSIZE*2] = (int) (tmp2 + tmp5)

	movq		[esi+8*6], mm1		;
	psubw		mm7, mm6			;wsptr[DCTSIZE*5] = (int) (tmp2 - tmp5);

	movq		[esi + 8*4], mm5

	movq		[esi + 8*10], mm7




/*****************************************************************/

  /* Pass 2: process rows from work array, store into output array. */
  /* Note that we must descale the results by a factor of 8 == 2**3, */
  /* and also undo the PASS1_BITS scaling. */

/*****************************************************************/
    /* Even part */

	mov			esi, eax
	mov			eax, outptr

//    tmp10 = ((DCTELEM) wsptr[0] + (DCTELEM) wsptr[4]);
//    tmp13 = ((DCTELEM) wsptr[2] + (DCTELEM) wsptr[6]);
//    tmp11 = ((DCTELEM) wsptr[0] - (DCTELEM) wsptr[4]);
//    tmp14 = ((DCTELEM) wsptr[2] - (DCTELEM) wsptr[6]);
	movq		mm0, [esi+8*0]		;wsptr[0,0],[0,1],[0,2],[0,3]

	movq		mm1, [esi+8*1]		;wsptr[0,4],[0,5],[0,6],[0,7]
	movq		mm2, mm0
	
	movq		mm3, [esi+8*2]		;wsptr[1,0],[1,1],[1,2],[1,3]
	paddw		mm0, mm1			;wsptr[0,tmp10],[xxx],[0,tmp13],[xxx]

	movq		mm4, [esi+8*3]		;wsptr[1,4],[1,5],[1,6],[1,7]
	psubw		mm2, mm1			;wsptr[0,tmp11],[xxx],[0,tmp14],[xxx]

	movq		mm6, mm0
	movq		mm5, mm3
	
	paddw		mm3, mm4			;wsptr[1,tmp10],[xxx],[1,tmp13],[xxx]
	movq		mm1, mm2

	psubw		mm5, mm4			;wsptr[1,tmp11],[xxx],[1,tmp14],[xxx]
	punpcklwd	mm0, mm3			;wsptr[0,tmp10],[1,tmp10],[xxx],[xxx]

	movq		mm7, [esi+8*7]		;wsptr[3,4],[3,5],[3,6],[3,7]
	punpckhwd	mm6, mm3			;wsptr[0,tmp13],[1,tmp13],[xxx],[xxx]

	movq		mm3, [esi+8*4]		;wsptr[2,0],[2,1],[2,2],[2,3]
	punpckldq	mm0, mm6	;wsptr[0,tmp10],[1,tmp10],[0,tmp13],[1,tmp13]

	punpcklwd	mm1, mm5			;wsptr[0,tmp11],[1,tmp11],[xxx],[xxx]
	movq		mm4, mm3

	movq		mm6, [esi+8*6]		;wsptr[3,0],[3,1],[3,2],[3,3]
	punpckhwd	mm2, mm5			;wsptr[0,tmp14],[1,tmp14],[xxx],[xxx]

	movq		mm5, [esi+8*5]		;wsptr[2,4],[2,5],[2,6],[2,7]
	punpckldq	mm1, mm2	;wsptr[0,tmp11],[1,tmp11],[0,tmp14],[1,tmp14]

	
	paddw		mm3, mm5			;wsptr[2,tmp10],[xxx],[2,tmp13],[xxx]
	movq		mm2, mm6

	psubw		mm4, mm5			;wsptr[2,tmp11],[xxx],[2,tmp14],[xxx]
	paddw		mm6, mm7			;wsptr[3,tmp10],[xxx],[3,tmp13],[xxx]

	movq		mm5, mm3
	punpcklwd	mm3, mm6			;wsptr[2,tmp10],[3,tmp10],[xxx],[xxx]
	
	psubw		mm2, mm7			;wsptr[3,tmp11],[xxx],[3,tmp14],[xxx]
	punpckhwd	mm5, mm6			;wsptr[2,tmp13],[3,tmp13],[xxx],[xxx]

	movq		mm7, mm4
	punpckldq	mm3, mm5	;wsptr[2,tmp10],[3,tmp10],[2,tmp13],[3,tmp13]

	punpcklwd	mm4, mm2			;wsptr[2,tmp11],[3,tmp11],[xxx],[xxx]

	punpckhwd	mm7, mm2			;wsptr[2,tmp14],[3,tmp14],[xxx],[xxx]

	punpckldq	mm4, mm7	;wsptr[2,tmp11],[3,tmp11],[2,tmp14],[3,tmp14]
	movq		mm6, mm1

//	mm0 = 	;wsptr[0,tmp10],[1,tmp10],[0,tmp13],[1,tmp13]
//	mm1 =	;wsptr[0,tmp11],[1,tmp11],[0,tmp14],[1,tmp14]


	movq		mm2, mm0
	punpckhdq	mm6, mm4	;wsptr[0,tmp14],[1,tmp14],[2,tmp14],[3,tmp14]

