kc3-lang/angle/src/compiler/translator/BuiltInFunctionEmulatorHLSL.cpp
-
Show log
Commit
-
Hash : 74da73fe
Author :
Date : 2017-02-01T15:37:48
Add ESSL 3.10 ldexp/frexp builtins This adds new built-ins found in ESSL 3.10 section 8.3 Common Functions. This includes constant folding support for ldexp and support for both GLSL and HLSL output. In HLSL these functions need to be emulated. BUG=angleproject:1730 TEST=angle_unittests Change-Id: I1330e69978b0cf53efbc3416150194764414e96c Reviewed-on: https://chromium-review.googlesource.com/435342 Reviewed-by: Corentin Wallez <cwallez@chromium.org> Reviewed-by: Jamie Madill <jmadill@chromium.org> Commit-Queue: Olli Etuaho <oetuaho@nvidia.com>
-
src/compiler/translator/BuiltInFunctionEmulatorHLSL.cpp
-
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047
// // Copyright (c) 2014 The ANGLE Project Authors. All rights reserved. // Use of this source code is governed by a BSD-style license that can be // found in the LICENSE file. // #include "angle_gl.h" #include "compiler/translator/BuiltInFunctionEmulator.h" #include "compiler/translator/BuiltInFunctionEmulatorHLSL.h" #include "compiler/translator/SymbolTable.h" #include "compiler/translator/VersionGLSL.h" namespace sh { void InitBuiltInIsnanFunctionEmulatorForHLSLWorkarounds(BuiltInFunctionEmulator *emu, int targetGLSLVersion) { if (targetGLSLVersion < GLSL_VERSION_130) return; TType *float1 = new TType(EbtFloat); TType *float2 = new TType(EbtFloat, 2); TType *float3 = new TType(EbtFloat, 3); TType *float4 = new TType(EbtFloat, 4); emu->addEmulatedFunction(EOpIsNan, float1, "bool webgl_isnan_emu(float x)\n" "{\n" " return (x > 0.0 || x < 0.0) ? false : x != 0.0;\n" "}\n" "\n"); emu->addEmulatedFunction( EOpIsNan, float2, "bool2 webgl_isnan_emu(float2 x)\n" "{\n" " bool2 isnan;\n" " for (int i = 0; i < 2; i++)\n" " {\n" " isnan[i] = (x[i] > 0.0 || x[i] < 0.0) ? false : x[i] != 0.0;\n" " }\n" " return isnan;\n" "}\n"); emu->addEmulatedFunction( EOpIsNan, float3, "bool3 webgl_isnan_emu(float3 x)\n" "{\n" " bool3 isnan;\n" " for (int i = 0; i < 3; i++)\n" " {\n" " isnan[i] = (x[i] > 0.0 || x[i] < 0.0) ? false : x[i] != 0.0;\n" " }\n" " return isnan;\n" "}\n"); emu->addEmulatedFunction( EOpIsNan, float4, "bool4 webgl_isnan_emu(float4 x)\n" "{\n" " bool4 isnan;\n" " for (int i = 0; i < 4; i++)\n" " {\n" " isnan[i] = (x[i] > 0.0 || x[i] < 0.0) ? false : x[i] != 0.0;\n" " }\n" " return isnan;\n" "}\n"); } void InitBuiltInFunctionEmulatorForHLSL(BuiltInFunctionEmulator *emu) { TType *float1 = new TType(EbtFloat); TType *float2 = new TType(EbtFloat, 2); TType *float3 = new TType(EbtFloat, 3); TType *float4 = new TType(EbtFloat, 4); TType *int1 = new TType(EbtInt); TType *int2 = new TType(EbtInt, 2); TType *int3 = new TType(EbtInt, 3); TType *int4 = new TType(EbtInt, 4); TType *uint1 = new TType(EbtUInt); TType *uint2 = new TType(EbtUInt, 2); TType *uint3 = new TType(EbtUInt, 3); TType *uint4 = new TType(EbtUInt, 4); emu->addEmulatedFunction(EOpMod, float1, float1, "float webgl_mod_emu(float x, float y)\n" "{\n" " return x - y * floor(x / y);\n" "}\n" "\n"); emu->addEmulatedFunction(EOpMod, float2, float2, "float2 webgl_mod_emu(float2 x, float2 y)\n" "{\n" " return x - y * floor(x / y);\n" "}\n" "\n"); emu->addEmulatedFunction(EOpMod, float2, float1, "float2 webgl_mod_emu(float2 x, float y)\n" "{\n" " return x - y * floor(x / y);\n" "}\n" "\n"); emu->addEmulatedFunction(EOpMod, float3, float3, "float3 webgl_mod_emu(float3 x, float3 y)\n" "{\n" " return x - y * floor(x / y);\n" "}\n" "\n"); emu->addEmulatedFunction(EOpMod, float3, float1, "float3 webgl_mod_emu(float3 x, float y)\n" "{\n" " return x - y * floor(x / y);\n" "}\n" "\n"); emu->addEmulatedFunction(EOpMod, float4, float4, "float4 webgl_mod_emu(float4 x, float4 y)\n" "{\n" " return x - y * floor(x / y);\n" "}\n" "\n"); emu->addEmulatedFunction(EOpMod, float4, float1, "float4 webgl_mod_emu(float4 x, float y)\n" "{\n" " return x - y * floor(x / y);\n" "}\n" "\n"); emu->addEmulatedFunction(EOpFrexp, float1, int1, "float webgl_frexp_emu(float x, out int exp)\n" "{\n" " float fexp;\n" " float mantissa = frexp(abs(x), fexp) * sign(x);\n" " exp = int(fexp);\n" " return mantissa;\n" "}\n" "\n"); emu->addEmulatedFunction(EOpFrexp, float2, int2, "float2 webgl_frexp_emu(float2 x, out int2 exp)\n" "{\n" " float2 fexp;\n" " float2 mantissa = frexp(abs(x), fexp) * sign(x);\n" " exp = int2(fexp);\n" " return