idctllm.c 25.5 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
#include "vpx_ports/config.h"
Hui Su's avatar
Hui Su committed
26
#include "vp8/common/idct.h"
27

Jingning Han's avatar
Jingning Han committed
28
29
30
#if CONFIG_HYBRIDTRANSFORM
#include "vp8/common/blockd.h"
#endif
31
32
33

#include <math.h>

John Koleszar's avatar
John Koleszar committed
34
35
36
static const int cospi8sqrt2minus1 = 20091;
static const int sinpi8sqrt2      = 35468;
static const int rounding = 0;
37

38
39
// TODO: these transforms can be further converted into integer forms
//       for complexity optimization
Jingning Han's avatar
Jingning Han committed
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
#if CONFIG_HYBRIDTRANSFORM
float idct_4[16] = {
  0.500000000000000,   0.653281482438188,   0.500000000000000,   0.270598050073099,
  0.500000000000000,   0.270598050073099,  -0.500000000000000,  -0.653281482438188,
  0.500000000000000,  -0.270598050073099,  -0.500000000000000,   0.653281482438188,
  0.500000000000000,  -0.653281482438188,   0.500000000000000,  -0.270598050073099
};

float iadst_4[16] = {
  0.228013428883779,   0.577350269189626,   0.656538502008139,   0.428525073124360,
  0.428525073124360,   0.577350269189626,  -0.228013428883779,  -0.656538502008139,
  0.577350269189626,                   0,  -0.577350269189626,   0.577350269189626,
  0.656538502008139,  -0.577350269189626,   0.428525073124359,  -0.228013428883779
};
#endif

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
#if CONFIG_HYBRIDTRANSFORM8X8
float idct_8[64] = {
  0.353553390593274,   0.490392640201615,   0.461939766255643,   0.415734806151273,
  0.353553390593274,   0.277785116509801,   0.191341716182545,   0.097545161008064,
  0.353553390593274,   0.415734806151273,   0.191341716182545,  -0.097545161008064,
 -0.353553390593274,  -0.490392640201615,  -0.461939766255643,  -0.277785116509801,
  0.353553390593274,   0.277785116509801,  -0.191341716182545,  -0.490392640201615,
 -0.353553390593274,   0.097545161008064,   0.461939766255643,   0.415734806151273,
  0.353553390593274,   0.097545161008064,  -0.461939766255643,  -0.277785116509801,
  0.353553390593274,   0.415734806151273,  -0.191341716182545,  -0.490392640201615,
  0.353553390593274,  -0.097545161008064,  -0.461939766255643,   0.277785116509801,
  0.353553390593274,  -0.415734806151273,  -0.191341716182545,   0.490392640201615,
  0.353553390593274,  -0.277785116509801,  -0.191341716182545,   0.490392640201615,
 -0.353553390593274,  -0.097545161008064,   0.461939766255643,  -0.415734806151273,
  0.353553390593274,  -0.415734806151273,   0.191341716182545,   0.097545161008064,
 -0.353553390593274,   0.490392640201615,  -0.461939766255643,   0.277785116509801,
  0.353553390593274,  -0.490392640201615,   0.461939766255643,  -0.415734806151273,
  0.353553390593274,  -0.277785116509801,   0.191341716182545,  -0.097545161008064
};

float iadst_8[64] = {
  0.089131608307533,   0.255357107325376,   0.387095214016349,   0.466553967085785,
  0.483002021635509,   0.434217976756762,   0.326790388032145,   0.175227946595735,
  0.175227946595735,   0.434217976756762,   0.466553967085785,   0.255357107325376,
 -0.089131608307533,  -0.387095214016348,  -0.483002021635509,  -0.326790388032145,
  0.255357107325376,   0.483002021635509,   0.175227946595735,  -0.326790388032145,
 -0.466553967085785,  -0.089131608307533,   0.387095214016349,   0.434217976756762,
  0.326790388032145,   0.387095214016349,  -0.255357107325376,  -0.434217976756762,
  0.175227946595735,   0.466553967085786,  -0.089131608307534,  -0.483002021635509,
  0.387095214016349,   0.175227946595735,  -0.483002021635509,   0.089131608307533,
  0.434217976756762,  -0.326790388032145,  -0.255357107325377,   0.466553967085785,
  0.434217976756762,  -0.089131608307533,  -0.326790388032145,   0.483002021635509,
 -0.255357107325376,  -0.175227946595735,   0.466553967085785,  -0.387095214016348,
  0.466553967085785,  -0.326790388032145,   0.089131608307533,   0.175227946595735,
 -0.387095214016348,   0.483002021635509,  -0.434217976756762,   0.255357107325376,
  0.483002021635509,  -0.466553967085785,   0.434217976756762,  -0.387095214016348,
  0.326790388032145,  -0.255357107325375,   0.175227946595736,  -0.089131608307532
};
#endif