	punpckldq	mm1, mm4	;wsptr[0,tmp11],[1,tmp11],[2,tmp11],[3,tmp11]
	psllw		mm6, 2

	pmulhw		mm6, fix_141
	punpckldq	mm0, mm3	;wsptr[0,tmp10],[1,tmp10],[2,tmp10],[3,tmp10]

	punpckhdq	mm2, mm3	;wsptr[0,tmp13],[1,tmp13],[2,tmp13],[3,tmp13]
	movq		mm7, mm0

//    tmp0 = tmp10 + tmp13;
//    tmp3 = tmp10 - tmp13;
	paddw		mm0, mm2	;[0,tmp0],[1,tmp0],[2,tmp0],[3,tmp0]
	psubw		mm7, mm2	;[0,tmp3],[1,tmp3],[2,tmp3],[3,tmp3]

//    tmp12 = MULTIPLY(tmp14, FIX_1_414213562) - tmp13;
	psubw		mm6, mm2	;wsptr[0,tmp12],[1,tmp12],[2,tmp12],[3,tmp12]
//    tmp1 = tmp11 + tmp12;
//    tmp2 = tmp11 - tmp12;
	movq		mm5, mm1



    /* Odd part */

//    z13 = (DCTELEM) wsptr[5] + (DCTELEM) wsptr[3];
//    z10 = (DCTELEM) wsptr[5] - (DCTELEM) wsptr[3];
//    z11 = (DCTELEM) wsptr[1] + (DCTELEM) wsptr[7];
//    z12 = (DCTELEM) wsptr[1] - (DCTELEM) wsptr[7];
	movq		mm3, [esi+8*0]		;wsptr[0,0],[0,1],[0,2],[0,3]
	paddw		mm1, mm6	;[0,tmp1],[1,tmp1],[2,tmp1],[3,tmp1]

	movq		mm4, [esi+8*1]		;wsptr[0,4],[0,5],[0,6],[0,7]
	psubw		mm5, mm6	;[0,tmp2],[1,tmp2],[2,tmp2],[3,tmp2]

	movq		mm6, mm3
	punpckldq	mm3, mm4			;wsptr[0,0],[0,1],[0,4],[0,5]

	punpckhdq	mm4, mm6			;wsptr[0,6],[0,7],[0,2],[0,3]
	movq		mm2, mm3

//Save tmp0 and tmp1 in wsptr
	movq		[esi+8*0], mm0		;save tmp0
	paddw		mm2, mm4			;wsptr[xxx],[0,z11],[xxx],[0,z13]

	
//Continue with z10 --- z13
	movq		mm6, [esi+8*2]		;wsptr[1,0],[1,1],[1,2],[1,3]
	psubw		mm3, mm4			;wsptr[xxx],[0,z12],[xxx],[0,z10]

	movq		mm0, [esi+8*3]		;wsptr[1,4],[1,5],[1,6],[1,7]
	movq		mm4, mm6

	movq		[esi+8*1], mm1		;save tmp1
	punpckldq	mm6, mm0			;wsptr[1,0],[1,1],[1,4],[1,5]

	punpckhdq	mm0, mm4			;wsptr[1,6],[1,7],[1,2],[1,3]
	movq		mm1, mm6
	
//Save tmp2 and tmp3 in wsptr
	paddw		mm6, mm0		;wsptr[xxx],[1,z11],[xxx],[1,z13]
	movq		mm4, mm2
	
//Continue with z10 --- z13
	movq		[esi+8*2], mm5		;save tmp2
	punpcklwd	mm2, mm6		;wsptr[xxx],[xxx],[0,z11],[1,z11]

	psubw		mm1, mm0		;wsptr[xxx],[1,z12],[xxx],[1,z10]
	punpckhwd	mm4, mm6		;wsptr[xxx],[xxx],[0,z13],[1,z13]

	movq		mm0, mm3
	punpcklwd	mm3, mm1		;wsptr[xxx],[xxx],[0,z12],[1,z12]

	movq		[esi+8*3], mm7		;save tmp3
	punpckhwd	mm0, mm1		;wsptr[xxx],[xxx],[0,z10],[1,z10]

	movq		mm6, [esi+8*4]		;wsptr[2,0],[2,1],[2,2],[2,3]
	punpckhdq	mm0, mm2		;wsptr[0,z10],[1,z10],[0,z11],[1,z11]

	movq		mm7, [esi+8*5]		;wsptr[2,4],[2,5],[2,6],[2,7]
	punpckhdq	mm3, mm4		;wsptr[0,z12],[1,z12],[0,z13],[1,z13]

