/usr/include/bullet/Bullet3OpenCL/NarrowphaseCollision/kernels/satConcaveKernels.h is in libbullet-dev 2.87+dfsg-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 | //this file is autogenerated using stringify.bat (premake --stringify) in the build folder of this project
static const char* satConcaveKernelsCL= \
"//keep this enum in sync with the CPU version (in btCollidable.h)\n"
"//written by Erwin Coumans\n"
"#define SHAPE_CONVEX_HULL 3\n"
"#define SHAPE_CONCAVE_TRIMESH 5\n"
"#define TRIANGLE_NUM_CONVEX_FACES 5\n"
"#define SHAPE_COMPOUND_OF_CONVEX_HULLS 6\n"
"#define B3_MAX_STACK_DEPTH 256\n"
"typedef unsigned int u32;\n"
"///keep this in sync with btCollidable.h\n"
"typedef struct\n"
"{\n"
" union {\n"
" int m_numChildShapes;\n"
" int m_bvhIndex;\n"
" };\n"
" union\n"
" {\n"
" float m_radius;\n"
" int m_compoundBvhIndex;\n"
" };\n"
" \n"
" int m_shapeType;\n"
" int m_shapeIndex;\n"
" \n"
"} btCollidableGpu;\n"
"#define MAX_NUM_PARTS_IN_BITS 10\n"
"///b3QuantizedBvhNode is a compressed aabb node, 16 bytes.\n"
"///Node can be used for leafnode or internal node. Leafnodes can point to 32-bit triangle index (non-negative range).\n"
"typedef struct\n"
"{\n"
" //12 bytes\n"
" unsigned short int m_quantizedAabbMin[3];\n"
" unsigned short int m_quantizedAabbMax[3];\n"
" //4 bytes\n"
" int m_escapeIndexOrTriangleIndex;\n"
"} b3QuantizedBvhNode;\n"
"typedef struct\n"
"{\n"
" float4 m_aabbMin;\n"
" float4 m_aabbMax;\n"
" float4 m_quantization;\n"
" int m_numNodes;\n"
" int m_numSubTrees;\n"
" int m_nodeOffset;\n"
" int m_subTreeOffset;\n"
"} b3BvhInfo;\n"
"int getTriangleIndex(const b3QuantizedBvhNode* rootNode)\n"
"{\n"
" unsigned int x=0;\n"
" unsigned int y = (~(x&0))<<(31-MAX_NUM_PARTS_IN_BITS);\n"
" // Get only the lower bits where the triangle index is stored\n"
" return (rootNode->m_escapeIndexOrTriangleIndex&~(y));\n"
"}\n"
"int getTriangleIndexGlobal(__global const b3QuantizedBvhNode* rootNode)\n"
"{\n"
" unsigned int x=0;\n"
" unsigned int y = (~(x&0))<<(31-MAX_NUM_PARTS_IN_BITS);\n"
" // Get only the lower bits where the triangle index is stored\n"
" return (rootNode->m_escapeIndexOrTriangleIndex&~(y));\n"
"}\n"
"int isLeafNode(const b3QuantizedBvhNode* rootNode)\n"
"{\n"
" //skipindex is negative (internal node), triangleindex >=0 (leafnode)\n"
" return (rootNode->m_escapeIndexOrTriangleIndex >= 0)? 1 : 0;\n"
"}\n"
"int isLeafNodeGlobal(__global const b3QuantizedBvhNode* rootNode)\n"
"{\n"
" //skipindex is negative (internal node), triangleindex >=0 (leafnode)\n"
" return (rootNode->m_escapeIndexOrTriangleIndex >= 0)? 1 : 0;\n"
"}\n"
" \n"
"int getEscapeIndex(const b3QuantizedBvhNode* rootNode)\n"
"{\n"
" return -rootNode->m_escapeIndexOrTriangleIndex;\n"
"}\n"
"int getEscapeIndexGlobal(__global const b3QuantizedBvhNode* rootNode)\n"
"{\n"
" return -rootNode->m_escapeIndexOrTriangleIndex;\n"
"}\n"
"typedef struct\n"
"{\n"
" //12 bytes\n"
" unsigned short int m_quantizedAabbMin[3];\n"
" unsigned short int m_quantizedAabbMax[3];\n"
" //4 bytes, points to the root of the subtree\n"
" int m_rootNodeIndex;\n"
" //4 bytes\n"
" int m_subtreeSize;\n"
" int m_padding[3];\n"
"} b3BvhSubtreeInfo;\n"
"typedef struct\n"
"{\n"
" float4 m_childPosition;\n"
" float4 m_childOrientation;\n"
" int m_shapeIndex;\n"
" int m_unused0;\n"
" int m_unused1;\n"
" int m_unused2;\n"
"} btGpuChildShape;\n"
"typedef struct\n"
"{\n"
" float4 m_pos;\n"
" float4 m_quat;\n"
" float4 m_linVel;\n"
" float4 m_angVel;\n"
" u32 m_collidableIdx;\n"
" float m_invMass;\n"
" float m_restituitionCoeff;\n"
" float m_frictionCoeff;\n"
"} BodyData;\n"
"typedef struct \n"
"{\n"
" float4 m_localCenter;\n"
" float4 m_extents;\n"
" float4 mC;\n"
" float4 mE;\n"
" \n"
" float m_radius;\n"
" int m_faceOffset;\n"
" int m_numFaces;\n"
" int m_numVertices;\n"
" int m_vertexOffset;\n"
" int m_uniqueEdgesOffset;\n"
" int m_numUniqueEdges;\n"
" int m_unused;\n"
"} ConvexPolyhedronCL;\n"
"typedef struct \n"
