Parent Directory
| 
Revision Log
Revision 651 - (view) (download)
| 1 : | chl | 434 | ;/***************************************************************************** |
| 2 : | ; * | ||
| 3 : | ; * XVID MPEG-4 VIDEO CODEC | ||
| 4 : | ; * mmx yuv planar to rgb conversion | ||
| 5 : | ; * | ||
| 6 : | ; * Copyright (C) 2001 - Michael Militzer <isibaar@xvid.org> | ||
| 7 : | ; * | ||
| 8 : | edgomez | 651 | ; * This file is part of XviD, a free MPEG-4 video encoder/decoder |
| 9 : | chl | 434 | ; * |
| 10 : | edgomez | 651 | ; * XviD is free software; you can redistribute it and/or modify it |
| 11 : | ; * under the terms of the GNU General Public License as published by | ||
| 12 : | chl | 434 | ; * the Free Software Foundation; either version 2 of the License, or |
| 13 : | ; * (at your option) any later version. | ||
| 14 : | ; * | ||
| 15 : | ; * This program is distributed in the hope that it will be useful, | ||
| 16 : | ; * but WITHOUT ANY WARRANTY; without even the implied warranty of | ||
| 17 : | ; * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | ||
| 18 : | ; * GNU General Public License for more details. | ||
| 19 : | ; * | ||
| 20 : | ; * You should have received a copy of the GNU General Public License | ||
| 21 : | ; * along with this program; if not, write to the Free Software | ||
| 22 : | ; * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA | ||
| 23 : | ; * | ||
| 24 : | edgomez | 651 | ; * Under section 8 of the GNU General Public License, the copyright |
| 25 : | ; * holders of XVID explicitly forbid distribution in the following | ||
| 26 : | ; * countries: | ||
| 27 : | chl | 434 | ; * |
| 28 : | edgomez | 651 | ; * - Japan |
| 29 : | ; * - United States of America | ||
| 30 : | ; * | ||
| 31 : | ; * Linking XviD statically or dynamically with other modules is making a | ||
| 32 : | ; * combined work based on XviD. Thus, the terms and conditions of the | ||
| 33 : | ; * GNU General Public License cover the whole combination. | ||
| 34 : | ; * | ||
| 35 : | ; * As a special exception, the copyright holders of XviD give you | ||
| 36 : | ; * permission to link XviD with independent modules that communicate with | ||
| 37 : | ; * XviD solely through the VFW1.1 and DShow interfaces, regardless of the | ||
| 38 : | ; * license terms of these independent modules, and to copy and distribute | ||
| 39 : | ; * the resulting combined work under terms of your choice, provided that | ||
| 40 : | ; * every copy of the combined work is accompanied by a complete copy of | ||
| 41 : | ; * the source code of XviD (the version of XviD used to produce the | ||
