Details | Last modification | View Log | RSS feed
| Rev | Author | Line No. | Line |
|---|---|---|---|
| 716 | lvd | 1 | #include "std.h" |
| 2 | |||
| 3 | #include "emul.h" |
||
| 4 | #include "vars.h" |
||
| 5 | #include "draw.h" |
||
| 6 | #include "dxrcopy.h" |
||
| 7 | |||
| 8 | // #define QUAD_BUFFER // tests show that this variant is slower, even in noflic mode |
||
| 9 | |||
| 10 | void line32_nf(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 11 | { |
||
| 12 | for (unsigned x = 0; x < temp.scx*4; x += 32) { |
||
| 13 | unsigned char byte = *src; |
||
| 14 | unsigned *t1 = tab + src[1]; |
||
| 15 | unsigned char byt1 = src[rb2_offs]; |
||
| 16 | unsigned *t2 = tab + src[rb2_offs+1]; |
||
| 17 | src += 2; |
||
| 18 | |||
| 19 | *(unsigned*)(dst+x) = t1[(byte << 1) & 0x100] + |
||
| 20 | t2[(byt1 << 1) & 0x100]; |
||
| 21 | *(unsigned*)(dst+x+4) = t1[(byte << 2) & 0x100] + |
||
| 22 | t2[(byt1 << 2) & 0x100]; |
||
| 23 | *(unsigned*)(dst+x+8) = t1[(byte << 3) & 0x100] + |
||
| 24 | t2[(byt1 << 3) & 0x100]; |
||
| 25 | *(unsigned*)(dst+x+12) = t1[(byte << 4) & 0x100] + |
||
| 26 | t2[(byt1 << 4) & 0x100]; |
||
| 27 | *(unsigned*)(dst+x+16) = t1[(byte << 5) & 0x100] + |
||
| 28 | t2[(byt1 << 5) & 0x100]; |
||
| 29 | *(unsigned*)(dst+x+20) = t1[(byte << 6) & 0x100] + |
||
| 30 | t2[(byt1 << 6) & 0x100]; |
||
| 31 | *(unsigned*)(dst+x+24) = t1[(byte << 7) & 0x100] + |
||
| 32 | t2[(byt1 << 7) & 0x100]; |
||
| 33 | *(unsigned*)(dst+x+28) = t1[(byte << 8) & 0x100] + |
||
| 34 | t2[(byt1 << 8) & 0x100]; |
||
| 35 | } |
||
| 36 | } |
||
| 37 | |||
| 38 | void line32d_nf(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 39 | { |
||
| 40 | for (unsigned x = 0; x < temp.scx*8; x += 64) { |
||
| 41 | unsigned char byte = *src; |
||
| 42 | unsigned *t1 = tab + src[1]; |
||
| 43 | unsigned char byt1 = src[rb2_offs]; |
||
| 44 | unsigned *t2 = tab + src[rb2_offs+1]; |
||
| 45 | src += 2; |
||
| 46 | |||
| 47 | *(unsigned*)(dst+x) = |
||
| 48 | *(unsigned*)(dst+x+4) = |
||
| 49 | t1[(byte << 1) & 0x100] + |
||
| 50 | t2[(byt1 << 1) & 0x100]; |
||
| 51 | *(unsigned*)(dst+x+8) = |
||
| 52 | *(unsigned*)(dst+x+12) = |
||
| 53 | t1[(byte << 2) & 0x100] + |
||
| 54 | t2[(byt1 << 2) & 0x100]; |
||
| 55 | *(unsigned*)(dst+x+16) = |
||
| 56 | *(unsigned*)(dst+x+20) = |
||
| 57 | t1[(byte << 3) & 0x100] + |
||
| 58 | t2[(byt1 << 3) & 0x100]; |
||
| 59 | *(unsigned*)(dst+x+24) = |
||
| 60 | *(unsigned*)(dst+x+28) = |
||
| 61 | t1[(byte << 4) & 0x100] + |
||
| 62 | t2[(byt1 << 4) & 0x100]; |
||
| 63 | *(unsigned*)(dst+x+32) = |
||
| 64 | *(unsigned*)(dst+x+36) = |
||
| 65 | t1[(byte << 5) & 0x100] + |
||
| 66 | t2[(byt1 << 5) & 0x100]; |
||
| 67 | *(unsigned*)(dst+x+40) = |
||
| 68 | *(unsigned*)(dst+x+44) = |
||
| 69 | t1[(byte << 6) & 0x100] + |
||
| 70 | t2[(byt1 << 6) & 0x100]; |
||
| 71 | *(unsigned*)(dst+x+48) = |
||
| 72 | *(unsigned*)(dst+x+52) = |
||
| 73 | t1[(byte << 7) & 0x100] + |
||
| 74 | t2[(byt1 << 7) & 0x100]; |
||
| 75 | *(unsigned*)(dst+x+56) = |
||
| 76 | *(unsigned*)(dst+x+60) = |
||
| 77 | t1[(byte << 8) & 0x100] + |
||
| 78 | t2[(byt1 << 8) & 0x100]; |
||
| 79 | } |
||
| 80 | } |
||
| 81 | |||
| 82 | void line32t_nf(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 83 | { |
||
| 84 | u32 *d = (u32 *)dst; |
||
| 85 | for (unsigned x = 0, i = 0; x < temp.scx*3; x += 24, i += 2) |
||
| 86 | { |
||
| 87 | u8 byte1 = src[i+0]; |
||
| 88 | unsigned *t1 = tab + src[i+1]; |
||
| 89 | u8 byte2 = src[i+rb2_offs]; |
||
| 90 | unsigned *t2 = tab + src[i+rb2_offs+1]; |
||
| 91 | |||
| 92 | u32 paper1 = t1[0]; |
||
| 93 | u32 ink1 = t1[0x100]; |
||
| 94 | |||
| 95 | u32 paper2 = t2[0]; |
||
| 96 | u32 ink2 = t2[0x100]; |
||
| 97 | |||
| 98 | d[x+0] = |
||
| 99 | d[x+1] = |
||
| 100 | d[x+2] = ((byte1 & 0x80) ? ink1 : paper1) + ((byte2 & 0x80) ? ink2 : paper2); |
||
| 101 | |||
| 102 | d[x+3] = |
||
| 103 | d[x+4] = |
||
| 104 | d[x+5] = ((byte1 & 0x40) ? ink1 : paper1) + ((byte2 & 0x40) ? ink2 : paper2); |
||
| 105 | |||
| 106 | d[x+6] = |
||
| 107 | d[x+7] = |
||
| 108 | d[x+8] = ((byte1 & 0x20) ? ink1 : paper1) + ((byte2 & 0x20) ? ink2 : paper2); |
||
| 109 | |||
| 110 | d[x+9] = |
||
| 111 | d[x+10] = |
||
| 112 | d[x+11] = ((byte1 & 0x10) ? ink1 : paper1) + ((byte2 & 0x10) ? ink2 : paper2); |
||
| 113 | |||
| 114 | d[x+12] = |
||
| 115 | d[x+13] = |
||
| 116 | d[x+14] = ((byte1 & 0x08) ? ink1 : paper1) + ((byte2 & 0x08) ? ink2 : paper2); |
||
| 117 | |||
| 118 | d[x+15] = |
||
| 119 | d[x+16] = |
||
| 120 | d[x+17] = ((byte1 & 0x04) ? ink1 : paper1) + ((byte2 & 0x04) ? ink2 : paper2); |
||
| 121 | |||
| 122 | d[x+18] = |
||
| 123 | d[x+19] = |
||
| 124 | d[x+20] = ((byte1 & 0x02) ? ink1 : paper1) + ((byte2 & 0x02) ? ink2 : paper2); |
||
| 125 | |||
| 126 | d[x+21] = |
||
| 127 | d[x+22] = |
||
| 128 | d[x+23] = ((byte1 & 0x01) ? ink1 : paper1) + ((byte2 & 0x01) ? ink2 : paper2); |
||
| 129 | } |
||
| 130 | } |
||
| 131 | |||
| 132 | void line32q_nf(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 133 | { |
||
| 134 | for (unsigned x = 0; x < temp.scx*16; x += 128) { |
||
| 135 | unsigned char byte = *src; |
||
| 136 | unsigned *t1 = tab + src[1]; |
||
| 137 | unsigned char byt1 = src[rb2_offs]; |
||
| 138 | unsigned *t2 = tab + src[rb2_offs+1]; |
||
| 139 | src += 2; |
||
| 140 | |||
| 141 | *(unsigned*)(dst+x+0x00) = |
||
| 142 | *(unsigned*)(dst+x+0x04) = |
||
| 143 | *(unsigned*)(dst+x+0x08) = |
||
| 144 | *(unsigned*)(dst+x+0x0C) = |
||
| 145 | t1[(byte << 1) & 0x100] + |
||
| 146 | t2[(byt1 << 1) & 0x100]; |
||
| 147 | *(unsigned*)(dst+x+0x10) = |
||
| 148 | *(unsigned*)(dst+x+0x14) = |
||
| 149 | *(unsigned*)(dst+x+0x18) = |
||
| 150 | *(unsigned*)(dst+x+0x1C) = |
||
| 151 | t1[(byte << 2) & 0x100] + |
||
| 152 | t2[(byt1 << 2) & 0x100]; |
||