"{\n"
" union\n"
" {\n"
" float4 m_min;\n"
" float m_minElems[4];\n"
" int m_minIndices[4];\n"
" };\n"
" union\n"
" {\n"
" float4 m_max;\n"
" float m_maxElems[4];\n"
" int m_maxIndices[4];\n"
" };\n"
"} btAabbCL;\n"
"#ifndef B3_AABB_H\n"
"#define B3_AABB_H\n"
"#ifndef B3_FLOAT4_H\n"
"#define B3_FLOAT4_H\n"
"#ifndef B3_PLATFORM_DEFINITIONS_H\n"
"#define B3_PLATFORM_DEFINITIONS_H\n"
"struct MyTest\n"
"{\n"
" int bla;\n"
"};\n"
"#ifdef __cplusplus\n"
"#else\n"
"//keep B3_LARGE_FLOAT*B3_LARGE_FLOAT < FLT_MAX\n"
"#define B3_LARGE_FLOAT 1e18f\n"
"#define B3_INFINITY 1e18f\n"
"#define b3Assert(a)\n"
"#define b3ConstArray(a) __global const a*\n"
"#define b3AtomicInc atomic_inc\n"
"#define b3AtomicAdd atomic_add\n"
"#define b3Fabs fabs\n"
"#define b3Sqrt native_sqrt\n"
"#define b3Sin native_sin\n"
"#define b3Cos native_cos\n"
"#define B3_STATIC\n"
"#endif\n"
"#endif\n"
"#ifdef __cplusplus\n"
"#else\n"
" typedef float4 b3Float4;\n"
" #define b3Float4ConstArg const b3Float4\n"
" #define b3MakeFloat4 (float4)\n"
" float b3Dot3F4(b3Float4ConstArg v0,b3Float4ConstArg v1)\n"
" {\n"
" float4 a1 = b3MakeFloat4(v0.xyz,0.f);\n"
" float4 b1 = b3MakeFloat4(v1.xyz,0.f);\n"
" return dot(a1, b1);\n"
" }\n"
" b3Float4 b3Cross3(b3Float4ConstArg v0,b3Float4ConstArg v1)\n"
" {\n"
" float4 a1 = b3MakeFloat4(v0.xyz,0.f);\n"
" float4 b1 = b3MakeFloat4(v1.xyz,0.f);\n"
" return cross(a1, b1);\n"
" }\n"
" #define b3MinFloat4 min\n"
" #define b3MaxFloat4 max\n"
" #define b3Normalized(a) normalize(a)\n"
"#endif \n"
" \n"
"inline bool b3IsAlmostZero(b3Float4ConstArg v)\n"
"{\n"
" if(b3Fabs(v.x)>1e-6 || b3Fabs(v.y)>1e-6 || b3Fabs(v.z)>1e-6) \n"
" return false;\n"
" return true;\n"
"}\n"
"inline int b3MaxDot( b3Float4ConstArg vec, __global const b3Float4* vecArray, int vecLen, float* dotOut )\n"
"{\n"
" float maxDot = -B3_INFINITY;\n"
" int i = 0;\n"
" int ptIndex = -1;\n"
" for( i = 0; i < vecLen; i++ )\n"
" {\n"
" float dot = b3Dot3F4(vecArray[i],vec);\n"
" \n"
" if( dot > maxDot )\n"
" {\n"
" maxDot = dot;\n"
" ptIndex = i;\n"
" }\n"
" }\n"
" b3Assert(ptIndex>=0);\n"
" if (ptIndex<0)\n"
" {\n"
" ptIndex = 0;\n"
" }\n"
" *dotOut = maxDot;\n"
" return ptIndex;\n"
"}\n"
"#endif //B3_FLOAT4_H\n"
"#ifndef B3_MAT3x3_H\n"
"#define B3_MAT3x3_H\n"
"#ifndef B3_QUAT_H\n"
"#define B3_QUAT_H\n"
"#ifndef B3_PLATFORM_DEFINITIONS_H\n"
"#ifdef __cplusplus\n"
"#else\n"
"#endif\n"
"#endif\n"
"#ifndef B3_FLOAT4_H\n"
"#ifdef __cplusplus\n"
"#else\n"
"#endif \n"
"#endif //B3_FLOAT4_H\n"
"#ifdef __cplusplus\n"
"#else\n"
" typedef float4 b3Quat;\n"
" #define b3QuatConstArg const b3Quat\n"
" \n"
" \n"
"inline float4 b3FastNormalize4(float4 v)\n"
"{\n"
" v = (float4)(v.xyz,0.f);\n"
" return fast_normalize(v);\n"
"}\n"
" \n"
"inline b3Quat b3QuatMul(b3Quat a, b3Quat b);\n"
"inline b3Quat b3QuatNormalized(b3QuatConstArg in);\n"
"inline b3Quat b3QuatRotate(b3QuatConstArg q, b3QuatConstArg vec);\n"
"inline b3Quat b3QuatInvert(b3QuatConstArg q);\n"
"inline b3Quat b3QuatInverse(b3QuatConstArg q);\n"
"inline b3Quat b3QuatMul(b3QuatConstArg a, b3QuatConstArg b)\n"
"{\n"
" b3Quat ans;\n"
" ans = b3Cross3( a, b );\n"
" ans += a.w*b+b.w*a;\n"
"// ans.w = a.w*b.w - (a.x*b.x+a.y*b.y+a.z*b.z);\n"
" ans.w = a.w*b.w - b3Dot3F4(a, b);\n"
" return ans;\n"
"}\n"
"inline b3Quat b3QuatNormalized(b3QuatConstArg in)\n"
"{\n"
" b3Quat q;\n"
" q=in;\n"
" //return b3FastNormalize4(in);\n"
" float len = native_sqrt(dot(q, q));\n"
" if(len > 0.f)\n"
" {\n"
" q *= 1.f / len;\n"
" }\n"
" else\n"
" {\n"
" q.x = q.y = q.z = 0.f;\n"
" q.w = 1.f;\n"
" }\n"
" return q;\n"
"}\n"
"inline float4 b3QuatRotate(b3QuatConstArg q, b3QuatConstArg vec)\n"
"{\n"
" b3Quat qInv = b3QuatInvert( q );\n"
" float4 vcpy = vec;\n"
" vcpy.w = 0.f;\n"
" float4 out = b3QuatMul(b3QuatMul(q,vcpy),qInv);\n"
" return out;\n"
"}\n"
"inline b3Quat b3QuatInverse(b3QuatConstArg q)\n"
"{\n"
" return (b3Quat)(-q.xyz, q.w);\n"
"}\n"
"inline b3Quat b3QuatInvert(b3QuatConstArg q)\n"
