mirror of
https://git.ffmpeg.org/ffmpeg.git
synced 2026-06-12 08:43:06 +00:00
Jun ZhaoandJun Zhao
cfa3ceac7a
Add NEON-optimized implementations for HEVC angular intra prediction
modes 10 (pure horizontal) and 26 (pure vertical) at 8-bit depth.
Mode 10 (Horizontal):
- Broadcasts left[y] to fill each row using ld2r/ld4r for efficiency
- Applies edge smoothing for luma blocks smaller than 32x32
Mode 26 (Vertical):
- Copies top reference row to all output rows
- Applies edge smoothing for luma blocks smaller than 32x32
Edge smoothing uses uhsub+usqadd to compute the filtered result
directly in 8-bit, avoiding widening to 16-bit intermediates.
The C pred_angular wrappers are made non-static with ff_ prefix to
allow the NEON dispatch to fall back to C for modes not yet optimized.
This will be reverted once all angular modes are implemented.
Note: since pred_angular[] is a per-size function pointer (not
per-mode), checkasm benchmarks will show '_neon' for all 33 modes
even though only modes 10/26 are truly accelerated; unoptimized
modes show ~1.0x speedup as they pass through the NEON wrapper to
the C fallback with negligible overhead.
Speedup over C on Apple M4 (checkasm --bench, 15-run average):
Mode 10 (Horizontal):
4x4: 4.66x 8x8: 5.80x 16x16: 16.86x 32x32: 24.89x
Mode 26 (Vertical):
4x4: 1.16x 8x8: 1.83x 16x16: 2.45x 32x32: 4.50x
Signed-off-by: Jun Zhao <barryjzhao@tencent.com>
89 lines
2.7 KiB
C
89 lines
2.7 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
|
|
*/
|
|
|
|
#include "hevcdec.h"
|
|
|
|
#include "pred.h"
|
|
|
|
#define BIT_DEPTH 8
|
|
#include "pred_template.c"
|
|
#undef BIT_DEPTH
|
|
|
|
#define BIT_DEPTH 9
|
|
#include "pred_template.c"
|
|
#undef BIT_DEPTH
|
|
|
|
#define BIT_DEPTH 10
|
|
#include "pred_template.c"
|
|
#undef BIT_DEPTH
|
|
|
|
#define BIT_DEPTH 12
|
|
#include "pred_template.c"
|
|
#undef BIT_DEPTH
|
|
|
|
void ff_hevc_pred_init(HEVCPredContext *hpc, int bit_depth)
|
|
{
|
|
#undef FUNC
|
|
#define FUNC(a, depth) a ## _ ## depth
|
|
|
|
#define HEVC_PRED(depth) \
|
|
hpc->intra_pred[0] = FUNC(intra_pred_2, depth); \
|
|
hpc->intra_pred[1] = FUNC(intra_pred_3, depth); \
|
|
hpc->intra_pred[2] = FUNC(intra_pred_4, depth); \
|
|
hpc->intra_pred[3] = FUNC(intra_pred_5, depth); \
|
|
hpc->pred_planar[0] = FUNC(pred_planar_0, depth); \
|
|
hpc->pred_planar[1] = FUNC(pred_planar_1, depth); \
|
|
hpc->pred_planar[2] = FUNC(pred_planar_2, depth); \
|
|
hpc->pred_planar[3] = FUNC(pred_planar_3, depth); \
|
|
hpc->pred_dc = FUNC(pred_dc, depth); \
|
|
hpc->pred_angular[0] = FUNC(ff_hevc_pred_angular_0, depth); \
|
|
hpc->pred_angular[1] = FUNC(ff_hevc_pred_angular_1, depth); \
|
|
hpc->pred_angular[2] = FUNC(ff_hevc_pred_angular_2, depth); \
|
|
hpc->pred_angular[3] = FUNC(ff_hevc_pred_angular_3, depth); \
|
|
hpc->ref_filter_3tap[0] = FUNC(ref_filter_3tap, depth); \
|
|
hpc->ref_filter_3tap[1] = FUNC(ref_filter_3tap, depth); \
|
|
hpc->ref_filter_3tap[2] = FUNC(ref_filter_3tap, depth); \
|
|
hpc->ref_filter_strong = FUNC(ref_filter_strong, depth);
|
|
|
|
switch (bit_depth) {
|
|
case 9:
|
|
HEVC_PRED(9);
|
|
break;
|
|
case 10:
|
|
HEVC_PRED(10);
|
|
break;
|
|
case 12:
|
|
HEVC_PRED(12);
|
|
break;
|
|
default:
|
|
HEVC_PRED(8);
|
|
break;
|
|
}
|
|
|
|
#if ARCH_AARCH64
|
|
ff_hevc_pred_init_aarch64(hpc, bit_depth);
|
|
#endif
|
|
#if ARCH_MIPS
|
|
ff_hevc_pred_init_mips(hpc, bit_depth);
|
|
#endif
|
|
}
|