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
|
/*
* Copyright (c) 2024 Institue of Software Chinese Academy of Sciences (ISCAS).
*
* 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 "config.h"
#include "libavutil/attributes.h"
#include "libavutil/cpu.h"
#include "libavutil/riscv/cpu.h"
#include "libavcodec/vp8dsp.h"
#include "vp8dsp.h"
void ff_vp8_idct_dc_add_rvv(uint8_t *dst, int16_t block[16], ptrdiff_t stride);
void ff_vp8_idct_dc_add4y_rvv(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride);
void ff_vp8_idct_dc_add4uv_rvv(uint8_t *dst, int16_t block[4][16], ptrdiff_t stride);
VP8_EPEL(16, rvi);
VP8_EPEL(8, rvi);
VP8_EPEL(4, rvi);
VP8_EPEL(16, rvv);
VP8_EPEL(8, rvv);
VP8_EPEL(4, rvv);
VP8_BILIN(16, rvv);
VP8_BILIN(8, rvv);
VP8_BILIN(4, rvv);
av_cold void ff_vp78dsp_init_riscv(VP8DSPContext *c)
{
#if HAVE_RV
int flags = av_get_cpu_flags();
if (flags & AV_CPU_FLAG_RV_MISALIGNED) {
#if __riscv_xlen >= 64
c->put_vp8_epel_pixels_tab[0][0][0] = ff_put_vp8_pixels16_rvi;
c->put_vp8_epel_pixels_tab[1][0][0] = ff_put_vp8_pixels8_rvi;
c->put_vp8_bilinear_pixels_tab[0][0][0] = ff_put_vp8_pixels16_rvi;
c->put_vp8_bilinear_pixels_tab[1][0][0] = ff_put_vp8_pixels8_rvi;
#endif
c->put_vp8_epel_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvi;
c->put_vp8_bilinear_pixels_tab[2][0][0] = ff_put_vp8_pixels4_rvi;
}
#if HAVE_RVV
if (flags & AV_CPU_FLAG_RVV_I32 && ff_rv_vlen_least(128)) {
c->put_vp8_bilinear_pixels_tab[0][0][1] = ff_put_vp8_bilin16_h_rvv;
c->put_vp8_bilinear_pixels_tab[0][0][2] = ff_put_vp8_bilin16_h_rvv;
c->put_vp8_bilinear_pixels_tab[1][0][1] = ff_put_vp8_bilin8_h_rvv;
c->put_vp8_bilinear_pixels_tab[1][0][2] = ff_put_vp8_bilin8_h_rvv;
c->put_vp8_bilinear_pixels_tab[2][0][1] = ff_put_vp8_bilin4_h_rvv;
c->put_vp8_bilinear_pixels_tab[2][0][2] = ff_put_vp8_bilin4_h_rvv;
c->put_vp8_bilinear_pixels_tab[0][1][0] = ff_put_vp8_bilin16_v_rvv;
c->put_vp8_bilinear_pixels_tab[0][2][0] = ff_put_vp8_bilin16_v_rvv;
c->put_vp8_bilinear_pixels_tab[1][1][0] = ff_put_vp8_bilin8_v_rvv;
c->put_vp8_bilinear_pixels_tab[1][2][0] = ff_put_vp8_bilin8_v_rvv;
c->put_vp8_bilinear_pixels_tab[2][1][0] = ff_put_vp8_bilin4_v_rvv;
c->put_vp8_bilinear_pixels_tab[2][2][0] = ff_put_vp8_bilin4_v_rvv;
c->put_vp8_bilinear_pixels_tab[0][1][1] = ff_put_vp8_bilin16_hv_rvv;
c->put_vp8_bilinear_pixels_tab[0][1][2] = ff_put_vp8_bilin16_hv_rvv;
c->put_vp8_bilinear_pixels_tab[0][2][1] = ff_put_vp8_bilin16_hv_rvv;
c->put_vp8_bilinear_pixels_tab[0][2][2] = ff_put_vp8_bilin16_hv_rvv;
c->put_vp8_bilinear_pixels_tab[1][1][1] = ff_put_vp8_bilin8_hv_rvv;
c->put_vp8_bilinear_pixels_tab[1][1][2] = ff_put_vp8_bilin8_hv_rvv;
c->put_vp8_bilinear_pixels_tab[1][2][1] = ff_put_vp8_bilin8_hv_rvv;
c->put_vp8_bilinear_pixels_tab[1][2][2] = ff_put_vp8_bilin8_hv_rvv;
c->put_vp8_bilinear_pixels_tab[2][1][1] = ff_put_vp8_bilin4_hv_rvv;
c->put_vp8_bilinear_pixels_tab[2][1][2] = ff_put_vp8_bilin4_hv_rvv;
c->put_vp8_bilinear_pixels_tab[2][2][1] = ff_put_vp8_bilin4_hv_rvv;
c->put_vp8_bilinear_pixels_tab[2][2][2] = ff_put_vp8_bilin4_hv_rvv;
c->put_vp8_epel_pixels_tab[0][0][2] = ff_put_vp8_epel16_h6_rvv;
c->put_vp8_epel_pixels_tab[1][0][2] = ff_put_vp8_epel8_h6_rvv;
c->put_vp8_epel_pixels_tab[2][0][2] = ff_put_vp8_epel4_h6_rvv;
c->put_vp8_epel_pixels_tab[0][0][1] = ff_put_vp8_epel16_h4_rvv;
c->put_vp8_epel_pixels_tab[1][0][1] = ff_put_vp8_epel8_h4_rvv;
c->put_vp8_epel_pixels_tab[2][0][1] = ff_put_vp8_epel4_h4_rvv;
c->put_vp8_epel_pixels_tab[0][2][0] = ff_put_vp8_epel16_v6_rvv;
c->put_vp8_epel_pixels_tab[1][2][0] = ff_put_vp8_epel8_v6_rvv;
c->put_vp8_epel_pixels_tab[2][2][0] = ff_put_vp8_epel4_v6_rvv;
c->put_vp8_epel_pixels_tab[0][1][0] = ff_put_vp8_epel16_v4_rvv;
c->put_vp8_epel_pixels_tab[1][1][0] = ff_put_vp8_epel8_v4_rvv;
c->put_vp8_epel_pixels_tab[2][1][0] = ff_put_vp8_epel4_v4_rvv;
}
#endif
#endif
}
av_cold void ff_vp8dsp_init_riscv(VP8DSPContext *c)
{
#if HAVE_RVV
int flags = av_get_cpu_flags();
if (flags & AV_CPU_FLAG_RVV_I32 && ff_rv_vlen_least(128)) {
c->vp8_idct_dc_add = ff_vp8_idct_dc_add_rvv;
c->vp8_idct_dc_add4y = ff_vp8_idct_dc_add4y_rvv;
if (flags & AV_CPU_FLAG_RVB_ADDR) {
c->vp8_idct_dc_add4uv = ff_vp8_idct_dc_add4uv_rvv;
}
}
#endif
}
|