96
97
98
#if CONFIG_HYBRIDTRANSFORM8X8 || CONFIG_HYBRIDTRANSFORM
void vp8_ihtllm_c(short *input, short *output, int pitch,
                  TX_TYPE tx_type, int tx_dim) {
99
100
101
102
  int i, j, k;
  float bufa[64], bufb[64]; // buffers are for floating-point test purpose
                            // the implementation could be simplified in
                            // conjunction with integer transform
103
104
105
106

                            // further notice, since we are thinking to use one
                            // function for both 4x4 and 8x8 transforms, the
                            // temporary buffers are simply initialized with 64.
107
108
109
110
111
112
113
114
115
116
117
  short *ip = input;
  short *op = output;
  int shortpitch = pitch >> 1;

  float *pfa = &bufa[0];
  float *pfb = &bufb[0];

  // pointers to vertical and horizontal transforms
  float *ptv, *pth;

  // load and convert residual array into floating-point
118
119
  for(j = 0; j < tx_dim; j++) {
    for(i = 0; i < tx_dim; i++) {
120
121
      pfa[i] = (float)ip[i];
    }
122
123
    pfa += tx_dim;
    ip  += tx_dim;
124
125
126
127
128
129
130
131
132
  }

  // vertical transformation
  pfa = &bufa[0];
  pfb = &bufb[0];

  switch(tx_type) {
    case ADST_ADST :
    case ADST_DCT  :
133
      ptv = (tx_dim == 4) ? &iadst_4[0] : &iadst_8[0];
134
135
136
      break;

    default :
137
      ptv = (tx_dim == 4) ? &idct_4[0] : &idct_8[0];
138
139
140
      break;
  }

141
142
  for(j = 0; j < tx_dim; j++) {
    for(i = 0; i < tx_dim; i++) {
143
      pfb[i] = 0 ;
144
145
      for(k = 0; k < tx_dim; k++) {
        pfb[i] += ptv[k] * pfa[(k * tx_dim)];
146
147
148
149
      }
      pfa += 1;
    }

150
151
    pfb += tx_dim;
    ptv += tx_dim;
152
153
154
155
156
157
158
159
160
161
    pfa = &bufa[0];
  }

  // horizontal transformation
  pfa = &bufa[0];
  pfb = &bufb[0];

  switch(tx_type) {
    case ADST_ADST :
    case  DCT_ADST :
162
      pth = (tx_dim == 4) ? &iadst_4[0] : &iadst_8[0];
163
164
165
      break;

    default :
166
      pth = (tx_dim == 4) ? &idct_4[0] : &idct_8[0];
167
168
169
      break;
  }

170
171
  for(j = 0; j < tx_dim; j++) {
    for(i = 0; i < tx_dim; i++) {
172
      pfa[i] = 0;
173
      for(k = 0; k < tx_dim; k++) {
174
175
        pfa[i] += pfb[k] * pth[k];
      }
176
      pth += tx_dim;
177
178
     }

179
180
    pfa += tx_dim;
    pfb += tx_dim;
181
182
183
184

    switch(tx_type) {
      case ADST_ADST :
      case  DCT_ADST :
185
        pth = (tx_dim == 4) ? &iadst_4[0] : &iadst_8[0];
186
187
188
        break;

      default :
189
        pth = (tx_dim == 4) ? &idct_4[0] : &idct_8[0];
190
191
192
193
194
195
196
197
        break;
    }
  }

  // convert to short integer format and load BLOCKD buffer
  op  = output;
  pfa = &bufa[0];

