1. Thejesh GN
  2. doom

Source

doom / src / tmap.nas

   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
;;-----------------------------------------------------------------------------
;;
;; $Id: tmap.nas,v 1.11 2003/06/10 23:36:09 ssntails Exp $
;;
;; Copyright (C) 1998-2000 by DooM Legacy Team.
;;
;; This program is free software; you can redistribute it and/or
;; modify it under the terms of the GNU General Public License
;; as published by the Free Software Foundation; either version 2
;; of the License, or (at your option) any later version.
;;
;; This program is distributed in the hope that it will be useful,
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
;; GNU General Public License for more details.
;;
;;
;; $Log: tmap.nas,v $
;; Revision 1.11  2003/06/10 23:36:09  ssntails
;; Variable flat support (32x32 to 2048x2048)
;;
;; Revision 1.10  2001/02/24 13:35:21  bpereira
;; no message
;;
;; Revision 1.9  2001/02/10 15:24:19  hurdler
;; Apply Rob's patch for Linux version
;;
;; Revision 1.8  2000/11/12 09:48:15  bpereira
;; no message
;;
;; Revision 1.7  2000/11/06 20:52:16  bpereira
;; no message
;;
;; Revision 1.6  2000/11/03 11:48:40  hurdler
;; Fix compiling problem under win32 with 3D-Floors and FragglScript (to verify!)
;;
;; Revision 1.5  2000/11/03 03:27:17  stroggonmeth
;; Again with the bug fixing...
;;
;; Revision 1.4  2000/11/02 17:50:10  stroggonmeth
;; Big 3Dfloors & FraggleScript commit!!
;;
;; Revision 1.3  2000/04/24 20:24:38  bpereira
;; no message
;;
;; Revision 1.2  2000/02/27 00:42:11  hurdler
;; fix CR+LF problem
;;
;; Revision 1.1.1.1  2000/02/22 20:32:32  hurdler
;; Initial import into CVS (v1.29 pr3)
;;
;;
;; DESCRIPTION:
;;      assembler optimised rendering code for software mode
;;      draw floor spans, and wall columns.
;;
;;-----------------------------------------------------------------------------


[BITS 32]

%ifdef LINUX
%macro cextern 1
[extern %1]
%endmacro

%macro cglobal 1
[global %1]
%endmacro

%define CODE_SEG .data
%else
%macro cextern 1
%define %1 _%1
[extern %1]
%endmacro

%macro cglobal 1
%define %1 _%1
[global %1]
%endmacro

%define CODE_SEG .text                         
%endif


;; externs
;; columns
cextern dc_x
cextern dc_yl
cextern dc_yh
cextern ylookup
cextern columnofs
cextern dc_source
cextern dc_texturemid
cextern dc_iscale
cextern centery
cextern dc_colormap
cextern dc_transmap
cextern colormaps

;; spans
cextern ds_x1
cextern ds_x2
cextern ds_y
cextern ds_xfrac
cextern ds_yfrac
cextern ds_xstep
cextern ds_ystep
cextern ds_source
cextern ds_colormap
;cextern ds_textureheight

; polygon edge rasterizer
cextern prastertab


;;----------------------------------------------------------------------
;;
;; 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.
;;
;;----------------------------------------------------------------------

[SECTION .data]

;;.align        4
loopcount       dd      0
pixelcount      dd      0
tystep          dd      0

[SECTION CODE_SEG write]

;----------------------------------------------------------------------------
;fixed_t FixedMul (fixed_t a, fixed_t b)
;----------------------------------------------------------------------------
cglobal FixedMul
;       align   16
FixedMul:
        mov     eax,[esp+4]
        imul    dword [esp+8]
        shrd    eax,edx,16
        ret

;----------------------------------------------------------------------------
;fixed_t FixedDiv2 (fixed_t a, fixed_t b);
;----------------------------------------------------------------------------
cglobal FixedDiv2
;       align   16
FixedDiv2:
        mov     eax,[esp+4]
        mov     edx,eax                 ;; these two instructions allow the next
        sar     edx,31                  ;; two to pair, on the Pentium processor.
        shld    edx,eax,16
        sal     eax,16
        idiv    dword [esp+8]
        ret

;----------------------------------------------------------------------------
; void  ASM_PatchRowBytes (int rowbytes);
;----------------------------------------------------------------------------
cglobal ASM_PatchRowBytes
;       align   16
ASM_PatchRowBytes:
        mov     eax,[esp+4]
        mov     [p1+2],eax
        mov     [p2+2],eax
        mov     [p3+2],eax
        mov     [p4+2],eax
        mov     [p5+2],eax
        mov     [p6+2],eax
        mov     [p7+2],eax
        mov     [p8+2],eax
        mov     [p9+2],eax
        mov     [pa+2],eax
        mov     [pb+2],eax
        mov     [pc+2],eax
        mov     [pd+2],eax
        mov     [pe+2],eax
        mov     [pf+2],eax
        mov     [pg+2],eax
        mov     [ph+2],eax
        mov     [pi+2],eax
        mov     [pj+2],eax
        mov     [pk+2],eax
        mov     [pl+2],eax
        mov     [pm+2],eax
        mov     [pn+2],eax
        mov     [po+2],eax
        mov     [pp+2],eax
        mov     [pq+2],eax
        add     eax,eax
        mov     [q1+2],eax
        mov     [q2+2],eax
        mov     [q3+2],eax
        mov     [q4+2],eax
        mov     [q5+2],eax
        mov     [q6+2],eax
        mov     [q7+2],eax
        mov     [q8+2],eax
        ret


