1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
|
/*
* Floating point AAN DCT
* Copyright (c) 2003 Michael Niedermayer <michaelni@gmx.at>
*
* this implementation is based upon the IJG integer AAN DCT (see jfdctfst.c)
*
* This file is part of FFmpeg.
*
* FFmpeg is free software; you can redistribute it and/or
* modify it under the terms of the GNU Lesser General Public
* License as published by the Free Software Foundation; either
* version 2.1 of the License, or (at your option) any later version.
*
* FFmpeg is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
* License along with FFmpeg; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*
* The AAN DCT in this file except ff_faandct248() can also be used under the
* new (3 clause) BSD license.
*/
/**
* @file faandct.c
* @brief
* Floating point AAN DCT
* @author Michael Niedermayer <michaelni@gmx.at>
*/
#include "dsputil.h"
#include "faandct.h"
#define FLOAT float
#ifdef FAAN_POSTSCALE
# define SCALE(x) postscale[x]
#else
# define SCALE(x) 1
#endif
//numbers generated by simple c code (not as accurate as they could be)
/*
for(i=0; i<8; i++){
printf("#define B%d %1.20llf\n", i, (long double)1.0/(cosl(i*acosl(-1.0)/(long double)16.0)*sqrtl(2)));
}
*/
#define B0 1.00000000000000000000
#define B1 0.72095982200694791383 // (cos(pi*1/16)sqrt(2))^-1
#define B2 0.76536686473017954350 // (cos(pi*2/16)sqrt(2))^-1
#define B3 0.85043009476725644878 // (cos(pi*3/16)sqrt(2))^-1
#define B4 1.00000000000000000000 // (cos(pi*4/16)sqrt(2))^-1
#define B5 1.27275858057283393842 // (cos(pi*5/16)sqrt(2))^-1
#define B6 1.84775906502257351242 // (cos(pi*6/16)sqrt(2))^-1
#define B7 3.62450978541155137218 // (cos(pi*7/16)sqrt(2))^-1
#define A1 0.70710678118654752438 // cos(pi*4/16)
#define A2 0.54119610014619698435 // cos(pi*6/16)sqrt(2)
#define A5 0.38268343236508977170 // cos(pi*6/16)
#define A4 1.30656296487637652774 // cos(pi*2/16)sqrt(2)
static const FLOAT postscale[64]={
B0*B0, B0*B1, B0*B2, B0*B3, B0*B4, B0*B5, B0*B6, B0*B7,
B1*B0, B1*B1, B1*B2, B1*B3, B1*B4, B1*B5, B1*B6, B1*B7,
B2*B0, B2*B1, B2*B2, B2*B3, B2*B4, B2*B5, B2*B6, B2*B7,
B3*B0, B3*B1, B3*B2, B3*B3, B3*B4, B3*B5, B3*B6, B3*B7,
B4*B0, B4*B1, B4*B2, B4*B3, B4*B4, B4*B5, B4*B6, B4*B7,
B5*B0, B5*B1, B5*B2, B5*B3, B5*B4, B5*B5, B5*B6, B5*B7,
B6*B0, B6*B1, B6*B2, B6*B3, B6*B4, B6*B5, B6*B6, B6*B7,
B7*B0, B7*B1, B7*B2, B7*B3, B7*B4, B7*B5, B7*B6, B7*B7,
};
static av_always_inline void row_fdct(FLOAT temp[64], DCTELEM * data)
{
FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
FLOAT tmp10, tmp11, tmp12, tmp13;
FLOAT z2, z4, z11, z13;
FLOAT av_unused z5;
int i;
for (i=0; i<8*8; i+=8) {
tmp0= data[0 + i] + data[7 + i];
tmp7= data[0 + i] - data[7 + i];
tmp1= data[1 + i] + data[6 + i];
tmp6= data[1 + i] - data[6 + i];
tmp2= data[2 + i] + data[5 + i];
tmp5= data[2 + i] - data[5 + i];
tmp3= data[3 + i] + data[4 + i];
tmp4= data[3 + i] - data[4 + i];
tmp10= tmp0 + tmp3;
tmp13= tmp0 - tmp3;
tmp11= tmp1 + tmp2;
tmp12= tmp1 - tmp2;