mantissa;\n" "}\n" "\n"); emu->addEmulatedFunction(EOpFrexp, float3, int3, "float3 webgl_frexp_emu(float3 x, out int3 exp)\n" "{\n" " float3 fexp;\n" " float3 mantissa = frexp(abs(x), fexp) * sign(x);\n" " exp = int3(fexp);\n" " return mantissa;\n" "}\n" "\n"); emu->addEmulatedFunction(EOpFrexp, float4, int4, "float4 webgl_frexp_emu(float4 x, out int4 exp)\n" "{\n" " float4 fexp;\n" " float4 mantissa = frexp(abs(x), fexp) * sign(x);\n" " exp = int4(fexp);\n" " return mantissa;\n" "}\n" "\n"); emu->addEmulatedFunction(EOpLdexp, float1, int1, "float webgl_ldexp_emu(float x, int exp)\n" "{\n" " return ldexp(x, float(exp));\n" "}\n" "\n"); emu->addEmulatedFunction(EOpLdexp, float2, int2, "float2 webgl_ldexp_emu(float2 x, int2 exp)\n" "{\n" " return ldexp(x, float2(exp));\n" "}\n" "\n"); emu->addEmulatedFunction(EOpLdexp, float3, int3, "float3 webgl_ldexp_emu(float3 x, int3 exp)\n" "{\n" " return ldexp(x, float3(exp));\n" "}\n" "\n"); emu->addEmulatedFunction(EOpLdexp, float4, int4, "float4 webgl_ldexp_emu(float4 x, int4 exp)\n" "{\n" " return ldexp(x, float4(exp));\n" "}\n" "\n"); emu->addEmulatedFunction(EOpFaceForward, float1, float1, float1, "float webgl_faceforward_emu(float N, float I, float Nref)\n" "{\n" " if(dot(Nref, I) >= 0)\n" " {\n" " return -N;\n" " }\n" " else\n" " {\n" " return N;\n" " }\n" "}\n" "\n"); emu->addEmulatedFunction(EOpFaceForward, float2, float2, float2, "float2 webgl_faceforward_emu(float2 N, float2 I, float2 Nref)\n" "{\n" " if(dot(Nref, I) >= 0)\n" " {\n" " return -N;\n" " }\n" " else\n" " {\n" " return N;\n" " }\n" "}\n" "\n"); emu->addEmulatedFunction(EOpFaceForward, float3, float3, float3, "float3 webgl_faceforward_emu(float3 N, float3 I, float3 Nref)\n" "{\n" " if(dot(Nref, I) >= 0)\n" " {\n" " return -N;\n" " }\n" " else\n" " {\n" " return N;\n" " }\n" "}\n" "\n"); emu->addEmulatedFunction(EOpFaceForward, float4, float4, float4, "float4 webgl_faceforward_emu(float4 N, float4 I, float4 Nref)\n" "{\n" " if(dot(Nref, I) >= 0)\n" " {\n" " return -N;\n" " }\n" " else\n" " {\n" " return N;\n" " }\n" "}\n" "\n"); emu->addEmulatedFunction(EOpAtan, float1, float1, "float webgl_atan_emu(float y, float x)\n" "{\n" " if(x == 0 && y == 0) x = 1;\n" // Avoid producing a NaN " return atan2(y, x);\n" "}\n"); emu->addEmulatedFunction(EOpAtan, float2, float2, "float2 webgl_atan_emu(float2 y, float2 x)\n" "{\n" " if(x[0] == 0 && y[0] == 0) x[0] = 1;\n" " if(x[1] == 0 && y[1] == 0) x[1] = 1;\n" " return float2(atan2(y[0], x[0]), atan2(y[1], x[1]));\n" "}\n"); emu->addEmulatedFunction( EOpAtan, float3, float3, "float3 webgl_atan_emu(float3 y, float3 x)\n" "{\n" " if(x[0] == 0 && y[0] == 0) x[0] = 1;\n" " if(x[1] == 0 && y[1] == 0) x[1] = 1;\n" " if(x[2] == 0 && y[2] == 0) x[2] = 1;\n" " return float3(atan2(y[0], x[0]), atan2(y[1], x[1]), atan2(y[2], x[2]));\n" "}\n"); emu->addEmulatedFunction(EOpAtan, float4, float4, "float4 webgl_atan_emu(float4 y, float4 x)\n" "{\n" " if(x[0] == 0 && y[0] == 0) x[0] = 1;\n" " if(x[1] == 0 && y[1] == 0) x[1] = 1;\n" " if(x[2] == 0 && y[2] == 0) x[2] = 1;\n" " if(x[3] == 0 && y[3] == 0) x[3] = 1;\n" " return float4(atan2(y[0], x[0]), atan2(y[1], x[1]), atan2(y[2], " "x[2]), atan2(y[3], x[3]));\n" "}\n"); emu->addEmulatedFunction(EOpAsinh, float1, "float webgl_asinh_emu(in float x) {\n" " return log(x + sqrt(pow(x, 2.0) + 1.0));\n" "}\n"); emu->addEmulatedFunction(EOpAsinh, float2, "float2 webgl_asinh_emu(in float2 x) {\n" " return log(x + sqrt(pow(x, 2.0) + 1.0));\n" "}\n"); emu->addEmulatedFunction(EOpAsinh, float3, "float3 webgl_asinh_emu(in float3 x) {\n" " return log(x + sqrt(pow(x, 2.0) + 1.0));\n" "}\n"); emu->addEmulatedFunction(EOpAsinh, float4, "float4 webgl_asinh_emu(in float4 x) {\n" " return log(x + sqrt(pow(x, 2.0) + 1.0));\n" "}\n"); emu->addEmulatedFunction(EOpAcosh, float1, "float webgl_acosh_emu(in float x) {\n" " return log(x + sqrt(x + 1.0) * sqrt(x - 1.0));\n" "}\n"); emu->addEmulatedFunction(EOpAcosh, float2, "float2 webgl_acosh_emu(in float2 x) {\n" " return log(x + sqrt(x + 1.0) * sqrt(x - 1.0));\n" "}\n"); emu->addEmulatedFunction(EOpAcosh, float3, "float3 webgl_acosh_emu(in float3 x) {\n" " return log(x + sqrt(x + 1.0) * sqrt(x - 1.0));\n" "}\n"); emu->addEmulatedFunction(EOpAcosh, float4, "float4 webgl_acosh_emu(in float4 x) {\n" " return log(x + sqrt(x + 1.0) * sqrt(x - 1.0));\n" "}\n"); emu->addEmulatedFunction(EOpAtanh, float1, "float webgl_atanh_emu(in float x) {\n" " return 0.5 * log((1.0 + x) / (1.0 - x));\n" "}\n"); emu->addEmulatedFunction(EOpAtanh, float2, "float2 webgl_atanh_emu(in float2 x) {\n" " return 0.5 * log((1.0 + x) / (1.0 - x));\n" "}\n"); emu->addEmulatedFunction(EOpAtanh, float3, "float3 webgl_atanh_emu(in float3 x) {\n" " return 0.5 * log((1.0 + x) / (1.0 - x));\n" "}\n"); emu->addEmulatedFunction(EOpAtanh, float4, "float4 webgl_atanh_emu(in float4 x) {\n" " return 0.5 * log((1.0 + x) / (1.0 - x));\n" "}\n"); emu->addEmulatedFunction( EOpRoundEven, float1, "float webgl_roundEven_emu(in float x) {\n" " return (frac(x) == 0.5 && trunc(x) % 2.0 == 0.0) ? trunc(x) : round(x);\n" "}\n"); emu->addEmulatedFunction( EOpRoundEven, float2, "float2 webgl_roundEven_emu(in float2 x) {\n" " float2 v;\n" " v[0] = (frac(x[0]) == 0.5 && trunc(x[0]) % 2.0 == 0.0) ? trunc(x[0]) : round(x[0]);\n" " v[1] = (frac(x[1]) == 0.5 && trunc(x[1]) % 2.0 == 0.0) ? trunc(x[1]) : round(x[1]);\n" " return v;\n" "}\n"); emu->addEmulatedFunction( EOpRoundEven, float3, "float3 webgl_roundEven_emu(in float3 x) {\n" " float3 v;\n" " v[0] = (frac(x[0]) == 0.5 && trunc(x[0]) % 2.0 == 0.0) ? trunc(x[0]) : round(x[0]);\n" " v[1] = (frac(x[1]) == 0.5 && trunc(x[1]) % 2.0 == 0.0) ? trunc(x[1]) : round(x[1]);\n" " v[2] = (frac(x[2]) == 0.5 && trunc(x[2]) % 2.0 == 0.0) ? trunc(x[2]) : round(x[2]);\n" " return v;\n" "}\n"); emu->addEmulatedFunction( EOpRoundEven, float4, "float4 webgl_roundEven_emu(in float4 x) {\n" " float4 v;\n" " v[0] = (frac(x[0]) == 0.5 && trunc(x[0]) % 2.0 == 0.0) ? trunc(x[0]) : round(x[0]);\n" " v[1] = (frac(x[1]) == 0.5 && trunc(x[1]) % 2.0 == 0.0) ? trunc(x[1]) : round(x[1]);\n" " v[2] = (frac(x[2]) == 0.5 && trunc(x[2]) % 2.0 == 0.0) ? trunc(x[2]) : round(x[2]);\n" " v[3] = (frac(x[3]) == 0.5 && trunc(x[3]) % 2.0 == 0.0) ? trunc(x[3]) : round(x[3]);\n" " return v;\n" "}\n"); emu->addEmulatedFunction(EOpPackSnorm2x16, float2, "int webgl_toSnorm16(in float x) {\n" " return int(round(clamp(x, -1.0, 1.0) * 32767.0));\n" "}\n" "\n" "uint webgl_packSnorm2x16_emu(in float2 v) {\n" " int x = webgl_toSnorm16(v.x);\n" " int y = webgl_toSnorm16(v.y);\n" " return (asuint(y) << 16) | (asuint(x) & 0xffffu);\n" "}\n"); emu->addEmulatedFunction(EOpPackUnorm2x16, float2, "uint webgl_toUnorm16(in float x) {\n" " return uint(round(clamp(x, 0.0, 1.0) * 65535.0));\n" "}\n" "\n" "uint webgl_packUnorm2x16_emu(in float2 v) {\n" " uint x = webgl_toUnorm16(v.x);\n" " uint y = webgl_toUnorm16(v.y);\n" " return (y << 16) | x;\n" "}\n"); emu->addEmulatedFunction(EOpPackHalf2x16, float2, "uint webgl_packHalf2x16_emu(in float2 v) {\n" " uint x = f32tof16(v.x);\n" " uint y = f32tof16(v.y);\n" " return (y << 16) | x;\n" "}\n"); emu->addEmulatedFunction(EOpUnpackSnorm2x16, uint1, "float webgl_fromSnorm16(in uint x) {\n" " int xi = asint(x & 0x7fffu) - asint(x & 0x8000u);\n" " return clamp(float(xi) / 32767.0, -1.0, 1.0);\n" "}\n" "\n" "float2 webgl_unpackSnorm2x16_emu(in uint u) {\n" " uint y = (u >> 16);\n" " uint x = u;\n" " return float2(webgl_fromSnorm16(x), webgl_fromSnorm16(y));\n" "}\n"); emu->addEmulatedFunction(EOpUnpackUnorm2x16, uint1, "float webgl_fromUnorm16(in uint x) {\n" " return float(x) / 65535.0;\n" "}\n" "\n" "float2 webgl_unpackUnorm2x16_emu(in uint u) {\n" " uint y = (u >> 16);\n" " uint x = u & 0xffffu;\n" " return float2(webgl_fromUnorm16(x), webgl_fromUnorm16(y));\n" "}\n"); emu->addEmulatedFunction(EOpUnpackHalf2x16, uint1, "float2 webgl_unpackHalf2x16_emu(in uint u) {\n" " uint y = (u >> 16);\n" " uint x = u & 0xffffu;\n" " return float2(f16tof32(x), f16tof32(y));\n" "}\n"); emu->addEmulatedFunction(EOpPackSnorm4x8, float4, "int webgl_toSnorm8(in float x) {\n" " return int(round(clamp(x, -1.0, 1.0) * 127.0));\n" "}\n" "\n" "uint webgl_packSnorm4x8_emu(in float4 v) {\n" " int x = webgl_toSnorm8(v.x);\n" " int y = webgl_toSnorm8(v.y);\n" " int z = webgl_toSnorm8(v.z);\n" " int w = webgl_toSnorm8(v.w);\n" " return ((asuint(w) & 0xffu) << 24) | ((asuint(z) & 0xffu) << 16) " "| ((asuint(y) & 0xffu) << 8) | (asuint(x) & 0xffu);\n" "}\n"); emu->addEmulatedFunction(EOpPackUnorm4x8, float4, "uint webgl_toUnorm8(in float x) {\n" " return uint(round(clamp(x, 0.0, 1.0) * 255.0));\n" "}\n" "\n" "uint webgl_packUnorm4x8_emu(in float4 v) {\n" " uint x = webgl_toUnorm8(v.x);\n" " uint y = webgl_toUnorm8(v.y);\n" " uint z = webgl_toUnorm8(v.z);\n" " uint w = webgl_toUnorm8(v.w);\n" " return (w << 24) | (z << 16) | (y << 8) | x;\n" "}\n"); emu->addEmulatedFunction(EOpUnpackSnorm4x8, uint1, "float webgl_fromSnorm8(in