DXR will be turned off on Tuesday, December 29th. It will redirect to Searchfox.
See the announcement on Discourse.

DXR is a code search and navigation tool aimed at making sense of large projects. It supports full-text and regex searches as well as structural queries.

Mercurial (d38398e5144e)

VCS Links

Line Code
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603
/*
 *  Copyright (c) 2015 The WebM project authors. All Rights Reserved.
 *
 *  Use of this source code is governed by a BSD-style license
 *  that can be found in the LICENSE file in the root of the source
 *  tree. An additional intellectual property rights grant can be found
 *  in the file PATENTS.  All contributing project authors may
 *  be found in the AUTHORS file in the root of the source tree.
 */

#include "vpx_dsp/mips/common_dspr2.h"

#if HAVE_DSPR2
void vpx_h_predictor_8x8_dspr2(uint8_t *dst, ptrdiff_t stride,
                               const uint8_t *above, const uint8_t *left) {
  int32_t tmp1, tmp2, tmp3, tmp4, tmp5, tmp6, tmp7, tmp8;
  (void)above;

  __asm__ __volatile__(
      "lb         %[tmp1],      (%[left])                   \n\t"
      "lb         %[tmp2],      1(%[left])                  \n\t"
      "lb         %[tmp3],      2(%[left])                  \n\t"
      "lb         %[tmp4],      3(%[left])                  \n\t"
      "lb         %[tmp5],      4(%[left])                  \n\t"
      "lb         %[tmp6],      5(%[left])                  \n\t"
      "lb         %[tmp7],      6(%[left])                  \n\t"
      "lb         %[tmp8],      7(%[left])                  \n\t"

      "replv.qb   %[tmp1],      %[tmp1]                     \n\t"
      "replv.qb   %[tmp2],      %[tmp2]                     \n\t"
      "replv.qb   %[tmp3],      %[tmp3]                     \n\t"
      "replv.qb   %[tmp4],      %[tmp4]                     \n\t"
      "replv.qb   %[tmp5],      %[tmp5]                     \n\t"
      "replv.qb   %[tmp6],      %[tmp6]                     \n\t"
      "replv.qb   %[tmp7],      %[tmp7]                     \n\t"
      "replv.qb   %[tmp8],      %[tmp8]                     \n\t"

      "sw         %[tmp1],      (%[dst])                    \n\t"
      "sw         %[tmp1],      4(%[dst])                   \n\t"
      "add        %[dst],       %[dst],         %[stride]   \n\t"
      "sw         %[tmp2],      (%[dst])                    \n\t"
      "sw         %[tmp2],      4(%[dst])                   \n\t"
      "add        %[dst],       %[dst],         %[stride]   \n\t"
      "sw         %[tmp3],      (%[dst])                    \n\t"
      "sw         %[tmp3],      4(%[dst])                   \n\t"
      "add        %[dst],       %[dst],         %[stride]   \n\t"
      "sw         %[tmp4],      (%[dst])                    \n\t"
      "sw         %[tmp4],      4(%[dst])                   \n\t"
      "add        %[dst],       %[dst],         %[stride]   \n\t"
      "sw         %[tmp5],      (%[dst])                    \n\t"
      "sw         %[tmp5],      4(%[dst])                   \n\t"
      "add        %[dst],       %[dst],         %[stride]   \n\t"
      "sw         %[tmp6],      (%[dst])                    \n\t"
      "sw         %[tmp6],      4(%[dst])                   \n\t"
      "add        %[dst],       %[dst],         %[stride]   \n\t"
      "sw         %[tmp7],      (%[dst])                    \n\t"
      "sw         %[tmp7],      4(%[dst])                   \n\t"
      "add        %[dst],       %[dst],         %[stride]   \n\t"
      "sw         %[tmp8],      (%[dst])                    \n\t"
      "sw         %[tmp8],      4(%[dst])                   \n\t"

      : [tmp1] "=&r"(tmp1), [tmp2] "=&r"(tmp2), [tmp3] "=&r"(tmp3),
        [tmp4] "=&r"(tmp4), [tmp5] "=&r"(tmp5), [tmp7] "=&r"(tmp7),
        [tmp6] "=&r"(tmp6), [tmp8] "=&r"(tmp8)
      : [left] "r"(left), [dst] "r"(dst), [stride] "r"(stride));
}

void vpx_dc_predictor_8x8_dspr2(uint8_t *dst, ptrdiff_t stride,
                                const uint8_t *above, const uint8_t *left) {
  int32_t expected_dc;
  int32_t average;
  int32_t tmp, above1, above_l1, above_r1, left1, left_r1, left_l1;
  int32_t above2, above_l2, above_r2, left2, left_r2, left_l2;

