1/* 2 * Texture block compression 3 * Copyright (C) 2015 Vittorio Giovara <vittorio.giovara@gmail.com> 4 * Based on public domain code by Fabian Giesen, Sean Barrett and Yann Collet. 5 * 6 * This file is part of FFmpeg 7 * 8 * Permission is hereby granted, free of charge, to any person obtaining a 9 * copy of this software and associated documentation files (the "Software"), 10 * to deal in the Software without restriction, including without limitation 11 * the rights to use, copy, modify, merge, publish, distribute, sublicense, 12 * and/or sell copies of the Software, and to permit persons to whom the 13 * Software is furnished to do so, subject to the following conditions: 14 * The above copyright notice and this permission notice shall be included 15 * in all copies or substantial portions of the Software. 16 * 17 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 18 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 19 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 20 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 21 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 22 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS 23 * IN THE SOFTWARE. 24 */ 25 26#include <stddef.h> 27#include <stdint.h> 28 29#include "libavutil/attributes.h" 30#include "libavutil/common.h" 31#include "libavutil/intreadwrite.h" 32 33#include "texturedsp.h" 34 35static const uint8_t expand5[32] = { 36 0, 8, 16, 24, 33, 41, 49, 57, 66, 74, 82, 90, 37 99, 107, 115, 123, 132, 140, 148, 156, 165, 173, 181, 189, 38 198, 206, 214, 222, 231, 239, 247, 255, 39}; 40 41static const uint8_t expand6[64] = { 42 0, 4, 8, 12, 16, 20, 24, 28, 32, 36, 40, 44, 43 48, 52, 56, 60, 65, 69, 73, 77, 81, 85, 89, 93, 44 97, 101, 105, 109, 113, 117, 121, 125, 130, 134, 138, 142, 45 146, 150, 154, 158, 162, 166, 170, 174, 178, 182, 186, 190, 46 195, 199, 203, 207, 211, 215, 219, 223, 227, 231, 235, 239, 47 243, 247, 251, 255, 48}; 49 50static const uint8_t match5[256][2] = { 51 { 0, 0 }, { 0, 0 }, { 0, 1 }, { 0, 1 }, { 1, 0 }, { 1, 0 }, 52 { 1, 0 }, { 1, 1 }, { 1, 1 }, { 2, 0 }, { 2, 0 }, { 0, 4 }, 53 { 2, 1 }, { 2, 1 }, { 2, 1 }, { 3, 0 }, { 3, 0 }, { 3, 0 }, 54 { 3, 1 }, { 1, 5 }, { 3, 2 }, { 3, 2 }, { 4, 0 }, { 4, 0 }, 55 { 4, 1 }, { 4, 1 }, { 4, 2 }, { 4, 2 }, { 4, 2 }, { 3, 5 }, 56 { 5, 1 }, { 5, 1 }, { 5, 2 }, { 4, 4 }, { 5, 3 }, { 5, 3 }, 57 { 5, 3 }, { 6, 2 }, { 6, 2 }, { 6, 2 }, { 6, 3 }, { 5, 5 }, 58 { 6, 4 }, { 6, 4 }, { 4, 8 }, { 7, 3 }, { 7, 3 }, { 7, 3 }, 59 { 7, 4 }, { 7, 4 }, { 7, 4 }, { 7, 5 }, { 5, 9 }, { 7, 6 }, 60 { 7, 6 }, { 8, 4 }, { 8, 4 }, { 8, 5 }, { 8, 5 }, { 8, 6 }, 61 { 8, 6 }, { 8, 6 }, { 7, 9 }, { 9, 5 }, { 9, 5 }, { 9, 6 }, 62 { 8, 8 }, { 9, 7 }, { 9, 7 }, { 9, 7 }, { 10, 6 }, { 10, 6 }, 63 { 10, 6 }, { 10, 7 }, { 9, 9 }, { 10, 8 }, { 10, 8 }, { 8, 12 }, 64 { 11, 7 }, { 11, 7 }, { 11, 7 }, { 11, 8 }, { 11, 8 }, { 11, 8 }, 65 { 11, 9 }, { 9, 13 }, { 11, 10 }, { 11, 10 }, { 