view avfft.h @ 12197:fbf4d5b1b664 libavcodec

Remove FF_MM_SSE2/3 flags for CPUs where this is generally not faster than regular MMX code. Examples of this are the Core1 CPU. Instead, set a new flag, FF_MM_SSE2/3SLOW, which can be checked for particular SSE2/3 functions that have been checked specifically on such CPUs and are actually faster than their MMX counterparts. In addition, use this flag to enable particular VP8 and LPC SSE2 functions that are faster than their MMX counterparts. Based on a patch by Loren Merritt <lorenm AT u washington edu>.
author rbultje
date Mon, 19 Jul 2010 22:38:23 +0000
parents fdafbcef52f5
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_AVFFT_H
#define AVCODEC_AVFFT_H

typedef float FFTSample;

typedef struct FFTComplex {
    FFTSample re, im;
} FFTComplex;

typedef struct FFTContext FFTContext;

/**
 * Set up a complex FFT.
 * @param nbits           log2 of the length of the input array
 * @param inverse         if 0 perform the forward transform, if 1 perform the inverse
 */
FFTContext *av_fft_init(int nbits, int inverse);

/**
 * Do the permutation needed BEFORE calling ff_fft_calc().
 */
void av_fft_permute(FFTContext *s, FFTComplex *z);

/**
 * Do a complex FFT with the parameters defined in av_fft_init(). The
 * input data must be permuted before. No 1.0/sqrt(n) normalization is done.
 */
void av_fft_calc(FFTContext *s, FFTComplex *z);

void av_fft_end(FFTContext *s);

FFTContext *av_mdct_init(int nbits, int inverse, double scale);
void av_imdct_calc(FFTContext *s, FFTSample *output, const FFTSample *input);
void av_imdct_half(FFTContext *s, FFTSample *output, const FFTSample *input);
void av_mdct_calc(FFTContext *s, FFTSample *output, const FFTSample *input);
void av_mdct_end(FFTContext *s);

/* Real Discrete Fourier Transform */

enum RDFTransformType {
    DFT_R2C,
    IDFT_C2R,
    IDFT_R2C,
    DFT_C2R,
};

typedef struct RDFTContext RDFTContext;

/**
 * Set up a real FFT.
 * @param nbits           log2 of the length of the input array
 * @param trans           the type of transform
 */
RDFTContext *av_rdft_init(int nbits, enum RDFTransformType trans);
void av_rdft_calc(RDFTContext *s, FFTSample *data);
void av_rdft_end(RDFTContext *s);

/* Discrete Cosine Transform */

typedef struct DCTContext DCTContext;

enum DCTTransformType {
    DCT_II = 0,
    DCT_III,
    DCT_I,
    DST_I,
};

/**
 * Set up DCT.
 * @param nbits           size of the input array:
 *                        (1 << nbits)     for DCT-II, DCT-III and DST-I
 *                        (1 << nbits) + 1 for DCT-I
 *
 * @note the first element of the input of DST-I is ignored
 */
DCTContext *av_dct_init(int nbits, enum DCTTransformType type);
void av_dct_calc(DCTContext *s, FFTSample *data);
void av_dct_end (DCTContext *s);

#endif /* AVCODEC_AVFFT_H */