1 |
;/***************************************************************************** |
;/***************************************************************************** |
2 |
; * |
; * |
3 |
; * XVID MPEG-4 VIDEO CODEC |
; * XVID MPEG-4 VIDEO CODEC |
4 |
; * Reduced-Resolution utilities |
; * - Reduced-Resolution utilities - |
5 |
; * |
; * |
6 |
; * Copyright(C) 2002 Pascal Massimino <skal@planet-d.net> |
; * Copyright(C) 2002 Pascal Massimino <skal@planet-d.net> |
7 |
; * |
; * |
|
; * This file is part of XviD, a free MPEG-4 video encoder/decoder |
|
|
; * |
|
8 |
; * XviD is free software; you can redistribute it and/or modify it |
; * XviD is free software; you can redistribute it and/or modify it |
9 |
; * under the terms of the GNU General Public License as published by |
; * under the terms of the GNU General Public License as published by |
10 |
; * the Free Software Foundation; either version 2 of the License, or |
; * the Free Software Foundation; either version 2 of the License, or |
19 |
; * along with this program; if not, write to the Free Software |
; * along with this program; if not, write to the Free Software |
20 |
; * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA |
; * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA |
21 |
; * |
; * |
22 |
; * Under section 8 of the GNU General Public License, the copyright |
; * $Id: reduced_mmx.asm,v 1.6 2004-08-29 10:02:38 edgomez Exp $ |
|
; * holders of XVID explicitly forbid distribution in the following |
|
|
; * countries: |
|
|
; * |
|
|
; * - Japan |
|
|
; * - United States of America |
|
|
; * |
|
|
; * Linking XviD statically or dynamically with other modules is making a |
|
|
; * combined work based on XviD. Thus, the terms and conditions of the |
|
|
; * GNU General Public License cover the whole combination. |
|
|
; * |
|
|
; * As a special exception, the copyright holders of XviD give you |
|
|
; * permission to link XviD with independent modules that communicate with |
|
|
; * XviD solely through the VFW1.1 and DShow interfaces, regardless of the |
|
|
; * license terms of these independent modules, and to copy and distribute |
|
|
; * the resulting combined work under terms of your choice, provided that |
|
|
; * every copy of the combined work is accompanied by a complete copy of |
|
|
; * the source code of XviD (the version of XviD used to produce the |
|
|
; * combined work), being distributed under the terms of the GNU General |
|
|
; * Public License plus this exception. An independent module is a module |
|
|
; * which is not derived from or based on XviD. |
|
|
; * |
|
|
; * Note that people who make modified versions of XviD are not obligated |
|
|
; * to grant this special exception for their modified versions; it is |
|
|
; * their choice whether to do so. The GNU General Public License gives |
|
|
; * permission to release a modified version without this exception; this |
|
|
; * exception also makes it possible to release a modified version which |
|
|
; * carries forward this exception. |
|
|
; * |
|
|
; * $Id: reduced_mmx.asm,v 1.2 2003-02-15 15:22:18 edgomez Exp $ |
|
23 |
; * |
; * |
24 |
; *************************************************************************/ |
; *************************************************************************/ |
25 |
|
|
26 |
bits 32 |
BITS 32 |
27 |
|
|
28 |
%macro cglobal 1 |
%macro cglobal 1 |
29 |
%ifdef PREFIX |
%ifdef PREFIX |
30 |
|
%ifdef MARK_FUNCS |
31 |
|
global _%1:function %1.endfunc-%1 |
32 |
|
%define %1 _%1:function %1.endfunc-%1 |
33 |
|
%else |
34 |
global _%1 |
global _%1 |
35 |
%define %1 _%1 |
%define %1 _%1 |
36 |
|
%endif |
37 |
|
%else |
38 |
|