| 42 : | ; * combined work), being distributed under the terms of the GNU General | ||
| 43 : | ; * Public License plus this exception. An independent module is a module | ||
| 44 : | ; * which is not derived from or based on XviD. | ||
| 45 : | ; * | ||
| 46 : | ; * Note that people who make modified versions of XviD are not obligated | ||
| 47 : | ; * to grant this special exception for their modified versions; it is | ||
| 48 : | ; * their choice whether to do so. The GNU General Public License gives | ||
| 49 : | ; * permission to release a modified version without this exception; this | ||
| 50 : | ; * exception also makes it possible to release a modified version which | ||
| 51 : | ; * carries forward this exception. | ||
| 52 : | ; * | ||
| 53 : | ; * $Id: yv12_to_rgb32_mmx.asm,v 1.4 2002-11-17 00:20:30 edgomez Exp $ | ||
| 54 : | ; * | ||
| 55 : | chl | 434 | ; ****************************************************************************/ |
| 56 : | edgomez | 332 | ; |
| 57 : | ;------------------------------------------------------------------------------ | ||
| 58 : | ; NB: n contrary to the c implementation this code does the conversion | ||
| 59 : | ; using direct calculations. Input data width must be a multiple of 8 | ||
| 60 : | ; and height must be even. | ||
| 61 : | ; This implementation is less precise than the c version but is | ||
| 62 : | ; more than twice as fast :-) | ||
| 63 : | ;------------------------------------------------------------------------------ | ||
| 64 : | |||
| 65 : | BITS 32 | ||
| 66 : | |||
| 67 : | |||
| 68 : | %macro cglobal 1 | ||
| 69 : | %ifdef PREFIX | ||
| 70 : | global _%1 | ||
| 71 : | %define %1 _%1 | ||
| 72 : | %else | ||
| 73 : | global %1 | ||
| 74 : | %endif | ||
| 75 : | %endmacro | ||
| 76 : | |||
| 77 : | |||
| 78 : | %define SCALEBITS 6 | ||
| 79 : | |||
| 80 : | |||
| 81 : | ALIGN 16 | ||
| 82 : | |||
| 83 : | SECTION .data | ||
| 84 : | |||
| 85 : | Y_SUB dw 16, 16, 16, 16 | ||
| 86 : | U_SUB dw 128, 128, 128, 128 | ||
| 87 : | V_SUB dw 128, 128, 128, 128 | ||
| 88 : | |||
| 89 : | Y_MUL dw 74, 74, 74, 74 | ||
| 90 : | |||
| 91 : | UG_MUL dw 25, 25, 25, 25 | ||
| 92 : | VG_MUL dw 52, 52, 52, 52 | ||
| 93 : | |||
| 94 : | UB_MUL dw 129, 129, 129, 129 | ||
| 95 : | VR_MUL dw 102, 102, 102, 102 | ||
| 96 : | |||
| 97 : | |||
| 98 : | ALIGN 16 | ||
| 99 : | |||
| 100 : | SECTION .text | ||
| 101 : | |||
| 102 : | ;------------------------------------------------------------------------------ | ||
| 103 : | ; | ||
| 104 : | ; void yv12_to_rgb32_mmx(uint8_t *dst, | ||
