dct.c 22.7 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
 */


#include <math.h>
13
#include "vpx_ports/config.h"
Hui Su's avatar
Hui Su committed
14
#include "vp8/common/idct.h"
15

Jingning Han's avatar
Jingning Han committed
16 17 18 19
#if CONFIG_HYBRIDTRANSFORM

#include "vp8/common/blockd.h"

20 21
// TODO: these transforms can be converted into integer forms to reduce
//       the complexity
Jingning Han's avatar
Jingning Han committed
22 23 24 25 26 27 28 29 30 31 32 33 34 35 36
float dct_4[16] = {
  0.500000000000000,  0.500000000000000,  0.500000000000000,  0.500000000000000,
  0.653281482438188,  0.270598050073099, -0.270598050073099, -0.653281482438188,
  0.500000000000000, -0.500000000000000, -0.500000000000000,  0.500000000000000,
  0.270598050073099, -0.653281482438188,  0.653281482438188, -0.270598050073099
};

float adst_4[16] = {
  0.228013428883779,  0.428525073124360,  0.577350269189626,  0.656538502008139,
  0.577350269189626,  0.577350269189626,  0.000000000000000, -0.577350269189626,
  0.656538502008139, -0.228013428883779, -0.577350269189626,  0.428525073124359,
  0.428525073124360, -0.656538502008139,  0.577350269189626, -0.228013428883779
};
#endif

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
#if CONFIG_HYBRIDTRANSFORM8X8
float dct_8[64] = {
  0.353553390593274,   0.353553390593274,   0.353553390593274,   0.353553390593274,
  0.353553390593274,   0.353553390593274,   0.353553390593274,   0.353553390593274,
  0.490392640201615,   0.415734806151273,   0.277785116509801,   0.097545161008064,
 -0.097545161008064,  -0.277785116509801,  -0.415734806151273,  -0.490392640201615,
  0.461939766255643,   0.191341716182545,  -0.191341716182545,  -0.461939766255643,
 -0.461939766255643,  -0.191341716182545,   0.191341716182545,   0.461939766255643,
  0.415734806151273,  -0.097545161008064,  -0.490392640201615,  -0.277785116509801,
  0.277785116509801,   0.490392640201615,   0.097545161008064,  -0.415734806151273,
  0.353553390593274,  -0.353553390593274,  -0.353553390593274,   0.353553390593274,
  0.353553390593274,  -0.353553390593274,  -0.353553390593274,   0.353553390593274,
  0.277785116509801,  -0.490392640201615,   0.097545161008064,   0.415734806151273,
 -0.415734806151273,  -0.097545161008064,   0.490392640201615,  -0.277785116509801,
  0.191341716182545,  -0.461939766255643,   0.461939766255643,  -0.191341716182545,
 -0.191341716182545,   0.461939766255643,  -0.461939766255643,   0.191341716182545,
  0.097545161008064,  -0.277785116509801,   0.415734806151273,  -0.490392640201615,
  0.490392640201615,  -0.415734806151273,   0.277785116509801,  -0.097545161008064
};

float adst_8[64] = {
  0.089131608307533,   0.175227946595735,   0.255357107325376,   0.326790388032145,
  0.387095214016349,   0.434217976756762,   0.466553967085785,   0.483002021635509,
  0.255357107325376,   0.434217976756762,   0.483002021635509,   0.387095214016349,
  0.175227946595735,  -0.089131608307533,  -0.326790388032145,  -0.466553967085785,
  0.387095214016349,   0.466553967085785,   0.175227946595735,  -0.255357107325376,
 -0.483002021635509,  -0.326790388032145,   0.089131608307533,   0.434217976756762,
  0.466553967085785,   0.255357107325376,  -0.326790388032145,  -0.434217976756762,
  0.089131608307533,   0.483002021635509,   0.175227946595735,  -0.387095214016348,
  0.483002021635509,  -0.089131608307533,  -0.466553967085785,   0.175227946595735,
  0.434217976756762,  -0.255357107325376,  -0.387095214016348,   0.326790388032145,
  0.434217976756762,  -0.387095214016348,  -0.089131608307533,   0.466553967085786,
 -0.326790388032145,  -0.175227946595735,   0.483002021635509,  -0.255357107325375,
  0.326790388032145,  -0.483002021635509,   0.387095214016349,  -0.089131608307534,
 -0.255357107325377,   0.466553967085785,  -0.434217976756762,   0.175227946595736,
  0.175227946595735,  -0.326790388032145,   0.434217976756762,  -0.483002021635509,
  0.466553967085785,  -0.387095214016348,   0.255357107325376,  -0.089131608307532
};
#endif
Jingning Han's avatar
Jingning Han committed
76

