1/*
2 * Copyright (c) 2017 Google Inc.
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 <stdint.h>
22
23#include "libavutil/attributes.h"
24#include "libavutil/internal.h"
25#include "libavutil/mem_internal.h"
26#include "libavutil/arm/cpu.h"
27#include "vp9dsp_init.h"
28
29#define declare_fpel(type, sz, suffix)                                          \
30void ff_vp9_##type##sz##suffix##_neon(uint8_t *dst, ptrdiff_t dst_stride,       \
31                                      const uint8_t *src, ptrdiff_t src_stride, \
32                                      int h, int mx, int my)
33
34#define decl_mc_func(op, filter, dir, sz, bpp)                                                   \
35void ff_vp9_##op##_##filter##sz##_##dir##_##bpp##_neon(uint8_t *dst, ptrdiff_t dst_stride,       \
36                                                       const uint8_t *src, ptrdiff_t src_stride, \
37                                                       int h, int mx, int my)
38
39#define define_8tap_2d_fn(op, filter, sz, bpp)                                      \
40static void op##_##filter##sz##_hv_##bpp##_neon(uint8_t *dst, ptrdiff_t dst_stride, \
41                                                const uint8_t *src,                 \
42                                                ptrdiff_t src_stride,               \
43                                                int h, int mx, int my)              \
44{                                                                                   \
45    LOCAL_ALIGNED_16(uint8_t, temp, [((1 + (sz < 64)) * sz + 8) * sz * 2]);         \
46    /* We only need h + 7 lines, but the horizontal filter assumes an               \
47     * even number of rows, so filter h + 8 lines here. */                          \
48    ff_vp9_put_##filter##sz##_h_##bpp##_neon(temp, 2 * sz,                          \
49                                             src - 3 * src_stride, src_stride,      \
50                                             h + 8, mx, 0);                         \
51    ff_vp9_##op##_##filter##sz##_v_##bpp##_neon(dst, dst_stride,                    \
52                                                temp + 3 * 2 * sz, 2 * sz,          \
53                                                h, 0, my);                          \
54}
55
56#define decl_filter_funcs(op, dir, sz, bpp)  \
57    decl_mc_func(op, regular, dir, sz, bpp); \
58    decl_mc_func(op, sharp,   dir, sz, bpp); \
59    decl_mc_func(op, smooth,  dir, sz, bpp)
60
61#define decl_mc_funcs(sz, bpp)      \
62    decl_filter_funcs(put, h,  sz, bpp); \
63    decl_filter_funcs(avg, h,  sz, bpp); \
64    decl_filter_funcs(put, v,  sz, bpp); \
65    decl_filter_funcs(avg, v,  sz, bpp); \
66    decl_filter_funcs(put, hv, sz, bpp); \
67    decl_filter_funcs(avg, hv, sz, bpp)
68
69declare_fpel(copy, 128, );
70declare_fpel(copy, 64,  );
71declare_fpel(copy, 32,  );
72declare_fpel(copy, 16,  );
73declare_fpel(copy, 8,   );
74declare_fpel(avg, 64, _16);
75declare_fpel(avg, 32, _16);
76declare_fpel(avg, 16, _16);
77declare_fpel(avg, 8,  _16);
78declare_fpel(avg, 4,  _16);
79
80decl_mc_funcs(64, BPP);
81decl_mc_funcs(32, BPP);
82decl_mc_funcs(16, BPP);
83decl_mc_funcs(8,  BPP);
84decl_mc_funcs(4,  BPP);
85
86#define define_8tap_2d_funcs(sz, bpp)        \
87    define_8tap_2d_fn(put, regular, sz, bpp) \
88    define_8tap_2d_fn(put, sharp,   sz, bpp) \
