view x86/vp56dsp_init.c @ 12492:58a960d6e34c libavcodec

Rename h264_idct_sse2.asm to h264_idct.asm; move inline IDCT asm from h264dsp_mmx.c to h264_idct.asm (as yasm code). Because the loops are now coded in asm instead of C, this is (depending on the function) up to 50% faster for cases where gcc didn't do a great job at looping. Since h264_idct_add8() is now faster than the manual loop setup in h264.c, in-asm idct calling can now be enabled for chroma as well (see r16207). For MMX, this is 5% faster. For SSE2 (which isn't done for chroma if h264.c does the looping), this makes it up to 50% faster. Speed gain overall is ~0.5-1.0%.
author rbultje
date Tue, 14 Sep 2010 13:36:26 +0000
parents 9fef0a8ddd63
children
line wrap: on
line source

/*
 * VP6 MMX/SSE2 optimizations
 * Copyright (C) 2009  Sebastien Lucas <sebastien.lucas@gmail.com>
 * Copyright (C) 2009  Zuxy Meng <zuxy.meng@gmail.com>
 *
 * 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
 */

#include "libavutil/cpu.h"
#include "libavutil/x86_cpu.h"
#include "libavcodec/dsputil.h"
#include "libavcodec/vp56dsp.h"

void ff_vp6_filter_diag4_mmx(uint8_t *dst, uint8_t *src, int stride,
                             const int16_t *h_weights,const int16_t *v_weights);
void ff_vp6_filter_diag4_sse2(uint8_t *dst, uint8_t *src, int stride,
                              const int16_t *h_weights,const int16_t *v_weights);

av_cold void ff_vp56dsp_init_x86(VP56DSPContext* c, enum CodecID codec)
{
#if HAVE_YASM
    int mm_flags = av_get_cpu_flags();

    if (CONFIG_VP6_DECODER && codec == CODEC_ID_VP6) {
        if (mm_flags & AV_CPU_FLAG_MMX) {
            c->vp6_filter_diag4 = ff_vp6_filter_diag4_mmx;
        }

        if (mm_flags & AV_CPU_FLAG_SSE2) {
            c->vp6_filter_diag4 = ff_vp6_filter_diag4_sse2;
        }
    }
#endif
}