	movq		mm1, [esi+8*6]		;wsptr[3,0],[3,1],[3,2],[3,3]
	movq		mm4, mm6

	punpckldq	mm6, mm7			;wsptr[2,0],[2,1],[2,4],[2,5]
	movq		mm5, mm1

	punpckhdq	mm7, mm4			;wsptr[2,6],[2,7],[2,2],[2,3]
	movq		mm2, mm6
	
	movq		mm4, [esi+8*7]		;wsptr[3,4],[3,5],[3,6],[3,7]
	paddw		mm6, mm7		;wsptr[xxx],[2,z11],[xxx],[2,z13]

	psubw		mm2, mm7		;wsptr[xxx],[2,z12],[xxx],[2,z10]
	punpckldq	mm1, mm4			;wsptr[3,0],[3,1],[3,4],[3,5]

	punpckhdq	mm4, mm5			;wsptr[3,6],[3,7],[3,2],[3,3]
	movq		mm7, mm1

	paddw		mm1, mm4		;wsptr[xxx],[3,z11],[xxx],[3,z13]
	psubw		mm7, mm4		;wsptr[xxx],[3,z12],[xxx],[3,z10]

	movq		mm5, mm6
	punpcklwd	mm6, mm1		;wsptr[xxx],[xxx],[2,z11],[3,z11]

	punpckhwd	mm5, mm1		;wsptr[xxx],[xxx],[2,z13],[3,z13]
	movq		mm4, mm2

	punpcklwd	mm2, mm7		;wsptr[xxx],[xxx],[2,z12],[3,z12]

	punpckhwd	mm4, mm7		;wsptr[xxx],[xxx],[2,z10],[3,z10]

	punpckhdq	mm4, mm6		;wsptr[2,z10],[3,z10],[2,z11],[3,z11]

	punpckhdq	mm2, mm5		;wsptr[2,z12],[3,z12],[2,z13],[3,z13]
	movq		mm5, mm0

	punpckldq	mm0, mm4		;wsptr[0,z10],[1,z10],[2,z10],[3,z10]

	punpckhdq	mm5, mm4		;wsptr[0,z11],[1,z11],[2,z11],[3,z11]
	movq		mm4, mm3

	punpckhdq	mm4, mm2		;wsptr[0,z13],[1,z13],[2,z13],[3,z13]
	movq		mm1, mm5

	punpckldq	mm3, mm2		;wsptr[0,z12],[1,z12],[2,z12],[3,z12]
//    tmp7 = z11 + z13;		/* phase 5 */
//    tmp8 = z11 - z13;		/* phase 5 */
	psubw		mm1, mm4		;tmp8

	paddw		mm5, mm4		;tmp7
//    tmp21 = MULTIPLY(tmp8, FIX_1_414213562); /* 2*c4 */
	psllw		mm1, 2

	psllw		mm0, 2

	pmulhw		mm1, fix_141	;tmp21
//    tmp20 = MULTIPLY(z12, (FIX_1_082392200- FIX_1_847759065))  /* 2*(c2-c6) */
//			+ MULTIPLY(z10, - FIX_1_847759065); /* 2*c2 */
	psllw		mm3, 2
	movq		mm7, mm0

	pmulhw		mm7, fix_n184
	movq		mm6, mm3

	movq		mm2, [esi+8*0]	;tmp0,final1

	pmulhw		mm6, fix_108n184
//	 tmp22 = MULTIPLY(z10,(FIX_1_847759065 - FIX_2_613125930)) /* -2*(c2+c6) */
//			+ MULTIPLY(z12, FIX_1_847759065); /* 2*c2 */
	movq		mm4, mm2		;final1
  
	pmulhw		mm0, fix_184n261
	paddw		mm2, mm5		;tmp0+tmp7,final1

	pmulhw		mm3, fix_184
	psubw		mm4, mm5		;tmp0-tmp7,final1

//    tmp6 = tmp22 - tmp7;	/* phase 2 */
	psraw		mm2, 5			;outptr[0,0],[1,0],[2,0],[3,0],final1

	paddsw		mm2, const_0x0080	;final1
	paddw		mm7, mm6			;tmp20
	psraw		mm4, 5			;outptr[0,7],[1,7],[2,7],[3,7],final1

	paddsw		mm4, const_0x0080	;final1
	paddw		mm3, mm0			;tmp22

//    tmp5 = tmp21 - tmp6;
	psubw		mm3, mm5		;tmp6

//    tmp4 = tmp20 + tmp5;
	movq		mm0, [esi+8*1]		;tmp1,final2
	psubw		mm1, mm3		;tmp5

	movq		mm6, mm0			;final2
	paddw		mm0, mm3		;tmp1+tmp6,final2

    /* Final output stage: scale down by a factor of 8 and range-limit */


//    outptr[0] = range_limit[IDESCALE(tmp0 + tmp7, PASS1_BITS+3)
//			    & RANGE_MASK];
//    outptr[7] = range_limit[IDESCALE(tmp0 - tmp7, PASS1_BITS+3)
//			    & RANGE_MASK];	final1