uint x) {\n" " int xi = asint(x & 0x7fu) - asint(x & 0x80u);\n" " return clamp(float(xi) / 127.0, -1.0, 1.0);\n" "}\n" "\n" "float4 webgl_unpackSnorm4x8_emu(in uint u) {\n" " uint w = (u >> 24);\n" " uint z = (u >> 16);\n" " uint y = (u >> 8);\n" " uint x = u;\n" " return float4(webgl_fromSnorm8(x), webgl_fromSnorm8(y), " "webgl_fromSnorm8(z), webgl_fromSnorm8(w));\n" "}\n"); emu->addEmulatedFunction(EOpUnpackUnorm4x8, uint1, "float webgl_fromUnorm8(in uint x) {\n" " return float(x) / 255.0;\n" "}\n" "\n" "float4 webgl_unpackUnorm4x8_emu(in uint u) {\n" " uint w = (u >> 24) & 0xffu;\n" " uint z = (u >> 16) & 0xffu;\n" " uint y = (u >> 8) & 0xffu;\n" " uint x = u & 0xffu;\n" " return float4(webgl_fromUnorm8(x), webgl_fromUnorm8(y), " "webgl_fromUnorm8(z), webgl_fromUnorm8(w));\n" "}\n"); // The matrix resulting from outer product needs to be transposed // (matrices are stored as transposed to simplify element access in HLSL). // So the function should return transpose(c * r) where c is a column vector // and r is a row vector. This can be simplified by using the following // formula: // transpose(c * r) = transpose(r) * transpose(c) // transpose(r) and transpose(c) are in a sense free, since to get the // transpose of r, we simply can build a column matrix out of the original // vector instead of a row matrix. emu->addEmulatedFunction(EOpOuterProduct, float2, float2, "float2x2 webgl_outerProduct_emu(in float2 c, in float2 r) {\n" " return mul(float2x1(r), float1x2(c));\n" "}\n"); emu->addEmulatedFunction(EOpOuterProduct, float3, float3, "float3x3 webgl_outerProduct_emu(in float3 c, in float3 r) {\n" " return mul(float3x1(r), float1x3(c));\n" "}\n"); emu->addEmulatedFunction(EOpOuterProduct, float4, float4, "float4x4 webgl_outerProduct_emu(in float4 c, in float4 r) {\n" " return mul(float4x1(r), float1x4(c));\n" "}\n"); emu->addEmulatedFunction(EOpOuterProduct, float3, float2, "float2x3 webgl_outerProduct_emu(in float3 c, in float2 r) {\n" " return mul(float2x1(r), float1x3(c));\n" "}\n"); emu->addEmulatedFunction(EOpOuterProduct, float2, float3, "float3x2 webgl_outerProduct_emu(in float2 c, in float3 r) {\n" " return mul(float3x1(r), float1x2(c));\n" "}\n"); emu->addEmulatedFunction(EOpOuterProduct, float4, float2, "float2x4 webgl_outerProduct_emu(in float4 c, in float2 r) {\n" " return mul(float2x1(r), float1x4(c));\n" "}\n"); emu->addEmulatedFunction(EOpOuterProduct, float2, float4, "float4x2 webgl_outerProduct_emu(in float2 c, in float4 r) {\n" " return mul(float4x1(r), float1x2(c));\n" "}\n"); emu->addEmulatedFunction(EOpOuterProduct, float4, float3, "float3x4 webgl_outerProduct_emu(in float4 c, in float3 r) {\n" " return mul(float3x1(r), float1x4(c));\n" "}\n"); emu->addEmulatedFunction(EOpOuterProduct, float3, float4, "float4x3 webgl_outerProduct_emu(in float3 c, in float4 r) {\n" " return mul(float4x1(r), float1x3(c));\n" "}\n"); TType *mat2 = new TType(EbtFloat, 2, 2); TType *mat3 = new TType(EbtFloat, 3, 3); TType *mat4 = new TType(EbtFloat, 4, 4); // Remember here that the parameter matrix is actually the transpose // of the matrix that we're trying to invert, and the resulting matrix // should also be the transpose of the inverse. // When accessing the parameter matrix with m[a][b] it can be thought of so // that a is the column and b is the row of the matrix that we're inverting. // We calculate the inverse as the adjugate matrix divided by the // determinant of the matrix being inverted. However, as the result needs // to be transposed, we actually use of the transpose of the adjugate matrix // which happens to be the cofactor matrix. That's stored in "cof". // We don't need to care about divide-by-zero since results are undefined // for singular or poorly-conditioned matrices. emu->addEmulatedFunction(EOpInverse, mat2, "float2x2 webgl_inverse_emu(in float2x2 m) {\n" " float2x2 cof = { m[1][1], -m[0][1], -m[1][0], m[0][0] };\n" " return cof / determinant(transpose(m));\n" "}\n"); // cofAB is the cofactor for column A and row B. emu->addEmulatedFunction( EOpInverse, mat3, "float3x3 webgl_inverse_emu(in float3x3 m) {\n" " float cof00 = m[1][1] * m[2][2] - m[2][1] * m[1][2];\n" " float cof01 = -(m[1][0] * m[2][2] - m[2][0] * m[1][2]);\n" " float cof02 = m[1][0] * m[2][1] - m[2][0] * m[1][1];\n" " float cof10 = -(m[0][1] * m[2][2] - m[2][1] * m[0][2]);\n" " float cof11 = m[0][0] * m[2][2] - m[2][0] * m[0][2];\n" " float cof12 = -(m[0][0] * m[2][1] - m[2][0] * m[0][1]);\n" " float