xref: /third_party/ffmpeg/libavcodec/hq_hqadsp.c (revision cabdff1a)
1/*
2 * Canopus HQ/HQA decoder
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/common.h"
25
26#include "hq_hqadsp.h"
27
28#define FIX_1_082 17734
29#define FIX_1_847 30274
30#define FIX_1_414 23170
31#define FIX_2_613 21407 // divided by two to fit the range
32
33#define IDCTMUL(a, b) ((int)((a) * (unsigned)(b)) >> 16)
34
35static inline void idct_row(int16_t *blk)
36{
37    int tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7, tmp8, tmp9, tmpA;
38    int tmpB, tmpC, tmpD, tmpE, tmpF, tmp10, tmp11, tmp12, tmp13, tmp14;
39
40    tmp0 = blk[5] - blk[3];
41    tmp1 = blk[5] + blk[3];
42    tmp2 = blk[1] - blk[7];
43    tmp3 = blk[1] + blk[7];
44    tmp4 = tmp3 - tmp1;
45    tmp5 = IDCTMUL(tmp0 + tmp2, FIX_1_847);
46    tmp6 = IDCTMUL(tmp2,        FIX_1_082) - tmp5;
47    tmp7 = tmp5 - IDCTMUL(tmp0, FIX_2_613) * 2;
48    tmp8 = tmp3 + tmp1;
49    tmp9 = tmp7 * 4 - tmp8;
50    tmpA = IDCTMUL(tmp4, FIX_1_414) * 4 - tmp9;
51    tmpB = tmp6 * 4 + tmpA;
52    tmpC = blk[2] + blk[6];
53    tmpD = blk[2] - blk[6];
54    tmpE = blk[0] - blk[4];
55    tmpF = blk[0] + blk[4];
56
57    tmp10 = IDCTMUL(tmpD, FIX_1_414) * 4 - tmpC;
58    tmp11 = tmpE - tmp10;
59    tmp12 = tmpF - tmpC;
60    tmp13 = tmpE + tmp10;
61    tmp14 = tmpF + tmpC;
62
63    blk[0] = tmp14 + tmp8;
64    blk[1] = tmp13 + tmp9;
65    blk[2] = tmp11 + tmpA;
66    blk[3] = tmp12 - tmpB;
67    blk[4] = tmp12 + tmpB;
68    blk[5] = tmp11 - tmpA;
69    blk[6] = tmp13 - tmp9;
70    blk[7] = tmp14 - tmp8;
71}
72
73static inline void idct_col(int16_t *blk)
74{
75    int tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7, tmp8, tmp9, tmpA;
76    int tmpB, tmpC, tmpD, tmpE, tmpF, tmp10, tmp11, tmp12, tmp13, tmp14;
77
78    tmp0 = blk[5 * 8] - blk[3 * 8];
79    tmp1 = blk[5 * 8] + blk[3 * 8];
80    tmp2 = blk[1 * 8] * 2 - (blk[7 * 8] >> 2);
81    tmp3 = blk[1 * 8] * 2 + (blk[7 * 8] >> 2);
82    tmp4 = tmp3 - tmp1;
83    tmp5 = IDCTMUL(tmp0 + tmp2, FIX_1_847);
84    tmp6 = IDCTMUL(tmp2,        FIX_1_082) - tmp5;
85    tmp7 = tmp5 - IDCTMUL(tmp0, FIX_2_613) * 2;
86    tmp8 = (tmp3 + tmp1) >> 1;
87    tmp9 = tmp7 * 2 - tmp8;
88    tmpA = IDCTMUL(tmp4, FIX_1_414) * 2 - tmp9;
89    tmpB = tmp6 * 2 + tmpA;
90    tmpC =  blk[2 * 8] + (blk[6 * 8] >> 1) >> 1;
91    tmpD =  blk[2 * 8] - (blk[6 * 8] >> 1);
92    tmpE = (blk[0 * 8] >> 1) - (blk[4 * 8] >> 1) + 0x2020;
93    tmpF = (blk[0 * 8] >> 1) + (blk[4 * 8] >> 1) + 0x2020;
94
95    tmp10 = IDCTMUL(tmpD, FIX_1_414) * 2 - tmpC;
96    tmp11 = tmpE - tmp10;
97    tmp12 = tmpF - tmpC;
98    tmp13 = tmpE + tmp10;
99    tmp14 = tmpF + tmpC;
100
101    blk[0 * 8] = (tmp14 + tmp8) >> 6;
102    blk[1 * 8] = (tmp13 + tmp9) >> 6;
103    blk[2 * 8] = (tmp11 + tmpA) >> 6;
104    blk[3 * 8] = (tmp12 - tmpB) >> 6;
105    blk[4 * 8] = (tmp12 + tmpB) >> 6;
106    blk[5 * 8] = (tmp11 - tmpA) >> 6;
107    blk[6 * 8] = (tmp13 - tmp9) >> 6;
108    blk[7 * 8] = (tmp14 - tmp8) >> 6;
109}
110
111static void hq_idct_put(uint8_t *dst, int stride, int16_t *block)
112{
113    int i, j;
114
115    for (i = 0; i < 8; i++)
116        idct_row(block + i * 8);
117    for (i = 0; i < 8; i++)
118        idct_col(block + i);
119
120    for (i = 0; i < 8; i++) {
121        for (j = 0; j < 8; j++)
122            dst[j] = av_clip_uint8(block[j + i * 8]);
123        dst += stride;
124    }
125}
126
127av_cold void ff_hqdsp_init(HQDSPContext *c)
128{
129    c->idct_put = hq_idct_put;
130}
131