//    outptr[1] = range_limit[IDESCALE(tmp1 + tmp6, PASS1_BITS+3)
//			    & RANGE_MASK];
//    outptr[6] = range_limit[IDESCALE(tmp1 - tmp6, PASS1_BITS+3)
//			    & RANGE_MASK];	final2
	psubw		mm6, mm3		;tmp1-tmp6,final2
	psraw		mm0, 5			;outptr[0,1],[1,1],[2,1],[3,1]

	paddsw		mm0, const_0x0080
	psraw		mm6, 5			;outptr[0,6],[1,6],[2,6],[3,6]
	
	paddsw		mm6, const_0x0080		;need to check this value
	packuswb	mm0, mm4	;out[0,1],[1,1],[2,1],[3,1],[0,7],[1,7],[2,7],[3,7]
	
	movq		mm5, [esi+8*2]		;tmp2,final3
	packuswb	mm2, mm6	;out[0,0],[1,0],[2,0],[3,0],[0,6],[1,6],[2,6],[3,6]

//    outptr[2] = range_limit[IDESCALE(tmp2 + tmp5, PASS1_BITS+3)
//			    & RANGE_MASK];
//    outptr[5] = range_limit[IDESCALE(tmp2 - tmp5, PASS1_BITS+3)
//			    & RANGE_MASK];	final3
	paddw		mm7, mm1		;tmp4
	movq		mm3, mm5

	paddw		mm5, mm1		;tmp2+tmp5
	psubw		mm3, mm1		;tmp2-tmp5

	psraw		mm5, 5			;outptr[0,2],[1,2],[2,2],[3,2]

	paddsw		mm5, const_0x0080
	movq		mm4, [esi+8*3]		;tmp3,final4
	psraw		mm3, 5			;outptr[0,5],[1,5],[2,5],[3,5]

	paddsw		mm3, const_0x0080


//    outptr[4] = range_limit[IDESCALE(tmp3 + tmp4, PASS1_BITS+3)
//			    & RANGE_MASK];
//    outptr[3] = range_limit[IDESCALE(tmp3 - tmp4, PASS1_BITS+3)
//			    & RANGE_MASK];	final4
	movq		mm6, mm4
	paddw		mm4, mm7		;tmp3+tmp4

	psubw		mm6, mm7		;tmp3-tmp4
	psraw		mm4, 5			;outptr[0,4],[1,4],[2,4],[3,4]
	mov			ecx, [eax]

	paddsw		mm4, const_0x0080
	psraw		mm6, 5			;outptr[0,3],[1,3],[2,3],[3,3]

	paddsw		mm6, const_0x0080
	packuswb	mm5, mm4	;out[0,2],[1,2],[2,2],[3,2],[0,4],[1,4],[2,4],[3,4]

	packuswb	mm6, mm3	;out[0,3],[1,3],[2,3],[3,3],[0,5],[1,5],[2,5],[3,5]
	movq		mm4, mm2

	movq		mm7, mm5
	punpcklbw	mm2, mm0	;out[0,0],[0,1],[1,0],[1,1],[2,0],[2,1],[3,0],[3,1]

	punpckhbw	mm4, mm0	;out[0,6],[0,7],[1,6],[1,7],[2,6],[2,7],[3,6],[3,7]
	movq		mm1, mm2

	punpcklbw	mm5, mm6	;out[0,2],[0,3],[1,2],[1,3],[2,2],[2,3],[3,2],[3,3]
	add		 	eax, 4

	punpckhbw	mm7, mm6	;out[0,4],[0,5],[1,4],[1,5],[2,4],[2,5],[3,4],[3,5]

	punpcklwd	mm2, mm5	;out[0,0],[0,1],[0,2],[0,3],[1,0],[1,1],[1,2],[1,3]
	add			ecx, output_col

	movq		mm6, mm7
	punpckhwd	mm1, mm5	;out[2,0],[2,1],[2,2],[2,3],[3,0],[3,1],[3,2],[3,3]

	movq		mm0, mm2
	punpcklwd	mm6, mm4	;out[0,4],[0,5],[0,6],[0,7],[1,4],[1,5],[1,6],[1,7]

	mov			ebx, [eax]
	punpckldq	mm2, mm6	;out[0,0],[0,1],[0,2],[0,3],[0,4],[0,5],[0,6],[0,7]

	add		 	eax, 4
	movq		mm3, mm1

	add			ebx, output_col 
	punpckhwd	mm7, mm4	;out[2,4],[2,5],[2,6],[2,7],[3,4],[3,5],[3,6],[3,7]
	
	movq		[ecx], mm2
	punpckhdq	mm0, mm6	;out[1,0],[1,1],[1,2],[1,3],[1,4],[1,5],[1,6],[1,7]

	mov			ecx, [eax]
	add		 	eax, 4
	add			ecx, output_col

	movq		[ebx], mm0
	punpckldq	mm1, mm7	;out[2,0],[2,1],[2,2],[2,3],[2,4],[2,5],[2,6],[2,7]

	mov			ebx, [eax]