198
199
  for(j = 0; j < tx_dim; j++) {
    for(i = 0; i < tx_dim; i++) {
200
201
202
      op[i] = (pfa[i] > 0 ) ? (short)( pfa[i] / 8 + 0.49) :
                             -(short)( - pfa[i] / 8 + 0.49);
    }
203

204
    op  += shortpitch;
205
    pfa += tx_dim;
206
207
208
  }
}
#endif
Jingning Han's avatar
Jingning Han committed
209

John Koleszar's avatar
John Koleszar committed
210
211
212
void vp8_short_idct4x4llm_c(short *input, short *output, int pitch) {
  int i;
  int a1, b1, c1, d1;
John Koleszar's avatar
John Koleszar committed
213

John Koleszar's avatar
John Koleszar committed
214
215
216
217
  short *ip = input;
  short *op = output;
  int temp1, temp2;
  int shortpitch = pitch >> 1;
John Koleszar's avatar
John Koleszar committed
218

John Koleszar's avatar
John Koleszar committed
219
220
221
  for (i = 0; i < 4; i++) {
    a1 = ip[0] + ip[8];
    b1 = ip[0] - ip[8];
John Koleszar's avatar
John Koleszar committed
222

John Koleszar's avatar
John Koleszar committed
223
224
225
    temp1 = (ip[4] * sinpi8sqrt2 + rounding) >> 16;
    temp2 = ip[12] + ((ip[12] * cospi8sqrt2minus1 + rounding) >> 16);
    c1 = temp1 - temp2;
John Koleszar's avatar
John Koleszar committed
226

John Koleszar's avatar
John Koleszar committed
227
228
229
    temp1 = ip[4] + ((ip[4] * cospi8sqrt2minus1 + rounding) >> 16);
    temp2 = (ip[12] * sinpi8sqrt2 + rounding) >> 16;
    d1 = temp1 + temp2;
John Koleszar's avatar
John Koleszar committed
230

John Koleszar's avatar
John Koleszar committed
231
232
    op[shortpitch * 0] = a1 + d1;
    op[shortpitch * 3] = a1 - d1;
John Koleszar's avatar
John Koleszar committed
233

John Koleszar's avatar
John Koleszar committed
234
235
    op[shortpitch * 1] = b1 + c1;
    op[shortpitch * 2] = b1 - c1;
John Koleszar's avatar
John Koleszar committed
236

John Koleszar's avatar
John Koleszar committed
237
238
239
    ip++;
    op++;
  }
John Koleszar's avatar
John Koleszar committed
240

John Koleszar's avatar
John Koleszar committed
241
242
  ip = output;
  op = output;
John Koleszar's avatar
John Koleszar committed
243

John Koleszar's avatar
John Koleszar committed
244
245
246
  for (i = 0; i < 4; i++) {
    a1 = ip[0] + ip[2];
    b1 = ip[0] - ip[2];
John Koleszar's avatar
John Koleszar committed
247

John Koleszar's avatar
John Koleszar committed
248
249
250
    temp1 = (ip[1] * sinpi8sqrt2 + rounding) >> 16;
    temp2 = ip[3] + ((ip[3] * cospi8sqrt2minus1 + rounding) >> 16);
    c1 = temp1 - temp2;
John Koleszar's avatar
John Koleszar committed
251

John Koleszar's avatar
John Koleszar committed
252
253
254
    temp1 = ip[1] + ((ip[1] * cospi8sqrt2minus1 + rounding) >> 16);
    temp2 = (ip[3] * sinpi8sqrt2 + rounding) >> 16;
    d1 = temp1 + temp2;
John Koleszar's avatar
John Koleszar committed
255

John Koleszar's avatar
John Koleszar committed
256
257
    op[0] = (a1 + d1 + 16) >> 5;
    op[3] = (a1 - d1 + 16) >> 5;
258

John Koleszar's avatar
John Koleszar committed
259
260
    op[1] = (b1 + c1 + 16) >> 5;
    op[2] = (b1 - c1 + 16) >> 5;
John Koleszar's avatar
John Koleszar committed
261

John Koleszar's avatar
John Koleszar committed
262
263
264
    ip += shortpitch;
    op += shortpitch;
  }
John Koleszar's avatar
John Koleszar committed
265
266
}