"{\n"
" return (b3Quat)(-q.xyz, q.w);\n"
"}\n"
"inline float4 b3QuatInvRotate(b3QuatConstArg q, b3QuatConstArg vec)\n"
"{\n"
" return b3QuatRotate( b3QuatInvert( q ), vec );\n"
"}\n"
"inline b3Float4 b3TransformPoint(b3Float4ConstArg point, b3Float4ConstArg translation, b3QuatConstArg orientation)\n"
"{\n"
" return b3QuatRotate( orientation, point ) + (translation);\n"
"}\n"
" \n"
"#endif \n"
"#endif //B3_QUAT_H\n"
"#ifdef __cplusplus\n"
"#else\n"
"typedef struct\n"
"{\n"
" b3Float4 m_row[3];\n"
"}b3Mat3x3;\n"
"#define b3Mat3x3ConstArg const b3Mat3x3\n"
"#define b3GetRow(m,row) (m.m_row[row])\n"
"inline b3Mat3x3 b3QuatGetRotationMatrix(b3Quat quat)\n"
"{\n"
" b3Float4 quat2 = (b3Float4)(quat.x*quat.x, quat.y*quat.y, quat.z*quat.z, 0.f);\n"
" b3Mat3x3 out;\n"
" out.m_row[0].x=1-2*quat2.y-2*quat2.z;\n"
" out.m_row[0].y=2*quat.x*quat.y-2*quat.w*quat.z;\n"
" out.m_row[0].z=2*quat.x*quat.z+2*quat.w*quat.y;\n"
" out.m_row[0].w = 0.f;\n"
" out.m_row[1].x=2*quat.x*quat.y+2*quat.w*quat.z;\n"
" out.m_row[1].y=1-2*quat2.x-2*quat2.z;\n"
" out.m_row[1].z=2*quat.y*quat.z-2*quat.w*quat.x;\n"
" out.m_row[1].w = 0.f;\n"
" out.m_row[2].x=2*quat.x*quat.z-2*quat.w*quat.y;\n"
" out.m_row[2].y=2*quat.y*quat.z+2*quat.w*quat.x;\n"
" out.m_row[2].z=1-2*quat2.x-2*quat2.y;\n"
" out.m_row[2].w = 0.f;\n"
" return out;\n"
"}\n"
"inline b3Mat3x3 b3AbsoluteMat3x3(b3Mat3x3ConstArg matIn)\n"
"{\n"
" b3Mat3x3 out;\n"
" out.m_row[0] = fabs(matIn.m_row[0]);\n"
" out.m_row[1] = fabs(matIn.m_row[1]);\n"
" out.m_row[2] = fabs(matIn.m_row[2]);\n"
" return out;\n"
"}\n"
"__inline\n"
"b3Mat3x3 mtZero();\n"
"__inline\n"
"b3Mat3x3 mtIdentity();\n"
"__inline\n"
"b3Mat3x3 mtTranspose(b3Mat3x3 m);\n"
"__inline\n"
"b3Mat3x3 mtMul(b3Mat3x3 a, b3Mat3x3 b);\n"
"__inline\n"
"b3Float4 mtMul1(b3Mat3x3 a, b3Float4 b);\n"
"__inline\n"
"b3Float4 mtMul3(b3Float4 a, b3Mat3x3 b);\n"
"__inline\n"
"b3Mat3x3 mtZero()\n"
"{\n"
" b3Mat3x3 m;\n"
" m.m_row[0] = (b3Float4)(0.f);\n"
" m.m_row[1] = (b3Float4)(0.f);\n"
" m.m_row[2] = (b3Float4)(0.f);\n"
" return m;\n"
"}\n"
"__inline\n"
"b3Mat3x3 mtIdentity()\n"
"{\n"
" b3Mat3x3 m;\n"
" m.m_row[0] = (b3Float4)(1,0,0,0);\n"
" m.m_row[1] = (b3Float4)(0,1,0,0);\n"
" m.m_row[2] = (b3Float4)(0,0,1,0);\n"
" return m;\n"
"}\n"
"__inline\n"
"b3Mat3x3 mtTranspose(b3Mat3x3 m)\n"
"{\n"
" b3Mat3x3 out;\n"
" out.m_row[0] = (b3Float4)(m.m_row[0].x, m.m_row[1].x, m.m_row[2].x, 0.f);\n"
" out.m_row[1] = (b3Float4)(m.m_row[0].y, m.m_row[1].y, m.m_row[2].y, 0.f);\n"
" out.m_row[2] = (b3Float4)(m.m_row[0].z, m.m_row[1].z, m.m_row[2].z, 0.f);\n"
" return out;\n"
"}\n"
"__inline\n"
"b3Mat3x3 mtMul(b3Mat3x3 a, b3Mat3x3 b)\n"
"{\n"
" b3Mat3x3 transB;\n"
" transB = mtTranspose( b );\n"
" b3Mat3x3 ans;\n"
" // why this doesn't run when 0ing in the for{}\n"
" a.m_row[0].w = 0.f;\n"
" a.m_row[1].w = 0.f;\n"
" a.m_row[2].w = 0.f;\n"
" for(int i=0; i<3; i++)\n"
" {\n"
"// a.m_row[i].w = 0.f;\n"
" ans.m_row[i].x = b3Dot3F4(a.m_row[i],transB.m_row[0]);\n"
" ans.m_row[i].y = b3Dot3F4(a.m_row[i],transB.m_row[1]);\n"
" ans.m_row[i].z = b3Dot3F4(a.m_row[i],transB.m_row[2]);\n"
" ans.m_row[i].w = 0.f;\n"
" }\n"
" return ans;\n"
"}\n"
"__inline\n"
"b3Float4 mtMul1(b3Mat3x3 a, b3Float4 b)\n"
"{\n"
" b3Float4 ans;\n"
" ans.x = b3Dot3F4( a.m_row[0], b );\n"
" ans.y = b3Dot3F4( a.m_row[1], b );\n"
" ans.z = b3Dot3F4( a.m_row[2], b );\n"
" ans.w = 0.f;\n"
" return ans;\n"
"}\n"
"__inline\n"
"b3Float4 mtMul3(b3Float4 a, b3Mat3x3 b)\n"
"{\n"
" b3Float4 colx = b3MakeFloat4(b.m_row[0].x, b.m_row[1].x, b.m_row[2].x, 0);\n"
" b3Float4 coly = b3MakeFloat4(b.m_row[0].y, b.m_row[1].y, b.m_row[2].y, 0);\n"
" b3Float4 colz = b3MakeFloat4(b.m_row[0].z, b.m_row[1].z, b.m_row[2].z, 0);\n"
" b3Float4 ans;\n"
" ans.x = b3Dot3F4( a, colx );\n"
" ans.y = b3Dot3F4( a, coly );\n"
" ans.z = b3Dot3F4( a, colz );\n"
" return ans;\n"
"}\n"
"#endif\n"
"#endif //B3_MAT3x3_H\n"
"typedef struct b3Aabb b3Aabb_t;\n"
"struct b3Aabb\n"
"{\n"
" union\n"
