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
|
/*
* Copyright © 2024 Rémi Denis-Courmont.
*
* 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 <stdint.h>
#include <string.h>
#include "libavutil/attributes.h"
#include "libavutil/cpu.h"
#include "libavutil/riscv/cpu.h"
#include "libavcodec/h264dsp.h"
extern const struct {
const h264_weight_func weight;
const h264_biweight_func biweight;
} ff_h264_weight_funcs_8_rvv[];
void ff_h264_v_loop_filter_luma_8_rvv(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t *tc0);
void ff_h264_h_loop_filter_luma_8_rvv(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t *tc0);
void ff_h264_h_loop_filter_luma_mbaff_8_rvv(uint8_t *pix, ptrdiff_t stride,
int alpha, int beta, int8_t *tc0);
void ff_h264_idct_add_8_rvv(uint8_t *dst, int16_t *block, int stride);
void ff_h264_idct8_add_8_rvv(uint8_t *dst, int16_t *block, int stride);
void ff_h264_idct_add16_8_rvv(uint8_t *dst, const int *blockoffset,
int16_t *block, int stride,
const uint8_t nnzc[5 * 8]);
void ff_h264_idct_add16intra_8_rvv(uint8_t *dst, const int *blockoffset,
int16_t *block, int stride,
const uint8_t nnzc[5 * 8]);
void ff_h264_idct8_add4_8_rvv(uint8_t *dst, const int *blockoffset,
int16_t *block, int stride,
const uint8_t nnzc[5 * 8]);
void ff_h264_idct_add_9_rvv(uint8_t *dst, int16_t *block, int stride);
void ff_h264_idct_add_10_rvv(uint8_t *dst, int16_t *block, int stride);
void ff_h264_idct_add_12_rvv(uint8_t *dst, int16_t *block, int stride);
void ff_h264_idct_add_14_rvv(uint8_t *dst, int16_t *block, int stride);
extern int ff_startcode_find_candidate_rvb(const uint8_t *, int);
extern int ff_startcode_find_candidate_rvv(const uint8_t *, int);
av_cold void ff_h264dsp_init_riscv(H264DSPContext *dsp, const int bit_depth,
const int chroma_format_idc)
{
#if HAVE_RV
int flags = av_get_cpu_flags();
if (flags & AV_CPU_FLAG_RVB_BASIC)
dsp->startcode_find_candidate = ff_startcode_find_candidate_rvb;
# if HAVE_RVV
if (flags & AV_CPU_FLAG_RVV_I32) {
const bool zvl128b = ff_rv_vlen_least(128);
if (bit_depth == 8 && zvl128b) {
for (int i = 0; i < 4; i++) {
dsp->weight_h264_pixels_tab[i] =
ff_h264_weight_funcs_8_rvv[i].weight;
dsp->biweight_h264_pixels_tab[i] =
ff_h264_weight_funcs_8_rvv[i].biweight;
}
dsp->h264_v_loop_filter_luma = ff_h264_v_loop_filter_luma_8_rvv;
dsp->h264_h_loop_filter_luma = ff_h264_h_loop_filter_luma_8_rvv;
dsp->h264_h_loop_filter_luma_mbaff =
ff_h264_h_loop_filter_luma_mbaff_8_rvv;
dsp->h264_idct_add = ff_h264_idct_add_8_rvv;
dsp->h264_idct8_add = ff_h264_idct8_add_8_rvv;
# if __riscv_xlen == 64
dsp->h264_idct_add16 = ff_h264_idct_add16_8_rvv;
dsp->h264_idct_add16intra = ff_h264_idct_add16intra_8_rvv;
dsp->h264_idct8_add4 = ff_h264_idct8_add4_8_rvv;
# endif
}
if (bit_depth == 9 && zvl128b)
dsp->h264_idct_add = ff_h264_idct_add_9_rvv;
if (bit_depth == 10 && zvl128b)
dsp->h264_idct_add = ff_h264_idct_add_10_rvv;
if (bit_depth == 12 && zvl128b)
dsp->h264_idct_add = ff_h264_idct_add_12_rvv;
if (bit_depth == 14 && zvl128b)
dsp->h264_idct_add = ff_h264_idct_add_14_rvv;
dsp->startcode_find_candidate = ff_startcode_find_candidate_rvv;
}
# endif
#endif
}
|
