--- idct.c 2002/11/26 23:44:10 1.5 +++ idct.c 2003/02/15 15:22:18 1.6 @@ -1,59 +1,42 @@ -/***************************************************************************** - * - * XVID MPEG-4 VIDEO CODEC - * - inverse fast disrete cosine transformation - integer C version - * - * These routines are from Independent JPEG Group's free JPEG software - * Copyright (C) 1991-1998, Thomas G. Lane (see the file README.IJG) - * - * This file is part of XviD, a free MPEG-4 video encoder/decoder - * - * XviD 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. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA - * - * Under section 8 of the GNU General Public License, the copyright - * 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: idct.c,v 1.5 2002/11/26 23:44:10 edgomez Exp $ +/* idct.c, inverse fast discrete cosine transform */ + +/* Copyright (C) 1996, MPEG Software Simulation Group. All Rights Reserved. */ + +/* + * Disclaimer of Warranty * - *************************************************************************/ + * These software programs are available to the user without any license fee or + * royalty on an "as is" basis. The MPEG Software Simulation Group disclaims + * any and all warranties, whether express, implied, or statuary, including any + * implied warranties or merchantability or of fitness for a particular + * purpose. In no event shall the copyright-holder be liable for any + * incidental, punitive, or consequential damages of any kind whatsoever + * arising from the use of these programs. + * + * This disclaimer of warranty extends to the user of these programs and user's + * customers, employees, agents, transferees, successors, and assigns. + * + * The MPEG Software Simulation Group does not represent or warrant that the + * programs furnished hereunder are free of infringement of any third-party + * patents. + * + * Commercial implementations of MPEG-1 and MPEG-2 video, including shareware, + * are subject to royalty fees to patent holders. Many of these patents are + * general enough such that they are unavoidable regardless of implementation + * design. + * + * MPEG2AVI + * -------- + * v0.16B33 renamed the initialization function to init_idct_int32() + * v0.16B32 removed the unused idct_row() and idct_col() functions + * v0.16B3 changed var declarations to static, to enforce data align + * v0.16B22 idct_FAST() renamed to idct_int32() + * also merged idct_FAST() into a single function, to help VC++ + * optimize it. + * + * v0.14 changed int to long, to avoid confusion when compiling on x86 + * platform ( in VC++ "int" -> 32bits ) + */ /**********************************************************/ /* inverse two dimensional DCT, Chen-Wang algorithm */ @@ -69,6 +52,7 @@ /* this code assumes >> to be a two's-complement arithmetic */ /* right shift: (-2)>>1 == -1 , (-3)>>1 == -2 */ +//#include #include "idct.h" #define W1 2841 /* 2048*sqrt(2)*cos(1*pi/16) */ @@ -80,16 +64,16 @@ /* global declarations */ -/*void init_idct_int32 (void); */ -/*void idct_int32 (short *block); */ +//void init_idct_int32 (void); +//void idct_int32 (short *block); /* private data */ static short iclip[1024]; /* clipping table */ static short *iclp; /* private prototypes */ -/*static void idctrow _ANSI_ARGS_((short *blk)); */ -/*static void idctcol _ANSI_ARGS_((short *blk)); */ +//static void idctrow _ANSI_ARGS_((short *blk)); +//static void idctcol _ANSI_ARGS_((short *blk)); /* row (horizontal) IDCT * @@ -101,13 +85,13 @@ * c[1..7] = 128*sqrt(2) */ -#if 0 +/* static void idctrow(blk) short *blk; { int X0, X1, X2, X3, X4, X5, X6, X7, X8; - /* shortcut */ + // shortcut if (!