tmap.s 42.2 KB
Newer Older
Alam Ed Arias committed
1 2 3
// SONIC ROBO BLAST 2
//-----------------------------------------------------------------------------
// Copyright (C) 1998-2000 by DooM Legacy Team.
James R. committed
4
// Copyright (C) 1999-2020 by Sonic Team Junior.
Alam Ed Arias committed
5 6 7 8 9 10 11 12 13 14 15
//
// This program is free software distributed under the
// terms of the GNU General Public License, version 2.
// See the 'LICENSE' file for more details.
//-----------------------------------------------------------------------------
/// \file  tmap.s
/// \brief optimised drawing routines for span/column rendering

// structures, must match the C structures!
#include "asm_defs.inc"

16
// Rappel: seuls EAX, ECX, EDX peuvent �tre �cras�s librement.
Alam Ed Arias committed
17 18 19 20 21 22 23 24 25 26 27 28 29 30
//         il faut sauver esi,edi, cd...gs

/* Attention aux comparaisons!                                              */
/*                                                                          */
/*      Intel_compare:                                                      */
/*                                                                          */
/*              cmp     A,B                     // A-B , set flags          */
/*              jg      A_greater_than_B                                    */
/*                                                                          */
/*      AT&T_compare:                                                       */
/*                                                                          */
/*              cmp     A,B                     // B-A , set flags          */
/*              jg      B_greater_than_A                                    */
/*                                                                          */
31
/*        (soustrait l'op�rande source DE l'op�rande destination,           */
Alam Ed Arias committed
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
/*         comme sur Motorola! )                                            */

// RAPPEL: Intel
//         SECTION:[BASE+INDEX*SCALE+DISP]
// devient SECTION:DISP(BASE,INDEX,SCALE)

//----------------------------------------------------------------------
//
// R_DrawColumn
//
//   New optimised version 10-01-1998 by D.Fabrice and P.Boris
//   TO DO: optimise it much farther... should take at most 3 cycles/pix
//          once it's fixed, add code to patch the offsets so that it
//          works in every screen width.
//
//----------------------------------------------------------------------

    .data
#ifdef LINUX
    .align 2
#else
    .align 4
#endif
C(loopcount):   .long   0
C(pixelcount):  .long   0
C(tystep):      .long   0

C(vidwidth):    .long   0       //use this one out of the inner loops
                                //so you don't need to patch everywhere...

#ifdef USEASM
Monster Iestyn committed
63
#if !defined( LINUX)
Alam Ed Arias committed
64 65 66 67 68
    .text
#endif
.globl C(ASM_PatchRowBytes)
C(ASM_PatchRowBytes):
    pushl   %ebp
69
    movl    %esp, %ebp      // assure l'"adressabilit� du stack"
Alam Ed Arias committed
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

    movl    ARG1, %edx         // read first arg
    movl    %edx, C(vidwidth)

    // 1 * vidwidth
    movl    %edx,p1+2
    movl    %edx,w1+2   //water
    movl    %edx,p1b+2  //sky

    movl    %edx,p5+2
      movl    %edx,sh5+2        //smokie test

    // 2 * vidwidth
    addl    ARG1,%edx

    movl    %edx,p2+2
    movl    %edx,w2+2   //water
    movl    %edx,p2b+2  //sky

    movl    %edx,p6+2
    movl    %edx,p7+2
    movl    %edx,p8+2
    movl    %edx,p9+2
      movl    %edx,sh6+2         //smokie test
      movl    %edx,sh7+2
      movl    %edx,sh8+2
      movl    %edx,sh9+2

    // 3 * vidwidth
    addl    ARG1,%edx

    movl    %edx,p3+2
    movl    %edx,w3+2   //water
    movl    %edx,p3b+2  //sky

    // 4 * vidwidth
    addl    ARG1,%edx

    movl    %edx,p4+2
    movl    %edx,w4+2   //water
    movl    %edx,p4b+2  //sky

    popl    %ebp
    ret


#ifdef LINUX
    .align 2
#else
    .align 5
#endif
.globl C(R_DrawColumn_8)
C(R_DrawColumn_8):
    pushl   %ebp                // preserve caller's stack frame pointer
    pushl   %esi                // preserve register variables
    pushl   %edi
    pushl   %ebx

//
// dest = ylookup[dc_yl] + columnofs[dc_x];
//
    movl     C(dc_yl),%ebp
    movl     %ebp,%ebx
    movl     C(ylookup)(,%ebx,4),%edi
    movl     C(dc_x),%ebx
    addl     C(columnofs)(,%ebx,4),%edi  // edi = dest

//
// pixelcount = yh - yl + 1
//
    movl     C(dc_yh),%eax
    incl     %eax
    subl     %ebp,%eax                   // pixel count
    movl     %eax,C(pixelcount)          // save for final pixel
    jle      vdone                       // nothing to scale

//
// frac = dc_texturemid - (centery-dc_yl)*fracstep;
//
    movl     C(dc_iscale),%ecx           // fracstep
    movl     C(centery),%eax
    subl     %ebp,%eax
    imul     %ecx,%eax
    movl     C(dc_texturemid),%edx
    subl     %eax,%edx
     movl     %edx,%ebx
     shrl     $16,%ebx          // frac int.
     andl     $0x0000007f,%ebx
     shll     $16,%edx          // y frac up

     movl     %ecx,%ebp
     shll     $16,%ebp          // fracstep f. up
     shrl     $16,%ecx          // fracstep i. ->cl
     andb     $0x7f,%cl

    movl     C(dc_source),%esi

//
// lets rock :) !
//
    movl    C(pixelcount),%eax
    movb    %al,%dh
    shrl    $2,%eax
    movb    %al,%ch             // quad count
    movl    C(dc_colormap),%eax
    testb   $3,%dh
    jz      v4quadloop

