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
|
/*
* 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 "libavcodec/vc1dsp.h"
#include "vc1dsp.h"
void ff_vc1_inv_trans_8x8_neon(int16_t *block);
void ff_vc1_inv_trans_4x8_neon(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void ff_vc1_inv_trans_8x4_neon(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void ff_vc1_inv_trans_4x4_neon(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void ff_vc1_inv_trans_8x8_dc_neon(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void ff_vc1_inv_trans_4x8_dc_neon(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void ff_vc1_inv_trans_8x4_dc_neon(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void ff_vc1_inv_trans_4x4_dc_neon(uint8_t *dest, ptrdiff_t stride, int16_t *block);
void ff_vc1_v_loop_filter4_neon(uint8_t *src, int stride, int pq);
void ff_vc1_h_loop_filter4_neon(uint8_t *src, int stride, int pq);
void ff_vc1_v_loop_filter8_neon(uint8_t *src, int stride, int pq);
void ff_vc1_h_loop_filter8_neon(uint8_t *src, int stride, int pq);
void ff_vc1_v_loop_filter16_neon(uint8_t *src, int stride, int pq);
void ff_vc1_h_loop_filter16_neon(uint8_t *src, int stride, int pq);
void ff_put_pixels8x8_neon(uint8_t *block, const uint8_t *pixels,
ptrdiff_t line_size, int rnd);
#define DECL_PUT(X, Y) \
void ff_put_vc1_mspel_mc##X##Y##_neon(uint8_t *dst, const uint8_t *src, \
ptrdiff_t stride, int rnd); \
static void ff_put_vc1_mspel_mc##X##Y##_16_neon(uint8_t *dst, const uint8_t *src, \
ptrdiff_t stride, int rnd) \
{ \
ff_put_vc1_mspel_mc##X##Y##_neon(dst+0, src+0, stride, rnd); \
ff_put_vc1_mspel_mc##X##Y##_neon(dst+8, src+8, stride, rnd); \
dst += 8*stride; src += 8*stride; \
ff_put_vc1_mspel_mc##X##Y##_neon(dst+0, src+0, stride, rnd); \
ff_put_vc1_mspel_mc##X##Y##_neon(dst+8, src+8, stride, rnd); \
}
DECL_PUT(1, 0)
DECL_PUT(2, 0)
DECL_PUT(3, 0)
DECL_PUT(0, 1)
DECL_PUT(0, 2)
DECL_PUT(0, 3)
DECL_PUT(1, 1)
DECL_PUT(1, 2)
DECL_PUT(1, 3)
DECL_PUT(2, 1)
DECL_PUT(2, 2)
DECL_PUT(2, 3)
DECL_PUT(3, 1)
DECL_PUT(3, 2)
DECL_PUT(3, 3)
void ff_put_vc1_chroma_mc8_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
int h, int x, int y);
void ff_avg_vc1_chroma_mc8_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
int h, int x, int y);
void ff_put_vc1_chroma_mc4_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
int h, int x, int y);
void ff_avg_vc1_chroma_mc4_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride,
int h, int x, int y);
#define FN_ASSIGN(X, Y) \
dsp->put_vc1_mspel_pixels_tab[0][X+4*Y] = ff_put_vc1_mspel_mc##X##Y##_16_neon; \
dsp->put_vc1_mspel_pixels_tab[1][X+4*Y] = ff_put_vc1_mspel_mc##X##Y##_neon
av_cold void ff_vc1dsp_init_neon(VC1DSPContext *dsp)
{
dsp->vc1_inv_trans_8x8 = ff_vc1_inv_trans_8x8_neon;
dsp->vc1_inv_trans_4x8 = ff_vc1_inv_trans_4x8_neon;
dsp->vc1_inv_trans_8x4 = ff_vc1_inv_trans_8x4_neon;
dsp->vc1_inv_trans_4x4 = ff_vc1_inv_trans_4x4_neon;
dsp->vc1_inv_trans_8x8_dc = ff_vc1_inv_trans_8x8_dc_neon;
dsp->vc1_inv_trans_4x8_dc = ff_vc1_inv_trans_4x8_dc_neon;
dsp->vc1_inv_trans_8x4_dc = ff_vc1_inv_trans_8x4_dc_neon;
dsp->vc1_inv_trans_4x4_dc = ff_vc1_inv_trans_4x4_dc_neon;
dsp->vc1_v_loop_filter4 = ff_vc1_v_loop_filter4_neon;
dsp->vc1_h_loop_filter4 = ff_vc1_h_loop_filter4_neon;
dsp->vc1_v_loop_filter8 = ff_vc1_v_loop_filter8_neon;
dsp->vc1_h_loop_filter8 = ff_vc1_h_loop_filter8_neon;
dsp->vc1_v_loop_filter16 = ff_vc1_v_loop_filter16_neon;
dsp->vc1_h_loop_filter16 = ff_vc1_h_loop_filter16_neon;
dsp->put_vc1_mspel_pixels_tab[1][ 0] = ff_put_pixels8x8_neon;
FN_ASSIGN(1, 0);
FN_ASSIGN(2, 0);
FN_ASSIGN(3, 0);
FN_ASSIGN(0, 1);
FN_ASSIGN(1, 1);
FN_ASSIGN(2, 1);
FN_ASSIGN(3, 1);
FN_ASSIGN(0, 2);
FN_ASSIGN(1, 2);
FN_ASSIGN(2, 2);
FN_ASSIGN(3, 2);
FN_ASSIGN(0, 3);
FN_ASSIGN(1, 3);
FN_ASSIGN(2, 3);
FN_ASSIGN(3, 3);
dsp->put_no_rnd_vc1_chroma_pixels_tab[0] = ff_put_vc1_chroma_mc8_neon;
dsp->avg_no_rnd_vc1_chroma_pixels_tab[0] = ff_avg_vc1_chroma_mc8_neon;
dsp->put_no_rnd_vc1_chroma_pixels_tab[1] = ff_put_vc1_chroma_mc4_neon;
dsp->avg_no_rnd_vc1_chroma_pixels_tab[1] = ff_avg_vc1_chroma_mc4_neon;
}
|