((X1 = blk[4]<<11) | (X2 = blk[6]) | (X3 = blk[2]) | (X4 = blk[1]) | (X5 = blk[7]) | (X6 = blk[5]) | (X7 = blk[3]))) { @@ -115,9 +99,9 @@ return; } - X0 = (blk[0]<<11) + 128; /* for proper rounding in the fourth stage */ + X0 = (blk[0]<<11) + 128; // for proper rounding in the fourth stage - /* first stage */ + // first stage X8 = W7*(X4+X5); X4 = X8 + (W1-W7)*X4; X5 = X8 - (W1+W7)*X5; @@ -125,7 +109,7 @@ X6 = X8 - (W3-W5)*X6; X7 = X8 - (W3+W5)*X7; - /* second stage */ + // second stage X8 = X0 + X1; X0 -= X1; X1 = W6*(X3+X2); @@ -136,7 +120,7 @@ X6 = X5 + X7; X5 -= X7; - /* third stage */ + // third stage X7 = X8 + X3; X8 -= X3; X3 = X0 + X2; @@ -144,7 +128,7 @@ X2 = (181*(X4+X5)+128)>>8; X4 = (181*(X4-X5)+128)>>8; - /* fourth stage */ + // fourth stage blk[0] = (X7+X1)>>8; blk[1] = (X3+X2)>>8; blk[2] = (X0+X4)>>8; @@ -153,8 +137,7 @@ blk[5] = (X0-X4)>>8; blk[6] = (X3-X2)>>8; blk[7] = (X7-X1)>>8; -} -#endif +}*/ /* column (vertical) IDCT * @@ -165,13 +148,13 @@ * where: c[0] = 1/1024 * c[1..7] = (1/1024)*sqrt(2) */ -#if 0 +/* static void idctcol(blk) short *blk; { int X0, X1, X2, X3, X4, X5, X6, X7, X8; - /* shortcut */ + // shortcut if (!((X1 = (blk[8*4]<<8)) | (X2 = blk[8*6]) | (X3 = blk[8*2]) | (X4 = blk[8*1]) | (X5 = blk[8*7]) | (X6 = blk[8*5]) | (X7 = blk[8*3]))) { @@ -182,7 +165,7 @@ X0 = (blk[8*0]<<8) + 8192; - /* first stage */ + // first stage X8 = W7*(X4+X5) + 4; X4 = (X8+(W1-W7)*X4)>>3; X5 = (X8-(W1+W7)*X5)>>3; @@ -190,7 +173,7 @@ X6 = (X8-(W3-W5)*X6)>>3; X7 = (X8-(W3+W5)*X7)>>3; - /* second stage */ + // second stage X8 = X0 + X1; X0 -= X1; X1 = W6*(X3+X2) + 4; @@ -201,7 +184,7 @@ X6 = X5 + X7; X5 -= X7; - /* third stage */ + // third stage X7 = X8 + X3; X8 -= X3; X3 = X0 + X2; @@ -209,7 +192,7 @@ X2 = (181*(X4+X5)+128)>>8; X4 = (181*(X4-X5)+128)>>8; - /* fourth stage */ + // fourth stage blk[8*0] = iclp[(X7+X1)>>14]; blk[8*1] = iclp[(X3+X2)>>14]; blk[8*2] = iclp[(X0+X4)>>14]; @@ -218,20 +201,19 @@ blk[8*5] = iclp[(X0-X4)>>14]; blk[8*6] = iclp[(X3-X2)>>14]; blk[8*7] = iclp[(X7-X1)>>14]; -} -#endif +}*/ -/* function pointer */ +// function pointer idctFuncPtr idct; /* two dimensional inverse discrete cosine transform */ -/*void j_rev_dct(block) */ -/*short *block; */ +//void j_rev_dct(block) +//short *block; void idct_int32(short *const block) { - /* idct_int32_init() must be called before the first call to this function! */ + // idct_int32_init() must be called before the first call to this function! /*int i; @@ -247,7 +229,7 @@ static long X0, X1, X2, X3, X4, X5, X6, X7, X8; - for (i = 0; i < 8; i++) /* idct rows */ + for (i = 0; i < 8; i++) // idct rows { blk = block + (i << 3); if (! @@ -259,9 +241,9 @@ continue; } - X0 = (blk[0] << 11) + 128; /* for proper rounding in the fourth stage */ + X0 = (blk[0] << 11) + 128; // for proper rounding in the fourth stage - /* first stage */ + // first stage X8 = W7 * (X4 + X5); X4 = X8 + (W1 - W7) * X4; X5 = X8 - (W1 + W7) * X5; @@ -269,7 +251,7 @@ X6 = X8 - (W3 - W5) * X6; X7 = X8 - (W3 + W5) * X7; - /* second stage */ + // second stage X8 = X0 + X1; X0 -= X1; X1 = W6 * (X3 + X2); @@ -280,7 +262,7 @@ X6 = X5 + X7; X5 -= X7; - /* third stage */ + // third stage X7 = X8 + X3; X8 -= X3; X3 = X0 + X2; @@ -288,7 +270,7 @@ X2 = (181 * (X4 + X5) + 128) >> 8; X4 = (181 * (X4 - X5) + 128) >> 8; - /* fourth stage */ + // fourth stage blk[0] = (short) ((X7 + X1) >> 8); blk[1] = (short) ((X3 + X2) >> 8); @@ -299,14 +281,14 @@ blk[6] = (short) ((X3 - X2) >> 8); blk[7] = (short) ((X7 - X1) >> 8); - } /* end for ( i = 0; i < 8; ++i ) IDCT-rows */ + } // end for ( i = 0; i < 8; ++i ) IDCT-rows - for (i = 0; i < 8; i++) /* idct columns */ + for (i = 0; i < 8; i++) // idct columns { blk = block + i; - /* shortcut */ + // shortcut if (! ((X1 = (blk[8 * 4] << 8)) | (X2 = blk[8 * 6]) | (X3 = blk[8 * @@ -322,7 +304,7 @@ X0 = (blk[8 * 0] << 8) + 8192; - /* first stage */ + // first stage X8 = W7 * (X4 + X5) + 4; X4 = (X8 + (W1 - W7) * X4) >> 3; X5 = (X8 - (W1 + W7) * X5) >> 3; @@ -330,7 +312,7 @@ X6 = (X8 - (W3 - W5) * X6) >> 3; X7 = (X8 - (W3 + W5) * X7) >> 3; - /* second stage */ + // second stage X8 = X0 + X1; X0 -= X1; X1 = W6 * (X3 + X2) + 4; @@ -341,7 +323,7 @@ X6 = X5 + X7; X5 -= X7; - /* third stage */ + // third stage X7 = X8 + X3; X8 -= X3; X3 = X0 + X2; @@ -349,7 +331,7 @@ X2 = (181 * (X4 + X5) + 128) >> 8; X4 = (181 * (X4 - X5) + 128) >> 8; - /* fourth stage */ + // fourth stage blk[8 * 0] = iclp[(X7 + X1) >> 14]; blk[8 * 1] = iclp[(X3 + X2) >> 14]; blk[8 * 2] = iclp[(X0 + X4) >> 14]; @@ -360,13 +342,13 @@ blk[8 * 7] = iclp[(X7 - X1) >> 14]; } -} /* end function idct_int32(block) */ +} // end function idct_int32(block) -/*void */ -/*idct_int32_init() */ +//void +//idct_int32_init() void -idct_int32_init(void) +idct_int32_init() { int i;