12, 8 }, { 12, 8 }, 66 { 12, 9 }, { 12, 9 }, { 12, 10 }, { 12, 10 }, { 12, 10 }, { 11, 13 }, 67 { 13, 9 }, { 13, 9 }, { 13, 10 }, { 12, 12 }, { 13, 11 }, { 13, 11 }, 68 { 13, 11 }, { 14, 10 }, { 14, 10 }, { 14, 10 }, { 14, 11 }, { 13, 13 }, 69 { 14, 12 }, { 14, 12 }, { 12, 16 }, { 15, 11 }, { 15, 11 }, { 15, 11 }, 70 { 15, 12 }, { 15, 12 }, { 15, 12 }, { 15, 13 }, { 13, 17 }, { 15, 14 }, 71 { 15, 14 }, { 16, 12 }, { 16, 12 }, { 16, 13 }, { 16, 13 }, { 16, 14 }, 72 { 16, 14 }, { 16, 14 }, { 15, 17 }, { 17, 13 }, { 17, 13 }, { 17, 14 }, 73 { 16, 16 }, { 17, 15 }, { 17, 15 }, { 17, 15 }, { 18, 14 }, { 18, 14 }, 74 { 18, 14 }, { 18, 15 }, { 17, 17 }, { 18, 16 }, { 18, 16 }, { 16, 20 }, 75 { 19, 15 }, { 19, 15 }, { 19, 15 }, { 19, 16 }, { 19, 16 }, { 19, 16 }, 76 { 19, 17 }, { 17, 21 }, { 19, 18 }, { 19, 18 }, { 20, 16 }, { 20, 16 }, 77 { 20, 17 }, { 20, 17 }, { 20, 18 }, { 20, 18 }, { 20, 18 }, { 19, 21 }, 78 { 21, 17 }, { 21, 17 }, { 21, 18 }, { 20, 20 }, { 21, 19 }, { 21, 19 }, 79 { 21, 19 }, { 22, 18 }, { 22, 18 }, { 22, 18 }, { 22, 19 }, { 21, 21 }, 80 { 22, 20 }, { 22, 20 }, { 20, 24 }, { 23, 19 }, { 23, 19 }, { 23, 19 }, 81 { 23, 20 }, { 23, 20 }, { 23, 20 }, { 23, 21 }, { 21, 25 }, { 23, 22 }, 82 { 23, 22 }, { 24, 20 }, { 24, 20 }, { 24, 21 }, { 24, 21 }, { 24, 22 }, 83 { 24, 22 }, { 24, 22 }, { 23, 25 }, { 25, 21 }, { 25, 21 }, { 25, 22 }, 84 { 24, 24 }, { 25, 23 }, { 25, 23 }, { 25, 23 }, { 26, 22 }, { 26, 22 }, 85 { 26, 22 }, { 26, 23 }, { 25, 25 }, { 26, 24 }, { 26, 24 }, { 24, 28 }, 86 { 27, 23 }, { 27, 23 }, { 27, 23 }, { 27, 24 }, { 27, 24 }, { 27, 24 }, 87 { 27, 25 }, { 25, 29 }, { 27, 26 }, { 27, 26 }, { 28, 24 }, { 28, 24 }, 88 { 28, 25 }, { 28, 25 }, { 28, 26 }, { 28, 26 }, { 28, 26 }, { 27, 29 }, 89 { 29, 25 }, { 29, 25 }, { 29, 26 }, { 28, 28 }, { 29, 27 }, { 29, 27 }, 90 { 29, 27 }, { 30, 26 }, { 30, 26 }, { 30, 26 }, { 30, 27 }, { 29, 29 }, 91 { 30, 28 }, { 30, 28 }, { 30, 28 }, { 31, 27 }, { 31, 27 }, { 31, 27 }, 92 { 31, 28 }, { 31, 28 }, { 31, 28 }, { 31, 29 }, { 31, 29 }, { 31, 30 }, 93 { 31, 30 }, { 31, 30 }, { 31, 31 }, { 31, 31 }, 94}; 95 96static const uint8_t match6[256][2] = { 97 { 0, 0 }, { 0, 1 }, { 1, 0 }, { 1, 0 }, { 1, 1 }, { 2, 0 }, 98 { 2, 1 }, { 3, 0 }, { 3, 0 }, { 3, 1 }, { 4, 0 }, { 4, 0 }, 99 { 4, 1 }, { 5, 0 }, { 5, 1 }, { 6, 0 }, { 6, 0 }, { 6, 1 }, 100 { 7, 0 }, { 7, 0 }, { 7, 1 }, { 8, 0 }, { 8, 1 }, { 8, 1 }, 101 { 8, 2 }, { 9, 1 }, { 9, 2 }, { 9, 2 }, { 9, 3 }, { 10, 2 }, 102 { 10, 3 }, { 10, 3 }, { 10, 4 }, { 11, 3 }, { 11, 4 }, { 11, 4 }, 103 { 11, 5 }, { 12, 4 }, { 12, 5 }, { 12, 5 }, { 12, 6 }, { 13, 5 }, 104 { 13, 6 }, { 8, 16 }, { 13, 7 }, { 14, 6 }, { 14, 7 }, { 9, 17 }, 105 { 14, 8 }, { 15, 7 }, { 15, 8 }, { 11, 16 }, { 15, 9 }, { 15, 10 }, 106 { 16, 8 }, { 16, 9 }, { 16, 10 }, { 15, 13 }, { 17, 9 }, { 17, 10 }, 107 { 17, 11 }, { 15, 16 }, { 18, 10 }, { 18, 11 }, { 18, 12 }, { 16, 16 }, 108 { 19, 11 }, { 19, 12 }, { 19, 13 }, { 