| 105 : | ; int dst_stride, | ||
| 106 : | ; uint8_t *y_src, | ||
| 107 : | ; uint8_t *u_src, | ||
| 108 : | ; uint8_t *v_src, | ||
| 109 : | ; int y_stride, int uv_stride, | ||
| 110 : | ; int width, int height); | ||
| 111 : | ; | ||
| 112 : | ;------------------------------------------------------------------------------ | ||
| 113 : | |||
| 114 : | cglobal yv12_to_rgb32_mmx | ||
| 115 : | yv12_to_rgb32_mmx: | ||
| 116 : | |||
| 117 : | push ebx | ||
| 118 : | push esi | ||
| 119 : | push edi | ||
| 120 : | push ebp | ||
| 121 : | |||
| 122 : | ; local vars alloc | ||
| 123 : | %define localsize 72 | ||
| 124 : | %define TEMP_Y1 esp | ||
| 125 : | %define TEMP_Y2 esp + 8 | ||
| 126 : | %define TEMP_G1 esp + 16 | ||
| 127 : | %define TEMP_G2 esp + 24 | ||
| 128 : | %define TEMP_B1 esp + 32 | ||
| 129 : | %define TEMP_B2 esp + 40 | ||
| 130 : | %define y_dif esp + 48 | ||
| 131 : | %define dst_dif esp + 52 | ||
| 132 : | %define uv_dif esp + 56 | ||
| 133 : | %define height esp + 60 | ||
| 134 : | %define width_8 esp + 64 | ||
| 135 : | %define height_2 esp + 68 | ||
| 136 : | sub esp, localsize | ||
| 137 : | |||
| 138 : | ; function code | ||
| 139 : | mov eax, [esp + 52 + localsize] ; height -> eax | ||
| 140 : | cmp eax, 0x00 | ||
| 141 : | jge near dont_flip ; flip? | ||
| 142 : | |||
| 143 : | neg eax ; neg height | ||
| 144 : | mov [height], eax | ||
| 145 : | |||
| 146 : | mov esi, [esp + 48 + localsize] ; width -> esi | ||
| 147 : | |||
| 148 : | mov ebp, [esp + 40 + localsize] ; y_stride -> ebp | ||
| 149 : | mov ebx, ebp | ||
| 150 : | shl ebx, 1 ; 2 * y_stride -> ebx | ||
| 151 : | neg ebx | ||
| 152 : | sub ebx, esi ; y_dif -> eax | ||
| 153 : | |||
| 154 : | mov [y_dif], ebx | ||
| 155 : | |||
| 156 : | sub eax, 1 ; height - 1 -> eax | ||
| 157 : | mul ebp ; (height - 1) * y_stride -> ebp | ||
| 158 : | mov ecx, eax | ||
| 159 : | mov eax, [esp + 28 + localsize] ; y_src -> eax | ||
| 160 : | add eax, ecx ; y_src -> eax | ||
| 161 : | mov ebx, eax | ||
| 162 : | sub ebx, ebp ; y_src2 -> ebx | ||
| 163 : | |||
| 164 : | mov ecx, [esp + 24 + localsize] ; dst_stride -> ecx | ||
| 165 : | mov edx, ecx | ||
| 166 : | shl edx, 3 | ||
| 167 : | mov ecx, edx ; 8 * dst_stride -> ecx | ||
| 168 : | shl esi, 2 | ||
| 169 : | sub ecx, esi ; 8 * dst_stride - 4 * width -> ecx | ||
| 170 : | |||
| 171 : | mov [dst_dif], ecx | ||
| 172 : | |||
| 173 : | mov esi, [esp + 20 + localsize] ; dst -> esi | ||
| 174 : | mov edi, esi | ||
| 175 : | shr edx, 1 | ||
| 176 : | add edi, edx ; dst2 -> edi | ||
| 177 : | |||
| 178 : | mov ebp, [esp + 48 + localsize] ; width -> ebp | ||
