comparison vp56.c @ 11665:85ee3d14b906 libavcodec

VP56: move vp56_edge_filter to new VP56DSPContext Using macro templates allows the vp[56]_adjust functions to be inlined instead of called through function pointers. The new function pointers enable optimised implementations of the filters. 4% faster VP6 decoding on Cortex-A8.

11664:3da317f52661

        lb->ref_frame = ref_frame;
        s->block_coeff[b][idx] *= s->dequant_dc;
    }
}

static void vp56_edge_filter(VP56Context *s, uint8_t *yuv,
                             int pix_inc, int line_inc, int t)
{
    int pix2_inc = 2 * pix_inc;
    int i, v;

    for (i=0; i<12; i++) {
        v = (yuv[-pix2_inc] + 3*(yuv[0]-yuv[-pix_inc]) - yuv[pix_inc] + 4) >>3;
        v = s->adjust(v, t);
        yuv[-pix_inc] = av_clip_uint8(yuv[-pix_inc] + v);
        yuv[0] = av_clip_uint8(yuv[0] - v);
        yuv += line_inc;
    }
}

static void vp56_deblock_filter(VP56Context *s, uint8_t *yuv,
                                int stride, int dx, int dy)
{
    int t = vp56_filter_threshold[s->quantizer];
    if (dx)  vp56_edge_filter(s, yuv +         10-dx ,      1, stride, t);
    if (dy)  vp56_edge_filter(s, yuv + stride*(10-dy), stride,      1, t);
}

static void vp56_mc(VP56Context *s, int b, int plane, uint8_t *src,
                    int stride, int x, int y)
{

    avctx->pix_fmt = has_alpha ? PIX_FMT_YUVA420P : PIX_FMT_YUV420P;

    if (avctx->idct_algo == FF_IDCT_AUTO)
        avctx->idct_algo = FF_IDCT_VP3;
    dsputil_init(&s->dsp, avctx);
    ff_init_scantable(s->dsp.idct_permutation, &s->scantable,ff_zigzag_direct);

    for (i=0; i<4; i++)
        s->framep[i] = &s->frames[i];
    s->framep[VP56_FRAME_UNUSED] = s->framep[VP56_FRAME_GOLDEN];

11665:85ee3d14b906

        lb->ref_frame = ref_frame;
        s->block_coeff[b][idx] *= s->dequant_dc;
    }
}

static void vp56_deblock_filter(VP56Context *s, uint8_t *yuv,
                                int stride, int dx, int dy)
{
    int t = vp56_filter_threshold[s->quantizer];
    if (dx)  s->vp56dsp.edge_filter_hor(yuv +         10-dx , stride, t);
    if (dy)  s->vp56dsp.edge_filter_ver(yuv + stride*(10-dy), stride, t);
}

static void vp56_mc(VP56Context *s, int b, int plane, uint8_t *src,
                    int stride, int x, int y)
{

    avctx->pix_fmt = has_alpha ? PIX_FMT_YUVA420P : PIX_FMT_YUV420P;

    if (avctx->idct_algo == FF_IDCT_AUTO)
        avctx->idct_algo = FF_IDCT_VP3;
    dsputil_init(&s->dsp, avctx);
    ff_vp56dsp_init(&s->vp56dsp, avctx->codec->id);
    ff_init_scantable(s->dsp.idct_permutation, &s->scantable,ff_zigzag_direct);

    for (i=0; i<4; i++)
        s->framep[i] = &s->frames[i];
    s->framep[VP56_FRAME_UNUSED] = s->framep[VP56_FRAME_GOLDEN];