TexLoad16b.h

   1 /*
   2 *       Glide64 - Glide video plugin for Nintendo 64 emulators.
   3 *       Copyright (c) 2002  Dave2001
   4 *       Copyright (c) 2008  Günther <guenther.emu@freenet.de>
   5 *
   6 *       This program is free software; you can redistribute it and/or modify
   7 *       it under the terms of the GNU General Public License as published by
   8 *       the Free Software Foundation; either version 2 of the License, or
   9 *       any later version.
  10 *
  11 *       This program is distributed in the hope that it will be useful,
  12 *       but WITHOUT ANY WARRANTY; without even the implied warranty of
  13 *       MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  14 *       GNU General Public License for more details.
  15 *
  16 *       You should have received a copy of the GNU General Public License
  17 *       along with this program; if not, write to the Free Software
  18 *       Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  19 */
  20
  21 //****************************************************************
  22 //
  23 // Glide64 - Glide Plugin for Nintendo 64 emulators (tested mostly with Project64)
  24 // Project started on December 29th, 2001
  25 //
  26 // To modify Glide64:
  27 // * Write your name and (optional)email, commented by your work, so I know who did it, and so that you can find which parts you modified when it comes time to send it to me.
  28 // * Do NOT send me the whole project or file that you modified.  Take out your modified code sections, and tell me where to put them.  If people sent the whole thing, I would have many different versions, but no idea how to combine them all.
  29 //
  30 // Official Glide64 development channel: #Glide64 on EFnet
  31 //
  32 // Original author: Dave2001 (Dave2999@hotmail.com)
  33 // Other authors: Gonetz, Gugaman
  34 //
  35 //****************************************************************
  36
  37 //****************************************************************
  38 // Size: 2, Format: 0
  39
  40 DWORD Load16bRGBA (unsigned char * dst, unsigned char * src, int wid_64, int height, int line, int real_width, int tile)
  41 {
  42         if (wid_64 < 1) wid_64 = 1;
  43         if (height < 1) height = 1;
  44         int ext = (real_width - (wid_64 << 2)) << 1;
  45 #ifndef GCC
  46         __asm {
  47                 mov esi,dword ptr [src]
  48                 mov edi,dword ptr [dst]
  49
  50                 mov ecx,dword ptr [height]
  51 y_loop:
  52                 push ecx
  53
  54                 mov ecx,dword ptr [wid_64]
  55 x_loop:
  56                 mov eax,dword ptr [esi]         // read both pixels
  57                 add esi,4
  58                 bswap eax
  59                 mov edx,eax
  60
  61                 ror ax,1
  62                 ror eax,16
  63                 ror ax,1
  64
  65                 mov dword ptr [edi],eax
  66                 add edi,4
  67
  68                 // * copy
  69                 mov eax,dword ptr [esi]         // read both pixels
  70                 add esi,4
  71                 bswap eax
  72                 mov edx,eax
  73
  74                 ror ax,1
  75                 ror eax,16
  76                 ror ax,1
  77
  78                 mov dword ptr [edi],eax
  79                 add edi,4
  80                 // *
  81
  82                 dec ecx
  83                 jnz x_loop
  84
  85                 pop ecx
  86                 dec ecx
  87                 jz end_y_loop
  88                 push ecx
  89
  90                 add esi,dword ptr [line]
  91                 add edi,dword ptr [ext]
  92
  93                 mov ecx,dword ptr [wid_64]
  94 x_loop_2:
  95                 mov eax,dword ptr [esi+4]               // read both pixels
  96                 bswap eax
  97                 mov edx,eax
  98
  99                 ror ax,1
 100                 ror eax,16
 101                 ror ax,1
 102
 103                 mov dword ptr [edi],eax
 104                 add edi,4
 105
 106                 // * copy
 107                 mov eax,dword ptr [esi]         // read both pixels
 108                 add esi,8
 109                 bswap eax
 110                 mov edx,eax
 111
 112                 ror ax,1
 113                 ror eax,16
 114                 ror ax,1
 115