//
//  do un-even pixel
//
    testb   $1,%dh
    jz      2f

    movb    (%esi,%ebx),%al     // prep un-even loops
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
    andb    $0x7f,%bl            // mask 0-127 texture index
     movb    %dl,(%edi)           // output pixel
    addl    C(vidwidth),%edi

//
//  do two non-quad-aligned pixels
//
2:
    testb   $2,%dh
    jz      3f

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
    andb    $0x7f,%bl            // mask 0-127 texture index
     movb    %dl,(%edi)           // output pixel

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
    andb    $0x7f,%bl            // mask 0-127 texture index
    addl    C(vidwidth),%edi
     movb    %dl,(%edi)           // output pixel

    addl    C(vidwidth),%edi

//
//  test if there was at least 4 pixels
//
3:
    testb   $0xFF,%ch           // test quad count
    jz      vdone

//
// ebp : ystep frac. upper 24 bits
// edx : y     frac. upper 24 bits
// ebx : y     i.    lower 7 bits,  masked for index
// ecx : ch = counter, cl = y step i.
// eax : colormap aligned 256
// esi : source texture column
// edi : dest screen
//
v4quadloop:
    movb    $0x7f,%dh           // prep mask
//    .align  4
vquadloop:
    movb    (%esi,%ebx),%al     // prep loop
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
    movb    %dl,(%edi)           // output pixel
     andb    $0x7f,%bl            // mask 0-127 texture index

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%eax),%dl
p1:    movb    %dl,0x12345678(%edi)
     andb    $0x7f,%bl

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%eax),%dl
p2:    movb    %dl,2*0x12345678(%edi)
     andb    $0x7f,%bl

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%eax),%dl
p3:    movb    %dl,3*0x12345678(%edi)
     andb    $0x7f,%bl

p4:    addl    $4*0x12345678,%edi

    decb   %ch
     jnz    vquadloop

vdone:
    popl    %ebx                // restore register variables
    popl    %edi
    popl    %esi
    popl    %ebp                // restore caller's stack frame pointer
    ret

#ifdef HORIZONTALDRAW
// --------------------------------------------------------------------------
// Horizontal Column Drawer Optimisation
// --------------------------------------------------------------------------

#ifdef LINUX
    .align 2
#else
    .align 5
#endif
.globl C(R_DrawHColumn_8)
C(R_DrawHColumn_8):
    pushl   %ebp
    pushl   %esi
    pushl   %edi
    pushl   %ebx

//
// dest = yhlookup[dc_x] + hcolumnofs[dc_yl];
//
    movl    C(dc_x),%ebx
    movl    C(yhlookup)(,%ebx,4),%edi
    movl    C(dc_yl),%ebp
    movl    %ebp,%ebx
    addl    C(hcolumnofs)(,%ebx,4),%edi  // edi = dest

//
// pixelcount = yh - yl + 1
//
    movl     C(dc_yh),%eax
    incl     %eax
    subl     %ebp,%eax                   // pixel count
    movl     %eax,C(pixelcount)          // save for final pixel
    jle      vhdone                      // nothing to scale

//
// frac = dc_texturemid - (centery-dc_yl)*fracstep;
//
    movl     C(dc_iscale),%ecx           // fracstep
    movl     C(centery),%eax
    subl     %ebp,%eax
    imul     %ecx,%eax
    movl     C(dc_texturemid),%edx
    subl     %eax,%edx
     movl     %edx,%ebx
     shrl     $16,%ebx          // frac int.
     andl     $0x0000007f,%ebx
     shll     $16,%edx          // y frac up

     movl     %ecx,%ebp
     shll     $16,%ebp          // fracstep f. up
     shrl     $16,%ecx          // fracstep i. ->cl
     andb     $0x7f,%cl

    movl     C(dc_source),%esi

//
// lets rock :) !
//

    movl    C(pixelcount),%eax
    movb    %al,%dh
    shrl    $2,%eax
    movb    %al,%ch     // quad count

    testb   %ch, %ch
    jz      vhnearlydone

    movl    C(dc_colormap),%eax
    decl    %edi                  //-----

vhloop:
    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
     andb    $0x7f,%bl
    incl    %edi                 //-----
     movb    (%eax),%dh
    movb    %dh,(%edi)           //-----

     movb    (%esi,%ebx),%al      // fetch source texel
    addl    %ebp,%edx
     incl    %edi                //-----
    adcb    %cl,%bl
     movb    (%eax),%dl
    andb    $0x7f,%bl
     movb    %dl,(%edi)          //-----

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
//    shll    $16,%edx
     andb    $0x7f,%bl
    incl    %edi                //-----
     movb    (%eax),%dh
    movb    %dh,(%edi)          //-----

     movb    (%esi,%ebx),%al      // fetch source texel
    addl    %ebp,%edx
     incl    %edi               //-----
    adcb    %cl,%bl
     movb    (%eax),%dl
    andb    $0x7f,%bl
     movb    %dl,(%edi)
//     movl    %edx,(%edi)
//    addl    $4,%edi

    decb   %ch
     jnz    vhloop

vhnearlydone:
//    movl    C(pixelcount)

vhdone:
    popl    %ebx
    popl    %edi
    popl    %esi
    popl    %ebp
    ret


// --------------------------------------------------------------------------
// Rotate a buffer 90 degree in clockwise order after horiz.col. draws
// --------------------------------------------------------------------------