;----------------------------------------------------------------------------
; 8bpp column drawer
;----------------------------------------------------------------------------

cglobal R_DrawColumn_8
;       align   16
R_DrawColumn_8:
        push    ebp                     ;; preserve caller's stack frame pointer
        push    esi                     ;; preserve register variables
        push    edi
        push    ebx
;;
;; dest = ylookup[dc_yl] + columnofs[dc_x];
;;
        mov     ebp,[dc_yl]
        mov     ebx,ebp
        mov     edi,[ylookup+ebx*4]
        mov     ebx,[dc_x]
        add     edi,[columnofs+ebx*4]  ;; edi = dest
;;
;; pixelcount = yh - yl + 1
;;
        mov     eax,[dc_yh]
        inc     eax
        sub     eax,ebp                 ;; pixel count
        mov     [pixelcount],eax        ;; save for final pixel
        jle     near vdone                   ;; nothing to scale
;;
;; frac = dc_texturemid - (centery-dc_yl)*fracstep;
;;
        mov     ecx,[dc_iscale]        ;; fracstep
        mov     eax,[centery]
        sub     eax,ebp
        imul    eax,ecx
        mov     edx,[dc_texturemid]
        sub     edx,eax
        mov     ebx,edx
        shr     ebx,16                  ;; frac int.
        and     ebx,0x7f
        shl     edx,16                  ;; y frac up

        mov     ebp,ecx
        shl     ebp,16                  ;; fracstep f. up
        shr     ecx,16                  ;; fracstep i. ->cl
        and     cl,0x7f
        mov     esi,[dc_source]
;;
;; lets rock :) !
;;
        mov     eax,[pixelcount]
        mov     dh,al
        shr     eax,2
        mov     ch,al                   ;; quad count
        mov     eax,[dc_colormap]
        test    dh,0x3
        je      near v4quadloop
;;
;;  do un-even pixel
;;
        test    dh,0x1
        je      two_uneven

        mov     al,[esi+ebx]            ;; prep un-even loops
        add     edx,ebp                 ;; ypos f += ystep f
        adc     bl,cl                   ;; ypos i += ystep i
        mov     dl,[eax]                ;; colormap texel
        and     bl,0x7f                 ;; mask 0-127 texture index
        mov     [edi],dl                ;; output pixel
p1:     add     edi,0x12345678
;;
;;  do two non-quad-aligned pixels
;;
two_uneven:
        test    dh,0x2
        je      f3

        mov     al,[esi+ebx]            ;; fetch source texel
        add     edx,ebp                 ;; ypos f += ystep f
        adc     bl,cl                   ;; ypos i += ystep i
        mov     dl,[eax]                ;; colormap texel
        and     bl,0x7f                 ;; mask 0-127 texture index
        mov     [edi],dl                ;; output pixel
        mov     al,[esi+ebx]
        add     edx,ebp                 ;; fetch source texel
        adc     bl,cl                   ;; ypos f += ystep f
        mov     dl,[eax]                ;; ypos i += ystep i
        and     bl,0x7f                 ;; colormap texel
p2:     add     edi,0x12345678          ;; mask 0-127 texture index
        mov     [edi],dl
p3:     add     edi,0x12345678          ;; output pixel
;;
;;  test if there was at least 4 pixels
;;
f3:
        test    ch,0xff                 ;; test quad count
        je      near vdone
;;
;; ebp : ystep frac. upper 16 bits
;; edx : y     frac. upper 16 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:
        mov     dh,0x7f                 ;; prep mask
align 4
vquadloop:
        mov     al,[esi+ebx]            ;; prep loop
        add     edx,ebp                 ;; ypos f += ystep f
        adc     bl,cl                   ;; ypos i += ystep i
        mov     dl,[eax]                ;; colormap texel
        mov     [edi],dl                ;; output pixel
        and     bl,0x7f                 ;; mask 0-127 texture index

        mov     al,[esi+ebx]            ;; fetch source texel
        add     edx,ebp
        adc     bl,cl
p4:     add     edi,0x12345678
        mov     dl,[eax]
        and     bl,0x7f
        mov     [edi],dl

        mov     al,[esi+ebx]            ;; fetch source texel
        add     edx,ebp
        adc     bl,cl
p5:     add     edi,0x12345678
        mov     dl,[eax]
        and     bl,0x7f
        mov     [edi],dl

        mov     al,[esi+ebx]            ;; fetch source texel
        add     edx,ebp
        adc     bl,cl
p6:     add     edi,0x12345678
        mov     dl,[eax]
        and     bl,0x7f
        mov     [edi],dl

p7:     add     edi,0x12345678

        dec     ch
        jne     vquadloop

vdone:
        pop     ebx                     ;; restore register variables
        pop     edi
        pop     esi
        pop     ebp                     ;; restore caller's stack frame pointer
        ret