17, 17 }, { 20, 12 }, { 20, 13 }, 109 { 20, 14 }, { 19, 16 }, { 21, 13 }, { 21, 14 }, { 21, 15 }, { 20, 17 }, 110 { 22, 14 }, { 22, 15 }, { 25, 10 }, { 22, 16 }, { 23, 15 }, { 23, 16 }, 111 { 26, 11 }, { 23, 17 }, { 24, 16 }, { 24, 17 }, { 27, 12 }, { 24, 18 }, 112 { 25, 17 }, { 25, 18 }, { 28, 13 }, { 25, 19 }, { 26, 18 }, { 26, 19 }, 113 { 29, 14 }, { 26, 20 }, { 27, 19 }, { 27, 20 }, { 30, 15 }, { 27, 21 }, 114 { 28, 20 }, { 28, 21 }, { 28, 21 }, { 28, 22 }, { 29, 21 }, { 29, 22 }, 115 { 24, 32 }, { 29, 23 }, { 30, 22 }, { 30, 23 }, { 25, 33 }, { 30, 24 }, 116 { 31, 23 }, { 31, 24 }, { 27, 32 }, { 31, 25 }, { 31, 26 }, { 32, 24 }, 117 { 32, 25 }, { 32, 26 }, { 31, 29 }, { 33, 25 }, { 33, 26 }, { 33, 27 }, 118 { 31, 32 }, { 34, 26 }, { 34, 27 }, { 34, 28 }, { 32, 32 }, { 35, 27 }, 119 { 35, 28 }, { 35, 29 }, { 33, 33 }, { 36, 28 }, { 36, 29 }, { 36, 30 }, 120 { 35, 32 }, { 37, 29 }, { 37, 30 }, { 37, 31 }, { 36, 33 }, { 38, 30 }, 121 { 38, 31 }, { 41, 26 }, { 38, 32 }, { 39, 31 }, { 39, 32 }, { 42, 27 }, 122 { 39, 33 }, { 40, 32 }, { 40, 33 }, { 43, 28 }, { 40, 34 }, { 41, 33 }, 123 { 41, 34 }, { 44, 29 }, { 41, 35 }, { 42, 34 }, { 42, 35 }, { 45, 30 }, 124 { 42, 36 }, { 43, 35 }, { 43, 36 }, { 46, 31 }, { 43, 37 }, { 44, 36 }, 125 { 44, 37 }, { 44, 37 }, { 44, 38 }, { 45, 37 }, { 45, 38 }, { 40, 48 }, 126 { 45, 39 }, { 46, 38 }, { 46, 39 }, { 41, 49 }, { 46, 40 }, { 47, 39 }, 127 { 47, 40 }, { 43, 48 }, { 47, 41 }, { 47, 42 }, { 48, 40 }, { 48, 41 }, 128 { 48, 42 }, { 47, 45 }, { 49, 41 }, { 49, 42 }, { 49, 43 }, { 47, 48 }, 129 { 50, 42 }, { 50, 43 }, { 50, 44 }, { 48, 48 }, { 51, 43 }, { 51, 44 }, 130 { 51, 45 }, { 49, 49 }, { 52, 44 }, { 52, 45 }, { 52, 46 }, { 51, 48 }, 131 { 53, 45 }, { 53, 46 }, { 53, 47 }, { 52, 49 }, { 54, 46 }, { 54, 47 }, 132 { 57, 42 }, { 54, 48 }, { 55, 47 }, { 55, 48 }, { 58, 43 }, { 55, 49 }, 133 { 56, 48 }, { 56, 49 }, { 59, 44 }, { 56, 50 }, { 57, 49 }, { 57, 50 }, 134 { 60, 45 }, { 57, 51 }, { 58, 50 }, { 58, 51 }, { 61, 46 }, { 58, 52 }, 135 { 59, 51 }, { 59, 52 }, { 62, 47 }, { 59, 53 }, { 60, 52 }, { 60, 53 }, 136 { 60, 53 }, { 60, 54 }, { 61, 53 }, { 61, 54 }, { 61, 54 }, { 61, 55 }, 137 { 62, 54 }, { 62, 55 }, { 62, 55 }, { 62, 56 }, { 63, 55 }, { 63, 56 }, 138 { 63, 56 }, { 63, 57 }, { 63, 58 }, { 63, 59 }, { 63, 59 }, { 63, 60 }, 139 { 63, 61 }, { 63, 62 }, { 63, 62 }, { 63, 63 }, 140}; 141 142/* Multiplication over 8 bit emulation */ 143#define mul8(a, b) (((a) * (b) + 128 + (((a) * (b) + 128) >> 8)) >> 8) 144 145/* Conversion from rgb24 to rgb565 */ 146#define rgb2rgb565(r, g, b) \ 147 ((mul8(r, 31) << 11) | (mul8(g, 63) << 5) | (mul8(b, 31) << 0)) 148 149/* Linear interpolation at 1/3 point between a and b */ 150#define lerp13(a, b) ((2 * (a) + (b)) / 3) 151 152/* Linear interpolation on an RGB pixel */ 153static inline void lerp13rgb(uint8_t *out, uint8_t *p1, uint8_t *p2) 154{ 155 out[0] = lerp13(p1[0], p2[0]); 156 out[1] = lerp13(p1[1], p2[1]); 