1/* 2 * VP9 compatible video decoder 3 * 4 * Copyright (C) 2013 Ronald S. Bultje <rsbultje gmail com> 5 * Copyright (C) 2013 Clément Bœsch <u pkh me> 6 * 7 * This file is part of FFmpeg. 8 * 9 * FFmpeg is free software; you can redistribute it and/or 10 * modify it under the terms of the GNU Lesser General Public 11 * License as published by the Free Software Foundation; either 12 * version 2.1 of the License, or (at your option) any later version. 13 * 14 * FFmpeg is distributed in the hope that it will be useful, 15 * but WITHOUT ANY WARRANTY; without even the implied warranty of 16 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU 17 * Lesser General Public License for more details. 18 * 19 * You should have received a copy of the GNU Lesser General Public 20 * License along with FFmpeg; if not, write to the Free Software 21 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA 22 */ 23 24#include "libavutil/common.h" 25#include "bit_depth_template.c" 26#include "vp9dsp.h" 27 28#if BIT_DEPTH != 12 29 30// FIXME see whether we can merge parts of this (perhaps at least 4x4 and 8x8) 31// back with h264pred.[ch] 32 33static void vert_4x4_c(uint8_t *_dst, ptrdiff_t stride, 34 const uint8_t *left, const uint8_t *_top) 35{ 36 pixel *dst = (pixel *) _dst; 37 const pixel *top = (const pixel *) _top; 38 pixel4 p4 = AV_RN4PA(top); 39 40 stride /= sizeof(pixel); 41 AV_WN4PA(dst + stride * 0, p4); 42 AV_WN4PA(dst + stride * 1, p4); 43 AV_WN4PA(dst + stride * 2, p4); 44 AV_WN4PA(dst + stride * 3, p4); 45} 46 47static void vert_8x8_c(uint8_t *_dst, ptrdiff_t stride, 48 const uint8_t *left, const uint8_t *_top) 49{ 50 pixel *dst = (pixel *) _dst; 51 const pixel *top = (const pixel *) _top; 52 pixel4 p4a = AV_RN4PA(top + 0); 53 pixel4 p4b = AV_RN4PA(top + 4); 54 int y; 55 56 stride /= sizeof(pixel); 57 for (y = 0; y < 8; y++) { 58 AV_WN4PA(dst + 0, p4a); 59 AV_WN4PA(dst + 4, p4b); 60 dst += stride; 61 } 62} 63 64static void vert_16x16_c(uint8_t *_dst, ptrdiff_t stride, 65 const uint8_t *left, const uint8_t *_top) 66{ 67 pixel *dst = (pixel *) _dst; 68 const pixel *top = (const pixel *) _top; 69 pixel4 p4a = AV_RN4PA(top + 0); 70 pixel4 p4b = AV_RN4PA(top + 4); 71 pixel4 p4c = AV_RN4PA(top + 8); 72 pixel4 p4d = AV_RN4PA(top + 12); 73 int y; 74 75 stride /= sizeof(pixel); 76 for (y = 0; y < 16; y++) { 77 AV_WN4PA(dst + 0, p4a); 78 AV_WN4PA(dst + 4, p4b); 79 AV_WN4PA(dst + 8, p4c); 80 AV_WN4PA(dst + 12, p4d); 81 dst += stride; 82 } 83} 84 85static void vert_32x32_c(uint8_t *_dst, ptrdiff_t stride, 86 const uint8_t *left, const uint8_t *_top) 87{ 88 pixel *dst = (pixel *) _dst; 89 const pixel *top = (const pixel *) _top; 90 pixel4 p4a = AV_RN4PA(top + 0); 91 pixel4 p4b = AV_RN4PA(top + 4); 92 pixel4 p4c = AV_RN4PA(top + 8); 93 pixel4 p4d = AV_RN4PA(top + 12); 94 pixel4 p4e = AV_RN4PA(top + 16); 95 pixel4 p4f = AV_RN4PA(top + 20); 96 pixel4 p4g = AV_RN4PA(top + 24); 97 pixel4 p4h = AV_RN4PA(top + 28); 98 int y; 99 100 stride /= sizeof(pixel); 101 for (y = 0; y < 32; y++) { 102 AV_WN4PA(dst + 0, p4a); 103 AV_WN4PA(dst + 4, p4b); 104 AV_WN4PA(dst + 8, p4c); 105 AV_WN4PA(dst + 12, p4d); 106 AV_WN4PA(dst + 16, p4e); 107 AV_WN4PA(dst + 20, p4f); 108 AV_WN4PA(dst + 24, p4g); 109 AV_WN4PA(dst + 28, p4h); 110 dst += stride; 111 } 112} 113 114static void hor_4x4_c(uint8_t *_dst, ptrdiff_t stride, 115 const uint8_t *_left, const uint8_t *top) 116{ 117 pixel *dst = (pixel *) _dst; 118 const pixel *left = (const pixel *) _left; 119 120 stride /= sizeof(pixel); 121 AV_WN4PA(dst + stride * 0, PIXEL_SPLAT_X4(left[3])); 122 AV_WN4PA(dst + stride * 1, PIXEL_SPLAT_X4(left[2])); 123 AV_WN4PA(dst + stride * 2, PIXEL_SPLAT_X4(left[1])); 124 AV_WN4PA(dst + stride * 3, PIXEL_SPLAT_X4(left[0])); 125} 126 127static void hor_8x8_c(uint8_t *_dst, ptrdiff_t stride, 128 const uint8_t *_left, const uint8_t *top) 129{ 130 pixel *dst = (pixel *) _dst; 131 const pixel *left = (const pixel *) _left; 132 int y; 133 134 stride /= sizeof(pixel); 135 for (y = 0; y < 8; y++) { 136 pixel4 p4 = PIXEL_SPLAT_X4(left[7 - y]); 137 138 AV_WN4PA(dst + 0, p4); 139 AV_WN4PA(dst + 4, p4); 140 dst += stride; 141 } 142} 143 144static void hor_16x16_c(uint8_t *_dst, ptrdiff_t stride, 145 const uint8_t *_left, const uint8_t *top) 146{ 147 pixel *dst = (pixel *) _dst; 148 const pixel *left = (const pixel *) _left; 149 int y; 150 151 stride /= sizeof(pixel); 152 for (y = 0; y < 16; y++) { 153 pixel4 p4 = PIXEL_SPLAT_X4(left[15 - y]); 154 155 AV_WN4PA(dst + 0, p4); 156 AV_WN4PA(dst + 4, p4); 157 AV_WN4PA(dst + 8, p4); 158 AV_WN4PA(dst + 12, p4); 159 dst += stride; 160 } 161} 162 163static void hor_32x32_c(uint8_t *_dst, ptrdiff_t stride, 164 const uint8_t *_left, const uint8_t *top) 165{ 166 pixel *dst = (pixel *) _dst; 167 const pixel *left = (const pixel *) _left; 168 int y; 169 170 stride /= sizeof(pixel); 171 for (y = 0; y < 32; y++) { 172 pixel4 p4 = PIXEL_SPLAT_X4(left[31 - y]); 173 174 AV_WN4PA(dst + 0, p4); 175 AV_WN4PA(dst + 4, p4); 176 AV_WN4PA(dst + 8, p4); 177 AV_WN4PA(dst + 12, p4); 178 AV_WN4PA(dst + 16, p4); 179 AV_WN4PA(dst + 20, p4); 180 AV_WN4PA(dst + 24, p4); 181 AV_WN4PA(dst + 28, p4); 182 dst += stride; 183 } 184} 185 186#endif /* BIT_DEPTH != 12 */ 187 188static void tm_4x4_c(uint8_t *_dst, ptrdiff_t stride, 189 const uint8_t *_left, const uint8_t *_top) 190{ 191 pixel *dst = (pixel *) _dst; 192 const pixel *left = (const pixel *) _left; 193 const pixel *top = (const pixel *) _top; 194 int y, tl = top[-1]; 195 196 stride /= sizeof(pixel); 197 for (y = 0; y < 4; y++) { 198 int l_m_tl = left[3 - y] - tl; 199 200 dst[0] = av_clip_pixel(top[0] + l_m_tl); 201 dst[1] = av_clip_pixel(top[1] + l_m_tl); 202 dst[2] = av_clip_pixel(top[2] + l_m_tl); 203 dst[3] = av_clip_pixel(top[3] + l_m_tl); 204 dst += stride; 205 } 206} 207 208static void tm_8x8_c(uint8_t *_dst, ptrdiff_t stride, 209 const uint8_t *_left, const uint8_t *_top) 210{ 211 pixel *dst = (pixel *) _dst; 212 const pixel *left = (const pixel *) _left; 213 const pixel *top = (const pixel *) _top; 214 int y, tl = top[-1]; 215 216 stride /= sizeof(pixel); 217 for (y = 0; y < 8; y++) { 218 int l_m_tl = left[7 - y] - tl; 219 220 dst[0] = av_clip_pixel(top[0] + l_m_tl); 221 dst[1] = av_clip_pixel(top[1] + l_m_tl); 222 dst[2] = av_clip_pixel(top[2] + l_m_tl); 223 dst[3] = av_clip_pixel(top[3] + l_m_tl); 224 dst[4] = av_clip_pixel(top[4] + l_m_tl); 225 dst[5] = av_clip_pixel(top[5] + l_m_tl); 226 dst[6] = av_clip_pixel(top[6] + l_m_tl); 227 dst[7] = av_clip_pixel(top[7] + l_m_tl); 228 dst += stride; 229 } 230} 231 232static void tm_16x16_c(uint8_t *_dst, ptrdiff_t stride, 233 const uint8_t *_left, const uint8_t *_top) 234{ 235 pixel *dst = (pixel *) _dst; 236 const pixel *left = (const pixel *) _left; 237 const pixel *top = (const pixel *) _top; 238 int y, tl = top[-1]; 239 240 stride /= sizeof(pixel); 241 for (y = 0; y < 16; y++) { 242 int l_m_tl = left[15 - y] - tl; 243 244 dst[ 0] = av_clip_pixel(top[ 0] + l_m_tl); 245 dst[ 1] = av_clip_pixel(top[ 1] + l_m_tl); 246 dst[ 2] = av_clip_pixel(top[ 2] + l_m_tl); 247 dst[ 3] = av_clip_pixel(top[ 3] + l_m_tl); 248 dst[ 4] = av_clip_pixel(top[ 4] + l_m_tl); 249 dst[ 5] = av_clip_pixel(top[ 5] + l_m_tl); 250 dst[ 6] = av_clip_pixel(top[ 6] + l_m_tl); 251 dst[ 7] = av_clip_pixel(top[ 7] + l_m_tl); 252 dst[ 8] = av_clip_pixel(top[ 8] + l_m_tl); 253 dst[ 9] = av_clip_pixel(top[ 9] + l_m_tl); 254 dst[10] = av_clip_pixel(top[10] + l_m_tl); 255 dst[11] = av_clip_pixel(top[11] + l_m_tl); 256 dst[12] = av_clip_pixel(top[12] + l_m_tl); 257 dst[13] = av_clip_pixel(top[13] + l_m_tl); 258 dst[14] = av_clip_pixel(top[14] + l_m_tl); 259 dst[15] = av_clip_pixel(top[15] + l_m_tl); 260 dst += stride; 261 } 262} 263 264static void tm_32x32_c(uint8_t *_dst, ptrdiff_t stride, 265 const uint8_t *_left, const uint8_t *_top) 266{ 267 pixel *dst = (pixel *) _dst; 268 const pixel *left = (const pixel *) _left; 269 const pixel *top = (const pixel *) _top; 270 int y, tl = top[-1]; 271 272 stride /= sizeof(pixel); 273 for (y = 0; y < 32; y++) { 274 int l_m_tl = left[31 - y] - tl; 275 276 dst[ 0] = av_clip_pixel(top[ 0] + l_m_tl); 277 dst[ 1] = av_clip_pixel(top[ 1] + l_m_tl); 278 dst[ 2] = av_clip_pixel(top[ 2] + l_m_tl); 279 dst[ 3] = av_clip_pixel(top[ 3] + l_m_tl); 280 dst[ 4] = av_clip_pixel(top[ 4] + l_m_tl); 281 dst[ 5] = av_clip_pixel(top[ 5] + l_m_tl); 282 dst[ 6] = av_clip_pixel(top[ 6] + l_m_tl); 283 dst[ 7] = av_clip_pixel(top[ 7] + l_m_tl); 284 dst[ 8] = av_clip_pixel(top[ 8] + l_m_tl); 285 dst[ 9] = av_clip_pixel(top[ 9] + l_m_tl); 286 dst[10] = av_clip_pixel(top[10] + l_m_tl); 287 dst[11] = av_clip_pixel(top[11] + l_m_tl); 288 dst[12] = av_clip_pixel(top[12] + l_m_tl); 289 dst[13] = av_clip_pixel(top[13] + l_m_tl); 290 dst[14] = av_clip_pixel(top[14] + l_m_tl); 291 dst[15] = av_clip_pixel(top[15] + l_m_tl); 292 dst[16] = av_clip_pixel(top[16] + l_m_tl); 293 dst[17] = av_clip_pixel(top[17] + l_m_tl); 294 dst[18] = av_clip_pixel(top[18] + l_m_tl); 295 dst[19] = av_clip_pixel(top[19] + l_m_tl); 296 dst[20] = av_clip_pixel(top[20] + l_m_tl); 297 dst[21] = av_clip_pixel(top[21] + l_m_tl); 298 dst[22] = av_clip_pixel(top[22] + l_m_tl); 299 dst[23] = av_clip_pixel(top[23] + l_m_tl); 300 dst[24] = av_clip_pixel(top[24] + l_m_tl); 301 dst[25] = av_clip_pixel(top[25] + l_m_tl); 302 dst[26] = av_clip_pixel(top[26] + l_m_tl); 303 dst[27] = av_clip_pixel(top[27] + l_m_tl); 304 dst[28] = av_clip_pixel(top[28] + l_m_tl); 305 dst[29] = av_clip_pixel(top[29] + l_m_tl); 306 dst[30] = av_clip_pixel(top[30] + l_m_tl); 307 dst[31] = av_clip_pixel(top[31] + l_m_tl); 308 dst += stride; 309 } 310} 311 312#if BIT_DEPTH != 12 313 314static void dc_4x4_c(uint8_t *_dst, ptrdiff_t stride, 315 const uint8_t *_left, const uint8_t *_top) 316{ 317 pixel *dst = (pixel *) _dst; 318 const pixel *left = (const pixel *) _left; 319 const pixel *top = (const pixel *) _top; 320 pixel4 dc = PIXEL_SPLAT_X4((left[0] + left[1] + left[2] + left[3] + 321 top[0] + top[1] + top[2] + top[3] + 4) >> 3); 322 323 stride /= sizeof(pixel); 324 AV_WN4PA(dst + stride * 0, dc); 325 AV_WN4PA(dst + stride * 1, dc); 326 AV_WN4PA(dst + stride * 2, dc); 327 AV_WN4PA(dst + stride * 3, dc); 328} 329 330static void dc_8x8_c(uint8_t *_dst, ptrdiff_t stride, 331 const uint8_t *_left, const uint8_t *_top) 332{ 333 pixel *dst = (pixel *) _dst; 334 const pixel *left = (const pixel *) _left; 335 const pixel *top = (const pixel *) _top; 336 pixel4 dc = PIXEL_SPLAT_X4 337 ((left[0] + left[1] + left[2] + left[3] + left[4] + left[5] + 338 