;;----------------------------------------------------------------------
;;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 !!!
;;
;;----------------------------------------------------------------------

cglobal R_DrawSkyColumn_8
;       align   16
R_DrawSkyColumn_8:
        push    ebp
        push    esi
        push    edi
        push    ebx
;;
;; dest = ylookup[dc_yl] + columnofs[dc_x];
;;
        mov     ebp,[dc_yl]
        mov     ebx,ebp
        mov     edi,[ylookup+ebx*4]
        mov     ebx,[dc_x]
        add     edi,[columnofs+ebx*4]   ;; edi = dest
;;
;; pixelcount = yh - yl + 1
;;
        mov     eax,[dc_yh]
        inc     eax
        sub     eax,ebp                 ;; pixel count
        mov     [pixelcount],eax        ;; save for final pixel
        jle     near    vskydone        ;; nothing to scale
;;
;; frac = dc_texturemid - (centery-dc_yl)*fracstep;
;;
        mov     ecx,[dc_iscale]        ;; fracstep
        mov     eax,[centery]
        sub     eax,ebp
        imul    eax,ecx
        mov     edx,[dc_texturemid]
        sub     edx,eax
        mov     ebx,edx
        shr     ebx,16                  ;; frac int.
        and     ebx,0xff
        shl     edx,16                  ;; y frac up
        mov     ebp,ecx
        shl     ebp,16                  ;; fracstep f. up
        shr     ecx,16                  ;; fracstep i. ->cl
        mov     esi,[dc_source]
;;
;; lets rock :) !
;;
        mov     eax,[pixelcount]
        mov     dh,al
        shr     eax,0x2
        mov     ch,al                   ;; quad count
        mov     eax,[dc_colormap]
        test    dh,0x3
        je      vskyquadloop
;;
;;  do un-even pixel
;;
        test    dh,0x1
        je      f2
        mov     al,[esi+ebx]            ;; prep un-even loops
        add     edx,ebp                 ;; ypos f += ystep f
        adc     bl,cl                   ;; ypos i += ystep i
        mov     dl,[eax]                ;; colormap texel
        mov     [edi],dl                ;; output pixel
p8:     add     edi,0x12345678
;;
;;  do two non-quad-aligned pixels
;;
f2:     test    dh,0x2
        je      skyf3

        mov     al,[esi+ebx]            ;; fetch source texel
        add     edx,ebp                 ;; ypos f += ystep f
        adc     bl,cl                   ;; ypos i += ystep i
        mov     dl,[eax]                ;; colormap texel
        mov     [edi],dl                ;; output pixel

        mov     al,[esi+ebx]            ;; fetch source texel
        add     edx,ebp                 ;; ypos f += ystep f
        adc     bl,cl                   ;; ypos i += ystep i
        mov     dl,[eax]                ;; colormap texel
p9:     add     edi,0x12345678
        mov     [edi],dl                ;; output pixel

pa:     add     edi,0x12345678
;;
;;  test if there was at least 4 pixels
;;
skyf3:  test    ch,0xff                 ;; test quad count
        je      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
;;
align 4
vskyquadloop:
        mov     al,[esi+ebx]            ;; prep loop
        add     edx,ebp                 ;; ypos f += ystep f
        mov     dl,[eax]                ;; colormap texel
        adc     bl,cl                   ;; ypos i += ystep i
        mov     [edi],dl                ;; output pixel

        mov     al,[esi+ebx]            ;; fetch source texel
        add     edx,ebp
        adc     bl,cl
pb:     add     edi,0x12345678
        mov     dl,[eax]
        mov     [edi],dl

        mov     al,[esi+ebx]            ;; fetch source texel
        add     edx,ebp
        adc     bl,cl
pc:     add     edi,0x12345678
        mov     dl,[eax]
        mov     [edi],dl

        mov     al,[esi+ebx]            ;; fetch source texel
        add     edx,ebp
        adc     bl,cl
pd:     add     edi,0x12345678
        mov     dl,[eax]
        mov     [edi],dl

pe:     add     edi,0x12345678

        dec     ch
        jne     vskyquadloop
vskydone:
        pop     ebx
        pop     edi
        pop     esi
        pop     ebp
        ret


;;----------------------------------------------------------------------
;; R_DrawTranslucentColumn_8
;;
;; 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...
;;----------------------------------------------------------------------

cglobal R_DrawTranslucentColumn_8
R_DrawTranslucentColumn_8:
        push    ebp                     ;; preserve caller's stack frame pointer
        push    esi                     ;; preserve register variables
        push    edi
        push    ebx
;;
;; dest = ylookup[dc_yl] + columnofs[dc_x];
;;
        mov     ebp,[dc_yl]
        mov     ebx,ebp
        mov     edi,[ylookup+ebx*4]
        mov     ebx,[dc_x]
        add     edi,[columnofs+ebx*4]   ;; edi = dest
;;
;; pixelcount = yh - yl + 1
;;
        mov     eax,[dc_yh]
        inc     eax
        sub     eax,ebp                 ;; pixel count
        mov     [pixelcount],eax        ;; save for final pixel
        jle     near    vtdone         ;; nothing to scale
;;
;; frac = dc_texturemid - (centery-dc_yl)*fracstep;
;;
        mov     ecx,[dc_iscale]        ;; fracstep
        mov     eax,[centery]
        sub     eax,ebp
        imul    eax,ecx
        mov     edx,[dc_texturemid]
        sub     edx,eax
        mov     ebx,edx

        shr     ebx,16                  ;; frac int.
        and     ebx,0x7f
        shl     edx,16                  ;; y frac up

        mov     ebp,ecx
        shl     ebp,16                  ;; fracstep f. up
        shr     ecx,16                  ;; fracstep i. ->cl
        and     cl,0x7f
        push    cx
        mov     ecx,edx
        pop     cx
        mov     edx,[dc_colormap]
        mov     esi,[dc_source]
;;
;; lets rock :) !
;;
        mov     eax,[pixelcount]
        shr     eax,0x2
        test    byte [pixelcount],0x3
        mov     ch,al                   ;; quad count
        mov     eax,[dc_transmap]
        je      vt4quadloop
;;
;;  do un-even pixel
;;
        test    byte [pixelcount],0x1
        je      trf2

