1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-02 03:06:28 +02:00
FFmpeg/libavcodec/synth_filter.h
Christophe Gisquet 08e3ea60ff x86: synth filter float: implement SSE2 version
Timings for Arrandale:
          C    SSE
win32:  2108   334
win64:  1152   322

Factorizing the inner loop with a call/jmp is a >15 cycles cost, even with
the jmp destination being aligned.

Unrolling for ARCH_X86_64 is a 20 cycles gain.

Signed-off-by: Janne Grunau <janne-libav@jannau.net>
2014-02-28 13:00:48 +01:00

39 lines
1.4 KiB
C

/*
* copyright (c) 2008 Michael Niedermayer <michaelni@gmx.at>
*
* This file is part of Libav.
*
* Libav 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.
*
* Libav 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 Libav; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#ifndef AVCODEC_SYNTH_FILTER_H
#define AVCODEC_SYNTH_FILTER_H
#include "fft.h"
typedef struct SynthFilterContext {
void (*synth_filter_float)(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);
} SynthFilterContext;
void ff_synth_filter_init(SynthFilterContext *c);
void ff_synth_filter_init_arm(SynthFilterContext *c);
void ff_synth_filter_init_x86(SynthFilterContext *c);
#endif /* AVCODEC_SYNTH_FILTER_H */