  __asm__ __volatile__(
      "lw              %[above1],         (%[above])                      \n\t"
      "lw              %[above2],         4(%[above])                     \n\t"
      "lw              %[left1],          (%[left])                       \n\t"
      "lw              %[left2],          4(%[left])                      \n\t"

      "preceu.ph.qbl   %[above_l1],       %[above1]                       \n\t"
      "preceu.ph.qbr   %[above_r1],       %[above1]                       \n\t"
      "preceu.ph.qbl   %[left_l1],        %[left1]                        \n\t"
      "preceu.ph.qbr   %[left_r1],        %[left1]                        \n\t"

      "preceu.ph.qbl   %[above_l2],       %[above2]                       \n\t"
      "preceu.ph.qbr   %[above_r2],       %[above2]                       \n\t"
      "preceu.ph.qbl   %[left_l2],        %[left2]                        \n\t"
      "preceu.ph.qbr   %[left_r2],        %[left2]                        \n\t"

      "addu.ph         %[average],        %[above_r1],      %[above_l1]   \n\t"
      "addu.ph         %[average],        %[average],       %[left_l1]    \n\t"
      "addu.ph         %[average],        %[average],       %[left_r1]    \n\t"

      "addu.ph         %[average],        %[average],       %[above_l2]   \n\t"
      "addu.ph         %[average],        %[average],       %[above_r2]   \n\t"
      "addu.ph         %[average],        %[average],       %[left_l2]    \n\t"
      "addu.ph         %[average],        %[average],       %[left_r2]    \n\t"

      "addiu           %[average],        %[average],       8             \n\t"

      "srl             %[tmp],            %[average],       16            \n\t"
      "addu.ph         %[average],        %[tmp],           %[average]    \n\t"
      "srl             %[expected_dc],    %[average],       4             \n\t"
      "replv.qb        %[expected_dc],    %[expected_dc]                  \n\t"

      "sw              %[expected_dc],    (%[dst])                        \n\t"
      "sw              %[expected_dc],    4(%[dst])                       \n\t"

      "add             %[dst],             %[dst],          %[stride]     \n\t"
      "sw              %[expected_dc],    (%[dst])                        \n\t"
      "sw              %[expected_dc],    4(%[dst])                       \n\t"

      "add             %[dst],             %[dst],          %[stride]     \n\t"
      "sw              %[expected_dc],    (%[dst])                        \n\t"
      "sw              %[expected_dc],    4(%[dst])                       \n\t"

      "add             %[dst],             %[dst],          %[stride]     \n\t"
      "sw              %[expected_dc],    (%[dst])                        \n\t"
      "sw              %[expected_dc],    4(%[dst])                       \n\t"

      "add             %[dst],             %[dst],          %[stride]     \n\t"
      "sw              %[expected_dc],    (%[dst])                        \n\t"
      "sw              %[expected_dc],    4(%[dst])                       \n\t"

      "add             %[dst],             %[dst],          %[stride]     \n\t"
      "sw              %[expected_dc],    (%[dst])                        \n\t"
      "sw              %[expected_dc],    4(%[dst])                       \n\t"

      "add             %[dst],             %[dst],          %[stride]     \n\t"
      "sw              %[expected_dc],    (%[dst])                        \n\t"
      "sw              %[expected_dc],    4(%[dst])                       \n\t"

      "add             %[dst],             %[dst],          %[stride]     \n\t"
      "sw              %[expected_dc],    (%[dst])                        \n\t"
      "sw              %[expected_dc],    4(%[dst])                       \n\t"

      : [above1] "=&r"(above1), [above_l1] "=&r"(above_l1),
        [above_r1] "=&r"(above_r1), [left1] "=&r"(left1),
        [left_l1] "=&r"(left_l1), [left_r1] "=&r"(left_r1),
        [above2] "=&r"(above2), [above_l2] "=&r"(above_l2),
        [above_r2] "=&r"(above_r2), [left2] "=&r"(left2),
        [left_l2] "=&r"(left_l2), [left_r2] "=&r"(left_r2),
        [average] "=&r"(average), [tmp] "=&r"(tmp),
        [expected_dc] "=&r"(expected_dc)
      : [above] "r"(above), [left] "r"(left), [dst] "r"(dst),
        [stride] "r"(stride));
}

void vpx_tm_predictor_8x8_dspr2(uint8_t *dst, ptrdiff_t stride,
                                const uint8_t *above, const uint8_t *left) {
  int32_t abovel, abover;
  int32_t abovel_1, abover_1;
  int32_t left0;
  int32_t res0, res1, res2, res3;
  int32_t reshw;
  int32_t top_left;
  uint8_t *cm = vpx_ff_cropTbl;