left[6] + left[7] + top[0] + top[1] + top[2] + top[3] + 339 top[4] + top[5] + top[6] + top[7] + 8) >> 4); 340 int y; 341 342 stride /= sizeof(pixel); 343 for (y = 0; y < 8; y++) { 344 AV_WN4PA(dst + 0, dc); 345 AV_WN4PA(dst + 4, dc); 346 dst += stride; 347 } 348} 349 350static void dc_16x16_c(uint8_t *_dst, ptrdiff_t stride, 351 const uint8_t *_left, const uint8_t *_top) 352{ 353 pixel *dst = (pixel *) _dst; 354 const pixel *left = (const pixel *) _left; 355 const pixel *top = (const pixel *) _top; 356 pixel4 dc = PIXEL_SPLAT_X4 357 ((left[0] + left[1] + left[2] + left[3] + left[4] + left[5] + left[6] + 358 left[7] + left[8] + left[9] + left[10] + left[11] + left[12] + 359 left[13] + left[14] + left[15] + top[0] + top[1] + top[2] + top[3] + 360 top[4] + top[5] + top[6] + top[7] + top[8] + top[9] + top[10] + 361 top[11] + top[12] + top[13] + top[14] + top[15] + 16) >> 5); 362 int y; 363 364 stride /= sizeof(pixel); 365 for (y = 0; y < 16; y++) { 366 AV_WN4PA(dst + 0, dc); 367 AV_WN4PA(dst + 4, dc); 368 AV_WN4PA(dst + 8, dc); 369 AV_WN4PA(dst + 12, dc); 370 dst += stride; 371 } 372} 373 374static void dc_32x32_c(uint8_t *_dst, ptrdiff_t stride, 375 const uint8_t *_left, const uint8_t *_top) 376{ 377 pixel *dst = (pixel *) _dst; 378 const pixel *left = (const pixel *) _left; 379 const pixel *top = (const pixel *) _top; 380 pixel4 dc = PIXEL_SPLAT_X4 381 ((left[0] + left[1] + left[2] + left[3] + left[4] + left[5] + left[6] + 382 left[7] + left[8] + left[9] + left[10] + left[11] + left[12] + 383 left[13] + left[14] + left[15] + left[16] + left[17] + left[18] + 384 left[19] + left[20] + left[21] + left[22] + left[23] + left[24] + 385 left[25] + left[26] + left[27] + left[28] + left[29] + left[30] + 386 left[31] + top[0] + top[1] + top[2] + top[3] + top[4] + top[5] + 387 top[6] + top[7] + top[8] + top[9] + top[10] + top[11] + top[12] + 388 top[13] + top[14] + top[15] + top[16] + top[17] + top[18] + top[19] + 389 top[20] + top[21] + top[22] + top[23] + top[24] + top[25] + top[26] + 390 top[27] + top[28] + top[29] + top[30] + top[31] + 32) >> 6); 391 int y; 392 393 stride /= sizeof(pixel); 394 for (y = 0; y < 32; y++) { 395 AV_WN4PA(dst + 0, dc); 396 AV_WN4PA(dst + 4, dc); 397 AV_WN4PA(dst + 8, dc); 398 AV_WN4PA(dst + 12, dc); 399 AV_WN4PA(dst + 16, dc); 400 AV_WN4PA(dst + 20, dc); 401 AV_WN4PA(dst + 24, dc); 402 AV_WN4PA(dst + 28, dc); 403 dst += stride; 404 } 405} 406 407static void dc_left_4x4_c(uint8_t *_dst, ptrdiff_t stride, 408 const uint8_t *_left, const uint8_t *top) 409{ 410 pixel *dst = (pixel *) _dst; 411 const pixel *left = (const pixel *) _left; 412 pixel4 dc = PIXEL_SPLAT_X4((left[0] + left[1] + left[2] + left[3] + 2) >> 2); 413 414 stride /= sizeof(pixel); 415 AV_WN4PA(dst + stride * 0, dc); 416 AV_WN4PA(dst + stride * 1, dc); 417 AV_WN4PA(dst + stride * 2, dc); 418 AV_WN4PA(dst + stride * 3, dc); 419} 420 421static void dc_left_8x8_c(uint8_t *_dst, ptrdiff_t stride, 422 const uint8_t *_left, const uint8_t *top) 423{ 424 pixel *dst = (pixel *) _dst; 425 const pixel *left = (const pixel *) _left; 426 pixel4 dc = PIXEL_SPLAT_X4 427 ((left[0] + left[1] + left[2] + left[3] + 428 left[4] + left[5] + left[6] + left[7] + 4) >> 3); 429 int y; 430 431 stride /= sizeof(pixel); 432 for (y = 0; y < 8; y++) { 433 AV_WN4PA(dst + 0, dc); 434 AV_WN4PA(dst + 4, dc); 435 dst += stride; 436 } 437} 438 439static void dc_left_16x16_c(uint8_t *_dst, ptrdiff_t stride, 440 const uint8_t *_left, const uint8_t *top) 441{ 442 pixel *dst = (pixel *) _dst; 443 const pixel *left = (const pixel *) _left; 444 pixel4 dc = PIXEL_SPLAT_X4 445 ((left[0] + left[1] + left[2] + left[3] + left[4] + left[5] + 446 left[6] + left[7] + left[8] + left[9] + left[10] + left[11] + 447 left[12] + left[13] + left[14] + left[15] + 8) >> 4); 448 int y; 449 450 stride /= sizeof(pixel); 451 for (y = 0; y < 16; y++) { 452 AV_WN4PA(dst + 0, dc); 453 AV_WN4PA(dst + 4, dc); 454 AV_WN4PA(dst + 8, dc); 455 AV_WN4PA(dst + 12, dc); 456 dst += stride; 457 } 458} 459 460static void dc_left_32x32_c(uint8_t *_dst, ptrdiff_t stride, 461 const uint8_t *_left, const uint8_t *top) 462{ 463 pixel *dst = (pixel *) _dst; 464 const pixel *left = (const pixel *) _left; 465 pixel4 dc = PIXEL_SPLAT_X4 466 ((left[0] + left[1] + left[2] + left[3] + left[4] + left[5] + 467 left[6] + left[7] + left[8] + left[9] + left[10] + left[11] + 468 left[12] + left[13] + left[14] + left[15] + left[16] + left[17] + 469 left[18] + left[19] + left[20] + left[21] + left[22] + left[23] + 470 left[24] + left[25] + left[26] + left[27] + left[28] + left[29] + 471 left[30] + left[31] + 16) >> 5); 472 int y; 473 474 stride /= sizeof(pixel); 475 for (y = 0; y < 32; y++) { 476 AV_WN4PA(dst + 0, dc); 477 AV_WN4PA(dst + 4, dc); 478 AV_WN4PA(dst + 8, dc); 479 AV_WN4PA(dst + 12, dc); 480 AV_WN4PA(dst + 16, dc); 481 AV_WN4PA(dst + 20, dc); 482 AV_WN4PA(dst + 24, dc); 483 AV_WN4PA(dst + 28, dc); 484 dst += stride; 485 } 486} 487 488static void dc_top_4x4_c(uint8_t *_dst, ptrdiff_t stride, 489 const uint8_t *left, const uint8_t *_top) 490{ 491 pixel *dst = (pixel *) _dst; 492 const pixel *top = (const pixel *) _top; 493 pixel4 dc = PIXEL_SPLAT_X4((top[0] + top[1] + top[2] + top[3] + 2) >> 2); 494 495 stride /= sizeof(pixel); 496 AV_WN4PA(dst + stride * 0, dc); 497 AV_WN4PA(dst + stride * 1, dc); 498 AV_WN4PA(dst + stride * 2, dc); 499 AV_WN4PA(dst + stride * 3, dc); 500} 501 502static void dc_top_8x8_c(uint8_t *_dst, ptrdiff_t stride, 503 const uint8_t *left, const uint8_t *_top) 504{ 505 pixel *dst = (pixel *) _dst; 506 const pixel *top = (const pixel *) _top; 507 pixel4 dc = PIXEL_SPLAT_X4 508 ((top[0] + top[1] + top[2] + top[3] + 509 top[4] + top[5] + top[6] + top[7] + 4) >> 3); 510 int y; 511 512 stride /= sizeof(pixel); 513 for (y = 0; y < 8; y++) { 514 AV_WN4PA(dst + 0, dc); 515 AV_WN4PA(dst + 4, dc); 516 dst += stride; 517 } 518} 519 520static void dc_top_16x16_c(uint8_t *_dst, ptrdiff_t stride, 521 const uint8_t *left, const uint8_t *_top) 522{ 523 pixel *dst = (pixel *) _dst; 524 const pixel *top = (const pixel *) _top; 525 pixel4 dc = PIXEL_SPLAT_X4 526 ((top[0] + top[1] + top[2] + top[3] + top[4] + top[5] + 527 top[6] + top[7] + top[8] + top[9] + top[10] + top[11] + 528 top[12] + top[13] + top[14] + top[15] + 8) >> 4); 529 int y; 530 531 stride /= sizeof(pixel); 532 for (y = 0; y < 16; y++) { 533 AV_WN4PA(dst + 0, dc); 534 AV_WN4PA(dst + 4, dc); 535 AV_WN4PA(dst + 8, dc); 536 AV_WN4PA(dst + 12, dc); 537 dst += stride; 538 } 539} 540 541static void dc_top_32x32_c(uint8_t *_dst, ptrdiff_t stride, 542 const uint8_t *left, const uint8_t *_top) 543{ 544 pixel *dst = (pixel *) _dst; 545 const pixel *top = (const pixel *) _top; 546 pixel4 dc = PIXEL_SPLAT_X4 547 ((top[0] + top[1] + top[2] + top[3] + top[4] + top[5] + 548 top[6] + top[7] + top[8] + top[9] + top[10] + top[11] + 549 top[12] + top[13] + top[14] + top[15] + top[16] + top[17] + 550 top[18] + top[19] + top[20] + top[21] + top[22] + top[23] + 551 top[24] + top[25] + top[26] + top[27] + top[28] + top[29] + 552 top[30] + top[31] + 16) >> 5); 553 int y; 554 555 stride /= sizeof(pixel); 556 for (y = 0; y < 32; y++) { 557 AV_WN4PA(dst + 0, dc); 558 AV_WN4PA(dst + 4, dc); 559 AV_WN4PA(dst + 8, dc); 560 AV_WN4PA(dst + 12, dc); 561 AV_WN4PA(dst + 16, dc); 562 AV_WN4PA(dst + 20, dc); 563 AV_WN4PA(dst + 24, dc); 564 AV_WN4PA(dst + 28, dc); 565 dst += stride; 566 } 567} 568 569#endif /* BIT_DEPTH != 12 */ 570 571static void dc_128_4x4_c(uint8_t *_dst, ptrdiff_t stride, 572 const uint8_t *left, const uint8_t *top) 573{ 574 pixel *dst = (pixel *) _dst; 575 pixel4 val = PIXEL_SPLAT_X4(128 << (BIT_DEPTH - 8)); 576 577 stride /= sizeof(pixel); 578 AV_WN4PA(dst + stride * 0, val); 579 AV_WN4PA(dst + stride * 1, val); 580 AV_WN4PA(dst + stride * 2, val); 581 AV_WN4PA(dst + stride * 3, val); 582} 583 584static void dc_128_8x8_c(uint8_t *_dst, ptrdiff_t stride, 585 const uint8_t *left, const uint8_t *top) 586{ 587 pixel *dst = (pixel *) _dst; 588 pixel4 val = PIXEL_SPLAT_X4(128 << (BIT_DEPTH - 8)); 589 int y; 590 591 stride /= sizeof(pixel); 592 for (y = 0; y < 8; y++) { 593 AV_WN4PA(dst + 0, val); 594 AV_WN4PA(dst + 4, val); 595 dst += stride; 596 } 597} 598 599static void dc_128_16x16_c(uint8_t *_dst, ptrdiff_t stride, 600 const uint8_t *left, const uint8_t *top) 601{ 602 pixel *dst = (pixel *) _dst; 603 pixel4 val = PIXEL_SPLAT_X4(128 << (BIT_DEPTH - 8)); 604 int y; 605 606 stride /= sizeof(pixel); 607 for (y = 0; y < 16; y++) { 608 AV_WN4PA(dst + 0, val); 609 AV_WN4PA(dst + 4, val); 610 AV_WN4PA(dst + 8, val); 611 AV_WN4PA(dst + 12, val); 612 dst += stride; 613 } 614} 615 616static void dc_128_32x32_c(uint8_t *_dst, ptrdiff_t stride, 617 const uint8_t *left, const uint8_t *top) 618{ 619 pixel *dst = (pixel *) _dst; 620 pixel4 val = PIXEL_SPLAT_X4(128 << (BIT_DEPTH - 8)); 621 int y; 622 623 stride /= sizeof(pixel); 624 for (y = 0; y < 32; y++) { 625 AV_WN4PA(dst + 0, val); 626 AV_WN4PA(dst + 4, val); 627 AV_WN4PA(dst + 8, val); 628 AV_WN4PA(dst + 12, val); 629 AV_WN4PA(dst + 16, val); 630 AV_WN4PA(dst + 20, val); 631 AV_WN4PA(dst + 24, val); 632 AV_WN4PA(dst + 28, val); 633 dst += stride; 634 } 635} 636 637static void dc_127_4x4_c(uint8_t *_dst, ptrdiff_t stride, 638 const uint8_t *left, const uint8_t *top) 639{ 640 pixel *dst = (pixel *) _dst; 641 pixel4 val = PIXEL_SPLAT_X4((128 << (BIT_DEPTH - 8)) - 1); 642 643 stride /= sizeof(pixel); 644 AV_WN4PA(dst + stride * 0, val); 645 AV_WN4PA(dst + stride * 1, val); 646 AV_WN4PA(dst + stride * 2, val); 647 AV_WN4PA(dst + stride * 3, val);} 648 649static void dc_127_8x8_c(uint8_t *_dst, ptrdiff_t stride, 650 const uint8_t *left, const uint8_t *top) 651{ 652 pixel *dst = (pixel *) _dst; 653 pixel4 val = PIXEL_SPLAT_X4((128 << (BIT_DEPTH - 8)) - 1); 654 int y; 655 656 stride /= sizeof(pixel); 657 for (y = 0; y < 8; y++) { 658 AV_WN4PA(dst + 0, val); 659 AV_WN4PA(dst + 4, val); 660 dst += stride; 661 } 662} 663 664static void dc_127_16x16_c(uint8_t *_dst, ptrdiff_t stride, 665 const uint8_t *left, const uint8_t *top) 666{ 667 pixel *dst = (pixel *) _dst; 668 pixel4 val = PIXEL_SPLAT_X4((128 << (BIT_DEPTH - 8)) - 1); 669 int y; 670 671 stride /= sizeof(pixel); 672 for (y = 0; y < 16; y++) { 673 AV_WN4PA(dst + 0, val); 674 AV_WN4PA(dst + 4, val); 675 AV_WN4PA(dst + 8, val); 676 AV_WN4PA(dst + 12, val); 677 dst += stride; 678 } 679} 680 681static void dc_127_32x32_c(uint8_t *_dst, ptrdiff_t stride, 682 const uint8_t *left, const uint8_t *top) 683{ 684 pixel *dst = (pixel *) _dst; 685 pixel4 val = PIXEL_SPLAT_X4((128 << (BIT_DEPTH - 8)) - 