1
0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-11-26 19:01:44 +02:00
FFmpeg/libavcodec/vp3dsp.h
gxw d86f698e38 avcodec/mips: [loongson] optimize theora decoding in vp3dsp.
Optimize theora decoding with msa in functions:
1. ff_vp3_idct_add_msa
2. ff_vp3_idct_put_msa
3. ff_vp3_idct_dc_add_msa
4. ff_vp3_v_loop_filter_msa
5. ff_vp3_h_loop_filter_msa
6. ff_put_no_rnd_pixels_l2_msa

Theora decoding speed improved about 36%(from 22fps to 30fps, Tested on loongson 2K1000).

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>
2018-12-27 23:12:04 +01:00

55 lines
2.1 KiB
C

/*
* 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_VP3DSP_H
#define AVCODEC_VP3DSP_H
#include <stddef.h>
#include <stdint.h>
typedef struct VP3DSPContext {
/**
* Copy 8xH pixels from source to destination buffer using a bilinear
* filter with no rounding (i.e. *dst = (*a + *b) >> 1).
*
* @param dst destination buffer, aligned by 8
* @param a first source buffer, no alignment
* @param b second source buffer, no alignment
* @param stride distance between two lines in source/dest buffers
* @param h height
*/
void (*put_no_rnd_pixels_l2)(uint8_t *dst,
const uint8_t *a,
const uint8_t *b,
ptrdiff_t stride, int h);
void (*idct_put)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void (*idct_add)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void (*idct_dc_add)(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void (*v_loop_filter)(uint8_t *src, ptrdiff_t stride, int *bounding_values);
void (*h_loop_filter)(uint8_t *src, ptrdiff_t stride, int *bounding_values);
} VP3DSPContext;
void ff_vp3dsp_init(VP3DSPContext *c, int flags);
void ff_vp3dsp_init_arm(VP3DSPContext *c, int flags);
void ff_vp3dsp_init_ppc(VP3DSPContext *c, int flags);
void ff_vp3dsp_init_x86(VP3DSPContext *c, int flags);
void ff_vp3dsp_init_mips(VP3DSPContext *c, int flags);
#endif /* AVCODEC_VP3DSP_H */