| 153 | *(unsigned*)(dst+x+0x20) = |
||
| 154 | *(unsigned*)(dst+x+0x24) = |
||
| 155 | *(unsigned*)(dst+x+0x28) = |
||
| 156 | *(unsigned*)(dst+x+0x2C) = |
||
| 157 | t1[(byte << 3) & 0x100] + |
||
| 158 | t2[(byt1 << 3) & 0x100]; |
||
| 159 | *(unsigned*)(dst+x+0x30) = |
||
| 160 | *(unsigned*)(dst+x+0x34) = |
||
| 161 | *(unsigned*)(dst+x+0x38) = |
||
| 162 | *(unsigned*)(dst+x+0x3C) = |
||
| 163 | t1[(byte << 4) & 0x100] + |
||
| 164 | t2[(byt1 << 4) & 0x100]; |
||
| 165 | *(unsigned*)(dst+x+0x40) = |
||
| 166 | *(unsigned*)(dst+x+0x44) = |
||
| 167 | *(unsigned*)(dst+x+0x48) = |
||
| 168 | *(unsigned*)(dst+x+0x4C) = |
||
| 169 | t1[(byte << 5) & 0x100] + |
||
| 170 | t2[(byt1 << 5) & 0x100]; |
||
| 171 | *(unsigned*)(dst+x+0x50) = |
||
| 172 | *(unsigned*)(dst+x+0x54) = |
||
| 173 | *(unsigned*)(dst+x+0x58) = |
||
| 174 | *(unsigned*)(dst+x+0x5C) = |
||
| 175 | t1[(byte << 6) & 0x100] + |
||
| 176 | t2[(byt1 << 6) & 0x100]; |
||
| 177 | *(unsigned*)(dst+x+0x60) = |
||
| 178 | *(unsigned*)(dst+x+0x64) = |
||
| 179 | *(unsigned*)(dst+x+0x68) = |
||
| 180 | *(unsigned*)(dst+x+0x6C) = |
||
| 181 | t1[(byte << 7) & 0x100] + |
||
| 182 | t2[(byt1 << 7) & 0x100]; |
||
| 183 | *(unsigned*)(dst+x+0x70) = |
||
| 184 | *(unsigned*)(dst+x+0x74) = |
||
| 185 | *(unsigned*)(dst+x+0x78) = |
||
| 186 | *(unsigned*)(dst+x+0x7C) = |
||
| 187 | t1[(byte << 8) & 0x100] + |
||
| 188 | t2[(byt1 << 8) & 0x100]; |
||
| 189 | } |
||
| 190 | } |
||
| 191 | |||
| 192 | #ifdef MOD_SSE2 |
||
| 193 | void line32(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 194 | { |
||
| 195 | __m128i *d = (__m128i *)dst; |
||
| 196 | __m128i m1, m2; |
||
| 197 | m1 = _mm_set_epi32(0x10, 0x20, 0x40, 0x80); |
||
| 198 | m2 = _mm_set_epi32(0x1, 0x2, 0x4, 0x8); |
||
| 199 | |||
| 200 | for (unsigned x = 0, i = 0; x < temp.scx / 4; x += 2, i += 2) |
||
| 201 | { |
||
| 202 | unsigned byte = src[i]; |
||
| 203 | unsigned attr = src[i+1]; |
||
| 204 | unsigned ink = tab[attr + 0x100]; |
||
| 205 | unsigned paper = tab[attr]; |
||
| 206 | |||
| 207 | __m128i b, b1, b2; |
||
| 208 | __m128i r1, r2; |
||
| 209 | __m128i iv, pv; |
||
| 210 | __m128i im1, pm1, im2, pm2; |
||
| 211 | __m128i vr1, vr2; |
||
| 212 | |||
| 213 | b = _mm_set1_epi32(byte); |
||
| 214 | iv = _mm_set1_epi32(ink); |
||
| 215 | pv = _mm_set1_epi32(paper); |
||
| 216 | |||
| 217 | b1 = _mm_and_si128(b, m1); |
||
| 218 | r1 = _mm_cmpeq_epi32(b1, m1); |
||
| 219 | im1 = _mm_and_si128(r1, iv); |
||
| 220 | pm1 = _mm_andnot_si128(r1, pv); |
||
| 221 | vr1 = _mm_or_si128(im1, pm1); |
||
| 222 | _mm_store_si128(&d[x], vr1); |
||
| 223 | |||
| 224 | b2 = _mm_and_si128(b, m2); |
||
| 225 | r2 = _mm_cmpeq_epi32(b2, m2); |
||
| 226 | im2 = _mm_and_si128(r2, iv); |
||
| 227 | pm2 = _mm_andnot_si128(r2, pv); |
||
| 228 | vr2 = _mm_or_si128(im2, pm2); |
||
| 229 | _mm_store_si128(&d[x+1], vr2); |
||
| 230 | } |
||
| 231 | } |
||
| 232 | #else |
||
| 233 | void line32(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 234 | { |
||
| 235 | unsigned *d = (unsigned *)dst; |
||
| 236 | for (unsigned x = 0, i = 0; x < temp.scx; x += 8, i += 2) |
||
| 237 | { |
||
| 238 | unsigned byte = src[i]; |
||
| 239 | unsigned attr = src[i+1]; |
||
| 240 | unsigned ink = tab[attr + 0x100]; |
||
| 241 | unsigned paper = tab[attr]; |
||
| 242 | |||
| 243 | d[x] = (byte & 0x80) ? ink : paper; // 7 |
||
| 244 | d[x+1] = (byte & 0x40) ? ink : paper; // 6 |
||
| 245 | d[x+2] = (byte & 0x20) ? ink : paper; // 5 |
||
| 246 | d[x+3] = (byte & 0x10) ? ink : paper; // 4 |
||
| 247 | |||
| 248 | d[x+4] = (byte & 0x08) ? ink : paper; // 3 |
||
| 249 | d[x+5] = (byte & 0x04) ? ink : paper; // 2 |
||
| 250 | d[x+6] = (byte & 0x02) ? ink : paper; // 1 |
||
| 251 | d[x+7] = (byte & 0x01) ? ink : paper; // 0 |
||
| 252 | } |
||
| 253 | } |
||
| 254 | #endif |
||
| 255 | |||
| 256 | #ifdef MOD_SSE2 |
||
| 257 | void line32d(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 258 | { |
||
| 259 | __m128i *d = (__m128i *)dst; |
||
| 260 | __m128i m1, m2; |
||
| 261 | m1 = _mm_set_epi32(0x10, 0x20, 0x40, 0x80); |
||
| 262 | m2 = _mm_set_epi32(0x1, 0x2, 0x4, 0x8); |
||
| 263 | |||
| 264 | for (unsigned x = 0, i = 0; x < temp.scx / 2; x += 4, i += 2) |
||
| 265 | { |
||
| 266 | unsigned byte = src[i]; |
||
| 267 | unsigned attr = src[i+1]; |
||
| 268 | unsigned ink = tab[attr + 0x100]; |
||
| 269 | unsigned paper = tab[attr]; |
||
| 270 | |||
| 271 | __m128i b, b1, b2; |
||
| 272 | __m128i r1, r2; |
||
| 273 | __m128i iv, pv; |
||
| 274 | __m128i im1, pm1, im2, pm2; |
||
| 275 | __m128i vr1, vr2; |
||
| 276 | __m128i l1, l2; |
||
| 277 | __m128i h1, h2; |
||
| 278 | |||
| 279 | b = _mm_set1_epi32(byte); |
||
| 280 | iv = _mm_set1_epi32(ink); |
||
| 281 | pv = _mm_set1_epi32(paper); |
||
| 282 | |||
| 283 | b1 = _mm_and_si128(b, m1); |
||
| 284 | r1 = _mm_cmpeq_epi32(b1, m1); |
||
| 285 | im1 = _mm_and_si128(r1, iv); |
||
| 286 | pm1 = _mm_andnot_si128(r1, pv); |
||
| 287 | vr1 = _mm_or_si128(im1, pm1); |
||
| 288 | |||
| 289 | l1 = _mm_unpacklo_epi32(vr1, vr1); |
||
| 290 | _mm_store_si128(&d[x], l1); |
||
| 291 | h1 = _mm_unpackhi_epi32(vr1, vr1); |
||
| 292 | _mm_store_si128(&d[x+1], h1); |
||
| 293 | |||
| 294 | b2 = _mm_and_si128(b, m2); |
||
| 295 | r2 = _mm_cmpeq_epi32(b2, m2); |
||
| 296 | im2 = _mm_and_si128(r2, iv); |
||
| 297 | pm2 = _mm_andnot_si128(r2, pv); |
||
| 298 | vr2 = _mm_or_si128(im2, pm2); |
||
| 299 | |||
| 300 | l2 = _mm_unpacklo_epi32(vr2, vr2); |
||
| 301 | _mm_store_si128(&d[x+2], l2); |
||
| 302 | h2 = _mm_unpackhi_epi32(vr2, vr2); |
||
| 303 | _mm_store_si128(&d[x+3], h2); |
||
| 304 | } |
||
| 305 | } |
||
| 306 | #else |
||
| 307 | void line32d(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 308 | { |
||
| 309 | unsigned *d = (unsigned *)dst; |
