Parent Directory | Revision Log
Revision 651 -
(view)
(download)
Original Path: trunk/xvidcore/src/image/x86_asm/yv12_to_rgb24_mmx.asm
1 : | chl | 434 | ;/***************************************************************************** |
2 : | ; * | ||
3 : | ; * XVID MPEG-4 VIDEO CODEC | ||
4 : | ; * mmx yv12 to rgb24 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 : | ; * | ||
28 : | ; * - 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_rgb24_mmx.asm,v 1.4 2002-11-17 00:20:30 edgomez Exp $ | ||
54 : | ; * | ||
55 : | chl | 434 | ; ****************************************************************************/ |
56 : | edgomez | 330 | ; |
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_rgb24_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_rgb24_mmx | ||
115 : | yv12_to_rgb24_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 : | |||
139 : | mov eax, [esp + 52 + localsize] ; height -> eax | ||
140 : | cmp eax, 0x00 | ||
141 : | jge near dont_flip ; flip? | ||
142 : | |||
143 : | neg eax | ||
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 : | add ecx, edx | ||
167 : | shl edx, 2 | ||
168 : | add ecx, edx ; 6 * dst_stride -> ecx | ||
169 : | mov edx, ecx | ||
170 : | sub ecx, esi | ||
171 : | shl esi, 1 | ||
172 : | sub ecx, esi ; 6 * dst_stride - 3 * width -> ecx | ||
173 : | |||
174 : | mov [dst_dif], ecx | ||
175 : | |||
176 : | mov esi, [esp + 20 + localsize] ; dst -> esi | ||
177 : | mov edi, esi | ||
178 : | shr edx, 1 | ||
179 : | add edi, edx ; dst2 -> edi | ||
180 : | |||
181 : | mov ebp, [esp + 48 + localsize] ; width -> ebp | ||
182 : | mov ecx, ebp ; width -> ecx | ||
183 : | shr ecx, 1 | ||
184 : | shr ebp, 3 ; width / 8 -> ebp | ||
185 : | mov [width_8], ebp | ||
186 : | |||
187 : | mov ebp, [esp + 44 + localsize] ; uv_stride -> ebp | ||
188 : | mov edx, ebp | ||
189 : | neg edx | ||
190 : | sub edx, ecx | ||
191 : | mov [uv_dif], edx | ||
192 : | |||
193 : | mov edx, ebp | ||
194 : | mov ebp, eax | ||
195 : | mov eax, [height] ; height -> eax | ||
196 : | shr eax, 1 ; height / 2 -> eax | ||
197 : | |||
198 : | mov ecx, [esp + 32 + localsize] ; u_src -> ecx | ||
199 : | sub eax, 1 | ||
200 : | mul edx | ||
201 : | add ecx, eax | ||
202 : | |||
203 : | mov edx, [esp + 36 + localsize] ; v_src -> edx | ||
204 : | add edx, eax | ||
205 : | |||
206 : | mov eax, ebp | ||
207 : | |||
208 : | mov ebp, [height] ; height -> ebp | ||