        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        add     ecx,ebp
        adc     bl,cl
        mov     al,[edi]                ;; fetch dest  : index into colormap
        and     bl,0x7f
        mov     dl,[eax]
        mov     dl,[edx]
        mov     [edi],dl
pf:     add     edi,0x12345678
;;
;;  do two non-quad-aligned pixels
;;
trf2:    test    byte [pixelcount],0x2
        je      trf3

        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        add     ecx,ebp
        adc     bl,cl
        mov     al,[edi]                ;; fetch dest  : index into colormap
        and     bl,0x7f
        mov     dl,[eax]
        mov     dl,[edx]
        mov     [edi],dl
pg:     add     edi,0x12345678

        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        add     ecx,ebp
        adc     bl,cl
        mov     al,[edi]                ;; fetch dest  : index into colormap
        and     bl,0x7f
        mov     dl,[eax]
        mov     dl,[edx]
        mov     [edi],dl
ph:     add     edi,0x12345678
;;
;;  test if there was at least 4 pixels
;;
trf3:   test    ch,0xff                 ;; test quad count
        je near vtdone

;;
;; 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
;;
vt4quadloop:
        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        mov     [tystep],ebp
pi:     add     edi,0x12345678
        mov     al,[edi]                ;; fetch dest  : index into colormap
pj:     sub     edi,0x12345678
        mov     ebp,edi
pk:     sub     edi,0x12345678
        jmp short inloop
align 4
vtquadloop:
        add     ecx,[tystep]
        adc     bl,cl
q1:     add     ebp,0x23456789
        and     bl,0x7f
        mov     dl,[eax]
        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        mov     dl,[edx]
        mov     [edi],dl
        mov     al,[ebp]                ;; fetch dest   : index into colormap
inloop:
        add     ecx,[tystep]
        adc     bl,cl
q2:     add     edi,0x23456789
        and     bl,0x7f
        mov     dl,[eax]
        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        mov     dl,[edx]
        mov     [ebp+0x0],dl
        mov     al,[edi]                ;; fetch dest   : index into colormap

        add     ecx,[tystep]
        adc     bl,cl
q3:     add     ebp,0x23456789
        and     bl,0x7f
        mov     dl,[eax]
        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        mov     dl,[edx]
        mov     [edi],dl
        mov     al,[ebp]                ;; fetch dest   : index into colormap

        add     ecx,[tystep]
        adc     bl,cl
q4:     add     edi,0x23456789
        and     bl,0x7f
        mov     dl,[eax]
        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        mov     dl,[edx]
        mov     [ebp],dl
        mov     al,[edi]                ;; fetch dest   : index into colormap

        dec     ch
        jne     vtquadloop
vtdone:
        pop     ebx
        pop     edi
        pop     esi
        pop     ebp
        ret


;;----------------------------------------------------------------------
;; R_DrawShadeColumn
;;
;;   for smoke..etc.. test.
;;----------------------------------------------------------------------
cglobal R_DrawShadeColumn_8
R_DrawShadeColumn_8:
        push    ebp                     ;; preserve caller's stack frame pointer
        push    esi                     ;; preserve register variables
        push    edi
        push    ebx

;;
;; dest = ylookup[dc_yl] + columnofs[dc_x];
;;
        mov     ebp,[dc_yl]
        mov     ebx,ebp
        mov     edi,[ylookup+ebx*4]
        mov     ebx,[dc_x]
        add     edi,[columnofs+ebx*4]  ;; edi = dest
;;
;; pixelcount = yh - yl + 1
;;
        mov     eax,[dc_yh]
        inc     eax
        sub     eax,ebp                 ;; pixel count
        mov     [pixelcount],eax       ;; save for final pixel
        jle near shdone                ;; nothing to scale
;;
;; frac = dc_texturemid - (centery-dc_yl)*fracstep;
;;
        mov     ecx,[dc_iscale]        ;; fracstep
        mov     eax,[centery]
        sub     eax,ebp
        imul    eax,ecx
        mov     edx,[dc_texturemid]
        sub     edx,eax
        mov     ebx,edx
        shr     ebx,16                  ;; frac int.
        and     ebx,byte +0x7f
        shl     edx,16                  ;; y frac up

        mov     ebp,ecx
        shl     ebp,16                  ;; fracstep f. up
        shr     ecx,16                  ;; fracstep i. ->cl
        and     cl,0x7f

        mov     esi,[dc_source]
;;
;; lets rock :) !
;;
        mov     eax,[pixelcount]
        mov     dh,al
        shr     eax,2
        mov     ch,al                   ;; quad count
        mov     eax,[colormaps]
        test    dh,3
        je      sh4quadloop
;;
;;  do un-even pixel
;;
        test    dh,0x1
        je      shf2

        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        add     edx,ebp
        adc     bl,cl
        mov     al,[edi]                ;; fetch dest  : index into colormap
        and     bl,0x7f
        mov     dl,[eax]
        mov     [edi],dl
pl:     add     edi,0x12345678
;;
;;  do two non-quad-aligned pixels
;;
shf2:
        test    dh,0x2
        je      shf3