Yaowu Xu's avatar
Yaowu Xu committed
77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92
static const int xC1S7 = 16069;
static const int xC2S6 = 15137;
static const int xC3S5 = 13623;
static const int xC4S4 = 11585;
static const int xC5S3 =  9102;
static const int xC6S2 =  6270;
static const int xC7S1 =  3196;

#define SHIFT_BITS 14
#define DOROUND(X) X += (1<<(SHIFT_BITS-1));

#define FINAL_SHIFT 3
#define FINAL_ROUNDING (1<<(FINAL_SHIFT -1))
#define IN_SHIFT (FINAL_SHIFT+1)


John Koleszar's avatar
John Koleszar committed
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
void vp8_short_fdct8x8_c(short *InputData, short *OutputData, int pitch) {
  int loop;
  int short_pitch = pitch >> 1;
  int is07, is12, is34, is56;
  int is0734, is1256;
  int id07, id12, id34, id56;
  int irot_input_x, irot_input_y;
  int icommon_product1;      // Re-used product  (c4s4 * (s12 - s56))
  int icommon_product2;      // Re-used product  (c4s4 * (d12 + d56))
  int temp1, temp2;          // intermediate variable for computation

  int  InterData[64];
  int  *ip = InterData;
  short *op = OutputData;

  for (loop = 0; loop < 8; loop++) {
    // Pre calculate some common sums and differences.
    is07 = (InputData[0] + InputData[7]) << IN_SHIFT;
    is12 = (InputData[1] + InputData[2]) << IN_SHIFT;
    is34 = (InputData[3] + InputData[4]) << IN_SHIFT;
    is56 = (InputData[5] + InputData[6]) << IN_SHIFT;
    id07 = (InputData[0] - InputData[7]) << IN_SHIFT;
    id12 = (InputData[1] - InputData[2]) << IN_SHIFT;
    id34 = (InputData[3] - InputData[4]) << IN_SHIFT;
    id56 = (InputData[5] - InputData[6]) << IN_SHIFT;

    is0734 = is07 + is34;
    is1256 = is12 + is56;

    // Pre-Calculate some common product terms.
    icommon_product1 = xC4S4 * (is12 - is56);
    DOROUND(icommon_product1)
    icommon_product1 >>= SHIFT_BITS;

    icommon_product2 = xC4S4 * (id12 + id56);
    DOROUND(icommon_product2)
    icommon_product2 >>= SHIFT_BITS;


    ip[0] = (xC4S4 * (is0734 + is1256));
    DOROUND(ip[0]);
    ip[0] >>= SHIFT_BITS;

    ip[4] = (xC4S4 * (is0734 - is1256));
    DOROUND(ip[4]);
    ip[4] >>= SHIFT_BITS;

    // Define inputs to rotation for outputs 2 and 6
    irot_input_x = id12 - id56;
    irot_input_y = is07 - is34;

    // Apply rotation for outputs 2 and 6.
    temp1 = xC6S2 * irot_input_x;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC2S6 * irot_input_y;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    ip[2] = temp1 + temp2;

    temp1 = xC6S2 * irot_input_y;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC2S6 * irot_input_x;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    ip[6] = temp1 - temp2;

    // Define inputs to rotation for outputs 1 and 7
    irot_input_x = icommon_product1 + id07;
    irot_input_y = -(id34 + icommon_product2);

    // Apply rotation for outputs 1 and 7.
    temp1 = xC1S7 * irot_input_x;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC7S1 * irot_input_y;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    ip[1] = temp1 - temp2;

    temp1 = xC7S1 * irot_input_x;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC1S7 * irot_input_y;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    ip[7] = temp1 + temp2;