209 : | shr ebp, 1 ; height / 2 -> ebp | ||
210 : | |||
211 : | pxor mm7, mm7 ; clear mm7 | ||
212 : | jmp y_loop | ||
213 : | |||
214 : | |||
215 : | dont_flip: | ||
216 : | mov esi, [esp + 48 + localsize] ; width -> esi | ||
217 : | |||
218 : | mov ebp, [esp + 40 + localsize] ; y_stride -> ebp | ||
219 : | mov ebx, ebp | ||
220 : | shl ebx, 1 ; 2 * y_stride -> ebx | ||
221 : | sub ebx, esi ; y_dif -> ebx | ||
222 : | |||
223 : | mov [y_dif], ebx | ||
224 : | |||
225 : | mov eax, [esp + 28 + localsize] ; y_src -> eax | ||
226 : | mov ebx, eax | ||
227 : | add ebx, ebp ; y_src2 -> ebp | ||
228 : | |||
229 : | mov ecx, [esp + 24 + localsize] ; dst_stride -> ecx | ||
230 : | mov edx, ecx | ||
231 : | add ecx, edx | ||
232 : | shl edx, 2 | ||
233 : | add ecx, edx ; 6 * dst_stride -> ecx | ||
234 : | mov edx, ecx | ||
235 : | sub ecx, esi | ||
236 : | shl esi, 1 | ||
237 : | sub ecx, esi ; 6 * dst_stride - 3 * width -> ecx | ||
238 : | |||
239 : | mov [dst_dif], ecx | ||
240 : | |||
241 : | mov esi, [esp + 20 + localsize] ; dst -> esi | ||
242 : | mov edi, esi | ||
243 : | shr edx, 1 | ||
244 : | add edi, edx ; dst2 -> edi | ||
245 : | |||
246 : | mov ebp, [esp + 48 + localsize] ; width -> ebp | ||
247 : | mov ecx, ebp ; width -> ecx | ||
248 : | shr ecx, 1 | ||
249 : | shr ebp, 3 ; width / 8 -> ebp | ||
250 : | mov [width_8], ebp | ||
251 : | |||
252 : | mov ebp, [esp + 44 + localsize] ; uv_stride -> ebp | ||
253 : | sub ebp, ecx | ||
254 : | mov [uv_dif], ebp | ||
255 : | |||
256 : | mov ecx, [esp + 32 + localsize] ; u_src -> ecx | ||
257 : | mov edx, [esp + 36 + localsize] ; v_src -> edx | ||
258 : | |||
259 : | mov ebp, [esp + 52 + localsize] ; height -> ebp | ||
260 : | shr ebp, 1 ; height / 2 -> ebp | ||
261 : | |||
262 : | pxor mm7, mm7 | ||
263 : | |||
264 : | y_loop: | ||
265 : | mov [height_2], ebp | ||
266 : | mov ebp, [width_8] | ||
267 : | |||
268 : | x_loop: | ||
269 : | movd mm2, [ecx] | ||
270 : | movd mm3, [edx] | ||
271 : | |||
272 : | punpcklbw mm2, mm7 ; u3u2u1u0 -> mm2 | ||
273 : | punpcklbw mm3, mm7 ; v3v2v1v0 -> mm3 | ||
274 : | |||
275 : | psubsw mm2, [U_SUB] ; U - 128 | ||
276 : | psubsw mm3, [V_SUB] ; V - 128 | ||
277 : | |||
278 : | movq mm4, mm2 | ||
279 : | movq mm5, mm3 | ||
280 : | |||
281 : | pmullw mm2, [UG_MUL] | ||
282 : | pmullw mm3, [VG_MUL] | ||
283 : | |||
284 : | movq mm6, mm2 ; u3u2u1u0 -> mm6 | ||
285 : | punpckhwd mm2, mm2 ; u3u3u2u2 -> mm2 | ||