" {\n"
" float m_min[4];\n"
" b3Float4 m_minVec;\n"
" int m_minIndices[4];\n"
" };\n"
" union\n"
" {\n"
" float m_max[4];\n"
" b3Float4 m_maxVec;\n"
" int m_signedMaxIndices[4];\n"
" };\n"
"};\n"
"inline void b3TransformAabb2(b3Float4ConstArg localAabbMin,b3Float4ConstArg localAabbMax, float margin,\n"
" b3Float4ConstArg pos,\n"
" b3QuatConstArg orn,\n"
" b3Float4* aabbMinOut,b3Float4* aabbMaxOut)\n"
"{\n"
" b3Float4 localHalfExtents = 0.5f*(localAabbMax-localAabbMin);\n"
" localHalfExtents+=b3MakeFloat4(margin,margin,margin,0.f);\n"
" b3Float4 localCenter = 0.5f*(localAabbMax+localAabbMin);\n"
" b3Mat3x3 m;\n"
" m = b3QuatGetRotationMatrix(orn);\n"
" b3Mat3x3 abs_b = b3AbsoluteMat3x3(m);\n"
" b3Float4 center = b3TransformPoint(localCenter,pos,orn);\n"
" \n"
" b3Float4 extent = b3MakeFloat4(b3Dot3F4(localHalfExtents,b3GetRow(abs_b,0)),\n"
" b3Dot3F4(localHalfExtents,b3GetRow(abs_b,1)),\n"
" b3Dot3F4(localHalfExtents,b3GetRow(abs_b,2)),\n"
" 0.f);\n"
" *aabbMinOut = center-extent;\n"
" *aabbMaxOut = center+extent;\n"
"}\n"
"/// conservative test for overlap between two aabbs\n"
"inline bool b3TestAabbAgainstAabb(b3Float4ConstArg aabbMin1,b3Float4ConstArg aabbMax1,\n"
" b3Float4ConstArg aabbMin2, b3Float4ConstArg aabbMax2)\n"
"{\n"
" bool overlap = true;\n"
" overlap = (aabbMin1.x > aabbMax2.x || aabbMax1.x < aabbMin2.x) ? false : overlap;\n"
" overlap = (aabbMin1.z > aabbMax2.z || aabbMax1.z < aabbMin2.z) ? false : overlap;\n"
" overlap = (aabbMin1.y > aabbMax2.y || aabbMax1.y < aabbMin2.y) ? false : overlap;\n"
" return overlap;\n"
"}\n"
"#endif //B3_AABB_H\n"
"/*\n"
"Bullet Continuous Collision Detection and Physics Library\n"
"Copyright (c) 2003-2013 Erwin Coumans http://bulletphysics.org\n"
"This software is provided 'as-is', without any express or implied warranty.\n"
"In no event will the authors be held liable for any damages arising from the use of this software.\n"
"Permission is granted to anyone to use this software for any purpose,\n"
"including commercial applications, and to alter it and redistribute it freely,\n"
"subject to the following restrictions:\n"
"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.\n"
"2. Altered source versions must be plainly marked as such, and must not be misrepresented as being the original software.\n"
"3. This notice may not be removed or altered from any source distribution.\n"
"*/\n"
"#ifndef B3_INT2_H\n"
"#define B3_INT2_H\n"
"#ifdef __cplusplus\n"
"#else\n"
"#define b3UnsignedInt2 uint2\n"
"#define b3Int2 int2\n"
"#define b3MakeInt2 (int2)\n"
"#endif //__cplusplus\n"
"#endif\n"
"typedef struct\n"
"{\n"
" float4 m_plane;\n"
" int m_indexOffset;\n"
" int m_numIndices;\n"
"} btGpuFace;\n"
"#define make_float4 (float4)\n"
"__inline\n"
"float4 cross3(float4 a, float4 b)\n"
"{\n"
" return cross(a,b);\n"
" \n"
"// float4 a1 = make_float4(a.xyz,0.f);\n"
"// float4 b1 = make_float4(b.xyz,0.f);\n"
"// return cross(a1,b1);\n"
"//float4 c = make_float4(a.y*b.z - a.z*b.y,a.z*b.x - a.x*b.z,a.x*b.y - a.y*b.x,0.f);\n"
" \n"
" // float4 c = make_float4(a.y*b.z - a.z*b.y,1.f,a.x*b.y - a.y*b.x,0.f);\n"
" \n"
" //return c;\n"
"}\n"
"__inline\n"
"float dot3F4(float4 a, float4 b)\n"
"{\n"
" float4 a1 = make_float4(a.xyz,0.f);\n"
" float4 b1 = make_float4(b.xyz,0.f);\n"
" return dot(a1, b1);\n"
"}\n"
"__inline\n"
"float4 fastNormalize4(float4 v)\n"
"{\n"
" v = make_float4(v.xyz,0.f);\n"
" return fast_normalize(v);\n"
"}\n"
"///////////////////////////////////////\n"
"// Quaternion\n"
"///////////////////////////////////////\n"
"typedef float4 Quaternion;\n"
"__inline\n"
"Quaternion qtMul(Quaternion a, Quaternion b);\n"
"__inline\n"
"Quaternion qtNormalize(Quaternion in);\n"
"__inline\n"
"float4 qtRotate(Quaternion q, float4 vec);\n"
"__inline\n"
"Quaternion qtInvert(Quaternion q);\n"
"__inline\n"
"Quaternion qtMul(Quaternion a, Quaternion b)\n"
"{\n"
" Quaternion ans;\n"
" ans = cross3( a, b );\n"
" ans += a.w*b+b.w*a;\n"
