| | 1 | /*\r |
| | 2 | * some color conversion and blitting routines\r |
| | 3 | * (C) notaz, 2006-2009\r |
| | 4 | * (C) irixxxx, 2020-2023\r |
| | 5 | *\r |
| | 6 | * This work is licensed under the terms of MAME license.\r |
| | 7 | * See COPYING file in the top-level directory.\r |
| | 8 | */\r |
| | 9 | \r |
| | 10 | .text\r |
| | 11 | .align 4\r |
| | 12 | \r |
| | 13 | @ Convert 0000bbbb ggggrrrr 0000bbbb ggggrrrr\r |
| | 14 | @ to 00000000 rrrr0000 gggg0000 bbbb0000 ...\r |
| | 15 | \r |
| | 16 | @ lr = 0x00f000f0, out: r3=lower_pix, r2=higher_pix; trashes rin\r |
| | 17 | .macro convRGB32_2 rin sh=0\r |
| | 18 | and r2, lr, \rin, lsr #4 @ blue\r |
| | 19 | and r3, \rin, lr\r |
| | 20 | orr r2, r2, r3, lsl #8 @ g0b0g0b0\r |
| | 21 | \r |
| | 22 | mov r3, r2, lsl #16 @ g0b00000\r |
| | 23 | and \rin,lr, \rin, ror #12 @ 00r000r0 (reversed)\r |
| | 24 | orr r3, r3, \rin, lsr #16 @ g0b000r0\r |
| | 25 | .if \sh == 1\r |
| | 26 | mov r3, r3, ror #17 @ shadow mode\r |
| | 27 | .elseif \sh == 2\r |
| | 28 | adds r3, r3, #0x40000000 @ green\r |
| | 29 | orrcs r3, r3, lr, lsl #24\r |
| | 30 | mov r3, r3, ror #8\r |
| | 31 | adds r3, r3, #0x40000000\r |
| | 32 | orrcs r3, r3, lr, lsl #24\r |
| | 33 | mov r3, r3, ror #16\r |
| | 34 | adds r3, r3, #0x40000000\r |
| | 35 | orrcs r3, r3, lr, lsl #24\r |
| | 36 | mov r3, r3, ror #24\r |
| | 37 | .else\r |
| | 38 | mov r3, r3, ror #16 @ r3=low\r |
| | 39 | .endif\r |
| | 40 | \r |
| | 41 | orr r3, r3, r3, lsr #3\r |
| | 42 | str r3, [r0], #4\r |
| | 43 | \r |
| | 44 | mov r2, r2, lsr #16\r |
| | 45 | orr r2, r2, \rin, lsl #16\r |
| | 46 | .if \sh == 1\r |
| | 47 | mov r2, r2, lsr #1\r |
| | 48 | .elseif \sh == 2\r |
| | 49 | mov r2, r2, ror #8\r |
| | 50 | adds r2, r2, #0x40000000 @ blue\r |
| | 51 | orrcs r2, r2, lr, lsl #24\r |
| | 52 | mov r2, r2, ror #8\r |
| | 53 | adds r2, r2, #0x40000000\r |
| | 54 | orrcs r2, r2, lr, lsl #24\r |
| | 55 | mov r2, r2, ror #8\r |
| | 56 | adds r2, r2, #0x40000000\r |
| | 57 | orrcs r2, r2, lr, lsl #24\r |
| | 58 | mov r2, r2, ror #8\r |
| | 59 | .endif\r |
| | 60 | \r |
| | 61 | orr r2, r2, r2, lsr #3\r |
| | 62 | str r2, [r0], #4\r |
| | 63 | .endm\r |
| | 64 | \r |
| | 65 | \r |
| | 66 | .global bgr444_to_rgb32 @ void *to, void *from, unsigned entries\r |
| | 67 | \r |
| | 68 | bgr444_to_rgb32:\r |
| | 69 | stmfd sp!, {r4-r7,lr}\r |
| | 70 | \r |
| | 71 | mov r12, r2, lsr #3 @ repeats\r |
| | 72 | mov lr, #0x00f00000\r |
| | 73 | orr lr, lr, #0x00f0\r |
| | 74 | \r |
| | 75 | .loopRGB32:\r |
| | 76 | ldmia r1!, {r4-r7}\r |
| | 77 | convRGB32_2 r4\r |
| | 78 | convRGB32_2 r5\r |