| 179 : | mov ecx, ebp ; width -> ecx | ||
| 180 : | shr ecx, 1 | ||
| 181 : | shr ebp, 3 ; width / 8 -> ebp | ||
| 182 : | mov [width_8], ebp | ||
| 183 : | |||
| 184 : | mov ebp, [esp + 44 + localsize] ; uv_stride -> ebp | ||
| 185 : | mov edx, ebp | ||
| 186 : | neg edx | ||
| 187 : | sub edx, ecx | ||
| 188 : | mov [uv_dif], edx | ||
| 189 : | |||
| 190 : | mov edx, ebp | ||
| 191 : | mov ebp, eax | ||
| 192 : | mov eax, [height] ; height -> eax | ||
| 193 : | shr eax, 1 ; height / 2 -> eax | ||
| 194 : | |||
| 195 : | mov ecx, [esp + 32 + localsize] ; u_src -> ecx | ||
| 196 : | sub eax, 1 | ||
| 197 : | mul edx | ||
| 198 : | add ecx, eax | ||
| 199 : | |||
| 200 : | mov edx, [esp + 36 + localsize] ; v_src -> edx | ||
| 201 : | add edx, eax | ||
| 202 : | |||
| 203 : | mov eax, ebp | ||
| 204 : | |||
| 205 : | mov ebp, [height] ; height -> ebp | ||
| 206 : | shr ebp, 1 ; height / 2 -> ebp | ||
| 207 : | |||
| 208 : | pxor mm7, mm7 | ||
| 209 : | jmp y_loop | ||
| 210 : | |||
| 211 : | |||
| 212 : | dont_flip: | ||
| 213 : | mov esi, [esp + 48 + localsize] ; width -> esi | ||
| 214 : | |||
| 215 : | mov ebp, [esp + 40 + localsize] ; y_stride -> ebp | ||
| 216 : | mov ebx, ebp | ||
| 217 : | shl ebx, 1 ; 2 * y_stride -> ebx | ||
| 218 : | sub ebx, esi ; y_dif -> ebx | ||
| 219 : | |||
| 220 : | mov [y_dif], ebx | ||
| 221 : | |||
| 222 : | mov eax, [esp + 28 + localsize] ; y_src -> eax | ||
| 223 : | mov ebx, eax | ||
| 224 : | add ebx, ebp ; y_src2 -> ebp | ||
| 225 : | |||
| 226 : | mov ecx, [esp + 24 + localsize] ; dst_stride -> ecx | ||
| 227 : | shl ecx, 3 | ||
| 228 : | mov edx, ecx ; 8 * dst_stride -> edx | ||
| 229 : | shl esi, 2 | ||
| 230 : | sub ecx, esi ; 8 * dst_stride - 4 * width -> ecx | ||
| 231 : | |||
| 232 : | mov [dst_dif], ecx | ||
| 233 : | |||
| 234 : | mov esi, [esp + 20 + localsize] ; dst -> esi | ||
| 235 : | mov edi, esi | ||
| 236 : | shr edx, 1 | ||
| 237 : | add edi, edx ; dst2 -> edi | ||
| 238 : | |||
| 239 : | mov ebp, [esp + 48 + localsize] ; width -> ebp | ||
| 240 : | mov ecx, ebp ; width -> ecx | ||
| 241 : | shr ecx, 1 | ||
| 242 : | shr ebp, 3 ; width / 8 -> ebp | ||
| 243 : | mov [width_8], ebp | ||
| 244 : | |||
| 245 : | mov ebp, [esp + 44 + localsize] ; uv_stride -> ebp | ||
| 246 : | sub ebp, ecx | ||
| 247 : | mov [uv_dif], ebp | ||
| 248 : | |||
| 249 : | mov ecx, [esp + 32 + localsize] ; u_src -> ecx | ||
| 250 : | mov edx, [esp + 36 + localsize] ; v_src -> edx | ||
| 251 : | |||
| 252 : | mov ebp, [esp + 52 + localsize] ; height -> ebp | ||
| 253 : | shr ebp, 1 ; height / 2 -> ebp | ||