	add			ebx, output_col
	punpckhdq	mm3, mm7	;out[3,0],[3,1],[3,2],[3,3],[3,4],[3,5],[3,6],[3,7]
	movq		[ecx], mm1


	movq		[ebx], mm3


		
/*******************************************************************/
	

	add			esi, 64
	add			eax, 4

/*******************************************************************/

//    tmp10 = ((DCTELEM) wsptr[0] + (DCTELEM) wsptr[4]);
//    tmp13 = ((DCTELEM) wsptr[2] + (DCTELEM) wsptr[6]);
//    tmp11 = ((DCTELEM) wsptr[0] - (DCTELEM) wsptr[4]);
//    tmp14 = ((DCTELEM) wsptr[2] - (DCTELEM) wsptr[6]);
	movq		mm0, [esi+8*0]		;wsptr[0,0],[0,1],[0,2],[0,3]

	movq		mm1, [esi+8*1]		;wsptr[0,4],[0,5],[0,6],[0,7]
	movq		mm2, mm0
	
	movq		mm3, [esi+8*2]		;wsptr[1,0],[1,1],[1,2],[1,3]
	paddw		mm0, mm1			;wsptr[0,tmp10],[xxx],[0,tmp13],[xxx]

	movq		mm4, [esi+8*3]		;wsptr[1,4],[1,5],[1,6],[1,7]
	psubw		mm2, mm1			;wsptr[0,tmp11],[xxx],[0,tmp14],[xxx]

	movq		mm6, mm0
	movq		mm5, mm3
	
	paddw		mm3, mm4			;wsptr[1,tmp10],[xxx],[1,tmp13],[xxx]
	movq		mm1, mm2

	psubw		mm5, mm4			;wsptr[1,tmp11],[xxx],[1,tmp14],[xxx]
	punpcklwd	mm0, mm3			;wsptr[0,tmp10],[1,tmp10],[xxx],[xxx]

	movq		mm7, [esi+8*7]		;wsptr[3,4],[3,5],[3,6],[3,7]
	punpckhwd	mm6, mm3			;wsptr[0,tmp13],[1,tmp13],[xxx],[xxx]

	movq		mm3, [esi+8*4]		;wsptr[2,0],[2,1],[2,2],[2,3]
	punpckldq	mm0, mm6	;wsptr[0,tmp10],[1,tmp10],[0,tmp13],[1,tmp13]

	punpcklwd	mm1, mm5			;wsptr[0,tmp11],[1,tmp11],[xxx],[xxx]
	movq		mm4, mm3

	movq		mm6, [esi+8*6]		;wsptr[3,0],[3,1],[3,2],[3,3]
	punpckhwd	mm2, mm5			;wsptr[0,tmp14],[1,tmp14],[xxx],[xxx]

	movq		mm5, [esi+8*5]		;wsptr[2,4],[2,5],[2,6],[2,7]
	punpckldq	mm1, mm2	;wsptr[0,tmp11],[1,tmp11],[0,tmp14],[1,tmp14]

	
	paddw		mm3, mm5			;wsptr[2,tmp10],[xxx],[2,tmp13],[xxx]
	movq		mm2, mm6

	psubw		mm4, mm5			;wsptr[2,tmp11],[xxx],[2,tmp14],[xxx]
	paddw		mm6, mm7			;wsptr[3,tmp10],[xxx],[3,tmp13],[xxx]

	movq		mm5, mm3
	punpcklwd	mm3, mm6			;wsptr[2,tmp10],[3,tmp10],[xxx],[xxx]
	
	psubw		mm2, mm7			;wsptr[3,tmp11],[xxx],[3,tmp14],[xxx]
	punpckhwd	mm5, mm6			;wsptr[2,tmp13],[3,tmp13],[xxx],[xxx]

	movq		mm7, mm4
	punpckldq	mm3, mm5	;wsptr[2,tmp10],[3,tmp10],[2,tmp13],[3,tmp13]

	punpcklwd	mm4, mm2			;wsptr[2,tmp11],[3,tmp11],[xxx],[xxx]

	punpckhwd	mm7, mm2			;wsptr[2,tmp14],[3,tmp14],[xxx],[xxx]

	punpckldq	mm4, mm7	;wsptr[2,tmp11],[3,tmp11],[2,tmp14],[3,tmp14]
	movq		mm6, mm1

//	mm0 = 	;wsptr[0,tmp10],[1,tmp10],[0,tmp13],[1,tmp13]
//	mm1 =	;wsptr[0,tmp11],[1,tmp11],[0,tmp14],[1,tmp14]


	movq		mm2, mm0
	punpckhdq	mm6, mm4	;wsptr[0,tmp14],[1,tmp14],[2,tmp14],[3,tmp14]

	punpckldq	mm1, mm4	;wsptr[0,tmp11],[1,tmp11],[2,tmp11],[3,tmp11]
	psllw		mm6, 2

	pmulhw		mm6, fix_141
	punpckldq	mm0, mm3	;wsptr[0,tmp10],[1,tmp10],[2,tmp10],[3,tmp10]

	punpckhdq	mm2, mm3	;wsptr[0,tmp13],[1,tmp13],[2,tmp13],[3,tmp13]
	movq		mm7, mm0

//    tmp0 = tmp10 + tmp13;
//    tmp3 = tmp10 - tmp13;
	paddw		mm0, mm2	;[0,tmp0],[1,tmp0],[2,tmp0],[3,tmp0]
	psubw		mm7, mm2	;[0,tmp3],[1,tmp3],[2,tmp3],[3,tmp3]