286 : | punpcklwd mm6, mm6 ; u1u1u0u0 -> mm6 | ||
287 : | |||
288 : | pmullw mm4, [UB_MUL] ; B_ADD -> mm4 | ||
289 : | |||
290 : | movq mm0, mm3 | ||
291 : | punpckhwd mm3, mm3 ; v3v3v2v2 -> mm2 | ||
292 : | punpcklwd mm0, mm0 ; v1v1v0v0 -> mm6 | ||
293 : | |||
294 : | paddsw mm2, mm3 | ||
295 : | paddsw mm6, mm0 | ||
296 : | |||
297 : | pmullw mm5, [VR_MUL] ; R_ADD -> mm5 | ||
298 : | |||
299 : | movq mm0, [eax] ; y7y6y5y4y3y2y1y0 -> mm0 | ||
300 : | |||
301 : | movq mm1, mm0 | ||
302 : | punpckhbw mm1, mm7 ; y7y6y5y4 -> mm1 | ||
303 : | punpcklbw mm0, mm7 ; y3y2y1y0 -> mm0 | ||
304 : | |||
305 : | psubsw mm0, [Y_SUB] ; Y - Y_SUB | ||
306 : | psubsw mm1, [Y_SUB] ; Y - Y_SUB | ||
307 : | |||
308 : | pmullw mm1, [Y_MUL] | ||
309 : | pmullw mm0, [Y_MUL] | ||
310 : | |||
311 : | movq [TEMP_Y2], mm1 ; y7y6y5y4 -> mm3 | ||
312 : | movq [TEMP_Y1], mm0 ; y3y2y1y0 -> mm7 | ||
313 : | |||
314 : | psubsw mm1, mm2 ; g7g6g5g4 -> mm1 | ||
315 : | psubsw mm0, mm6 ; g3g2g1g0 -> mm0 | ||
316 : | |||
317 : | psraw mm1, SCALEBITS | ||
318 : | psraw mm0, SCALEBITS | ||
319 : | |||
320 : | packuswb mm0, mm1 ;g7g6g5g4g3g2g1g0 -> mm0 | ||
321 : | |||
322 : | movq [TEMP_G1], mm0 | ||
323 : | |||
324 : | movq mm0, [ebx] ; y7y6y5y4y3y2y1y0 -> mm0 | ||
325 : | |||
326 : | movq mm1, mm0 | ||
327 : | |||
328 : | punpckhbw mm1, mm7 ; y7y6y5y4 -> mm1 | ||
329 : | punpcklbw mm0, mm7 ; y3y2y1y0 -> mm0 | ||
330 : | |||
331 : | psubsw mm0, [Y_SUB] ; Y - Y_SUB | ||
332 : | psubsw mm1, [Y_SUB] ; Y - Y_SUB | ||
333 : | |||
334 : | pmullw mm1, [Y_MUL] | ||
335 : | pmullw mm0, [Y_MUL] | ||
336 : | |||
337 : | movq mm3, mm1 | ||
338 : | psubsw mm1, mm2 ; g7g6g5g4 -> mm1 | ||
339 : | |||
340 : | movq mm2, mm0 | ||
341 : | psubsw mm0, mm6 ; g3g2g1g0 -> mm0 | ||
342 : | |||
343 : | psraw mm1, SCALEBITS | ||
344 : | psraw mm0, SCALEBITS | ||
345 : | |||
346 : | packuswb mm0, mm1 ; g7g6g5g4g3g2g1g0 -> mm0 | ||
347 : | |||
348 : | movq [TEMP_G2], mm0 | ||
349 : | |||
350 : | movq mm0, mm4 | ||
351 : | punpckhwd mm4, mm4 ; u3u3u2u2 -> mm2 | ||
352 : | punpcklwd mm0, mm0 ; u1u1u0u0 -> mm6 | ||
353 : | |||
354 : | movq mm1, mm3 ; y7y6y5y4 -> mm1 | ||
355 : | paddsw mm3, mm4 ; b7b6b5b4 -> mm3 | ||
356 : | |||
357 : | movq mm7, mm2 ; y3y2y1y0 -> mm7 | ||
358 : | |||
359 : | paddsw mm2, mm0 ; b3b2b1b0 -> mm2 | ||
360 : | |||
361 : | psraw mm3, SCALEBITS | ||
362 : | psraw mm2, SCALEBITS | ||
363 : | |||