cof20 = m[0][1] * m[1][2] - m[1][1] * m[0][2];\n" " float cof21 = -(m[0][0] * m[1][2] - m[1][0] * m[0][2]);\n" " float cof22 = m[0][0] * m[1][1] - m[1][0] * m[0][1];\n" " float3x3 cof = { cof00, cof10, cof20, cof01, cof11, cof21, cof02, cof12, cof22 };\n" " return cof / determinant(transpose(m));\n" "}\n"); emu->addEmulatedFunction( EOpInverse, mat4, "float4x4 webgl_inverse_emu(in float4x4 m) {\n" " float cof00 = m[1][1] * m[2][2] * m[3][3] + m[2][1] * m[3][2] * m[1][3] + m[3][1] * " "m[1][2] * m[2][3]" " - m[1][1] * m[3][2] * m[2][3] - m[2][1] * m[1][2] * m[3][3] - m[3][1] * m[2][2] * " "m[1][3];\n" " float cof01 = -(m[1][0] * m[2][2] * m[3][3] + m[2][0] * m[3][2] * m[1][3] + m[3][0] * " "m[1][2] * m[2][3]" " - m[1][0] * m[3][2] * m[2][3] - m[2][0] * m[1][2] * m[3][3] - m[3][0] * m[2][2] * " "m[1][3]);\n" " float cof02 = m[1][0] * m[2][1] * m[3][3] + m[2][0] * m[3][1] * m[1][3] + m[3][0] * " "m[1][1] * m[2][3]" " - m[1][0] * m[3][1] * m[2][3] - m[2][0] * m[1][1] * m[3][3] - m[3][0] * m[2][1] * " "m[1][3];\n" " float cof03 = -(m[1][0] * m[2][1] * m[3][2] + m[2][0] * m[3][1] * m[1][2] + m[3][0] * " "m[1][1] * m[2][2]" " - m[1][0] * m[3][1] * m[2][2] - m[2][0] * m[1][1] * m[3][2] - m[3][0] * m[2][1] * " "m[1][2]);\n" " float cof10 = -(m[0][1] * m[2][2] * m[3][3] + m[2][1] * m[3][2] * m[0][3] + m[3][1] * " "m[0][2] * m[2][3]" " - m[0][1] * m[3][2] * m[2][3] - m[2][1] * m[0][2] * m[3][3] - m[3][1] * m[2][2] * " "m[0][3]);\n" " float cof11 = m[0][0] * m[2][2] * m[3][3] + m[2][0] * m[3][2] * m[0][3] + m[3][0] * " "m[0][2] * m[2][3]" " - m[0][0] * m[3][2] * m[2][3] - m[2][0] * m[0][2] * m[3][3] - m[3][0] * m[2][2] * " "m[0][3];\n" " float cof12 = -(m[0][0] * m[2][1] * m[3][3] + m[2][0] * m[3][1] * m[0][3] + m[3][0] * " "m[0][1] * m[2][3]" " - m[0][0] * m[3][1] * m[2][3] - m[2][0] * m[0][1] * m[3][3] - m[3][0] * m[2][1] * " "m[0][3]);\n" " float cof13 = m[0][0] * m[2][1] * m[3][2] + m[2][0] * m[3][1] * m[0][2] + m[3][0] * " "m[0][1] * m[2][2]" " - m[0][0] * m[3][1] * m[2][2] - m[2][0] * m[0][1] * m[3][2] - m[3][0] * m[2][1] * " "m[0][2];\n" " float cof20 = m[0][1] * m[1][2] * m[3][3] + m[1][1] * m[3][2] * m[0][3] + m[3][1] * " "m[0][2] * m[1][3]" " - m[0][1] * m[3][2] * m[1][3] - m[1][1] * m[0][2] * m[3][3] - m[3][1] * m[1][2] * " "m[0][3];\n" " float cof21 = -(m[0][0] * m[1][2] * m[3][3] + m[1][0] * m[3][2] * m[0][3] + m[3][0] * " "m[0][2] * m[1][3]" " - m[0][0] * m[3][2] * m[1][3] - m[1][0] * m[0][2] * m[3][3] - m[3][0] * m[1][2] * " "m[0][3]);\n" " float cof22 = m[0][0] * m[1][1] * m[3][3] + m[1][0] * m[3][1] * m[0][3] + m[3][0] * " "m[0][1] * m[1][3]" " - m[0][0] * m[3][1] * m[1][3] - m[1][0] * m[0][1] * m[3][3] - m[3][0] * m[1][1] * " "m[0][3];\n" " float cof23 = -(m[0][0] * m[1][1] * m[3][2] + m[1][0] * m[3][1] * m[0][2] + m[3][0] * " "m[0][1] * m[1][2]" " - m[0][0] * m[3][1] * m[1][2] - m[1][0] * m[0][1] * m[3][2] - m[3][0] * m[1][1] * " "m[0][2]);\n" " float cof30 = -(m[0][1] * m[1][2] * m[2][3] + m[1][1] * m[2][2] * m[0][3] + m[2][1] * " "m[0][2] * m[1][3]" " - m[0][1] * m[2][2] * m[1][3] - m[1][1] * m[0][2] * m[2][3] - m[2][1] * m[1][2] * " "m[0][3]);\n" " float cof31 = m[0][0] * m[1][2] * m[2][3] + m[1][0] * m[2][2] * m[0][3] + m[2][0] * " "m[0][2] * m[1][3]" " - m[0][0] * m[2][2] * m[1][3] - m[1][0] * m[0][2] * m[2][3] - m[2][0] * m[1][2] * " "m[0][3];\n" " float cof32 = -(m[0][0] * m[1][1] * m[2][3] + m[1][0] * m[2][1] * m[0][3] + m[2][0] * " "m[0][1] * m[1][3]" " - m[0][0] * m[2][1] * m[1][3] - m[1][0] * m[0][1] * m[2][3] - m[2][0] * m[1][1] * " "m[0][3]);\n" " float cof33 = m[0][0] * m[1][1] * m[2][2] + m[1][0] * m[2][1] * m[0][2] + m[2][0] * " "m[0][1] * m[1][2]" " - m[0][0] * m[2][1] * m[1][2] - m[1][0] * m[0][1] * m[2][2] - m[2][0] * m[1][1] * " "m[0][2];\n" " float4x4 cof = { cof00, cof10, cof20, cof30, cof01, cof11, cof21, cof31," " cof02, cof12, cof22, cof32, cof03, cof13, cof23, cof33 };\n" " return cof / determinant(transpose(m));\n" "}\n"); TType *bool1 = new TType(EbtBool); TType *bool2 = new TType(EbtBool, 2); TType *bool3 = new TType(EbtBool, 3); TType *bool4 = new TType(EbtBool, 4); // Emulate ESSL3 variant of mix that takes last argument as boolean vector. // genType mix (genType x, genType y, genBType a): Selects which vector each returned component // comes from. // For a component of 'a' that is false, the corresponding component of 'x' is returned.For a // component of 'a' that is true, // the corresponding component of 'y' is