view h264idct.c @ 2504:f12657081093 libavcodec

INTRA PCM macroblocks support patch by (Loic )lll+ffmpeg m4x org) This patch adds the support for INTRA PCM macroblocks in CAVLC and CABAC mode, the deblocking needed a small modification and so did the intra4x4_pred_mode prediction. With this patch, the 5 streams of the conformance suite containing INTRA PCM macroblocks now decode entirely, 4 are completely corrects, 1 is incorrect since the first B slice because of deblocking in B slice not yet implemented. The code is not optimized for speed, it is not necessary IPCM macroblocks are rare, but it could be optimized for code size, if someone want to do this, feel free.

/*
 * H.264 IDCT
 * Copyright (c) 2004 Michael Niedermayer <[e-mail]>
 *
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This library 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
 * Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 */
 
/**
 * @file h264-idct.c
 * H.264 IDCT.
 * @author Michael Niedermayer <[e-mail]>
 */
 
#include "dsputil.h"

static always_inline void idct_internal(uint8_t *dst, DCTELEM *block, int stride, int block_stride, int shift, int add){
    int i;
    uint8_t *cm = cropTbl + MAX_NEG_CROP;

    block[0] += 1<<(shift-1);

    for(i=0; i<4; i++){
        const int z0=  block[0 + block_stride*i]     +  block[2 + block_stride*i];
        const int z1=  block[0 + block_stride*i]     -  block[2 + block_stride*i];
        const int z2= (block[1 + block_stride*i]>>1) -  block[3 + block_stride*i];
        const int z3=  block[1 + block_stride*i]     + (block[3 + block_stride*i]>>1);

        block[0 + block_stride*i]= z0 + z3;
        block[1 + block_stride*i]= z1 + z2;
        block[2 + block_stride*i]= z1 - z2;
        block[3 + block_stride*i]= z0 - z3;
    }

    for(i=0; i<4; i++){
        const int z0=  block[i + block_stride*0]     +  block[i + block_stride*2];
        const int z1=  block[i + block_stride*0]     -  block[i + block_stride*2];
        const int z2= (block[i + block_stride*1]>>1) -  block[i + block_stride*3];
        const int z3=  block[i + block_stride*1]     + (block[i + block_stride*3]>>1);

        dst[i + 0*stride]= cm[ add*dst[i + 0*stride] + ((z0 + z3) >> shift) ];
        dst[i + 1*stride]= cm[ add*dst[i + 1*stride] + ((z1 + z2) >> shift) ];
        dst[i + 2*stride]= cm[ add*dst[i + 2*stride] + ((z1 - z2) >> shift) ];
        dst[i + 3*stride]= cm[ add*dst[i + 3*stride] + ((z0 - z3) >> shift) ];
    }
}

void ff_h264_idct_add_c(uint8_t *dst, DCTELEM *block, int stride){
    idct_internal(dst, block, stride, 4, 6, 1);
}

void ff_h264_lowres_idct_add_c(uint8_t *dst, int stride, DCTELEM *block){
    idct_internal(dst, block, stride, 8, 3, 1);
}

void ff_h264_lowres_idct_put_c(uint8_t *dst, int stride, DCTELEM *block){
    idct_internal(dst, block, stride, 8, 3, 0);
}