  __asm__ __volatile__(
      "ulw             %[reshw],       (%[above])                         \n\t"
      "ulw             %[top_left],    4(%[above])                        \n\t"

      "lbu             %[left0],       (%[left])                          \n\t"

      "preceu.ph.qbl   %[abovel],      %[reshw]                           \n\t"
      "preceu.ph.qbr   %[abover],      %[reshw]                           \n\t"
      "preceu.ph.qbl   %[abovel_1],    %[top_left]                        \n\t"
      "preceu.ph.qbr   %[abover_1],    %[top_left]                        \n\t"

      "lbu             %[top_left],    -1(%[above])                       \n\t"
      "replv.ph        %[left0],       %[left0]                           \n\t"

      "replv.ph        %[top_left],    %[top_left]                        \n\t"

      "addu.ph         %[reshw],       %[abovel],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        (%[dst])                           \n\t"
      "sb              %[res1],        1(%[dst])                          \n\t"
      "sb              %[res2],        2(%[dst])                          \n\t"
      "sb              %[res3],        3(%[dst])                          \n\t"

      "addu.ph         %[reshw],       %[abovel_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbu             %[left0],       1(%[left])                         \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        4(%[dst])                          \n\t"
      "sb              %[res1],        5(%[dst])                          \n\t"
      "sb              %[res2],        6(%[dst])                          \n\t"
      "sb              %[res3],        7(%[dst])                          \n\t"

      "replv.ph        %[left0],       %[left0]                           \n\t"
      "add             %[dst],          %[dst],             %[stride]     \n\t"

      "addu.ph         %[reshw],       %[abovel],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        (%[dst])                           \n\t"
      "sb              %[res1],        1(%[dst])                          \n\t"
      "sb              %[res2],        2(%[dst])                          \n\t"
      "sb              %[res3],        3(%[dst])                          \n\t"

      "addu.ph         %[reshw],       %[abovel_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbu             %[left0],       2(%[left])                         \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        4(%[dst])                          \n\t"
      "sb              %[res1],        5(%[dst])                          \n\t"
      "sb              %[res2],        6(%[dst])                          \n\t"
      "sb              %[res3],        7(%[dst])                          \n\t"

      "replv.ph        %[left0],       %[left0]                           \n\t"
      "add             %[dst],          %[dst],             %[stride]     \n\t"

      "addu.ph         %[reshw],       %[abovel],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        (%[dst])                           \n\t"
      "sb              %[res1],        1(%[dst])                          \n\t"
      "sb              %[res2],        2(%[dst])                          \n\t"
      "sb              %[res3],        3(%[dst])                          \n\t"

      "addu.ph         %[reshw],       %[abovel_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbu             %[left0],       3(%[left])                         \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        4(%[dst])                          \n\t"
      "sb              %[res1],        5(%[dst])                          \n\t"
      "sb              %[res2],        6(%[dst])                          \n\t"
      "sb              %[res3],        7(%[dst])                          \n\t"

      "replv.ph        %[left0],       %[left0]                           \n\t"
      "add             %[dst],          %[dst],             %[stride]     \n\t"

      "addu.ph         %[reshw],       %[abovel],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        (%[dst])                           \n\t"
      "sb              %[res1],        1(%[dst])                          \n\t"
      "sb              %[res2],        2(%[dst])                          \n\t"
      "sb              %[res3],        3(%[dst])                          \n\t"

      "addu.ph         %[reshw],       %[abovel_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbu             %[left0],       4(%[left])                         \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        4(%[dst])                          \n\t"
      "sb              %[res1],        5(%[dst])                          \n\t"
      "sb              %[res2],        6(%[dst])                          \n\t"
      "sb              %[res3],        7(%[dst])                          \n\t"

      "replv.ph        %[left0],       %[left0]                           \n\t"
      "add             %[dst],          %[dst],             %[stride]     \n\t"