returned. emu->addEmulatedFunction(EOpMix, float1, float1, bool1, "float webgl_mix_emu(float x, float y, bool a)\n" "{\n" " return a ? y : x;\n" "}\n"); emu->addEmulatedFunction(EOpMix, float2, float2, bool2, "float2 webgl_mix_emu(float2 x, float2 y, bool2 a)\n" "{\n" " return a ? y : x;\n" "}\n"); emu->addEmulatedFunction(EOpMix, float3, float3, bool3, "float3 webgl_mix_emu(float3 x, float3 y, bool3 a)\n" "{\n" " return a ? y : x;\n" "}\n"); emu->addEmulatedFunction(EOpMix, float4, float4, bool4, "float4 webgl_mix_emu(float4 x, float4 y, bool4 a)\n" "{\n" " return a ? y : x;\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldExtract, uint1, int1, int1, "uint webgl_bitfieldExtract_emu(uint value, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return 0u;\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint mask = ((maskMsb - 1u) | maskMsb) << offset;\n" " return (value & mask) >> offset;\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldExtract, uint2, int1, int1, "uint2 webgl_bitfieldExtract_emu(uint2 value, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return uint2(0u, 0u);\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint mask = ((maskMsb - 1u) | maskMsb) << offset;\n" " return (value & mask) >> offset;\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldExtract, uint3, int1, int1, "uint3 webgl_bitfieldExtract_emu(uint3 value, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return uint3(0u, 0u, 0u);\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint mask = ((maskMsb - 1u) | maskMsb) << offset;\n" " return (value & mask) >> offset;\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldExtract, uint4, int1, int1, "uint4 webgl_bitfieldExtract_emu(uint4 value, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return uint4(0u, 0u, 0u, 0u);\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint mask = ((maskMsb - 1u) | maskMsb) << offset;\n" " return (value & mask) >> offset;\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldExtract, int1, int1, int1, "int webgl_bitfieldExtract_emu(int value, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return 0;\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint mask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint resultUnsigned = (asuint(value) & mask) >> offset;\n" " if (bits != 32 && (resultUnsigned & maskMsb) != 0)\n" " {\n" " uint higherBitsMask = ((1u << (32 - bits)) - 1u) << bits;\n" " resultUnsigned |= higherBitsMask;\n" " }\n" " return asint(resultUnsigned);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldExtract, int2, int1, int1, "int2 webgl_bitfieldExtract_emu(int2 value, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return int2(0, 0);\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint mask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint2 resultUnsigned = (asuint(value) & mask) >> offset;\n" " if (bits != 32)\n" " {\n" " uint higherBitsMask = ((1u << (32 - bits)) - 1u) << bits;\n" " resultUnsigned |= ((resultUnsigned & maskMsb) >> (bits - 1)) * higherBitsMask;\n" " }\n" " return asint(resultUnsigned);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldExtract, int3, int1, int1, "int3 webgl_bitfieldExtract_emu(int3 value, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return int3(0, 0, 0);\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint mask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint3 resultUnsigned = (asuint(value) & mask) >> offset;\n" " if (bits != 32)\n" " {\n" " uint higherBitsMask = ((1u << (32 - bits)) - 1u) << bits;\n" " resultUnsigned |= ((resultUnsigned & maskMsb) >> (bits - 1)) * higherBitsMask;\n" " }\n" " return asint(resultUnsigned);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldExtract, int4, int1, int1, "int4 webgl_bitfieldExtract_emu(int4 value, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return int4(0, 0, 0, 0);\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint mask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint4 resultUnsigned = (asuint(value) & mask) >> offset;\n" " if (bits != 32)\n" " {\n" " uint higherBitsMask = ((1u << (32 - bits)) - 1u) << bits;\n" " resultUnsigned |= ((resultUnsigned & maskMsb) >> (bits - 1)) * higherBitsMask;\n" " }\n" " return asint(resultUnsigned);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldInsert, uint1, uint1, int1, int1, "uint webgl_bitfieldInsert_emu(uint base, uint insert, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return