#ifdef LINUX
    .align 2
#else
    .align 5
#endif
.globl C(R_RotateBuffer)
C(R_RotateBuffer):
    pushl   %ebp
    pushl   %esi
    pushl   %edi
    pushl   %ebx


    movl    C(dc_source),%esi
    movl    C(dc_colormap),%edi


    movb    (%esi),%ah
     addl    $200,%esi
    movb    (%ebx),%al
     addl    $200,%ebx
    bswap    %eax
    movb    (%esi),%ah
     addl    $200,%esi
    movb    (%ebx),%al
     addl    $200,%ebx
    movl    %eax,(%edi)
     addl    $4,%edi


    popl    %ebx
    popl    %edi
    popl    %esi
    popl    %ebp
    ret
#endif

//----------------------------------------------------------------------
//13-02-98:
//   R_DrawSkyColumn : same as R_DrawColumn but:
//
//            - wrap around 256 instead of 127.
//   this is needed because we have a higher texture for mouselook,
//   we need at least 200 lines for the sky.
//
//   NOTE: the sky should never wrap, so it could use a faster method.
//         for the moment, we'll still use a wrapping method...
//
//  IT S JUST A QUICK CUT N PASTE, WAS NOT OPTIMISED AS IT SHOULD BE !!!
//
//----------------------------------------------------------------------

#ifdef LINUX
    .align 2
#else
    .align 5
#endif
.globl C(R_DrawSkyColumn_8)
C(R_DrawSkyColumn_8):
    pushl   %ebp
    pushl   %esi
    pushl   %edi
    pushl   %ebx

//
// dest = ylookup[dc_yl] + columnofs[dc_x];
//
    movl     C(dc_yl),%ebp
    movl     %ebp,%ebx
    movl     C(ylookup)(,%ebx,4),%edi
    movl     C(dc_x),%ebx
    addl     C(columnofs)(,%ebx,4),%edi  // edi = dest

//
// pixelcount = yh - yl + 1
//
    movl     C(dc_yh),%eax
    incl     %eax
    subl     %ebp,%eax                   // pixel count
    movl     %eax,C(pixelcount)          // save for final pixel
    jle      vskydone                       // nothing to scale

//
// frac = dc_texturemid - (centery-dc_yl)*fracstep;
//
    movl     C(dc_iscale),%ecx           // fracstep
    movl     C(centery),%eax
    subl     %ebp,%eax
    imul     %ecx,%eax
    movl     C(dc_texturemid),%edx
    subl     %eax,%edx
     movl     %edx,%ebx
     shrl     $16,%ebx          // frac int.
     andl     $0x000000ff,%ebx
     shll     $16,%edx          // y frac up

     movl     %ecx,%ebp
     shll     $16,%ebp          // fracstep f. up
     shrl     $16,%ecx          // fracstep i. ->cl

    movl     C(dc_source),%esi

//
// lets rock :) !
//
    movl    C(pixelcount),%eax
    movb    %al,%dh
    shrl    $2,%eax
    movb    %al,%ch             // quad count
    movl    C(dc_colormap),%eax
    testb   $3,%dh
    jz      v4skyquadloop

//
//  do un-even pixel
//
    testb   $1,%dh
    jz      2f

    movb    (%esi,%ebx),%al     // prep un-even loops
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
     movb    %dl,(%edi)           // output pixel
    addl    C(vidwidth),%edi

//
//  do two non-quad-aligned pixels
//
2:
    testb   $2,%dh
    jz      3f

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
     movb    %dl,(%edi)           // output pixel

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
    addl    C(vidwidth),%edi
     movb    %dl,(%edi)           // output pixel

    addl    C(vidwidth),%edi

//
//  test if there was at least 4 pixels
//
3:
    testb   $0xFF,%ch           // test quad count
    jz      vskydone

//
// ebp : ystep frac. upper 24 bits
// edx : y     frac. upper 24 bits
// ebx : y     i.    lower 7 bits,  masked for index
// ecx : ch = counter, cl = y step i.
// eax : colormap aligned 256
// esi : source texture column
// edi : dest screen
//
v4skyquadloop:
//    .align  4
vskyquadloop:
    movb    (%esi,%ebx),%al     // prep loop
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
    movb    %dl,(%edi)           // output pixel

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%eax),%dl
p1b:    movb    %dl,0x12345678(%edi)

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%eax),%dl
p2b:    movb    %dl,2*0x12345678(%edi)

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%eax),%dl
p3b:    movb    %dl,3*0x12345678(%edi)

p4b:    addl    $4*0x12345678,%edi

    decb   %ch
     jnz    vskyquadloop

vskydone:
    popl    %ebx                // restore register variables
    popl    %edi
    popl    %esi
    popl    %ebp                // restore caller's stack frame pointer
    ret



//----------------------------------------------------------------------
//
// R_DrawSpan
//
// Horizontal texture mapping
//
//----------------------------------------------------------------------

    .data

ystep:          .long   0
xstep:          .long   0
C(texwidth):    .long   64      // texture width
Monster Iestyn committed
619
#if !defined( LINUX)
Alam Ed Arias committed
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
    .text
#endif
#ifdef LINUX
    .align 2
#else
    .align 4
#endif
.globl C(R_DrawSpan_8)
C(R_DrawSpan_8):
    pushl   %ebp                // preserve caller's stack frame pointer
    pushl   %esi                // preserve register variables
    pushl   %edi
    pushl   %ebx


//
// find loop count
//
    movl    C(ds_x2),%eax
    incl    %eax
    subl    C(ds_x1),%eax               // pixel count
    movl    %eax,C(pixelcount)          // save for final pixel
    js      hdone                       // nothing to scale
    shrl    $1,%eax                     // double pixel count
    movl    %eax,C(loopcount)