        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        add     edx,ebp
        adc     bl,cl
        mov     al,[edi]                ;; fetch dest  : index into colormap
        and     bl,0x7f
        mov     dl,[eax]
        mov     [edi],dl
pm:     add     edi,0x12345678

        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        add     edx,ebp
        adc     bl,cl
        mov     al,[edi]                ;; fetch dest  : index into colormap
        and     bl,0x7f
        mov     dl,[eax]
        mov     [edi],dl
pn:     add     edi,0x12345678
;;
;;  test if there was at least 4 pixels
;;
shf3:
        test    ch,0xff                 ;; test quad count
        je near 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:
        mov     dh,0x7f                 ;; prep mask
        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        mov     [tystep],ebp
po:     add     edi,0x12345678
        mov     al,[edi]                ;; fetch dest  : index into colormap
pp:     sub     edi,0x12345678
        mov     ebp,edi
pq:     sub     edi,0x12345678
        jmp short shinloop

align  4
shquadloop:
        add     edx,[tystep]
        adc     bl,cl
        and     bl,dh
q5:     add     ebp,0x12345678
        mov     dl,[eax]
        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        mov     [edi],dl
        mov     al,[ebp]                ;; fetch dest : index into colormap
shinloop:
        add     edx,[tystep]
        adc     bl,cl
        and     bl,dh
q6:     add     edi,0x12345678
        mov     dl,[eax]
        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        mov     [ebp],dl
        mov     al,[edi]                ;; fetch dest : index into colormap

        add     edx,[tystep]
        adc     bl,cl
        and     bl,dh
q7:     add     ebp,0x12345678
        mov     dl,[eax]
        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        mov     [edi],dl
        mov     al,[ebp]                ;; fetch dest : index into colormap

        add     edx,[tystep]
        adc     bl,cl
        and     bl,dh
q8:     add     edi,0x12345678
        mov     dl,[eax]
        mov     ah,[esi+ebx]            ;; fetch texel : colormap number
        mov     [ebp],dl
        mov     al,[edi]                ;; fetch dest : index into colormap

        dec     ch
        jne     shquadloop

shdone:
        pop     ebx                     ;; restore register variables
        pop     edi
        pop     esi
        pop     ebp                     ;; restore caller's stack frame pointer
        ret



;;----------------------------------------------------------------------
;;
;;      R_DrawSpan
;;
;;      Horizontal texture mapping
;;
;;----------------------------------------------------------------------


[SECTION .data]

oldcolormap     dd      0

[SECTION CODE_SEG write]

; R_DrawSpan is no longer in assembly due to variable flat size support SSNTails 06-10-2003
cglobal R_DrawSpan_8a
R_DrawSpan_8a:
        push    ebp                     ;; preserve caller's stack frame pointer
        push    esi                     ;; preserve register variables
        push    edi
        push    ebx
;;
;; initilise registers
;;
  
        mov     edx, [ds_xfrac]
        mov     eax, [ds_ystep]
        ror     edx, 14
        ror     eax, 15
        mov      bl, dl
        mov     ecx, [ds_xstep]
        mov      dh, al
        mov      ax, 1
        mov     [tystep], eax


        mov     eax, [ds_yfrac]
        ror     ecx, 13
        ror     eax, 16
        mov      dl, cl
        mov      bh, al
        xor      cx, cx
        and     ebx, 0x3fff
        mov     [pixelcount],ecx

        mov     ecx, [ds_x2]
        mov     edi, [ds_y]
        mov     esi, [ds_x1]
        mov     edi, [ylookup+edi*4]
        mov     ebp, ebx
        add     edi, [columnofs+esi*4]
        sub     esi, ecx                ;; pixel count
        shr     ebp, 2
        mov     ecx, [ds_colormap]
        mov      ax, si
        mov     esi, [ds_source]
        sar      ax,1
        jnc     near .midloop           ;; check parity

;   summary
; edx = high16bit xfrac[0..13], ah=ystep[16..24] al=xtep[14..21]
; ebx = high16bit =0, bh=yfrac[16..24], bl=xfrac[14..21] 
; ecx = colormap table cl=0 (colormap is aligned 8 bits)
; eax = high16bit yfrac[0..15], dx = count
; esi = flat texture source
; edi = screeen buffer destination
; ebp = work register
; pixelcount = high16bit xstep[0..13] rest to 0
; tystep     = high16bit ystep[0..15] low 16 bit = 2 (increment of count)

align 4
.loop
        add     eax, [tystep]
         mov      cl, [esi+ebp]
        adc      bh, dh
         mov      cl, [ecx]
        and      bh, 0x3f 
         mov   [edi], cl
        mov     ebp, ebx        
         inc     edi
         shr     ebp, 2

.midloop:
        add     edx, [pixelcount]
         mov      cl, [esi+ebp]
        adc      bl, dl
         mov      cl, [ecx]
        mov     ebp, ebx 
         mov   [edi], cl
        inc     edi
         shr     ebp, 2

        test    eax, 0xffff
        jnz     near .loop

.hdone: pop     ebx                     ;; restore register variables
        pop     edi
        pop     esi
        pop     ebp                     ;; restore caller's stack frame pointer
        ret