89    define_8tap_2d_fn(put, smooth,  sz, bpp) \
90    define_8tap_2d_fn(avg, regular, sz, bpp) \
91    define_8tap_2d_fn(avg, sharp,   sz, bpp) \
92    define_8tap_2d_fn(avg, smooth,  sz, bpp)
93
94define_8tap_2d_funcs(64, BPP)
95define_8tap_2d_funcs(32, BPP)
96define_8tap_2d_funcs(16, BPP)
97define_8tap_2d_funcs(8,  BPP)
98define_8tap_2d_funcs(4,  BPP)
99
100
101static av_cold void vp9dsp_mc_init_arm(VP9DSPContext *dsp)
102{
103    int cpu_flags = av_get_cpu_flags();
104
105    if (have_neon(cpu_flags)) {
106#define init_fpel(idx1, idx2, sz, type, suffix)      \
107    dsp->mc[idx1][FILTER_8TAP_SMOOTH ][idx2][0][0] = \
108    dsp->mc[idx1][FILTER_8TAP_REGULAR][idx2][0][0] = \
109    dsp->mc[idx1][FILTER_8TAP_SHARP  ][idx2][0][0] = \
110    dsp->mc[idx1][FILTER_BILINEAR    ][idx2][0][0] = ff_vp9_##type##sz##suffix##_neon
111
112#define init_copy_avg(idx, sz1, sz2) \
113    init_fpel(idx, 0, sz2, copy, );  \
114    init_fpel(idx, 1, sz1, avg, _16)
115
116#define init_mc_func(idx1, idx2, op, filter, fname, dir, mx, my, sz, pfx, bpp) \
117    dsp->mc[idx1][filter][idx2][mx][my] = pfx##op##_##fname##sz##_##dir##_##bpp##_neon
118
119#define init_mc_funcs(idx, dir, mx, my, sz, pfx, bpp)                                   \
120    init_mc_func(idx, 0, put, FILTER_8TAP_REGULAR, regular, dir, mx, my, sz, pfx, bpp); \
121    init_mc_func(idx, 0, put, FILTER_8TAP_SHARP,   sharp,   dir, mx, my, sz, pfx, bpp); \
122    init_mc_func(idx, 0, put, FILTER_8TAP_SMOOTH,  smooth,  dir, mx, my, sz, pfx, bpp); \
123    init_mc_func(idx, 1, avg, FILTER_8TAP_REGULAR, regular, dir, mx, my, sz, pfx, bpp); \
124    init_mc_func(idx, 1, avg, FILTER_8TAP_SHARP,   sharp,   dir, mx, my, sz, pfx, bpp); \
125    init_mc_func(idx, 1, avg, FILTER_8TAP_SMOOTH,  smooth,  dir, mx, my, sz, pfx, bpp)
126
127#define init_mc_funcs_dirs(idx, sz, bpp)            \
128    init_mc_funcs(idx, h,  1, 0, sz, ff_vp9_, bpp); \
129    init_mc_funcs(idx, v,  0, 1, sz, ff_vp9_, bpp); \
130    init_mc_funcs(idx, hv, 1, 1, sz,        , bpp)
131
132        init_copy_avg(0, 64, 128);
133        init_copy_avg(1, 32, 64);
134        init_copy_avg(2, 16, 32);
135        init_copy_avg(3, 8,  16);
136        init_copy_avg(4, 4,  8);
137
138        init_mc_funcs_dirs(0, 64, BPP);
139        init_mc_funcs_dirs(1, 32, BPP);
140        init_mc_funcs_dirs(2, 16, BPP);
141        init_mc_funcs_dirs(3, 8,  BPP);
142        init_mc_funcs_dirs(4, 4,  BPP);
143    }
144}
145
146#define define_itxfm2(type_a, type_b, sz, bpp)                                     \
147void ff_vp9_##type_a##_##type_b##_##sz##x##sz##_add_##bpp##_neon(uint8_t *_dst,    \
148                                                                 ptrdiff_t stride, \
149                                                                 int16_t *_block, int eob)
150#define define_itxfm(type_a, type_b, sz, bpp) define_itxfm2(type_a, type_b, sz, bpp)
151
152#define define_itxfm_funcs(sz, bpp)      \
153    define_itxfm(idct,  idct,  sz, bpp); \
154    define_itxfm(iadst, idct,  sz, bpp); \
155    define_itxfm(idct,  iadst, sz, bpp); \
156    define_itxfm(iadst, iadst, sz, bpp)
157
158define_itxfm_funcs(4,  BPP);
159define_itxfm_funcs(8,  BPP);
160define_itxfm_funcs(16, BPP);
161define_itxfm(idct, idct, 32, BPP);
162define_itxfm(iwht, iwht, 4,  BPP);
163
164
165static av_cold void vp9dsp_itxfm_init_arm(VP9DSPContext *dsp)
166{
167    int cpu_flags = av_get_cpu_flags();
168