temp[0 + i]= tmp10 + tmp11;
temp[4 + i]= tmp10 - tmp11;
tmp12 += tmp13;
tmp12 *= A1;
temp[2 + i]= tmp13 + tmp12;
temp[6 + i]= tmp13 - tmp12;
tmp4 += tmp5;
tmp5 += tmp6;
tmp6 += tmp7;
#if 0
z5= (tmp4 - tmp6) * A5;
z2= tmp4*A2 + z5;
z4= tmp6*A4 + z5;
#else
z2= tmp4*(A2+A5) - tmp6*A5;
z4= tmp6*(A4-A5) + tmp4*A5;
#endif
tmp5*=A1;
z11= tmp7 + tmp5;
z13= tmp7 - tmp5;
temp[5 + i]= z13 + z2;
temp[3 + i]= z13 - z2;
temp[1 + i]= z11 + z4;
temp[7 + i]= z11 - z4;
}
}
void ff_faandct(DCTELEM * data)
{
FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
FLOAT tmp10, tmp11, tmp12, tmp13;
FLOAT z2, z4, z11, z13;
FLOAT av_unused z5;
FLOAT temp[64];
int i;
emms_c();
row_fdct(temp, data);
for (i=0; i<8; i++) {
tmp0= temp[8*0 + i] + temp[8*7 + i];
tmp7= temp[8*0 + i] - temp[8*7 + i];
tmp1= temp[8*1 + i] + temp[8*6 + i];
tmp6= temp[8*1 + i] - temp[8*6 + i];
tmp2= temp[8*2 + i] + temp[8*5 + i];
tmp5= temp[8*2 + i] - temp[8*5 + i];
tmp3= temp[8*3 + i] + temp[8*4 + i];
tmp4= temp[8*3 + i] - temp[8*4 + i];
tmp10= tmp0 + tmp3;
tmp13= tmp0 - tmp3;
tmp11= tmp1 + tmp2;
tmp12= tmp1 - tmp2;
data[8*0 + i]= lrintf(SCALE(8*0 + i) * (tmp10 + tmp11));
data[8*4 + i]= lrintf(SCALE(8*4 + i) * (tmp10 - tmp11));
tmp12 += tmp13;
tmp12 *= A1;
data[8*2 + i]= lrintf(SCALE(8*2 + i) * (tmp13 + tmp12));
data[8*6 + i]= lrintf(SCALE(8*6 + i) * (tmp13 - tmp12));
tmp4 += tmp5;
tmp5 += tmp6;
tmp6 += tmp7;
#if 0
z5= (tmp4 - tmp6) * A5;
z2= tmp4*A2 + z5;
z4= tmp6*A4 + z5;
#else
z2= tmp4*(A2+A5) - tmp6*A5;
z4= tmp6*(A4-A5) + tmp4*A5;
#endif
tmp5*=A1;
z11= tmp7 + tmp5;
z13= tmp7 - tmp5;
data[8*5 + i]= lrintf(SCALE(8*5 + i) * (z13 + z2));
data[8*3 + i]= lrintf(SCALE(8*3 + i) * (z13 - z2));
data[8*1 + i]= lrintf(SCALE(8*1 + i) * (z11 + z4));
data[8*7 + i]= lrintf(SCALE(8*7 + i) * (z11 - z4));
}
}
void ff_faandct248(DCTELEM * data)
{
FLOAT tmp0, tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7;
FLOAT tmp10, tmp11, tmp12, tmp13;
FLOAT temp[64];
int i;
emms_c();
row_fdct(temp, data);
for (i=0; i<8; i++) {
tmp0 = temp[8*0 + i] + temp[8*1 + i];
tmp1 = temp[8*2 + i] + temp[8*3 + i];
tmp2 = temp[8*4 + i] + temp[8*5 + i];
tmp3 = temp[8*6 + i] + temp[8*7 + i];
tmp4 = temp[8*0 + i] - temp[8*1 + i];
tmp5 = temp[8*2 + i] - temp[8*3 + i];
tmp6 = temp[8*4 + i] - temp[8*5 + i];
tmp7 = temp[8*6 + i] - temp[8*7 + i];
tmp10 = tmp0 + tmp3;
tmp11 = tmp1 + tmp2;
tmp12 = tmp1 - tmp2;
tmp13 = tmp0 - tmp3;
data[8*0 + i] = lrintf(SCALE(8*0 + i) * (tmp10 + tmp11));
data[8*4 + i] = lrintf(SCALE(8*4 + i) * (tmp10 - tmp11));
tmp12 += tmp13;
tmp12 *= A1;
data[8*2 + i] = lrintf(SCALE(8*2 + i) * (tmp13 + tmp12));
data[8*6 + i] = lrintf(SCALE(8*6 + i) * (tmp13 - tmp12));
tmp10 = tmp4 + tmp7;
tmp11 = tmp5 + tmp6;
tmp12 = tmp5 - tmp6;
tmp13 = tmp4 - tmp7;
data[8*1 + i] = lrintf(SCALE(8*0 + i) * (tmp10 + tmp11));
data[8*5 + i] = lrintf(SCALE(8*4 + i) * (tmp10 - tmp11));
tmp12 += tmp13;
tmp12 *= A1;
data[8*3 + i] = lrintf(SCALE(8*2 + i) * (tmp13 + tmp12));
data[8*7 + i] = lrintf(SCALE(8*6 + i) * (tmp13 - tmp12));
}
}
|