John Koleszar's avatar
John Koleszar committed
267
268
269
270
271
272
273
274
275
276
277
278
279
void vp8_short_idct4x4llm_1_c(short *input, short *output, int pitch) {
  int i;
  int a1;
  short *op = output;
  int shortpitch = pitch >> 1;
  a1 = ((input[0] + 16) >> 5);
  for (i = 0; i < 4; i++) {
    op[0] = a1;
    op[1] = a1;
    op[2] = a1;
    op[3] = a1;
    op += shortpitch;
  }
John Koleszar's avatar
John Koleszar committed
280
281
}

John Koleszar's avatar
John Koleszar committed
282
283
284
void vp8_dc_only_idct_add_c(short input_dc, unsigned char *pred_ptr, unsigned char *dst_ptr, int pitch, int stride) {
  int a1 = ((input_dc + 16) >> 5);
  int r, c;
285

John Koleszar's avatar
John Koleszar committed
286
287
288
  for (r = 0; r < 4; r++) {
    for (c = 0; c < 4; c++) {
      int a = a1 + pred_ptr[c];
289

John Koleszar's avatar
John Koleszar committed
290
291
      if (a < 0)
        a = 0;
292

John Koleszar's avatar
John Koleszar committed
293
294
      if (a > 255)
        a = 255;
295

John Koleszar's avatar
John Koleszar committed
296
      dst_ptr[c] = (unsigned char) a;
John Koleszar's avatar
John Koleszar committed
297
    }
298

John Koleszar's avatar
John Koleszar committed
299
300
301
    dst_ptr += stride;
    pred_ptr += pitch;
  }
John Koleszar's avatar
John Koleszar committed
302

John Koleszar's avatar
John Koleszar committed
303
}
John Koleszar's avatar
John Koleszar committed
304

John Koleszar's avatar
John Koleszar committed
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
void vp8_short_inv_walsh4x4_c(short *input, short *output) {
  int i;
  int a1, b1, c1, d1;
  short *ip = input;
  short *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]));

    op[0] = (a1 + b1 + 1) >> 1;
    op[1] = (c1 + d1) >> 1;
    op[2] = (a1 - b1) >> 1;
    op[3] = (d1 - c1) >> 1;

    ip += 4;
    op += 4;
  }

  ip = output;
  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 + 1) >> 1;
    op[4] = (c1 + d1) >> 1;
    op[8] = (a1 - b1) >> 1;
    op[12] = (d1 - c1) >> 1;
    ip++;
    op++;
  }
John Koleszar's avatar
John Koleszar committed
340
341
}

John Koleszar's avatar
John Koleszar committed
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
void vp8_short_inv_walsh4x4_1_c(short *in, short *out) {
  int i;
  short tmp[4];
  short *ip = in;
  short *op = tmp;

  op[0] = (ip[0] + 1) >> 1;
  op[1] = op[2] = op[3] = (ip[0] >> 1);

  ip = tmp;
  op = out;
  for (i = 0; i < 4; i++) {
    op[0] = (ip[0] + 1) >> 1;
    op[4] = op[8] = op[12] = (ip[0] >> 1);
    ip++;
    op++;
  }
John Koleszar's avatar
John Koleszar committed
359
}
360

Hui Su's avatar
Hui Su committed
361
#if CONFIG_LOSSLESS
John Koleszar's avatar
John Koleszar committed
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
void vp8_short_inv_walsh4x4_lossless_c(short *input, short *output) {
  int i;
  int a1, b1, c1, d1;
  short *ip = input;
  short *op = output;

  for (i = 0; i < 4; i++) {
    a1 = ((ip[0] + ip[3])) >> Y2_WHT_UPSCALE_FACTOR;
    b1 = ((ip[1] + ip[2])) >> Y2_WHT_UPSCALE_FACTOR;
    c1 = ((ip[1] - ip[2])) >> Y2_WHT_UPSCALE_FACTOR;
    d1 = ((ip[0] - ip[3])) >> Y2_WHT_UPSCALE_FACTOR;