"// ans.w = a.w*b.w - (a.x*b.x+a.y*b.y+a.z*b.z);\n"
" ans.w = a.w*b.w - dot3F4(a, b);\n"
" return ans;\n"
"}\n"
"__inline\n"
"Quaternion qtNormalize(Quaternion in)\n"
"{\n"
" return fastNormalize4(in);\n"
"// in /= length( in );\n"
"// return in;\n"
"}\n"
"__inline\n"
"float4 qtRotate(Quaternion q, float4 vec)\n"
"{\n"
" Quaternion qInv = qtInvert( q );\n"
" float4 vcpy = vec;\n"
" vcpy.w = 0.f;\n"
" float4 out = qtMul(qtMul(q,vcpy),qInv);\n"
" return out;\n"
"}\n"
"__inline\n"
"Quaternion qtInvert(Quaternion q)\n"
"{\n"
" return (Quaternion)(-q.xyz, q.w);\n"
"}\n"
"__inline\n"
"float4 qtInvRotate(const Quaternion q, float4 vec)\n"
"{\n"
" return qtRotate( qtInvert( q ), vec );\n"
"}\n"
"__inline\n"
"float4 transform(const float4* p, const float4* translation, const Quaternion* orientation)\n"
"{\n"
" return qtRotate( *orientation, *p ) + (*translation);\n"
"}\n"
"__inline\n"
"float4 normalize3(const float4 a)\n"
"{\n"
" float4 n = make_float4(a.x, a.y, a.z, 0.f);\n"
" return fastNormalize4( n );\n"
"}\n"
"inline void projectLocal(const ConvexPolyhedronCL* hull, const float4 pos, const float4 orn, \n"
"const float4* dir, const float4* vertices, float* min, float* max)\n"
"{\n"
" min[0] = FLT_MAX;\n"
" max[0] = -FLT_MAX;\n"
" int numVerts = hull->m_numVertices;\n"
" const float4 localDir = qtInvRotate(orn,*dir);\n"
" float offset = dot(pos,*dir);\n"
" for(int i=0;i<numVerts;i++)\n"
" {\n"
" float dp = dot(vertices[hull->m_vertexOffset+i],localDir);\n"
" if(dp < min[0]) \n"
" min[0] = dp;\n"
" if(dp > max[0]) \n"
" max[0] = dp;\n"
" }\n"
" if(min[0]>max[0])\n"
" {\n"
" float tmp = min[0];\n"
" min[0] = max[0];\n"
" max[0] = tmp;\n"
" }\n"
" min[0] += offset;\n"
" max[0] += offset;\n"
"}\n"
"inline void project(__global const ConvexPolyhedronCL* hull, const float4 pos, const float4 orn, \n"
"const float4* dir, __global const float4* vertices, float* min, float* max)\n"
"{\n"
" min[0] = FLT_MAX;\n"
" max[0] = -FLT_MAX;\n"
" int numVerts = hull->m_numVertices;\n"
" const float4 localDir = qtInvRotate(orn,*dir);\n"
" float offset = dot(pos,*dir);\n"
" for(int i=0;i<numVerts;i++)\n"
" {\n"
" float dp = dot(vertices[hull->m_vertexOffset+i],localDir);\n"
" if(dp < min[0]) \n"
" min[0] = dp;\n"
" if(dp > max[0]) \n"
" max[0] = dp;\n"
" }\n"
" if(min[0]>max[0])\n"
" {\n"
" float tmp = min[0];\n"
" min[0] = max[0];\n"
" max[0] = tmp;\n"
" }\n"
" min[0] += offset;\n"
" max[0] += offset;\n"
"}\n"
"inline bool TestSepAxisLocalA(const ConvexPolyhedronCL* hullA, __global const ConvexPolyhedronCL* hullB, \n"
" const float4 posA,const float4 ornA,\n"
" const float4 posB,const float4 ornB,\n"
" float4* sep_axis, const float4* verticesA, __global const float4* verticesB,float* depth)\n"
"{\n"
" float Min0,Max0;\n"
" float Min1,Max1;\n"
" projectLocal(hullA,posA,ornA,sep_axis,verticesA, &Min0, &Max0);\n"
" project(hullB,posB,ornB, sep_axis,verticesB, &Min1, &Max1);\n"
" if(Max0<Min1 || Max1<Min0)\n"
" return false;\n"
" float d0 = Max0 - Min1;\n"
" float d1 = Max1 - Min0;\n"
" *depth = d0<d1 ? d0:d1;\n"
" return true;\n"
"}\n"
"inline bool IsAlmostZero(const float4 v)\n"
"{\n"
" if(fabs(v.x)>1e-6f || fabs(v.y)>1e-6f || fabs(v.z)>1e-6f)\n"
" return false;\n"
" return true;\n"
"}\n"
"bool findSeparatingAxisLocalA( const ConvexPolyhedronCL* hullA, __global const ConvexPolyhedronCL* hullB, \n"
" const float4 posA1,\n"
" const float4 ornA,\n"
" const float4 posB1,\n"
" const float4 ornB,\n"
" const float4 DeltaC2,\n"
" \n"
" const float4* verticesA, \n"
" const float4* uniqueEdgesA, \n"
" const btGpuFace* facesA,\n"
" const int* indicesA,\n"
" __global const float4* verticesB, \n"
" __global const float4* uniqueEdgesB, \n"
" __global const btGpuFace* facesB,\n"
" __global const int* indicesB,\n"
" float4* sep,\n"
" float* dmin)\n"
"{\n"
" \n"
" float4 posA = posA1;\n"
" posA.w = 0.f;\n"
" float4 posB = posB1;\n"
" posB.w = 0.f;\n"
" int curPlaneTests=0;\n"
" {\n"