//    tmp12 = MULTIPLY(tmp14, FIX_1_414213562) - tmp13;
	psubw		mm6, mm2	;wsptr[0,tmp12],[1,tmp12],[2,tmp12],[3,tmp12]
//    tmp1 = tmp11 + tmp12;
//    tmp2 = tmp11 - tmp12;
	movq		mm5, mm1



    /* Odd part */

//    z13 = (DCTELEM) wsptr[5] + (DCTELEM) wsptr[3];
//    z10 = (DCTELEM) wsptr[5] - (DCTELEM) wsptr[3];
//    z11 = (DCTELEM) wsptr[1] + (DCTELEM) wsptr[7];
//    z12 = (DCTELEM) wsptr[1] - (DCTELEM) wsptr[7];
	movq		mm3, [esi+8*0]		;wsptr[0,0],[0,1],[0,2],[0,3]
	paddw		mm1, mm6	;[0,tmp1],[1,tmp1],[2,tmp1],[3,tmp1]

	movq		mm4, [esi+8*1]		;wsptr[0,4],[0,5],[0,6],[0,7]
	psubw		mm5, mm6	;[0,tmp2],[1,tmp2],[2,tmp2],[3,tmp2]

	movq		mm6, mm3
	punpckldq	mm3, mm4			;wsptr[0,0],[0,1],[0,4],[0,5]

	punpckhdq	mm4, mm6			;wsptr[0,6],[0,7],[0,2],[0,3]
	movq		mm2, mm3

//Save tmp0 and tmp1 in wsptr
	movq		[esi+8*0], mm0		;save tmp0
	paddw		mm2, mm4			;wsptr[xxx],[0,z11],[xxx],[0,z13]

	
//Continue with z10 --- z13
	movq		mm6, [esi+8*2]		;wsptr[1,0],[1,1],[1,2],[1,3]
	psubw		mm3, mm4			;wsptr[xxx],[0,z12],[xxx],[0,z10]

	movq		mm0, [esi+8*3]		;wsptr[1,4],[1,5],[1,6],[1,7]
	movq		mm4, mm6

	movq		[esi+8*1], mm1		;save tmp1
	punpckldq	mm6, mm0			;wsptr[1,0],[1,1],[1,4],[1,5]

	punpckhdq	mm0, mm4			;wsptr[1,6],[1,7],[1,2],[1,3]
	movq		mm1, mm6
	
//Save tmp2 and tmp3 in wsptr
	paddw		mm6, mm0		;wsptr[xxx],[1,z11],[xxx],[1,z13]
	movq		mm4, mm2
	
//Continue with z10 --- z13
	movq		[esi+8*2], mm5		;save tmp2
	punpcklwd	mm2, mm6		;wsptr[xxx],[xxx],[0,z11],[1,z11]

	psubw		mm1, mm0		;wsptr[xxx],[1,z12],[xxx],[1,z10]
	punpckhwd	mm4, mm6		;wsptr[xxx],[xxx],[0,z13],[1,z13]

	movq		mm0, mm3
	punpcklwd	mm3, mm1		;wsptr[xxx],[xxx],[0,z12],[1,z12]

	movq		[esi+8*3], mm7		;save tmp3
	punpckhwd	mm0, mm1		;wsptr[xxx],[xxx],[0,z10],[1,z10]

	movq		mm6, [esi+8*4]		;wsptr[2,0],[2,1],[2,2],[2,3]
	punpckhdq	mm0, mm2		;wsptr[0,z10],[1,z10],[0,z11],[1,z11]

	movq		mm7, [esi+8*5]		;wsptr[2,4],[2,5],[2,6],[2,7]
	punpckhdq	mm3, mm4		;wsptr[0,z12],[1,z12],[0,z13],[1,z13]

	movq		mm1, [esi+8*6]		;wsptr[3,0],[3,1],[3,2],[3,3]
	movq		mm4, mm6

	punpckldq	mm6, mm7			;wsptr[2,0],[2,1],[2,4],[2,5]
	movq		mm5, mm1

	punpckhdq	mm7, mm4			;wsptr[2,6],[2,7],[2,2],[2,3]
	movq		mm2, mm6
	
	movq		mm4, [esi+8*7]		;wsptr[3,4],[3,5],[3,6],[3,7]
	paddw		mm6, mm7		;wsptr[xxx],[2,z11],[xxx],[2,z13]

