1/*
2 * Copyright (c) 2021 Loongson Technology Corporation Limited
3 * Contributed by Hao Chen <chenhao@loongson.cn>
4 *
5 * This file is part of FFmpeg.
6 *
7 * FFmpeg is free software; you can redistribute it and/or
8 * modify it under the terms of the GNU Lesser General Public
9 * License as published by the Free Software Foundation; either
10 * version 2.1 of the License, or (at your option) any later version.
11 *
12 * FFmpeg is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
15 * Lesser General Public License for more details.
16 *
17 * You should have received a copy of the GNU Lesser General Public
18 * License along with FFmpeg; if not, write to the Free Software
19 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
20 */
21
22#include "libavutil/loongarch/cpu.h"
23#include "libavutil/attributes.h"
24#include "libavcodec/vp9dsp.h"
25#include "vp9dsp_loongarch.h"
26
27#define init_subpel1(idx1, idx2, idxh, idxv, sz, dir, type)  \
28    dsp->mc[idx1][FILTER_8TAP_SMOOTH ][idx2][idxh][idxv] =   \
29        ff_##type##_8tap_smooth_##sz##dir##_lsx;             \
30    dsp->mc[idx1][FILTER_8TAP_REGULAR][idx2][idxh][idxv] =   \
31        ff_##type##_8tap_regular_##sz##dir##_lsx;            \
32    dsp->mc[idx1][FILTER_8TAP_SHARP  ][idx2][idxh][idxv] =   \
33        ff_##type##_8tap_sharp_##sz##dir##_lsx;
34
35#define init_subpel2(idx, idxh, idxv, dir, type)      \
36    init_subpel1(0, idx, idxh, idxv, 64, dir, type);  \
37    init_subpel1(1, idx, idxh, idxv, 32, dir, type);  \
38    init_subpel1(2, idx, idxh, idxv, 16, dir, type);  \
39    init_subpel1(3, idx, idxh, idxv,  8, dir, type);  \
40    init_subpel1(4, idx, idxh, idxv,  4, dir, type);
41
42#define init_subpel3(idx, type)         \
43    init_subpel2(idx, 1, 0, h, type);   \
44    init_subpel2(idx, 0, 1, v, type);   \
45    init_subpel2(idx, 1, 1, hv, type);
46
47#define init_fpel(idx1, idx2, sz, type)                                    \
48    dsp->mc[idx1][FILTER_8TAP_SMOOTH ][idx2][0][0] = ff_##type##sz##_lsx;  \
49    dsp->mc[idx1][FILTER_8TAP_REGULAR][idx2][0][0] = ff_##type##sz##_lsx;  \
50    dsp->mc[idx1][FILTER_8TAP_SHARP  ][idx2][0][0] = ff_##type##sz##_lsx;  \
51    dsp->mc[idx1][FILTER_BILINEAR    ][idx2][0][0] = ff_##type##sz##_lsx;
52
53#define init_copy(idx, sz)                    \
54    init_fpel(idx, 0, sz, copy);              \
55    init_fpel(idx, 1, sz, avg);
56
57#define init_intra_pred1_lsx(tx, sz)                            \
58    dsp->intra_pred[tx][VERT_PRED]    = ff_vert_##sz##_lsx;     \
59    dsp->intra_pred[tx][HOR_PRED]     = ff_hor_##sz##_lsx;      \
60    dsp->intra_pred[tx][DC_PRED]      = ff_dc_##sz##_lsx;       \
61    dsp->intra_pred[tx][LEFT_DC_PRED] = ff_dc_left_##sz##_lsx;  \
62    dsp->intra_pred[tx][TOP_DC_PRED]  = ff_dc_top_##sz##_lsx;   \
63    dsp->intra_pred[tx][DC_128_PRED]  = ff_dc_128_##sz##_lsx;   \
64    dsp->intra_pred[tx][DC_127_PRED]  = ff_dc_127_##sz##_lsx;   \