| 254 : | |||
| 255 : | pxor mm7, mm7 | ||
| 256 : | |||
| 257 : | y_loop: | ||
| 258 : | mov [height_2], ebp | ||
| 259 : | mov ebp, [width_8] | ||
| 260 : | |||
| 261 : | x_loop: | ||
| 262 : | movd mm2, [ecx] | ||
| 263 : | movd mm3, [edx] | ||
| 264 : | |||
| 265 : | punpcklbw mm2, mm7 ; u3u2u1u0 -> mm2 | ||
| 266 : | punpcklbw mm3, mm7 ; v3v2v1v0 -> mm3 | ||
| 267 : | |||
| 268 : | psubsw mm2, [U_SUB] ; U - 128 | ||
| 269 : | psubsw mm3, [V_SUB] ; V - 128 | ||
| 270 : | |||
| 271 : | movq mm4, mm2 | ||
| 272 : | movq mm5, mm3 | ||
| 273 : | |||
| 274 : | pmullw mm2, [UG_MUL] | ||
| 275 : | pmullw mm3, [VG_MUL] | ||
| 276 : | |||
| 277 : | movq mm6, mm2 ; u3u2u1u0 -> mm6 | ||
| 278 : | punpckhwd mm2, mm2 ; u3u3u2u2 -> mm2 | ||
| 279 : | punpcklwd mm6, mm6 ; u1u1u0u0 -> mm6 | ||
| 280 : | |||
| 281 : | pmullw mm4, [UB_MUL] ; B_ADD -> mm4 | ||
| 282 : | |||
| 283 : | movq mm0, mm3 | ||
| 284 : | punpckhwd mm3, mm3 ; v3v3v2v2 -> mm2 | ||
| 285 : | punpcklwd mm0, mm0 ; v1v1v0v0 -> mm6 | ||
| 286 : | |||
| 287 : | paddsw mm2, mm3 | ||
| 288 : | paddsw mm6, mm0 | ||
| 289 : | |||
| 290 : | pmullw mm5, [VR_MUL] ; R_ADD -> mm5 | ||
| 291 : | |||
| 292 : | movq mm0, [eax] ; y7y6y5y4y3y2y1y0 -> mm0 | ||
| 293 : | |||
| 294 : | movq mm1, mm0 | ||
| 295 : | punpckhbw mm1, mm7 ; y7y6y5y4 -> mm1 | ||
| 296 : | punpcklbw mm0, mm7 ; y3y2y1y0 -> mm0 | ||
| 297 : | |||
| 298 : | psubsw mm0, [Y_SUB] ; Y - Y_SUB | ||
| 299 : | psubsw mm1, [Y_SUB] ; Y - Y_SUB | ||
| 300 : | |||
| 301 : | pmullw mm1, [Y_MUL] | ||
| 302 : | pmullw mm0, [Y_MUL] | ||
| 303 : | |||
| 304 : | movq [TEMP_Y2], mm1 ; y7y6y5y4 -> mm3 | ||
| 305 : | movq [TEMP_Y1], mm0 ; y3y2y1y0 -> mm7 | ||
| 306 : | |||
| 307 : | psubsw mm1, mm2 ; g7g6g5g4 -> mm1 | ||
| 308 : | psubsw mm0, mm6 ; g3g2g1g0 -> mm0 | ||
| 309 : | |||
| 310 : | psraw mm1, SCALEBITS | ||
| 311 : | psraw mm0, SCALEBITS | ||
| 312 : | |||
| 313 : | packuswb mm0, mm1 ;g7g6g5g4g3g2g1g0 -> mm0 | ||
| 314 : | |||
| 315 : | movq [TEMP_G1], mm0 | ||
| 316 : | |||
| 317 : | movq mm0, [ebx] ; y7y6y5y4y3y2y1y0 -> mm0 | ||
| 318 : | |||
| 319 : | movq mm1, mm0 | ||
| 320 : | |||
| 321 : | punpckhbw mm1, mm7 ; y7y6y5y4 -> mm1 | ||
| 322 : | punpcklbw mm0, mm7 ; y3y2y1y0 -> mm0 | ||
| 323 : | |||
| 324 : | psubsw mm0, [Y_SUB] ; Y - Y_SUB | ||
| 325 : | psubsw mm1, [Y_SUB] ; Y - Y_SUB | ||
| 326 : | |||
| 327 : | pmullw mm1, [Y_MUL] | ||
| 328 : | pmullw mm0, [Y_MUL] | ||
| 329 : | |||
| 330 : | movq mm3, mm1 | ||
| 331 : | psubsw mm1, mm2 ; g7g6g5g4 -> mm1 | ||
| 332 : | |||
| 333 : | movq mm2, mm0 | ||
| 334 : | psubsw mm0, mm6 ; g3g2g1g0 -> mm0 | ||