" int numFacesA = hullA->m_numFaces;\n"
" // Test normals from hullA\n"
" for(int i=0;i<numFacesA;i++)\n"
" {\n"
" const float4 normal = facesA[hullA->m_faceOffset+i].m_plane;\n"
" float4 faceANormalWS = qtRotate(ornA,normal);\n"
" if (dot3F4(DeltaC2,faceANormalWS)<0)\n"
" faceANormalWS*=-1.f;\n"
" curPlaneTests++;\n"
" float d;\n"
" if(!TestSepAxisLocalA( hullA, hullB, posA,ornA,posB,ornB,&faceANormalWS, verticesA, verticesB,&d))\n"
" return false;\n"
" if(d<*dmin)\n"
" {\n"
" *dmin = d;\n"
" *sep = faceANormalWS;\n"
" }\n"
" }\n"
" }\n"
" if((dot3F4(-DeltaC2,*sep))>0.0f)\n"
" {\n"
" *sep = -(*sep);\n"
" }\n"
" return true;\n"
"}\n"
"bool findSeparatingAxisLocalB( __global const ConvexPolyhedronCL* hullA, const ConvexPolyhedronCL* hullB, \n"
" const float4 posA1,\n"
" const float4 ornA,\n"
" const float4 posB1,\n"
" const float4 ornB,\n"
" const float4 DeltaC2,\n"
" __global const float4* verticesA, \n"
" __global const float4* uniqueEdgesA, \n"
" __global const btGpuFace* facesA,\n"
" __global const int* indicesA,\n"
" const float4* verticesB,\n"
" const float4* uniqueEdgesB, \n"
" const btGpuFace* facesB,\n"
" const int* indicesB,\n"
" float4* sep,\n"
" float* dmin)\n"
"{\n"
" float4 posA = posA1;\n"
" posA.w = 0.f;\n"
" float4 posB = posB1;\n"
" posB.w = 0.f;\n"
" int curPlaneTests=0;\n"
" {\n"
" int numFacesA = hullA->m_numFaces;\n"
" // Test normals from hullA\n"
" for(int i=0;i<numFacesA;i++)\n"
" {\n"
" const float4 normal = facesA[hullA->m_faceOffset+i].m_plane;\n"
" float4 faceANormalWS = qtRotate(ornA,normal);\n"
" if (dot3F4(DeltaC2,faceANormalWS)<0)\n"
" faceANormalWS *= -1.f;\n"
" curPlaneTests++;\n"
" float d;\n"
" if(!TestSepAxisLocalA( hullB, hullA, posB,ornB,posA,ornA, &faceANormalWS, verticesB,verticesA, &d))\n"
" return false;\n"
" if(d<*dmin)\n"
" {\n"
" *dmin = d;\n"
" *sep = faceANormalWS;\n"
" }\n"
" }\n"
" }\n"
" if((dot3F4(-DeltaC2,*sep))>0.0f)\n"
" {\n"
" *sep = -(*sep);\n"
" }\n"
" return true;\n"
"}\n"
"bool findSeparatingAxisEdgeEdgeLocalA( const ConvexPolyhedronCL* hullA, __global const ConvexPolyhedronCL* hullB, \n"
" const float4 posA1,\n"
" const float4 ornA,\n"
" const float4 posB1,\n"
" const float4 ornB,\n"
" const float4 DeltaC2,\n"
" const float4* verticesA, \n"
" const float4* uniqueEdgesA, \n"
" const btGpuFace* facesA,\n"
" const int* indicesA,\n"
" __global const float4* verticesB, \n"
" __global const float4* uniqueEdgesB, \n"
" __global const btGpuFace* facesB,\n"
" __global const int* indicesB,\n"
" float4* sep,\n"
" float* dmin)\n"
"{\n"
" float4 posA = posA1;\n"
" posA.w = 0.f;\n"
" float4 posB = posB1;\n"
" posB.w = 0.f;\n"
" int curPlaneTests=0;\n"
" int curEdgeEdge = 0;\n"
" // Test edges\n"
" for(int e0=0;e0<hullA->m_numUniqueEdges;e0++)\n"
" {\n"
" const float4 edge0 = uniqueEdgesA[hullA->m_uniqueEdgesOffset+e0];\n"
" float4 edge0World = qtRotate(ornA,edge0);\n"
" for(int e1=0;e1<hullB->m_numUniqueEdges;e1++)\n"
" {\n"
" const float4 edge1 = uniqueEdgesB[hullB->m_uniqueEdgesOffset+e1];\n"
" float4 edge1World = qtRotate(ornB,edge1);\n"
" float4 crossje = cross3(edge0World,edge1World);\n"
" curEdgeEdge++;\n"
" if(!IsAlmostZero(crossje))\n"
" {\n"
" crossje = normalize3(crossje);\n"
" if (dot3F4(DeltaC2,crossje)<0)\n"
" crossje *= -1.f;\n"
" float dist;\n"
" bool result = true;\n"
" {\n"
" float Min0,Max0;\n"
" float Min1,Max1;\n"
" projectLocal(hullA,posA,ornA,&crossje,verticesA, &Min0, &Max0);\n"
" project(hullB,posB,ornB,&crossje,verticesB, &Min1, &Max1);\n"
" \n"
" if(Max0<Min1 || Max1<Min0)\n"
" result = false;\n"
" \n"
" float d0 = Max0 - Min1;\n"
" float d1 = Max1 - Min0;\n"
" dist = d0<d1 ? d0:d1;\n"
" result = true;\n"
" }\n"
" \n"
" if(dist<*dmin)\n"
" {\n"
" *dmin = dist;\n"
" *sep = crossje;\n"
" }\n"
" }\n"
" }\n"
" }\n"
" \n"
" if((dot3F4(-DeltaC2,*sep))>0.0f)\n"
" {\n"
" *sep = -(*sep);\n"
" }\n"
" return true;\n"
"}\n"
"inline int findClippingFaces(const float4 separatingNormal,\n"
" const ConvexPolyhedronCL* hullA, \n"