//
// build composite position
//
    movl    C(ds_xfrac),%ebp
    shll    $10,%ebp
    andl    $0x0ffff0000,%ebp
    movl    C(ds_yfrac),%eax
    shrl    $6,%eax
    andl    $0x0ffff,%eax
    movl    C(ds_y),%edi
    orl     %eax,%ebp

    movl    C(ds_source),%esi

//
// calculate screen dest
//

    movl    C(ylookup)(,%edi,4),%edi
    movl    C(ds_x1),%eax
    addl    C(columnofs)(,%eax,4),%edi

//
// build composite step
//
    movl    C(ds_xstep),%ebx
    shll    $10,%ebx
    andl    $0x0ffff0000,%ebx
    movl    C(ds_ystep),%eax
    shrl    $6,%eax
    andl    $0x0ffff,%eax
    orl     %eax,%ebx

    //movl        %eax,OFFSET hpatch1+2        // convice tasm to modify code...
    movl    %ebx,hpatch1+2
    //movl        %eax,OFFSET hpatch2+2        // convice tasm to modify code...
    movl    %ebx,hpatch2+2
    movl    %esi,hpatch3+2
    movl    %esi,hpatch4+2
// %eax      aligned colormap
// %ebx      aligned colormap
// %ecx,%edx  scratch
// %esi      virtual source
// %edi      moving destination pointer
// %ebp      frac
    movl    C(ds_colormap),%eax
//    shld    $22,%ebp,%ecx           // begin calculating third pixel (y units)
//    shld    $6,%ebp,%ecx            // begin calculating third pixel (x units)
     movl    %ebp,%ecx
    addl    %ebx,%ebp               // advance frac pointer
     shrw    $10,%cx
     roll    $6,%ecx
    andl    $4095,%ecx              // finish calculation for third pixel
//    shld    $22,%ebp,%edx           // begin calculating fourth pixel (y units)
//    shld    $6,%ebp,%edx            // begin calculating fourth pixel (x units)
     movl    %ebp,%edx
     shrw    $10,%dx
     roll    $6,%edx
    addl    %ebx,%ebp               // advance frac pointer
    andl    $4095,%edx              // finish calculation for fourth pixel
    movl    %eax,%ebx
    movb    (%esi,%ecx),%al         // get first pixel
    movb    (%esi,%edx),%bl         // get second pixel
    testl   $0x0fffffffe,C(pixelcount)
    movb    (%eax),%dl             // color translate first pixel

//    jnz hdoubleloop             // at least two pixels to map
//    jmp hchecklast

//    movw $0xf0f0,%dx //see visplanes start

    jz      hchecklast
    movb    (%ebx),%dh              // color translate second pixel
    movl    C(loopcount),%esi
//    .align  4
hdoubleloop:
//    shld    $22,%ebp,%ecx        // begin calculating third pixel (y units)
//    shld    $6,%ebp,%ecx         // begin calculating third pixel (x units)
    movl    %ebp,%ecx
    shrw    $10,%cx
    roll    $6,%ecx
hpatch1:
    addl    $0x012345678,%ebp    // advance frac pointer
    movw    %dx,(%edi)           // write first pixel
    andl    $4095,%ecx           // finish calculation for third pixel
//    shld    $22,%ebp,%edx        // begin calculating fourth pixel (y units)
//    shld    $6,%ebp,%edx         // begin calculating fourth pixel (x units)
    movl    %ebp,%edx
    shrw    $10,%dx
    roll    $6,%edx
hpatch3:
    movb    0x012345678(%ecx),%al      // get third pixel
//    movb    %bl,1(%edi)          // write second pixel
    andl    $4095,%edx           // finish calculation for fourth pixel
hpatch2:
    addl    $0x012345678,%ebp    // advance frac pointer
hpatch4:
    movb    0x012345678(%edx),%bl      // get fourth pixel
    movb    (%eax),%dl           // color translate third pixel
    addl    $2,%edi              // advance to third pixel destination
    decl    %esi                 // done with loop?
    movb    (%ebx),%dh           // color translate fourth pixel
    jnz hdoubleloop

// check for final pixel
hchecklast:
    testl   $1,C(pixelcount)
    jz      hdone
    movb    %dl,(%edi)           // write final pixel

hdone:
    popl    %ebx                 // restore register variables
    popl    %edi
    popl    %esi
    popl    %ebp                 // restore caller's stack frame pointer
    ret


//.endif


//----------------------------------------------------------------------
// R_DrawTransColumn
//
// Vertical column texture drawer, with transparency. Replaces Doom2's
// 'fuzz' effect, which was not so beautiful.
// Transparency is always impressive in some way, don't know why...
//----------------------------------------------------------------------

#ifdef LINUX
    .align 2
#else
    .align 5
#endif

.globl C(R_DrawTranslucentColumn_8)
C(R_DrawTranslucentColumn_8):
    pushl   %ebp                // preserve caller's stack frame pointer
    pushl   %esi                // preserve register variables
    pushl   %edi
    pushl   %ebx

//
// dest = ylookup[dc_yl] + columnofs[dc_x];
//
    movl     C(dc_yl),%ebp
    movl     %ebp,%ebx
    movl     C(ylookup)(,%ebx,4),%edi
    movl     C(dc_x),%ebx
    addl     C(columnofs)(,%ebx,4),%edi  // edi = dest

//
// pixelcount = yh - yl + 1
//
    movl     C(dc_yh),%eax
    incl     %eax
    subl     %ebp,%eax                   // pixel count
    movl     %eax,C(pixelcount)          // save for final pixel
    jle      vtdone                       // nothing to scale

