1/*
2 * Copyright (c) 2015 Shivraj Patil (Shivraj.Patil@imgtec.com)
3 *
4 * This file is part of FFmpeg.
5 *
6 * FFmpeg is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
10 *
11 * FFmpeg is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
14 * Lesser General Public License for more details.
15 *
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with FFmpeg; if not, write to the Free Software
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
19 */
20
21#include "libavutil/attributes.h"
22#include "libavutil/mips/cpu.h"
23#include "config.h"
24#include "libavutil/common.h"
25#include "libavcodec/vp9dsp.h"
26#include "vp9dsp_mips.h"
27
28#if HAVE_MSA
29static av_cold void vp9dsp_intrapred_init_msa(VP9DSPContext *dsp, int bpp)
30{
31    if (bpp == 8) {
32#define init_intra_pred_msa(tx, sz)                             \
33    dsp->intra_pred[tx][VERT_PRED]    = ff_vert_##sz##_msa;     \
34    dsp->intra_pred[tx][HOR_PRED]     = ff_hor_##sz##_msa;      \
35    dsp->intra_pred[tx][DC_PRED]      = ff_dc_##sz##_msa;       \
36    dsp->intra_pred[tx][LEFT_DC_PRED] = ff_dc_left_##sz##_msa;  \
37    dsp->intra_pred[tx][TOP_DC_PRED]  = ff_dc_top_##sz##_msa;   \
38    dsp->intra_pred[tx][DC_128_PRED]  = ff_dc_128_##sz##_msa;   \
39    dsp->intra_pred[tx][DC_127_PRED]  = ff_dc_127_##sz##_msa;   \
40    dsp->intra_pred[tx][DC_129_PRED]  = ff_dc_129_##sz##_msa;   \
41    dsp->intra_pred[tx][TM_VP8_PRED]  = ff_tm_##sz##_msa;       \
42
43    init_intra_pred_msa(TX_16X16, 16x16);
44    init_intra_pred_msa(TX_32X32, 32x32);
45#undef init_intra_pred_msa
46
47#define init_intra_pred_msa(tx, sz)                             \
48    dsp->intra_pred[tx][DC_PRED]      = ff_dc_##sz##_msa;       \
49    dsp->intra_pred[tx][LEFT_DC_PRED] = ff_dc_left_##sz##_msa;  \
50    dsp->intra_pred[tx][TOP_DC_PRED]  = ff_dc_top_##sz##_msa;   \
51    dsp->intra_pred[tx][TM_VP8_PRED]  = ff_tm_##sz##_msa;       \
52
53    init_intra_pred_msa(TX_4X4, 4x4);
54    init_intra_pred_msa(TX_8X8, 8x8);
55#undef init_intra_pred_msa
56    }
57}
58
59static av_cold void vp9dsp_itxfm_init_msa(VP9DSPContext *dsp, int bpp)
60{
61    if (bpp == 8) {
62#define init_itxfm(tx, sz)                                         \
63    dsp->itxfm_add[tx][DCT_DCT]   = ff_idct_idct_##sz##_add_msa;   \
64    dsp->itxfm_add[tx][DCT_ADST]  = ff_iadst_idct_##sz##_add_msa;  \
65    dsp->itxfm_add[tx][ADST_DCT]  = ff_idct_iadst_##sz##_add_msa;  \
66    dsp->itxfm_add[tx][ADST_ADST] = ff_iadst_iadst_##sz##_add_msa  \
67
68#define init_idct(tx, nm)                        \
69    dsp->itxfm_add[tx][DCT_DCT]   =              \
70    dsp->itxfm_add[tx][ADST_DCT]  =              \
71    dsp->itxfm_add[tx][DCT_ADST]  =              \
72    dsp->itxfm_add[tx][ADST_ADST] = nm##_add_msa
73
