mirror of
https://mirror.skon.top/https://github.com/FFmpeg/FFmpeg
synced 2026-04-20 21:00:41 +08:00
Add NEON-optimized implementation for HEVC intra DC prediction at 8-bit
depth, supporting all block sizes (4x4 to 32x32).
DC prediction computes the average of top and left reference samples
using uaddlv, with urshr for rounded division. For luma blocks smaller
than 32x32, edge smoothing is applied: the first row and column are
blended toward the reference using (ref[i] + 3*dc + 2) >> 2 computed
entirely in the NEON domain. Fill stores use pre-computed address
patterns to break dependency chains.
Also adds the aarch64 initialization framework (Makefile, pred.c/pred.h
hooks, hevcpred_init_aarch64.c).
Speedup over C on Apple M4 (checkasm --bench):
4x4: 2.28x 8x8: 3.14x 16x16: 3.29x 32x32: 3.02x
Signed-off-by: Jun Zhao <barryjzhao@tencent.com>
50 lines
1.8 KiB
C
50 lines
1.8 KiB
C
/*
|
|
* HEVC video Decoder
|
|
*
|
|
* Copyright (C) 2012 - 2013 Guillaume Martres
|
|
*
|
|
* 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_HEVC_PRED_H
|
|
#define AVCODEC_HEVC_PRED_H
|
|
|
|
#include <stddef.h>
|
|
#include <stdint.h>
|
|
|
|
struct HEVCLocalContext;
|
|
struct HEVCPPS;
|
|
|
|
typedef struct HEVCPredContext {
|
|
void (*intra_pred[4])(struct HEVCLocalContext *lc,
|
|
const struct HEVCPPS *pps, int x0, int y0, int c_idx);
|
|
|
|
void (*pred_planar[4])(uint8_t *src, const uint8_t *top,
|
|
const uint8_t *left, ptrdiff_t stride);
|
|
void (*pred_dc)(uint8_t *src, const uint8_t *top, const uint8_t *left,
|
|
ptrdiff_t stride, int log2_size, int c_idx);
|
|
void (*pred_angular[4])(uint8_t *src, const uint8_t *top,
|
|
const uint8_t *left, ptrdiff_t stride,
|
|
int c_idx, int mode);
|
|
} HEVCPredContext;
|
|
|
|
void ff_hevc_pred_init(HEVCPredContext *hpc, int bit_depth);
|
|
void ff_hevc_pred_init_mips(HEVCPredContext *hpc, int bit_depth);
|
|
void ff_hevc_pred_init_aarch64(HEVCPredContext *hpc, int bit_depth);
|
|
|
|
#endif /* AVCODEC_HEVC_PRED_H */
|