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
|
/* idct.c, inverse fast discrete cosine transform */
/* Copyright (C) 1996, MPEG Software Simulation Group. All Rights Reserved. */
/*
* Disclaimer of Warranty
*
* These software programs are available to the user without any license fee or
* royalty on an "as is" basis. The MPEG Software Simulation Group disclaims
* any and all warranties, whether express, implied, or statuary, including any
* implied warranties or merchantability or of fitness for a particular
* purpose. In no event shall the copyright-holder be liable for any
* incidental, punitive, or consequential damages of any kind whatsoever
* arising from the use of these programs.
*
* This disclaimer of warranty extends to the user of these programs and user's
* customers, employees, agents, transferees, successors, and assigns.
*
* The MPEG Software Simulation Group does not represent or warrant that the
* programs furnished hereunder are free of infringement of any third-party
* patents.
*
* Commercial implementations of MPEG-1 and MPEG-2 video, including shareware,
* are subject to royalty fees to patent holders. Many of these patents are
* general enough such that they are unavoidable regardless of implementation
* design.
*
*/
/**********************************************************/
/* inverse two dimensional DCT, Chen-Wang algorithm */
/* (cf. IEEE ASSP-32, pp. 803-816, Aug. 1984) */
/* 32-bit integer arithmetic (8 bit coefficients) */
/* 11 mults, 29 adds per DCT */
/* sE, 18.8.91 */
/**********************************************************/
/* coefficients extended to 12 bit for IEEE1180-1990 */
/* compliance sE, 2.1.94 */
/**********************************************************/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
/* this code assumes >> to be a two's-complement arithmetic */
/* right shift: (-2)>>1 == -1 , (-3)>>1 == -2 */
#define W1 2841 /* 2048*sqrt(2)*cos(1*pi/16) */
#define W2 2676 /* 2048*sqrt(2)*cos(2*pi/16) */
#define W3 2408 /* 2048*sqrt(2)*cos(3*pi/16) */
#define W5 1609 /* 2048*sqrt(2)*cos(5*pi/16) */
#define W6 1108 /* 2048*sqrt(2)*cos(6*pi/16) */
#define W7 565 /* 2048*sqrt(2)*cos(7*pi/16) */
#include "dct.h"
/* private data */
static short iclip[1024]; /* clipping table */
static short *iclp;
/* private prototypes */
static void idctrow (short *blk);
static void idctcol (short *blk);
/* row (horizontal) IDCT
*
* 7 pi 1
* dst[k] = sum c[l] * src[l] * cos( -- * ( k + - ) * l )
* l=0 8 2
*
* where: c[0] = 128
* c[1..7] = 128*sqrt(2)
*/
static void
idctrow (blk)
short *blk;
{
int x0, x1, x2, x3, x4, x5, x6, x7, x8;
/* shortcut */
if (!((x1 = blk[4] << 11) | (x2 = blk[6]) | (x3 = blk[2]) |
