idctllm.c 11.9 KB
Newer Older
John Koleszar's avatar
John Koleszar committed
1
/*
2
 *  Copyright (c) 2010 The WebM project authors. All Rights Reserved.
John Koleszar's avatar
John Koleszar committed
3
 *
4
 *  Use of this source code is governed by a BSD-style license
5
6
 *  that can be found in the LICENSE file in the root of the source
 *  tree. An additional intellectual property rights grant can be found
7
 *  in the file PATENTS.  All contributing project authors may
8
 *  be found in the AUTHORS file in the root of the source tree.
John Koleszar's avatar
John Koleszar committed
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
 */


/****************************************************************************
 * Notes:
 *
 * This implementation makes use of 16 bit fixed point verio of two multiply
 * constants:
 *         1.   sqrt(2) * cos (pi/8)
 *         2.   sqrt(2) * sin (pi/8)
 * Becuase the first constant is bigger than 1, to maintain the same 16 bit
 * fixed point precision as the second one, we use a trick of
 *         x * a = x + x*(a-1)
 * so
 *         x * sqrt(2) * cos (pi/8) = x + x * (sqrt(2) *cos(pi/8)-1).
 **************************************************************************/
25
26
#include "vpx_ports/config.h"

27
28
29

#include <math.h>

John Koleszar's avatar
John Koleszar committed
30
31
32
static const int cospi8sqrt2minus1 = 20091;
static const int sinpi8sqrt2      = 35468;
static const int rounding = 0;
33

John Koleszar's avatar
John Koleszar committed
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
void vp8_short_idct4x4llm_c(short *input, short *output, int pitch)
{
    int i;
    int a1, b1, c1, d1;

    short *ip = input;
    short *op = output;
    int temp1, temp2;
    int shortpitch = pitch >> 1;

    for (i = 0; i < 4; i++)
    {
        a1 = ip[0] + ip[8];
        b1 = ip[0] - ip[8];

        temp1 = (ip[4] * sinpi8sqrt2 + rounding) >> 16;
        temp2 = ip[12] + ((ip[12] * cospi8sqrt2minus1 + rounding) >> 16);
        c1 = temp1 - temp2;

        temp1 = ip[4] + ((ip[4] * cospi8sqrt2minus1 + rounding) >> 16);
        temp2 = (ip[12] * sinpi8sqrt2 + rounding) >> 16;
        d1 = temp1 + temp2;

        op[shortpitch*0] = a1 + d1;
        op[shortpitch*3] = a1 - d1;

        op[shortpitch*1] = b1 + c1;
        op[shortpitch*2] = b1 - c1;

        ip++;
        op++;
    }

    ip = output;
    op = output;

    for (i = 0; i < 4; i++)
    {
        a1 = ip[0] + ip[2];
        b1 = ip[0] - ip[2];

        temp1 = (ip[1] * sinpi8sqrt2 + rounding) >> 16;
        temp2 = ip[3] + ((ip[3] * cospi8sqrt2minus1 + rounding) >> 16);
        c1 = temp1 - temp2;

        temp1 = ip[1] + ((ip[1] * cospi8sqrt2minus1 + rounding) >> 16);
        temp2 = (ip[3] * sinpi8sqrt2 + rounding) >> 16;
        d1 = temp1 + temp2;

83
84
85
86
87
        op[0] = (a1 + d1 + 16) >> 5;
        op[3] = (a1 - d1 + 16) >> 5;

        op[1] = (b1 + c1 + 16) >> 5;
        op[2] = (b1 - c1 + 16) >> 5;
John Koleszar's avatar
John Koleszar committed
88
89
90
91
92
93
94
95
96
97
98
99

        ip += shortpitch;
        op += shortpitch;
    }
}

void vp8_short_idct4x4llm_1_c(short *input, short *output, int pitch)
{
    int i;
    int a1;
    short *op = output;
    int shortpitch = pitch >> 1;
100
    a1 = ((input[0] + 16) >> 5);
John Koleszar's avatar
John Koleszar committed
101
102
103
104
105
106
107
108
109
110
    for (i = 0; i < 4; i++)
    {
        op[0] = a1;
        op[1] = a1;
        op[2] = a1;
        op[3] = a1;
        op += shortpitch;
    }
}

111
void vp8_dc_only_idct_add_c(short input_dc, unsigned char *pred_ptr, unsigned char *dst_ptr, int pitch, int stride)
John Koleszar's avatar
John Koleszar committed
112
{
113
    int a1 = ((input_dc + 16) >> 5);
114
    int r, c;
John Koleszar's avatar
John Koleszar committed
115