    // Define inputs to rotation for outputs 3 and 5
    irot_input_x = id07 - icommon_product1;
    irot_input_y = id34 - icommon_product2;

    // Apply rotation for outputs 3 and 5.
    temp1 = xC3S5 * irot_input_x;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC5S3 * irot_input_y;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    ip[3] = temp1 - temp2;


    temp1 = xC5S3 * irot_input_x;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC3S5 * irot_input_y;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    ip[5] = temp1 + temp2;

    // Increment data pointer for next row
    InputData += short_pitch;
    ip += 8;
  }
Yaowu Xu's avatar
Yaowu Xu committed
208

John Koleszar's avatar
John Koleszar committed
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
  // Performed DCT on rows, now transform the columns
  ip = InterData;
  for (loop = 0; loop < 8; loop++) {
    // Pre calculate some common sums and differences.
    is07 = ip[0 * 8] + ip[7 * 8];
    is12 = ip[1 * 8] + ip[2 * 8];
    is34 = ip[3 * 8] + ip[4 * 8];
    is56 = ip[5 * 8] + ip[6 * 8];

    id07 = ip[0 * 8] - ip[7 * 8];
    id12 = ip[1 * 8] - ip[2 * 8];
    id34 = ip[3 * 8] - ip[4 * 8];
    id56 = ip[5 * 8] - ip[6 * 8];

    is0734 = is07 + is34;
    is1256 = is12 + is56;

    // Pre-Calculate some common product terms
    icommon_product1 = xC4S4 * (is12 - is56);
    icommon_product2 = xC4S4 * (id12 + id56);
    DOROUND(icommon_product1)
    DOROUND(icommon_product2)
    icommon_product1 >>= SHIFT_BITS;
    icommon_product2 >>= SHIFT_BITS;


    temp1 = xC4S4 * (is0734 + is1256);
    temp2 = xC4S4 * (is0734 - is1256);
    DOROUND(temp1);
    DOROUND(temp2);
    temp1 >>= SHIFT_BITS;

    temp2 >>= SHIFT_BITS;
    op[0 * 8] = (temp1 + FINAL_ROUNDING) >> FINAL_SHIFT;
    op[4 * 8] = (temp2 + FINAL_ROUNDING) >> FINAL_SHIFT;

    // Define inputs to rotation for outputs 2 and 6
    irot_input_x = id12 - id56;
    irot_input_y = is07 - is34;

    // Apply rotation for outputs 2 and 6.
    temp1 = xC6S2 * irot_input_x;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC2S6 * irot_input_y;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    op[2 * 8] = (temp1 + temp2 + FINAL_ROUNDING) >> FINAL_SHIFT;

    temp1 = xC6S2 * irot_input_y;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC2S6 * irot_input_x;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    op[6 * 8] = (temp1 - temp2 + FINAL_ROUNDING) >> FINAL_SHIFT;

    // Define inputs to rotation for outputs 1 and 7
    irot_input_x = icommon_product1 + id07;
    irot_input_y = -(id34 + icommon_product2);

    // Apply rotation for outputs 1 and 7.
    temp1 = xC1S7 * irot_input_x;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC7S1 * irot_input_y;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    op[1 * 8] = (temp1 - temp2 + FINAL_ROUNDING) >> FINAL_SHIFT;

    temp1 = xC7S1 * irot_input_x;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC1S7 * irot_input_y;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    op[7 * 8] = (temp1 + temp2 + FINAL_ROUNDING) >> FINAL_SHIFT;

    // Define inputs to rotation for outputs 3 and 5
    irot_input_x = id07 - icommon_product1;
    irot_input_y = id34 - icommon_product2;

    // Apply rotation for outputs 3 and 5.
    temp1 = xC3S5 * irot_input_x;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC5S3 * irot_input_y;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    op[3 * 8] = (temp1 - temp2 + FINAL_ROUNDING) >> FINAL_SHIFT;


    temp1 = xC5S3 * irot_input_x;
    DOROUND(temp1);
    temp1 >>= SHIFT_BITS;
    temp2 = xC3S5 * irot_input_y;
    DOROUND(temp2);
    temp2 >>= SHIFT_BITS;
    op[5 * 8] = (temp1 + temp2 + FINAL_ROUNDING) >> FINAL_SHIFT;