65    dsp->intra_pred[tx][DC_129_PRED]  = ff_dc_129_##sz##_lsx;   \
66    dsp->intra_pred[tx][TM_VP8_PRED]  = ff_tm_##sz##_lsx;       \
67
68#define init_intra_pred2_lsx(tx, sz)                            \
69    dsp->intra_pred[tx][DC_PRED]      = ff_dc_##sz##_lsx;       \
70    dsp->intra_pred[tx][LEFT_DC_PRED] = ff_dc_left_##sz##_lsx;  \
71    dsp->intra_pred[tx][TOP_DC_PRED]  = ff_dc_top_##sz##_lsx;   \
72    dsp->intra_pred[tx][TM_VP8_PRED]  = ff_tm_##sz##_lsx;       \
73
74#define init_idct(tx, nm)                        \
75    dsp->itxfm_add[tx][DCT_DCT]   =              \
76    dsp->itxfm_add[tx][ADST_DCT]  =              \
77    dsp->itxfm_add[tx][DCT_ADST]  =              \
78    dsp->itxfm_add[tx][ADST_ADST] = nm##_add_lsx;
79
80#define init_itxfm(tx, sz)                                     \
81    dsp->itxfm_add[tx][DCT_DCT] = ff_idct_idct_##sz##_add_lsx;
82
83av_cold void ff_vp9dsp_init_loongarch(VP9DSPContext *dsp, int bpp)
84{
85    int cpu_flags = av_get_cpu_flags();
86    if (have_lsx(cpu_flags))
87        if (bpp == 8) {
88            init_subpel3(0, put);
89            init_subpel3(1, avg);
90            init_copy(0, 64);
91            init_copy(1, 32);
92            init_copy(2, 16);
93            init_copy(3, 8);
94            init_intra_pred1_lsx(TX_16X16, 16x16);
95            init_intra_pred1_lsx(TX_32X32, 32x32);
96            init_intra_pred2_lsx(TX_4X4, 4x4);
97            init_intra_pred2_lsx(TX_8X8, 8x8);
98            init_itxfm(TX_8X8, 8x8);
99            init_itxfm(TX_16X16, 16x16);
100            init_idct(TX_32X32, ff_idct_idct_32x32);
101            dsp->loop_filter_8[0][0] = ff_loop_filter_h_4_8_lsx;
102            dsp->loop_filter_8[0][1] = ff_loop_filter_v_4_8_lsx;
103            dsp->loop_filter_8[1][0] = ff_loop_filter_h_8_8_lsx;
104            dsp->loop_filter_8[1][1] = ff_loop_filter_v_8_8_lsx;
105            dsp->loop_filter_8[2][0] = ff_loop_filter_h_16_8_lsx;
106            dsp->loop_filter_8[2][1] = ff_loop_filter_v_16_8_lsx;
107
108            dsp->loop_filter_16[0] = ff_loop_filter_h_16_16_lsx;
109            dsp->loop_filter_16[1] = ff_loop_filter_v_16_16_lsx;
110
111            dsp->loop_filter_mix2[0][0][0] = ff_loop_filter_h_44_16_lsx;
112            dsp->loop_filter_mix2[0][0][1] = ff_loop_filter_v_44_16_lsx;
113            dsp->loop_filter_mix2[0][1][0] = ff_loop_filter_h_48_16_lsx;
114            dsp->loop_filter_mix2[0][1][1] = ff_loop_filter_v_48_16_lsx;
115            dsp->loop_filter_mix2[1][0][0] = ff_loop_filter_h_84_16_lsx;
116            dsp->loop_filter_mix2[1][0][1] = ff_loop_filter_v_84_16_lsx;
117            dsp->loop_filter_mix2[1][1][0] = ff_loop_filter_h_88_16_lsx;
118            dsp->loop_filter_mix2[1][1][1] = ff_loop_filter_v_88_16_lsx;
119        }
120}
121
122#undef init_subpel1
123#undef init_subpel2
124#undef init_subpel3
125#undef init_copy
126#undef init_fpel
127#undef init_intra_pred1_lsx
128#undef init_intra_pred2_lsx
129#undef init_idct
130#undef init_itxfm
131