" __global const ConvexPolyhedronCL* hullB,\n"
" const float4 posA, const Quaternion ornA,const float4 posB, const Quaternion ornB,\n"
" __global float4* worldVertsA1,\n"
" __global float4* worldNormalsA1,\n"
" __global float4* worldVertsB1,\n"
" int capacityWorldVerts,\n"
" const float minDist, float maxDist,\n"
" const float4* verticesA,\n"
" const btGpuFace* facesA,\n"
" const int* indicesA,\n"
" __global const float4* verticesB,\n"
" __global const btGpuFace* facesB,\n"
" __global const int* indicesB,\n"
" __global int4* clippingFaces, int pairIndex)\n"
"{\n"
" int numContactsOut = 0;\n"
" int numWorldVertsB1= 0;\n"
" \n"
" \n"
" int closestFaceB=0;\n"
" float dmax = -FLT_MAX;\n"
" \n"
" {\n"
" for(int face=0;face<hullB->m_numFaces;face++)\n"
" {\n"
" const float4 Normal = make_float4(facesB[hullB->m_faceOffset+face].m_plane.x,\n"
" facesB[hullB->m_faceOffset+face].m_plane.y, facesB[hullB->m_faceOffset+face].m_plane.z,0.f);\n"
" const float4 WorldNormal = qtRotate(ornB, Normal);\n"
" float d = dot3F4(WorldNormal,separatingNormal);\n"
" if (d > dmax)\n"
" {\n"
" dmax = d;\n"
" closestFaceB = face;\n"
" }\n"
" }\n"
" }\n"
" \n"
" {\n"
" const btGpuFace polyB = facesB[hullB->m_faceOffset+closestFaceB];\n"
" int numVertices = polyB.m_numIndices;\n"
" if (numVertices>capacityWorldVerts)\n"
" numVertices = capacityWorldVerts;\n"
" if (numVertices<0)\n"
" numVertices = 0;\n"
" \n"
" for(int e0=0;e0<numVertices;e0++)\n"
" {\n"
" if (e0<capacityWorldVerts)\n"
" {\n"
" const float4 b = verticesB[hullB->m_vertexOffset+indicesB[polyB.m_indexOffset+e0]];\n"
" worldVertsB1[pairIndex*capacityWorldVerts+numWorldVertsB1++] = transform(&b,&posB,&ornB);\n"
" }\n"
" }\n"
" }\n"
" \n"
" int closestFaceA=0;\n"
" {\n"
" float dmin = FLT_MAX;\n"
" for(int face=0;face<hullA->m_numFaces;face++)\n"
" {\n"
" const float4 Normal = make_float4(\n"
" facesA[hullA->m_faceOffset+face].m_plane.x,\n"
" facesA[hullA->m_faceOffset+face].m_plane.y,\n"
" facesA[hullA->m_faceOffset+face].m_plane.z,\n"
" 0.f);\n"
" const float4 faceANormalWS = qtRotate(ornA,Normal);\n"
" \n"
" float d = dot3F4(faceANormalWS,separatingNormal);\n"
" if (d < dmin)\n"
" {\n"
" dmin = d;\n"
" closestFaceA = face;\n"
" worldNormalsA1[pairIndex] = faceANormalWS;\n"
" }\n"
" }\n"
" }\n"
" \n"
" int numVerticesA = facesA[hullA->m_faceOffset+closestFaceA].m_numIndices;\n"
" if (numVerticesA>capacityWorldVerts)\n"
" numVerticesA = capacityWorldVerts;\n"
" if (numVerticesA<0)\n"
" numVerticesA=0;\n"
" \n"
" for(int e0=0;e0<numVerticesA;e0++)\n"
" {\n"
" if (e0<capacityWorldVerts)\n"
" {\n"
" const float4 a = verticesA[hullA->m_vertexOffset+indicesA[facesA[hullA->m_faceOffset+closestFaceA].m_indexOffset+e0]];\n"
" worldVertsA1[pairIndex*capacityWorldVerts+e0] = transform(&a, &posA,&ornA);\n"
" }\n"
" }\n"
" \n"
" clippingFaces[pairIndex].x = closestFaceA;\n"
" clippingFaces[pairIndex].y = closestFaceB;\n"
" clippingFaces[pairIndex].z = numVerticesA;\n"
" clippingFaces[pairIndex].w = numWorldVertsB1;\n"
" \n"
" \n"
" return numContactsOut;\n"
"}\n"
"// work-in-progress\n"
"__kernel void findConcaveSeparatingAxisVertexFaceKernel( __global int4* concavePairs,\n"
" __global const BodyData* rigidBodies,\n"
" __global const btCollidableGpu* collidables,\n"
" __global const ConvexPolyhedronCL* convexShapes,\n"
" __global const float4* vertices,\n"
" __global const float4* uniqueEdges,\n"
" __global const btGpuFace* faces,\n"
" __global const int* indices,\n"
" __global const btGpuChildShape* gpuChildShapes,\n"
" __global btAabbCL* aabbs,\n"
" __global float4* concaveSeparatingNormalsOut,\n"
" __global int* concaveHasSeparatingNormals,\n"
" __global int4* clippingFacesOut,\n"
" __global float4* worldVertsA1GPU,\n"
" __global float4* worldNormalsAGPU,\n"
" __global float4* worldVertsB1GPU,\n"
" __global float* dmins,\n"
" int vertexFaceCapacity,\n"
" int numConcavePairs\n"
" )\n"
"{\n"
" \n"
" int i = get_global_id(0);\n"