116
    for (r = 0; r < 4; r++)
John Koleszar's avatar
John Koleszar committed
117
    {
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
        for (c = 0; c < 4; c++)
        {
            int a = a1 + pred_ptr[c] ;

            if (a < 0)
                a = 0;

            if (a > 255)
                a = 255;

            dst_ptr[c] = (unsigned char) a ;
        }

        dst_ptr += stride;
        pred_ptr += pitch;
John Koleszar's avatar
John Koleszar committed
133
    }
134

John Koleszar's avatar
John Koleszar committed
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
}

void vp8_short_inv_walsh4x4_c(short *input, short *output)
{
    int i;
    int a1, b1, c1, d1;
    int a2, b2, c2, d2;
    short *ip = input;
    short *op = output;

    for (i = 0; i < 4; i++)
    {
        a1 = ip[0] + ip[12];
        b1 = ip[4] + ip[8];
        c1 = ip[4] - ip[8];
        d1 = ip[0] - ip[12];

        op[0] = a1 + b1;
        op[4] = c1 + d1;
        op[8] = a1 - b1;
        op[12] = d1 - c1;
        ip++;
        op++;
    }

    ip = output;
    op = output;

    for (i = 0; i < 4; i++)
    {
        a1 = ip[0] + ip[3];
        b1 = ip[1] + ip[2];
        c1 = ip[1] - ip[2];
        d1 = ip[0] - ip[3];

        a2 = a1 + b1;
        b2 = c1 + d1;
        c2 = a1 - b1;
        d2 = d1 - c1;

175
176
177
178
        op[0] = (a2 + 1) >> 2;
        op[1] = (b2 + 1) >> 2;
        op[2] = (c2 + 1) >> 2;
        op[3] = (d2 + 1) >> 2;
Paul Wilkins's avatar
Paul Wilkins committed
179

John Koleszar's avatar
John Koleszar committed
180
181
182
183
184
185
186
187
188
189
190
        ip += 4;
        op += 4;
    }
}

void vp8_short_inv_walsh4x4_1_c(short *input, short *output)
{
    int i;
    int a1;
    short *op = output;

Yaowu Xu's avatar
Yaowu Xu committed
191
    a1 = (input[0] + 1 )>> 2;
John Koleszar's avatar
John Koleszar committed
192
193
194
195
196
197
198
199
200
201

    for (i = 0; i < 4; i++)
    {
        op[0] = a1;
        op[1] = a1;
        op[2] = a1;
        op[3] = a1;
        op += 4;
    }
}
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
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344

#if CONFIG_T8X8

#define FAST_IDCT_8X8

void vp8_short_idct8x8_1_c(short *input, short *output, int pitch)
{
    int i, b;
    int a1;
    short *op = output;
    short *orig_op = output;
    int shortpitch = pitch >> 1;
    a1 = ((input[0] + 4) >> 3);
    for (b = 0; b < 4; b++)
    {
        for (i = 0; i < 4; i++)
        {
            op[0] = a1;
            op[1] = a1;
            op[2] = a1;
            op[3] = a1;
            op += shortpitch;
        }
        op = orig_op + (b+1)%2*4 +(b+1)/2*4*shortpitch;
    }
}

void vp8_dc_only_idct_add_8x8_c(short input_dc, unsigned char *pred_ptr, unsigned char *dst_ptr, int pitch, int stride)
{
    int a1 = ((input_dc + 4) >> 3);
    int r, c, b;
    unsigned char *orig_pred = pred_ptr;
    unsigned char *orig_dst = dst_ptr;
    for (b = 0; b < 4; b++)
    {
        for (r = 0; r < 4; r++)
        {
          for (c = 0; c < 4; c++)
          {
              int a = a1 + pred_ptr[c] ;

              if (a < 0)
                 a = 0;

              if (a > 255)
                 a = 255;

              dst_ptr[c] = (unsigned char) a ;
         }

         dst_ptr += stride;
         pred_ptr += pitch;
       }
        dst_ptr = orig_dst + (b+1)%2*4 + (b+1)/2*4*stride;
        pred_ptr = orig_pred + (b+1)%2*4 + (b+1)/2*4*pitch;
    }
}

#ifdef FAST_IDCT_8X8

#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) */

/* 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 (int *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 (int *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] =
      ((blk[8 * 0] + 32) >> 6);
    return;
  }
345
  x0 = (blk[8 * 0] << 8) + 16384;
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374