| 335 : | |||
| 336 : | psraw mm1, SCALEBITS | ||
| 337 : | psraw mm0, SCALEBITS | ||
| 338 : | |||
| 339 : | packuswb mm0, mm1 ; g7g6g5g4g3g2g1g0 -> mm0 | ||
| 340 : | |||
| 341 : | movq [TEMP_G2], mm0 | ||
| 342 : | |||
| 343 : | movq mm0, mm4 | ||
| 344 : | punpckhwd mm4, mm4 ; u3u3u2u2 -> mm2 | ||
| 345 : | punpcklwd mm0, mm0 ; u1u1u0u0 -> mm6 | ||
| 346 : | |||
| 347 : | movq mm1, mm3 ; y7y6y5y4 -> mm1 | ||
| 348 : | paddsw mm3, mm4 ; b7b6b5b4 -> mm3 | ||
| 349 : | |||
| 350 : | movq mm7, mm2 ; y3y2y1y0 -> mm7 | ||
| 351 : | |||
| 352 : | paddsw mm2, mm0 ; b3b2b1b0 -> mm2 | ||
| 353 : | |||
| 354 : | psraw mm3, SCALEBITS | ||
| 355 : | psraw mm2, SCALEBITS | ||
| 356 : | |||
| 357 : | packuswb mm2, mm3 ; b7b6b5b4b3b2b1b0 -> mm2 | ||
| 358 : | |||
| 359 : | movq [TEMP_B2], mm2 | ||
| 360 : | |||
| 361 : | movq mm3, [TEMP_Y2] | ||
| 362 : | movq mm2, [TEMP_Y1] | ||
| 363 : | |||
| 364 : | movq mm6, mm3 ; TEMP_Y2 -> mm6 | ||
| 365 : | paddsw mm3, mm4 ; b7b6b5b4 -> mm3 | ||
| 366 : | |||
| 367 : | movq mm4, mm2 ; TEMP_Y1 -> mm4 | ||
| 368 : | paddsw mm2, mm0 ; b3b2b1b0 -> mm2 | ||
| 369 : | |||
| 370 : | psraw mm3, SCALEBITS | ||
| 371 : | psraw mm2, SCALEBITS | ||
| 372 : | |||
| 373 : | packuswb mm2, mm3 ; b7b6b5b4b3b2b1b0 -> mm2 | ||
| 374 : | |||
| 375 : | movq [TEMP_B1], mm2 | ||
| 376 : | |||
| 377 : | movq mm0, mm5 | ||
| 378 : | punpckhwd mm5, mm5 ; v3v3v2v2 -> mm5 | ||
| 379 : | punpcklwd mm0, mm0 ; v1v1v0v0 -> mm0 | ||
| 380 : | |||
| 381 : | paddsw mm1, mm5 ; r7r6r5r4 -> mm1 | ||
| 382 : | paddsw mm7, mm0 ; r3r2r1r0 -> mm7 | ||
| 383 : | |||
| 384 : | psraw mm1, SCALEBITS | ||
| 385 : | psraw mm7, SCALEBITS | ||
| 386 : | |||
| 387 : | packuswb mm7, mm1 ; r7r6r5r4r3r2r1r0 -> mm7 (TEMP_R2) | ||
| 388 : | |||
| 389 : | paddsw mm6, mm5 ; r7r6r5r4 -> mm6 | ||
| 390 : | paddsw mm4, mm0 ; r3r2r1r0 -> mm4 | ||
| 391 : | |||
| 392 : | psraw mm6, SCALEBITS | ||
| 393 : | psraw mm4, SCALEBITS | ||
| 394 : | |||
| 395 : | packuswb mm4, mm6 ; r7r6r5r4r3r2r1r0 -> mm4 (TEMP_R1) | ||
| 396 : | |||
| 397 : | movq mm0, [TEMP_B1] | ||
| 398 : | movq mm1, [TEMP_G1] | ||
| 399 : | |||
| 400 : | movq mm6, mm7 | ||
| 401 : | |||
| 402 : | movq mm2, mm0 | ||
| 403 : | punpcklbw mm2, mm4 ; r3b3r2b2r1b1r0b0 -> mm2 | ||
| 404 : | punpckhbw mm0, mm4 ; r7b7r6b6r5b5r4b4 -> mm0 | ||
| 405 : | |||
| 406 : | pxor mm7, mm7 | ||
| 407 : | |||
| 408 : | movq mm3, mm1 | ||
| 409 : | punpcklbw mm1, mm7 ; 0g30g20g10g0 -> mm1 | ||
| 410 : | punpckhbw mm3, mm7 ; 0g70g60g50g4 -> mm3 | ||
| 411 : | |||
| 412 : | movq mm4, mm2 | ||
| 413 : | punpcklbw mm2, mm1 ; 0r1g1b10r0g0b0 -> mm2 | ||