74    init_itxfm(TX_4X4, 4x4);
75    init_itxfm(TX_8X8, 8x8);
76    init_itxfm(TX_16X16, 16x16);
77    init_idct(TX_32X32, ff_idct_idct_32x32);
78#undef init_itxfm
79#undef init_idct
80    }
81}
82
83static av_cold void vp9dsp_mc_init_msa(VP9DSPContext *dsp, int bpp)
84{
85    if (bpp == 8) {
86#define init_fpel(idx1, idx2, sz, type)                                    \
87    dsp->mc[idx1][FILTER_8TAP_SMOOTH ][idx2][0][0] = ff_##type##sz##_msa;  \
88    dsp->mc[idx1][FILTER_8TAP_REGULAR][idx2][0][0] = ff_##type##sz##_msa;  \
89    dsp->mc[idx1][FILTER_8TAP_SHARP  ][idx2][0][0] = ff_##type##sz##_msa;  \
90    dsp->mc[idx1][FILTER_BILINEAR    ][idx2][0][0] = ff_##type##sz##_msa
91
92#define init_copy_avg(idx, sz)    \
93    init_fpel(idx, 0, sz, copy);  \
94    init_fpel(idx, 1, sz, avg)
95
96#define init_avg(idx, sz)  \
97    init_fpel(idx, 1, sz, avg)
98
99    init_copy_avg(0, 64);
100    init_copy_avg(1, 32);
101    init_copy_avg(2, 16);
102    init_copy_avg(3,  8);
103    init_avg(4,  4);
104
105#undef init_copy_avg
106#undef init_avg
107#undef init_fpel
108
109#define init_subpel1(idx1, idx2, idxh, idxv, sz, dir, type)  \
110    dsp->mc[idx1][FILTER_BILINEAR    ][idx2][idxh][idxv] =   \
111        ff_##type##_bilin_##sz##dir##_msa;                   \
112    dsp->mc[idx1][FILTER_8TAP_SMOOTH ][idx2][idxh][idxv] =   \
113        ff_##type##_8tap_smooth_##sz##dir##_msa;             \
114    dsp->mc[idx1][FILTER_8TAP_REGULAR][idx2][idxh][idxv] =   \
115        ff_##type##_8tap_regular_##sz##dir##_msa;            \
116    dsp->mc[idx1][FILTER_8TAP_SHARP  ][idx2][idxh][idxv] =   \
117        ff_##type##_8tap_sharp_##sz##dir##_msa;
118
119#define init_subpel2(idx, idxh, idxv, dir, type)      \
120    init_subpel1(0, idx, idxh, idxv, 64, dir, type);  \
121    init_subpel1(1, idx, idxh, idxv, 32, dir, type);  \
122    init_subpel1(2, idx, idxh, idxv, 16, dir, type);  \
123    init_subpel1(3, idx, idxh, idxv,  8, dir, type);  \
124    init_subpel1(4, idx, idxh, idxv,  4, dir, type)
125
126#define init_subpel3(idx, type)         \
127    init_subpel2(idx, 1, 1, hv, type);  \
128    init_subpel2(idx, 0, 1, v, type);   \
129    init_subpel2(idx, 1, 0, h, type)
130
131    init_subpel3(0, put);
132    init_subpel3(1, avg);
133
134#undef init_subpel1
135#undef init_subpel2
136#undef init_subpel3
137    }
138}
139
140static av_cold void vp9dsp_loopfilter_init_msa(VP9DSPContext *dsp, int bpp)
141{
142    if (bpp == 8) {
143        dsp->loop_filter_8[0][0] = ff_loop_filter_h_4_8_msa;
144        dsp->loop_filter_8[0][1] = ff_loop_filter_v_4_8_msa;
145        dsp->loop_filter_8[1][0] = ff_loop_filter_h_8_8_msa;
146        dsp->loop_filter_8[1][1] = ff_loop_filter_v_8_8_msa;
147        dsp->loop_filter_8[2][0] = ff_loop_filter_h_16_8_msa;