| | 79 | convRGB32_2 r6\r |
| | 80 | convRGB32_2 r7\r |
| | 81 | \r |
| | 82 | subs r12, r12, #1\r |
| | 83 | bgt .loopRGB32\r |
| | 84 | \r |
| | 85 | ldmfd sp!, {r4-r7,pc}\r |
| | 86 | \r |
| | 87 | \r |
| | 88 | .global bgr444_to_rgb32_sh @ void *to, void *from\r |
| | 89 | \r |
| | 90 | bgr444_to_rgb32_sh:\r |
| | 91 | stmfd sp!, {r4-r7,lr}\r |
| | 92 | \r |
| | 93 | mov r12, #0x40>>3 @ repeats\r |
| | 94 | add r0, r0, #0x40*4\r |
| | 95 | mov lr, #0x00f00000\r |
| | 96 | orr lr, lr, #0x00f0\r |
| | 97 | \r |
| | 98 | .loopRGB32sh:\r |
| | 99 | ldmia r1!, {r4-r7}\r |
| | 100 | convRGB32_2 r4, 2\r |
| | 101 | convRGB32_2 r5, 2\r |
| | 102 | convRGB32_2 r6, 2\r |
| | 103 | convRGB32_2 r7, 2\r |
| | 104 | \r |
| | 105 | subs r12, r12, #1\r |
| | 106 | bgt .loopRGB32sh\r |
| | 107 | \r |
| | 108 | mov r12, #0x40>>3 @ repeats\r |
| | 109 | sub r1, r1, #0x40*2\r |
| | 110 | and lr, lr, lr, lsl #1 @ kill LSB for correct shadow colors\r |
| | 111 | \r |
| | 112 | .loopRGB32hi:\r |
| | 113 | ldmia r1!, {r4-r7}\r |
| | 114 | convRGB32_2 r4, 1\r |
| | 115 | convRGB32_2 r5, 1\r |
| | 116 | convRGB32_2 r6, 1\r |
| | 117 | convRGB32_2 r7, 1\r |
| | 118 | \r |
| | 119 | subs r12, r12, #1\r |
| | 120 | bgt .loopRGB32hi\r |
| | 121 | \r |
| | 122 | ldmfd sp!, {r4-r7,lr}\r |
| | 123 | bx lr\r |
| | 124 | \r |
| | 125 | \r |
| | 126 | @ @@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@\r |
| | 127 | \r |
| | 128 | .global vidcpy_8bit @ void *dest, void *src, int x_y, int w_h\r |
| | 129 | vidcpy_8bit:\r |
| | 130 | stmfd sp!, {r4-r6,lr}\r |
| | 131 | \r |
| | 132 | mov r12, r2, lsl #16 @ y\r |
| | 133 | \r |
| | 134 | mov r4, r12, lsr #16-8 @ 320*y = 256*y+64*y\r |
| | 135 | add r4, r4, r12, lsr #16-6\r |
| | 136 | add r0, r0, r4 @ pd += 320*y + x\r |
| | 137 | add r0, r0, r2, lsr #16\r |
| | 138 | \r |
| | 139 | add r4, r4, r12, lsr #16-3 @ 328*y = 320*y + 8*y\r |
| | 140 | add r1, r1, r4 @ ps += 328*y + x + 8\r |
| | 141 | add r1, r1, r2, lsr #16\r |
| | 142 | add r1, r1, #8\r |
| | 143 | \r |
| | 144 | mov lr, r3, lsr #16 @ w\r |
| | 145 | mov r12, r3, lsl #16 @ h\r |
| | 146 | \r |
| | 147 | vidCpy8bit_loop_out:\r |
| | 148 | movs r6, lr, lsr #5\r |
| | 149 | @ beq vidCpy8bit_loop_end\r |
| | 150 | vidCpy8bit_loop:\r |
| | 151 | subs r6, r6, #1\r |
| | 152 | ldmia r1!, {r2-r5}\r |
| | 153 | stmia r0!, {r2-r5}\r |
| | 154 | ldmia r1!, {r2-r5}\r |
| | 155 | stmia r0!, {r2-r5}\r |
| | 156 | bne vidCpy8bit_loop\r |
| | 157 | \r |
| | 158 | ands r6, lr, #0x0018\r |
| | 159 | beq vidCpy8bit_loop_end\r |
| | 160 | vidCpy8bit_loop2:\r |