364 : | packuswb mm2, mm3 ; b7b6b5b4b3b2b1b0 -> mm2 | ||
365 : | |||
366 : | movq [TEMP_B2], mm2 | ||
367 : | |||
368 : | movq mm3, [TEMP_Y2] | ||
369 : | movq mm2, [TEMP_Y1] | ||
370 : | |||
371 : | movq mm6, mm3 ; TEMP_Y2 -> mm6 | ||
372 : | paddsw mm3, mm4 ; b7b6b5b4 -> mm3 | ||
373 : | |||
374 : | movq mm4, mm2 ; TEMP_Y1 -> mm4 | ||
375 : | paddsw mm2, mm0 ; b3b2b1b0 -> mm2 | ||
376 : | |||
377 : | psraw mm3, SCALEBITS | ||
378 : | psraw mm2, SCALEBITS | ||
379 : | |||
380 : | packuswb mm2, mm3 ; b7b6b5b4b3b2b1b0 -> mm2 | ||
381 : | |||
382 : | movq [TEMP_B1], mm2 | ||
383 : | |||
384 : | movq mm0, mm5 | ||
385 : | punpckhwd mm5, mm5 ; v3v3v2v2 -> mm5 | ||
386 : | punpcklwd mm0, mm0 ; v1v1v0v0 -> mm0 | ||
387 : | |||
388 : | paddsw mm1, mm5 ; r7r6r5r4 -> mm1 | ||
389 : | paddsw mm7, mm0 ; r3r2r1r0 -> mm7 | ||
390 : | |||
391 : | psraw mm1, SCALEBITS | ||
392 : | psraw mm7, SCALEBITS | ||
393 : | |||
394 : | packuswb mm7, mm1 ; r7r6r5r4r3r2r1r0 -> mm7 (TEMP_R2) | ||
395 : | |||
396 : | paddsw mm6, mm5 ; r7r6r5r4 -> mm6 | ||
397 : | paddsw mm4, mm0 ; r3r2r1r0 -> mm4 | ||
398 : | |||
399 : | psraw mm6, SCALEBITS | ||
400 : | psraw mm4, SCALEBITS | ||
401 : | |||
402 : | packuswb mm4, mm6 ; r7r6r5r4r3r2r1r0 -> mm4 (TEMP_R1) | ||
403 : | |||
404 : | movq mm0, [TEMP_B1] | ||
405 : | movq mm1, [TEMP_G1] | ||
406 : | |||
407 : | movq mm6, mm7 | ||
408 : | |||
409 : | movq mm2, mm0 | ||
410 : | punpcklbw mm2, mm4 ; r3b3r2b2r1b1r0b0 -> mm2 | ||
411 : | punpckhbw mm0, mm4 ; r7b7r6b6r5b5r4b4 -> mm0 | ||
412 : | |||
413 : | pxor mm7, mm7 | ||
414 : | |||
415 : | movq mm3, mm1 | ||
416 : | punpcklbw mm1, mm7 ; 0g30g20g10g0 -> mm1 | ||
417 : | punpckhbw mm3, mm7 ; 0g70g60g50g4 -> mm3 | ||
418 : | |||
419 : | movq mm4, mm2 | ||
420 : | punpcklbw mm2, mm1 ; 0r1g1b10r0g0b0 -> mm2 | ||
421 : | punpckhbw mm4, mm1 ; 0r3g3b30r2g2b2 -> mm4 | ||
422 : | |||
423 : | movq mm5, mm0 | ||
424 : | punpcklbw mm0, mm3 ; 0r5g5b50r4g4b4 -> mm0 | ||
425 : | punpckhbw mm5, mm3 ; 0r7g7b70r6g6b6 -> mm5 | ||
426 : | |||
427 : | movd [esi], mm2 | ||
428 : | psrlq mm2, 32 | ||
429 : | |||
430 : | movd [esi + 3], mm2 | ||
431 : | movd [esi + 6], mm4 | ||
432 : | |||
433 : | psrlq mm4, 32 | ||
434 : | |||
435 : | movd [esi + 9], mm4 | ||
436 : | movd [esi + 12], mm0 | ||
437 : | |||
438 : | psrlq mm0, 32 | ||
439 : | |||
440 : | movd [esi + 15], mm0 | ||
441 : | movd [esi + 18], mm5 | ||
442 : | |||
443 : | psrlq mm5, 32 | ||
444 : | |||