//
// frac = dc_texturemid - (centery-dc_yl)*fracstep;
//
    movl     C(dc_iscale),%ecx           // fracstep
    movl     C(centery),%eax
    subl     %ebp,%eax
    imul     %ecx,%eax
    movl     C(dc_texturemid),%edx
    subl     %eax,%edx
    movl     %edx,%ebx

    shrl     $16,%ebx          // frac int.
    andl     $0x0000007f,%ebx
    shll     $16,%edx          // y frac up

    movl     %ecx,%ebp
    shll     $16,%ebp          // fracstep f. up
    shrl     $16,%ecx          // fracstep i. ->cl
    andb     $0x7f,%cl
    pushw    %cx
    movl     %edx,%ecx
    popw     %cx
    movl     C(dc_colormap),%edx
    movl     C(dc_source),%esi

//
// lets rock :) !
//
    movl    C(pixelcount),%eax
    shrl    $2,%eax
    testb   $0x03,C(pixelcount)
    movb    %al,%ch             // quad count
    movl    C(dc_transmap),%eax
    jz      vt4quadloop
//
//  do un-even pixel
//
    testb   $1,C(pixelcount)
    jz      2f

    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
     addl    %ebp,%ecx
    adcb    %cl,%bl
     movb    (%edi),%al           // fetch dest  : index into colormap
    andb    $0x7f,%bl
     movb    (%eax),%dl
    movb    (%edx), %dl          // use colormap now !
    movb    %dl,(%edi)
     addl    C(vidwidth),%edi
//
//  do two non-quad-aligned pixels
//
2:
    testb   $2,C(pixelcount)
    jz      3f

    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
     addl    %ebp,%ecx
    adcb    %cl,%bl
     movb    (%edi),%al           // fetch dest  : index into colormap
    andb    $0x7f,%bl
     movb    (%eax),%dl
    movb    (%edx), %dl          // use colormap now !
    movb    %dl,(%edi)
     addl    C(vidwidth),%edi

    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
     addl    %ebp,%ecx
    adcb    %cl,%bl
     movb    (%edi),%al           // fetch dest  : index into colormap
    andb    $0x7f,%bl
     movb    (%eax),%dl
    movb    (%edx), %dl          // use colormap now !
    movb    %dl,(%edi)
     addl    C(vidwidth),%edi

//
//  test if there was at least 4 pixels
//
3:
    testb   $0xFF,%ch           // test quad count
    jz      vtdone

//
// tystep : ystep frac. upper 24 bits
// edx : upper 24 bit : colomap
//  dl : tmp pixel to write
// ebx : y     i.    lower 7 bits,  masked for index
// ecx : y     frac. upper 16 bits
// ecx : ch = counter, cl = y step i.
// eax : transmap aligned 65535 (upper 16 bit)
//  ah : background pixel (from the screen buffer)
//  al : foreground pixel (from the texture)
// esi : source texture column
// ebp,edi : dest screen
//
vt4quadloop:
    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
p5: movb    0x12345678(%edi),%al           // fetch dest  : index into colormap

    movl    %ebp,C(tystep)
    movl    %edi,%ebp
    subl    C(vidwidth),%edi
    jmp inloop
//    .align  4
vtquadloop:
    addl    C(tystep),%ecx
    adcb    %cl,%bl
p6: addl    $2*0x12345678,%ebp
    andb    $0x7f,%bl
    movb    (%eax),%dl
    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
    movb    (%edx), %dl          // use colormap now !
    movb    %dl,(%edi)
    movb    (%ebp),%al           // fetch dest  : index into colormap
inloop:
    addl    C(tystep),%ecx
    adcb    %cl,%bl
p7: addl    $2*0x12345678,%edi
    andb    $0x7f,%bl
    movb    (%eax),%dl
    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
    movb    (%edx), %dl          // use colormap now !
    movb    %dl,(%ebp)
    movb    (%edi),%al           // fetch dest  : index into colormap

    addl    C(tystep),%ecx
    adcb    %cl,%bl
p8: addl    $2*0x12345678,%ebp
    andb    $0x7f,%bl
    movb    (%eax),%dl
    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
    movb    (%edx), %dl          // use colormap now !
    movb    %dl,(%edi)
    movb    (%ebp),%al           // fetch dest  : index into colormap

    addl    C(tystep),%ecx
    adcb    %cl,%bl
p9: addl    $2*0x12345678,%edi
    andb    $0x7f,%bl
    movb    (%eax),%dl
    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
    movb    (%edx), %dl          // use colormap now !
    movb    %dl,(%ebp)
    movb    (%edi),%al           // fetch dest  : index into colormap

    decb   %ch
     jnz    vtquadloop

vtdone:
    popl    %ebx                // restore register variables
    popl    %edi
    popl    %esi
    popl    %ebp                // restore caller's stack frame pointer
    ret

#endif // ifdef USEASM



//----------------------------------------------------------------------
// R_DrawShadeColumn
//
//   for smoke..etc.. test.
//----------------------------------------------------------------------

#ifdef LINUX
    .align 2
#else
    .align 5
#endif
.globl C(R_DrawShadeColumn_8)
C(R_DrawShadeColumn_8):
    pushl   %ebp                // preserve caller's stack frame pointer
    pushl   %esi                // preserve register variables
    pushl   %edi
    pushl   %ebx

//
// dest = ylookup[dc_yl] + columnofs[dc_x];
//
    movl     C(dc_yl),%ebp
    movl     %ebp,%ebx
    movl     C(ylookup)(,%ebx,4),%edi
    movl     C(dc_x),%ebx
    addl     C(columnofs)(,%ebx,4),%edi  // edi = dest