||
| 310 | for (unsigned x = 0, i = 0; x < temp.scx * 2; x += 16, i+= 2) |
||
| 311 | { |
||
| 312 | // [vv] Òàêîé ïîðÿäîê çàïèñè ïîçâîëÿåò icl ãåíåðèðîâàòü cmovcc âìåñòî jcc |
||
| 313 | unsigned char byte = src[i]; |
||
| 314 | unsigned char attr = src[i+1]; |
||
| 315 | unsigned ink = tab[attr + 0x100]; |
||
| 316 | unsigned paper = tab[attr]; |
||
| 317 | |||
| 318 | d[x] = d[x+1] = (byte & 0x80) ? ink : paper; // 7 |
||
| 319 | d[x+2] = d[x+3] = (byte & 0x40) ? ink : paper; // 6 |
||
| 320 | d[x+4] = d[x+5] = (byte & 0x20) ? ink : paper; // 5 |
||
| 321 | d[x+6] = d[x+7] = (byte & 0x10) ? ink : paper; // 4 |
||
| 322 | d[x+8] = d[x+9] = (byte & 0x08) ? ink : paper; // 3 |
||
| 323 | d[x+10] = d[x+11] = (byte & 0x04) ? ink : paper; // 2 |
||
| 324 | d[x+12] = d[x+13] = (byte & 0x02) ? ink : paper; // 1 |
||
| 325 | d[x+14] = d[x+15] = (byte & 0x01) ? ink : paper; // 0 |
||
| 326 | } |
||
| 327 | } |
||
| 328 | #endif |
||
| 329 | |||
| 330 | void line32t(unsigned char *dst, const unsigned char *src, const unsigned *tab) |
||
| 331 | { |
||
| 332 | unsigned *d = (unsigned *)dst; |
||
| 333 | for (unsigned x = 0, i = 0; x < temp.scx * 3; x += 3*8, i += 2) |
||
| 334 | { |
||
| 335 | unsigned char byte = src[i]; |
||
| 336 | unsigned attr = src[i + 1]; |
||
| 337 | unsigned ink = tab[attr + 0x100]; |
||
| 338 | unsigned paper = tab[attr]; |
||
| 339 | |||
| 340 | d[x] = d[x + 1] = d[x + 2] = (byte & 0x80) ? ink : paper; |
||
| 341 | d[x + 3] = d[x + 4] = d[x + 5] = (byte & 0x40) ? ink : paper; |
||
| 342 | d[x + 6] = d[x + 7] = d[x + 8] = (byte & 0x20) ? ink : paper; |
||
| 343 | d[x + 9] = d[x + 10] = d[x + 11] = (byte & 0x10) ? ink : paper; |
||
| 344 | d[x + 12] = d[x + 13] = d[x + 14] = (byte & 0x08) ? ink : paper; |
||
| 345 | d[x + 15] = d[x + 16] = d[x + 17] = (byte & 0x04) ? ink : paper; |
||
| 346 | d[x + 18] = d[x + 19] = d[x + 20] = (byte & 0x02) ? ink : paper; |
||
| 347 | d[x + 21] = d[x + 22] = d[x + 23] = (byte & 0x01) ? ink : paper; |
||
| 348 | } |
||
| 349 | } |
||
| 350 | |||
| 351 | void line32q(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 352 | { |
||
| 353 | for (unsigned x = 0; x < temp.scx*16; x += 128) { |
||
| 354 | unsigned char byte = *src++; |
||
| 355 | unsigned *t = tab + *src++; |
||
| 356 | *(unsigned*)(dst+x+0x00) = |
||
| 357 | *(unsigned*)(dst+x+0x04) = |
||
| 358 | *(unsigned*)(dst+x+0x08) = |
||
| 359 | *(unsigned*)(dst+x+0x0C) = |
||
| 360 | t[(byte << 1) & 0x100]; |
||
| 361 | *(unsigned*)(dst+x+0x10) = |
||
| 362 | *(unsigned*)(dst+x+0x14) = |
||
| 363 | *(unsigned*)(dst+x+0x18) = |
||
| 364 | *(unsigned*)(dst+x+0x1C) = |
||
| 365 | t[(byte << 2) & 0x100]; |
||
| 366 | *(unsigned*)(dst+x+0x20) = |
||
| 367 | *(unsigned*)(dst+x+0x24) = |
||
| 368 | *(unsigned*)(dst+x+0x28) = |
||
| 369 | *(unsigned*)(dst+x+0x2C) = |
||
| 370 | t[(byte << 3) & 0x100]; |
||
| 371 | *(unsigned*)(dst+x+0x30) = |
||
| 372 | *(unsigned*)(dst+x+0x34) = |
||
| 373 | *(unsigned*)(dst+x+0x38) = |
||
| 374 | *(unsigned*)(dst+x+0x3C) = |
||
| 375 | t[(byte << 4) & 0x100]; |
||
| 376 | *(unsigned*)(dst+x+0x40) = |
||
| 377 | *(unsigned*)(dst+x+0x44) = |
||
| 378 | *(unsigned*)(dst+x+0x48) = |
||
| 379 | *(unsigned*)(dst+x+0x4C) = |
||
| 380 | t[(byte << 5) & 0x100]; |
||
| 381 | *(unsigned*)(dst+x+0x50) = |
||
| 382 | *(unsigned*)(dst+x+0x54) = |
||
| 383 | *(unsigned*)(dst+x+0x58) = |
||
| 384 | *(unsigned*)(dst+x+0x5C) = |
||
| 385 | t[(byte << 6) & 0x100]; |
||
| 386 | *(unsigned*)(dst+x+0x60) = |
||
| 387 | *(unsigned*)(dst+x+0x64) = |
||
| 388 | *(unsigned*)(dst+x+0x68) = |
||
| 389 | *(unsigned*)(dst+x+0x6C) = |
||
| 390 | t[(byte << 7) & 0x100]; |
||
| 391 | *(unsigned*)(dst+x+0x70) = |
||
| 392 | *(unsigned*)(dst+x+0x74) = |
||
| 393 | *(unsigned*)(dst+x+0x78) = |
||
| 394 | *(unsigned*)(dst+x+0x7C) = |
||
| 395 | t[(byte << 8) & 0x100]; |
||
| 396 | } |
||
| 397 | } |
||
| 398 | |||
| 399 | void line16_nf(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 400 | { |
||
| 401 | for (unsigned x = 0; x < temp.scx*2; x += 32) { |
||
| 402 | unsigned s = *(unsigned*)src, attr = (s >> 6) & 0x3FC; |
||
| 403 | unsigned r = *(unsigned*)(src + rb2_offs), atr2 = (r >> 6) & 0x3FC; |
||
| 404 | *(unsigned*)(dst+x) = (tab[((s >> 6) & 3) + attr]) + |
||
| 405 | (tab[((r >> 6) & 3) + atr2]); |
||
| 406 | *(unsigned*)(dst+x+4) = (tab[((s >> 4) & 3) + attr]) + |
||
| 407 | (tab[((r >> 4) & 3) + atr2]); |
||
| 408 | *(unsigned*)(dst+x+8) = (tab[((s >> 2) & 3) + attr]) + |
||
| 409 | (tab[((r >> 2) & 3) + atr2]); |
||
| 410 | *(unsigned*)(dst+x+12)= (tab[((s >> 0) & 3) + attr]) + |
||
| 411 | (tab[((r >> 0) & 3) + atr2]); |
||
| 412 | attr = (s >> 22) & 0x3FC; atr2 = (r >> 22) & 0x3FC; |
||
| 413 | *(unsigned*)(dst+x+16)= (tab[((s >>22) & 3) + attr]) + |
||
| 414 | (tab[((r >>22) & 3) + atr2]); |
||
| 415 | *(unsigned*)(dst+x+20)= (tab[((s >>20) & 3) + attr]) + |
||
| 416 | (tab[((r >>20) & 3) + atr2]); |
||
| 417 | *(unsigned*)(dst+x+24)= (tab[((s >>18) & 3) + attr]) + |
||
| 418 | (tab[((r >>18) & 3) + atr2]); |
||
| 419 | *(unsigned*)(dst+x+28)= (tab[((s >>16) & 3) + attr]) + |
||
| 420 | (tab[((r >>16) & 3) + atr2]); |
||
| 421 | src += 4; |
||
| 422 | } |
||
| 423 | } |
||
| 424 | |||
| 425 | #define line16d_nf line32_nf |
||
| 426 | |||
| 427 | #define line16q line32d |
||
| 428 | #define line16q_nf line32d_nf |
||
| 429 | |||
| 430 | void line16t(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 431 | { |
||
| 432 | u16 *d = (u16 *)dst; |
||
| 433 | for (unsigned x = 0; x < temp.scx*3; x += 24) |
||
| 434 | { |
||
| 435 | unsigned char byte = *src++; |
||
| 436 | unsigned *t = tab + *src++; |
||
| 437 | u16 paper_yu = t[0]; |
||
| 438 | u16 paper_yv = t[0] >> 16; |
||
| 439 | u16 ink_yu = t[0x100]; |
||
| 440 | u16 ink_yv = t[0x100] >> 16; |