	psubw		mm2, mm7		;wsptr[xxx],[2,z12],[xxx],[2,z10]
	punpckldq	mm1, mm4			;wsptr[3,0],[3,1],[3,4],[3,5]

	punpckhdq	mm4, mm5			;wsptr[3,6],[3,7],[3,2],[3,3]
	movq		mm7, mm1

	paddw		mm1, mm4		;wsptr[xxx],[3,z11],[xxx],[3,z13]
	psubw		mm7, mm4		;wsptr[xxx],[3,z12],[xxx],[3,z10]

	movq		mm5, mm6
	punpcklwd	mm6, mm1		;wsptr[xxx],[xxx],[2,z11],[3,z11]

	punpckhwd	mm5, mm1		;wsptr[xxx],[xxx],[2,z13],[3,z13]
	movq		mm4, mm2

	punpcklwd	mm2, mm7		;wsptr[xxx],[xxx],[2,z12],[3,z12]

	punpckhwd	mm4, mm7		;wsptr[xxx],[xxx],[2,z10],[3,z10]

	punpckhdq	mm4, mm6		;wsptr[2,z10],[3,z10],[2,z11],[3,z11]

	punpckhdq	mm2, mm5		;wsptr[2,z12],[3,z12],[2,z13],[3,z13]
	movq		mm5, mm0

	punpckldq	mm0, mm4		;wsptr[0,z10],[1,z10],[2,z10],[3,z10]

	punpckhdq	mm5, mm4		;wsptr[0,z11],[1,z11],[2,z11],[3,z11]
	movq		mm4, mm3

	punpckhdq	mm4, mm2		;wsptr[0,z13],[1,z13],[2,z13],[3,z13]
	movq		mm1, mm5

	punpckldq	mm3, mm2		;wsptr[0,z12],[1,z12],[2,z12],[3,z12]
//    tmp7 = z11 + z13;		/* phase 5 */
//    tmp8 = z11 - z13;		/* phase 5 */
	psubw		mm1, mm4		;tmp8

	paddw		mm5, mm4		;tmp7
//    tmp21 = MULTIPLY(tmp8, FIX_1_414213562); /* 2*c4 */
	psllw		mm1, 2

	psllw		mm0, 2

	pmulhw		mm1, fix_141	;tmp21
//    tmp20 = MULTIPLY(z12, (FIX_1_082392200- FIX_1_847759065))  /* 2*(c2-c6) */
//			+ MULTIPLY(z10, - FIX_1_847759065); /* 2*c2 */
	psllw		mm3, 2
	movq		mm7, mm0

	pmulhw		mm7, fix_n184
	movq		mm6, mm3

	movq		mm2, [esi+8*0]	;tmp0,final1

	pmulhw		mm6, fix_108n184
//	 tmp22 = MULTIPLY(z10,(FIX_1_847759065 - FIX_2_613125930)) /* -2*(c2+c6) */
//			+ MULTIPLY(z12, FIX_1_847759065); /* 2*c2 */
	movq		mm4, mm2		;final1
  
	pmulhw		mm0, fix_184n261
	paddw		mm2, mm5		;tmp0+tmp7,final1

	pmulhw		mm3, fix_184
	psubw		mm4, mm5		;tmp0-tmp7,final1

//    tmp6 = tmp22 - tmp7;	/* phase 2 */
	psraw		mm2, 5			;outptr[0,0],[1,0],[2,0],[3,0],final1

	paddsw		mm2, const_0x0080	;final1
	paddw		mm7, mm6			;tmp20
	psraw		mm4, 5			;outptr[0,7],[1,7],[2,7],[3,7],final1

	paddsw		mm4, const_0x0080	;final1
	paddw		mm3, mm0			;tmp22

//    tmp5 = tmp21 - tmp6;
	psubw		mm3, mm5		;tmp6

//    tmp4 = tmp20 + tmp5;
	movq		mm0, [esi+8*1]		;tmp1,final2
	psubw		mm1, mm3		;tmp5

	movq		mm6, mm0			;final2
	paddw		mm0, mm3		;tmp1+tmp6,final2

    /* Final output stage: scale down by a factor of 8 and range-limit */


//    outptr[0] = range_limit[IDESCALE(tmp0 + tmp7, PASS1_BITS+3)
//			    & RANGE_MASK];
//    outptr[7] = range_limit[IDESCALE(tmp0 - tmp7, PASS1_BITS+3)
//			    & RANGE_MASK];	final1