//
// pixelcount = yh - yl + 1
//
    movl     C(dc_yh),%eax
    incl     %eax
    subl     %ebp,%eax                   // pixel count
    movl     %eax,C(pixelcount)          // save for final pixel
    jle      shdone                       // nothing to scale

//
// frac = dc_texturemid - (centery-dc_yl)*fracstep;
//
    movl     C(dc_iscale),%ecx           // fracstep
    movl     C(centery),%eax
    subl     %ebp,%eax
    imul     %ecx,%eax
    movl     C(dc_texturemid),%edx
    subl     %eax,%edx
     movl     %edx,%ebx
     shrl     $16,%ebx          // frac int.
     andl     $0x0000007f,%ebx
     shll     $16,%edx          // y frac up

     movl     %ecx,%ebp
     shll     $16,%ebp          // fracstep f. up
     shrl     $16,%ecx          // fracstep i. ->cl
     andb     $0x7f,%cl

    movl     C(dc_source),%esi

//
// lets rock :) !
//
    movl    C(pixelcount),%eax
    movb    %al,%dh
    shrl    $2,%eax
    movb    %al,%ch             // quad count
    movl    C(colormaps),%eax
    testb   $0x03,%dh
    jz      sh4quadloop

//
//  do un-even pixel
//
    testb   $1,%dh
    jz      2f

    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%edi),%al           // fetch dest  : index into colormap
    andb    $0x7f,%bl
     movb    (%eax),%dl
    movb    %dl,(%edi)
     addl    C(vidwidth),%edi

//
//  do two non-quad-aligned pixels
//
2:
    testb   $2,%dh
    jz      3f

    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%edi),%al           // fetch dest  : index into colormap
    andb    $0x7f,%bl
     movb    (%eax),%dl
    movb    %dl,(%edi)
     addl    C(vidwidth),%edi

    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%edi),%al           // fetch dest  : index into colormap
    andb    $0x7f,%bl
     movb    (%eax),%dl
    movb    %dl,(%edi)
     addl    C(vidwidth),%edi

//
//  test if there was at least 4 pixels
//
3:
    testb   $0xFF,%ch           // test quad count
    jz      shdone

//
// ebp : ystep frac. upper 24 bits
// edx : y     frac. upper 24 bits
// ebx : y     i.    lower 7 bits,  masked for index
// ecx : ch = counter, cl = y step i.
// eax : colormap aligned 256
// esi : source texture column
// edi : dest screen
//
sh4quadloop:
    movb    $0x7f,%dh           // prep mask

    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
sh5:    movb    0x12345678(%edi),%al           // fetch dest  : index into colormap

    movl    %ebp,C(tystep)
    movl    %edi,%ebp
    subl    C(vidwidth),%edi
    jmp shinloop
//    .align  4
shquadloop:
    addl    C(tystep),%edx
    adcb    %cl,%bl
    andb    %dh,%bl
sh6:    addl    $2*0x12345678,%ebp
    movb    (%eax),%dl
    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
    movb    %dl,(%edi)
    movb    (%ebp),%al           // fetch dest  : index into colormap
shinloop:
    addl    C(tystep),%edx
    adcb    %cl,%bl
    andb    %dh,%bl
sh7:    addl    $2*0x12345678,%edi
    movb    (%eax),%dl
    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
    movb    %dl,(%ebp)
    movb    (%edi),%al           // fetch dest  : index into colormap

    addl    C(tystep),%edx
    adcb    %cl,%bl
    andb    %dh,%bl
sh8:    addl    $2*0x12345678,%ebp
    movb    (%eax),%dl
    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
    movb    %dl,(%edi)
    movb    (%ebp),%al           // fetch dest  : index into colormap

    addl    C(tystep),%edx
    adcb    %cl,%bl
    andb    %dh,%bl
sh9:    addl    $2*0x12345678,%edi
    movb    (%eax),%dl
    movb    (%esi,%ebx),%ah      // fetch texel : colormap number
    movb    %dl,(%ebp)
    movb    (%edi),%al           // fetch dest  : index into colormap

    decb   %ch
     jnz    shquadloop

shdone:
    popl    %ebx                // restore register variables
    popl    %edi
    popl    %esi
    popl    %ebp                // restore caller's stack frame pointer
    ret



//----------------------------------------------------------------------
//
//  R_DrawWaterColumn : basically it's just a copy of R_DrawColumn,
//                      but it uses dc_colormap from dc_yl to dc_yw-1
//                      then it uses dc_wcolormap from dc_yw to dc_yh
//
//  Thus, the 'underwater' part of the walls is remapped to 'water-like'
//  colors.
//
//----------------------------------------------------------------------

#ifdef LINUX
    .align 2
#else
    .align 5
#endif
.globl C(R_DrawWaterColumn)
C(R_DrawWaterColumn):
    pushl   %ebp                // preserve caller's stack frame pointer
    pushl   %esi                // preserve register variables
    pushl   %edi
    pushl   %ebx

//
// dest = ylookup[dc_yl] + columnofs[dc_x];
//
    movl     C(dc_yl),%ebp
    movl     %ebp,%ebx
    movl     C(ylookup)(,%ebx,4),%edi
    movl     C(dc_x),%ebx
    addl     C(columnofs)(,%ebx,4),%edi  // edi = dest

//
// pixelcount = yh - yl + 1
//
    movl     C(dc_yh),%eax
    incl     %eax
    subl     %ebp,%eax                   // pixel count
    movl     %eax,C(pixelcount)          // save for final pixel
    jle      wdone                       // nothing to scale