1); 686 int y; 687 688 stride /= sizeof(pixel); 689 for (y = 0; y < 32; y++) { 690 AV_WN4PA(dst + 0, val); 691 AV_WN4PA(dst + 4, val); 692 AV_WN4PA(dst + 8, val); 693 AV_WN4PA(dst + 12, val); 694 AV_WN4PA(dst + 16, val); 695 AV_WN4PA(dst + 20, val); 696 AV_WN4PA(dst + 24, val); 697 AV_WN4PA(dst + 28, val); 698 dst += stride; 699 } 700} 701 702static void dc_129_4x4_c(uint8_t *_dst, ptrdiff_t stride, 703 const uint8_t *left, const uint8_t *top) 704{ 705 pixel *dst = (pixel *) _dst; 706 pixel4 val = PIXEL_SPLAT_X4((128 << (BIT_DEPTH - 8)) + 1); 707 708 stride /= sizeof(pixel); 709 AV_WN4PA(dst + stride * 0, val); 710 AV_WN4PA(dst + stride * 1, val); 711 AV_WN4PA(dst + stride * 2, val); 712 AV_WN4PA(dst + stride * 3, val); 713} 714 715static void dc_129_8x8_c(uint8_t *_dst, ptrdiff_t stride, 716 const uint8_t *left, const uint8_t *top) 717{ 718 pixel *dst = (pixel *) _dst; 719 pixel4 val = PIXEL_SPLAT_X4((128 << (BIT_DEPTH - 8)) + 1); 720 int y; 721 722 stride /= sizeof(pixel); 723 for (y = 0; y < 8; y++) { 724 AV_WN4PA(dst + 0, val); 725 AV_WN4PA(dst + 4, val); 726 dst += stride; 727 } 728} 729 730static void dc_129_16x16_c(uint8_t *_dst, ptrdiff_t stride, 731 const uint8_t *left, const uint8_t *top) 732{ 733 pixel *dst = (pixel *) _dst; 734 pixel4 val = PIXEL_SPLAT_X4((128 << (BIT_DEPTH - 8)) + 1); 735 int y; 736 737 stride /= sizeof(pixel); 738 for (y = 0; y < 16; y++) { 739 AV_WN4PA(dst + 0, val); 740 AV_WN4PA(dst + 4, val); 741 AV_WN4PA(dst + 8, val); 742 AV_WN4PA(dst + 12, val); 743 dst += stride; 744 } 745} 746 747static void dc_129_32x32_c(uint8_t *_dst, ptrdiff_t stride, 748 const uint8_t *left, const uint8_t *top) 749{ 750 pixel *dst = (pixel *) _dst; 751 pixel4 val = PIXEL_SPLAT_X4((128 << (BIT_DEPTH - 8)) + 1); 752 int y; 753 754 stride /= sizeof(pixel); 755 for (y = 0; y < 32; y++) { 756 AV_WN4PA(dst + 0, val); 757 AV_WN4PA(dst + 4, val); 758 AV_WN4PA(dst + 8, val); 759 AV_WN4PA(dst + 12, val); 760 AV_WN4PA(dst + 16, val); 761 AV_WN4PA(dst + 20, val); 762 AV_WN4PA(dst + 24, val); 763 AV_WN4PA(dst + 28, val); 764 dst += stride; 765 } 766} 767 768#if BIT_DEPTH != 12 769 770#if BIT_DEPTH == 8 771#define memset_bpc memset 772#else 773static inline void memset_bpc(uint16_t *dst, int val, int len) { 774 int n; 775 for (n = 0; n < len; n++) { 776 dst[n] = val; 777 } 778} 779#endif 780 781#define DST(x, y) dst[(x) + (y) * stride] 782 783static void diag_downleft_4x4_c(uint8_t *_dst, ptrdiff_t stride, 784 const uint8_t *left, const uint8_t *_top) 785{ 786 pixel *dst = (pixel *) _dst; 787 const pixel *top = (const pixel *) _top; 788 int a0 = top[0], a1 = top[1], a2 = top[2], a3 = top[3], 789 a4 = top[4], a5 = top[5], a6 = top[6], a7 = top[7]; 790 791 stride /= sizeof(pixel); 792 DST(0,0) = (a0 + a1 * 2 + a2 + 2) >> 2; 793 DST(1,0) = DST(0,1) = (a1 + a2 * 2 + a3 + 2) >> 2; 794 DST(2,0) = DST(1,1) = DST(0,2) = (a2 + a3 * 2 + a4 + 2) >> 2; 795 DST(3,0) = DST(2,1) = DST(1,2) = DST(0,3) = (a3 + a4 * 2 + a5 + 2) >> 2; 796 DST(3,1) = DST(2,2) = DST(1,3) = (a4 + a5 * 2 + a6 + 2) >> 2; 797 DST(3,2) = DST(2,3) = (a5 + a6 * 2 + a7 + 2) >> 2; 798 DST(3,3) = a7; // note: this is different from vp8 and such 799} 800 801#define def_diag_downleft(size) \ 802static void diag_downleft_##size##x##size##_c(uint8_t *_dst, ptrdiff_t stride, \ 803 const uint8_t *left, const uint8_t *_top) \ 804{ \ 805 pixel *dst = (pixel *) _dst; \ 806 const pixel *top = (const pixel *) _top; \ 807 int i, j; \ 808 pixel v[size - 1]; \ 809\ 810 stride /= sizeof(pixel); \ 811 for (i = 0; i < size - 2; i++) \ 812 v[i] = (top[i] + top[i + 1] * 2 + top[i + 2] + 2) >> 2; \ 813 v[size - 2] = (top[size - 2] + top[size - 1] * 3 + 2) >> 2; \ 814\ 815 for (j = 0; j < size; j++) { \ 816 memcpy(dst + j*stride, v + j, (size - 1 - j) * sizeof(pixel)); \ 817 memset_bpc(dst + j*stride + size - 1 - j, top[size - 1], j + 1); \ 818 } \ 819} 820 821def_diag_downleft(8) 822def_diag_downleft(16) 823def_diag_downleft(32) 824 825static void diag_downright_4x4_c(uint8_t *_dst, ptrdiff_t stride, 826 const uint8_t *_left, const uint8_t *_top) 827{ 828 pixel *dst = (pixel *) _dst; 829 const pixel *top = (const pixel *) _top; 830 const pixel *left = (const pixel *) _left; 831 int tl = top[-1], a0 = top[0], a1 = top[1], a2 = top[2], a3 = top[3], 832 l0 = left[3], l1 = left[2], l2 = left[1], l3 = left[0]; 833 834 stride /= sizeof(pixel); 835 DST(0,3) = (l1 + l2 * 2 + l3 + 2) >> 2; 836 DST(0,2) = DST(1,3) = (l0 + l1 * 2 + l2 + 2) >> 2; 837 DST(0,1) = DST(1,2) = DST(2,3) = (tl + l0 * 2 + l1 + 2) >> 2; 838 DST(0,0) = DST(1,1) = DST(2,2) = DST(3,3) = (l0 + tl * 2 + a0 + 2) >> 2; 839 DST(1,0) = DST(2,1) = DST(3,2) = (tl + a0 * 2 + a1 + 2) >> 2; 840 DST(2,0) = DST(3,1) = (a0 + a1 * 2 + a2 + 2) >> 2; 841 DST(3,0) = (a1 + a2 * 2 + a3 + 2) >> 2; 842} 843 844#define def_diag_downright(size) \ 845static void diag_downright_##size##x##size##_c(uint8_t *_dst, ptrdiff_t stride, \ 846 const uint8_t *_left, const uint8_t *_top) \ 847{ \ 848 pixel *dst = (pixel *) _dst; \ 849 const pixel *top = (const pixel *) _top; \ 850 const pixel *left = (const pixel *) _left; \ 851 int i, j; \ 852 pixel v[size + size - 1]; \ 853\ 854 stride /= sizeof(pixel); \ 855 for (i = 0; i < size - 2; i++) { \ 856 v[i ] = (left[i] + left[i + 1] * 2 + left[i + 2] + 2) >> 2; \ 857 v[size + 1 + i] = (top[i] + top[i + 1] * 2 + top[i + 2] + 2) >> 2; \ 858 } \ 859 v[size - 2] = (left[size - 2] + left[size - 1] * 2 + top[-1] + 2) >> 2; \ 860 v[size - 1] = (left[size - 1] + top[-1] * 2 + top[ 0] + 2) >> 2; \ 861 v[size ] = (top[-1] + top[0] * 2 + top[ 1] + 2) >> 2; \ 862\ 863 for (j = 0; j < size; j++) \ 864 memcpy(dst + j*stride, v + size - 1 - j, size * sizeof(pixel)); \ 865} 866 867def_diag_downright(8) 868def_diag_downright(16) 869def_diag_downright(32) 870 871static void vert_right_4x4_c(uint8_t *_dst, ptrdiff_t stride, 872 const uint8_t *_left, const uint8_t *_top) 873{ 874 pixel *dst = (pixel *) _dst; 875 const pixel *top = (const pixel *) _top; 876 const pixel *left = (const pixel *) _left; 877 int tl = top[-1], a0 = top[0], a1 = top[1], a2 = top[2], a3 = top[3], 878 l0 = left[3], l1 = left[2], l2 = left[1]; 879 880 stride /= sizeof(pixel); 881 DST(0,3) = (l0 + l1 * 2 + l2 + 2) >> 2; 882 DST(0,2) = (tl + l0 * 2 + l1 + 2) >> 2; 883 DST(0,0) = DST(1,2) = (tl + a0 + 1) >> 1; 884 DST(0,1) = DST(1,3) = (l0 + tl * 2 + a0 + 2) >> 2; 885 DST(1,0) = DST(2,2) = (a0 + a1 + 1) >> 1; 886 DST(1,1) = DST(2,3) = (tl + a0 * 2 + a1 + 2) >> 2; 887 DST(2,0) = DST(3,2) = (a1 + a2 + 1) >> 1; 888 DST(2,1) = DST(3,3) = (a0 + a1 * 2 + a2 + 2) >> 2; 889 DST(3,0) = (a2 + a3 + 1) >> 1; 890 DST(3,1) = (a1 + a2 * 2 + a3 + 2) >> 2; 891} 892 893#define def_vert_right(size) \ 894static void vert_right_##size##x##size##_c(uint8_t *_dst, ptrdiff_t stride, \ 895 const uint8_t *_left, const uint8_t *_top) \ 896{ \ 897 pixel *dst = (pixel *) _dst; \ 898 const pixel *top = (const pixel *) _top; \ 899 const pixel *left = (const pixel *) _left; \ 900 int i, j; \ 901 pixel ve[size + size/2 - 1], vo[size + size/2 - 1]; \ 902\ 903 stride /= sizeof(pixel); \ 904 for (i = 0; i < size/2 - 2; i++) { \ 905 vo[i] = (left[i*2 + 3] + left[i*2 + 2] * 2 + left[i*2 + 1] + 2) >> 2; \ 906 ve[i] = (left[i*2 + 4] + left[i*2 + 3] * 2 + left[i*2 + 2] + 2) >> 2; \ 907 } \ 908 vo[size/2 - 2] = (left[size - 1] + left[size - 2] * 2 + left[size - 3] + 2) >> 2; \ 909 ve[size/2 - 2] = (top[-1] + left[size - 1] * 2 + left[size - 2] + 2) >> 2; \ 910\ 911 ve[size/2 - 1] = (top[-1] + top[0] + 1) >> 1; \ 912 vo[size/2 - 1] = (left[size - 1] + top[-1] * 2 + top[0] + 2) >> 2; \ 913 for (i = 0; i < size - 1; i++) { \ 914 ve[size/2 + i] = (top[i] + top[i + 1] + 1) >> 1; \ 915 vo[size/2 + i] = (top[i - 1] + top[i] * 2 + top[i + 1] + 2) >> 2; \ 916 } \ 917\ 918 for (j = 0; j < size / 2; j++) { \ 919 memcpy(dst + j*2 *stride, ve + size/2 - 1 - j, size * sizeof(pixel)); \ 920 memcpy(dst + (j*2 + 1)*stride, vo + size/2 - 1 - j, size * sizeof(pixel)); \ 921 } \ 922} 923 924def_vert_right(8) 925def_vert_right(16) 926def_vert_right(32) 927 928static void hor_down_4x4_c(uint8_t *_dst, ptrdiff_t stride, 929 const uint8_t *_left, const uint8_t *_top) 930{ 931 pixel *dst = (pixel *) _dst; 932 const pixel *top = (const pixel *) _top; 933 const pixel *left = (const pixel *) _left; 934 int l0 = left[3], l1 = left[2], l2 = left[1], l3 = left[0], 935 tl = top[-1], a0 = top[0], a1 = top[1], a2 = top[2]; 936 937 stride /= sizeof(pixel); 938 DST(2,0) = (tl + a0 * 2 + a1 + 2) >> 2; 939 DST(3,0) = (a0 + a1 * 2 + a2 + 2) >> 2; 940 DST(0,0) = DST(2,1) = (tl + l0 + 1) >> 1; 941 DST(1,0) = DST(3,1) = (a0 + tl * 2 + l0 + 2) >> 2; 942 DST(0,1) = DST(2,2) = (l0 + l1 + 1) >> 1; 943 DST(1,1) = DST(3,2) = (tl + l0 * 2 + l1 + 2) >> 2; 944 DST(0,2) = DST(2,3) = (l1 + l2 + 1) >> 1; 945 DST(1,2) = DST(3,3) = (l0 + l1 * 2 + l2 + 2) >> 2; 946 DST(0,3) = (l2 + l3 + 1) >> 1; 947 DST(1,3) = (l1 + l2 * 2 + l3 + 2) >> 2; 948} 949 950#define def_hor_down(size) \ 951static void hor_down_##size##x##size##_c(uint8_t *_dst, ptrdiff_t stride, \ 952 const uint8_t *_left, const uint8_t *_top) \ 953{ \ 954 pixel *dst = (pixel *) _dst; \ 955 const pixel *top = (const pixel *) _top; \ 956 const pixel *left = (const pixel *) _left; \ 957 int i, j; \ 958 pixel v[size * 3 - 2]; \ 959\ 960 stride /= sizeof(pixel); \ 961 for (i = 0; i < size - 2; i++) { \ 962 v[i*2 ] = (left[i + 1] + left[i + 0] + 1) >> 1; \ 963 v[i*2 + 1] = (left[i + 2] + left[i + 1] * 2 + left[i + 0] + 2) >> 2; \ 964 v[size*2 + i] = (top[i - 1] + top[i] * 2 + top[i + 1] + 2) >> 2; \ 965 } \ 966 v[size*2 - 2] = (top[-1] + left[size - 1] + 1) >> 1; \ 967 v[size*2 - 4] = (left[size - 1] + left[size - 2] + 1) >> 1; \ 968 v[size*2 - 1] = (top[0] + top[-1] * 2 + left[size - 1] + 2) >> 2; \ 969 v[size*2 - 3] = (top[-1] + left[size - 1] * 2 + left[size - 2] + 2) >> 2; \ 970\ 971 for (j = 0; j < size; j++) \ 972 memcpy(dst + j*stride, v + size*2 - 2 - j*2, size * sizeof(pixel)); \ 973} 974 975def_hor_down(8) 976def_hor_down(16) 977def_hor_down(32) 978 979static void vert_left_4x4_c(uint8_t *_dst, ptrdiff_t stride, 980 const uint8_t *left, const uint8_t *_top) 981{ 982 pixel *dst = (pixel *) _dst; 983 const pixel *top = (const pixel *) _top; 984 int a0 = top[0], a1 = top[1], a2 = top[2], a3 = top[3], 985 a4 = top[4], a5 = top[5], a6 = top[6]; 986 987 stride /= sizeof(pixel); 988 DST(0,0) = (a0 + a1 + 1) >> 1; 989 DST(0,1) = (a0 + a1 * 2 + a2 + 2) >> 2; 990 DST(1,0) = DST(0,2) = (a1 + a2 + 1) >> 1; 991 DST(1,1) = DST(0,3) = (a1 + a2 * 2 + a3 + 2) >> 2; 992 DST(2,0) = DST(1,2) = (a2 + a3 + 