//    outptr[1] = range_limit[IDESCALE(tmp1 + tmp6, PASS1_BITS+3)
//			    & RANGE_MASK];
//    outptr[6] = range_limit[IDESCALE(tmp1 - tmp6, PASS1_BITS+3)
//			    & RANGE_MASK];	final2
	psubw		mm6, mm3		;tmp1-tmp6,final2
	psraw		mm0, 5			;outptr[0,1],[1,1],[2,1],[3,1]

	paddsw		mm0, const_0x0080
	psraw		mm6, 5			;outptr[0,6],[1,6],[2,6],[3,6]
	
	paddsw		mm6, const_0x0080		;need to check this value
	packuswb	mm0, mm4	;out[0,1],[1,1],[2,1],[3,1],[0,7],[1,7],[2,7],[3,7]
	
	movq		mm5, [esi+8*2]		;tmp2,final3
	packuswb	mm2, mm6	;out[0,0],[1,0],[2,0],[3,0],[0,6],[1,6],[2,6],[3,6]

//    outptr[2] = range_limit[IDESCALE(tmp2 + tmp5, PASS1_BITS+3)
//			    & RANGE_MASK];
//    outptr[5] = range_limit[IDESCALE(tmp2 - tmp5, PASS1_BITS+3)
//			    & RANGE_MASK];	final3
	paddw		mm7, mm1		;tmp4
	movq		mm3, mm5

	paddw		mm5, mm1		;tmp2+tmp5
	psubw		mm3, mm1		;tmp2-tmp5

	psraw		mm5, 5			;outptr[0,2],[1,2],[2,2],[3,2]

	paddsw		mm5, const_0x0080
	movq		mm4, [esi+8*3]		;tmp3,final4
	psraw		mm3, 5			;outptr[0,5],[1,5],[2,5],[3,5]

	paddsw		mm3, const_0x0080


//    outptr[4] = range_limit[IDESCALE(tmp3 + tmp4, PASS1_BITS+3)
//			    & RANGE_MASK];
//    outptr[3] = range_limit[IDESCALE(tmp3 - tmp4, PASS1_BITS+3)
//			    & RANGE_MASK];	final4
	movq		mm6, mm4
	paddw		mm4, mm7		;tmp3+tmp4

	psubw		mm6, mm7		;tmp3-tmp4
	psraw		mm4, 5			;outptr[0,4],[1,4],[2,4],[3,4]
	mov			ecx, [eax]

	paddsw		mm4, const_0x0080
	psraw		mm6, 5			;outptr[0,3],[1,3],[2,3],[3,3]

	paddsw		mm6, const_0x0080
	packuswb	mm5, mm4	;out[0,2],[1,2],[2,2],[3,2],[0,4],[1,4],[2,4],[3,4]

	packuswb	mm6, mm3	;out[0,3],[1,3],[2,3],[3,3],[0,5],[1,5],[2,5],[3,5]
	movq		mm4, mm2

	movq		mm7, mm5
	punpcklbw	mm2, mm0	;out[0,0],[0,1],[1,0],[1,1],[2,0],[2,1],[3,0],[3,1]

	punpckhbw	mm4, mm0	;out[0,6],[0,7],[1,6],[1,7],[2,6],[2,7],[3,6],[3,7]
	movq		mm1, mm2

	punpcklbw	mm5, mm6	;out[0,2],[0,3],[1,2],[1,3],[2,2],[2,3],[3,2],[3,3]
	add		 	eax, 4

	punpckhbw	mm7, mm6	;out[0,4],[0,5],[1,4],[1,5],[2,4],[2,5],[3,4],[3,5]

	punpcklwd	mm2, mm5	;out[0,0],[0,1],[0,2],[0,3],[1,0],[1,1],[1,2],[1,3]
	add			ecx, output_col

	movq		mm6, mm7
	punpckhwd	mm1, mm5	;out[2,0],[2,1],[2,2],[2,3],[3,0],[3,1],[3,2],[3,3]

	movq		mm0, mm2
	punpcklwd	mm6, mm4	;out[0,4],[0,5],[0,6],[0,7],[1,4],[1,5],[1,6],[1,7]

	mov			ebx, [eax]
	punpckldq	mm2, mm6	;out[0,0],[0,1],[0,2],[0,3],[0,4],[0,5],[0,6],[0,7]

	add		 	eax, 4
	movq		mm3, mm1

	add			ebx, output_col 
	punpckhwd	mm7, mm4	;out[2,4],[2,5],[2,6],[2,7],[3,4],[3,5],[3,6],[3,7]
	
	movq		[ecx], mm2
	punpckhdq	mm0, mm6	;out[1,0],[1,1],[1,2],[1,3],[1,4],[1,5],[1,6],[1,7]

	mov			ecx, [eax]
	add		 	eax, 4
	add			ecx, output_col

	movq		[ebx], mm0
	punpckldq	mm1, mm7	;out[2,0],[2,1],[2,2],[2,3],[2,4],[2,5],[2,6],[2,7]

	mov			ebx, [eax]

	add			ebx, output_col
	punpckhdq	mm3, mm7	;out[3,0],[3,1],[3,2],[3,3],[3,4],[3,5],[3,6],[3,7]
	movq		[ecx], mm1

	movq		[ebx], mm3

	emms
	}
}
#endif

#endif /* DCT_IFAST_SUPPORTED */