(x4 = blk[1]) | (x5 = blk[7]) | (x6 = blk[5]) | (x7 = blk[3]))) {
blk[0] = blk[1] = blk[2] = blk[3] = blk[4] = blk[5] = blk[6] = blk[7] =
blk[0] << 3;
return;
}
x0 = (blk[0] << 11) + 128; /* for proper rounding in the fourth stage */
/* first stage */
x8 = W7 * (x4 + x5);
x4 = x8 + (W1 - W7) * x4;
x5 = x8 - (W1 + W7) * x5;
x8 = W3 * (x6 + x7);
x6 = x8 - (W3 - W5) * x6;
x7 = x8 - (W3 + W5) * x7;
/* second stage */
x8 = x0 + x1;
x0 -= x1;
x1 = W6 * (x3 + x2);
x2 = x1 - (W2 + W6) * x2;
x3 = x1 + (W2 - W6) * x3;
x1 = x4 + x6;
x4 -= x6;
x6 = x5 + x7;
x5 -= x7;
/* third stage */
x7 = x8 + x3;
x8 -= x3;
x3 = x0 + x2;
x0 -= x2;
x2 = (181 * (x4 + x5) + 128) >> 8;
x4 = (181 * (x4 - x5) + 128) >> 8;
/* fourth stage */
blk[0] = (x7 + x1) >> 8;
blk[1] = (x3 + x2) >> 8;
blk[2] = (x0 + x4) >> 8;
blk[3] = (x8 + x6) >> 8;
blk[4] = (x8 - x6) >> 8;
blk[5] = (x0 - x4) >> 8;
blk[6] = (x3 - x2) >> 8;
blk[7] = (x7 - x1) >> 8;
}
/* column (vertical) IDCT
*
* 7 pi 1
* dst[8*k] = sum c[l] * src[8*l] * cos( -- * ( k + - ) * l )
* l=0 8 2
*
* where: c[0] = 1/1024
* c[1..7] = (1/1024)*sqrt(2)
*/
static void
idctcol (blk)
short *blk;
{
int x0, x1, x2, x3, x4, x5, x6, x7, x8;
/* shortcut */
if (!((x1 = (blk[8 * 4] << 8)) | (x2 = blk[8 * 6]) | (x3 = blk[8 * 2]) |
(x4 = blk[8 * 1]) | (x5 = blk[8 * 7]) | (x6 = blk[8 * 5]) | (x7 =
blk[8 * 3]))) {
blk[8 * 0] = blk[8 * 1] = blk[8 * 2] = blk[8 * 3] = blk[8 * 4] =
blk[8 * 5] = blk[8 * 6] = blk[8 * 7] = iclp[(blk[8 * 0] + 32) >> 6];
return;
}
x0 = (blk[8 * 0] << 8) + 8192;
/* first stage */
x8 = W7 * (x4 + x5) + 4;
x4 = (x8 + (W1 - W7) * x4) >> 3;
x5 = (x8 - (W1 + W7) * x5) >> 3;
x8 = W3 * (x6 + x7) + 4;
x6 = (x8 - (W3 - W5) * x6) >> 3;
x7 = (x8 - (W3 + W5) * x7) >> 3;
/* second stage */
x8 = x0 + x1;
x0 -= x1;
x1 = W6 * (x3 + x2) + 4;
x2 = (x1 - (W2 + W6) * x2) >> 3;
x3 = (x1 + (W2 - W6) * x3) >> 3;
x1 = x4 + x6;
x4 -= x6;
x6 = x5 + x7;
x5 -= x7;
/* third stage */
x7 = x8 + x3;
x8 -= x3;
x3 = x0 + x2;
x0 -= x2;
x2 = (181 * (x4 + x5) + 128) >> 8;
x4 = (181 * (x4 - x5) + 128) >> 8;
/* fourth stage */
blk[8 * 0] = iclp[(x7 + x1) >> 14];
blk[8 * 1] = iclp[(x3 + x2) >> 14];
blk[8 * 2] = iclp[(x0 + x4) >> 14];
blk[8 * 3] = iclp[(x8 + x6) >> 14];
blk[8 * 4] = iclp[(x8 - x6) >> 14];
blk[8 * 5] = iclp[(x0 - x4) >> 14];
blk[8 * 6] = iclp[(x3 - x2) >> 14];
blk[8 * 7] = iclp[(x7 - x1) >> 14];
}
/* two dimensional inverse discrete cosine transform */
void
gst_idct_fast_int_idct (block)
short *block;
{
int i;
for (i = 0; i < 8; i++)
idctrow (block + 8 * i);
for (i = 0; i < 8; i++)
idctcol (block + i);
}
void
gst_idct_init_fast_int_idct ()
{
int i;
iclp = iclip + 512;
for (i = -512; i < 512; i++)
iclp[i] = (i < -256) ? -256 : ((i > 255) ? 255 : i);
}
|
