1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
|
/*
* 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, ptrdiff_t stride, int alpha,
int beta, int8_t *tc0);
void ff_h264_h_loop_filter_luma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta, int8_t *tc0);
void ff_h264_v_loop_filter_luma_intra_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta);
void ff_h264_h_loop_filter_luma_intra_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta);
void ff_h264_v_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta, int8_t *tc0);
void ff_h264_h_loop_filter_chroma_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta, int8_t *tc0);
void ff_h264_h_loop_filter_chroma422_neon(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta, int8_t *tc0);
void ff_h264_v_loop_filter_chroma_intra_neon(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta);
void ff_h264_h_loop_filter_chroma_intra_neon(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta);
void ff_h264_h_loop_filter_chroma422_intra_neon(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta);
void ff_h264_h_loop_filter_chroma_mbaff_intra_neon(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta);
void ff_weight_h264_pixels_16_neon(uint8_t *dst, ptrdiff_t stride, int height,
int log2_den, int weight, int offset);
void ff_weight_h264_pixels_8_neon(uint8_t *dst, ptrdiff_t stride, int height,
int log2_den, int weight, int offset);
void ff_weight_h264_pixels_4_neon(uint8_t *dst, ptrdiff_t stride, int height,
int log2_den, int weight, int offset);
void ff_biweight_h264_pixels_16_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
int height, int log2_den, int weightd,
int weights, int offset);
void ff_biweight_h264_pixels_8_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
int height, int log2_den, int weightd,
int weights, int offset);
void ff_biweight_h264_pixels_4_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
int height, int log2_den, int weightd,
int weights, int offset);
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[5 * 8]);
void ff_h264_idct_add16intra_neon(uint8_t *dst, const int *block_offset,
int16_t *block, int stride,
const uint8_t nnzc[5 * 8]);
void ff_h264_idct_add8_neon(uint8_t **dest, const int *block_offset,
int16_t *block, int stride,
const uint8_t nnzc[15 * 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[5 * 8]);
void ff_h264_v_loop_filter_luma_neon_10(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta, int8_t *tc0);
void ff_h264_h_loop_filter_luma_neon_10(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta, int8_t *tc0);
void ff_h264_v_loop_filter_luma_intra_neon_10(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta);
void ff_h264_h_loop_filter_luma_intra_neon_10(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta);
void ff_h264_v_loop_filter_chroma_neon_10(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta, int8_t *tc0);
void ff_h264_h_loop_filter_chroma_neon_10(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta, int8_t *tc0);
void ff_h264_h_loop_filter_chroma422_neon_10(uint8_t *pix, ptrdiff_t stride, int alpha,
int beta, int8_t *tc0);
void ff_h264_v_loop_filter_chroma_intra_neon_10(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta);
void ff_h264_h_loop_filter_chroma_intra_neon_10(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta);
void ff_h264_h_loop_filter_chroma422_intra_neon_10(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta);
void ff_h264_h_loop_filter_chroma_mbaff_intra_neon_10(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta);
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_luma_intra= ff_h264_v_loop_filter_luma_intra_neon;
c->h264_h_loop_filter_luma_intra= ff_h264_h_loop_filter_luma_intra_neon;
c->h264_v_loop_filter_chroma = ff_h264_v_loop_filter_chroma_neon;
c->h264_v_loop_filter_chroma_intra = ff_h264_v_loop_filter_chroma_intra_neon;
if (chroma_format_idc <= 1) {
c->h264_h_loop_filter_chroma = ff_h264_h_loop_filter_chroma_neon;
c->h264_h_loop_filter_chroma_intra = ff_h264_h_loop_filter_chroma_intra_neon;
c->h264_h_loop_filter_chroma_mbaff_intra = ff_h264_h_loop_filter_chroma_mbaff_intra_neon;
} else {
c->h264_h_loop_filter_chroma = ff_h264_h_loop_filter_chroma422_neon;
c->h264_h_loop_filter_chroma_mbaff = ff_h264_h_loop_filter_chroma_neon;
c->h264_h_loop_filter_chroma_intra = ff_h264_h_loop_filter_chroma422_intra_neon;
c->h264_h_loop_filter_chroma_mbaff_intra = ff_h264_h_loop_filter_chroma_intra_neon;
}
c->weight_h264_pixels_tab[0] = ff_weight_h264_pixels_16_neon;
c->weight_h264_pixels_tab[1] = ff_weight_h264_pixels_8_neon;
c->weight_h264_pixels_tab[2] = ff_weight_h264_pixels_4_neon;
c->biweight_h264_pixels_tab[0] = ff_biweight_h264_pixels_16_neon;
c->biweight_h264_pixels_tab[1] = ff_biweight_h264_pixels_8_neon;
c->biweight_h264_pixels_tab[2] = ff_biweight_h264_pixels_4_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;
} else if (have_neon(cpu_flags) && bit_depth == 10) {
c->h264_v_loop_filter_chroma = ff_h264_v_loop_filter_chroma_neon_10;
c->h264_v_loop_filter_chroma_intra = ff_h264_v_loop_filter_chroma_intra_neon_10;
if (chroma_format_idc <= 1) {
c->h264_h_loop_filter_chroma = ff_h264_h_loop_filter_chroma_neon_10;
c->h264_h_loop_filter_chroma_intra = ff_h264_h_loop_filter_chroma_intra_neon_10;
c->h264_h_loop_filter_chroma_mbaff_intra = ff_h264_h_loop_filter_chroma_mbaff_intra_neon_10;
} else {
c->h264_h_loop_filter_chroma = ff_h264_h_loop_filter_chroma422_neon_10;
c->h264_h_loop_filter_chroma_mbaff = ff_h264_h_loop_filter_chroma_neon_10;
c->h264_h_loop_filter_chroma_intra = ff_h264_h_loop_filter_chroma422_intra_neon_10;
c->h264_h_loop_filter_chroma_mbaff_intra = ff_h264_h_loop_filter_chroma_intra_neon_10;
}
}
}
|