%ifdef MARK_FUNCS |
39 |
|
global %1:function %1.endfunc-%1 |
40 |
%else |
%else |
41 |
global %1 |
global %1 |
42 |
%endif |
%endif |
43 |
|
%endif |
44 |
%endmacro |
%endmacro |
45 |
|
|
46 |
;=========================================================================== |
;=========================================================================== |
47 |
|
|
48 |
section .data |
%ifdef FORMAT_COFF |
49 |
|
SECTION .rodata |
50 |
|
%else |
51 |
|
SECTION .rodata align=16 |
52 |
|
%endif |
53 |
|
|
54 |
align 16 |
align 16 |
55 |
Up31 dw 3, 1, 3, 1 |
Up31 dw 3, 1, 3, 1 |
67 |
|
|
68 |
;=========================================================================== |
;=========================================================================== |
69 |
|
|
70 |
section .text |
SECTION .text |
71 |
|
|
72 |
cglobal xvid_Copy_Upsampled_8x8_16To8_mmx |
cglobal xvid_Copy_Upsampled_8x8_16To8_mmx |
73 |
cglobal xvid_Add_Upsampled_8x8_16To8_mmx |
cglobal xvid_Add_Upsampled_8x8_16To8_mmx |
271 |
STORE_1 mm2, mm3 |
STORE_1 mm2, mm3 |
272 |
|
|
273 |
ret |
ret |
274 |
|
.endfunc |
275 |
|
|
276 |
;=========================================================================== |
;=========================================================================== |
277 |
; |
; |
466 |
STORE_ADD_1 mm2, mm3 |
STORE_ADD_1 mm2, mm3 |
467 |
|
|
468 |
ret |
ret |
469 |
|
.endfunc |
470 |
|
|
471 |
;=========================================================================== |
;=========================================================================== |
472 |
; |
; |
598 |
STORE_1 mm2, mm3 |
STORE_1 mm2, mm3 |
599 |
|
|
600 |
ret |
ret |
601 |
|
.endfunc |
602 |
|
|
603 |
;=========================================================================== |
;=========================================================================== |
604 |
; |
; |
707 |
STORE_ADD_1 mm2, mm3 |
STORE_ADD_1 mm2, mm3 |
708 |
|
|
709 |
ret |
ret |
710 |
|
.endfunc |
711 |
|
|
712 |
|
|
713 |
;=========================================================================== |
;=========================================================================== |
764 |
pop edi |
pop edi |
765 |
pop esi |
pop esi |
766 |
ret |
ret |
767 |
|
.endfunc |
768 |
|
|
769 |
; mmx is of no use here. Better use plain ASM. Moreover, |
; mmx is of no use here. Better use plain ASM. Moreover, |
770 |
; this is for the fun of ASM coding, coz' every modern compiler can |
; this is for the fun of ASM coding, coz' every modern compiler can |
804 |
pop edi |
pop edi |
805 |
pop esi |
pop esi |
806 |
ret |
ret |
807 |
|
.endfunc |
808 |
|
|
809 |
; this one's just a little faster than gcc's code. Very little. |
; this one's just a little faster than gcc's code. Very little. |
810 |
|
|
841 |
pop edi |
pop edi |
842 |
pop esi |
pop esi |
843 |
ret |
ret |
844 |
|
.endfunc |
845 |
|
|
846 |
;////////////////////////////////////////////////////////////////////// |
;////////////////////////////////////////////////////////////////////// |
847 |
;// 16b downsampling 16x16 -> 8x8 |
;// 16b downsampling 16x16 -> 8x8 |
931 |
COPY_TWO_LINES_1331 ecx + 6*16 +8 |
COPY_TWO_LINES_1331 ecx + 6*16 +8 |
932 |
|
|
933 |
ret |
ret |
934 |
|
.endfunc |
935 |
|
|
936 |
;=========================================================================== |
;=========================================================================== |
937 |
; |
; |
996 |
DIFF_TWO_LINES_1331 ecx + 6*16 +8 |
DIFF_TWO_LINES_1331 ecx + 6*16 +8 |
997 |
|
|
998 |
ret |
ret |
999 |
|
.endfunc |
1000 |
|
|
1001 |
;////////////////////////////////////////////////////////////////////// |
;////////////////////////////////////////////////////////////////////// |
1002 |
|
|