view dcadsp.h @ 12334:435319d67bd8 libavcodec

Use word-writing instead of dword-writing (with two cached but otherwise unchanged bytes) in the horizontal simple loopfilter. This makes the filter quite a bit faster in itself (~30 cycles less on Core1), probably mostly because we don't need a complex 4x4 transpose, but only a simple byte interleave. Also allows using pextrw on SSE4, which speeds up even more (e.g. 25% faster on Core i7).
author rbultje
date Sat, 31 Jul 2010 23:13:15 +0000
parents 8d3539d6ba3d
children
line wrap: on
line source

/*
 * This file is part of FFmpeg.
 *
 * FFmpeg 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 2.1 of the License, or (at your option) any later version.
 *
 * FFmpeg 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 FFmpeg; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
 */

#ifndef AVCODEC_DCADSP_H
#define AVCODEC_DCADSP_H

typedef struct DCADSPContext {
    void (*lfe_fir)(float *out, const float *in, const float *coefs,
                    int decifactor, float scale, float bias);
} DCADSPContext;

void ff_dcadsp_init(DCADSPContext *s);
void ff_dcadsp_init_arm(DCADSPContext *s);

#endif /* AVCODEC_DCADSP_H */