| 414 : | punpckhbw mm4, mm1 ; 0r3g3b30r2g2b2 -> mm4 | ||
| 415 : | |||
| 416 : | movq mm5, mm0 | ||
| 417 : | punpcklbw mm0, mm3 ; 0r5g5b50r4g4b4 -> mm0 | ||
| 418 : | punpckhbw mm5, mm3 ; 0r7g7b70r6g6b6 -> mm5 | ||
| 419 : | |||
| 420 : | movq [esi], mm2 | ||
| 421 : | movq [esi + 8], mm4 | ||
| 422 : | movq [esi + 16], mm0 | ||
| 423 : | movq [esi + 24], mm5 | ||
| 424 : | |||
| 425 : | movq mm0, [TEMP_B2] | ||
| 426 : | movq mm1, [TEMP_G2] | ||
| 427 : | |||
| 428 : | movq mm2, mm0 | ||
| 429 : | punpcklbw mm2, mm6 ; r3b3r2b2r1b1r0b0 -> mm2 | ||
| 430 : | punpckhbw mm0, mm6 ; r7b7r6b6r5b5r4b4 -> mm0 | ||
| 431 : | |||
| 432 : | movq mm3, mm1 | ||
| 433 : | punpcklbw mm1, mm7 ; 0g30g20g10g0 -> mm1 | ||
| 434 : | punpckhbw mm3, mm7 ; 0g70g60g50g4 -> mm3 | ||
| 435 : | |||
| 436 : | movq mm4, mm2 | ||
| 437 : | punpcklbw mm2, mm1 ; 0r1g1b10r0g0b0 -> mm2 | ||
| 438 : | punpckhbw mm4, mm1 ; 0r3g3b30r2g2b2 -> mm4 | ||
| 439 : | |||
| 440 : | movq mm5, mm0 | ||
| 441 : | punpcklbw mm0, mm3 ; 0r5g5b50r4g4b4 -> mm0 | ||
| 442 : | punpckhbw mm5, mm3 ; 0r7g7b70r6g6b6 -> mm5 | ||
| 443 : | |||
| 444 : | movq [edi], mm2 | ||
| 445 : | movq [edi + 8], mm4 | ||
| 446 : | movq [edi + 16], mm0 | ||
| 447 : | movq [edi + 24], mm5 | ||
| 448 : | |||
| 449 : | add esi, 32 | ||
| 450 : | add edi, 32 | ||
| 451 : | |||
| 452 : | add eax, 8 | ||
| 453 : | add ebx, 8 | ||
| 454 : | add ecx, 4 | ||
| 455 : | add edx, 4 | ||
| 456 : | |||
| 457 : | dec ebp | ||
| 458 : | |||
| 459 : | jnz near x_loop | ||
| 460 : | |||
| 461 : | add esi, [dst_dif] | ||
| 462 : | add edi, [dst_dif] | ||
| 463 : | |||
| 464 : | add eax, [y_dif] | ||
| 465 : | add ebx, [y_dif] | ||
| 466 : | |||
| 467 : | add ecx, [uv_dif] | ||
| 468 : | add edx, [uv_dif] | ||
| 469 : | |||
| 470 : | mov ebp, [height_2] | ||
| 471 : | dec ebp | ||
| 472 : | jnz near y_loop | ||
| 473 : | |||
| 474 : | emms | ||
| 475 : | |||
| 476 : | ;; Local vars deallocation | ||
| 477 : | add esp, localsize | ||
| 478 : | %undef TEMP_Y1 | ||
| 479 : | %undef TEMP_Y2 | ||
| 480 : | %undef TEMP_G1 | ||
| 481 : | %undef TEMP_G2 | ||
| 482 : | %undef TEMP_B1 | ||
| 483 : | %undef TEMP_B2 | ||
| 484 : | %undef y_dif | ||
| 485 : | %undef dst_dif | ||
| 486 : | %undef uv_dif | ||
| 487 : | %undef height | ||
| 488 : | %undef width_8 | ||
| 489 : | %undef height_2 | ||
| 490 : | %undef localsize | ||
| 491 : | |||
| 492 : | pop ebp | ||
| 493 : | pop edi | ||
| 494 : | pop esi | ||
| 495 : | pop ebx | ||
| 496 : | |||
| 497 : | ret |
| No admin address has been configured | ViewVC Help |
| Powered by ViewVC 1.0.4 |