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
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
|
/*
* idct.c
* Copyright (C) 1999-2000 Aaron Holtzman <aholtzma@ess.engr.uvic.ca>
*
* Portions of this code are from the MPEG software simulation group
* idct implementation. This code will be replaced with a new
* implementation soon.
*
* This file is part of mpeg2dec, a free MPEG-2 video stream decoder.
*
* mpeg2dec is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* mpeg2dec 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 General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
/**********************************************************/
/* 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 */
/**********************************************************/
/* this code assumes >> to be a two's-complement arithmetic */
/* right shift: (-2)>>1 == -1 , (-3)>>1 == -2 */
#include "config.h"
#include <stdio.h>
#include <inttypes.h>
#include "mpeg2_internal.h"
#include "mm_accel.h"
#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) */
// idct main entry point
void (*idct_block_copy) (int16_t * block, uint8_t * dest, int stride);
void (*idct_block_add) (int16_t * block, uint8_t * dest, int stride);
static void idct_block_copy_c (int16_t *block, uint8_t * dest, int stride);
static void idct_block_add_c (int16_t *block, uint8_t * dest, int stride);
static uint8_t clip_lut[1024];
#define CLIP(i) ((clip_lut+384)[ (i)])
void idct_init (void)
{
#ifdef ARCH_X86
if (config.flags & MM_ACCEL_X86_MMXEXT) {
fprintf (stderr, "Using MMXEXT for IDCT transform\n");
idct_block_copy = idct_block_copy_mmxext;
idct_block_add = idct_block_add_mmxext;
idct_mmx_init ();
} else if (config.flags & MM_ACCEL_X86_MMX) {
fprintf (stderr, "Using MMX for IDCT transform\n");
idct_block_copy = idct_block_copy_mmx;
idct_block_add = idct_block_add_mmx;
idct_mmx_init ();
} else
#endif
#ifdef LIBMPEG2_MLIB
if (config.flags & MM_ACCEL_MLIB) {
fprintf (stderr, "Using mlib for IDCT transform\n");
idct_block_copy = idct_block_copy_mlib;
idct_block_add = idct_block_add_mlib;
} else
#endif
{
int i;
fprintf (stderr, "No accelerated IDCT transform found\n");
idct_block_copy = idct_block_copy_c;
idct_block_add = idct_block_add_c;
for (i = -384; i < 640; i++)
clip_lut[i+384] = (i < 0) ? 0 : ((i > 255) ? 255 : i);
}
}
/* 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 inline idct_row (int16_t * block)
{
int x0, x1, x2, x3, x4, x5, x6, x7, x8;
x1 = block[4] << 11;
x2 = block[6];
x3 = block[2];
x4 = block[1];
x5 = block[7];
x6 = block[5];
x7 = block[3];
/* shortcut */
if (! (x1 | x2 | x3 | x4 | x5 | x6 | x7 )) {
block[0] = block[1] = block[2] = block[3] = block[4] =
block[5] = block[6] = block[7] = block[0]<<3;
return;
}
x0 = (block[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 */
block[0] = (x7 + x1) >> 8;
block[1] = (x3 + x2) >> 8;
block[2] = (x0 + x4) >> 8;
block[3] = (x8 + x6) >> 8;
block[4] = (x8 - x6) >> 8;
block[5] = (x0 - x4) >> 8;
block[6] = (x3 - x2) >> 8;
block[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 inline idct_col (int16_t *block)
{
int x0, x1, x2, x3, x4, x5, x6, x7, x8;
/* shortcut */
x1 = block [8*4] << 8;
x2 = block [8*6];
x3 = block [8*2];
x4 = block [8*1];
x5 = block [8*7];
x6 = block [8*5];
x7 = block [8*3];
#if 0
if (! (x1 | x2 | x3 | x4 | x5 | x6 | x7 )) {
block[8*0] = block[8*1] = block[8*2] = block[8*3] = block[8*4] =
block[8*5] = block[8*6] = block[8*7] = (block[8*0] + 32) >> 6;
return;
}
#endif
x0 = (block[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 */
block[8*0] = (x7 + x1) >> 14;
block[8*1] = (x3 + x2) >> 14;
block[8*2] = (x0 + x4) >> 14;
block[8*3] = (x8 + x6) >> 14;
block[8*4] = (x8 - x6) >> 14;
block[8*5] = (x0 - x4) >> 14;
block[8*6] = (x3 - x2) >> 14;
block[8*7] = (x7 - x1) >> 14;
}
void idct_block_copy_c (int16_t * block, uint8_t * dest, int stride)
{
int i;
for (i = 0; i < 8; i++)
idct_row (block + 8 * i);
for (i = 0; i < 8; i++)
idct_col (block + i);
i = 8;
do {
dest[0] = CLIP (block[0]);
dest[1] = CLIP (block[1]);
dest[2] = CLIP (block[2]);
dest[3] = CLIP (block[3]);
dest[4] = CLIP (block[4]);
dest[5] = CLIP (block[5]);
dest[6] = CLIP (block[6]);
dest[7] = CLIP (block[7]);
dest += stride;
block += 8;
} while (--i);
}
void idct_block_add_c (int16_t * block, uint8_t * dest, int stride)
{
int i;
for (i = 0; i < 8; i++)
idct_row (block + 8 * i);
for (i = 0; i < 8; i++)
idct_col (block + i);
i = 8;
do {
dest[0] = CLIP (block[0] + dest[0]);
dest[1] = CLIP (block[1] + dest[1]);
dest[2] = CLIP (block[2] + dest[2]);
dest[3] = CLIP (block[3] + dest[3]);
dest[4] = CLIP (block[4] + dest[4]);
dest[5] = CLIP (block[5] + dest[5]);
dest[6] = CLIP (block[6] + dest[6]);
dest[7] = CLIP (block[7] + dest[7]);
dest += stride;
block += 8;
} while (--i);
}
|