    op[0] = (a1 + b1 + 1) >> 1;
    op[1] = (c1 + d1) >> 1;
    op[2] = (a1 - b1) >> 1;
    op[3] = (d1 - c1) >> 1;

    ip += 4;
    op += 4;
  }

  ip = output;
  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 + 1) >> 1) << Y2_WHT_UPSCALE_FACTOR;
    op[4] = ((c1 + d1) >> 1) << Y2_WHT_UPSCALE_FACTOR;
    op[8] = ((a1 - b1) >> 1) << Y2_WHT_UPSCALE_FACTOR;
    op[12] = ((d1 - c1) >> 1) << Y2_WHT_UPSCALE_FACTOR;

    ip++;
    op++;
  }
Hui Su's avatar
Hui Su committed
400
401
}

John Koleszar's avatar
John Koleszar committed
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
void vp8_short_inv_walsh4x4_1_lossless_c(short *in, short *out) {
  int i;
  short tmp[4];
  short *ip = in;
  short *op = tmp;

  op[0] = ((ip[0] >> Y2_WHT_UPSCALE_FACTOR) + 1) >> 1;
  op[1] = op[2] = op[3] = ((ip[0] >> Y2_WHT_UPSCALE_FACTOR) >> 1);

  ip = tmp;
  op = out;
  for (i = 0; i < 4; i++) {
    op[0] = ((ip[0] + 1) >> 1) << Y2_WHT_UPSCALE_FACTOR;
    op[4] = op[8] = op[12] = ((ip[0] >> 1)) << Y2_WHT_UPSCALE_FACTOR;
    ip++;
    op++;
  }
Hui Su's avatar
Hui Su committed
419
420
}

John Koleszar's avatar
John Koleszar committed
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
void vp8_short_inv_walsh4x4_x8_c(short *input, short *output, int pitch) {
  int i;
  int a1, b1, c1, d1;
  short *ip = input;
  short *op = output;
  int shortpitch = pitch >> 1;

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

    op[0] = (a1 + b1 + 1) >> 1;
    op[1] = (c1 + d1) >> 1;
    op[2] = (a1 - b1) >> 1;
    op[3] = (d1 - c1) >> 1;

    ip += 4;
    op += shortpitch;
  }

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


    op[shortpitch * 0] = (a1 + b1 + 1) >> 1;
    op[shortpitch * 1] = (c1 + d1) >> 1;
    op[shortpitch * 2] = (a1 - b1) >> 1;
    op[shortpitch * 3] = (d1 - c1) >> 1;

    ip++;
    op++;
  }
}
Hui Su's avatar
Hui Su committed
461

John Koleszar's avatar
John Koleszar committed
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
void vp8_short_inv_walsh4x4_1_x8_c(short *in, short *out, int pitch) {
  int i;
  short tmp[4];
  short *ip = in;
  short *op = tmp;
  int shortpitch = pitch >> 1;

  op[0] = ((ip[0] >> WHT_UPSCALE_FACTOR) + 1) >> 1;
  op[1] = op[2] = op[3] = ((ip[0] >> WHT_UPSCALE_FACTOR) >> 1);


  ip = tmp;
  op = out;
  for (i = 0; i < 4; i++) {
    op[shortpitch * 0] = (ip[0] + 1) >> 1;
    op[shortpitch * 1] = op[shortpitch * 2] = op[shortpitch * 3] = ip[0] >> 1;
    ip++;
    op++;
  }
}
Hui Su's avatar
Hui Su committed
482

John Koleszar's avatar
John Koleszar committed
483
484
485
486
void vp8_dc_only_inv_walsh_add_c(short input_dc, unsigned char *pred_ptr, unsigned char *dst_ptr, int pitch, int stride) {
  int r, c;
  short tmp[16];
  vp8_short_inv_walsh4x4_1_x8_c(&input_dc, tmp, 4 << 1);
Hui Su's avatar
Hui Su committed
487

John Koleszar's avatar
John Koleszar committed
488
489
490
491
492
  for (r = 0; r < 4; r++) {
    for (c = 0; c < 4; c++) {
      int a = tmp[r * 4 + c] + pred_ptr[c];
      if (a < 0)
        a = 0;
Hui Su's avatar
Hui Su committed
493