1) >> 1; 993 DST(2,1) = DST(1,3) = (a2 + a3 * 2 + a4 + 2) >> 2; 994 DST(3,0) = DST(2,2) = (a3 + a4 + 1) >> 1; 995 DST(3,1) = DST(2,3) = (a3 + a4 * 2 + a5 + 2) >> 2; 996 DST(3,2) = (a4 + a5 + 1) >> 1; 997 DST(3,3) = (a4 + a5 * 2 + a6 + 2) >> 2; 998} 999 1000#define def_vert_left(size) \ 1001static void vert_left_##size##x##size##_c(uint8_t *_dst, ptrdiff_t stride, \ 1002 const uint8_t *left, const uint8_t *_top) \ 1003{ \ 1004 pixel *dst = (pixel *) _dst; \ 1005 const pixel *top = (const pixel *) _top; \ 1006 int i, j; \ 1007 pixel ve[size - 1], vo[size - 1]; \ 1008\ 1009 stride /= sizeof(pixel); \ 1010 for (i = 0; i < size - 2; i++) { \ 1011 ve[i] = (top[i] + top[i + 1] + 1) >> 1; \ 1012 vo[i] = (top[i] + top[i + 1] * 2 + top[i + 2] + 2) >> 2; \ 1013 } \ 1014 ve[size - 2] = (top[size - 2] + top[size - 1] + 1) >> 1; \ 1015 vo[size - 2] = (top[size - 2] + top[size - 1] * 3 + 2) >> 2; \ 1016\ 1017 for (j = 0; j < size / 2; j++) { \ 1018 memcpy(dst + j*2 * stride, ve + j, (size - j - 1) * sizeof(pixel)); \ 1019 memset_bpc(dst + j*2 * stride + size - j - 1, top[size - 1], j + 1); \ 1020 memcpy(dst + (j*2 + 1) * stride, vo + j, (size - j - 1) * sizeof(pixel)); \ 1021 memset_bpc(dst + (j*2 + 1) * stride + size - j - 1, top[size - 1], j + 1); \ 1022 } \ 1023} 1024 1025def_vert_left(8) 1026def_vert_left(16) 1027def_vert_left(32) 1028 1029static void hor_up_4x4_c(uint8_t *_dst, ptrdiff_t stride, 1030 const uint8_t *_left, const uint8_t *top) 1031{ 1032 pixel *dst = (pixel *) _dst; 1033 const pixel *left = (const pixel *) _left; 1034 int l0 = left[0], l1 = left[1], l2 = left[2], l3 = left[3]; 1035 1036 stride /= sizeof(pixel); 1037 DST(0,0) = (l0 + l1 + 1) >> 1; 1038 DST(1,0) = (l0 + l1 * 2 + l2 + 2) >> 2; 1039 DST(0,1) = DST(2,0) = (l1 + l2 + 1) >> 1; 1040 DST(1,1) = DST(3,0) = (l1 + l2 * 2 + l3 + 2) >> 2; 1041 DST(0,2) = DST(2,1) = (l2 + l3 + 1) >> 1; 1042 DST(1,2) = DST(3,1) = (l2 + l3 * 3 + 2) >> 2; 1043 DST(0,3) = DST(1,3) = DST(2,2) = DST(2,3) = DST(3,2) = DST(3,3) = l3; 1044} 1045 1046#define def_hor_up(size) \ 1047static void hor_up_##size##x##size##_c(uint8_t *_dst, ptrdiff_t stride, \ 1048 const uint8_t *_left, const uint8_t *top) \ 1049{ \ 1050 pixel *dst = (pixel *) _dst; \ 1051 const pixel *left = (const pixel *) _left; \ 1052 int i, j; \ 1053 pixel v[size*2 - 2]; \ 1054\ 1055 stride /= sizeof(pixel); \ 1056 for (i = 0; i < size - 2; i++) { \ 1057 v[i*2 ] = (left[i] + left[i + 1] + 1) >> 1; \ 1058 v[i*2 + 1] = (left[i] + left[i + 1] * 2 + left[i + 2] + 2) >> 2; \ 1059 } \ 1060 v[size*2 - 4] = (left[size - 2] + left[size - 1] + 1) >> 1; \ 1061 v[size*2 - 3] = (left[size - 2] + left[size - 1] * 3 + 2) >> 2; \ 1062\ 1063 for (j = 0; j < size / 2; j++) \ 1064 memcpy(dst + j*stride, v + j*2, size * sizeof(pixel)); \ 1065 for (j = size / 2; j < size; j++) { \ 1066 memcpy(dst + j*stride, v + j*2, (size*2 - 2 - j*2) * sizeof(pixel)); \ 1067 memset_bpc(dst + j*stride + size*2 - 2 - j*2, left[size - 1], \ 1068 2 + j*2 - size); \ 1069 } \ 1070} 1071 1072def_hor_up(8) 1073def_hor_up(16) 1074def_hor_up(32) 1075 1076#undef DST 1077 1078#endif /* BIT_DEPTH != 12 */ 1079 1080#if BIT_DEPTH != 8 1081void ff_vp9dsp_intrapred_init_10(VP9DSPContext *dsp); 1082#endif 1083#if BIT_DEPTH != 10 1084static 1085#endif 1086av_cold void FUNC(ff_vp9dsp_intrapred_init)(VP9DSPContext *dsp) 1087{ 1088#define init_intra_pred_bd_aware(tx, sz) \ 1089 dsp->intra_pred[tx][TM_VP8_PRED] = tm_##sz##_c; \ 1090 dsp->intra_pred[tx][DC_128_PRED] = dc_128_##sz##_c; \ 1091 dsp->intra_pred[tx][DC_127_PRED] = dc_127_##sz##_c; \ 1092 dsp->intra_pred[tx][DC_129_PRED] = dc_129_##sz##_c 1093 1094#if BIT_DEPTH == 12 1095 ff_vp9dsp_intrapred_init_10(dsp); 1096#define init_intra_pred(tx, sz) \ 1097 init_intra_pred_bd_aware(tx, sz) 1098#else 1099 #define init_intra_pred(tx, sz) \ 1100 dsp->intra_pred[tx][VERT_PRED] = vert_##sz##_c; \ 1101 dsp->intra_pred[tx][HOR_PRED] = hor_##sz##_c; \ 1102 dsp->intra_pred[tx][DC_PRED] = dc_##sz##_c; \ 1103 dsp->intra_pred[tx][DIAG_DOWN_LEFT_PRED] = diag_downleft_##sz##_c; \ 1104 dsp->intra_pred[tx][DIAG_DOWN_RIGHT_PRED] = diag_downright_##sz##_c; \ 1105 dsp->intra_pred[tx][VERT_RIGHT_PRED] = vert_right_##sz##_c; \ 1106 dsp->intra_pred[tx][HOR_DOWN_PRED] = hor_down_##sz##_c; \ 1107 dsp->intra_pred[tx][VERT_LEFT_PRED] = vert_left_##sz##_c; \ 1108 dsp->intra_pred[tx][HOR_UP_PRED] = hor_up_##sz##_c; \ 1109 dsp->intra_pred[tx][LEFT_DC_PRED] = dc_left_##sz##_c; \ 1110 dsp->intra_pred[tx][TOP_DC_PRED] = dc_top_##sz##_c; \ 1111 init_intra_pred_bd_aware(tx, sz) 1112#endif 1113 1114 init_intra_pred(TX_4X4, 4x4); 1115 init_intra_pred(TX_8X8, 8x8); 1116 init_intra_pred(TX_16X16, 16x16); 1117 init_intra_pred(TX_32X32, 32x32); 1118 1119#undef init_intra_pred 1120#undef init_intra_pred_bd_aware 1121} 1122 1123#define itxfm_wrapper(type_a, type_b, sz, bits, has_dconly) \ 1124static void type_a##_##type_b##_##sz##x##sz##_add_c(uint8_t *_dst, \ 1125 ptrdiff_t stride, \ 1126 int16_t *_block, int eob) \ 1127{ \ 1128 int i, j; \ 1129 pixel *dst = (pixel *) _dst; \ 1130 dctcoef *block = (dctcoef *) _block, tmp[sz * sz], out[sz]; \ 1131\ 1132 stride /= sizeof(pixel); \ 1133 if (has_dconly && eob == 1) { \ 1134 const int t = ((((dctint) block[0] * 11585 + (1 << 13)) >> 14) \ 1135 * 11585 + (1 << 13)) >> 14; \ 1136 block[0] = 0; \ 1137 for (i = 0; i < sz; i++) { \ 1138 for (j = 0; j < sz; j++) \ 1139 dst[j * stride] = av_clip_pixel(dst[j * stride] + \ 1140 (bits ? \ 1141 (int)(t + (1U << (bits - 1))) >> bits : \ 1142 t)); \ 1143 dst++; \ 1144 } \ 1145 return; \ 1146 } \ 1147\ 1148 for (i = 0; i < sz; i++) \ 1149 type_a##sz##_1d(block + i, sz, tmp + i * sz, 0); \ 1150 memset(block, 0, sz * sz * sizeof(*block)); \ 1151 for (i = 0; i < sz; i++) { \ 1152 type_b##sz##_1d(tmp + i, sz, out, 1); \ 1153 for (j = 0; j < sz; j++) \ 1154 dst[j * stride] = av_clip_pixel(dst[j * stride] + \ 1155 (bits ? \ 1156 (int)(out[j] + (1U << (bits - 1))) >> bits : \ 1157 out[j])); \ 1158 dst++; \ 1159 } \ 1160} 1161 1162#define itxfm_wrap(sz, bits) \ 1163itxfm_wrapper(idct, idct, sz, bits, 1) \ 1164itxfm_wrapper(iadst, idct, sz, bits, 0) \ 1165itxfm_wrapper(idct, iadst, sz, bits, 0) \ 1166itxfm_wrapper(iadst, iadst, sz, bits, 0) 1167 1168#define IN(x) ((dctint) in[(x) * stride]) 1169 1170static av_always_inline void idct4_1d(const dctcoef *in, ptrdiff_t stride, 1171 dctcoef *out, int pass) 1172{ 1173 dctint t0, t1, t2, t3; 1174 1175 t0 = ((IN(0) + IN(2)) * 11585 + (1 << 13)) >> 14; 1176 t1 = ((IN(0) - IN(2)) * 11585 + (1 << 13)) >> 14; 1177 t2 = (IN(1) * 6270 - IN(3) * 15137 + (1 << 13)) >> 14; 1178 t3 = (IN(1) * 15137 + IN(3) * 6270 + (1 << 13)) >> 14; 1179 1180 out[0] = t0 + t3; 1181 out[1] = t1 + t2; 1182 out[2] = t1 - t2; 1183 out[3] = t0 - t3; 1184} 1185 1186static av_always_inline void iadst4_1d(const dctcoef *in, ptrdiff_t stride, 1187 dctcoef *out, int pass) 1188{ 1189 dctint t0, t1, t2, t3; 1190 1191 t0 = 5283 * IN(0) + 15212 * IN(2) + 9929 * IN(3); 1192 t1 = 9929 * IN(0) - 5283 * IN(2) - 15212 * IN(3); 1193 t2 = 13377 * (IN(0) - IN(2) + IN(3)); 1194 t3 = 13377 * IN(1); 1195 1196 out[0] = (t0 + t3 + (1 << 13)) >> 14; 1197 out[1] = (t1 + t3 + (1 << 13)) >> 14; 1198 out[2] = (t2 + (1 << 13)) >> 14; 1199 out[3] = (t0 + t1 - t3 + (1 << 13)) >> 14; 1200} 1201 1202itxfm_wrap(4, 4) 1203 1204static av_always_inline void idct8_1d(const dctcoef *in, ptrdiff_t stride, 1205 dctcoef *out, int pass) 1206{ 1207 dctint t0, t0a, t1, t1a, t2, t2a, t3, t3a, t4, t4a, t5, t5a, t6, t6a, t7, t7a; 1208 1209 t0a = ((IN(0) + IN(4)) * 11585 + (1 << 13)) >> 14; 1210 t1a = ((IN(0) - IN(4)) * 11585 + (1 << 13)) >> 14; 1211 t2a = (IN(2) * 6270 - IN(6) * 15137 + (1 << 13)) >> 14; 1212 t3a = (IN(2) * 15137 + IN(6) * 6270 + (1 << 13)) >> 14; 1213 t4a = (IN(1) * 3196 - IN(7) * 16069 + (1 << 13)) >> 14; 1214 t5a = (IN(5) * 13623 - IN(3) * 9102 + (1 << 13)) >> 14; 1215 t6a = (IN(5) * 9102 + IN(3) * 13623 + (1 << 13)) >> 14; 1216 t7a = (IN(1) * 16069 + IN(7) * 3196 + (1 << 13)) >> 14; 1217 1218 t0 = t0a + t3a; 1219 t1 = t1a + t2a; 1220 t2 = t1a - t2a; 1221 t3 = t0a - t3a; 1222 t4 = t4a + t5a; 1223 t5a = t4a - t5a; 1224 t7 = t7a + t6a; 1225 t6a = t7a - t6a; 1226 1227 t5 = ((t6a - t5a) * 11585 + (1 << 13)) >> 14; 1228 t6 = ((t6a + t5a) * 11585 + (1 << 13)) >> 14; 1229 1230 out[0] = t0 + t7; 1231 out[1] = t1 + t6; 1232 out[2] = t2 + t5; 1233 out[3] = t3 + t4; 1234 out[4] = t3 - t4; 1235 out[5] = t2 - t5; 1236 out[6] = t1 - t6; 1237 out[7] = t0 - t7; 1238} 1239 1240static av_always_inline void iadst8_1d(const dctcoef *in, ptrdiff_t stride, 1241 dctcoef *out, int pass) 1242{ 1243 dctint t0, t0a, t1, t1a, t2, t2a, t3, t3a, t4, t4a, t5, t5a, t6, t6a, t7, t7a; 1244 1245 t0a = 16305 * IN(7) + 1606 * IN(0); 1246 t1a = 1606 * IN(7) - 16305 * IN(0); 1247 t2a = 14449 * IN(5) + 7723 * IN(2); 1248 t3a = 7723 * IN(5) - 14449 * IN(2); 1249 t4a = 10394 * IN(3) + 12665 * IN(4); 1250 t5a = 12665 * IN(3) - 10394 * IN(4); 1251 t6a = 4756 * IN(1) + 15679 * IN(6); 1252 t7a = 15679 * IN(1) - 4756 * IN(6); 1253 1254 t0 = (t0a + t4a + (1 << 13)) >> 14; 1255 t1 = (t1a + t5a + (1 << 13)) >> 14; 1256 t2 = (t2a + t6a + (1 << 13)) >> 14; 1257 t3 = (t3a + t7a + (1 << 13)) >> 14; 1258 t4 = (t0a - t4a + (1 << 13)) >> 14; 1259 t5 = (t1a - t5a + (1 << 13)) >> 14; 1260 t6 = (t2a - t6a + (1 << 13)) >> 14; 1261 t7 = (t3a - t7a + (1 << 13)) >> 14; 1262 1263 t4a = 15137U * t4 + 6270U * t5; 1264 t5a = 6270U * t4 - 15137U * t5; 1265 t6a = 15137U * t7 - 6270U * t6; 1266 t7a = 6270U * t7 + 15137U * t6; 1267 1268 out[0] = t0 + t2; 1269 out[7] = -(t1 + t3); 1270 t2 = t0 - t2; 1271 t3 = t1 - t3; 1272 1273 out[1] = -((dctint)((1U << 13) + t4a + t6a) >> 14); 1274 out[6] = (dctint)((1U << 13) + t5a + t7a) >> 14; 1275 t6 = (dctint)((1U << 13) + t4a - t6a) >> 14; 1276 t7 = (dctint)((1U << 13) + t5a - t7a) >> 14; 1277 1278 out[3] = -((dctint)((t2 + t3) * 11585U + (1 << 13)) >> 14); 1279 out[4] = (dctint)((t2 - t3) * 11585U + (1 << 13)) >> 14; 1280 out[2] = (dctint)((t6 + t7) * 11585U + (1 << 13)) >> 14; 1281 out[5] = -((dctint)((t6 - t7) * 11585U + (1 << 13)) >> 14); 1282} 1283 1284itxfm_wrap(8, 5) 1285 1286static av_always_inline void idct16_1d(const dctcoef *in, ptrdiff_t stride, 1287 dctcoef *out, int pass) 1288{ 1289 dctint t0, t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11, t12, t13, t14, t15; 1290 dctint t0a, t1a, t2a, t3a, t4a, t5a, t6a, t7a; 1291 dctint t8a, t9a, t10a, t11a, t12a, t13a, t14a, t15a; 1292 1293 t0a = (dctint)((IN(0) + IN(8)) * 11585U + (1 << 13)) >> 14; 1294 t1a = (dctint)((IN(0) - IN(8)) * 11585U + (1 << 13)) >> 14; 1295 t2a = (dctint)(IN(4) * 6270U - IN(12) * 15137U + (1 << 13)) >> 14; 1296 t3a = (dctint)(IN(4) * 15137U + IN(12) * 6270U + (1 << 13)) >> 14; 1297 t4a = (dctint)(IN(2) * 3196U - IN(14) * 16069U + (1 << 13)) >> 14; 1298 t7a = (dctint)(IN(2) * 16069U + IN(14) * 3196U + (1 << 13)) >> 14; 1299 t5a = (dctint)(IN(10) * 13623U - IN(6) * 9102U + (1 << 13)) >> 14; 1300 t6a = (dctint)(IN(10) * 9102U + IN(6) * 13623U + (1 << 13)) >> 14; 1301 t8a = (dctint)(IN(1) * 1606U - IN(15) * 16305U + (1 << 13)) >> 14; 1302 t15a = (dctint)(IN(1) * 16305U + IN(15) * 1606U + (1 << 13)) >> 14; 1303 t9a = (dctint)(IN(9) * 12665U - IN(7) * 10394U + (1 << 13)) >> 14; 1304 t14a = (dctint)(IN(9) * 10394U + IN(7) * 12665U + (1 << 13)) >> 14; 1305 t10a = (dctint)(IN(5) * 7723U - IN(11) * 14449U + (1 << 13)) >> 14; 1306 t13a = (dctint)(IN(5) * 14449U + IN(11) * 7723U + (1 << 13)) >> 14; 1307 t11a = (dctint)(IN(13) * 15679U - IN(3) * 4756U + (1 << 13)) >> 14; 1308 t12a = (dctint)(IN(13) * 4756U + IN(3) * 15679U + (1 << 13)) >> 14; 1309 1310 t0 = t0a + t3a; 1311 t1 = t1a + t2a; 1312 t2 = t1a - t2a; 1313 t3 = t0a - t3a; 1314 t4 = t4a + t5a; 1315 t5 = t4a - t5a; 1316 t6 = t7a - t6a; 1317 t7 = t7a + t6a; 1318 t8 = t8a + t9a; 1319 t9 = t8a - t9a; 1320 t10 = t11a - t10a; 1321 t11 = t11a + t10a; 1322 t12 = t12a + t13a; 1323 t13 = t12a - t13a; 1324 t14 = t15a - t14a; 1325 t15 = t15a + t14a; 1326 1327 t5a = (dctint)((t6 - t5) * 11585U + (1 << 13)) >> 14; 1328 t6a = (dctint)((t6 + t5) * 11585U + (1 << 13)) >> 14; 1329 t9a = (dctint)( t14 * 6270U - t9 * 15137U + (1 << 13)) >> 14; 1330 t14a = (dctint)( t14 * 15137U + t9 * 6270U + (1 << 13)) >> 14; 1331 t10a = (dctint)(-(t13 * 15137U + t10 * 6270U) + (1 << 13)) >> 14; 1332 t13a = (dctint)( t13 * 6270U - t10 * 15137U + (1 << 13)) >> 14; 1333 1334 t0a = t0 + t7; 1335 t1a = t1 + t6a; 1336 t2a = t2 + t5a; 1337 t3a = t3 + t4; 1338 t4 = t3 - t4; 1339 t5 = t2 - t5a; 1340 t6 = t1 - t6a; 1341 t7 = t0 - t7; 1342 t8a = t8 + t11; 1343 t9 = t9a + t10a; 1344 t10 = t9a - t10a; 1345 t11a = t8 - t11; 1346 t12a = t15 - t12; 1347 t13 = t14a - t13a; 1348 t14 = t14a + t13a; 1349 t15a = t15 + t12; 1350 1351 t10a = (dctint)((t13 - t10) * 11585U + (1 << 13)) >> 14; 1352 t13a = (dctint)((t13 + t10) * 11585U + (1 << 13)) >> 14; 1353 t11 = (dctint)((t12a - t11a) * 11585U + (1 << 13)) >> 14; 1354 t12 = (dctint)((t12a + t11a) * 11585U + (1 << 13)) >> 14; 1355 1356 out[ 0] = t0a + t15a; 1357 out[ 1] = t1a + t14; 1358 out[ 2] = t2a + t13a; 1359 out[ 3] = t3a + t12; 1360 out[ 4] = t4 + t11; 1361 out[ 5] = t5 + t10a; 1362 out[ 6] = t6 + t9; 1363 out[ 7] = t7 + t8a; 1364 out[ 8] = t7 - t8a; 1365 out[ 9] = t6 - t9; 1366 out[10] = t5 - t10a; 1367 out[11] = t4 - t11; 1368 out[12] = t3a - t12; 1369 out[13] = t2a - t13a; 1370 out[14] = t1a - t14; 1371 out[15] = t0a - t15a; 1372} 1373 1374static av_always_inline void iadst16_1d(const dctcoef *in, ptrdiff_t stride, 1375 dctcoef *out, int pass) 1376{ 1377 dctint t0, t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11, t12, t13, t14, t15; 1378 dctint t0a, t1a, t2a, t3a, t4a, t5a, t6a, t7a; 1379 dctint t8a, t9a, t10a, t11a, t12a, t13a, t14a, t15a; 1380 1381 t0 = IN(15) * 16364U + IN(0) * 804U; 1382 t1 = IN(15) * 804U - IN(0) * 16364U; 1383 t2 = IN(13) * 15893U + IN(2) * 3981U; 1384 t3 = IN(13) * 3981U - IN(2) * 15893U; 1385 t4 = IN(11) * 14811U + IN(4) * 7005U; 1386 t5 = IN(11) * 7005U - IN(4) * 14811U; 1387 t6 = IN(9) * 13160U + IN(6) * 9760U; 1388 t7 = IN(9) * 9760U - IN(6) * 13160U; 1389 t8 = IN(7) * 11003U + IN(8) * 12140U; 1390 t9 = IN(7) * 12140U - IN(8) * 11003U; 1391 t10 = IN(5) * 8423U + IN(10) * 14053U; 1392 t11 = IN(5) * 14053U - IN(10) * 8423U; 1393 t12 = IN(3) * 5520U + IN(12) * 15426U; 1394 t13 = IN(3) * 15426U - IN(12) * 5520U; 1395 t14 = IN(1) * 2404U + IN(14) * 16207U; 1396 t15 = IN(1) * 16207U - IN(14) * 2404U; 1397 1398 t0a = (dctint)((1U << 13) + t0 + t8 ) >> 14; 1399 t1a = (dctint)((1U << 13) + t1 + t9 ) >> 14; 1400 t2a = (dctint)((1U << 13) + t2 + t10) >> 14; 1401 t3a = (dctint)((1U << 13) + t3 + t11) >> 14; 1402 t4a = (dctint)((1U << 13) + t4 + t12) >> 14; 1403 t5a = (dctint)((1U << 13) + t5 + t13) >> 14; 1404 t6a = (dctint)((1U << 13) + t6 + t14) >> 14; 1405 t7a = (dctint)((1U << 13) + t7 + t15) >> 14; 1406 t8a = (dctint)((1U << 13) + t0 - t8 ) >> 14; 1407 t9a = (dctint)((1U << 13) + t1 - t9 ) >> 14; 1408 t10a = (dctint)((1U << 13) + t2 - t10) >> 14; 1409 t11a = (dctint)((1U << 13) + t3 - t11) >> 14; 1410 t12a = (dctint)((1U << 13) + t4 - t12) >> 14; 1411 t13a = (dctint)((1U << 13) + t5 - t13) >> 14; 1412 t14a = (dctint)((1U << 13) + t6 - t14) >> 14; 1413 t15a = (dctint)((1U << 13) + t7 - t15) >> 14; 1414 1415 t8 = t8a * 16069U + t9a * 3196U; 1416 t9 = t8a * 3196U - t9a * 16069U; 1417 t10 = t10a * 9102U + t11a * 13623U; 1418 t11 = t10a * 13623U - t11a * 9102U; 1419 t12 = t13a * 16069U - t12a * 3196U; 1420 t13 = t13a * 3196U + t12a * 16069U; 1421 t14 = t15a * 9102U - t14a * 13623U; 1422 t15 = t15a * 13623U + t14a * 9102U; 1423 1424 t0 = t0a + t4a; 1425 t1 = t1a + t5a; 1426 t2 = t2a + t6a; 1427 t3 = t3a + t7a; 1428 t4 = t0a - t4a; 1429 t5 = t1a - t5a; 1430 t6 = t2a - t6a; 1431 t7 = t3a - t7a; 1432 t8a = (dctint)((1U << 13) + t8 + t12) >> 14; 1433 t9a = (dctint)((1U << 13) + t9 + t13) >> 14; 1434 t10a = (dctint)((1U << 13) + t10 + t14) >> 14; 1435 t11a = (dctint)((1U << 13) + t11 + t15) >> 14; 1436 t12a = (dctint)((1U << 13) + t8 - t12) >> 14; 1437 t13a = (dctint)((1U << 13) + t9 - t13) >> 14; 1438 t14a = (dctint)((1U << 13) + t10 - t14) >> 14; 1439 t15a = (dctint)((1U << 13) + t11 - t15) >> 14; 1440 1441 t4a = t4 * 15137U + t5 * 6270U; 1442 t5a = t4 * 6270U - t5 * 15137U; 1443 t6a = t7 * 15137U - t6 * 6270U; 1444 t7a = t7 * 6270U + t6 * 15137U; 1445 t12 = t12a * 15137U + t13a * 6270U; 1446 t13 = t12a * 6270U - t13a * 15137U; 1447 t14 = t15a * 15137U - t14a * 6270U; 1448 t15 = t15a * 6270U + t14a * 15137U; 1449 1450 out[ 0] = t0 + t2; 1451 out[15] = -(t1 + t3); 1452 t2a = t0 - t2; 1453 t3a = t1 - t3; 1454 out[ 3] = -((dctint)((1U << 13) + t4a + t6a) >> 14); 1455 out[12] = (dctint)((1U << 13) + t5a + t7a) >> 14; 1456 t6 = (dctint)((1U << 13) + t4a - t6a) >> 14; 1457 t7 = (dctint)((1U << 13) + t5a - t7a) >> 14; 1458 out[ 1] = -(t8a + t10a); 1459 out[14] = t9a + t11a; 1460 t10 = t8a - t10a; 1461 t11 = t9a - t11a; 1462 out[ 2] = (dctint)((1U << 13) + t12 + t14) >> 14; 1463 out[13] = -((dctint)((1U << 13) + t13 + t15) >> 14); 1464 t14a = (dctint)((1U << 13) + t12 - t14) >> 14; 1465 t15a = (dctint)((1U << 13) + t13 - t15) >> 14; 1466 1467 out[ 7] = (dctint)(-(t2a + t3a) * 11585U + (1 << 13)) >> 14; 1468 out[ 8] = (dctint)( (t2a - t3a) * 11585U + (1 << 13)) >> 14; 1469 out[ 4] = (dctint)( (t7 + t6) * 11585U + (1 << 13)) >> 14; 1470 out[11] = (dctint)( (t7 - t6) * 11585U + (1 << 13)) >> 14; 1471 out[ 6] = (dctint)( (t11 + t10) * 11585U + (1 << 13)) >> 14; 1472 out[ 9] = (dctint)( (t11 - t10) * 11585U + (1 << 13)) >> 14; 1473 out[ 5] = (dctint)(-(t14a + t15a) * 11585U + (1 << 13)) >> 14; 1474 out[10] = (dctint)( (t14a - t15a) * 11585U + (1 << 13)) >> 14; 1475} 1476 1477itxfm_wrap(16, 6) 1478 1479static av_always_inline void idct32_1d(const dctcoef *in, ptrdiff_t stride, 1480 dctcoef *out, int pass) 1481{ 1482 dctint t0a = (dctint)((IN(0) + IN(16)) * 11585U + (1 << 13)) >> 14; 1483 dctint t1a = (dctint)((IN(0) - IN(16)) * 11585U + (1 << 13)) >> 14; 1484 dctint t2a = (dctint)(IN( 8) * 6270U - IN(24) * 15137U + (1 << 13)) >> 14; 1485 dctint t3a = (dctint)(IN( 8) * 15137U + IN(24) * 6270U + (1 << 13)) >> 14; 1486 dctint t4a = (dctint)(IN( 4) * 3196U - IN(28) * 16069U + (1 << 13)) >> 14; 1487 dctint t7a = (dctint)(IN( 4) * 16069U + IN(28) * 3196U + (1 << 13)) >> 14; 1488 dctint t5a = (dctint)(IN(20) * 13623U - IN(12) * 9102U + (1 << 13)) >> 14; 1489 dctint t6a = (dctint)(IN(20) * 9102U + IN(12) * 13623U + (1 << 13)) >> 14; 1490 dctint t8a = (dctint)(IN( 2) * 1606U - IN(30) * 16305U + (1 << 13)) >> 14; 1491 dctint t15a = (dctint)(IN( 2) * 16305U + IN(30) * 1606U + (1 << 13)) >> 14; 1492 dctint t9a = (dctint)(IN(18) * 12665U - IN(14) * 10394U + (1 << 13)) >> 14; 1493 dctint t14a = (dctint)(IN(18) * 10394U + IN(14) * 12665U + (1 << 13)) >> 14; 1494 dctint t10a = (dctint)(IN(10) * 7723U - IN(22) * 14449U + (1 << 13)) >> 14; 1495 dctint t13a = (dctint)(IN(10) * 14449U + IN(22) * 7723U + (1 << 13)) >> 14; 1496 dctint t11a = (dctint)(IN(26) * 15679U - IN( 6) * 4756U + (1 << 13)) >> 14; 1497 dctint t12a = (dctint)(IN(26) * 4756U + IN( 6) * 15679U + (1 << 13)) >> 14; 1498 dctint t16a = (dctint)(IN( 1) * 804U - IN(31) * 16364U + (1 << 13)) >> 14; 1499 dctint t31a = (dctint)(IN( 1) * 16364U + IN(31) * 804U + (1 << 13)) >> 14; 1500 dctint t17a = (dctint)(IN(17) * 12140U - IN(15) * 11003U + (1 << 13)) >> 14; 1501 dctint t30a = (dctint)(IN(17) * 11003U + IN(15) * 12140U + (1 << 13)) >> 14; 1502 dctint t18a = (dctint)(IN( 9) * 7005U - IN(23) * 14811U + (1 << 13)) >> 14; 1503 dctint t29a = (dctint)(IN( 9) * 14811U + IN(23) * 7005U + (1 << 13)) >> 14; 1504 dctint t19a = (dctint)(IN(25) * 15426U - IN( 7) * 5520U + (1 << 13)) >> 14; 1505 dctint t28a = (dctint)(IN(25) * 5520U + IN( 7) * 15426U + (1 << 13)) >> 14; 1506 dctint t20a = (dctint)(IN( 5) * 3981U - IN(27) * 15893U + (1 << 13)) >> 14; 1507 dctint t27a = (dctint)(IN( 5) * 15893U + IN(27) * 3981U + (1 << 13)) >> 14; 1508 dctint t21a = (dctint)(IN(21) * 14053U - IN(11) * 8423U + (1 << 13)) >> 14; 1509 dctint t26a = (dctint)(IN(21) * 8423U + IN(11) * 14053U + (1 << 13)) >> 14; 1510 dctint t22a = (dctint)(IN(13) * 9760U - IN(19) * 13160U + (1 << 13)) >> 14; 1511 dctint t25a = (dctint)(IN(13) * 13160U + IN(19) * 9760U + (1 << 13)) >> 14; 1512 dctint t23a = (dctint)(IN(29) * 16207U - IN( 3) * 2404U + (1 << 13)) >> 14; 1513 dctint t24a = (dctint)(IN(29) * 2404U + IN( 3) * 16207U + (1 << 13)) >> 14; 1514 1515 dctint t0 = t0a + t3a; 1516 dctint t1 = t1a + t2a; 1517 dctint t2 = t1a - t2a; 1518 dctint t3 = t0a - t3a; 1519 dctint t4 = t4a + t5a; 1520 dctint t5 = t4a - t5a; 1521 dctint t6 = t7a - t6a; 1522 dctint t7 = t7a + t6a; 1523 dctint t8 = t8a + t9a; 1524 dctint t9 = t8a - t9a; 1525 dctint t10 = t11a - t10a; 1526 dctint t11 = t11a + t10a; 1527 dctint t12 = t12a + t13a; 1528 dctint t13 = t12a - t13a; 1529 dctint t14 = t15a - t14a; 1530 dctint t15 = t15a + t14a; 1531 dctint t16 = t16a + t17a; 1532 dctint t17 = t16a - t17a; 1533 dctint t18 = t19a - t18a; 1534 dctint t19 = t19a + t18a; 1535 dctint t20 = t20a + t21a; 1536 dctint t21 = t20a - t21a; 1537 dctint t22 = t23a - t22a; 1538 dctint t23 = t23a + t22a; 1539 dctint t24 = t24a + t25a; 1540 dctint t25 = t24a - t25a; 1541 dctint t26 = t27a - t26a; 1542 dctint t27 = t27a + t26a; 1543 dctint t28 = t28a + t29a; 1544 dctint t29 = t28a - t29a; 1545 dctint t30 = t31a - t30a; 1546 dctint t31 = t31a + t30a; 1547 1548 t5a = (dctint)((t6 - t5) * 11585U + (1 << 13)) >> 14; 1549 t6a = (dctint)((t6 + t5) * 11585U + (1 << 13)) >> 14; 1550 t9a = (dctint)( t14 * 6270U - t9 * 15137U + (1 << 13)) >> 14; 1551 t14a = (dctint)( t14 * 15137U + t9 * 6270U + (1 << 13)) >> 14; 1552 t10a = (dctint)(-(t13 * 15137U + t10 * 6270U) + (1 << 13)) >> 14; 1553 t13a = (dctint)( t13 * 6270U - t10 * 15137U + (1 << 13)) >> 14; 1554 t17a = (dctint)( t30 * 3196U - t17 * 16069U + (1 << 13)) >> 14; 1555 t30a = (dctint)( t30 * 16069U + t17 * 3196U + (1 << 13)) >> 14; 1556 t18a = (dctint)(-(t29 * 16069U + t18 * 3196U) + (1 << 13)) >> 14; 1557 t29a = (dctint)( t29 * 3196U - t18 * 16069U + (1 << 13)) >> 14; 1558 t21a = (dctint)( t26 * 13623U - t21 * 9102U + (1 << 13)) >> 14; 1559 t26a = (dctint)( t26 * 9102U + t21 * 13623U + (1 << 13)) >> 14; 1560 t22a = (dctint)(-(t25 * 9102U + t22 * 13623U) + (1 << 13)) >> 14; 1561 t25a = (dctint)( t25 * 13623U - t22 * 9102U + (1 << 13)) >> 14; 1562 1563 t0a = t0 + t7; 1564 t1a = t1 + t6a; 1565 t2a = t2 + t5a; 1566 t3a = t3 + t4; 1567 t4a = t3 - t4; 1568 t5 = t2 - t5a; 1569 t6 = t1 - t6a; 1570 t7a = t0 - t7; 1571 t8a = t8 + t11; 1572 t9 = t9a + t10a; 1573 t10 = t9a - t10a; 1574 t11a = t8 - t11; 1575 t12a = t15 - t12; 1576 t13 = t14a - t13a; 1577 t14 = t14a + t13a; 1578 t15a = t15 + t12; 1579 t16a = t16 + t19; 1580 t17 = t17a + t18a; 1581 t18 = t17a - t18a; 1582 t19a = t16 - t19; 1583 t20a = t23 - t20; 1584 t21 = t22a - t21a; 1585 t22 = t22a + t21a; 1586 t23a = t23 + t20; 1587 t24a = t24 + t27; 1588 t25 = t25a + t26a; 1589 t26 = t25a - t26a; 1590 t27a = t24 - t27; 1591 t28a = t31 - t28; 1592 t29 = t30a - t29a; 1593 t30 = t30a + t29a; 1594 t31a = t31 + t28; 1595 1596 t10a = (dctint)((t13 - t10) * 11585U + (1 << 13)) >> 14; 1597 t13a = (dctint)((t13 + t10) * 11585U + (1 << 13)) >> 14; 1598 t11 = (dctint)((t12a - t11a) * 11585U + (1 << 13)) >> 14; 1599 t12 = (dctint)((t12a + t11a) * 11585U + (1 << 13)) >> 14; 1600 t18a = (dctint)( t29 * 6270U - t18 * 15137U + (1 << 13)) >> 14; 1601 t29a = (dctint)( t29 * 15137U + t18 * 6270U + (1 << 13)) >> 14; 1602 t19 = (dctint)( t28a * 6270U - t19a * 15137U + (1 << 13)) >> 14; 1603 t28 = (dctint)( t28a * 15137U + t19a * 6270U + (1 << 13)) >> 14; 1604 t20 = (dctint)(-(t27a * 15137U + t20a * 6270U) + (1 << 13)) >> 14; 1605 t27 = (dctint)( t27a * 6270U - t20a * 15137U + (1 << 13)) >> 14; 1606 t21a = (dctint)(-(t26 * 15137U + t21 * 6270U) + (1 << 13)) >> 14; 1607 t26a = (dctint)( t26 * 6270U - t21 * 15137U + (1 << 13)) >> 14; 1608 1609 t0 = t0a + t15a; 1610 t1 = t1a + t14; 1611 t2 = t2a + t13a; 1612 t3 = t3a + t12; 1613 t4 = t4a + t11; 1614 t5a = t5 + t10a; 1615 t6a = t6 + t9; 1616 t7 = t7a + t8a; 1617 t8 = t7a - t8a; 1618 t9a = t6 - t9; 1619 t10 = t5 - t10a; 1620 t11a = t4a - t11; 1621 t12a = t3a - t12; 1622 t13 = t2a - t13a; 1623 t14a = t1a - t14; 1624 t15 = t0a - t15a; 1625 t16 = t16a + t23a; 1626 t17a = t17 + t22; 1627 t18 = t18a + t21a; 1628 t19a = t19 + t20; 1629 t20a = t19 - t20; 1630 t21 = t18a - t21a; 1631 t22a = t17 - t22; 1632 t23 = t16a - t23a; 1633 t24 = t31a - t24a; 1634 t25a = t30 - t25; 1635 t26 = t29a - t26a; 1636 t27a = t28 - t27; 1637 t28a = t28 + t27; 1638 t29 = t29a + t26a; 1639 t30a = t30 + t25; 1640 t31 = t31a + t24a; 1641 1642 t20 = (dctint)((t27a - t20a) * 11585U + (1 << 13)) >> 14; 1643 t27 = (dctint)((t27a + t20a) * 11585U + (1 << 13)) >> 14; 1644 t21a = (dctint)((t26 - t21 ) * 11585U + (1 << 13)) >> 14; 1645 t26a = (dctint)((t26 + t21 ) * 11585U + (1 << 13)) >> 14; 1646 t22 = (dctint)((t25a - t22a) * 11585U + (1 << 13)) >> 14; 1647 t25 = (dctint)((t25a + t22a) * 11585U + (1 << 13)) >> 14; 1648 t23a = (dctint)((t24 - t23 ) * 11585U + (1 << 13)) >> 14; 1649 t24a = (dctint)((t24 + t23 ) * 11585U + (1 << 13)) >> 14; 1650 1651 out[ 0] = t0 + t31; 1652 out[ 1] = t1 + t30a; 1653 out[ 2] = t2 + t29; 1654 out[ 3] = t3 + t28a; 1655 out[ 4] = t4 + t27; 1656 out[ 5] = t5a + t26a; 1657 out[ 6] = t6a + t25; 1658 out[ 7] = t7 + t24a; 1659 out[ 8] = t8 + t23a; 1660 out[ 9] = t9a + t22; 1661 out[10] = t10 + t21a; 1662 out[11] = t11a + t20; 1663 out[12] = t12a + t19a; 1664 out[13] = t13 + t18; 1665 out[14] = t14a + t17a; 1666 out[15] = t15 + t16; 1667 out[16] = t15 - t16; 1668 out[17] = t14a - t17a; 1669 out[18] = t13 - t18; 1670 out[19] = t12a - t19a; 1671 out[20] = t11a - t20; 1672 out[21] = t10 - t21a; 1673 out[22] = t9a - t22; 1674 out[23] = t8 - t23a; 1675 out[24] = t7 - t24a; 1676 out[25] = t6a - t25; 1677 out[26] = t5a - t26a; 1678 out[27] = t4 - t27; 1679 out[28] = t3 - t28a; 1680 out[29] = t2 - t29; 1681 out[30] = t1 - t30a; 1682 out[31] = t0 - t31; 1683} 1684 1685itxfm_wrapper(idct, idct, 32, 6, 1) 1686 1687static av_always_inline void iwht4_1d(const dctcoef *in, ptrdiff_t stride, 1688 dctcoef *out, int pass) 1689{ 1690 int t0, t1, t2, t3, t4; 1691 1692 if (pass == 0) { 1693 t0 = IN(0) >> 2; 1694 t1 = IN(3) >> 2; 1695 t2 = IN(1) >> 2; 1696 t3 = IN(2) >> 2; 1697 } else { 1698 t0 = IN(0); 1699 t1 = IN(3); 1700 t2 = IN(1); 1701 t3 = IN(2); 1702 } 1703 1704 t0 += t2; 1705 t3 -= t1; 1706 t4 = (t0 - t3) >> 1; 1707 t1 = t4 - t1; 1708 t2 = t4 - t2; 1709 t0 -= t1; 1710 t3 += t2; 1711 1712 out[0] = t0; 1713 out[1] = t1; 1714 out[2] = t2; 1715 out[3] = t3; 1716} 1717 1718itxfm_wrapper(iwht, iwht, 4, 0, 0) 1719 1720#undef IN 1721#undef itxfm_wrapper 1722#undef itxfm_wrap 1723 1724static av_cold void vp9dsp_itxfm_init(VP9DSPContext *dsp) 1725{ 1726#define init_itxfm(tx, sz) \ 1727 dsp->itxfm_add[tx][DCT_DCT] = idct_idct_##sz##_add_c; \ 1728 dsp->itxfm_add[tx][DCT_ADST] = iadst_idct_##sz##_add_c; \ 1729 dsp->itxfm_add[tx][ADST_DCT] = idct_iadst_##sz##_add_c; \ 1730 dsp->itxfm_add[tx][ADST_ADST] = iadst_iadst_##sz##_add_c 1731 1732#define init_idct(tx, nm) \ 1733 dsp->itxfm_add[tx][DCT_DCT] = \ 1734 dsp->itxfm_add[tx][ADST_DCT] = \ 1735 dsp->itxfm_add[tx][DCT_ADST] = \ 1736 dsp->itxfm_add[tx][ADST_ADST] = nm##_add_c 1737 1738 init_itxfm(TX_4X4, 4x4); 1739 init_itxfm(TX_8X8, 8x8); 1740 init_itxfm(TX_16X16, 16x16); 1741 init_idct(TX_32X32, idct_idct_32x32); 1742 init_idct(4 /* lossless */, iwht_iwht_4x4); 1743 1744#undef init_itxfm 1745#undef init_idct 1746} 1747 1748static av_always_inline void loop_filter(pixel *dst, int E, int I, int H, 1749 ptrdiff_t stridea, ptrdiff_t strideb, 1750 int wd) 1751{ 1752 int i, F = 1 << (BIT_DEPTH - 8); 1753 1754 E <<= (BIT_DEPTH - 8); 1755 I <<= (BIT_DEPTH - 8); 1756 H <<= (BIT_DEPTH - 8); 1757 for (i = 0; i < 8; i++, dst += stridea) { 1758 int p7, p6, p5, p4; 1759 int p3 = dst[strideb * -4], p2 = dst[strideb * -3]; 1760 int p1 = dst[strideb * -2], p0 = dst[strideb * -1]; 1761 int q0 = dst[strideb * +0], q1 = dst[strideb * +1]; 1762 int q2 = dst[strideb * +2], q3 = dst[strideb * +3]; 1763 int q4, q5, q6, q7; 1764 int fm = FFABS(p3 - p2) <= I && FFABS(p2 - p1) <= I && 1765 FFABS(p1 - p0) <= I && FFABS(q1 - q0) <= I && 1766 FFABS(q2 - q1) <= I && FFABS(q3 - q2) <= I && 1767 FFABS(p0 - q0) * 2 + (FFABS(p1 - q1) >> 1) <= E; 1768 int flat8out, flat8in; 1769 1770 if (!fm) 1771 continue; 1772 1773 if (wd >= 16) { 1774 p7 = dst[strideb * -8]; 1775 p6 = dst[strideb * -7]; 1776 p5 = dst[strideb * -6]; 1777 p4 = dst[strideb * -5]; 1778 q4 = dst[strideb * +4]; 1779 q5 = dst[strideb * +5]; 1780 q6 = dst[strideb * +6]; 1781 q7 = dst[strideb * +7]; 1782 1783 flat8out = FFABS(p7 - p0) <= F && FFABS(p6 - p0) <= F && 1784 FFABS(p5 - p0) <= F && FFABS(p4 - p0) <= F && 1785 FFABS(q4 - q0) <= F && FFABS(q5 - q0) <= F && 1786 FFABS(q6 - q0) <= F && FFABS(q7 - q0) <= F; 1787 } 1788 1789 if (wd >= 8) 1790 flat8in = FFABS(p3 - p0) <= F && FFABS(p2 - p0) <= F && 1791 FFABS(p1 - p0) <= F && FFABS(q1 - q0) <= F && 1792 FFABS(q2 - q0) <= F && FFABS(q3 - q0) <= F; 1793 1794 if (wd >= 16 && flat8out && flat8in) { 1795 dst[strideb * -7] = (p7 + p7 + p7 + p7 + p7 + p7 + p7 + p6 * 2 + 1796 p5 + p4 + p3 + p2 + p1 + p0 + q0 + 8) >> 4; 1797 dst[strideb * -6] = (p7 + p7 + p7 + p7 + p7 + p7 + p6 + p5 * 2 + 1798 p4 + p3 + p2 + p1 + p0 + q0 + q1 + 8) >> 4; 1799 dst[strideb * -5] = (p7 + p7 + p7 + p7 + p7 + p6 + p5 + p4 * 2 + 1800 p3 + p2 + p1 + p0 + q0 + q1 + q2 + 8) >> 4; 1801 dst[strideb * -4] = (p7 + p7 + p7 + p7 + p6 + p5 + p4 + p3 * 2 + 1802 p2 + p1 + p0 + q0 + q1 + q2 + q3 + 8) >> 4; 1803 dst[strideb * -3] = (p7 + p7 + p7 + p6 + p5 + p4 + p3 + p2 * 2 + 1804 p1 + p0 + q0 + q1 + q2 + q3 + q4 + 8) >> 4; 1805 dst[strideb * -2] = (p7 + p7 + p6 + p5 + p4 + p3 + p2 + p1 * 2 + 1806 p0 + q0 + q1 + q2 + q3 + q4 + q5 + 8) >> 4; 1807 dst[strideb * -1] = (p7 + p6 + p5 + p4 + p3 + p2 + p1 + p0 * 2 + 1808 q0 + q1 + q2 + q3 + q4 + q5 + q6 + 8) >> 4; 1809 dst[strideb * +0] = (p6 + p5 + p4 + p3 + p2 + p1 + p0 + q0 * 2 + 1810 q1 + q2 + q3 + q4 + q5 + q6 + q7 + 8) >> 4; 1811 dst[strideb * +1] = (p5 + p4 + p3 + p2 + p1 + p0 + q0 + q1 * 2 + 1812 q2 + q3 + q4 + q5 + q6 + q7 + q7 + 8) >> 4; 1813 dst[strideb * +2] = (p4 + p3 + p2 + p1 + p0 + q0 + q1 + q2 * 2 + 1814 q3 + q4 + q5 + q6 + q7 + q7 + q7 + 8) >> 4; 1815 dst[strideb * +3] = (p3 + p2 + p1 + p0 + q0 + q1 + q2 + q3 * 2 + 1816 q4 + q5 + q6 + q7 + q7 + q7 + q7 + 8) >> 4; 1817 dst[strideb * +4] = (p2 + p1 + p0 + q0 + q1 + q2 + q3 + q4 * 2 + 1818 q5 + q6 + q7 + q7 + q7 + q7 + q7 + 8) >> 4; 1819 dst[strideb * +5] = (p1 + p0 + q0 + q1 + q2 + q3 + q4 + q5 * 2 + 1820 q6 + q7 + q7 + q7 + q7 + q7 + q7 + 8) >> 4; 1821 dst[strideb * +6] = (p0 + q0 + q1 + q2 + q3 + q4 + q5 + q6 * 2 + 1822 q7 + q7 + q7 + q7 + q7 + q7 + q7 + 8) >> 4; 1823 } else if (wd >= 8 && flat8in) { 1824 dst[strideb * -3] = (p3 + p3 + p3 + 2 * p2 + p1 + p0 + q0 + 4) >> 3; 1825 dst[strideb * -2] = (p3 + p3 + p2 + 2 * p1 + p0 + q0 + q1 + 4) >> 3; 1826 dst[strideb * -1] = (p3 + p2 + p1 + 2 * p0 + q0 + q1 + q2 + 4) >> 3; 1827 dst[strideb * +0] = (p2 + p1 + p0 + 2 * q0 + q1 + q2 + q3 + 4) >> 3; 1828 dst[strideb * +1] = (p1 + p0 + q0 + 2 * q1 + q2 + q3 + q3 + 4) >> 3; 1829 dst[strideb * +2] = (p0 + q0 + q1 + 2 * q2 + q3 + q3 + q3 + 4) >> 3; 1830 } else { 1831 int hev = FFABS(p1 - p0) > H || FFABS(q1 - q0) > H; 1832 1833 if (hev) { 1834 int f = av_clip_intp2(p1 - q1, BIT_DEPTH - 1), f1, f2; 1835 f = av_clip_intp2(3 * (q0 - p0) + f, BIT_DEPTH - 1); 1836 1837 f1 = FFMIN(f + 4, (1 << (BIT_DEPTH - 1)) - 1) >> 3; 1838 f2 = FFMIN(f + 3, (1 << (BIT_DEPTH - 1)) - 1) >> 3; 1839 1840 dst[strideb * -1] = av_clip_pixel(p0 + f2); 1841 dst[strideb * +0] = av_clip_pixel(q0 - f1); 1842 } else { 1843 int f = av_clip_intp2(3 * (q0 - p0), BIT_DEPTH - 1), f1, f2; 1844 1845 f1 = FFMIN(f + 4, (1 << (BIT_DEPTH - 1)) - 1) >> 3; 1846 f2 = FFMIN(f + 3, (1 << (BIT_DEPTH - 1)) - 1) >> 3; 1847 1848 dst[strideb * -1] = av_clip_pixel(p0 + f2); 1849 dst[strideb * +0] = av_clip_pixel(q0 - f1); 1850 1851 f = (f1 + 1) >> 1; 1852 dst[strideb * -2] = av_clip_pixel(p1 + f); 1853 dst[strideb * +1] = av_clip_pixel(q1 - f); 1854 } 1855 } 1856 } 1857} 1858 1859#define lf_8_fn(dir, wd, stridea, strideb) \ 1860static void loop_filter_##dir##_##wd##_8_c(uint8_t *_dst, \ 1861 ptrdiff_t stride, \ 1862 int E, int I, int H) \ 1863{ \ 1864 pixel *dst = (pixel *) _dst; \ 1865 stride /= sizeof(pixel); \ 1866 loop_filter(dst, E, I, H, stridea, strideb, wd); \ 1867} 1868 1869#define lf_8_fns(wd) \ 1870lf_8_fn(h, wd, stride, 1) \ 1871lf_8_fn(v, wd, 1, stride) 1872 1873lf_8_fns(4) 1874lf_8_fns(8) 1875lf_8_fns(16) 1876 1877#undef lf_8_fn 1878#undef lf_8_fns 1879 1880#define lf_16_fn(dir, stridea) \ 1881static void loop_filter_##dir##_16_16_c(uint8_t *dst, \ 1882 ptrdiff_t stride, \ 1883 int E, int I, int H) \ 1884{ \ 1885 loop_filter_##dir##_16_8_c(dst, stride, E, I, H); \ 1886 loop_filter_##dir##_16_8_c(dst + 8 * stridea, stride, E, I, H); \ 1887} 1888 1889lf_16_fn(h, stride) 1890lf_16_fn(v, sizeof(pixel)) 1891 1892#undef lf_16_fn 1893 1894#define lf_mix_fn(dir, wd1, wd2, stridea) \ 1895static void loop_filter_##dir##_##wd1##wd2##_16_c(uint8_t *dst, \ 1896 ptrdiff_t stride, \ 1897 int E, int I, int H) \ 1898{ \ 1899 loop_filter_##dir##_##wd1##_8_c(dst, stride, E & 0xff, I & 0xff, H & 0xff); \ 1900 loop_filter_##dir##_##wd2##_8_c(dst + 8 * stridea, stride, E >> 8, I >> 8, H >> 8); \ 1901} 1902 1903#define lf_mix_fns(wd1, wd2) \ 1904lf_mix_fn(h, wd1, wd2, stride) \ 1905lf_mix_fn(v, wd1, wd2, sizeof(pixel)) 1906 1907lf_mix_fns(4, 4) 1908lf_mix_fns(4, 8) 1909lf_mix_fns(8, 4) 1910lf_mix_fns(8, 8) 1911 1912#undef lf_mix_fn 1913#undef lf_mix_fns 1914 1915static av_cold void vp9dsp_loopfilter_init(VP9DSPContext *dsp) 1916{ 1917 dsp->loop_filter_8[0][0] = loop_filter_h_4_8_c; 1918 dsp->loop_filter_8[0][1] = loop_filter_v_4_8_c; 1919 dsp->loop_filter_8[1][0] = loop_filter_h_8_8_c; 1920 dsp->loop_filter_8[1][1] = loop_filter_v_8_8_c; 1921 dsp->loop_filter_8[2][0] = loop_filter_h_16_8_c; 1922 dsp->loop_filter_8[2][1] = loop_filter_v_16_8_c; 1923 1924 dsp->loop_filter_16[0] = loop_filter_h_16_16_c; 1925 dsp->loop_filter_16[1] = loop_filter_v_16_16_c; 1926 1927 dsp->loop_filter_mix2[0][0][0] = loop_filter_h_44_16_c; 1928 dsp->loop_filter_mix2[0][0][1] = loop_filter_v_44_16_c; 1929 dsp->loop_filter_mix2[0][1][0] = loop_filter_h_48_16_c; 1930 dsp->loop_filter_mix2[0][1][1] = loop_filter_v_48_16_c; 1931 dsp->loop_filter_mix2[1][0][0] = loop_filter_h_84_16_c; 1932 dsp->loop_filter_mix2[1][0][1] = loop_filter_v_84_16_c; 1933 dsp->loop_filter_mix2[1][1][0] = loop_filter_h_88_16_c; 1934 dsp->loop_filter_mix2[1][1][1] = loop_filter_v_88_16_c; 1935} 1936 1937#if BIT_DEPTH != 12 1938 1939static av_always_inline void copy_c(uint8_t *dst, ptrdiff_t dst_stride, 1940 const uint8_t *src, ptrdiff_t src_stride, 1941 int w, int h) 1942{ 1943 do { 1944 memcpy(dst, src, w * sizeof(pixel)); 1945 1946 dst += dst_stride; 1947 src += src_stride; 1948 } while (--h); 1949} 1950 1951static av_always_inline void avg_c(uint8_t *_dst, ptrdiff_t dst_stride, 1952 const uint8_t *_src, ptrdiff_t src_stride, 1953 int w, int h) 1954{ 1955 pixel *dst = (pixel *) _dst; 1956 const pixel *src = (const pixel *) _src; 1957 1958 dst_stride /= sizeof(pixel); 1959 src_stride /= sizeof(pixel); 1960 do { 1961 int x; 1962 1963 for (x = 0; x < w; x += 4) 1964 AV_WN4PA(&dst[x], rnd_avg_pixel4(AV_RN4PA(&dst[x]), AV_RN4P(&src[x]))); 1965 1966 dst += dst_stride; 1967 src += src_stride; 1968 } while (--h); 1969} 1970 1971#define fpel_fn(type, sz) \ 1972static void type##sz##_c(uint8_t *dst, ptrdiff_t dst_stride, \ 1973 const uint8_t *src, ptrdiff_t src_stride, \ 1974 int h, int mx, int my) \ 1975{ \ 1976 type##_c(dst, dst_stride, src, src_stride, sz, h); \ 1977} 1978 1979#define copy_avg_fn(sz) \ 1980fpel_fn(copy, sz) \ 1981fpel_fn(avg, sz) 1982 1983copy_avg_fn(64) 1984copy_avg_fn(32) 1985copy_avg_fn(16) 1986copy_avg_fn(8) 1987copy_avg_fn(4) 1988 1989#undef fpel_fn 1990#undef copy_avg_fn 1991 1992#endif /* BIT_DEPTH != 12 */ 1993 1994#define FILTER_8TAP(src, x, F, stride) \ 1995 av_clip_pixel((F[0] * src[x + -3 * stride] + \ 1996 F[1] * src[x + -2 * stride] + \ 1997 F[2] * src[x + -1 * stride] + \ 1998 F[3] * src[x + +0 * stride] + \ 1999 F[4] * src[x + +1 * stride] + \ 2000 F[5] * src[x + +2 * stride] + \ 2001 F[6] * src[x + +3 * stride] + \ 2002 F[7] * src[x + +4 * stride] + 64) >> 7) 2003 2004static av_always_inline void do_8tap_1d_c(uint8_t *_dst, ptrdiff_t dst_stride, 2005 const uint8_t *_src, ptrdiff_t src_stride, 2006 int w, int h, ptrdiff_t ds, 2007 const int16_t *filter, int avg) 2008{ 2009 pixel *dst = (pixel *) _dst; 2010 const pixel *src = (const pixel *) _src; 2011 2012 dst_stride /= sizeof(pixel); 2013 src_stride /= sizeof(pixel); 2014 do { 2015 int x; 2016 2017 for (x = 0; x < w; x++) 2018 if (avg) { 2019 dst[x] = (dst[x] + FILTER_8TAP(src, x, filter, ds) + 1) >> 1; 2020 } else { 2021 dst[x] = FILTER_8TAP(src, x, filter, ds); 2022 } 2023 2024 dst += dst_stride; 2025 src += src_stride; 2026 } while (--h); 2027} 2028 2029#define filter_8tap_1d_fn(opn, opa, dir, ds) \ 2030static av_noinline void opn##_8tap_1d_##dir##_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2031 const uint8_t *src, ptrdiff_t src_stride, \ 2032 int w, int h, const int16_t *filter) \ 2033{ \ 2034 do_8tap_1d_c(dst, dst_stride, src, src_stride, w, h, ds, filter, opa); \ 2035} 2036 2037filter_8tap_1d_fn(put, 0, v, src_stride / sizeof(pixel)) 2038filter_8tap_1d_fn(put, 0, h, 1) 2039filter_8tap_1d_fn(avg, 1, v, src_stride / sizeof(pixel)) 2040filter_8tap_1d_fn(avg, 1, h, 1) 2041 2042#undef filter_8tap_1d_fn 2043 2044static av_always_inline void do_8tap_2d_c(uint8_t *_dst, ptrdiff_t dst_stride, 2045 const uint8_t *_src, ptrdiff_t src_stride, 2046 int w, int h, const int16_t *filterx, 2047 const int16_t *filtery, int avg) 2048{ 2049 int tmp_h = h + 7; 2050 pixel tmp[64 * 71], *tmp_ptr = tmp; 2051 pixel *dst = (pixel *) _dst; 2052 const pixel *src = (const pixel *) _src; 2053 2054 dst_stride /= sizeof(pixel); 2055 src_stride /= sizeof(pixel); 2056 src -= src_stride * 3; 2057 do { 2058 int x; 2059 2060 for (x = 0; x < w; x++) 2061 tmp_ptr[x] = FILTER_8TAP(src, x, filterx, 1); 2062 2063 tmp_ptr += 64; 2064 src += src_stride; 2065 } while (--tmp_h); 2066 2067 tmp_ptr = tmp + 64 * 3; 2068 do { 2069 int x; 2070 2071 for (x = 0; x < w; x++) 2072 if (avg) { 2073 dst[x] = (dst[x] + FILTER_8TAP(tmp_ptr, x, filtery, 64) + 1) >> 1; 2074 } else { 2075 dst[x] = FILTER_8TAP(tmp_ptr, x, filtery, 64); 2076 } 2077 2078 tmp_ptr += 64; 2079 dst += dst_stride; 2080 } while (--h); 2081} 2082 2083#define filter_8tap_2d_fn(opn, opa) \ 2084static av_noinline void opn##_8tap_2d_hv_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2085 const uint8_t *src, ptrdiff_t src_stride, \ 2086 int w, int h, const int16_t *filterx, \ 2087 const int16_t *filtery) \ 2088{ \ 2089 do_8tap_2d_c(dst, dst_stride, src, src_stride, w, h, filterx, filtery, opa); \ 2090} 2091 2092filter_8tap_2d_fn(put, 0) 2093filter_8tap_2d_fn(avg, 1) 2094 2095#undef filter_8tap_2d_fn 2096 2097#define filter_fn_1d(sz, dir, dir_m, type, type_idx, avg) \ 2098static void avg##_8tap_##type##_##sz##dir##_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2099 const uint8_t *src, ptrdiff_t src_stride, \ 2100 int h, int mx, int my) \ 2101{ \ 2102 avg##_8tap_1d_##dir##_c(dst, dst_stride, src, src_stride, sz, h, \ 2103 ff_vp9_subpel_filters[type_idx][dir_m]); \ 2104} 2105 2106#define filter_fn_2d(sz, type, type_idx, avg) \ 2107static void avg##_8tap_##type##_##sz##hv_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2108 const uint8_t *src, ptrdiff_t src_stride, \ 2109 int h, int mx, int my) \ 2110{ \ 2111 avg##_8tap_2d_hv_c(dst, dst_stride, src, src_stride, sz, h, \ 2112 ff_vp9_subpel_filters[type_idx][mx], \ 2113 ff_vp9_subpel_filters[type_idx][my]); \ 2114} 2115 2116#if BIT_DEPTH != 12 2117 2118#define FILTER_BILIN(src, x, mxy, stride) \ 2119 (src[x] + ((mxy * (src[x + stride] - src[x]) + 8) >> 4)) 2120 2121static av_always_inline void do_bilin_1d_c(uint8_t *_dst, ptrdiff_t dst_stride, 2122 const uint8_t *_src, ptrdiff_t src_stride, 2123 int w, int h, ptrdiff_t ds, int mxy, int avg) 2124{ 2125 pixel *dst = (pixel *) _dst; 2126 const pixel *src = (const pixel *) _src; 2127 2128 dst_stride /= sizeof(pixel); 2129 src_stride /= sizeof(pixel); 2130 do { 2131 int x; 2132 2133 for (x = 0; x < w; x++) 2134 if (avg) { 2135 dst[x] = (dst[x] + FILTER_BILIN(src, x, mxy, ds) + 1) >> 1; 2136 } else { 2137 dst[x] = FILTER_BILIN(src, x, mxy, ds); 2138 } 2139 2140 dst += dst_stride; 2141 src += src_stride; 2142 } while (--h); 2143} 2144 2145#define bilin_1d_fn(opn, opa, dir, ds) \ 2146static av_noinline void opn##_bilin_1d_##dir##_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2147 const uint8_t *src, ptrdiff_t src_stride, \ 2148 int w, int h, int mxy) \ 2149{ \ 2150 do_bilin_1d_c(dst, dst_stride, src, src_stride, w, h, ds, mxy, opa); \ 2151} 2152 2153bilin_1d_fn(put, 0, v, src_stride / sizeof(pixel)) 2154bilin_1d_fn(put, 0, h, 1) 2155bilin_1d_fn(avg, 1, v, src_stride / sizeof(pixel)) 2156bilin_1d_fn(avg, 1, h, 1) 2157 2158#undef bilin_1d_fn 2159 2160static av_always_inline void do_bilin_2d_c(uint8_t *_dst, ptrdiff_t dst_stride, 2161 const uint8_t *_src, ptrdiff_t src_stride, 2162 int w, int h, int mx, int my, int avg) 2163{ 2164 pixel tmp[64 * 65], *tmp_ptr = tmp; 2165 int tmp_h = h + 1; 2166 pixel *dst = (pixel *) _dst; 2167 const pixel *src = (const pixel *) _src; 2168 2169 dst_stride /= sizeof(pixel); 2170 src_stride /= sizeof(pixel); 2171 do { 2172 int x; 2173 2174 for (x = 0; x < w; x++) 2175 tmp_ptr[x] = FILTER_BILIN(src, x, mx, 1); 2176 2177 tmp_ptr += 64; 2178 src += src_stride; 2179 } while (--tmp_h); 2180 2181 tmp_ptr = tmp; 2182 do { 2183 int x; 2184 2185 for (x = 0; x < w; x++) 2186 if (avg) { 2187 dst[x] = (dst[x] + FILTER_BILIN(tmp_ptr, x, my, 64) + 1) >> 1; 2188 } else { 2189 dst[x] = FILTER_BILIN(tmp_ptr, x, my, 64); 2190 } 2191 2192 tmp_ptr += 64; 2193 dst += dst_stride; 2194 } while (--h); 2195} 2196 2197#define bilin_2d_fn(opn, opa) \ 2198static av_noinline void opn##_bilin_2d_hv_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2199 const uint8_t *src, ptrdiff_t src_stride, \ 2200 int w, int h, int