kc3-lang/SDL/src/stdlib/SDL_mslibc.c
-
Show log
Commit
-
Hash : d1dc1952
Author :
Date : 2023-03-23T06:45:19
Implement _intel_fast_(memcpy|memset) The classic Intel compiler generates calls to these functions when building the SDL library with SDL_LIBC=OFF.
-
src/stdlib/SDL_mslibc.c
-
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719
/* Simple DirectMedia Layer Copyright (C) 1997-2023 Sam Lantinga <slouken@libsdl.org> This software is provided 'as-is', without any express or implied warranty. In no event will the authors be held liable for any damages arising from the use of this software. Permission is granted to anyone to use this software for any purpose, including commercial applications, and to alter it and redistribute it freely, subject to the following restrictions: 1. The origin of this software must not be misrepresented; you must not claim that you wrote the original software. If you use this software in a product, an acknowledgment in the product documentation would be appreciated but is not required. 2. Altered source versions must be plainly marked as such, and must not be misrepresented as being the original software. 3. This notice may not be removed or altered from any source distribution. */ #if defined(__clang_analyzer__) && !defined(SDL_DISABLE_ANALYZE_MACROS) #define SDL_DISABLE_ANALYZE_MACROS 1 #endif #include "../SDL_internal.h" /* This file contains SDL replacements for functions in the C library */ #if !defined(HAVE_LIBC) && !defined(SDL_STATIC_LIB) /* These are some C runtime intrinsics that need to be defined */ #if defined(_MSC_VER) #ifndef __FLTUSED__ #define __FLTUSED__ __declspec(selectany) int _fltused = 1; #endif /* The optimizer on Visual Studio 2005 and later generates memcpy() and memset() calls. Always provide it for the SDL2 DLL, but skip it when building static lib w/ static runtime. */ #if (_MSC_VER >= 1400) && (!defined(_MT) || defined(DLL_EXPORT)) /* NOLINTNEXTLINE(readability-redundant-declaration) */ extern void *memcpy(void *dst, const void *src, size_t len); #pragma intrinsic(memcpy) #if !defined(__clang__) #pragma function(memcpy) #endif /* NOLINTNEXTLINE(readability-inconsistent-declaration-parameter-name) */ void *memcpy(void *dst, const void *src, size_t len) { return SDL_memcpy(dst, src, len); } /* NOLINTNEXTLINE(readability-redundant-declaration) */ extern void *memset(void *dst, int c, size_t len); #pragma intrinsic(memset) #if !defined(__clang__) #pragma function(memset) #endif /* NOLINTNEXTLINE(readability-inconsistent-declaration-parameter-name) */ void *memset(void *dst, int c, size_t len) { return SDL_memset(dst, c, len); } #endif /* (_MSC_VER >= 1400) && (!defined(_MT) || defined(DLL_EXPORT)) */ #ifdef _M_IX86 /* Float to long */ void __declspec(naked) _ftol() { /* *INDENT-OFF* */ __asm { push ebp mov ebp,esp sub esp,20h and esp,0FFFFFFF0h