148        dsp->loop_filter_8[2][1] = ff_loop_filter_v_16_8_msa;
149
150        dsp->loop_filter_16[0] = ff_loop_filter_h_16_16_msa;
151        dsp->loop_filter_16[1] = ff_loop_filter_v_16_16_msa;
152
153        dsp->loop_filter_mix2[0][0][0] = ff_loop_filter_h_44_16_msa;
154        dsp->loop_filter_mix2[0][0][1] = ff_loop_filter_v_44_16_msa;
155        dsp->loop_filter_mix2[0][1][0] = ff_loop_filter_h_48_16_msa;
156        dsp->loop_filter_mix2[0][1][1] = ff_loop_filter_v_48_16_msa;
157        dsp->loop_filter_mix2[1][0][0] = ff_loop_filter_h_84_16_msa;
158        dsp->loop_filter_mix2[1][0][1] = ff_loop_filter_v_84_16_msa;
159        dsp->loop_filter_mix2[1][1][0] = ff_loop_filter_h_88_16_msa;
160        dsp->loop_filter_mix2[1][1][1] = ff_loop_filter_v_88_16_msa;
161    }
162}
163
164static av_cold void vp9dsp_init_msa(VP9DSPContext *dsp, int bpp)
165{
166    vp9dsp_intrapred_init_msa(dsp, bpp);
167    vp9dsp_itxfm_init_msa(dsp, bpp);
168    vp9dsp_mc_init_msa(dsp, bpp);
169    vp9dsp_loopfilter_init_msa(dsp, bpp);
170}
171#endif  // #if HAVE_MSA
172
173#if HAVE_MMI
174static av_cold void vp9dsp_mc_init_mmi(VP9DSPContext *dsp)
175{
176#define init_subpel1(idx1, idx2, idxh, idxv, sz, dir, type)  \
177    dsp->mc[idx1][FILTER_8TAP_SMOOTH ][idx2][idxh][idxv] =   \
178        ff_##type##_8tap_smooth_##sz##dir##_mmi;             \
179    dsp->mc[idx1][FILTER_8TAP_REGULAR][idx2][idxh][idxv] =   \
180        ff_##type##_8tap_regular_##sz##dir##_mmi;            \
181    dsp->mc[idx1][FILTER_8TAP_SHARP  ][idx2][idxh][idxv] =   \
182        ff_##type##_8tap_sharp_##sz##dir##_mmi;
183
184#define init_subpel2(idx, idxh, idxv, dir, type)      \
185    init_subpel1(0, idx, idxh, idxv, 64, dir, type);  \
186    init_subpel1(1, idx, idxh, idxv, 32, dir, type);  \
187    init_subpel1(2, idx, idxh, idxv, 16, dir, type);  \
188    init_subpel1(3, idx, idxh, idxv,  8, dir, type);  \
189    init_subpel1(4, idx, idxh, idxv,  4, dir, type)
190
191#define init_subpel3(idx, type)         \
192    init_subpel2(idx, 1, 1, hv, type);  \
193    init_subpel2(idx, 0, 1, v, type);   \
194    init_subpel2(idx, 1, 0, h, type)
195
196    init_subpel3(0, put);
197    init_subpel3(1, avg);
198
199#undef init_subpel1
200#undef init_subpel2
201#undef init_subpel3
202}
203
204static av_cold void vp9dsp_init_mmi(VP9DSPContext *dsp, int bpp)
205{
206    if (bpp == 8) {
207        vp9dsp_mc_init_mmi(dsp);
208    }
209}
210#endif  // #if HAVE_MMI
211
212av_cold void ff_vp9dsp_init_mips(VP9DSPContext *dsp, int bpp)
213{
214#if HAVE_MSA || HAVE_MMI
215    int cpu_flags = av_get_cpu_flags();
216#endif
217
218#if HAVE_MMI
219    if (have_mmi(cpu_flags))
220        vp9dsp_init_mmi(dsp, bpp);
221#endif
222
223#if HAVE_MSA
224    if (have_msa(cpu_flags))
225        vp9dsp_init_msa(dsp, bpp);
226#endif
227}
228