xref: /third_party/ffmpeg/libavcodec/vp9lpf.c (revision cabdff1a)
1/*
2 * VP9 compatible video decoder
3 *
4 * Copyright (C) 2013 Ronald S. Bultje <rsbultje gmail com>
5 * Copyright (C) 2013 Clément Bœsch <u pkh me>
6 *
7 * This file is part of FFmpeg.
8 *
9 * FFmpeg is free software; you can redistribute it and/or
10 * modify it under the terms of the GNU Lesser General Public
11 * License as published by the Free Software Foundation; either
12 * version 2.1 of the License, or (at your option) any later version.
13 *
14 * FFmpeg is distributed in the hope that it will be useful,
15 * but WITHOUT ANY WARRANTY; without even the implied warranty of
16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
17 * Lesser General Public License for more details.
18 *
19 * You should have received a copy of the GNU Lesser General Public
20 * License along with FFmpeg; if not, write to the Free Software
21 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
22 */
23
24#include "vp9dec.h"
25
26static av_always_inline void filter_plane_cols(VP9Context *s, int col, int ss_h, int ss_v,
27                                               uint8_t *lvl, uint8_t (*mask)[4],
28                                               uint8_t *dst, ptrdiff_t ls)
29{
30    int y, x, bytesperpixel = s->bytesperpixel;
31
32    // filter edges between columns (e.g. block1 | block2)
33    for (y = 0; y < 8; y += 2 << ss_v, dst += 16 * ls, lvl += 16 << ss_v) {
34        uint8_t *ptr = dst, *l = lvl, *hmask1 = mask[y], *hmask2 = mask[y + 1 + ss_v];
35        unsigned hm1 = hmask1[0] | hmask1[1] | hmask1[2], hm13 = hmask1[3];
36        unsigned hm2 = hmask2[1] | hmask2[2], hm23 = hmask2[3];
37        unsigned hm = hm1 | hm2 | hm13 | hm23;
38
39        for (x = 1; hm & ~(x - 1); x <<= 1, ptr += 8 * bytesperpixel >> ss_h) {
40            if (col || x > 1) {
41                if (hm1 & x) {
42                    int L = *l, H = L >> 4;
43                    int E = s->filter_lut.mblim_lut[L], I = s->filter_lut.lim_lut[L];
44
45                    if (hmask1[0] & x) {
46                        if (hmask2[0] & x) {
47                            av_assert2(l[8 << ss_v] == L);
48                            s->dsp.loop_filter_16[0](ptr, ls, E, I, H);
49                        } else {
50                            s->dsp.loop_filter_8[2][0](ptr, ls, E, I, H);
51                        }
52                    } else if (hm2 & x) {
53                        L = l[8 << ss_v];
54                        H |= (L >> 4) << 8;
55                        E |= s->filter_lut.mblim_lut[L] << 8;
56                        I |= s->filter_lut.lim_lut[L] << 8;
57                        s->dsp.loop_filter_mix2[!!(hmask1[1] & x)]
58                                               [!!(hmask2[1] & x)]
59                                               [0](ptr, ls, E, I, H);
60                    } else {
61                        s->dsp.loop_filter_8[!!(hmask1[1] & x)]
62                                            [0](ptr, ls, E, I, H);
63                    }
64                } else if (hm2 & x) {
65                    int L = l[8 << ss_v], H = L >> 4;
66                    int E = s->filter_lut.mblim_lut[L], I = s->filter_lut.lim_lut[L];
67
68                    s->dsp.loop_filter_8[!!(hmask2[1] & x)]
69                                        [0](ptr + 8 * ls, ls, E, I, H);
70                }
71            }
72            if (ss_h) {
73                if (x & 0xAA)
74                    l += 2;
75            } else {
76                if (hm13 & x) {
77                    int L = *l, H = L >> 4;
78                    int E = s->filter_lut.mblim_lut[L], I = s->filter_lut.lim_lut[L];
79
80                    if (hm23 & x) {
81                        L = l[8 << ss_v];
82                        H |= (L >> 4) << 8;
83                        E |= s->filter_lut.mblim_lut[L] << 8;
84                        I |= s->filter_lut.lim_lut[L] << 8;
85                        s->dsp.loop_filter_mix2[0][0][0](ptr + 4 * bytesperpixel, ls, E, I, H);
86                    } else {
87                        s->dsp.loop_filter_8[0][0](ptr + 4 * bytesperpixel, ls, E, I, H);
88                    }
89                } else if (hm23 & x) {
90                    int L = l[8 << ss_v], H = L >> 4;
91                    int E = s->filter_lut.mblim_lut[L], I = s->filter_lut.lim_lut[L];
92
93                    s->dsp.loop_filter_8[0][0](ptr + 8 * ls + 4 * bytesperpixel, ls, E, I, H);
94                }
95                l++;
96            }
97        }
98    }
99}
100
101static av_always_inline void filter_plane_rows(VP9Context *s, int row, int ss_h, int ss_v,
102                                               uint8_t *lvl, uint8_t (*mask)[4],