fld st(0) fst dword ptr [esp+18h] fistp qword ptr [esp+10h] fild qword ptr [esp+10h] mov edx,dword ptr [esp+18h] mov eax,dword ptr [esp+10h] test eax,eax je integer_QnaN_or_zero arg_is_not_integer_QnaN: fsubp st(1),st test edx,edx jns positive fstp dword ptr [esp] mov ecx,dword ptr [esp] xor ecx,80000000h add ecx,7FFFFFFFh adc eax,0 mov edx,dword ptr [esp+14h] adc edx,0 jmp localexit positive: fstp dword ptr [esp] mov ecx,dword ptr [esp] add ecx,7FFFFFFFh sbb eax,0 mov edx,dword ptr [esp+14h] sbb edx,0 jmp localexit integer_QnaN_or_zero: mov edx,dword ptr [esp+14h] test edx,7FFFFFFFh jne arg_is_not_integer_QnaN fstp dword ptr [esp+18h] fstp dword ptr [esp+18h] localexit: leave ret } /* *INDENT-ON* */ } void _ftol2_sse() { _ftol(); } void _ftol2() { _ftol(); } /* 64-bit math operators for 32-bit systems */ void __declspec(naked) _allmul() { /* *INDENT-OFF* */ __asm { mov eax, dword ptr[esp+8] mov ecx, dword ptr[esp+10h] or ecx, eax mov ecx, dword ptr[esp+0Ch] jne hard mov eax, dword ptr[esp+4] mul ecx ret 10h hard: push ebx mul ecx mov ebx, eax mov eax, dword ptr[esp+8] mul dword ptr[esp+14h] add ebx, eax mov eax, dword ptr[esp+8] mul ecx add edx, ebx pop ebx ret 10h } /* *INDENT-ON* */ } void __declspec(naked) _alldiv() { /* *INDENT-OFF* */ __asm { push edi push esi push ebx xor edi,edi mov eax,dword ptr [esp+14h] or eax,eax jge L1 inc edi mov edx,dword ptr [esp+10h] neg eax neg edx sbb eax,0 mov dword ptr [esp+14h],eax mov dword ptr [esp+10h],edx L1: mov eax,dword ptr [esp+1Ch] or eax,eax jge L2 inc edi mov edx,dword ptr [esp+18h] neg eax neg edx sbb eax,0 mov dword ptr [esp+1Ch],eax mov dword ptr [esp+18h],edx L2: or eax,eax jne L3 mov ecx,dword ptr [esp+18h] mov eax,dword ptr [esp+14h] xor edx,edx div ecx mov ebx,eax mov eax,dword ptr [esp+10h] div ecx mov edx,ebx jmp L4 L3: mov ebx,eax mov ecx,dword ptr [esp+18h] mov edx,dword ptr [esp+14h] mov eax,dword ptr [esp+10h] L5: shr ebx,1 rcr ecx,1 shr edx,1 rcr eax,1 or ebx,ebx jne L5 div ecx mov esi,eax mul dword ptr [esp+1Ch] mov ecx,eax mov eax,dword ptr [esp+18h] mul esi add edx,ecx jb L6 cmp edx,dword ptr [esp+14h] ja L6 jb L7 cmp eax,dword ptr [esp+10h] jbe L7 L6: dec esi L7: xor edx,edx mov eax,esi L4: dec edi jne L8 neg edx neg eax sbb edx,0 L8: pop ebx pop esi pop edi ret 10h } /* *INDENT-ON* */ } void __declspec(naked) _aulldiv() { /* *INDENT-OFF* */ __asm { push ebx push esi mov eax,dword ptr [esp+18h] or eax,eax jne L1 mov ecx,dword ptr [esp+14h] mov eax,dword ptr [esp+10h] xor edx,edx div ecx mov ebx,eax mov eax,dword ptr [esp+0Ch] div ecx mov edx,ebx jmp L2 L1: mov ecx,eax mov ebx,dword ptr [esp+14h] mov edx,dword ptr [esp+10h] mov eax,dword ptr [esp+0Ch] L3: shr ecx,1 rcr ebx,1 shr edx,1 rcr eax,1 or ecx,ecx jne L3 div ebx mov esi,eax mul dword ptr [esp+18h] mov ecx,eax mov eax,dword ptr [esp+14h] mul esi add edx,ecx jb L4 cmp