157 out[2] = lerp13(p1[2], p2[2]); 158} 159 160/* Conversion from rgb565 to rgb24 */ 161static inline void rgb5652rgb(uint8_t *out, uint16_t v) 162{ 163 int rv = (v & 0xf800) >> 11; 164 int gv = (v & 0x07e0) >> 5; 165 int bv = (v & 0x001f) >> 0; 166 167 out[0] = expand5[rv]; 168 out[1] = expand6[gv]; 169 out[2] = expand5[bv]; 170 out[3] = 0; 171} 172 173/* Color matching function */ 174static unsigned int match_colors(const uint8_t *block, ptrdiff_t stride, 175 uint16_t c0, uint16_t c1) 176{ 177 uint32_t mask = 0; 178 int dirr, dirg, dirb; 179 int dots[16]; 180 int stops[4]; 181 int x, y, k = 0; 182 int c0_point, half_point, c3_point; 183 uint8_t color[16]; 184 static const uint32_t indexMap[8] = { 185 0U << 30, 2U << 30, 0U << 30, 2U << 30, 186 3U << 30, 3U << 30, 1U << 30, 1U << 30, 187 }; 188 189 /* Fill color and compute direction for each component */ 190 rgb5652rgb(color + 0, c0); 191 rgb5652rgb(color + 4, c1); 192 lerp13rgb(color + 8, color + 0, color + 4); 193 lerp13rgb(color + 12, color + 4, color + 0); 194 195 dirr = color[0 * 4 + 0] - color[1 * 4 + 0]; 196 dirg = color[0 * 4 + 1] - color[1 * 4 + 1]; 197 dirb = color[0 * 4 + 2] - color[1 * 4 + 2]; 198 199 for (y = 0; y < 4; y++) { 200 for (x = 0; x < 4; x++) 201 dots[k++] = block[0 + x * 4 + y * stride] * dirr + 202 block[1 + x * 4 + y * stride] * dirg + 203 block[2 + x * 4 + y * stride] * dirb; 204 205 stops[y] = color[0 + y * 4] * dirr + 206 color[1 + y * 4] * dirg + 207 color[2 + y * 4] * dirb; 208 } 209 210 /* Think of the colors as arranged on a line; project point onto that line, 211 * then choose next color out of available ones. we compute the crossover 212 * points for 'best color in top half'/'best in bottom half' and then 213 * the same inside that subinterval. 214 * 215 * Relying on this 1d approximation isn't always optimal in terms of 216 * Euclidean distance, but it's very close and a lot faster. 217 * 218 * http://cbloomrants.blogspot.com/2008/12/12-08-08-dxtc-summary.html */ 219 c0_point = (stops[1] + stops[3]) >> 1; 220 half_point = (stops[3] + stops[2]) >> 1; 221 c3_point = (stops[2] + stops[0]) >> 1; 222 223 for (x = 0; x < 16; x++) { 224 int dot = dots[x]; 225 int bits = (dot < half_point ? 4 : 0) | 226 (dot < c0_point ? 2 : 0) | 227 (dot < c3_point ? 1 : 0); 228 229 mask >>= 2; 230 mask |= indexMap[bits]; 231 } 232 233 return mask; 234} 235 236/* Color optimization function */ 237static void optimize_colors(const uint8_t *block, ptrdiff_t stride, 238 uint16_t *pmax16, uint16_t *pmin16) 239{ 240 const uint8_t *minp; 241 const uint8_t *maxp; 242 const int iter_power = 4; 243 double magn; 244 int v_r, v_g, v_b; 245 float covf[6], vfr, vfg, vfb; 246 int mind, maxd; 247 int cov[6] = { 0 }; 248 int mu[3], min[3], max[3]; 249 int ch, iter, x, y; 250 251 /* Determine color distribution */ 252 for (ch = 0; ch < 3; ch++) { 253 const uint8_t *bp = &block[ch]; 254 int muv, minv, maxv; 255 256 muv = minv = maxv = bp[0]; 257 for (y = 0; y < 4; y++) { 258 for (x = 0; x < 4; x++) { 259 muv += bp[x * 4 + y * stride]; 260 if (bp[x * 4 + y * stride] < minv) 261 minv = bp[x * 4 + y * stride]; 262 else if (bp[x * 4 + y * stride] > maxv) 263 maxv = bp[x * 4 + y * stride]; 264 } 265 } 266 267 mu[ch] = (muv + 8) >> 4; 268 min[ch] = minv; 269 max[ch] = maxv; 270 } 271 272 /* Determine covariance matrix */ 273 for (y = 0; y < 4; y++) { 274 for (x = 0; x < 4; x++) { 275 int r = block[x * 4 + stride * y + 0] - mu[0]; 276 int g = block[x * 4 + stride * y + 1] - mu[1]; 277 int b = block[x * 4 + stride * y + 2] - mu[2]; 278 279 cov[0] += r * r; 280 cov[1] += r * g; 281 cov[2] += r * b; 282 cov[3] += g * g; 283 cov[4] += g * b; 284 cov[5] += b * b; 285 } 286 } 287 288 /* Convert covariance matrix to float, find principal axis via power iter */ 289 for (x = 0; x < 6; x++) 290 covf[x] = cov[x] / 255.0f; 291 292 vfr = (float) (max[0] - min[0]); 293 vfg = (float) (max[1] - min[1]); 294 vfb = (float) (max[2] - min[2]); 295 296 for (iter = 0; iter < iter_power; iter++) { 297 float r = vfr * covf[0] + vfg * covf[1] + vfb * covf[2]; 298 float g = vfr * covf[1] + vfg * covf[3] + vfb * covf[4]; 299 float b = vfr * covf[2] + vfg * covf[4] + vfb * covf[5]; 300 301 vfr = r; 302 vfg = g; 303 vfb = b; 304 } 305 306 magn = fabs(vfr); 307 if (fabs(vfg) > magn) 308 magn = fabs(vfg); 309 if (fabs(vfb) > magn) 310 magn = fabs(vfb); 311 312 /* if magnitude is too small, default to luminance */ 313 if (magn < 4.0f) { 314 /* JPEG YCbCr luma coefs, scaled by 1000 */ 315 v_r = 299; 316 v_g = 587; 317 v_b = 114; 318 } else { 319 magn = 512.0 / magn; 320 v_r = (int) (vfr * magn); 321 v_g = (int) (vfg * magn); 322 v_b = (int) (vfb * magn); 323 } 324 325 /* Pick colors at extreme points */ 326 mind = maxd = block[0] * v_r + block[1] * v_g + block[2] * v_b; 327 minp = maxp = block; 328 for (y = 0; y < 4; y++) { 329 for (x = 0; x < 4; x++) { 330 int dot = block[x * 4 + y * stride + 0] * v_r + 331 block[x * 4 + y * stride + 1] * v_g + 332 block[x * 4 + y * stride + 2] * v_b; 333 334 if (dot < mind) { 335 mind = dot; 336 minp = block + x * 4 + y * stride; 337 } else if (dot > maxd) { 338 maxd = dot; 339 maxp = block + x * 4 + y * stride; 340 } 341 } 342 } 343 344 *pmax16 = rgb2rgb565(maxp[0], maxp[1], maxp[2]); 345 *pmin16 = rgb2rgb565(minp[0], minp[1], minp[2]); 346} 347 348/* Try to optimize colors to suit block contents better, by solving 349 * a least squares system via normal equations + Cramer's rule. */ 350static int refine_colors(const uint8_t *block, ptrdiff_t stride, 351 uint16_t *pmax16, uint16_t *pmin16, uint32_t mask) 352{ 353 uint32_t cm = mask; 354 uint16_t oldMin = *pmin16; 355 uint16_t oldMax = *pmax16; 356 uint16_t min16, max16; 357 int x, y; 358 359 /* Additional magic to save a lot of multiplies in the accumulating loop. 360 * The tables contain precomputed products of weights for least squares 361 * system, accumulated inside one 32-bit register */ 362 static const int w1tab[4] = { 3, 0, 2, 1 }; 363 static const int prods[4] = { 0x090000, 0x000900, 0x040102, 0x010402 }; 364 365 /* Check if all pixels have the same index */ 366 if ((mask ^ (mask << 2)) < 4) { 367 /* If so, linear system would be singular; solve using optimal 368 * single-color match on average color. */ 369 int r = 8, g = 8, b = 8; 370 for (y = 0; y < 4; y++) { 371 for (x = 0; x < 4; x++) { 372 r += block[0 + x * 4 + y * stride]; 373 g += block[1 + x * 4 + y * stride]; 374 b += block[2 + x * 4 + y * stride]; 375 } 376 } 377 378 r >>= 4; 379 g >>= 4; 380 b >>= 4; 381 382 max16 = (match5[r][0] << 11) | (match6[g][0] << 5) | match5[b][0]; 383 min16 = (match5[r][1] << 11) | (match6[g][1] << 5) | match5[b][1]; 384 } else { 385 float fr, fg, fb; 386 int at1_r = 0, at1_g = 0, at1_b = 0; 387 int at2_r = 0, at2_g = 0, at2_b = 0; 388 int akku = 0; 389 int xx, xy, yy; 390 391 for (y = 0; y < 4; y++) { 392 for (x = 0; x < 4; x++) { 393 int step = cm & 3; 394 int w1 = w1tab[step]; 395 int r = block[0 + x * 4 + y * stride]; 396 int g = block[1 + x * 4 + y * stride]; 397 int b = block[2 + x * 4 + y * stride]; 398 399 akku += prods[step]; 400 at1_r += w1 * r; 401 at1_g += w1 * g; 402 at1_b += w1 * b; 403 at2_r += r; 404 at2_g += g; 405 at2_b += b; 406 407 cm >>= 2; 408 } 409 } 410 411 at2_r = 3 * at2_r - at1_r; 412 at2_g = 3 * at2_g - at1_g; 413 at2_b = 3 * at2_b - at1_b; 414 415 /* Extract solutions and decide solvability */ 416 xx = akku >> 16; 417 yy = (akku >> 8) & 0xFF; 418 xy = (akku >> 0) & 0xFF; 419 420 fr = 3.0f * 31.0f / 255.0f / (xx * yy - xy * xy); 421 fg = fr * 63.0f / 31.0f; 422 fb = fr; 423 424 /* Solve */ 425 max16 = av_clip_uintp2((at1_r * yy - at2_r * xy) * fr + 0.5f, 5) << 11; 426 max16 |= av_clip_uintp2((at1_g * yy - at2_g * xy) * fg + 0.5f, 6) << 5; 427 max16 |= av_clip_uintp2((at1_b * yy - at2_b * xy) * fb + 0.5f, 5) << 0; 428 429 min16 = av_clip_uintp2((at2_r * xx - at1_r * xy) * fr + 0.5f, 5) << 11; 430 min16 |= av_clip_uintp2((at2_g * xx - at1_g * xy) * fg + 0.5f, 6) << 5; 431 min16 |= av_clip_uintp2((at2_b * xx - at1_b * xy) * fb + 0.5f, 5) << 0; 432 } 433 434 *pmin16 = min16; 435 *pmax16 = max16; 436 return oldMin != min16 || oldMax != max16; 437} 438 439/* Check if input block is a constant color */ 440static int constant_color(const uint8_t *block, ptrdiff_t stride) 441{ 442 int x, y; 443 uint32_t first = AV_RL32(block); 444 445 for (y = 0; y < 4; y++) 446 for (x = 0; x < 4; x++) 447 if (first != AV_RL32(block + x * 4 + y * stride)) 448 return 0; 449 return 1; 450} 451 452/* Main color compression function */ 453static void compress_color(uint8_t *dst, ptrdiff_t stride, const uint8_t *block) 454{ 455 uint32_t mask; 456 uint16_t max16, min16; 457 int constant = constant_color(block, stride); 458 459 /* Constant color will load values from tables */ 460 if (constant) { 461 int r = block[0]; 462 int g = block[1]; 463 int b = block[2]; 464 mask = 0xAAAAAAAA; 465 max16 = (match5[r][0] << 11) | (match6[g][0] << 5) | match5[b][0]; 466 min16 = (match5[r][1] << 11) | (match6[g][1] << 5) | match5[b][1]; 467 } else { 468 int refine; 469 470 /* Otherwise find pca and map along principal axis */ 471 optimize_colors(block, stride, &max16, &min16); 472 if (max16 != min16) 473 mask = match_colors(block, stride, max16, min16); 474 else 475 mask = 0; 476 477 /* One pass refinement */ 478 refine = refine_colors(block, stride, &max16, &min16, mask); 479 if (refine) { 480 if (max16 != min16) 481 mask = match_colors(block, stride, max16, min16); 482 else 483 mask = 0; 484 } 485 } 486 487 /* Finally write the color block */ 488 if (max16 < min16) { 489 FFSWAP(uint16_t, min16, max16); 490 mask ^= 0x55555555; 491 } 492 493 AV_WL16(dst + 0, max16); 494 AV_WL16(dst + 2, min16); 495 AV_WL32(dst + 4, mask); 496} 497 498/* Alpha compression function */ 499static void compress_alpha(uint8_t *dst, ptrdiff_t stride, const uint8_t *block) 500{ 501 int x, y; 502 int dist, bias, dist4, dist2; 503 int mn, mx; 504 int bits = 0; 505 int mask = 0; 506 507 memset(dst, 0, 8); 508 509 /* Find min/max color */ 510 mn = mx = block[3]; 511 for (y = 0; y < 4; y++) { 512 for (x = 0; x < 4; x++) { 513 int val = block[3 + x * 4 + y * stride]; 514 if (val < mn) 515 mn = val; 516 else if (val > mx) 517 mx = val; 518 } 519 } 520 521 /* Encode them */ 522 dst[0] = (uint8_t) mx; 523 dst[1] = (uint8_t) mn; 524 dst += 2; 525 526 /* Mono-alpha shortcut */ 527 if (mn == mx) 528 return; 529 530 /* Determine bias and emit color indices. 531 * Given the choice of mx/mn, these indices are optimal: 532 * fgiesen.wordpress.com/2009/12/15/dxt5-alpha-block-index-determination */ 533 dist = mx - mn; 534 535 dist4 = dist * 4; 536 dist2 = dist * 2; 537 if (dist < 8) 538 bias = dist - 1 - mn * 7; 539 else 540 bias = dist / 2 + 2 - mn * 7; 541 542 for (y = 0; y < 4; y++) { 543 for (x = 0; x < 4; x++) { 544 int alp = block[3 + x * 4 + y * stride] * 7 + bias; 545 int ind, tmp; 546 547 /* This is a "linear scale" lerp factor between 0 (val=min) 548 * and 7 (val=max) to select index. */ 549 tmp = (alp >= dist4) ? -1 : 0; 550 ind = tmp & 4; 551 alp -= dist4 & tmp; 552 tmp = (alp >= dist2) ? -1 : 0; 553 ind += tmp & 2; 554 alp -= dist2 & tmp; 555 ind += (alp >= dist); 556 557 /* Turn linear scale into DXT index (0/1 are extreme points) */ 558 ind = -ind & 7; 559 ind ^= (2 > ind); 560 561 /* Write index */ 562 mask |= ind << bits; 563 bits += 3; 564 if (bits >= 8) { 565 *dst++ = mask; 566 mask >>= 8; 567 bits -= 8; 568 } 569 } 570 } 571} 572 573/** 574 * Convert a RGBA buffer to unscaled YCoCg. 575 * Scale is usually introduced to avoid banding over a certain range of colors, 576 * but this version of the algorithm does not introduce it as much as other 577 * implementations, allowing for a simpler and faster conversion. 