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
167
168
169
|
/*
* ARM NEON optimised HEVC IDCT
* Copyright (c) 2017 Alexandra Hájková
*
* This file is part of Libav.
*
* Libav 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.
*
* Libav 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 Libav; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "libavutil/attributes.h"
#include "libavutil/cpu.h"
#include "libavutil/arm/cpu.h"
#include "libavcodec/hevcdsp.h"
void ff_hevc_add_residual_4x4_8_neon(uint8_t *_dst, int16_t *coeffs,
ptrdiff_t stride);
void ff_hevc_add_residual_4x4_10_neon(uint8_t *_dst, int16_t *coeffs,
ptrdiff_t stride);
void ff_hevc_add_residual_8x8_8_neon(uint8_t *_dst, int16_t *coeffs,
ptrdiff_t stride);
void ff_hevc_add_residual_8x8_10_neon(uint8_t *_dst, int16_t *coeffs,
ptrdiff_t stride);
void ff_hevc_add_residual_16x16_8_neon(uint8_t *_dst, int16_t *coeffs,
ptrdiff_t stride);
void ff_hevc_add_residual_16x16_10_neon(uint8_t *_dst, int16_t *coeffs,
ptrdiff_t stride);
void ff_hevc_add_residual_32x32_8_neon(uint8_t *_dst, int16_t *coeffs,
ptrdiff_t stride);
void ff_hevc_add_residual_32x32_10_neon(uint8_t *_dst, int16_t *coeffs,
ptrdiff_t stride);
void ff_hevc_idct_4x4_dc_8_neon(int16_t *coeffs);
void ff_hevc_idct_8x8_dc_8_neon(int16_t *coeffs);
void ff_hevc_idct_16x16_dc_8_neon(int16_t *coeffs);
void ff_hevc_idct_32x32_dc_8_neon(int16_t *coeffs);
void ff_hevc_idct_4x4_dc_10_neon(int16_t *coeffs);
void ff_hevc_idct_8x8_dc_10_neon(int16_t *coeffs);
void ff_hevc_idct_16x16_dc_10_neon(int16_t *coeffs);
void ff_hevc_idct_32x32_dc_10_neon(int16_t *coeffs);
void ff_hevc_idct_4x4_8_neon(int16_t *coeffs, int col_limit);
void ff_hevc_idct_8x8_8_neon(int16_t *coeffs, int col_limit);
void ff_hevc_idct_16x16_8_neon(int16_t *coeffs, int col_limit);
void ff_hevc_idct_32x32_8_neon(int16_t *coeffs, int col_limit);
void ff_hevc_idct_4x4_10_neon(int16_t *coeffs, int col_limit);
void ff_hevc_idct_8x8_10_neon(int16_t *coeffs, int col_limit);
void ff_hevc_idct_16x16_10_neon(int16_t *coeffs, int col_limit);
void ff_hevc_idct_32x32_10_neon(int16_t *coeffs, int col_limit);
void ff_hevc_get_pixels_4_8_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_4_10_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_8_8_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_8_10_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_12_8_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_12_10_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_16_8_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_16_10_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_24_8_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_24_10_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_32_8_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_32_10_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_48_8_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_48_10_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_64_8_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
void ff_hevc_get_pixels_64_10_neon(int16_t *dst, ptrdiff_t dststride, uint8_t *src,
ptrdiff_t srcstride, int height, int mx, int my,
int16_t *mcbuffer);
av_cold void ff_hevc_dsp_init_arm(HEVCDSPContext *c, int bit_depth)
{
int cpu_flags = av_get_cpu_flags();
if (have_neon(cpu_flags)) {
if (bit_depth == 8) {
c->add_residual[0] = ff_hevc_add_residual_4x4_8_neon;
c->add_residual[1] = ff_hevc_add_residual_8x8_8_neon;
c->add_residual[2] = ff_hevc_add_residual_16x16_8_neon;
c->add_residual[3] = ff_hevc_add_residual_32x32_8_neon;
c->idct_dc[0] = ff_hevc_idct_4x4_dc_8_neon;
c->idct_dc[1] = ff_hevc_idct_8x8_dc_8_neon;
c->idct_dc[2] = ff_hevc_idct_16x16_dc_8_neon;
c->idct_dc[3] = ff_hevc_idct_32x32_dc_8_neon;
c->idct[0] = ff_hevc_idct_4x4_8_neon;
c->idct[1] = ff_hevc_idct_8x8_8_neon;
c->idct[2] = ff_hevc_idct_16x16_8_neon;
c->idct[3] = ff_hevc_idct_32x32_8_neon;
c->put_hevc_qpel[0][0][0] = ff_hevc_get_pixels_4_8_neon;
c->put_hevc_qpel[0][0][1] = ff_hevc_get_pixels_8_8_neon;
c->put_hevc_qpel[0][0][2] = ff_hevc_get_pixels_12_8_neon;
c->put_hevc_qpel[0][0][3] = ff_hevc_get_pixels_16_8_neon;
c->put_hevc_qpel[0][0][4] = ff_hevc_get_pixels_24_8_neon;
c->put_hevc_qpel[0][0][5] = ff_hevc_get_pixels_32_8_neon;
c->put_hevc_qpel[0][0][6] = ff_hevc_get_pixels_48_8_neon;
c->put_hevc_qpel[0][0][7] = ff_hevc_get_pixels_64_8_neon;
}
if (bit_depth == 10) {
c->add_residual[0] = ff_hevc_add_residual_4x4_10_neon;
c->add_residual[1] = ff_hevc_add_residual_8x8_10_neon;
c->add_residual[2] = ff_hevc_add_residual_16x16_10_neon;
c->add_residual[3] = ff_hevc_add_residual_32x32_10_neon;
c->idct_dc[0] = ff_hevc_idct_4x4_dc_10_neon;
c->idct_dc[1] = ff_hevc_idct_8x8_dc_10_neon;
c->idct_dc[2] = ff_hevc_idct_16x16_dc_10_neon;
c->idct_dc[3] = ff_hevc_idct_32x32_dc_10_neon;
c->idct[0] = ff_hevc_idct_4x4_10_neon;
c->idct[1] = ff_hevc_idct_8x8_10_neon;
c->idct[2] = ff_hevc_idct_16x16_10_neon;
c->idct[3] = ff_hevc_idct_32x32_10_neon;
c->put_hevc_qpel[0][0][0] = ff_hevc_get_pixels_4_10_neon;
c->put_hevc_qpel[0][0][1] = ff_hevc_get_pixels_8_10_neon;
c->put_hevc_qpel[0][0][2] = ff_hevc_get_pixels_12_10_neon;
c->put_hevc_qpel[0][0][3] = ff_hevc_get_pixels_16_10_neon;
c->put_hevc_qpel[0][0][4] = ff_hevc_get_pixels_24_10_neon;
c->put_hevc_qpel[0][0][5] = ff_hevc_get_pixels_32_10_neon;
c->put_hevc_qpel[0][0][6] = ff_hevc_get_pixels_48_10_neon;
c->put_hevc_qpel[0][0][7] = ff_hevc_get_pixels_64_10_neon;
}
}
}
|