169    if (have_neon(cpu_flags)) {
170#define init_itxfm2(tx, sz, bpp)                                               \
171    dsp->itxfm_add[tx][DCT_DCT]   = ff_vp9_idct_idct_##sz##_add_##bpp##_neon;  \
172    dsp->itxfm_add[tx][DCT_ADST]  = ff_vp9_iadst_idct_##sz##_add_##bpp##_neon; \
173    dsp->itxfm_add[tx][ADST_DCT]  = ff_vp9_idct_iadst_##sz##_add_##bpp##_neon; \
174    dsp->itxfm_add[tx][ADST_ADST] = ff_vp9_iadst_iadst_##sz##_add_##bpp##_neon
175#define init_itxfm(tx, sz, bpp) init_itxfm2(tx, sz, bpp)
176
177#define init_idct2(tx, nm, bpp)     \
178    dsp->itxfm_add[tx][DCT_DCT]   = \
179    dsp->itxfm_add[tx][ADST_DCT]  = \
180    dsp->itxfm_add[tx][DCT_ADST]  = \
181    dsp->itxfm_add[tx][ADST_ADST] = ff_vp9_##nm##_add_##bpp##_neon
182#define init_idct(tx, nm, bpp) init_idct2(tx, nm, bpp)
183
184        init_itxfm(TX_4X4,   4x4,   BPP);
185        init_itxfm(TX_8X8,   8x8,   BPP);
186        init_itxfm(TX_16X16, 16x16, BPP);
187        init_idct(TX_32X32, idct_idct_32x32, BPP);
188        init_idct(4,        iwht_iwht_4x4,   BPP);
189    }
190}
191
192#define define_loop_filter(dir, wd, size, bpp) \
193void ff_vp9_loop_filter_##dir##_##wd##_##size##_##bpp##_neon(uint8_t *dst, ptrdiff_t stride, int E, int I, int H)
194
195#define define_loop_filters(wd, size, bpp) \
196    define_loop_filter(h, wd, size, bpp);  \
197    define_loop_filter(v, wd, size, bpp)
198
199define_loop_filters(4,  8,  BPP);
200define_loop_filters(8,  8,  BPP);
201define_loop_filters(16, 8,  BPP);
202
203define_loop_filters(16, 16, BPP);
204
205define_loop_filters(44, 16, BPP);
206define_loop_filters(48, 16, BPP);
207define_loop_filters(84, 16, BPP);
208define_loop_filters(88, 16, BPP);
209
210static av_cold void vp9dsp_loopfilter_init_arm(VP9DSPContext *dsp)
211{
212    int cpu_flags = av_get_cpu_flags();
213
214    if (have_neon(cpu_flags)) {
215#define init_lpf_func_8(idx1, idx2, dir, wd, bpp) \
216    dsp->loop_filter_8[idx1][idx2] = ff_vp9_loop_filter_##dir##_##wd##_8_##bpp##_neon
217
218#define init_lpf_func_16(idx, dir, bpp) \
219    dsp->loop_filter_16[idx] = ff_vp9_loop_filter_##dir##_16_16_##bpp##_neon
220
221#define init_lpf_func_mix2(idx1, idx2, idx3, dir, wd, bpp) \
222    dsp->loop_filter_mix2[idx1][idx2][idx3] = ff_vp9_loop_filter_##dir##_##wd##_16_##bpp##_neon
223
224#define init_lpf_funcs_8_wd(idx, wd, bpp) \
225    init_lpf_func_8(idx, 0, h, wd, bpp);  \
226    init_lpf_func_8(idx, 1, v, wd, bpp)
227
228#define init_lpf_funcs_16(bpp)   \
229    init_lpf_func_16(0, h, bpp); \
230    init_lpf_func_16(1, v, bpp)
231
232#define init_lpf_funcs_mix2_wd(idx1, idx2, wd, bpp) \
233    init_lpf_func_mix2(idx1, idx2, 0, h, wd, bpp);  \
234    init_lpf_func_mix2(idx1, idx2, 1, v, wd, bpp)
235
236#define init_lpf_funcs_8(bpp)        \
237    init_lpf_funcs_8_wd(0, 4,  bpp); \
238    init_lpf_funcs_8_wd(1, 8,  bpp); \
239    init_lpf_funcs_8_wd(2, 16, bpp)
240
241#define init_lpf_funcs_mix2(bpp)           \
242    init_lpf_funcs_mix2_wd(0, 0, 44, bpp); \
243    init_lpf_funcs_mix2_wd(0, 1, 48, bpp); \
244    init_lpf_funcs_mix2_wd(1, 0, 84, bpp); \
245    init_lpf_funcs_mix2_wd(1, 1, 88, bpp)
246
247        init_lpf_funcs_8(BPP);
248        init_lpf_funcs_16(BPP);
249        init_lpf_funcs_mix2(BPP);
250    }
251}
252
253av_cold void INIT_FUNC(VP9DSPContext *dsp)
254{
255    vp9dsp_mc_init_arm(dsp);
256    vp9dsp_loopfilter_init_arm(dsp);
257    vp9dsp_itxfm_init_arm(dsp);
258}
259