 116                 mov dword ptr [edi],eax
 117                 add edi,4
 118                 // *
 119
 120                 dec ecx
 121                 jnz x_loop_2
 122
 123                 add esi,dword ptr [line]
 124                 add edi,dword ptr [ext]
 125
 126                 pop ecx
 127                 dec ecx
 128                 jnz y_loop
 129
 130 end_y_loop:
 131         }
 132 #else // _WIN32
 133    //printf("Load16bRGBA\n");
 134    long lTemp, lHeight = (long) height;
 135    asm volatile (
 136                  "y_loop7:              \n"
 137          "mov %[c], %[temp]     \n"
 138
 139                  "mov %[wid_64], %%ecx \n"
 140                  "x_loop7:              \n"
 141                  "mov (%[src]), %%eax    \n"            // read both pixels
 142                  "add $4, %[src]         \n"
 143                  "bswap %%eax           \n"
 144                  "mov %%eax, %%edx      \n"
 145
 146                  "ror $1, %%ax          \n"
 147                  "ror $16, %%eax        \n"
 148                  "ror $1, %%ax          \n"
 149
 150                  "mov %%eax, (%[dst])    \n"
 151                  "add $4, %[dst]         \n"
 152
 153                  // * copy
 154                  "mov (%[src]), %%eax    \n"            // read both pixels
 155                  "add $4, %[src]         \n"
 156                  "bswap %%eax           \n"
 157                  "mov %%eax, %%edx      \n"
 158
 159                  "ror $1, %%ax          \n"
 160                  "ror $16, %%eax        \n"
 161                  "ror $1, %%ax          \n"
 162
 163                  "mov %%eax, (%[dst])    \n"
 164                  "add $4, %[dst]         \n"
 165                  // *
 166
 167                  "dec %%ecx             \n"
 168                  "jnz x_loop7           \n"
 169
 170          "mov %[temp], %[c]     \n"
 171                  "dec %%ecx             \n"
 172                  "jz end_y_loop7        \n"
 173          "mov %[c], %[temp]     \n"
 174
 175                  "add %[line], %[src]   \n"
 176                  "add %[ext], %[dst]    \n"
 177
 178                  "mov %[wid_64], %%ecx \n"
 179                  "x_loop_27:            \n"
 180                  "mov 4(%[src]), %%eax   \n"            // read both pixels
 181                  "bswap %%eax           \n"
 182                  "mov %%eax, %%edx      \n"
 183
 184                  "ror $1, %%ax          \n"
 185                  "ror $16, %%eax        \n"
 186                  "ror $1, %%ax          \n"
 187
 188                  "mov %%eax, (%[dst])    \n"
 189                  "add $4, %[dst]         \n"
 190
 191                  // * copy
 192                  "mov (%[src]), %%eax    \n"            // read both pixels
 193                  "add $8, %[src]         \n"
 194                  "bswap %%eax           \n"
 195                  "mov %%eax, %%edx      \n"
 196
 197                  "ror $1, %%ax          \n"
 198                  "ror $16, %%eax        \n"
 199                  "ror $1, %%ax          \n"
 200
 201                  "mov %%eax, (%[dst])    \n"
 202                  "add $4, %[dst]         \n"
 203                  // *
 204
 205                  "dec %%ecx             \n"
 206                  "jnz x_loop_27         \n"
 207
 208                  "add %[line], %[src]   \n"
 209                  "add %[ext], %[dst]    \n"
 210
 211          "mov %[temp], %[c]     \n"
 212                  "dec %%ecx             \n"
 213                  "jnz y_loop7           \n"
 214
 215                  "end_y_loop7:          \n"
 216                  : [temp]"=m"(lTemp), [src]"+S"(src), [dst]"+D"(dst), [c]"+c"(lHeight)
 217                  : [wid_64] "g" (wid_64), [line] "g" ((uintptr_t)line), [ext] "g" ((uintptr_t)ext)
 218                  : "memory", "cc", "eax", "edx"
 219                  );
 220 #endif // _WIN32
 221         return (1 << 16) | GR_TEXFMT_ARGB_1555;
 222 }
 223
 224 //****************************************************************
 225 // Size: 2, Format: 3
 226 //
 227 // ** by Gugaman/Dave2001 **
 228
 229 DWORD Load16bIA (unsigned char * dst, unsigned char * src, int wid_64, int height, int line, int real_width, int tile)
 230 {
 231         if (wid_64 < 1) wid_64 = 1;
 232         if (height < 1) height = 1;
 233         int ext = (real_width - (wid_64 << 2)) << 1;