  /* 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 */
375
376
377
378
379
380
381
382
  blk[8 * 0] = (x7 + x1 ) >> 14;
  blk[8 * 1] = (x3 + x2 ) >> 14;
  blk[8 * 2] = (x0 + x4 ) >> 14;
  blk[8 * 3] = (x8 + x6 ) >> 14;
  blk[8 * 4] = (x8 - x6 ) >> 14;
  blk[8 * 5] = (x0 - x4 ) >> 14;
  blk[8 * 6] = (x3 - x2 ) >> 14;
  blk[8 * 7] = (x7 - x1 ) >> 14;
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
}

#define TX_DIM 8
void vp8_short_idct8x8_c(short *coefs, short *block, int pitch)
// an approximate 8x8 dct implementation, but not used
{
    int X[TX_DIM*TX_DIM];
    int i,j;
    int shortpitch = pitch >> 1;

    for (i = 0; i < TX_DIM; i++)
    {
        for (j = 0; j < TX_DIM; j++)
        {
             X[i * TX_DIM + j] = (int)coefs[i * TX_DIM + j];
        }
    }
  for (i = 0; i < 8; i++)
    idctrow (X + 8 * i);

  for (i = 0; i < 8; i++)
    idctcol (X + i);

    for (i = 0; i < TX_DIM; i++)
    {
        for (j = 0; j < TX_DIM; j++)
        {
410
             block[i*shortpitch+j]  = X[i * TX_DIM + j]>>1;
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
        }
    }
}

#else

/* This is really for testing */
void vp8_short_idct8x8_c(short *input, short *output, int pitch)
{
    int X[8][8];
    double C[8][8]={{0.0}}, Ct[8][8]={{0.0}}, temp[8][8]={{0.0}};
    int i,j,k;
    double temp1=0.0;
    double pi = atan( 1.0 ) * 4.0;
    //static int count=0;

    int shortpitch = pitch >> 1;

    for (i = 0; i < 8; i++)
    {
        for (j = 0; j < 8; j++)
        {
             X[i][j] = input[i * 8 + j];
        }
     }

    // TODO: DCT matrix should be calculated once for all
    for ( j = 0 ; j < 8 ; j++ ) {
        C[ 0 ][ j ] = 1.0 / sqrt( (double) 8 );
        Ct[ j ][ 0 ] = C[ 0 ][ j ];
    }
    for ( i = 1 ; i < 8 ; i++ ) {
        for ( j = 0 ; j < 8 ; j++ ) {
            C[ i ][ j ] = sqrt( 2.0 / 8 ) *
                          cos( pi * ( 2 * j + 1 ) * i / ( 2.0 * 8 ) );
            Ct[ j ][ i ] = C[ i ][ j ];
        }
    }
    /*  MatrixMultiply( temp, input, C ); */
        for ( i = 0 ; i < 8 ; i++ ) {
            for ( j = 0 ; j < 8 ; j++ ) {
                temp[ i ][ j ] = 0.0;
                for ( k = 0 ; k < 8 ; k++ )
                    temp[ i ][ j ] += X[ i ][ k ] * C[ k ][ j ];
            }
        }

    /*  MatrixMultiply( output, Ct, temp ); */
        for ( i = 0 ; i < 8 ; i++ ) {
            for ( j = 0 ; j < 8 ; j++ ) {
                temp1 = 0.0;
                for ( k = 0 ; k < 8 ; k++ )
                    temp1 += Ct[ i ][ k ] * temp[ k ][ j ];
                X[ i ][ j ] = floor( temp1/ 2.0 + 0.5);
            }
        }

    for (i = 0; i < 8; i++)
    {
        for (j = 0; j < 8; j++)
        {
             output[i*shortpitch+j]  = X[i][j];
        }
    }
}
#endif

void vp8_short_ihaar2x2_c(short *input, short *output, int pitch)
{
   int i, x;
   short *ip = input; //0,1, 4, 8
   short *op = output;
   for (i = 0; i < 16; i++)
   {
       op[i] = 0;
   }

488
489
490
491
   op[0] = (ip[0] + ip[1] + ip[4] + ip[8])>>2;
   op[1] = (ip[0] - ip[1] + ip[4] - ip[8])>>2;
   op[4] = (ip[0] + ip[1] - ip[4] - ip[8])>>2;
   op[8] = (ip[0] - ip[1] - ip[4] + ip[8])>>2;
492
493
494
495
496
497
498
}

void vp8_short_ihaar2x2_1_c(short *input, short *output, int pitch)
{
   int a1;
   short *ip = input;
   short *op = output;
499
   a1 = ip[0]>> 2;
500
501
502
503
504
505
506
   op[0] = a1;
   op[2] = a1;
   op[8] = a1;
   op[10] = a1;

}
#endif