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
|
/*
* 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 "config.h"
#include "libavutil/attributes.h"
#include "libavutil/aarch64/cpu.h"
#include "libavcodec/mpegvideo.h"
int ff_pix_abs16_neon(MpegEncContext *s, const uint8_t *blk1, const uint8_t *blk2,
ptrdiff_t stride, int h);
int ff_pix_abs16_xy2_neon(MpegEncContext *s, const uint8_t *blk1, const uint8_t *blk2,
ptrdiff_t stride, int h);
int ff_pix_abs16_x2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int ff_pix_abs16_y2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int ff_pix_abs8_neon(MpegEncContext *s, const uint8_t *blk1, const uint8_t *blk2,
ptrdiff_t stride, int h);
int sse16_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int sse8_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int sse4_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int vsad16_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
ptrdiff_t stride, int h);
int vsad_intra16_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
ptrdiff_t stride, int h) ;
int vsad_intra8_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
ptrdiff_t stride, int h) ;
int vsse16_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
ptrdiff_t stride, int h);
int vsse_intra16_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
ptrdiff_t stride, int h);
int nsse16_neon(int multiplier, const uint8_t *s, const uint8_t *s2,
ptrdiff_t stride, int h);
int nsse16_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
ptrdiff_t stride, int h);
int pix_median_abs16_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int pix_median_abs8_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int ff_pix_abs8_x2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int ff_pix_abs8_y2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int ff_pix_abs8_xy2_neon(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int nsse8_neon(int multiplier, const uint8_t *s, const uint8_t *s2,
ptrdiff_t stride, int h);
int nsse8_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
ptrdiff_t stride, int h);
int vsse8_neon(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
ptrdiff_t stride, int h);
int vsse_intra8_neon(MpegEncContext *c, const uint8_t *s, const uint8_t *dummy,
ptrdiff_t stride, int h);
#if HAVE_DOTPROD
int sse16_neon_dotprod(MpegEncContext *v, const uint8_t *pix1, const uint8_t *pix2,
ptrdiff_t stride, int h);
int vsse_intra16_neon_dotprod(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
ptrdiff_t stride, int h);
#endif
av_cold void ff_me_cmp_init_aarch64(MECmpContext *c, AVCodecContext *avctx)
{
int cpu_flags = av_get_cpu_flags();
if (have_neon(cpu_flags)) {
c->pix_abs[0][0] = ff_pix_abs16_neon;
c->pix_abs[0][1] = ff_pix_abs16_x2_neon;
c->pix_abs[0][2] = ff_pix_abs16_y2_neon;
c->pix_abs[0][3] = ff_pix_abs16_xy2_neon;
c->pix_abs[1][0] = ff_pix_abs8_neon;
c->pix_abs[1][1] = ff_pix_abs8_x2_neon;
c->pix_abs[1][2] = ff_pix_abs8_y2_neon;
c->pix_abs[1][3] = ff_pix_abs8_xy2_neon;
c->sad[0] = ff_pix_abs16_neon;
c->sad[1] = ff_pix_abs8_neon;
c->sse[0] = sse16_neon;
c->sse[1] = sse8_neon;
c->sse[2] = sse4_neon;
c->vsad[0] = vsad16_neon;
c->vsad[4] = vsad_intra16_neon;
c->vsad[5] = vsad_intra8_neon;
c->vsse[0] = vsse16_neon;
c->vsse[1] = vsse8_neon;
c->vsse[4] = vsse_intra16_neon;
c->vsse[5] = vsse_intra8_neon;
c->nsse[0] = nsse16_neon_wrapper;
c->nsse[1] = nsse8_neon_wrapper;
c->median_sad[0] = pix_median_abs16_neon;
c->median_sad[1] = pix_median_abs8_neon;
}
#if HAVE_DOTPROD
if (have_dotprod(cpu_flags)) {
c->sse[0] = sse16_neon_dotprod;
c->vsse[4] = vsse_intra16_neon_dotprod;
}
#endif
}
int nsse16_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
ptrdiff_t stride, int h)
{
if (c)
return nsse16_neon(c->avctx->nsse_weight, s1, s2, stride, h);
else
return nsse16_neon(8, s1, s2, stride, h);
}
int nsse8_neon_wrapper(MpegEncContext *c, const uint8_t *s1, const uint8_t *s2,
ptrdiff_t stride, int h)
{
if (c)
return nsse8_neon(c->avctx->nsse_weight, s1, s2, stride, h);
else
return nsse8_neon(8, s1, s2, stride, h);
}
|