John Koleszar's avatar
John Koleszar committed
494
495
      if (a > 255)
        a = 255;
Hui Su's avatar
Hui Su committed
496

John Koleszar's avatar
John Koleszar committed
497
      dst_ptr[c] = (unsigned char) a;
Hui Su's avatar
Hui Su committed
498
499
    }

John Koleszar's avatar
John Koleszar committed
500
501
502
    dst_ptr += stride;
    pred_ptr += pitch;
  }
Hui Su's avatar
Hui Su committed
503
504
}
#endif
Yaowu Xu's avatar
Yaowu Xu committed
505

Yaowu Xu's avatar
Yaowu Xu committed
506
507
508
void vp8_dc_only_idct_add_8x8_c(short input_dc,
                                unsigned char *pred_ptr,
                                unsigned char *dst_ptr,
John Koleszar's avatar
John Koleszar committed
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
                                int pitch, int stride) {
  int a1 = ((input_dc + 16) >> 5);
  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;
530
    }
John Koleszar's avatar
John Koleszar committed
531
532
533
    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;
  }
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
}

#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) */

John Koleszar's avatar
John Koleszar committed
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
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;
597
598
599
600
601
602
603
604
}

/* 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) */
John Koleszar's avatar
John Koleszar committed
605
606
static void idctcol(int *blk) {
  int x0, x1, x2, x3, x4, x5, x6, x7, x8;
Yaowu Xu's avatar
Yaowu Xu committed
607

John Koleszar's avatar
John Koleszar committed
608
609
  /* shortcut */
  if (!((x1 = (blk[8 * 4] << 8)) | (x2 = blk[8 * 6]) | (x3 = blk[8 * 2]) |
Yaowu Xu's avatar
Yaowu Xu committed
610
        (x4 = blk[8 * 1]) | (x5 = blk[8 * 7]) | (x6 = blk[8 * 5]) |
John Koleszar's avatar
John Koleszar committed
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
        (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;
  }

  x0 = (blk[8 * 0] << 8) + 16384;

  /* 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] = (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;
656
657
658
}

#define TX_DIM 8
John Koleszar's avatar
John Koleszar committed
659
660
661
662
663
664
665
666
667
void vp8_short_idct8x8_c(short *coefs, short *block, int pitch) {
  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] + 1
                                + (coefs[i * TX_DIM + j] < 0)) >> 2;
668
    }
John Koleszar's avatar
John Koleszar committed
669
670
671
672
673
674
675
676
677
678
  }
  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++) {
      block[i * shortpitch + j]  = X[i * TX_DIM + j] >> 1;
679
    }
John Koleszar's avatar
John Koleszar committed
680
  }
681
682
683
}


John Koleszar's avatar
John Koleszar committed
684
685
686
687
688
689
690
691
692
693
694
695
void vp8_short_ihaar2x2_c(short *input, short *output, int pitch) {
  int i;
  short *ip = input; // 0,1, 4, 8
  short *op = output;
  for (i = 0; i < 16; i++) {
    op[i] = 0;
  }

  op[0] = (ip[0] + ip[1] + ip[4] + ip[8] + 1) >> 1;
  op[1] = (ip[0] - ip[1] + ip[4] - ip[8]) >> 1;
  op[4] = (ip[0] + ip[1] - ip[4] - ip[8]) >> 1;
  op[8] = (ip[0] - ip[1] - ip[4] + ip[8]) >> 1;
696
697
}

Daniel Kang's avatar
Daniel Kang committed
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724

#if CONFIG_TX16X16
#if 0
// Keep a really bad float version as reference for now.
void vp8_short_idct16x16_c(short *input, short *output, int pitch) {
  double x;
  const int short_pitch = pitch >> 1;
  int i, j, k, l;
  for (l = 0; l < 16; ++l) {
    for (k = 0; k < 16; ++k) {
      double s = 0;
      for (i = 0; i < 16; ++i) {
        for (j = 0; j < 16; ++j) {
          x=cos(PI*j*(l+0.5)/16.0)*cos(PI*i*(k+0.5)/16.0)*input[i*16+j]/32;
          if (i != 0)
            x *= sqrt(2.0);
          if (j != 0)
            x *= sqrt(2.0);
          s += x;
        }
      }
      output[k*short_pitch+l] = (short)round(s);
    }
  }
}
#endif