||
| 441 | |||
| 442 | d[x+0] = (byte & 0x80) ? ink_yu : paper_yu; |
||
| 443 | d[x+1] = (byte & 0x80) ? ink_yv : paper_yv; |
||
| 444 | d[x+2] = (byte & 0x80) ? ink_yu : paper_yu; |
||
| 445 | |||
| 446 | d[x+3] = (byte & 0x40) ? ink_yv : paper_yv; |
||
| 447 | d[x+4] = (byte & 0x40) ? ink_yu : paper_yu; |
||
| 448 | d[x+5] = (byte & 0x40) ? ink_yv : paper_yv; |
||
| 449 | |||
| 450 | d[x+6] = (byte & 0x20) ? ink_yu : paper_yu; |
||
| 451 | d[x+7] = (byte & 0x20) ? ink_yv : paper_yv; |
||
| 452 | d[x+8] = (byte & 0x20) ? ink_yu : paper_yu; |
||
| 453 | |||
| 454 | d[x+9] = (byte & 0x10) ? ink_yv : paper_yv; |
||
| 455 | d[x+10] = (byte & 0x10) ? ink_yu : paper_yu; |
||
| 456 | d[x+11] = (byte & 0x10) ? ink_yv : paper_yv; |
||
| 457 | |||
| 458 | d[x+12] = (byte & 0x08) ? ink_yu : paper_yu; |
||
| 459 | d[x+13] = (byte & 0x08) ? ink_yv : paper_yv; |
||
| 460 | d[x+14] = (byte & 0x08) ? ink_yu : paper_yu; |
||
| 461 | |||
| 462 | d[x+15] = (byte & 0x04) ? ink_yv : paper_yv; |
||
| 463 | d[x+16] = (byte & 0x04) ? ink_yu : paper_yu; |
||
| 464 | d[x+17] = (byte & 0x04) ? ink_yv : paper_yv; |
||
| 465 | |||
| 466 | d[x+18] = (byte & 0x02) ? ink_yu : paper_yu; |
||
| 467 | d[x+19] = (byte & 0x02) ? ink_yv : paper_yv; |
||
| 468 | d[x+20] = (byte & 0x02) ? ink_yu : paper_yu; |
||
| 469 | |||
| 470 | d[x+21] = (byte & 0x01) ? ink_yv : paper_yv; |
||
| 471 | d[x+22] = (byte & 0x01) ? ink_yu : paper_yu; |
||
| 472 | d[x+23] = (byte & 0x01) ? ink_yv : paper_yv; |
||
| 473 | } |
||
| 474 | } |
||
| 475 | |||
| 476 | void line16t_nf(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 477 | { |
||
| 478 | u16 *d = (u16 *)dst; |
||
| 479 | for (unsigned x = 0, i = 0; x < temp.scx*3; x += 24, i += 2) |
||
| 480 | { |
||
| 481 | u8 byte1 = src[i+0]; |
||
| 482 | unsigned *t1 = tab + src[i+1]; |
||
| 483 | u8 byte2 = src[i+rb2_offs]; |
||
| 484 | unsigned *t2 = tab + src[i+rb2_offs+1]; |
||
| 485 | |||
| 486 | u16 paper_yu1 = t1[0]; |
||
| 487 | u16 paper_yv1 = t1[0] >> 16; |
||
| 488 | u16 ink_yu1 = t1[0x100]; |
||
| 489 | u16 ink_yv1 = t1[0x100] >> 16; |
||
| 490 | |||
| 491 | u16 paper_yu2 = t2[0]; |
||
| 492 | u16 paper_yv2 = t2[0] >> 16; |
||
| 493 | u16 ink_yu2 = t2[0x100]; |
||
| 494 | u16 ink_yv2 = t2[0x100] >> 16; |
||
| 495 | |||
| 496 | d[x+0] = ((byte1 & 0x80) ? ink_yu1 : paper_yu1) + ((byte2 & 0x80) ? ink_yu2 : paper_yu2); |
||
| 497 | d[x+1] = ((byte1 & 0x80) ? ink_yv1 : paper_yv1) + ((byte2 & 0x80) ? ink_yv2 : paper_yv2); |
||
| 498 | d[x+2] = ((byte1 & 0x80) ? ink_yu1 : paper_yu1) + ((byte2 & 0x80) ? ink_yu2 : paper_yu2); |
||
| 499 | |||
| 500 | d[x+3] = ((byte1 & 0x40) ? ink_yv1 : paper_yv1) + ((byte2 & 0x40) ? ink_yv2 : paper_yv2); |
||
| 501 | d[x+4] = ((byte1 & 0x40) ? ink_yu1 : paper_yu1) + ((byte2 & 0x40) ? ink_yu2 : paper_yu2); |
||
| 502 | d[x+5] = ((byte1 & 0x40) ? ink_yv1 : paper_yv1) + ((byte2 & 0x40) ? ink_yv2 : paper_yv2); |
||
| 503 | |||
| 504 | d[x+6] = ((byte1 & 0x20) ? ink_yu1 : paper_yu1) + ((byte2 & 0x20) ? ink_yu2 : paper_yu2); |
||
| 505 | d[x+7] = ((byte1 & 0x20) ? ink_yv1 : paper_yv1) + ((byte2 & 0x20) ? ink_yv2 : paper_yv2); |
||
| 506 | d[x+8] = ((byte1 & 0x20) ? ink_yu1 : paper_yu1) + ((byte2 & 0x20) ? ink_yu2 : paper_yu2); |
||
| 507 | |||
| 508 | d[x+9] = ((byte1 & 0x10) ? ink_yv1 : paper_yv1) + ((byte2 & 0x10) ? ink_yv2 : paper_yv2); |
||
| 509 | d[x+10] = ((byte1 & 0x10) ? ink_yu1 : paper_yu1) + ((byte2 & 0x10) ? ink_yu2 : paper_yu2); |
||
| 510 | d[x+11] = ((byte1 & 0x10) ? ink_yv1 : paper_yv1) + ((byte2 & 0x10) ? ink_yv2 : paper_yv2); |
||
| 511 | |||
| 512 | d[x+12] = ((byte1 & 0x08) ? ink_yu1 : paper_yu1) + ((byte2 & 0x08) ? ink_yu2 : paper_yu2); |
||
| 513 | d[x+13] = ((byte1 & 0x08) ? ink_yv1 : paper_yv1) + ((byte2 & 0x08) ? ink_yv2 : paper_yv2); |
||
| 514 | d[x+14] = ((byte1 & 0x08) ? ink_yu1 : paper_yu1) + ((byte2 & 0x08) ? ink_yu2 : paper_yu2); |
||
| 515 | |||
| 516 | d[x+15] = ((byte1 & 0x04) ? ink_yv1 : paper_yv1) + ((byte2 & 0x04) ? ink_yv2 : paper_yv2); |
||
| 517 | d[x+16] = ((byte1 & 0x04) ? ink_yu1 : paper_yu1) + ((byte2 & 0x04) ? ink_yu2 : paper_yu2); |
||
| 518 | d[x+17] = ((byte1 & 0x04) ? ink_yv1 : paper_yv1) + ((byte2 & 0x04) ? ink_yv2 : paper_yv2); |
||
| 519 | |||
| 520 | d[x+18] = ((byte1 & 0x02) ? ink_yu1 : paper_yu1) + ((byte2 & 0x02) ? ink_yu2 : paper_yu2); |
||
| 521 | d[x+19] = ((byte1 & 0x02) ? ink_yv1 : paper_yv1) + ((byte2 & 0x02) ? ink_yv2 : paper_yv2); |
||
| 522 | d[x+20] = ((byte1 & 0x02) ? ink_yu1 : paper_yu1) + ((byte2 & 0x02) ? ink_yu2 : paper_yu2); |
||
| 523 | |||
| 524 | d[x+21] = ((byte1 & 0x01) ? ink_yv1 : paper_yv1) + ((byte2 & 0x01) ? ink_yv2 : paper_yv2); |
||
| 525 | d[x+22] = ((byte1 & 0x01) ? ink_yu1 : paper_yu1) + ((byte2 & 0x01) ? ink_yu2 : paper_yu2); |
||
| 526 | d[x+23] = ((byte1 & 0x01) ? ink_yv1 : paper_yv1) + ((byte2 & 0x01) ? ink_yv2 : paper_yv2); |
||
| 527 | } |
||
| 528 | } |
||
| 529 | |||
| 530 | void line8(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 531 | { |
||
| 532 | for (unsigned x = 0; x < temp.scx; x += 32) { |
||
| 533 | unsigned src0 = *(unsigned*)src, attr = (src0 >> 4) & 0xFF0; |
||
| 534 | *(unsigned*)(dst+x) = tab[((src0 >> 4) & 0xF) + attr]; |
||
| 535 | *(unsigned*)(dst+x+4) = tab[((src0 >> 0) & 0xF) + attr]; |
||
| 536 | attr = (src0 >> 20) & 0xFF0; |
||
| 537 | *(unsigned*)(dst+x+8) = tab[((src0 >> 20) & 0xF) + attr]; |
||
| 538 | *(unsigned*)(dst+x+12) = tab[((src0 >> 16) & 0xF) + attr]; |
||
| 539 | src0 = *(unsigned*)(src+4), attr = (src0 >> 4) & 0xFF0; |
||
| 540 | *(unsigned*)(dst+x+16) = tab[((src0 >> 4) & 0xF) + attr]; |
||
| 541 | *(unsigned*)(dst+x+20) = tab[((src0 >> 0) & 0xF) + attr]; |
||
| 542 | attr = (src0 >> 20) & 0xFF0; |
||
| 543 | *(unsigned*)(dst+x+24) = tab[((src0 >> 20) & 0xF) + attr]; |
||