445 : | movd [esi + 21], mm5 | ||
446 : | |||
447 : | movq mm0, [TEMP_B2] | ||
448 : | movq mm1, [TEMP_G2] | ||
449 : | |||
450 : | movq mm2, mm0 | ||
451 : | punpcklbw mm2, mm6 ; r3b3r2b2r1b1r0b0 -> mm2 | ||
452 : | punpckhbw mm0, mm6 ; r7b7r6b6r5b5r4b4 -> mm0 | ||
453 : | |||
454 : | movq mm3, mm1 | ||
455 : | punpcklbw mm1, mm7 ; 0g30g20g10g0 -> mm1 | ||
456 : | punpckhbw mm3, mm7 ; 0g70g60g50g4 -> mm3 | ||
457 : | |||
458 : | movq mm4, mm2 | ||
459 : | punpcklbw mm2, mm1 ; 0r1g1b10r0g0b0 -> mm2 | ||
460 : | punpckhbw mm4, mm1 ; 0r3g3b30r2g2b2 -> mm4 | ||
461 : | |||
462 : | movq mm5, mm0 | ||
463 : | punpcklbw mm0, mm3 ; 0r5g5b50r4g4b4 -> mm0 | ||
464 : | punpckhbw mm5, mm3 ; 0r7g7b70r6g6b6 -> mm5 | ||
465 : | |||
466 : | movd [edi], mm2 | ||
467 : | psrlq mm2, 32 | ||
468 : | |||
469 : | movd [edi + 3], mm2 | ||
470 : | movd [edi + 6], mm4 | ||
471 : | |||
472 : | psrlq mm4, 32 | ||
473 : | |||
474 : | movd [edi + 9], mm4 | ||
475 : | movd [edi + 12], mm0 | ||
476 : | |||
477 : | psrlq mm0, 32 | ||
478 : | |||
479 : | movd [edi + 15], mm0 | ||
480 : | movd [edi + 18], mm5 | ||
481 : | |||
482 : | psrlq mm5, 32 | ||
483 : | |||
484 : | movd [edi + 21], mm5 | ||
485 : | |||
486 : | add esi, 24 | ||
487 : | add edi, 24 | ||
488 : | |||
489 : | add eax, 8 | ||
490 : | add ebx, 8 | ||
491 : | add ecx, 4 | ||
492 : | add edx, 4 | ||
493 : | |||
494 : | dec ebp | ||
495 : | |||
496 : | jnz near x_loop | ||
497 : | |||
498 : | add esi, [dst_dif] | ||
499 : | add edi, [dst_dif] | ||
500 : | |||
501 : | add eax, [y_dif] | ||
502 : | add ebx, [y_dif] | ||
503 : | |||
504 : | add ecx, [uv_dif] | ||
505 : | add edx, [uv_dif] | ||
506 : | |||
507 : | mov ebp, [height_2] | ||
508 : | dec ebp | ||
509 : | jnz near y_loop | ||
510 : | |||
511 : | emms | ||
512 : | |||
513 : | ;; Local vars deallocation | ||
514 : | add esp, localsize | ||
515 : | %undef TEMP_Y1 | ||
516 : | %undef TEMP_Y2 | ||
517 : | %undef TEMP_G1 | ||
518 : | %undef TEMP_G2 | ||
519 : | %undef TEMP_B1 | ||
520 : | %undef TEMP_B2 | ||
521 : | %undef y_dif | ||
522 : | %undef dst_dif | ||
523 : | %undef uv_dif | ||
524 : | %undef height | ||
525 : | %undef width_8 | ||
526 : | %undef height_2 | ||
527 : | %undef localsize | ||
528 : | |||
529 : | pop ebp | ||
530 : | pop edi | ||
531 : | pop esi | ||
532 : | pop ebx | ||
533 : | |||
534 : | ret |
No admin address has been configured | ViewVC Help |
Powered by ViewVC 1.0.4 |