view arm/fft_init_arm.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%.

/*
 * Copyright (c) 2009 Mans Rullgard <[e-mail]>
 *
 * 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 "libavcodec/fft.h"
#include "libavcodec/synth_filter.h"

void ff_fft_permute_neon(FFTContext *s, FFTComplex *z);
void ff_fft_calc_neon(FFTContext *s, FFTComplex *z);

void ff_imdct_calc_neon(FFTContext *s, FFTSample *output, const FFTSample *input);
void ff_imdct_half_neon(FFTContext *s, FFTSample *output, const FFTSample *input);
void ff_mdct_calc_neon(FFTContext *s, FFTSample *output, const FFTSample *input);

void ff_rdft_calc_neon(struct RDFTContext *s, FFTSample *z);

void ff_synth_filter_float_neon(FFTContext *imdct,
                                float *synth_buf_ptr, int *synth_buf_offset,
                                float synth_buf2[32], const float window[512],
                                float out[32], const float in[32],
                                float scale, float bias);

av_cold void ff_fft_init_arm(FFTContext *s)
{
    if (HAVE_NEON) {
        s->fft_permute  = ff_fft_permute_neon;
        s->fft_calc     = ff_fft_calc_neon;
        s->imdct_calc   = ff_imdct_calc_neon;
        s->imdct_half   = ff_imdct_half_neon;
        s->mdct_calc    = ff_mdct_calc_neon;
        s->permutation  = FF_MDCT_PERM_INTERLEAVE;
    }
}

#if CONFIG_RDFT
av_cold void ff_rdft_init_arm(RDFTContext *s)
{
    if (HAVE_NEON)
        s->rdft_calc    = ff_rdft_calc_neon;
}
#endif

#if CONFIG_DCA_DECODER
av_cold void ff_synth_filter_init_arm(SynthFilterContext *s)
{
    if (HAVE_NEON)
        s->synth_filter_float = ff_synth_filter_float_neon;
}
#endif