| 544 | *(unsigned*)(dst+x+28) = tab[((src0 >> 16) & 0xF) + attr]; |
||
| 545 | src += 8; |
||
| 546 | } |
||
| 547 | } |
||
| 548 | |||
| 549 | void line8_nf(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 550 | { |
||
| 551 | for (unsigned x = 0; x < temp.scx; x += 32) { |
||
| 552 | unsigned s = *(unsigned*)src, attr = (s >> 4) & 0xFF0; |
||
| 553 | unsigned r = *(unsigned*)(src + rb2_offs), atr2 = (r >> 4) & 0xFF0; |
||
| 554 | *(unsigned*)(dst+x) = (tab[((s >> 4) & 0xF) + attr] & 0x0F0F0F0F) + |
||
| 555 | (tab[((r >> 4) & 0xF) + atr2] & 0xF0F0F0F0); |
||
| 556 | *(unsigned*)(dst+x+4) = (tab[((s >> 0) & 0xF) + attr] & 0x0F0F0F0F) + |
||
| 557 | (tab[((r >> 0) & 0xF) + atr2] & 0xF0F0F0F0); |
||
| 558 | attr = (s >> 20) & 0xFF0; atr2 = (r >> 20) & 0xFF0; |
||
| 559 | *(unsigned*)(dst+x+8) = (tab[((s >> 20) & 0xF) + attr] & 0x0F0F0F0F) + |
||
| 560 | (tab[((r >> 20) & 0xF) + atr2] & 0xF0F0F0F0); |
||
| 561 | *(unsigned*)(dst+x+12) = (tab[((s >> 16) & 0xF) + attr] & 0x0F0F0F0F) + |
||
| 562 | (tab[((r >> 16) & 0xF) + atr2] & 0xF0F0F0F0); |
||
| 563 | s = *(unsigned*)(src+4), attr = (s >> 4) & 0xFF0; |
||
| 564 | r = *(unsigned*)(src+rb2_offs+4), atr2 = (r >> 4) & 0xFF0; |
||
| 565 | *(unsigned*)(dst+x+16) = (tab[((s >> 4) & 0xF) + attr] & 0x0F0F0F0F) + |
||
| 566 | (tab[((r >> 4) & 0xF) + atr2] & 0xF0F0F0F0); |
||
| 567 | *(unsigned*)(dst+x+20) = (tab[((s >> 0) & 0xF) + attr] & 0x0F0F0F0F) + |
||
| 568 | (tab[((r >> 0) & 0xF) + atr2] & 0xF0F0F0F0); |
||
| 569 | attr = (s >> 20) & 0xFF0; atr2 = (r >> 20) & 0xFF0; |
||
| 570 | *(unsigned*)(dst+x+24) = (tab[((s >> 20) & 0xF) + attr] & 0x0F0F0F0F) + |
||
| 571 | (tab[((r >> 20) & 0xF) + atr2] & 0xF0F0F0F0); |
||
| 572 | *(unsigned*)(dst+x+28) = (tab[((s >> 16) & 0xF) + attr] & 0x0F0F0F0F) + |
||
| 573 | (tab[((r >> 16) & 0xF) + atr2] & 0xF0F0F0F0); |
||
| 574 | src += 8; |
||
| 575 | } |
||
| 576 | } |
||
| 577 | |||
| 578 | void line8d(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 579 | { |
||
| 580 | for (unsigned x = 0; x < temp.scx*2; x += 32) { |
||
| 581 | unsigned s = *(unsigned*)src, attr = (s >> 6) & 0x3FC; |
||
| 582 | *(unsigned*)(dst+x) = tab[((s >> 6) & 3) + attr]; |
||
| 583 | *(unsigned*)(dst+x+4) = tab[((s >> 4) & 3) + attr]; |
||
| 584 | *(unsigned*)(dst+x+8) = tab[((s >> 2) & 3) + attr]; |
||
| 585 | *(unsigned*)(dst+x+12)= tab[((s >> 0) & 3) + attr]; |
||
| 586 | attr = (s >> 22) & 0x3FC; |
||
| 587 | *(unsigned*)(dst+x+16)= tab[((s >>22) & 3) + attr]; |
||
| 588 | *(unsigned*)(dst+x+20)= tab[((s >>20) & 3) + attr]; |
||
| 589 | *(unsigned*)(dst+x+24)= tab[((s >>18) & 3) + attr]; |
||
| 590 | *(unsigned*)(dst+x+28)= tab[((s >>16) & 3) + attr]; |
||
| 591 | src += 4; |
||
| 592 | } |
||
| 593 | } |
||
| 594 | |||
| 595 | |||
| 596 | void line8t(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 597 | { |
||
| 598 | for (unsigned x = 0; x < temp.scx*3; x += 24) |
||
| 599 | { |
||
| 600 | unsigned char byte = *src++; |
||
| 601 | unsigned *t = tab + *src++; |
||
| 602 | dst[x+0] = dst[x+1] = dst[x+2] = t[(byte << 1) & 0x100]; |
||
| 603 | dst[x+3] = dst[x+4] = dst[x+5] = t[(byte << 2) & 0x100]; |
||
| 604 | dst[x+6] = dst[x+7] = dst[x+8] = t[(byte << 3) & 0x100]; |
||
| 605 | dst[x+9] = dst[x+10] = dst[x+11] = t[(byte << 4) & 0x100]; |
||
| 606 | dst[x+12] = dst[x+13] = dst[x+14] = t[(byte << 5) & 0x100]; |
||
| 607 | dst[x+15] = dst[x+16] = dst[x+17] = t[(byte << 6) & 0x100]; |
||
| 608 | dst[x+18] = dst[x+19] = dst[x+20] = t[(byte << 7) & 0x100]; |
||
| 609 | dst[x+21] = dst[x+22] = dst[x+23] = t[(byte << 8) & 0x100]; |
||
| 610 | } |
||
| 611 | } |
||
| 612 | |||
| 613 | void line8q(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 614 | { |
||
| 615 | for (unsigned x = 0; x < temp.scx*4; x += 32) { |
||
| 616 | unsigned char byte = *src++; |
||
| 617 | unsigned *t = tab + *src++; |
||
| 618 | *(unsigned*)(dst+x+0x00) = t[(byte << 1) & 0x100]; |
||
| 619 | *(unsigned*)(dst+x+0x04) = t[(byte << 2) & 0x100]; |
||
| 620 | *(unsigned*)(dst+x+0x08) = t[(byte << 3) & 0x100]; |
||
| 621 | *(unsigned*)(dst+x+0x0C) = t[(byte << 4) & 0x100]; |
||
| 622 | *(unsigned*)(dst+x+0x10) = t[(byte << 5) & 0x100]; |
||
| 623 | *(unsigned*)(dst+x+0x14) = t[(byte << 6) & 0x100]; |
||
| 624 | *(unsigned*)(dst+x+0x18) = t[(byte << 7) & 0x100]; |
||
| 625 | *(unsigned*)(dst+x+0x1C) = t[(byte << 8) & 0x100]; |
||
| 626 | } |
||
| 627 | } |
||
| 628 | |||
| 629 | void line8d_nf(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 630 | { |
||
| 631 | for (unsigned x = 0; x < temp.scx*2; x += 32) { |
||
| 632 | unsigned s = *(unsigned*)src, attr = (s >> 6) & 0x3FC; |
||
| 633 | unsigned r = *(unsigned*)(src + rb2_offs), atr2 = (r >> 6) & 0x3FC; |
||
| 634 | *(unsigned*)(dst+x) = (tab[((s >> 6) & 3) + attr] & 0x0F0F0F0F) + |
||
| 635 | (tab[((r >> 6) & 3) + atr2] & 0xF0F0F0F0); |
||
| 636 | *(unsigned*)(dst+x+4) = (tab[((s >> 4) & 3) + attr] & 0x0F0F0F0F) + |
||
| 637 | (tab[((r >> 4) & 3) + atr2] & 0xF0F0F0F0); |
||
| 638 | *(unsigned*)(dst+x+8) = (tab[((s >> 2) & 3) + attr] & 0x0F0F0F0F) + |
||
| 639 | (tab[((r >> 2) & 3) + atr2] & 0xF0F0F0F0); |
||
| 640 | *(unsigned*)(dst+x+12)= (tab[((s >> 0) & 3) + attr] & 0x0F0F0F0F) + |
||
| 641 | (tab[((r >> 0) & 3) + atr2] & 0xF0F0F0F0); |
||
| 642 | attr = (s >> 22) & 0x3FC; atr2 = (r >> 22) & 0x3FC; |
||
| 643 | *(unsigned*)(dst+x+16)= (tab[((s >>22) & 3) + attr] & 0x0F0F0F0F) + |
||
| 644 | (tab[((r >>22) & 3) + atr2] & 0xF0F0F0F0); |
||
| 645 | *(unsigned*)(dst+x+20)= (tab[((s >>20) & 3) + attr] & 0x0F0F0F0F) + |
||
| 646 | (tab[((r >>20) & 3) + atr2] & 0xF0F0F0F0); |
||
| 647 | *(unsigned*)(dst+x+24)= (tab[((s >>18) & 3) + attr] & 0x0F0F0F0F) + |
||
| 648 | (tab[((r >>18) & 3) + atr2] & 0xF0F0F0F0); |
||
| 649 | *(unsigned*)(dst+x+28)= (tab[((s >>16) & 3) + attr] & 0x0F0F0F0F) + |