base;\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint insertMask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint baseMask = ~insertMask;\n" " return (base & baseMask) | ((insert << offset) & insertMask);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldInsert, uint2, uint2, int1, int1, "uint2 webgl_bitfieldInsert_emu(uint2 base, uint2 insert, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return base;\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint insertMask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint baseMask = ~insertMask;\n" " return (base & baseMask) | ((insert << offset) & insertMask);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldInsert, uint3, uint3, int1, int1, "uint3 webgl_bitfieldInsert_emu(uint3 base, uint3 insert, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return base;\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint insertMask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint baseMask = ~insertMask;\n" " return (base & baseMask) | ((insert << offset) & insertMask);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldInsert, uint4, uint4, int1, int1, "uint4 webgl_bitfieldInsert_emu(uint4 base, uint4 insert, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return base;\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint insertMask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint baseMask = ~insertMask;\n" " return (base & baseMask) | ((insert << offset) & insertMask);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldInsert, int1, int1, int1, int1, "int webgl_bitfieldInsert_emu(int base, int insert, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return base;\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint insertMask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint baseMask = ~insertMask;\n" " uint resultUnsigned = (asuint(base) & baseMask) | ((asuint(insert) << offset) & " "insertMask);\n" " return asint(resultUnsigned);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldInsert, int2, int2, int1, int1, "int2 webgl_bitfieldInsert_emu(int2 base, int2 insert, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return base;\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint insertMask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint baseMask = ~insertMask;\n" " uint2 resultUnsigned = (asuint(base) & baseMask) | ((asuint(insert) << offset) & " "insertMask);\n" " return asint(resultUnsigned);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldInsert, int3, int3, int1, int1, "int3 webgl_bitfieldInsert_emu(int3 base, int3 insert, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return base;\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint insertMask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint baseMask = ~insertMask;\n" " uint3 resultUnsigned = (asuint(base) & baseMask) | ((asuint(insert) << offset) & " "insertMask);\n" " return asint(resultUnsigned);\n" "}\n"); emu->addEmulatedFunction( EOpBitfieldInsert, int4, int4, int1, int1, "int4 webgl_bitfieldInsert_emu(int4 base, int4 insert, int offset, int bits)\n" "{\n" " if (offset < 0 || bits <= 0 || offset >= 32 || bits > 32 || offset + bits > 32)\n" " {\n" " return base;\n" " }\n" " uint maskMsb = (1u << (bits - 1));\n" " uint insertMask = ((maskMsb - 1u) | maskMsb) << offset;\n" " uint baseMask = ~insertMask;\n" " uint4 resultUnsigned = (asuint(base) & baseMask) | ((asuint(insert) << offset) & " "insertMask);\n" " return asint(resultUnsigned);\n" "}\n"); emu->addEmulatedFunction(EOpUaddCarry, uint1, uint1, uint1, "uint webgl_uaddCarry_emu(uint x, uint y, out uint carry)\n" "{\n" " carry = uint(x > (0xffffffffu - y));\n" " return x + y;\n" "}\n"); emu->addEmulatedFunction(EOpUaddCarry, uint2, uint2, uint2, "uint2 webgl_uaddCarry_emu(uint2 x, uint2 y, out uint2 carry)\n" "{\n" " carry = uint2(x > (0xffffffffu - y));\n" " return x + y;\n" "}\n"); emu->addEmulatedFunction(EOpUaddCarry, uint3, uint3, uint3, "uint3 webgl_uaddCarry_emu(uint3 x, uint3 y, out uint3 carry)\n" "{\n" " carry = uint3(x > (0xffffffffu - y));\n" " return x + y;\n" "}\n"); emu->addEmulatedFunction(EOpUaddCarry, uint4, uint4, uint4, "uint4 webgl_uaddCarry_emu(uint4 x, uint4 y, out uint4 carry)\n" "{\n" " carry = uint4(x > (0xffffffffu - y));\n" " return x + y;\n" "}\n"); emu->addEmulatedFunction(EOpUsubBorrow, uint1, uint1, uint1, "uint webgl_usubBorrow_emu(uint x, uint