mirror of
https://github.com/FFmpeg/FFmpeg.git
synced 2024-11-21 10:55:51 +02:00
bf0470a5be
* commit '36e3b1f2fd262028834a9d7b1eb533c1218ee6c2': aarch64: h264 loop filter NEON optimizations Merged-by: Michael Niedermayer <michaelni@gmx.at>
77 lines
3.5 KiB
C
77 lines
3.5 KiB
C
/*
|
|
* Copyright (c) 2010 Mans Rullgard <mans@mansr.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 <stdint.h>
|
|
|
|
#include "libavutil/attributes.h"
|
|
#include "libavutil/cpu.h"
|
|
#include "libavutil/aarch64/cpu.h"
|
|
#include "libavcodec/h264dsp.h"
|
|
|
|
void ff_h264_v_loop_filter_luma_neon(uint8_t *pix, int stride, int alpha,
|
|
int beta, int8_t *tc0);
|
|
void ff_h264_h_loop_filter_luma_neon(uint8_t *pix, int stride, int alpha,
|
|
int beta, int8_t *tc0);
|
|
void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, int stride, int alpha,
|
|
int beta, int8_t *tc0);
|
|
void ff_h264_h_loop_filter_chroma_neon(uint8_t *pix, int stride, int alpha,
|
|
int beta, int8_t *tc0);
|
|
|
|
void ff_h264_idct_add_neon(uint8_t *dst, int16_t *block, int stride);
|
|
void ff_h264_idct_dc_add_neon(uint8_t *dst, int16_t *block, int stride);
|
|
void ff_h264_idct_add16_neon(uint8_t *dst, const int *block_offset,
|
|
int16_t *block, int stride,
|
|
const uint8_t nnzc[6*8]);
|
|
void ff_h264_idct_add16intra_neon(uint8_t *dst, const int *block_offset,
|
|
int16_t *block, int stride,
|
|
const uint8_t nnzc[6*8]);
|
|
void ff_h264_idct_add8_neon(uint8_t **dest, const int *block_offset,
|
|
int16_t *block, int stride,
|
|
const uint8_t nnzc[6*8]);
|
|
|
|
void ff_h264_idct8_add_neon(uint8_t *dst, int16_t *block, int stride);
|
|
void ff_h264_idct8_dc_add_neon(uint8_t *dst, int16_t *block, int stride);
|
|
void ff_h264_idct8_add4_neon(uint8_t *dst, const int *block_offset,
|
|
int16_t *block, int stride,
|
|
const uint8_t nnzc[6*8]);
|
|
|
|
av_cold void ff_h264dsp_init_aarch64(H264DSPContext *c, const int bit_depth,
|
|
const int chroma_format_idc)
|
|
{
|
|
int cpu_flags = av_get_cpu_flags();
|
|
|
|
if (have_neon(cpu_flags) && bit_depth == 8) {
|
|
c->h264_v_loop_filter_luma = ff_h264_v_loop_filter_luma_neon;
|
|
c->h264_h_loop_filter_luma = ff_h264_h_loop_filter_luma_neon;
|
|
c->h264_v_loop_filter_chroma = ff_h264_v_loop_filter_chroma_neon;
|
|
c->h264_h_loop_filter_chroma = ff_h264_h_loop_filter_chroma_neon;
|
|
|
|
c->h264_idct_add = ff_h264_idct_add_neon;
|
|
c->h264_idct_dc_add = ff_h264_idct_dc_add_neon;
|
|
c->h264_idct_add16 = ff_h264_idct_add16_neon;
|
|
c->h264_idct_add16intra = ff_h264_idct_add16intra_neon;
|
|
if (chroma_format_idc <= 1)
|
|
c->h264_idct_add8 = ff_h264_idct_add8_neon;
|
|
c->h264_idct8_add = ff_h264_idct8_add_neon;
|
|
c->h264_idct8_dc_add = ff_h264_idct8_dc_add_neon;
|
|
c->h264_idct8_add4 = ff_h264_idct8_add4_neon;
|
|
}
|
|
}
|