||
| 650 | (tab[((r >>16) & 3) + atr2] & 0xF0F0F0F0); |
||
| 651 | src += 4; |
||
| 652 | } |
||
| 653 | } |
||
| 654 | |||
| 655 | void line8t_nf(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 656 | { |
||
| 657 | for (unsigned x = 0, i = 0; x < temp.scx*3; x += 24, i += 2) |
||
| 658 | { |
||
| 659 | u32 byte1 = src[i+0]; |
||
| 660 | u32 byte2 = src[i+rb2_offs+0]; |
||
| 661 | unsigned *t1 = tab + src[i+1]; |
||
| 662 | unsigned *t2 = tab + src[i+rb2_offs+1]; |
||
| 663 | u8 ink1 = u8(t1[0x100] & 0x0F); |
||
| 664 | u8 ink2 = u8(t2[0x100] & 0xF0); |
||
| 665 | u8 paper1 = u8(t1[0] & 0x0F); |
||
| 666 | u8 paper2 = u8(t2[0] & 0xF0); |
||
| 667 | |||
| 668 | dst[x+0] = dst[x+1] = dst[x+2] = ((byte1 & 0x80) ? ink1 : paper1) + ((byte2 & 0x80) ? ink2 : paper2); |
||
| 669 | dst[x+3] = dst[x+4] = dst[x+5] = ((byte1 & 0x40) ? ink1 : paper1) + ((byte2 & 0x40) ? ink2 : paper2); |
||
| 670 | dst[x+6] = dst[x+7] = dst[x+8] = ((byte1 & 0x20) ? ink1 : paper1) + ((byte2 & 0x20) ? ink2 : paper2); |
||
| 671 | dst[x+9] = dst[x+10] = dst[x+11] = ((byte1 & 0x10) ? ink1 : paper1) + ((byte2 & 0x10) ? ink2 : paper2); |
||
| 672 | dst[x+12] = dst[x+13] = dst[x+14] = ((byte1 & 0x08) ? ink1 : paper1) + ((byte2 & 0x08) ? ink2 : paper2); |
||
| 673 | dst[x+15] = dst[x+16] = dst[x+17] = ((byte1 & 0x04) ? ink1 : paper1) + ((byte2 & 0x04) ? ink2 : paper2); |
||
| 674 | dst[x+18] = dst[x+19] = dst[x+20] = ((byte1 & 0x02) ? ink1 : paper1) + ((byte2 & 0x02) ? ink2 : paper2); |
||
| 675 | dst[x+21] = dst[x+22] = dst[x+23] = ((byte1 & 0x01) ? ink1 : paper1) + ((byte2 & 0x01) ? ink2 : paper2); |
||
| 676 | } |
||
| 677 | } |
||
| 678 | |||
| 679 | void line8q_nf(unsigned char *dst, unsigned char *src, unsigned *tab) |
||
| 680 | { |
||
| 681 | for (unsigned x = 0; x < temp.scx*4; x += 32) { |
||
| 682 | unsigned char byte1 = src[0], byte2 = src[rb2_offs+0]; |
||
| 683 | unsigned *t1 = tab + src[1], *t2 = tab + src[rb2_offs+1]; |
||
| 684 | src += 2; |
||
| 685 | |||
| 686 | *(unsigned*)(dst+x+0x00) = (t1[(byte1 << 1) & 0x100] & 0x0F0F0F0F) + (t2[(byte2 << 1) & 0x100] & 0xF0F0F0F0); |
||
| 687 | *(unsigned*)(dst+x+0x04) = (t1[(byte1 << 2) & 0x100] & 0x0F0F0F0F) + (t2[(byte2 << 2) & 0x100] & 0xF0F0F0F0); |
||
| 688 | *(unsigned*)(dst+x+0x08) = (t1[(byte1 << 3) & 0x100] & 0x0F0F0F0F) + (t2[(byte2 << 3) & 0x100] & 0xF0F0F0F0); |
||
| 689 | *(unsigned*)(dst+x+0x0C) = (t1[(byte1 << 4) & 0x100] & 0x0F0F0F0F) + (t2[(byte2 << 4) & 0x100] & 0xF0F0F0F0); |
||
| 690 | *(unsigned*)(dst+x+0x10) = (t1[(byte1 << 5) & 0x100] & 0x0F0F0F0F) + (t2[(byte2 << 5) & 0x100] & 0xF0F0F0F0); |
||
| 691 | *(unsigned*)(dst+x+0x14) = (t1[(byte1 << 6) & 0x100] & 0x0F0F0F0F) + (t2[(byte2 << 6) & 0x100] & 0xF0F0F0F0); |
||
| 692 | *(unsigned*)(dst+x+0x18) = (t1[(byte1 << 7) & 0x100] & 0x0F0F0F0F) + (t2[(byte2 << 7) & 0x100] & 0xF0F0F0F0); |
||
| 693 | *(unsigned*)(dst+x+0x1C) = (t1[(byte1 << 8) & 0x100] & 0x0F0F0F0F) + (t2[(byte2 << 8) & 0x100] & 0xF0F0F0F0); |
||
| 694 | } |
||
| 695 | } |
||
| 696 | |||
| 697 | |||
| 698 | void rend_copy32_nf(unsigned char *dst, unsigned pitch) |
||
| 699 | { |
||
| 700 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 701 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 702 | line32_nf(dst, src, t.sctab32_nf[0]); |
||
| 703 | dst += pitch; src += delta; |
||
| 704 | } |
||
| 705 | } |
||
| 706 | |||
| 707 | void rend_copy32(unsigned char *dst, unsigned pitch) |
||
| 708 | { |
||
| 709 | unsigned char *src = rbuf; |
||
| 710 | unsigned delta = temp.scx / 4; |
||
| 711 | for (unsigned y = 0; y < temp.scy; y++) |
||
| 712 | { |
||
| 713 | line32(dst, src, t.sctab32[0]); |
||
| 714 | dst += pitch; |
||
| 715 | src += delta; |
||
| 716 | } |
||
| 717 | } |
||
| 718 | |||
| 719 | void rend_copy32d1_nf(unsigned char *dst, unsigned pitch) |
||
| 720 | { |
||
| 721 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 722 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 723 | line32d_nf(dst, src, t.sctab32_nf[0]); dst += pitch; |
||
| 724 | src += delta; |
||
| 725 | } |
||
| 726 | } |
||
| 727 | |||
| 728 | void rend_copy32d_nf(unsigned char *dst, unsigned pitch) |
||
| 729 | { |
||
| 730 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 731 | if (conf.alt_nf) { |
||
| 732 | int offset = rb2_offs; |
||
| 733 | if (comp.frame_counter & 1) src += rb2_offs, offset = -offset; |
||
| 734 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 735 | line32d(dst, src, t.sctab32[0]); dst += pitch; |
||
| 736 | line32d(dst, src+offset, t.sctab32[0]); dst += pitch; |
||
| 737 | src += delta; |
||
| 738 | } |
||
| 739 | } else { |
||
| 740 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 741 | line32d_nf(dst, src, t.sctab32_nf[0]); dst += pitch; |
||
| 742 | line32d_nf(dst, src, t.sctab32_nf[1]); dst += pitch; |
||
| 743 | src += delta; |
||
| 744 | } |
||
| 745 | } |
||
| 746 | } |
||
| 747 | |||
| 748 | void rend_copy32t_nf(unsigned char *dst, unsigned pitch) |
||
| 749 | { |
||
| 750 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 751 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 752 | line32t_nf(dst, src, t.sctab32_nf[0]); dst += pitch; |
||
| 753 | line32t_nf(dst, src, t.sctab32_nf[0]); dst += pitch; |
||
| 754 | line32t_nf(dst, src, t.sctab32_nf[0]); dst += pitch; |
||
| 755 | src += delta; |
||
| 756 | } |
||
| 757 | } |
||
| 758 | |||
| 759 | void rend_copy32q_nf(unsigned char *dst, unsigned pitch) |
||
| 760 | { |
||
| 761 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 762 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 763 | #ifdef QUAD_BUFFER |
||
| 764 | unsigned char buffer[MAX_WIDTH*4*sizeof(DWORD)]; |
||
| 765 | line32q_nf(buffer, src, t.sctab32_nf[0]); |
||
| 766 | for (int i = 0; i < 4; i++) { |
||
| 767 | memcpy(dst, buffer, temp.scx*16); |