      "addu.ph         %[reshw],       %[abovel],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        (%[dst])                           \n\t"
      "sb              %[res1],        1(%[dst])                          \n\t"
      "sb              %[res2],        2(%[dst])                          \n\t"
      "sb              %[res3],        3(%[dst])                          \n\t"

      "addu.ph         %[reshw],       %[abovel_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbu             %[left0],       5(%[left])                         \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        4(%[dst])                          \n\t"
      "sb              %[res1],        5(%[dst])                          \n\t"
      "sb              %[res2],        6(%[dst])                          \n\t"
      "sb              %[res3],        7(%[dst])                          \n\t"

      "replv.ph        %[left0],       %[left0]                           \n\t"
      "add             %[dst],          %[dst],             %[stride]     \n\t"

      "addu.ph         %[reshw],       %[abovel],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        (%[dst])                           \n\t"
      "sb              %[res1],        1(%[dst])                          \n\t"
      "sb              %[res2],        2(%[dst])                          \n\t"
      "sb              %[res3],        3(%[dst])                          \n\t"

      "addu.ph         %[reshw],       %[abovel_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbu             %[left0],       6(%[left])                         \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        4(%[dst])                          \n\t"
      "sb              %[res1],        5(%[dst])                          \n\t"
      "sb              %[res2],        6(%[dst])                          \n\t"
      "sb              %[res3],        7(%[dst])                          \n\t"

      "replv.ph        %[left0],       %[left0]                           \n\t"
      "add             %[dst],          %[dst],             %[stride]     \n\t"

      "addu.ph         %[reshw],       %[abovel],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        (%[dst])                           \n\t"
      "sb              %[res1],        1(%[dst])                          \n\t"
      "sb              %[res2],        2(%[dst])                          \n\t"
      "sb              %[res3],        3(%[dst])                          \n\t"

      "addu.ph         %[reshw],       %[abovel_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbu             %[left0],       7(%[left])                         \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        4(%[dst])                          \n\t"
      "sb              %[res1],        5(%[dst])                          \n\t"
      "sb              %[res2],        6(%[dst])                          \n\t"
      "sb              %[res3],        7(%[dst])                          \n\t"

      "replv.ph        %[left0],       %[left0]                           \n\t"
      "add             %[dst],          %[dst],             %[stride]     \n\t"

      "addu.ph         %[reshw],       %[abovel],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover],           %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        (%[dst])                           \n\t"
      "sb              %[res1],        1(%[dst])                          \n\t"
      "sb              %[res2],        2(%[dst])                          \n\t"
      "sb              %[res3],        3(%[dst])                          \n\t"

      "addu.ph         %[reshw],       %[abovel_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res2],        %[reshw],            16            \n\t"
      "sra             %[res2],        %[res2],             16            \n\t"
      "sra             %[res3],        %[reshw],            16            \n\t"

      "addu.ph         %[reshw],       %[abover_1],         %[left0]      \n\t"
      "subu.ph         %[reshw],       %[reshw],            %[top_left]   \n\t"

      "sll             %[res0],        %[reshw],            16            \n\t"
      "sra             %[res0],        %[res0],             16            \n\t"
      "sra             %[res1],        %[reshw],            16            \n\t"

      "lbux            %[res0],        %[res0](%[cm])                     \n\t"
      "lbux            %[res1],        %[res1](%[cm])                     \n\t"
      "lbux            %[res2],        %[res2](%[cm])                     \n\t"
      "lbux            %[res3],        %[res3](%[cm])                     \n\t"

      "sb              %[res0],        4(%[dst])                          \n\t"
      "sb              %[res1],        5(%[dst])                          \n\t"
      "sb              %[res2],        6(%[dst])                          \n\t"
      "sb              %[res3],        7(%[dst])                          \n\t"

      : [abovel] "=&r"(abovel), [abover] "=&r"(abover),
        [abovel_1] "=&r"(abovel_1), [abover_1] "=&r"(abover_1),
        [left0] "=&r"(left0), [res2] "=&r"(res2), [res3] "=&r"(res3),
        [res0] "=&r"(res0), [res1] "=&r"(res1), [reshw] "=&r"(reshw),
        [top_left] "=&r"(top_left)
      : [above] "r"(above), [left] "r"(left), [dst] "r"(dst),
        [stride] "r"(stride), [cm] "r"(cm));
}
#endif  // #if HAVE_DSPR2