y, out uint borrow)\n" "{\n" " borrow = uint(x < y);\n" " return x - y;\n" "}\n"); emu->addEmulatedFunction(EOpUsubBorrow, uint2, uint2, uint2, "uint2 webgl_usubBorrow_emu(uint2 x, uint2 y, out uint2 borrow)\n" "{\n" " borrow = uint2(x < y);\n" " return x - y;\n" "}\n"); emu->addEmulatedFunction(EOpUsubBorrow, uint3, uint3, uint3, "uint3 webgl_usubBorrow_emu(uint3 x, uint3 y, out uint3 borrow)\n" "{\n" " borrow = uint3(x < y);\n" " return x - y;\n" "}\n"); emu->addEmulatedFunction(EOpUsubBorrow, uint4, uint4, uint4, "uint4 webgl_usubBorrow_emu(uint4 x, uint4 y, out uint4 borrow)\n" "{\n" " borrow = uint4(x < y);\n" " return x - y;\n" "}\n"); // (a + b2^16) * (c + d2^16) = ac + (ad + bc) * 2^16 + bd * 2^32 // Also note that below, a * d + ((a * c) >> 16) is guaranteed not to overflow, because: // a <= 0xffff, d <= 0xffff, ((a * c) >> 16) <= 0xffff and 0xffff * 0xffff + 0xffff = 0xffff0000 BuiltInFunctionEmulator::FunctionId umulExtendedUint1 = emu->addEmulatedFunction( EOpUmulExtended, uint1, uint1, uint1, uint1, "void webgl_umulExtended_emu(uint x, uint y, out uint msb, out uint lsb)\n" "{\n" " lsb = x * y;\n" " uint a = (x & 0xffffu);\n" " uint b = (x >> 16);\n" " uint c = (y & 0xffffu);\n" " uint d = (y >> 16);\n" " uint ad = a * d + ((a * c) >> 16);\n" " uint bc = b * c;\n" " uint carry = uint(ad > (0xffffffffu - bc));\n" " msb = ((ad + bc) >> 16) + (carry << 16) + b * d;\n" "}\n"); emu->addEmulatedFunctionWithDependency( umulExtendedUint1, EOpUmulExtended, uint2, uint2, uint2, uint2, "void webgl_umulExtended_emu(uint2 x, uint2 y, out uint2 msb, out uint2 lsb)\n" "{\n" " webgl_umulExtended_emu(x.x, y.x, msb.x, lsb.x);\n" " webgl_umulExtended_emu(x.y, y.y, msb.y, lsb.y);\n" "}\n"); emu->addEmulatedFunctionWithDependency( umulExtendedUint1, EOpUmulExtended, uint3, uint3, uint3, uint3, "void webgl_umulExtended_emu(uint3 x, uint3 y, out uint3 msb, out uint3 lsb)\n" "{\n" " webgl_umulExtended_emu(x.x, y.x, msb.x, lsb.x);\n" " webgl_umulExtended_emu(x.y, y.y, msb.y, lsb.y);\n" " webgl_umulExtended_emu(x.z, y.z, msb.z, lsb.z);\n" "}\n"); emu->addEmulatedFunctionWithDependency( umulExtendedUint1, EOpUmulExtended, uint4, uint4, uint4, uint4, "void webgl_umulExtended_emu(uint4 x, uint4 y, out uint4 msb, out uint4 lsb)\n" "{\n" " webgl_umulExtended_emu(x.x, y.x, msb.x, lsb.x);\n" " webgl_umulExtended_emu(x.y, y.y, msb.y, lsb.y);\n" " webgl_umulExtended_emu(x.z, y.z, msb.z, lsb.z);\n" " webgl_umulExtended_emu(x.w, y.w, msb.w, lsb.w);\n" "}\n"); // The imul emulation does two's complement negation on the lsb and msb manually in case the // result needs to be negative. // TODO(oetuaho): Note that this code doesn't take one edge case into account, where x or y is // -2^31. abs(-2^31) is undefined. BuiltInFunctionEmulator::FunctionId imulExtendedInt1 = emu->addEmulatedFunctionWithDependency( umulExtendedUint1, EOpImulExtended, int1, int1, int1, int1, "void webgl_imulExtended_emu(int x, int y, out int msb, out int lsb)\n" "{\n" " uint unsignedMsb;\n" " uint unsignedLsb;\n" " bool negative = (x < 0) != (y < 0);\n" " webgl_umulExtended_emu(uint(abs(x)), uint(abs(y)), unsignedMsb, unsignedLsb);\n" " lsb = asint(unsignedLsb);\n" " msb = asint(unsignedMsb);\n" " if (negative)\n" " {\n" " lsb = ~lsb;\n" " msb = ~msb;\n" " if (lsb == 0xffffffff)\n" " {\n" " lsb = 0;\n" " msb += 1;\n" " }\n" " else\n" " {\n" " lsb += 1;\n" " }\n" " }\n" "}\n"); emu->addEmulatedFunctionWithDependency( imulExtendedInt1, EOpImulExtended, int2, int2, int2, int2, "void webgl_imulExtended_emu(int2 x, int2 y, out int2 msb, out int2 lsb)\n" "{\n" " webgl_imulExtended_emu(x.x, y.x, msb.x, lsb.x);\n" " webgl_imulExtended_emu(x.y, y.y, msb.y, lsb.y);\n" "}\n"); emu->addEmulatedFunctionWithDependency( imulExtendedInt1, EOpImulExtended, int3, int3, int3, int3, "void webgl_imulExtended_emu(int3 x, int3 y, out int3 msb, out int3 lsb)\n" "{\n" " webgl_imulExtended_emu(x.x, y.x, msb.x, lsb.x);\n" " webgl_imulExtended_emu(x.y, y.y, msb.y, lsb.y);\n" " webgl_imulExtended_emu(x.z, y.z, msb.z, lsb.z);\n" "}\n"); emu->addEmulatedFunctionWithDependency( imulExtendedInt1, EOpImulExtended, int4, int4, int4, int4, "void webgl_imulExtended_emu(int4 x, int4 y, out int4 msb, out int4 lsb)\n" "{\n" " webgl_imulExtended_emu(x.x, y.x, msb.x, lsb.x);\n" " webgl_imulExtended_emu(x.y, y.y, msb.y, lsb.y);\n" " webgl_imulExtended_emu(x.z, y.z, msb.z, lsb.z);\n" " webgl_imulExtended_emu(x.w, y.w, msb.w, lsb.w);\n" "}\n"); } } // namespace sh