||
| 768 | dst += pitch; |
||
| 769 | } |
||
| 770 | #else |
||
| 771 | line32q_nf(dst, src, t.sctab32_nf[0]); dst += pitch; |
||
| 772 | line32q_nf(dst, src, t.sctab32_nf[0]); dst += pitch; |
||
| 773 | line32q_nf(dst, src, t.sctab32_nf[0]); dst += pitch; |
||
| 774 | line32q_nf(dst, src, t.sctab32_nf[0]); dst += pitch; |
||
| 775 | #endif |
||
| 776 | src += delta; |
||
| 777 | } |
||
| 778 | } |
||
| 779 | |||
| 780 | void rend_copy32d1(unsigned char *dst, unsigned pitch) |
||
| 781 | { |
||
| 782 | unsigned char *src = rbuf; |
||
| 783 | unsigned delta = temp.scx/4; |
||
| 784 | for (unsigned y = 0; y < temp.scy; y++) |
||
| 785 | { |
||
| 786 | line32d(dst, src, t.sctab32[0]); dst += pitch; |
||
| 787 | src += delta; |
||
| 788 | } |
||
| 789 | } |
||
| 790 | |||
| 791 | void rend_copy32d(unsigned char *dst, unsigned pitch) |
||
| 792 | { |
||
| 793 | unsigned char *src = rbuf; |
||
| 794 | unsigned delta = temp.scx / 4; |
||
| 795 | for (unsigned y = 0; y < temp.scy; y++) |
||
| 796 | { |
||
| 797 | line32d(dst, src, t.sctab32[0]); dst += pitch; // ×åòíûå ñòðîêè |
||
| 798 | line32d(dst, src, t.sctab32[1]); dst += pitch; // Íå÷åòíûå ñòðîêè |
||
| 799 | src += delta; |
||
| 800 | } |
||
| 801 | } |
||
| 802 | |||
| 803 | void rend_copy32t(unsigned char *dst, unsigned pitch) |
||
| 804 | { |
||
| 805 | unsigned char *src = rbuf; |
||
| 806 | unsigned delta = temp.scx / 4; |
||
| 807 | for (unsigned y = 0; y < temp.scy; y++) |
||
| 808 | { |
||
| 809 | line32t(dst, src, t.sctab32[0]); dst += pitch; |
||
| 810 | line32t(dst, src, t.sctab32[0]); dst += pitch; |
||
| 811 | line32t(dst, src, t.sctab32[0]); dst += pitch; |
||
| 812 | src += delta; |
||
| 813 | } |
||
| 814 | } |
||
| 815 | |||
| 816 | void rend_copy32q(unsigned char *dst, unsigned pitch) |
||
| 817 | { |
||
| 818 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 819 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 820 | #ifdef QUAD_BUFFER |
||
| 821 | unsigned char buffer[MAX_WIDTH*4*sizeof(DWORD)]; |
||
| 822 | line32q(buffer, src, t.sctab32[0]); |
||
| 823 | for (int i = 0; i < 4; i++) { |
||
| 824 | memcpy(dst, buffer, temp.scx*16); |
||
| 825 | dst += pitch; |
||
| 826 | } |
||
| 827 | #else |
||
| 828 | line32q(dst, src, t.sctab32[0]); dst += pitch; |
||
| 829 | line32q(dst, src, t.sctab32[0]); dst += pitch; |
||
| 830 | line32q(dst, src, t.sctab32[0]); dst += pitch; |
||
| 831 | line32q(dst, src, t.sctab32[0]); dst += pitch; |
||
| 832 | #endif |
||
| 833 | src += delta; |
||
| 834 | } |
||
| 835 | } |
||
| 836 | |||
| 837 | void rend_copy16(unsigned char *dst, unsigned pitch) |
||
| 838 | { |
||
| 839 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 840 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 841 | line16(dst, src, t.sctab16[0]); |
||
| 842 | dst += pitch, src += delta; |
||
| 843 | } |
||
| 844 | } |
||
| 845 | |||
| 846 | void rend_copy16_nf(unsigned char *dst, unsigned pitch) |
||
| 847 | { |
||
| 848 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 849 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 850 | line16_nf(dst, src, t.sctab16_nf[0]); |
||
| 851 | dst += pitch, src += delta; |
||
| 852 | } |
||
| 853 | } |
||
| 854 | |||
| 855 | void rend_copy16d1(unsigned char *dst, unsigned pitch) |
||
| 856 | { |
||
| 857 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 858 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 859 | line16d(dst, src, t.sctab16d[0]); dst += pitch; |
||
| 860 | src += delta; |
||
| 861 | } |
||
| 862 | } |
||
| 863 | |||
| 864 | void rend_copy16d(unsigned char *dst, unsigned pitch) |
||
| 865 | { |
||
| 866 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 867 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 868 | line16d(dst, src, t.sctab16d[0]); dst += pitch; |
||
| 869 | line16d(dst, src, t.sctab16d[1]); dst += pitch; |
||
| 870 | src += delta; |
||
| 871 | } |
||
| 872 | } |
||
| 873 | |||
| 874 | void rend_copy16t(unsigned char *dst, unsigned pitch) |
||
| 875 | { |
||
| 876 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 877 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 878 | line16t(dst, src, t.sctab16d[0]); dst += pitch; |
||
| 879 | line16t(dst, src, t.sctab16d[0]); dst += pitch; |
||
| 880 | line16t(dst, src, t.sctab16d[0]); dst += pitch; |
||
| 881 | src += delta; |
||
| 882 | } |
||
| 883 | } |
||
| 884 | |||
| 885 | void rend_copy16q(unsigned char *dst, unsigned pitch) |
||
| 886 | { |
||
| 887 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 888 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 889 | line16q(dst, src, t.sctab16d[0]); dst += pitch; |
||
| 890 | line16q(dst, src, t.sctab16d[0]); dst += pitch; |
||
| 891 | line16q(dst, src, t.sctab16d[0]); dst += pitch; |
||
| 892 | line16q(dst, src, t.sctab16d[0]); dst += pitch; |
||
| 893 | src += delta; |
||
| 894 | } |
||
| 895 | } |
||
| 896 | |||
| 897 | void rend_copy16d1_nf(unsigned char *dst, unsigned pitch) |
||
| 898 | { |
||
| 899 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 900 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 901 | line16d_nf(dst, src, t.sctab16d_nf[0]); dst += pitch; |
||
| 902 | src += delta; |
||
| 903 | } |
||
| 904 | } |
||
| 905 | |||
| 906 | void rend_copy16d_nf(unsigned char *dst, unsigned pitch) |
||
| 907 | { |
||
| 908 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 909 | if (conf.alt_nf) { |
||
| 910 | int offset = rb2_offs; |
||
| 911 | if (comp.frame_counter & 1) src += rb2_offs, offset = -offset; |
||
| 912 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 913 | line16d(dst, src, t.sctab16d[0]); dst += pitch; |
||
| 914 | line16d(dst, src+offset, t.sctab16d[0]); dst += pitch; |
||
| 915 | src += delta; |
||
| 916 | } |
||
| 917 | } else { |
||