103                                               uint8_t *dst, ptrdiff_t ls)
104{
105    int y, x, bytesperpixel = s->bytesperpixel;
106
107    //                                 block1
108    // filter edges between rows (e.g. ------)
109    //                                 block2
110    for (y = 0; y < 8; y++, dst += 8 * ls >> ss_v) {
111        uint8_t *ptr = dst, *l = lvl, *vmask = mask[y];
112        unsigned vm = vmask[0] | vmask[1] | vmask[2], vm3 = vmask[3];
113
114        for (x = 1; vm & ~(x - 1); x <<= (2 << ss_h), ptr += 16 * bytesperpixel, l += 2 << ss_h) {
115            if (row || y) {
116                if (vm & x) {
117                    int L = *l, H = L >> 4;
118                    int E = s->filter_lut.mblim_lut[L], I = s->filter_lut.lim_lut[L];
119
120                    if (vmask[0] & x) {
121                        if (vmask[0] & (x << (1 + ss_h))) {
122                            av_assert2(l[1 + ss_h] == L);
123                            s->dsp.loop_filter_16[1](ptr, ls, E, I, H);
124                        } else {
125                            s->dsp.loop_filter_8[2][1](ptr, ls, E, I, H);
126                        }
127                    } else if (vm & (x << (1 + ss_h))) {
128                        L = l[1 + ss_h];
129                        H |= (L >> 4) << 8;
130                        E |= s->filter_lut.mblim_lut[L] << 8;
131                        I |= s->filter_lut.lim_lut[L] << 8;
132                        s->dsp.loop_filter_mix2[!!(vmask[1] &  x)]
133                                               [!!(vmask[1] & (x << (1 + ss_h)))]
134                                               [1](ptr, ls, E, I, H);
135                    } else {
136                        s->dsp.loop_filter_8[!!(vmask[1] & x)]
137                                            [1](ptr, ls, E, I, H);
138                    }
139                } else if (vm & (x << (1 + ss_h))) {
140                    int L = l[1 + ss_h], H = L >> 4;
141                    int E = s->filter_lut.mblim_lut[L], I = s->filter_lut.lim_lut[L];
142
143                    s->dsp.loop_filter_8[!!(vmask[1] & (x << (1 + ss_h)))]
144                                        [1](ptr + 8 * bytesperpixel, ls, E, I, H);
145                }
146            }
147            if (!ss_v) {
148                if (vm3 & x) {
149                    int L = *l, H = L >> 4;
150                    int E = s->filter_lut.mblim_lut[L], I = s->filter_lut.lim_lut[L];
151
152                    if (vm3 & (x << (1 + ss_h))) {
153                        L = l[1 + ss_h];
154                        H |= (L >> 4) << 8;
155                        E |= s->filter_lut.mblim_lut[L] << 8;
156                        I |= s->filter_lut.lim_lut[L] << 8;
157                        s->dsp.loop_filter_mix2[0][0][1](ptr + ls * 4, ls, E, I, H);
158                    } else {
159                        s->dsp.loop_filter_8[0][1](ptr + ls * 4, ls, E, I, H);
160                    }
161                } else if (vm3 & (x << (1 + ss_h))) {
162                    int L = l[1 + ss_h], H = L >> 4;
163                    int E = s->filter_lut.mblim_lut[L], I = s->filter_lut.lim_lut[L];
164
165                    s->dsp.loop_filter_8[0][1](ptr + ls * 4 + 8 * bytesperpixel, ls, E, I, H);
166                }
167            }
168        }
169        if (ss_v) {
170            if (y & 1)
171                lvl += 16;
172        } else {
173            lvl += 8;
174        }
175    }
176}
177
178void ff_vp9_loopfilter_sb(AVCodecContext *avctx, VP9Filter *lflvl,
179                          int row, int col, ptrdiff_t yoff, ptrdiff_t uvoff)
180{
181    VP9Context *s = avctx->priv_data;
182    AVFrame *f = s->s.frames[CUR_FRAME].tf.f;
183    uint8_t *dst = f->data[0] + yoff;
184    ptrdiff_t ls_y = f->linesize[0], ls_uv = f->linesize[1];
185    uint8_t (*uv_masks)[8][4] = lflvl->mask[s->ss_h | s->ss_v];
186    int p;
187
188    /* FIXME: In how far can we interleave the v/h loopfilter calls? E.g.
189     * if you think of them as acting on a 8x8 block max, we can interleave
190     * each v/h within the single x loop, but that only works if we work on
191     * 8 pixel blocks, and we won't always do that (we want at least 16px
192     * to use SSE2 optimizations, perhaps 32 for AVX2) */
193
194    filter_plane_cols(s, col, 0, 0, lflvl->level, lflvl->mask[0][0], dst, ls_y);
195    filter_plane_rows(s, row, 0, 0, lflvl->level, lflvl->mask[0][1], dst, ls_y);
196
197    for (p = 0; p < 2; p++) {
198        dst = f->data[1 + p] + uvoff;
199        filter_plane_cols(s, col, s->ss_h, s->ss_v, lflvl->level, uv_masks[0], dst, ls_uv);
200        filter_plane_rows(s, row, s->ss_h, s->ss_v, lflvl->level, uv_masks[1], dst, ls_uv);
201    }
202}
203