 234 #ifndef GCC
 235         __asm {
 236                 mov esi,dword ptr [src]
 237                 mov edi,dword ptr [dst]
 238
 239                 mov ecx,dword ptr [height]
 240 y_loop:
 241                 push ecx
 242
 243                 mov ecx,dword ptr [wid_64]
 244 x_loop:
 245                 mov eax,dword ptr [esi]         // read both pixels
 246                 add esi,4
 247                 mov dword ptr [edi],eax
 248                 add edi,4
 249
 250                 // * copy
 251                 mov eax,dword ptr [esi]         // read both pixels
 252                 add esi,4
 253                 mov dword ptr [edi],eax
 254                 add edi,4
 255                 // *
 256
 257                 dec ecx
 258                 jnz x_loop
 259
 260                 pop ecx
 261                 dec ecx
 262                 jz end_y_loop
 263                 push ecx
 264
 265                 add esi,dword ptr [line]
 266                 add edi,dword ptr [ext]
 267
 268                 mov ecx,dword ptr [wid_64]
 269 x_loop_2:
 270                 mov eax,dword ptr [esi+4]               // read both pixels
 271                 mov dword ptr [edi],eax
 272                 add edi,4
 273
 274                 // * copy
 275                 mov eax,dword ptr [esi]         // read both pixels
 276                 add esi,8
 277                 mov dword ptr [edi],eax
 278                 add edi,4
 279                 // *
 280
 281                 dec ecx
 282                 jnz x_loop_2
 283
 284                 add esi,dword ptr [line]
 285                 add edi,dword ptr [ext]
 286
 287                 pop ecx
 288                 dec ecx
 289                 jnz y_loop
 290
 291 end_y_loop:
 292         }
 293 #else // _WIN32
 294    //printf("Load16bIA\n");
 295    long lTemp, lHeight = (long) height;
 296    asm volatile (
 297                  "y_loop8:              \n"
 298          "mov %[c], %[temp]     \n"
 299
 300                  "mov %[wid_64], %%ecx \n"
 301                  "x_loop8:              \n"
 302                  "mov (%[src]), %%eax    \n"            // read both pixels
 303                  "add $4, %[src]         \n"
 304                  "mov %%eax, (%[dst])    \n"
 305                  "add $4, %[dst]         \n"
 306
 307                  // * copy
 308                  "mov (%[src]), %%eax    \n"            // read both pixels
 309                  "add $4, %[src]         \n"
 310                  "mov %%eax, (%[dst])    \n"
 311                  "add $4, %[dst]         \n"
 312                  // *
 313
 314                  "dec %%ecx             \n"
 315                  "jnz x_loop8           \n"
 316
 317          "mov %[temp], %[c]     \n"
 318                  "dec %%ecx             \n"
 319                  "jz end_y_loop8        \n"
 320          "mov %[c], %[temp]     \n"
 321
 322                  "add %[line], %[src]   \n"
 323                  "add %[ext], %[dst]    \n"
 324
 325                  "mov %[wid_64], %%ecx \n"
 326                  "x_loop_28:            \n"
 327                  "mov 4(%[src]), %%eax   \n"            // read both pixels
 328                  "mov %%eax, (%[dst])    \n"
 329                  "add $4, %[dst]         \n"
 330
 331                  // * copy
 332                  "mov (%[src]), %%eax    \n"            // read both pixels
 333                  "add $8, %[src]         \n"
 334                  "mov %%eax, (%[dst])    \n"
 335                  "add $4, %[dst]         \n"
 336                  // *
 337
 338                  "dec %%ecx             \n"
 339                  "jnz x_loop_28         \n"
 340
 341                  "add %[line], %[src]   \n"
 342                  "add %[ext], %[dst]    \n"
 343
 344          "mov %[temp], %[c]     \n"
 345                  "dec %%ecx             \n"
 346                  "jnz y_loop8           \n"
 347
 348                  "end_y_loop8:          \n"
 349                  : [temp]"=m"(lTemp), [src]"+S"(src), [dst]"+D"(dst), [c]"+c"(lHeight)
 350                  : [wid_64] "g" (wid_64), [line] "g" ((uintptr_t)line), [ext] "g" ((uintptr_t)ext)
 351                  : "memory", "cc", "eax"
 352                  );
 353 #endif // _WIN32
 354         return (1 << 16) | GR_TEXFMT_ALPHA_INTENSITY_88;
 355 }
 356