578 */ 579static void rgba2ycocg(uint8_t *dst, const uint8_t *pixel) 580{ 581 int r = pixel[0]; 582 int g = (pixel[1] + 1) >> 1; 583 int b = pixel[2]; 584 int t = (2 + r + b) >> 2; 585 586 dst[0] = av_clip_uint8(128 + ((r - b + 1) >> 1)); /* Co */ 587 dst[1] = av_clip_uint8(128 + g - t); /* Cg */ 588 dst[2] = 0; 589 dst[3] = av_clip_uint8(g + t); /* Y */ 590} 591 592/** 593 * Compress one block of RGBA pixels in a DXT1 texture and store the 594 * resulting bytes in 'dst'. Alpha is not preserved. 595 * 596 * @param dst output buffer. 597 * @param stride scanline in bytes. 598 * @param block block to compress. 599 * @return how much texture data has been written. 600 */ 601static int dxt1_block(uint8_t *dst, ptrdiff_t stride, const uint8_t *block) 602{ 603 compress_color(dst, stride, block); 604 605 return 8; 606} 607 608/** 609 * Compress one block of RGBA pixels in a DXT5 texture and store the 610 * resulting bytes in 'dst'. Alpha is preserved. 611 * 612 * @param dst output buffer. 613 * @param stride scanline in bytes. 614 * @param block block to compress. 615 * @return how much texture data has been written. 616 */ 617static int dxt5_block(uint8_t *dst, ptrdiff_t stride, const uint8_t *block) 618{ 619 compress_alpha(dst, stride, block); 620 compress_color(dst + 8, stride, block); 621 622 return 16; 623} 624 625/** 626 * Compress one block of RGBA pixels in a DXT5-YCoCg texture and store the 627 * resulting bytes in 'dst'. Alpha is not preserved. 628 * 629 * @param dst output buffer. 630 * @param stride scanline in bytes. 631 * @param block block to compress. 632 * @return how much texture data has been written. 633 */ 634static int dxt5ys_block(uint8_t *dst, ptrdiff_t stride, const uint8_t *block) 635{ 636 int x, y; 637 uint8_t reorder[64]; 638 639 /* Reorder the components and then run a normal DXT5 compression. */ 640 for (y = 0; y < 4; y++) 641 for (x = 0; x < 4; x++) 642 rgba2ycocg(reorder + x * 4 + y * 16, block + x * 4 + y * stride); 643 644 compress_alpha(dst + 0, 16, reorder); 645 compress_color(dst + 8, 16, reorder); 646 647 return 16; 648} 649 650/** 651 * Compress one block of RGBA pixels in a RGTC1U texture and store the 652 * resulting bytes in 'dst'. Use the alpha channel of the input image. 653 * 654 * @param dst output buffer. 655 * @param stride scanline in bytes. 656 * @param block block to compress. 657 * @return how much texture data has been written. 658 */ 659static int rgtc1u_alpha_block(uint8_t *dst, ptrdiff_t stride, const uint8_t *block) 660{ 661 compress_alpha(dst, stride, block); 662 663 return 8; 664} 665 666av_cold void ff_texturedspenc_init(TextureDSPContext *c) 667{ 668 c->dxt1_block = dxt1_block; 669 c->dxt5_block = dxt5_block; 670 c->dxt5ys_block = dxt5ys_block; 671 c->rgtc1u_alpha_block = rgtc1u_alpha_block; 672} 673 674#define TEXTUREDSP_FUNC_NAME ff_texturedsp_compress_thread 675#define TEXTUREDSP_TEX_FUNC(a, b, c) tex_funct(c, b, a) 676#include "texturedsp_template.c" 677