[SECTION .data]

obelix          dd      0
etaussi         dd      0

[SECTION CODE_SEG]

cglobal R_DrawSpan_8_old
R_DrawSpan_8_old:
        push    ebp                     ;; preserve caller's stack frame pointer
        push    esi                     ;; preserve register variables
        push    edi
        push    ebx
;;
;; find loop count
;;
        mov     eax,[ds_x2]
        inc     eax
        sub     eax,[ds_x1]             ;; pixel count
        mov     [pixelcount],eax        ;; save for final pixel
        js near .hdone                  ;; nothing to scale
        shr     eax,0x1                 ;; double pixel count
        mov     [loopcount],eax
;;
;; build composite position
;;
        mov     ebp,[ds_xfrac]
        shl     ebp,10
        and     ebp,0xffff0000
        mov     eax,[ds_yfrac]
        shr     eax,6
        and     eax,0xffff
        mov     edi,[ds_y]
        or      ebp,eax

        mov     esi,[ds_source]
;;
;; calculate screen dest
;;
        mov     edi,[ylookup+edi*4]
        mov     eax,[ds_x1]
        add     edi,[columnofs+eax*4]
;;
;; build composite step
;;
        mov     ebx,[ds_xstep]
        shl     ebx,10
        and     ebx,0xffff0000
        mov     eax,[ds_ystep]
        shr     eax,6
        and     eax,0xffff
        or      ebx,eax

        mov     [obelix],ebx
        mov     [etaussi],esi

;; %eax      aligned colormap
;; %ebx      aligned colormap
;; %ecx,%edx  scratch
;; %esi      virtual source
;; %edi      moving destination pointer
;; %ebp      frac

        mov     eax,[ds_colormap]
        mov     ecx,ebp
        add     ebp,ebx                 ;; advance frac pointer
        shr     cx,10
        rol     ecx,6
        and     ecx,4095                ;; finish calculation for third pixel
        mov     edx,ebp
        shr     dx,10
        rol     edx,6
        add     ebp,ebx                 ;; advance frac pointer
        and     edx,4095                ;; finish calculation for fourth pixel
        mov     ebx,eax
        mov     al,[esi+ecx]            ;; get first pixel
        mov     bl,[esi+edx]            ;; get second pixel

        test dword [pixelcount],0xfffffffe

        mov     dl,[eax]                ;; color translate first pixel

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

        je      .hchecklast

        mov     dh,[ebx]                ;; color translate second pixel
        mov     esi,[loopcount]
align 4
.hdoubleloop:
        mov     ecx,ebp
        shr     cx,10
        rol     ecx,6
         add     ebp,[obelix]            ;; advance frac pointer
        mov     [edi],dx                ;; write first pixel
         and     ecx,4095                ;; finish calculation for third pixel
        mov     edx,ebp
        shr     dx,10
        rol     edx,6
         add     ecx,[etaussi]
        and     edx,4095                ;; finish calculation for fourth pixel
         mov     al,[ecx]                ;; get third pixel
        add     ebp,[obelix]            ;; advance frac pointer
         add     edx,[etaussi]
        mov     bl,[edx]                ;; get fourth pixel
         mov     dl,[eax]                ;; color translate third pixel
        add     edi,byte +0x2           ;; advance to third pixel destination
         dec     esi                     ;; done with loop?
        mov     dh,[ebx]                ;; color translate fourth pixel
         jne     .hdoubleloop
;; check for final pixel
.hchecklast:
        test dword [pixelcount],0x1
        je      .hdone
        mov     [edi],dl                ;; write final pixel
.hdone: pop     ebx                     ;; restore register variables
        pop     edi
        pop     esi
        pop     ebp                     ;; restore caller's stack frame pointer
        ret


;; ========================================================================
;;  Rasterization des segments d'un polyg�ne textur� de mani�re LINEAIRE.
;;  Il s'agit donc d'interpoler les coordonn�es aux bords de la texture en
;;  m�me temps que les abscisses minx/maxx pour chaque ligne.
;;  L'argument 'dir' indique quels bords de la texture sont interpol�s:
;;    0 : segments associ�s aux bord SUPERIEUR et INFERIEUR ( TY constant )
;;    1 : segments associ�s aux bord GAUCHE    et DROITE    ( TX constant )
;; ========================================================================
;;
;;  void   rasterize_segment_tex( LONG x1, LONG y1, LONG x2, LONG y2, LONG tv1, LONG tv2, LONG tc, LONG dir );
;;                                   ARG1     ARG2     ARG3     ARG4      ARG5      ARG6     ARG7       ARG8
;;
;;  Pour dir = 0, (tv1,tv2) = (tX1,tX2), tc = tY, en effet TY est constant.
;;
;;  Pour dir = 1, (tv1,tv2) = (tY1,tY2), tc = tX, en effet TX est constant.
;;
;;
;;  Uses:  extern struct rastery *_rastertab;
;;

[SECTION CODE_SEG write]

MINX            EQU    0
MAXX            EQU    4
TX1             EQU    8
TY1             EQU    12
TX2             EQU    16
TY2             EQU    20
RASTERY_SIZEOF  EQU    24

cglobal rasterize_segment_tex
rasterize_segment_tex:
        push    ebp
        mov     ebp,esp

        sub     esp,byte +0x8           ;; alloue les variables locales

        push    ebx
        push    esi
        push    edi
        o16 mov ax,es
        push    eax

;;        #define DX       [ebp-4]
;;        #define TD       [ebp-8]

        mov     eax,[ebp+0xc]           ;; y1
        mov     ebx,[ebp+0x14]          ;; y2
        cmp     ebx,eax
        je near .L_finished             ;; special (y1==y2) segment horizontal, exit!