725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
static const double C1 = 0.995184726672197;
static const double C2 = 0.98078528040323;
static const double C3 = 0.956940335732209;
static const double C4 = 0.923879532511287;
static const double C5 = 0.881921264348355;
static const double C6 = 0.831469612302545;
static const double C7 = 0.773010453362737;
static const double C8 = 0.707106781186548;
static const double C9 = 0.634393284163646;
static const double C10 = 0.555570233019602;
static const double C11 = 0.471396736825998;
static const double C12 = 0.38268343236509;
static const double C13 = 0.290284677254462;
static const double C14 = 0.195090322016128;
static const double C15 = 0.098017140329561;


Daniel Kang's avatar
Daniel Kang committed
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
static void butterfly_16x16_idct_1d(double input[16], double output[16]) {
  double step[16];
  double intermediate[16];
  double temp1, temp2;


  // step 1 and 2
  step[ 0] = input[0] + input[8];
  step[ 1] = input[0] - input[8];

  temp1 = input[4]*C12;
  temp2 = input[12]*C4;

  temp1 -= temp2;
  temp1 *= C8;

  step[ 2] = 2*(temp1);

  temp1 = input[4]*C4;
  temp2 = input[12]*C12;
  temp1 += temp2;
  temp1 = (temp1);
  temp1 *= C8;
  step[ 3] = 2*(temp1);

  temp1 = input[2]*C8;
  temp1 = 2*(temp1);
  temp2 = input[6] + input[10];

  step[ 4] = temp1 + temp2;
  step[ 5] = temp1 - temp2;

  temp1 = input[14]*C8;
  temp1 = 2*(temp1);
  temp2 = input[6] - input[10];

  step[ 6] = temp2 - temp1;
  step[ 7] = temp2 + temp1;

  // for odd input
  temp1 = input[3]*C12;
  temp2 = input[13]*C4;
  temp1 += temp2;
  temp1 = (temp1);
  temp1 *= C8;
  intermediate[ 8] = 2*(temp1);

  temp1 = input[3]*C4;
  temp2 = input[13]*C12;
  temp2 -= temp1;
  temp2 = (temp2);
  temp2 *= C8;
  intermediate[ 9] = 2*(temp2);

  intermediate[10] = 2*(input[9]*C8);
  intermediate[11] = input[15] - input[1];
  intermediate[12] = input[15] + input[1];
  intermediate[13] = 2*((input[7]*C8));

  temp1 = input[11]*C12;
  temp2 = input[5]*C4;
  temp2 -= temp1;
  temp2 = (temp2);
  temp2 *= C8;
  intermediate[14] = 2*(temp2);

  temp1 = input[11]*C4;
  temp2 = input[5]*C12;
  temp1 += temp2;
  temp1 = (temp1);
  temp1 *= C8;
  intermediate[15] = 2*(temp1);

  step[ 8] = intermediate[ 8] + intermediate[14];
  step[ 9] = intermediate[ 9] + intermediate[15];
  step[10] = intermediate[10] + intermediate[11];
  step[11] = intermediate[10] - intermediate[11];
  step[12] = intermediate[12] + intermediate[13];
  step[13] = intermediate[12] - intermediate[13];
  step[14] = intermediate[ 8] - intermediate[14];
  step[15] = intermediate[ 9] - intermediate[15];

  // step 3
  output[0] = step[ 0] + step[ 3];
  output[1] = step[ 1] + step[ 2];
  output[2] = step[ 1] - step[ 2];
  output[3] = step[ 0] - step[ 3];

  temp1 = step[ 4]*C14;
  temp2 = step[ 7]*C2;
  temp1 -= temp2;
  output[4] =  (temp1);

  temp1 = step[ 4]*C2;
  temp2 = step[ 7]*C14;
  temp1 += temp2;
  output[7] =  (temp1);

  temp1 = step[ 5]*C10;
  temp2 = step[ 6]*C6;
  temp1 -= temp2;
  output[5] =  (temp1);

  temp1 = step[ 5]*C6;
  temp2 = step[ 6]*C10;
  temp1 += temp2;
  output[6] =  (temp1);

  output[8] = step[ 8] + step[11];
  output[9] = step[ 9] + step[10];
  output[10] = step[ 9] - step[10];
  output[11] = step[ 8] - step[11];
  output[12] = step[12] + step[15];
  output[13] = step[13] + step[14];
  output[14] = step[13] - step[14];
  output[15] = step[12] - step[15];