| 918 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 919 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 920 | line16d_nf(dst, src, t.sctab16d_nf[0]); dst += pitch; |
||
| 921 | line16d_nf(dst, src, t.sctab16d_nf[1]); dst += pitch; |
||
| 922 | src += delta; |
||
| 923 | } |
||
| 924 | } |
||
| 925 | } |
||
| 926 | |||
| 927 | void rend_copy16t_nf(unsigned char *dst, unsigned pitch) |
||
| 928 | { |
||
| 929 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 930 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 931 | line16t_nf(dst, src, t.sctab16d_nf[0]); dst += pitch; |
||
| 932 | line16t_nf(dst, src, t.sctab16d_nf[0]); dst += pitch; |
||
| 933 | line16t_nf(dst, src, t.sctab16d_nf[0]); dst += pitch; |
||
| 934 | src += delta; |
||
| 935 | } |
||
| 936 | } |
||
| 937 | |||
| 938 | void rend_copy16q_nf(unsigned char *dst, unsigned pitch) |
||
| 939 | { |
||
| 940 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 941 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 942 | line16q_nf(dst, src, t.sctab16d_nf[0]); dst += pitch; |
||
| 943 | line16q_nf(dst, src, t.sctab16d_nf[0]); dst += pitch; |
||
| 944 | line16q_nf(dst, src, t.sctab16d_nf[0]); dst += pitch; |
||
| 945 | line16q_nf(dst, src, t.sctab16d_nf[0]); dst += pitch; |
||
| 946 | src += delta; |
||
| 947 | } |
||
| 948 | } |
||
| 949 | |||
| 950 | void __fastcall rend_copy8(unsigned char *dst, unsigned pitch) |
||
| 951 | { |
||
| 952 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 953 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 954 | line8(dst, src, t.sctab8[0]); |
||
| 955 | dst += pitch, src += delta; |
||
| 956 | } |
||
| 957 | } |
||
| 958 | |||
| 959 | void __fastcall rend_copy8_nf(unsigned char *dst, unsigned pitch) |
||
| 960 | { |
||
| 961 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 962 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 963 | line8_nf(dst, src, t.sctab8[0]); |
||
| 964 | dst += pitch, src += delta; |
||
| 965 | } |
||
| 966 | } |
||
| 967 | |||
| 968 | void rend_copy8d1(unsigned char *dst, unsigned pitch) |
||
| 969 | { |
||
| 970 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 971 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 972 | line8d(dst, src, t.sctab8d[0]); dst += pitch; |
||
| 973 | src += delta; |
||
| 974 | } |
||
| 975 | } |
||
| 976 | |||
| 977 | void rend_copy8d(unsigned char *dst, unsigned pitch) |
||
| 978 | { |
||
| 979 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 980 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 981 | line8d(dst, src, t.sctab8d[0]); dst += pitch; |
||
| 982 | line8d(dst, src, t.sctab8d[1]); dst += pitch; |
||
| 983 | src += delta; |
||
| 984 | } |
||
| 985 | } |
||
| 986 | |||
| 987 | void rend_copy8t(unsigned char *dst, unsigned pitch) |
||
| 988 | { |
||
| 989 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 990 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 991 | line8t(dst, src, t.sctab8q); dst += pitch; |
||
| 992 | line8t(dst, src, t.sctab8q); dst += pitch; |
||
| 993 | line8t(dst, src, t.sctab8q); dst += pitch; |
||
| 994 | src += delta; |
||
| 995 | } |
||
| 996 | } |
||
| 997 | |||
| 998 | void rend_copy8q(unsigned char *dst, unsigned pitch) |
||
| 999 | { |
||
| 1000 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 1001 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 1002 | line8q(dst, src, t.sctab8q); dst += pitch; |
||
| 1003 | line8q(dst, src, t.sctab8q); dst += pitch; |
||
| 1004 | line8q(dst, src, t.sctab8q); dst += pitch; |
||
| 1005 | line8q(dst, src, t.sctab8q); dst += pitch; |
||
| 1006 | src += delta; |
||
| 1007 | } |
||
| 1008 | } |
||
| 1009 | |||
| 1010 | void rend_copy8d1_nf(unsigned char *dst, unsigned pitch) |
||
| 1011 | { |
||
| 1012 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 1013 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 1014 | line8d_nf(dst, src, t.sctab8d[0]); dst += pitch; |
||
| 1015 | src += delta; |
||
| 1016 | } |
||
| 1017 | } |
||
| 1018 | |||
| 1019 | void rend_copy8d_nf(unsigned char *dst, unsigned pitch) |
||
| 1020 | { |
||
| 1021 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 1022 | if (conf.alt_nf) { |
||
| 1023 | int offset = rb2_offs; |
||
| 1024 | if (comp.frame_counter & 1) src += rb2_offs, offset = -offset; |
||
| 1025 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 1026 | line8d(dst, src, t.sctab8d[0]); dst += pitch; |
||
| 1027 | line8d(dst, src+offset, t.sctab8d[0]); dst += pitch; |
||
| 1028 | src += delta; |
||
| 1029 | } |
||
| 1030 | } else { |
||
| 1031 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 1032 | line8d_nf(dst, src, t.sctab8d[0]); dst += pitch; |
||
| 1033 | line8d_nf(dst, src, t.sctab8d[1]); dst += pitch; |
||
| 1034 | src += delta; |
||
| 1035 | } |
||
| 1036 | } |
||
| 1037 | } |
||
| 1038 | |||
| 1039 | void rend_copy8t_nf(unsigned char *dst, unsigned pitch) |
||
| 1040 | { |
||
| 1041 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 1042 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 1043 | line8t_nf(dst, src, t.sctab8q); dst += pitch; |
||
| 1044 | line8t_nf(dst, src, t.sctab8q); dst += pitch; |
||
| 1045 | line8t_nf(dst, src, t.sctab8q); dst += pitch; |
||
| 1046 | src += delta; |
||
| 1047 | } |
||
| 1048 | } |
||
| 1049 | |||
| 1050 | void rend_copy8q_nf(unsigned char *dst, unsigned pitch) |
||
| 1051 | { |
||
| 1052 | unsigned char *src = rbuf; unsigned delta = temp.scx/4; |
||
| 1053 | for (unsigned y = 0; y < temp.scy; y++) { |
||
| 1054 | line8q_nf(dst, src, t.sctab8q); dst += pitch; |
||
| 1055 | line8q_nf(dst, src, t.sctab8q); dst += pitch; |
||
| 1056 | line8q_nf(dst, src, t.sctab8q); dst += pitch; |
||
| 1057 | line8q_nf(dst, src, t.sctab8q); dst += pitch; |
||
| 1058 | src += delta; |
||
| 1059 | } |
||
| 1060 | } |