        jg near .L_rasterize_right

;;rasterize_left:       ;; on rasterize un segment � la GAUCHE du polyg�ne

        mov     ecx,eax
        sub     ecx,ebx
        inc     ecx                     ;; y1-y2+1

        mov     eax,RASTERY_SIZEOF
        mul     ebx                     ;; * y2
        mov     esi,[prastertab]
        add     esi,eax                 ;; point into rastertab[y2]

        mov     eax,[ebp+0x8]           ;; ARG1
        sub     eax,[ebp+0x10]          ;; ARG3
        shl     eax,0x10                ;;     ((x1-x2)<<PRE) ...
        cdq
        idiv    ecx                     ;; dx =     ...        / (y1-y2+1)
        mov     [ebp-0x4],eax           ;; DX

        mov     eax,[ebp+0x18]          ;; ARG5
        sub     eax,[ebp+0x1c]          ;; ARG6
        shl     eax,0x10
        cdq
        idiv    ecx                     ;;      tdx =((tx1-tx2)<<PRE) / (y1-y2+1)
        mov     [ebp-0x8],eax           ;; idem tdy =((ty1-ty2)<<PRE) / (y1-y2+1)

        mov     eax,[ebp+0x10]          ;; ARG3
        shl     eax,0x10                ;; x = x2<<PRE

        mov     ebx,[ebp+0x1c]          ;; ARG6
        shl     ebx,0x10                ;; tx = tx2<<PRE    d0
                                        ;; ty = ty2<<PRE    d1
        mov     edx,[ebp+0x20]          ;; ARG7
        shl     edx,0x10                ;; ty = ty<<PRE     d0
                                        ;; tx = tx<<PRE     d1
        push    ebp
        mov     edi,[ebp-0x4]           ;; DX
        cmp     dword [ebp+0x24],byte +0x0      ;; ARG8   direction ?

        mov     ebp,[ebp-0x8]           ;; TD
        je      .L_rleft_h_loop
;;
;; TY varie, TX est constant
;;
.L_rleft_v_loop:
        mov     [esi+MINX],eax           ;; rastertab[y].minx = x
          add     ebx,ebp
        mov     [esi+TX1],edx           ;;             .tx1  = tx
          add     eax,edi
        mov     [esi+TY1],ebx           ;;             .ty1  = ty

        ;;addl    DX, %eax        // x     += dx
        ;;addl    TD, %ebx        // ty    += tdy

        add     esi,RASTERY_SIZEOF      ;; next raster line into rastertab[]
        dec     ecx
        jne     .L_rleft_v_loop
        pop     ebp
        jmp     .L_finished
;;
;; TX varie, TY est constant
;;
.L_rleft_h_loop:
        mov     [esi+MINX],eax           ;; rastertab[y].minx = x
          add     eax,edi
        mov     [esi+TX1],ebx           ;;             .tx1  = tx
          add     ebx,ebp
        mov     [esi+TY1],edx           ;;             .ty1  = ty

        ;;addl    DX, %eax        // x     += dx
        ;;addl    TD, %ebx        // tx    += tdx

        add     esi,RASTERY_SIZEOF      ;; next raster line into rastertab[]
        dec     ecx
        jne     .L_rleft_h_loop
        pop     ebp
        jmp     .L_finished
;;
;; on rasterize un segment � la DROITE du polyg�ne
;;
.L_rasterize_right:
        mov     ecx,ebx
        sub     ecx,eax
        inc     ecx                     ;; y2-y1+1

        mov     ebx,RASTERY_SIZEOF
        mul     ebx                     ;;   * y1
        mov     esi,[prastertab]
        add     esi,eax                 ;;  point into rastertab[y1]

        mov     eax,[ebp+0x10]          ;; ARG3
        sub     eax,[ebp+0x8]           ;; ARG1
        shl     eax,0x10                ;; ((x2-x1)<<PRE) ...
        cdq
        idiv    ecx                     ;;  dx =     ...        / (y2-y1+1)
        mov     [ebp-0x4],eax           ;; DX

        mov     eax,[ebp+0x1c]          ;; ARG6
        sub     eax,[ebp+0x18]          ;; ARG5
        shl     eax,0x10
        cdq
        idiv    ecx                     ;;       tdx =((tx2-tx1)<<PRE) / (y2-y1+1)
        mov     [ebp-0x8],eax           ;;  idem tdy =((ty2-ty1)<<PRE) / (y2-y1+1)

        mov     eax,[ebp+0x8]           ;; ARG1
        shl     eax,0x10                ;; x  = x1<<PRE

        mov     ebx,[ebp+0x18]          ;; ARG5
        shl     ebx,0x10                ;; tx = tx1<<PRE    d0
                                        ;; ty = ty1<<PRE    d1
        mov     edx,[ebp+0x20]          ;; ARG7
        shl     edx,0x10                ;; ty = ty<<PRE     d0
                                        ;; tx = tx<<PRE     d1
        push    ebp
        mov     edi,[ebp-0x4]           ;; DX

        cmp     dword [ebp+0x24], 0     ;; direction ?

         mov     ebp,[ebp-0x8]          ;; TD
        je      .L_rright_h_loop
;;
;; TY varie, TX est constant
;;
.L_rright_v_loop:

        mov     [esi+MAXX],eax           ;; rastertab[y].maxx = x
          add     ebx,ebp
        mov     [esi+TX2],edx          ;;             .tx2  = tx
          add     eax,edi
        mov     [esi+TY2],ebx          ;;             .ty2  = ty