edx,dword ptr [esp+10h] ja L4 jb L5 cmp eax,dword ptr [esp+0Ch] jbe L5 L4: dec esi L5: xor edx,edx mov eax,esi L2: pop esi pop ebx ret 10h } /* *INDENT-ON* */ } void __declspec(naked) _allrem() { /* *INDENT-OFF* */ __asm { push ebx push edi xor edi,edi mov eax,dword ptr [esp+10h] or eax,eax jge L1 inc edi mov edx,dword ptr [esp+0Ch] neg eax neg edx sbb eax,0 mov dword ptr [esp+10h],eax mov dword ptr [esp+0Ch],edx L1: mov eax,dword ptr [esp+18h] or eax,eax jge L2 mov edx,dword ptr [esp+14h] neg eax neg edx sbb eax,0 mov dword ptr [esp+18h],eax mov dword ptr [esp+14h],edx L2: or eax,eax jne L3 mov ecx,dword ptr [esp+14h] mov eax,dword ptr [esp+10h] xor edx,edx div ecx mov eax,dword ptr [esp+0Ch] div ecx mov eax,edx xor edx,edx dec edi jns L4 jmp L8 L3: mov ebx,eax mov ecx,dword ptr [esp+14h] mov edx,dword ptr [esp+10h] mov eax,dword ptr [esp+0Ch] L5: shr ebx,1 rcr ecx,1 shr edx,1 rcr eax,1 or ebx,ebx jne L5 div ecx mov ecx,eax mul dword ptr [esp+18h] xchg eax,ecx mul dword ptr [esp+14h] add edx,ecx jb L6 cmp edx,dword ptr [esp+10h] ja L6 jb L7 cmp eax,dword ptr [esp+0Ch] jbe L7 L6: sub eax,dword ptr [esp+14h] sbb edx,dword ptr [esp+18h] L7: sub eax,dword ptr [esp+0Ch] sbb edx,dword ptr [esp+10h] dec edi jns L8 L4: neg edx neg eax sbb edx,0 L8: pop edi pop ebx ret 10h } /* *INDENT-ON* */ } void __declspec(naked) _aullrem() { /* *INDENT-OFF* */ __asm { push ebx mov eax,dword ptr [esp+14h] or eax,eax jne L1 mov ecx,dword ptr [esp+10h] mov eax,dword ptr [esp+0Ch] xor edx,edx div ecx mov eax,dword ptr [esp+8] div ecx mov eax,edx xor edx,edx jmp L2 L1: mov ecx,eax mov ebx,dword ptr [esp+10h] mov edx,dword ptr [esp+0Ch] mov eax,dword ptr [esp+8] L3: shr ecx,1 rcr ebx,1 shr edx,1 rcr eax,1 or ecx,ecx jne L3 div ebx mov ecx,eax mul dword ptr [esp+14h] xchg eax,ecx mul dword ptr [esp+10h] add edx,ecx jb L4 cmp edx,dword ptr [esp+0Ch] ja L4 jb L5 cmp eax,dword ptr [esp+8] jbe L5 L4: sub eax,dword ptr [esp+10h] sbb edx,dword ptr [esp+14h] L5: sub eax,dword ptr [esp+8] sbb edx,dword ptr [esp+0Ch] neg edx neg eax sbb edx,0 L2: pop ebx ret 10h } /* *INDENT-ON* */ } void __declspec(naked) _alldvrm() { /* *INDENT-OFF* */ __asm { push edi push esi push ebp xor edi,edi xor ebp,ebp mov eax,dword ptr [esp+14h] or eax,eax jge L1 inc edi inc ebp mov edx,dword ptr [esp+10h] neg eax neg edx sbb eax,0 mov dword ptr [esp+14h],eax mov dword ptr [esp+10h],edx L1: mov eax,dword ptr [esp+1Ch] or eax,eax jge L2 inc edi mov edx,dword ptr [esp+18h] neg eax neg edx sbb eax,0 mov dword ptr [esp+1Ch],eax mov dword ptr [esp+18h],edx L2: or eax,eax jne L3 mov ecx,dword ptr [esp+18h] mov eax,dword ptr [esp+14h] xor edx,edx div ecx mov ebx,eax mov eax,dword ptr [esp+10h] div ecx mov esi,eax mov eax,ebx mul dword ptr [esp+18h] mov ecx,eax mov eax,esi mul dword ptr [esp+18h] add edx,ecx jmp L4 L3: mov ebx,eax mov ecx,dword ptr [esp+18h] mov