//
// frac = dc_texturemid - (centery-dc_yl)*fracstep;
//
    movl     C(dc_iscale),%ecx           // fracstep
    movl     C(centery),%eax
    subl     %ebp,%eax
    imul     %ecx,%eax
    movl     C(dc_texturemid),%edx
    subl     %eax,%edx
     movl     %edx,%ebx
     shrl     $16,%ebx          // frac int.
     andl     $0x0000007f,%ebx
     shll     $16,%edx          // y frac up

     movl     %ecx,%ebp
     shll     $16,%ebp          // fracstep f. up
     shrl     $16,%ecx          // fracstep i. ->cl
     andb     $0x7f,%cl

    movl     C(dc_source),%esi

//
// lets rock :) !
//
    movl    C(pixelcount),%eax
    movb    %al,%dh
    shrl    $2,%eax
    movb    %al,%ch             // quad count
    movl    C(dc_wcolormap),%eax
    testb   $3,%dh
    jz      w4quadloop

//
//  do un-even pixel
//
    testb   $1,%dh
    jz      2f

    movb    (%esi,%ebx),%al     // prep un-even loops
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
    andb    $0x7f,%bl            // mask 0-127 texture index
     movb    %dl,(%edi)           // output pixel
    addl    C(vidwidth),%edi

//
//  do two non-quad-aligned pixels
//
2:
    testb   $2,%dh
    jz      3f

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
    andb    $0x7f,%bl            // mask 0-127 texture index
     movb    %dl,(%edi)           // output pixel

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
    andb    $0x7f,%bl            // mask 0-127 texture index
    addl    C(vidwidth),%edi
     movb    %dl,(%edi)           // output pixel

    addl    C(vidwidth),%edi

//
//  test if there was at least 4 pixels
//
3:
    testb   $0xFF,%ch           // test quad count
    jz      wdone

//
// ebp : ystep frac. upper 24 bits
// edx : y     frac. upper 24 bits
// ebx : y     i.    lower 7 bits,  masked for index
// ecx : ch = counter, cl = y step i.
// eax : colormap aligned 256
// esi : source texture column
// edi : dest screen
//
w4quadloop:
    movb    $0x7f,%dh           // prep mask
//    .align  4
wquadloop:
    movb    (%esi,%ebx),%al     // prep loop
     addl    %ebp,%edx            // ypos f += ystep f
    adcb    %cl,%bl              // ypos i += ystep i
     movb    (%eax),%dl           // colormap texel
    movb    %dl,(%edi)           // output pixel
     andb    $0x7f,%bl            // mask 0-127 texture index

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%eax),%dl
w1:    movb    %dl,0x12345678(%edi)
     andb    $0x7f,%bl

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%eax),%dl
w2:    movb    %dl,2*0x12345678(%edi)
     andb    $0x7f,%bl

    movb    (%esi,%ebx),%al      // fetch source texel
     addl    %ebp,%edx
    adcb    %cl,%bl
     movb    (%eax),%dl
w3:    movb    %dl,3*0x12345678(%edi)
     andb    $0x7f,%bl

w4:    addl    $4*0x12345678,%edi

    decb   %ch
     jnz    wquadloop

wdone:
    popl    %ebx                // restore register variables
    popl    %edi
    popl    %esi
    popl    %ebp                // restore caller's stack frame pointer
    ret







//----------------------------------------------------------------------
//
//  R_DrawSpanNoWrap
//
//      Horizontal texture mapping, does not remap colors,
//      neither needs to wrap around the source texture.
//
//      Thus, a special optimisation can be used...
//
//----------------------------------------------------------------------

    .data

advancetable:   .long   0, 0
Monster Iestyn committed
1341
#if !defined( LINUX)
Alam Ed Arias committed
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
    .text
#endif
#ifdef LINUX
    .align 2
#else
    .align 4
#endif
.globl C(R_DrawSpanNoWrap)
C(R_DrawSpanNoWrap):
    pushl   %ebp                // preserve caller's stack frame pointer
    pushl   %esi                // preserve register variables
    pushl   %edi
    pushl   %ebx

//
// find loop count
//

    movl    C(ds_x2),%eax
    incl    %eax
    subl    C(ds_x1),%eax               // pixel count
    movl    %eax,C(pixelcount)          // save for final pixel
    jle     htvdone                       // nothing to scale
//    shrl    $1,%eax                     // double pixel count
//    movl    %eax,C(loopcount)

//
// calculate screen dest
//

    movl    C(ds_y),%edi        //full destination start address

//
// set up advancetable
//

    movl    C(ds_xstep),%ebp
    movl    C(ds_ystep),%ecx
    movl    %ecx,%eax
    movl    %ebp,%edx
    sarl    $16,%edx            // xstep >>= 16;
    movl    C(vidwidth),%ebx
    sarl    $16,%eax            // ystep >>= 16;
    jz      0f
    imull   %ebx,%eax           // (ystep >> 16) * texwidth;
0:
    addl    %edx,%eax           // add in xstep
                                // (ystep >> 16) * texwidth + (xstep >> 16);

    movl    %eax,advancetable+4 // advance base in y
    addl    %ebx,%eax           // ((ystep >> 16) + 1) * texwidth +
                                //  (xstep >> 16);
    movl    %eax,advancetable   // advance extra in y

    shll    $16,%ebp            // left-justify xstep fractional part
    movl    %ebp,xstep
    shll    $16,%ecx            // left-justify ystep fractional part
    movl    %ecx,ystep

//
// calculate the texture starting address
//
    movl    C(ds_source),%esi       // texture source

     movl    C(ds_yfrac),%eax
     movl    %eax,%edx
     sarl    $16,%eax
    movl    C(ds_xfrac),%ecx
     imull   %ebx,%eax               // (yfrac >> 16) * texwidth
    movl    %ecx,%ebx
    sarl    $16,%ecx
    movl    %ecx,%ebp
     addl    %eax,%ebp               // source = (xfrac >> 16) +
                                    //           ((yfrac >> 16) * texwidth);