| | 161 | ldmia r1!, {r2-r3}\r |
| | 162 | subs r6, r6, #8\r |
| | 163 | stmia r0!, {r2-r3}\r |
| | 164 | bne vidCpy8bit_loop2\r |
| | 165 | \r |
| | 166 | vidCpy8bit_loop_end:\r |
| | 167 | subs r12,r12,#1<<16\r |
| | 168 | add r0, r0, #320\r |
| | 169 | sub r0, r0, lr\r |
| | 170 | add r1, r1, #328\r |
| | 171 | sub r1, r1, lr\r |
| | 172 | bne vidCpy8bit_loop_out\r |
| | 173 | \r |
| | 174 | ldmfd sp!, {r4-r6,pc}\r |
| | 175 | \r |
| | 176 | \r |
| | 177 | .global vidcpy_8bit_rot @ void *dest, void *src, int x_y, int w_h\r |
| | 178 | vidcpy_8bit_rot:\r |
| | 179 | stmfd sp!, {r4-r10,lr}\r |
| | 180 | \r |
| | 181 | mov r12, r2, lsl #16 @ y\r |
| | 182 | \r |
| | 183 | add r0, r0, r12, lsr #16 @ pd += y + (319-x)*240\r |
| | 184 | mov r4, #320\r |
| | 185 | sub r4, r4, #1\r |
| | 186 | sub r4, r4, r2, lsr #16 @ (319-x)\r |
| | 187 | add r0, r0, r4, lsl #8\r |
| | 188 | sub r0, r0, r4, lsl #4\r |
| | 189 | \r |
| | 190 | mov r4, r12, lsr #16-8 @ 328*y = 256*y + 64*y + 8*y\r |
| | 191 | add r4, r4, r12, lsr #16-6\r |
| | 192 | add r4, r4, r12, lsr #16-3\r |
| | 193 | add r1, r1, r4 @ ps += 328*y + x + 8\r |
| | 194 | add r1, r1, r2, lsr #16\r |
| | 195 | add r1, r1, #8\r |
| | 196 | \r |
| | 197 | mov lr, r3, lsr #16 @ w\r |
| | 198 | mov r12, r3, lsl #16 @ h\r |
| | 199 | \r |
| | 200 | mov r8, #328\r |
| | 201 | vidCpy8bitrot_loop_out:\r |
| | 202 | mov r10, r0\r |
| | 203 | movs r9, lr, lsr #2\r |
| | 204 | @ beq vidCpy8bitrot_loop_end\r |
| | 205 | vidCpy8bitrot_loop:\r |
| | 206 | mov r6, r1\r |
| | 207 | ldr r2, [r6], r8\r |
| | 208 | ldr r3, [r6], r8\r |
| | 209 | ldr r4, [r6], r8\r |
| | 210 | ldr r5, [r6], r8\r |
| | 211 | \r |
| | 212 | mov r6, r2, lsl #24\r |
| | 213 | mov r6, r6, lsr #8\r |
| | 214 | orr r6, r6, r3, lsl #24\r |
| | 215 | mov r6, r6, lsr #8\r |
| | 216 | orr r6, r6, r4, lsl #24\r |
| | 217 | mov r6, r6, lsr #8\r |
| | 218 | orr r6, r6, r5, lsl #24\r |
| | 219 | str r6, [r0], #-240\r |
| | 220 | \r |
| | 221 | and r6, r3, #0xff00\r |
| | 222 | and r7, r2, #0xff00\r |
| | 223 | orr r6, r6, r7, lsr #8\r |
| | 224 | and r7, r4, #0xff00\r |
| | 225 | orr r6, r6, r7, lsl #8\r |
| | 226 | and r7, r5, #0xff00\r |
| | 227 | orr r6, r6, r7, lsl #16\r |
| | 228 | str r6, [r0], #-240\r |
| | 229 | \r |
| | 230 | and r6, r4, #0xff0000\r |
| | 231 | and r7, r2, #0xff0000\r |
| | 232 | orr r6, r6, r7, lsr #16\r |
| | 233 | and r7, r3, #0xff0000\r |
| | 234 | orr r6, r6, r7, lsr #8\r |
| | 235 | and r7, r5, #0xff0000\r |
| | 236 | orr r6, r6, r7, lsl #8\r |
| | 237 | str r6, [r0], #-240\r |
| | 238 | \r |
| | 239 | mov r6, r5, lsr #24\r |