edx,dword ptr [esp+14h] mov eax,dword ptr [esp+10h] L5: shr ebx,1 rcr ecx,1 shr edx,1 rcr eax,1 or ebx,ebx jne L5 div ecx mov esi,eax mul dword ptr [esp+1Ch] mov ecx,eax mov eax,dword ptr [esp+18h] mul esi add edx,ecx jb L6 cmp edx,dword ptr [esp+14h] ja L6 jb L7 cmp eax,dword ptr [esp+10h] jbe L7 L6: dec esi sub eax,dword ptr [esp+18h] sbb edx,dword ptr [esp+1Ch] L7: xor ebx,ebx L4: sub eax,dword ptr [esp+10h] sbb edx,dword ptr [esp+14h] dec ebp jns L9 neg edx neg eax sbb edx,0 L9: mov ecx,edx mov edx,ebx mov ebx,ecx mov ecx,eax mov eax,esi dec edi jne L8 neg edx neg eax sbb edx,0 L8: pop ebp pop esi pop edi ret 10h } /* *INDENT-ON* */ } void __declspec(naked) _aulldvrm() { /* *INDENT-OFF* */ __asm { push esi mov eax,dword ptr [esp+14h] or eax,eax jne L1 mov ecx,dword ptr [esp+10h] mov eax,dword ptr [esp+0Ch] xor edx,edx div ecx mov ebx,eax mov eax,dword ptr [esp+8] div ecx mov esi,eax mov eax,ebx mul dword ptr [esp+10h] mov ecx,eax mov eax,esi mul dword ptr [esp+10h] add edx,ecx jmp L2 L1: mov ecx,eax mov ebx,dword ptr [esp+10h] mov edx,dword ptr [esp+0Ch] mov eax,dword ptr [esp+8] L3: shr ecx,1 rcr ebx,1 shr edx,1 rcr eax,1 or ecx,ecx jne L3 div ebx mov esi,eax mul dword ptr [esp+14h] mov ecx,eax mov eax,dword ptr [esp+10h] mul esi add edx,ecx jb L4 cmp edx,dword ptr [esp+0Ch] ja L4 jb L5 cmp eax,dword ptr [esp+8] jbe L5 L4: dec esi sub eax,dword ptr [esp+10h] sbb edx,dword ptr [esp+14h] L5: xor ebx,ebx L2: sub eax,dword ptr [esp+8] sbb edx,dword ptr [esp+0Ch] neg edx neg eax sbb edx,0 mov ecx,edx mov edx,ebx mov ebx,ecx mov ecx,eax mov eax,esi pop esi ret 10h } /* *INDENT-ON* */ } void __declspec(naked) _allshl() { /* *INDENT-OFF* */ __asm { cmp cl,40h jae RETZERO cmp cl,20h jae MORE32 shld edx,eax,cl shl eax,cl ret MORE32: mov edx,eax xor eax,eax and cl,1Fh shl edx,cl ret RETZERO: xor eax,eax xor edx,edx ret } /* *INDENT-ON* */ } void __declspec(naked) _allshr() { /* *INDENT-OFF* */ __asm { cmp cl,3Fh jae RETSIGN cmp cl,20h jae MORE32 shrd eax,edx,cl sar edx,cl ret MORE32: mov eax,edx sar edx,1Fh and cl,1Fh sar eax,cl ret RETSIGN: sar edx,1Fh mov eax,edx ret } /* *INDENT-ON* */ } void __declspec(naked) _aullshr() { /* *INDENT-OFF* */ __asm { cmp cl,40h jae RETZERO cmp cl,20h jae MORE32 shrd eax,edx,cl shr edx,cl ret MORE32: mov eax,edx xor edx,edx and cl,1Fh shr eax,cl ret RETZERO: xor eax,eax xor edx,edx ret } /* *INDENT-ON* */ } #endif /* _M_IX86 */ #endif /* MSC_VER */ #if defined(__ICL) /* The classic Intel compiler generates calls to _intel_fast_memcpy * and _intel_fast_memset when building an optimized SDL library */ void *_intel_fast_memcpy(void *dst, const void *src, size_t len) { return SDL_memcpy(dst, src, len); } void *_intel_fast_memset(void *dst, int c, size_t len) { return SDL_memset(dst, c, len); } #endif #endif /* !HAVE_LIBC && !SDL_STATIC_LIB */ /* vi: set ts=4 sw=4 expandtab: */