        ;;addl    DX, %eax        // x     += dx
        ;;addl    TD, %ebx        // ty    += tdy

        add     esi,RASTERY_SIZEOF
        dec     ecx
        jne     .L_rright_v_loop

        pop     ebp

        jmp     short .L_finished
;;
;; TX varie, TY est constant
;;
.L_rright_h_loop:
        mov     [esi+MAXX],eax           ;; rastertab[y].maxx = x
          add     eax,edi
        mov     [esi+TX2],ebx          ;;             .tx2  = tx
          add     ebx,ebp
        mov     [esi+TY2],edx          ;;             .ty2  = ty

        ;;addl    DX, %eax        // x     += dx
        ;;addl    TD, %ebx        // tx    += tdx

        add     esi,RASTERY_SIZEOF
        dec     ecx
        jne     .L_rright_h_loop

        pop     ebp

.L_finished:
        pop     eax
        o16 mov es,ax
        pop     edi
        pop     esi
        pop     ebx

        mov     esp,ebp
        pop     ebp
        ret


;;; this version can draw 64x64 tiles, but they would have to be arranged 4 per row,
;; so that the stride from one line to the next is 256
;;
;; .data
;;xstep         dd      0
;;ystep         dd      0
;;texwidth      dd      64              ;; texture width
;; .text
;; this code is kept in case we add high-detail floor textures for example (256x256)
;       align   16
;_R_DrawSpan_8:
;       push ebp                        ;; preserve caller's stack frame pointer
;       push esi                        ;; preserve register variables
;       push edi
;       push ebx
;;
;; find loop count
;;
;       mov eax,[ds_x2]
;       inc eax
;       sub eax,[ds_x1]                 ;; pixel count
;       mov [pixelcount],eax            ;; save for final pixel
;       js near .hdone                  ;; nothing to scale
;;
;; calculate screen dest
;;
;       mov edi,[ds_y]
;       mov edi,[ylookup+edi*4]
;       mov eax,[ds_x1]
;       add edi,[columnofs+eax*4]
;;
;; prepare registers for inner loop
;;
;       xor eax,eax
;       mov edx,[ds_xfrac]
;       ror edx,16
;       mov al,dl
;       mov ecx,[ds_yfrac]
;       ror ecx,16
;       mov ah,cl
;
;       mov ebx,[ds_xstep]
;       ror ebx,16
;       mov ch,bl
;       and ebx,0xffff0000
;       mov [xstep],ebx
;       mov ebx,[ds_ystep]
;       ror ebx,16
;       mov dh,bl
;       and ebx,0xffff0000
;       mov [ystep],ebx
;
;       mov esi,[ds_source]
;
;;; %eax      Yi,Xi in %ah,%al
;;; %ebx      aligned colormap
;;; %ecx      Yfrac upper, dXi in %ch, %cl is counter (upto 1024pels, =4x256)
;;; %edx      Xfrac upper, dYi in %dh, %dl receives mapped pixels from (ebx)
;;;  ystep    dYfrac, add to %ecx, low word is 0
;;;  xstep    dXfrac, add to %edx, low word is 0
;;; %ebp      temporary register serves as offset like %eax
;;; %esi      virtual source
;;; %edi      moving destination pointer
;
;       mov ebx,[pixelcount]
;       shr ebx,0x2                     ;; 4 pixels per loop
;       test bl,0xff
;       je near .hchecklast
;       mov cl,bl
;
;       mov ebx,[dc_colormap]
;;;
;;; prepare loop with first pixel
;;;
;       add ecx,[ystep]                 ;;pr�a1
;       adc ah,dh
;       add edx,[xstep]
;       adc al,ch
;       and eax,0x3f3f
;       mov bl,[esi+eax]                ;;pr�b1
;       mov dl,[ebx]                    ;;pr�c1
;
;       add ecx,[ystep]                 ;;a2
;        adc ah,dh
;
;.hdoubleloop:
;       mov [edi+1],dl
;        add edx,[xstep]
;       adc al,ch
;        add edi,byte +0x2
;       mov ebp,eax
;        add ecx,[ystep]
;       adc ah,dh
;        and ebp,0x3f3f
;       add edx,[xstep]
;        mov bl,[esi+ebp]
;       adc al,ch
;        mov dl,[ebx]
;       and eax,0x3f3f
;        mov [edi],dl
;       mov bl,[esi+eax]
;        add ecx,[ystep]
;       adc ah,dh
;        add edx,[xstep]
;       adc al,ch
;        mov dl,[ebx]
;       mov ebp,eax
;        mov [edi+1],dl
;       and ebp,0x3f3f
;        add ecx,[ystep]
;       adc ah,dh
;        mov bl,[esi+ebp]
;       add edi,byte +0x2
;        add edx,[xstep]
;       adc al,ch
;        mov dl,[ebx]
;       and eax,0x3f3f
;        mov [edi],dl
;       mov bl,[esi+eax]
;        add ecx,[ystep]
;       adc ah,dh
;        mov dl,[ebx]
;       dec cl
;        jne near .hdoubleloop
;;; check for final pixel
;.hchecklast:
;;; to do
;.hdone:
;       pop ebx
;       pop edi
;       pop esi
;       pop ebp
;       ret