| | 240 | mov r6, r6, lsl #8\r |
| | 241 | orr r6, r6, r4, lsr #24\r |
| | 242 | mov r6, r6, lsl #8\r |
| | 243 | orr r6, r6, r3, lsr #24\r |
| | 244 | mov r6, r6, lsl #8\r |
| | 245 | orr r6, r6, r2, lsr #24\r |
| | 246 | str r6, [r0], #-240\r |
| | 247 | \r |
| | 248 | subs r9, r9, #1\r |
| | 249 | add r1, r1, #4\r |
| | 250 | bne vidCpy8bitrot_loop\r |
| | 251 | \r |
| | 252 | vidCpy8bitrot_loop_end:\r |
| | 253 | subs r12,r12,#4<<16\r |
| | 254 | add r0, r10, #4\r |
| | 255 | sub r1, r1, lr\r |
| | 256 | add r1, r1, #4*328\r |
| | 257 | bne vidCpy8bitrot_loop_out\r |
| | 258 | \r |
| | 259 | ldmfd sp!, {r4-r10,pc}\r |
| | 260 | \r |
| | 261 | \r |
| | 262 | .global rotated_blit8 @ void *dst, void *linesx4, u32 y, int is_32col\r |
| | 263 | rotated_blit8:\r |
| | 264 | stmfd sp!,{r4-r8,lr}\r |
| | 265 | mov r8, #320\r |
| | 266 | \r |
| | 267 | rotated_blit8_2:\r |
| | 268 | add r0, r0, #(240*320)\r |
| | 269 | sub r0, r0, #(240+4) @ y starts from 4\r |
| | 270 | add r0, r0, r2\r |
| | 271 | \r |
| | 272 | tst r3, r3\r |
| | 273 | subne r0, r0, #(240*32)\r |
| | 274 | addne r1, r1, #32\r |
| | 275 | movne lr, #256/4\r |
| | 276 | moveq lr, #320/4\r |
| | 277 | \r |
| | 278 | rotated_blit_loop8:\r |
| | 279 | mov r6, r1\r |
| | 280 | ldr r2, [r6], r8\r |
| | 281 | ldr r3, [r6], r8\r |
| | 282 | ldr r4, [r6], r8\r |
| | 283 | ldr r5, [r6], r8\r |
| | 284 | \r |
| | 285 | mov r6, r2, lsl #24\r |
| | 286 | mov r6, r6, lsr #8\r |
| | 287 | orr r6, r6, r3, lsl #24\r |
| | 288 | mov r6, r6, lsr #8\r |
| | 289 | orr r6, r6, r4, lsl #24\r |
| | 290 | mov r6, r6, lsr #8\r |
| | 291 | orr r6, r6, r5, lsl #24\r |
| | 292 | str r6, [r0], #-240\r |
| | 293 | \r |
| | 294 | and r6, r3, #0xff00\r |
| | 295 | and r7, r2, #0xff00\r |
| | 296 | orr r6, r6, r7, lsr #8\r |
| | 297 | and r7, r4, #0xff00\r |
| | 298 | orr r6, r6, r7, lsl #8\r |
| | 299 | and r7, r5, #0xff00\r |
| | 300 | orr r6, r6, r7, lsl #16\r |
| | 301 | str r6, [r0], #-240\r |
| | 302 | \r |
| | 303 | and r6, r4, #0xff0000\r |
| | 304 | and r7, r2, #0xff0000\r |
| | 305 | orr r6, r6, r7, lsr #16\r |
| | 306 | and r7, r3, #0xff0000\r |
| | 307 | orr r6, r6, r7, lsr #8\r |
| | 308 | and r7, r5, #0xff0000\r |
| | 309 | orr r6, r6, r7, lsl #8\r |
| | 310 | str r6, [r0], #-240\r |
| | 311 | \r |
| | 312 | mov r6, r5, lsr #24\r |
| | 313 | mov r6, r6, lsl #8\r |
| | 314 | orr r6, r6, r4, lsr #24\r |
| | 315 | mov r6, r6, lsl #8\r |
| | 316 | orr r6, r6, r3, lsr #24\r |
| | 317 | mov r6, r6, lsl #8\r |
| | 318 | orr r6, r6, r2, lsr #24\r |
| | 319 | str r6, [r0], #-240\r |
| | 320 | \r |
| | 321 | subs lr, lr, #1\r |