  // output 4
  step[ 0] = output[0] + output[7];
  step[ 1] = output[1] + output[6];
  step[ 2] = output[2] + output[5];
  step[ 3] = output[3] + output[4];
  step[ 4] = output[3] - output[4];
  step[ 5] = output[2] - output[5];
  step[ 6] = output[1] - output[6];
  step[ 7] = output[0] - output[7];

  temp1 = output[8]*C7;
  temp2 = output[15]*C9;
  temp1 -= temp2;
  step[ 8] = (temp1);

  temp1 = output[9]*C11;
  temp2 = output[14]*C5;
  temp1 += temp2;
  step[ 9] = (temp1);

  temp1 = output[10]*C3;
  temp2 = output[13]*C13;
  temp1 -= temp2;
  step[10] = (temp1);

  temp1 = output[11]*C15;
  temp2 = output[12]*C1;
  temp1 += temp2;
  step[11] = (temp1);

  temp1 = output[11]*C1;
  temp2 = output[12]*C15;
  temp2 -= temp1;
  step[12] = (temp2);

  temp1 = output[10]*C13;
  temp2 = output[13]*C3;
  temp1 += temp2;
  step[13] = (temp1);

  temp1 = output[9]*C5;
  temp2 = output[14]*C11;
  temp2 -= temp1;
  step[14] = (temp2);

  temp1 = output[8]*C9;
  temp2 = output[15]*C7;
  temp1 += temp2;
  step[15] = (temp1);

  // step 5
  output[0] = (step[0] + step[15]);
  output[1] = (step[1] + step[14]);
  output[2] = (step[2] + step[13]);
  output[3] = (step[3] + step[12]);
  output[4] = (step[4] + step[11]);
  output[5] = (step[5] + step[10]);
  output[6] = (step[6] + step[ 9]);
  output[7] = (step[7] + step[ 8]);

  output[15] = (step[0] - step[15]);
  output[14] = (step[1] - step[14]);
  output[13] = (step[2] - step[13]);
  output[12] = (step[3] - step[12]);
  output[11] = (step[4] - step[11]);
  output[10] = (step[5] - step[10]);
  output[9] = (step[6] - step[ 9]);
  output[8] = (step[7] - step[ 8]);
}

// Remove once an int version of iDCT is written
#if 0
void reference_16x16_idct_1d(double input[16], double output[16]) {
  const double kPi = 3.141592653589793238462643383279502884;
  const double kSqrt2 = 1.414213562373095048801688724209698;
  for (int k = 0; k < 16; k++) {
    output[k] = 0.0;
    for (int n = 0; n < 16; n++) {
      output[k] += input[n]*cos(kPi*(2*k+1)*n/32.0);
      if (n == 0)
        output[k] = output[k]/kSqrt2;
    }
  }
}
#endif

void vp8_short_idct16x16_c(short *input, short *output, int pitch) {
  double out[16*16], out2[16*16];
  const int short_pitch = pitch >> 1;
  int i, j;
    // First transform rows
  for (i = 0; i < 16; ++i) {
    double temp_in[16], temp_out[16];
    for (j = 0; j < 16; ++j)
      temp_in[j] = input[j + i*short_pitch];
    butterfly_16x16_idct_1d(temp_in, temp_out);
    for (j = 0; j < 16; ++j)
      out[j + i*16] = temp_out[j];
  }
  // Then transform columns
  for (i = 0; i < 16; ++i) {
    double temp_in[16], temp_out[16];
    for (j = 0; j < 16; ++j)
      temp_in[j] = out[j*16 + i];
    butterfly_16x16_idct_1d(temp_in, temp_out);
    for (j = 0; j < 16; ++j)
      out2[j*16 + i] = temp_out[j];
  }
  for (i = 0; i < 16*16; ++i)
    output[i] = round(out2[i]/128);
}
#endif