    // Increment data pointer for next column.
    ip++;
    op++;
  }
Yaowu Xu's avatar
Yaowu Xu committed
313
}
314

John Koleszar's avatar
John Koleszar committed
315 316 317 318 319 320 321 322 323 324 325 326 327 328
void vp8_short_fhaar2x2_c(short *input, short *output, int pitch) { // pitch = 8
  /* [1 1; 1 -1] orthogonal transform */
  /* use position: 0,1, 4, 8 */
  int i;
  short *ip1 = input;
  short *op1 = output;
  for (i = 0; i < 16; i++) {
    op1[i] = 0;
  }

  op1[0] = (ip1[0] + ip1[1] + ip1[4] + ip1[8] + 1) >> 1;
  op1[1] = (ip1[0] - ip1[1] + ip1[4] - ip1[8]) >> 1;
  op1[4] = (ip1[0] + ip1[1] - ip1[4] - ip1[8]) >> 1;
  op1[8] = (ip1[0] - ip1[1] - ip1[4] + ip1[8]) >> 1;
329 330

}
Yaowu Xu's avatar
Yaowu Xu committed
331

332 333 334
#if CONFIG_HYBRIDTRANSFORM8X8 || CONFIG_HYBRIDTRANSFORM
void vp8_fht_c(short *input, short *output, int pitch,
               TX_TYPE tx_type, int tx_dim) {
335 336 337 338 339 340 341 342 343 344 345 346 347 348
  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
  short *ip = input;
  short *op = output;

  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
349 350
  for(j = 0; j < tx_dim; j++) {
    for(i = 0; i < tx_dim; i++) {
351 352
      pfa[i] = (float)ip[i];
    }
353
    pfa += tx_dim;
354 355 356 357 358 359 360 361 362 363
    ip  += pitch / 2;
  }

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

  switch(tx_type) {
    case ADST_ADST :
    case ADST_DCT  :
364
      ptv = (tx_dim == 4) ? &adst_4[0] : &adst_8[0];
365 366 367
      break;

    default :
368
      ptv = (tx_dim == 4) ? &dct_4[0] : &dct_8[0];
369 370 371
      break;
  }

372 373
  for(j = 0; j < tx_dim; j++) {
    for(i = 0; i < tx_dim; i++) {
374
      pfb[i] = 0;
375 376
      for(k = 0; k < tx_dim; k++) {
        pfb[i] += ptv[k] * pfa[(k * tx_dim)];
377 378 379
      }
      pfa += 1;
    }
380 381
    pfb += tx_dim;
    ptv += tx_dim;
382 383 384 385 386 387 388 389 390 391
    pfa = &bufa[0];
  }

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

  switch(tx_type) {
    case ADST_ADST :
    case  DCT_ADST :
392
      pth = (tx_dim == 4) ? &adst_4[0] : &adst_8[0];
393 394 395
      break;

    default :
396
      pth = (tx_dim == 4) ? &dct_4[0] : &dct_8[0];
397 398 399
      break;
  }

400 401
  for(j = 0; j < tx_dim; j++) {
    for(i = 0; i < tx_dim; i++) {
402
      pfa[i] = 0;
403
      for(k = 0; k < tx_dim; k++) {
404 405
        pfa[i] += pfb[k] * pth[k];
      }
406
      pth += tx_dim;
407 408
     }

409 410
    pfa += tx_dim;
    pfb += tx_dim;
411 412 413 414

    switch(tx_type) {
      case ADST_ADST :
      case  DCT_ADST :
415
        pth = (tx_dim == 4) ? &adst_4[0] : &adst_8[0];
416 417 418
        break;

      default :
419
        pth = (tx_dim == 4) ? &dct_4[0] : &dct_8[0];
420 421 422 423 424 425 426 427
        break;
    }
  }

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

428 429
  for(j = 0; j < tx_dim; j++) {
    for(i = 0; i < tx_dim; i++) {
430 431 432
      op[i] = (pfa[i] > 0 ) ? (short)( 8 * pfa[i] + 0.49) :
                                   -(short)(- 8 * pfa[i] + 0.49);
    }
433 434
    op  += tx_dim;
    pfa += tx_dim;
435 436 437 438
  }
}
#endif