| | 322 | add r1, r1, #4\r |
| | 323 | bne rotated_blit_loop8\r |
| | 324 | \r |
| | 325 | ldmfd sp!,{r4-r8,pc}\r |
| | 326 | \r |
| | 327 | \r |
| | 328 | @ input: r2-r5\r |
| | 329 | @ output: r7,r8\r |
| | 330 | @ trash: r6\r |
| | 331 | .macro rb_line_low\r |
| | 332 | mov r6, r2, lsl #16\r |
| | 333 | mov r7, r3, lsl #16\r |
| | 334 | orr r7, r7, r6, lsr #16\r |
| | 335 | mov r6, r4, lsl #16\r |
| | 336 | mov r8, r5, lsl #16\r |
| | 337 | orr r8, r8, r6, lsr #16\r |
| | 338 | .endm\r |
| | 339 | \r |
| | 340 | .macro rb_line_hi\r |
| | 341 | mov r6, r2, lsr #16\r |
| | 342 | mov r7, r3, lsr #16\r |
| | 343 | orr r7, r6, r7, lsl #16\r |
| | 344 | mov r6, r4, lsr #16\r |
| | 345 | mov r8, r5, lsr #16\r |
| | 346 | orr r8, r6, r8, lsl #16\r |
| | 347 | .endm\r |
| | 348 | \r |
| | 349 | .global rotated_blit16 @ void *dst, void *linesx4, u32 y, int is_32col\r |
| | 350 | rotated_blit16:\r |
| | 351 | stmfd sp!,{r4-r8,lr}\r |
| | 352 | \r |
| | 353 | add r0, r0, #(240*320)*2\r |
| | 354 | sub r0, r0, #(240+4)*2 @ y starts from 4\r |
| | 355 | add r0, r0, r2, lsl #1\r |
| | 356 | \r |
| | 357 | tst r3, r3\r |
| | 358 | subne r0, r0, #(240*32)*2\r |
| | 359 | addne r1, r1, #32*2\r |
| | 360 | movne lr, #256/4\r |
| | 361 | moveq lr, #320/4\r |
| | 362 | \r |
| | 363 | rotated_blit_loop16:\r |
| | 364 | ldr r2, [r1, #320*0*2]\r |
| | 365 | ldr r3, [r1, #320*1*2]\r |
| | 366 | ldr r4, [r1, #320*2*2]\r |
| | 367 | ldr r5, [r1, #320*3*2]\r |
| | 368 | rb_line_low\r |
| | 369 | stmia r0, {r7,r8}\r |
| | 370 | sub r0, r0, #240*2\r |
| | 371 | rb_line_hi\r |
| | 372 | stmia r0, {r7,r8}\r |
| | 373 | sub r0, r0, #240*2\r |
| | 374 | \r |
| | 375 | ldr r2, [r1, #320*0*2+4]\r |
| | 376 | ldr r3, [r1, #320*1*2+4]\r |
| | 377 | ldr r4, [r1, #320*2*2+4]\r |
| | 378 | ldr r5, [r1, #320*3*2+4]\r |
| | 379 | rb_line_low\r |
| | 380 | stmia r0, {r7,r8}\r |
| | 381 | sub r0, r0, #240*2\r |
| | 382 | rb_line_hi\r |
| | 383 | stmia r0, {r7,r8}\r |
| | 384 | sub r0, r0, #240*2\r |
| | 385 | \r |
| | 386 | subs lr, lr, #1\r |
| | 387 | add r1, r1, #8\r |
| | 388 | bne rotated_blit_loop16\r |
| | 389 | \r |
| | 390 | ldmfd sp!,{r4-r8,pc}\r |
| | 391 | \r |
| | 392 | \r |
| | 393 | .global spend_cycles @ c\r |
| | 394 | \r |
| | 395 | spend_cycles:\r |
| | 396 | mov r0, r0, lsr #2 @ 4 cycles/iteration\r |
| | 397 | sub r0, r0, #2 @ entry/exit/init\r |
| | 398 | .sc_loop:\r |
| | 399 | subs r0, r0, #1\r |
| | 400 | bpl .sc_loop\r |
| | 401 | \r |
| | 402 | bx lr\r |
| | 403 | \r |
| | 404 | @ vim:filetype=armasm\r |
notaz.gp2x.de / picodrive.git / blame_incremental