mx, int my) \ 2201{ \ 2202 do_bilin_2d_c(dst, dst_stride, src, src_stride, w, h, mx, my, opa); \ 2203} 2204 2205bilin_2d_fn(put, 0) 2206bilin_2d_fn(avg, 1) 2207 2208#undef bilin_2d_fn 2209 2210#define bilinf_fn_1d(sz, dir, dir_m, avg) \ 2211static void avg##_bilin_##sz##dir##_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2212 const uint8_t *src, ptrdiff_t src_stride, \ 2213 int h, int mx, int my) \ 2214{ \ 2215 avg##_bilin_1d_##dir##_c(dst, dst_stride, src, src_stride, sz, h, dir_m); \ 2216} 2217 2218#define bilinf_fn_2d(sz, avg) \ 2219static void avg##_bilin_##sz##hv_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2220 const uint8_t *src, ptrdiff_t src_stride, \ 2221 int h, int mx, int my) \ 2222{ \ 2223 avg##_bilin_2d_hv_c(dst, dst_stride, src, src_stride, sz, h, mx, my); \ 2224} 2225 2226#else 2227 2228#define bilinf_fn_1d(a, b, c, d) 2229#define bilinf_fn_2d(a, b) 2230 2231#endif 2232 2233#define filter_fn(sz, avg) \ 2234filter_fn_1d(sz, h, mx, regular, FILTER_8TAP_REGULAR, avg) \ 2235filter_fn_1d(sz, v, my, regular, FILTER_8TAP_REGULAR, avg) \ 2236filter_fn_2d(sz, regular, FILTER_8TAP_REGULAR, avg) \ 2237filter_fn_1d(sz, h, mx, smooth, FILTER_8TAP_SMOOTH, avg) \ 2238filter_fn_1d(sz, v, my, smooth, FILTER_8TAP_SMOOTH, avg) \ 2239filter_fn_2d(sz, smooth, FILTER_8TAP_SMOOTH, avg) \ 2240filter_fn_1d(sz, h, mx, sharp, FILTER_8TAP_SHARP, avg) \ 2241filter_fn_1d(sz, v, my, sharp, FILTER_8TAP_SHARP, avg) \ 2242filter_fn_2d(sz, sharp, FILTER_8TAP_SHARP, avg) \ 2243bilinf_fn_1d(sz, h, mx, avg) \ 2244bilinf_fn_1d(sz, v, my, avg) \ 2245bilinf_fn_2d(sz, avg) 2246 2247#define filter_fn_set(avg) \ 2248filter_fn(64, avg) \ 2249filter_fn(32, avg) \ 2250filter_fn(16, avg) \ 2251filter_fn(8, avg) \ 2252filter_fn(4, avg) 2253 2254filter_fn_set(put) 2255filter_fn_set(avg) 2256 2257#undef filter_fn 2258#undef filter_fn_set 2259#undef filter_fn_1d 2260#undef filter_fn_2d 2261#undef bilinf_fn_1d 2262#undef bilinf_fn_2d 2263 2264#if BIT_DEPTH != 8 2265void ff_vp9dsp_mc_init_10(VP9DSPContext *dsp); 2266#endif 2267#if BIT_DEPTH != 10 2268static 2269#endif 2270av_cold void FUNC(ff_vp9dsp_mc_init)(VP9DSPContext *dsp) 2271{ 2272#if BIT_DEPTH == 12 2273 ff_vp9dsp_mc_init_10(dsp); 2274#else /* BIT_DEPTH == 12 */ 2275 2276#define init_fpel(idx1, idx2, sz, type) \ 2277 dsp->mc[idx1][FILTER_8TAP_SMOOTH ][idx2][0][0] = type##sz##_c; \ 2278 dsp->mc[idx1][FILTER_8TAP_REGULAR][idx2][0][0] = type##sz##_c; \ 2279 dsp->mc[idx1][FILTER_8TAP_SHARP ][idx2][0][0] = type##sz##_c; \ 2280 dsp->mc[idx1][FILTER_BILINEAR ][idx2][0][0] = type##sz##_c 2281 2282#define init_copy_avg(idx, sz) \ 2283 init_fpel(idx, 0, sz, copy); \ 2284 init_fpel(idx, 1, sz, avg) 2285 2286 init_copy_avg(0, 64); 2287 init_copy_avg(1, 32); 2288 init_copy_avg(2, 16); 2289 init_copy_avg(3, 8); 2290 init_copy_avg(4, 4); 2291 2292#undef init_copy_avg 2293#undef init_fpel 2294 2295#endif /* BIT_DEPTH == 12 */ 2296 2297#define init_subpel1_bd_aware(idx1, idx2, idxh, idxv, sz, dir, type) \ 2298 dsp->mc[idx1][FILTER_8TAP_SMOOTH ][idx2][idxh][idxv] = type##_8tap_smooth_##sz##dir##_c; \ 2299 dsp->mc[idx1][FILTER_8TAP_REGULAR][idx2][idxh][idxv] = type##_8tap_regular_##sz##dir##_c; \ 2300 dsp->mc[idx1][FILTER_8TAP_SHARP ][idx2][idxh][idxv] = type##_8tap_sharp_##sz##dir##_c 2301 2302#if BIT_DEPTH == 12 2303#define init_subpel1 init_subpel1_bd_aware 2304#else 2305#define init_subpel1(idx1, idx2, idxh, idxv, sz, dir, type) \ 2306 init_subpel1_bd_aware(idx1, idx2, idxh, idxv, sz, dir, type); \ 2307 dsp->mc[idx1][FILTER_BILINEAR ][idx2][idxh][idxv] = type##_bilin_##sz##dir##_c 2308#endif 2309 2310#define init_subpel2(idx, idxh, idxv, dir, type) \ 2311 init_subpel1(0, idx, idxh, idxv, 64, dir, type); \ 2312 init_subpel1(1, idx, idxh, idxv, 32, dir, type); \ 2313 init_subpel1(2, idx, idxh, idxv, 16, dir, type); \ 2314 init_subpel1(3, idx, idxh, idxv, 8, dir, type); \ 2315 init_subpel1(4, idx, idxh, idxv, 4, dir, type) 2316 2317#define init_subpel3(idx, type) \ 2318 init_subpel2(idx, 1, 1, hv, type); \ 2319 init_subpel2(idx, 0, 1, v, type); \ 2320 init_subpel2(idx, 1, 0, h, type) 2321 2322 init_subpel3(0, put); 2323 init_subpel3(1, avg); 2324 2325#undef init_subpel1 2326#undef init_subpel2 2327#undef init_subpel3 2328#undef init_subpel1_bd_aware 2329} 2330 2331static av_always_inline void do_scaled_8tap_c(uint8_t *_dst, ptrdiff_t dst_stride, 2332 const uint8_t *_src, ptrdiff_t src_stride, 2333 int w, int h, int mx, int my, 2334 int dx, int dy, int avg, 2335 const int16_t (*filters)[8]) 2336{ 2337 int tmp_h = (((h - 1) * dy + my) >> 4) + 8; 2338 pixel tmp[64 * 135], *tmp_ptr = tmp; 2339 pixel *dst = (pixel *) _dst; 2340 const pixel *src = (const pixel *) _src; 2341 2342 dst_stride /= sizeof(pixel); 2343 src_stride /= sizeof(pixel); 2344 src -= src_stride * 3; 2345 do { 2346 int x; 2347 int imx = mx, ioff = 0; 2348 2349 for (x = 0; x < w; x++) { 2350 tmp_ptr[x] = FILTER_8TAP(src, ioff, filters[imx], 1); 2351 imx += dx; 2352 ioff += imx >> 4; 2353 imx &= 0xf; 2354 } 2355 2356 tmp_ptr += 64; 2357 src += src_stride; 2358 } while (--tmp_h); 2359 2360 tmp_ptr = tmp + 64 * 3; 2361 do { 2362 int x; 2363 const int16_t *filter = filters[my]; 2364 2365 for (x = 0; x < w; x++) 2366 if (avg) { 2367 dst[x] = (dst[x] + FILTER_8TAP(tmp_ptr, x, filter, 64) + 1) >> 1; 2368 } else { 2369 dst[x] = FILTER_8TAP(tmp_ptr, x, filter, 64); 2370 } 2371 2372 my += dy; 2373 tmp_ptr += (my >> 4) * 64; 2374 my &= 0xf; 2375 dst += dst_stride; 2376 } while (--h); 2377} 2378 2379#define scaled_filter_8tap_fn(opn, opa) \ 2380static av_noinline void opn##_scaled_8tap_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2381 const uint8_t *src, ptrdiff_t src_stride, \ 2382 int w, int h, int mx, int my, int dx, int dy, \ 2383 const int16_t (*filters)[8]) \ 2384{ \ 2385 do_scaled_8tap_c(dst, dst_stride, src, src_stride, w, h, mx, my, dx, dy, \ 2386 opa, filters); \ 2387} 2388 2389scaled_filter_8tap_fn(put, 0) 2390scaled_filter_8tap_fn(avg, 1) 2391 2392#undef scaled_filter_8tap_fn 2393 2394#undef FILTER_8TAP 2395 2396#define scaled_filter_fn(sz, type, type_idx, avg) \ 2397static void avg##_scaled_##type##_##sz##_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2398 const uint8_t *src, ptrdiff_t src_stride, \ 2399 int h, int mx, int my, int dx, int dy) \ 2400{ \ 2401 avg##_scaled_8tap_c(dst, dst_stride, src, src_stride, sz, h, mx, my, dx, dy, \ 2402 ff_vp9_subpel_filters[type_idx]); \ 2403} 2404 2405#if BIT_DEPTH != 12 2406 2407static av_always_inline void do_scaled_bilin_c(uint8_t *_dst, ptrdiff_t dst_stride, 2408 const uint8_t *_src, ptrdiff_t src_stride, 2409 int w, int h, int mx, int my, 2410 int dx, int dy, int avg) 2411{ 2412 pixel tmp[64 * 129], *tmp_ptr = tmp; 2413 int tmp_h = (((h - 1) * dy + my) >> 4) + 2; 2414 pixel *dst = (pixel *) _dst; 2415 const pixel *src = (const pixel *) _src; 2416 2417 dst_stride /= sizeof(pixel); 2418 src_stride /= sizeof(pixel); 2419 do { 2420 int x; 2421 int imx = mx, ioff = 0; 2422 2423 for (x = 0; x < w; x++) { 2424 tmp_ptr[x] = FILTER_BILIN(src, ioff, imx, 1); 2425 imx += dx; 2426 ioff += imx >> 4; 2427 imx &= 0xf; 2428 } 2429 2430 tmp_ptr += 64; 2431 src += src_stride; 2432 } while (--tmp_h); 2433 2434 tmp_ptr = tmp; 2435 do { 2436 int x; 2437 2438 for (x = 0; x < w; x++) 2439 if (avg) { 2440 dst[x] = (dst[x] + FILTER_BILIN(tmp_ptr, x, my, 64) + 1) >> 1; 2441 } else { 2442 dst[x] = FILTER_BILIN(tmp_ptr, x, my, 64); 2443 } 2444 2445 my += dy; 2446 tmp_ptr += (my >> 4) * 64; 2447 my &= 0xf; 2448 dst += dst_stride; 2449 } while (--h); 2450} 2451 2452#define scaled_bilin_fn(opn, opa) \ 2453static av_noinline void opn##_scaled_bilin_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2454 const uint8_t *src, ptrdiff_t src_stride, \ 2455 int w, int h, int mx, int my, int dx, int dy) \ 2456{ \ 2457 do_scaled_bilin_c(dst, dst_stride, src, src_stride, w, h, mx, my, dx, dy, opa); \ 2458} 2459 2460scaled_bilin_fn(put, 0) 2461scaled_bilin_fn(avg, 1) 2462 2463#undef scaled_bilin_fn 2464 2465#undef FILTER_BILIN 2466 2467#define scaled_bilinf_fn(sz, avg) \ 2468static void avg##_scaled_bilin_##sz##_c(uint8_t *dst, ptrdiff_t dst_stride, \ 2469 const uint8_t *src, ptrdiff_t src_stride, \ 2470 int h, int mx, int my, int dx, int dy) \ 2471{ \ 2472 avg##_scaled_bilin_c(dst, dst_stride, src, src_stride, sz, h, mx, my, dx, dy); \ 2473} 2474 2475#else 2476 2477#define scaled_bilinf_fn(a, b) 2478 2479#endif 2480 2481#define scaled_filter_fns(sz, avg) \ 2482scaled_filter_fn(sz, regular, FILTER_8TAP_REGULAR, avg) \ 2483scaled_filter_fn(sz, smooth, FILTER_8TAP_SMOOTH, avg) \ 2484scaled_filter_fn(sz, sharp, FILTER_8TAP_SHARP, avg) \ 2485scaled_bilinf_fn(sz, avg) 2486 2487#define scaled_filter_fn_set(avg) \ 2488scaled_filter_fns(64, avg) \ 2489scaled_filter_fns(32, avg) \ 2490scaled_filter_fns(16, avg) \ 2491scaled_filter_fns(8, avg) \ 2492scaled_filter_fns(4, avg) 2493 2494scaled_filter_fn_set(put) 2495scaled_filter_fn_set(avg) 2496 2497#undef scaled_filter_fns 2498#undef scaled_filter_fn_set 2499#undef scaled_filter_fn 2500#undef scaled_bilinf_fn 2501 2502#if BIT_DEPTH != 8 2503void ff_vp9dsp_scaled_mc_init_10(VP9DSPContext *dsp); 2504#endif 2505#if BIT_DEPTH != 10 2506static 2507#endif 2508av_cold void FUNC(ff_vp9dsp_scaled_mc_init)(VP9DSPContext *dsp) 2509{ 2510#define init_scaled_bd_aware(idx1, idx2, sz, type) \ 2511 dsp->smc[idx1][FILTER_8TAP_SMOOTH ][idx2] = type##_scaled_smooth_##sz##_c; \ 2512 dsp->smc[idx1][FILTER_8TAP_REGULAR][idx2] = type##_scaled_regular_##sz##_c; \ 2513 dsp->smc[idx1][FILTER_8TAP_SHARP ][idx2] = type##_scaled_sharp_##sz##_c 2514 2515#if BIT_DEPTH == 12 2516 ff_vp9dsp_scaled_mc_init_10(dsp); 2517#define init_scaled(a,b,c,d) init_scaled_bd_aware(a,b,c,d) 2518#else 2519#define init_scaled(idx1, idx2, sz, type) \ 2520 init_scaled_bd_aware(idx1, idx2, sz, type); \ 2521 dsp->smc[idx1][FILTER_BILINEAR ][idx2] = type##_scaled_bilin_##sz##_c 2522#endif 2523 2524#define init_scaled_put_avg(idx, sz) \ 2525 init_scaled(idx, 0, sz, put); \ 2526 init_scaled(idx, 1, sz, avg) 2527 2528 init_scaled_put_avg(0, 64); 2529 init_scaled_put_avg(1, 32); 2530 init_scaled_put_avg(2, 16); 2531 init_scaled_put_avg(3, 8); 2532 init_scaled_put_avg(4, 4); 2533 2534#undef init_scaled_put_avg 2535#undef init_scaled 2536#undef init_scaled_bd_aware 2537} 2538 2539av_cold void FUNC(ff_vp9dsp_init)(VP9DSPContext *dsp) 2540{ 2541 FUNC(ff_vp9dsp_intrapred_init)(dsp); 2542 vp9dsp_itxfm_init(dsp); 2543 vp9dsp_loopfilter_init(dsp); 2544 FUNC(ff_vp9dsp_mc_init)(dsp); 2545 FUNC(ff_vp9dsp_scaled_mc_init)(dsp); 2546} 2547