John Koleszar's avatar
John Koleszar committed
439 440 441 442 443
void vp8_short_fdct4x4_c(short *input, short *output, int pitch) {
  int i;
  int a1, b1, c1, d1;
  short *ip = input;
  short *op = output;
John Koleszar's avatar
John Koleszar committed
444

John Koleszar's avatar
John Koleszar committed
445 446 447 448 449
  for (i = 0; i < 4; i++) {
    a1 = ((ip[0] + ip[3]) << 5);
    b1 = ((ip[1] + ip[2]) << 5);
    c1 = ((ip[1] - ip[2]) << 5);
    d1 = ((ip[0] - ip[3]) << 5);
Paul Wilkins's avatar
Paul Wilkins committed
450

John Koleszar's avatar
John Koleszar committed
451 452
    op[0] = a1 + b1;
    op[2] = a1 - b1;
John Koleszar's avatar
John Koleszar committed
453

John Koleszar's avatar
John Koleszar committed
454 455
    op[1] = (c1 * 2217 + d1 * 5352 +  14500) >> 12;
    op[3] = (d1 * 2217 - c1 * 5352 +   7500) >> 12;
John Koleszar's avatar
John Koleszar committed
456

John Koleszar's avatar
John Koleszar committed
457 458
    ip += pitch / 2;
    op += 4;
John Koleszar's avatar
John Koleszar committed
459

John Koleszar's avatar
John Koleszar committed
460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477
  }
  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 + 7) >> 4;
    op[8]  = (a1 - b1 + 7) >> 4;

    op[4]  = ((c1 * 2217 + d1 * 5352 +  12000) >> 16) + (d1 != 0);
    op[12] = (d1 * 2217 - c1 * 5352 +  51000) >> 16;

    ip++;
    op++;
  }
John Koleszar's avatar
John Koleszar committed
478 479
}

Jingning Han's avatar
Jingning Han committed
480 481 482 483
void vp8_short_fdct8x4_c(short *input, short *output, int pitch)
{
    vp8_short_fdct4x4_c(input,   output,    pitch);
    vp8_short_fdct4x4_c(input + 4, output + 16, pitch);
Yaowu Xu's avatar
Yaowu Xu committed
484
}
John Koleszar's avatar
John Koleszar committed
485

John Koleszar's avatar
John Koleszar committed
486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523
void vp8_short_walsh4x4_c(short *input, short *output, int pitch) {
  int i;
  int a1, b1, c1, d1;
  short *ip = input;
  short *op = output;
  int pitch_short = pitch >> 1;

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

    op[0] = (a1 + b1 + 1) >> 1;
    op[4] = (c1 + d1) >> 1;
    op[8] = (a1 - b1) >> 1;
    op[12] = (d1 - c1) >> 1;

    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];

    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;
  }
Hui Su's avatar
Hui Su committed
524 525 526
}

#if CONFIG_LOSSLESS
John Koleszar's avatar
John Koleszar committed
527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564
void vp8_short_walsh4x4_lossless_c(short *input, short *output, int pitch) {
  int i;
  int a1, b1, c1, d1;
  short *ip = input;
  short *op = output;
  int pitch_short = pitch >> 1;

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

    op[0] = (a1 + b1 + 1) >> 1;
    op[4] = (c1 + d1) >> 1;
    op[8] = (a1 - b1) >> 1;
    op[12] = (d1 - c1) >> 1;

    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];

    op[0] = ((a1 + b1 + 1) >> 1) << Y2_WHT_UPSCALE_FACTOR;
    op[1] = ((c1 + d1) >> 1) << Y2_WHT_UPSCALE_FACTOR;
    op[2] = ((a1 - b1) >> 1) << Y2_WHT_UPSCALE_FACTOR;
    op[3] = ((d1 - c1) >> 1) << Y2_WHT_UPSCALE_FACTOR;

    ip += 4;
    op += 4;
  }
Hui Su's avatar
Hui Su committed
565 566
}

John Koleszar's avatar
John Koleszar committed
567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604
void vp8_short_walsh4x4_x8_c(short *input, short *output, int pitch) {
  int i;
  int a1, b1, c1, d1;
  short *ip = input;
  short *op = output;
  int pitch_short = pitch >> 1;