//
//  esi : texture source
//  edi : screen dest
//  eax : colormap aligned on 256 boundary, hehehe...
//  ebx : xfrac << 16
//  ecx : used in loop, contains either 0 or -1, *4, offset into advancetable
//  edx : yfrac << 16
//  ebp : offset into texture
//

    shll    $16,%edx             // yfrac upper word, lower byte will be used
    movl    C(ds_colormap),%eax
    shll    $16,%ebx             // xfrac upper word, lower unused

    movl    C(pixelcount),%ecx
    shrl    $2,%ecx
    movb    %cl,%dh             // quad pixels count

    movl    C(pixelcount),%ecx
    andl    $3,%ecx
    jz      htvquadloop         // pixelcount is multiple of 4
    decl    %ecx
    jz      1f
    decl    %ecx
    jz      2f

//
//  do one to three pixels first
//
    addl    ystep,%edx          // yfrac += ystep
   sbbl    %ecx,%ecx           // turn carry into 0 or -1 if set
    movb    (%esi,%ebp),%al          // get texture pixel
   addl    xstep,%ebx           // xfrac += xstep
//    movb    (%eax),%dl           // pixel goes through colormap
   adcl    advancetable+4(,%ecx,4),%ebp       // advance source
    movb    %al,(%edi)           // write pixel dest

   incl    %edi

2:
    addl    ystep,%edx          // yfrac += ystep
   sbbl    %ecx,%ecx           // turn carry into 0 or -1 if set
    movb    (%esi,%ebp),%al          // get texture pixel
   addl    xstep,%ebx           // xfrac += xstep
//    movb    (%eax),%dl           // pixel goes through colormap
   adcl    advancetable+4(,%ecx,4),%ebp       // advance source
    movb    %al,(%edi)           // write pixel dest

   incl    %edi

1:
    addl    ystep,%edx          // yfrac += ystep
   sbbl    %ecx,%ecx           // turn carry into 0 or -1 if set
    movb    (%esi,%ebp),%al          // get texture pixel
   addl    xstep,%ebx           // xfrac += xstep
//    movb    (%eax),%dl           // pixel goes through colormap
   adcl    advancetable+4(,%ecx,4),%ebp       // advance source
    movb    %al,(%edi)           // write pixel dest

   incl    %edi

//
//  test if there was at least 4 pixels
//
    testb   $0xFF,%dh
    jz      htvdone

//
//  two pixels per loop
// U
//  V
htvquadloop:
    addl    ystep,%edx             // yfrac += ystep
   sbbl    %ecx,%ecx               // turn carry into 0 or -1 if set
    movb    (%esi,%ebp),%al        // get texture pixel
   addl    xstep,%ebx              // xfrac += xstep
//    movb    (%eax),%dl             // pixel goes through colormap
   adcl    advancetable+4(,%ecx,4),%ebp       // advance source
    movb    %al,(%edi)             // write pixel dest

    addl    ystep,%edx
   sbbl    %ecx,%ecx
    movb    (%esi,%ebp),%al
   addl    xstep,%ebx
//    movb    (%eax),%dl
   adcl    advancetable+4(,%ecx,4),%ebp
    movb    %al,1(%edi)

    addl    ystep,%edx
   sbbl    %ecx,%ecx
    movb    (%esi,%ebp),%al
   addl    xstep,%ebx
//    movb    (%eax),%dl
   adcl    advancetable+4(,%ecx,4),%ebp
    movb    %al,2(%edi)

    addl    ystep,%edx
   sbbl    %ecx,%ecx
    movb    (%esi,%ebp),%al
   addl    xstep,%ebx
//    movb    (%eax),%dl
   adcl    advancetable+4(,%ecx,4),%ebp
    movb    %al,3(%edi)

   addl    $4, %edi
    incl    %ecx    //dummy

   decb   %dh
    jnz    htvquadloop          // paire dans V-pipe

htvdone:
    popl    %ebx                // restore register variables
    popl    %edi
    popl    %esi
    popl    %ebp                // restore caller's stack frame pointer
    ret


//.endif

#ifdef HORIZONTALDRAW
// void R_RotateBuffere (void)

#ifdef LINUX
    .align 2
#else
    .align 4
#endif
.globl C(R_RotateBufferasm)
C(R_RotateBufferasm):
    pushl   %ebp                // preserve caller's stack frame pointer
    pushl   %esi                // preserve register variables
    pushl   %edi
    pushl   %ebx

    movl    C(dc_source),%esi
    movl    C(dc_colormap),%edi

    movl    $200,%edx
ra2:
    movl    $40,%ecx
ra:
    movb    -2*200(%esi),%al
    movb    -6*200(%esi),%bl
    movb    -3*200(%esi),%ah
    movb    -7*200(%esi),%bh
    shll    $16,%eax
    shll    $16,%ebx
    movb    (%esi),%al
    movb    -4*200(%esi),%bl
    movb    -1*200(%esi),%ah
    movb    -5*200(%esi),%bh
    movl    %eax,(%edi)
    subl    $8*200,%esi
    movl    %ebx,4(%edi)
    addl    $8,%edi
    decl    %ecx
    jnz     ra

    addl    $320*200+1,%esi      //32*480 passe a la ligne suivante
//    addl    320-32,%edi

    decl    %edx
    jnz     ra2

    pop   %ebp                // preserve caller's stack frame pointer
    pop   %esi                // preserve register variables
    pop   %edi
    pop   %ebx
    ret
#endif