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

    op[0] = (a1 + b1 + 1) >> 1;
    op[4] = (c1 + d1) >> 1;
    op[8] = (a1 - b1) >> 1;
    op[12] = (d1 - c1) >> 1;

    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];

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

    ip += 4;
    op += 4;
  }
Hui Su's avatar
Hui Su committed
605 606
}

John Koleszar's avatar
John Koleszar committed
607
void vp8_short_walsh8x4_x8_c(short *input, short *output, int pitch) {
Hui Su's avatar
Hui Su committed
608 609 610 611
  vp8_short_walsh4x4_x8_c(input,   output,    pitch);
  vp8_short_walsh4x4_x8_c(input + 4, output + 16, pitch);
}
#endif
Daniel Kang's avatar
Daniel Kang committed
612 613

#if CONFIG_TX16X16
614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629
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
630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812
static void dct16x16_1d(double input[16], double output[16]) {
  double step[16];
  double intermediate[16];
  double temp1, temp2;

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

  step[ 8] = output[ 8] + output[11];
  step[ 9] = output[ 9] + output[10];
  step[10] = output[ 9] - output[10];
  step[11] = output[ 8] - output[11];

  step[12] = output[12] + output[15];
  step[13] = output[13] + output[14];
  step[14] = output[13] - output[14];
  step[15] = output[12] - output[15];

  // step 4
  output[ 0] = (step[ 0] + step[ 1]);
  output[ 8] = (step[ 0] - step[ 1]);

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

  temp1 = step[2]*C4;
  temp2 = step[3]*C12;
  temp1 = temp2 - temp1;
  output[12] = 2*(temp1*C8);

  output[ 2] = 2*((step[4] + step[ 5])*C8);
  output[14] = 2*((step[7] - step[ 6])*C8);

  temp1 = step[4] - step[5];
  temp2 = step[6] + step[7];
  output[ 6] = (temp1 + temp2);
  output[10] = (temp1 - temp2);

  intermediate[8] = step[8] + step[14];
  intermediate[9] = step[9] + step[15];

  temp1 = intermediate[8]*C12;
  temp2 = intermediate[9]*C4;
  temp1 = temp1 - temp2;
  output[3] = 2*(temp1*C8);

  temp1 = intermediate[8]*C4;
  temp2 = intermediate[9]*C12;
  temp1 = temp2 + temp1;
  output[13] = 2*(temp1*C8);

  output[ 9] = 2*((step[10] + step[11])*C8);

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

  output[15] = (intermediate[11] + intermediate[12]);
  output[ 1] = -(intermediate[11] - intermediate[12]);

  output[ 7] = 2*(intermediate[13]*C8);

  temp1 = intermediate[14]*C12;
  temp2 = intermediate[15]*C4;
  temp1 = temp1 - temp2;
  output[11] = -2*(temp1*C8);

  temp1 = intermediate[14]*C4;
  temp2 = intermediate[15]*C12;
  temp1 = temp2 + temp1;
  output[ 5] = 2*(temp1*C8);
}

void vp8_short_fdct16x16_c(short *input, short *out, int pitch) {
    int shortpitch = pitch >> 1;
    int i, j;
    double output[256];
    // First transform columns
    for (i = 0; i < 16; i++) {
        double temp_in[16], temp_out[16];
        for (j = 0; j < 16; j++)
            temp_in[j] = input[j*shortpitch + i];
        dct16x16_1d(temp_in, temp_out);
        for (j = 0; j < 16; j++)
            output[j*16 + i] = temp_out[j];
    }
    // Then transform rows
    for (i = 0; i < 16; ++i) {
        double temp_in[16], temp_out[16];
        for (j = 0; j < 16; ++j)
            temp_in[j] = output[j + i*16];
        dct16x16_1d(temp_in, temp_out);
        for (j = 0; j < 16; ++j)
            output[j + i*16] = temp_out[j];
    }
    // Scale by some magic number
    for (i = 0; i < 256; i++)
        out[i] = (short)round(output[i]/2);
}
#endif