" if (i>=numConcavePairs)\n"
" return;\n"
" \n"
" concaveHasSeparatingNormals[i] = 0;\n"
" \n"
" int pairIdx = i;\n"
" \n"
" int bodyIndexA = concavePairs[i].x;\n"
" int bodyIndexB = concavePairs[i].y;\n"
" \n"
" int collidableIndexA = rigidBodies[bodyIndexA].m_collidableIdx;\n"
" int collidableIndexB = rigidBodies[bodyIndexB].m_collidableIdx;\n"
" \n"
" int shapeIndexA = collidables[collidableIndexA].m_shapeIndex;\n"
" int shapeIndexB = collidables[collidableIndexB].m_shapeIndex;\n"
" \n"
" if (collidables[collidableIndexB].m_shapeType!=SHAPE_CONVEX_HULL&&\n"
" collidables[collidableIndexB].m_shapeType!=SHAPE_COMPOUND_OF_CONVEX_HULLS)\n"
" {\n"
" concavePairs[pairIdx].w = -1;\n"
" return;\n"
" }\n"
" \n"
" \n"
" \n"
" int numFacesA = convexShapes[shapeIndexA].m_numFaces;\n"
" int numActualConcaveConvexTests = 0;\n"
" \n"
" int f = concavePairs[i].z;\n"
" \n"
" bool overlap = false;\n"
" \n"
" ConvexPolyhedronCL convexPolyhedronA;\n"
" \n"
" //add 3 vertices of the triangle\n"
" convexPolyhedronA.m_numVertices = 3;\n"
" convexPolyhedronA.m_vertexOffset = 0;\n"
" float4 localCenter = make_float4(0.f,0.f,0.f,0.f);\n"
" \n"
" btGpuFace face = faces[convexShapes[shapeIndexA].m_faceOffset+f];\n"
" float4 triMinAabb, triMaxAabb;\n"
" btAabbCL triAabb;\n"
" triAabb.m_min = make_float4(1e30f,1e30f,1e30f,0.f);\n"
" triAabb.m_max = make_float4(-1e30f,-1e30f,-1e30f,0.f);\n"
" \n"
" float4 verticesA[3];\n"
" for (int i=0;i<3;i++)\n"
" {\n"
" int index = indices[face.m_indexOffset+i];\n"
" float4 vert = vertices[convexShapes[shapeIndexA].m_vertexOffset+index];\n"
" verticesA[i] = vert;\n"
" localCenter += vert;\n"
" \n"
" triAabb.m_min = min(triAabb.m_min,vert);\n"
" triAabb.m_max = max(triAabb.m_max,vert);\n"
" \n"
" }\n"
" \n"
" overlap = true;\n"
" overlap = (triAabb.m_min.x > aabbs[bodyIndexB].m_max.x || triAabb.m_max.x < aabbs[bodyIndexB].m_min.x) ? false : overlap;\n"
" overlap = (triAabb.m_min.z > aabbs[bodyIndexB].m_max.z || triAabb.m_max.z < aabbs[bodyIndexB].m_min.z) ? false : overlap;\n"
" overlap = (triAabb.m_min.y > aabbs[bodyIndexB].m_max.y || triAabb.m_max.y < aabbs[bodyIndexB].m_min.y) ? false : overlap;\n"
" \n"
" if (overlap)\n"
" {\n"
" float dmin = FLT_MAX;\n"
" int hasSeparatingAxis=5;\n"
" float4 sepAxis=make_float4(1,2,3,4);\n"
" \n"
" int localCC=0;\n"
" numActualConcaveConvexTests++;\n"
" \n"
" //a triangle has 3 unique edges\n"
" convexPolyhedronA.m_numUniqueEdges = 3;\n"
" convexPolyhedronA.m_uniqueEdgesOffset = 0;\n"
" float4 uniqueEdgesA[3];\n"
" \n"
" uniqueEdgesA[0] = (verticesA[1]-verticesA[0]);\n"
" uniqueEdgesA[1] = (verticesA[2]-verticesA[1]);\n"
" uniqueEdgesA[2] = (verticesA[0]-verticesA[2]);\n"
" \n"
" \n"
" convexPolyhedronA.m_faceOffset = 0;\n"
" \n"
" float4 normal = make_float4(face.m_plane.x,face.m_plane.y,face.m_plane.z,0.f);\n"
" \n"
" btGpuFace facesA[TRIANGLE_NUM_CONVEX_FACES];\n"
" int indicesA[3+3+2+2+2];\n"
" int curUsedIndices=0;\n"
" int fidx=0;\n"
" \n"
" //front size of triangle\n"
" {\n"
" facesA[fidx].m_indexOffset=curUsedIndices;\n"
" indicesA[0] = 0;\n"
" indicesA[1] = 1;\n"
" indicesA[2] = 2;\n"
" curUsedIndices+=3;\n"
" float c = face.m_plane.w;\n"
" facesA[fidx].m_plane.x = normal.x;\n"
" facesA[fidx].m_plane.y = normal.y;\n"
" facesA[fidx].m_plane.z = normal.z;\n"
" facesA[fidx].m_plane.w = c;\n"
" facesA[fidx].m_numIndices=3;\n"
" }\n"
" fidx++;\n"
" //back size of triangle\n"
" {\n"
" facesA[fidx].m_indexOffset=curUsedIndices;\n"
" indicesA[3]=2;\n"
" indicesA[4]=1;\n"
" indicesA[5]=0;\n"
" curUsedIndices+=3;\n"
" float c = dot(normal,verticesA[0]);\n"
" float c1 = -face.m_plane.w;\n"
" facesA[fidx].m_plane.x = -normal.x;\n"
" facesA[fidx].m_plane.y = -normal.y;\n"
" facesA[fidx].m_plane.z = -normal.z;\n"
" facesA[fidx].m_plane.w = c;\n"
" facesA[fidx].m_numIndices=3;\n"
" }\n"
" fidx++;\n"
" \n"
" bool addEdgePlanes = true;\n"
" if (addEdgePlanes)\n"
" {\n"
" int numVertices=3;\n"
" int prevVertex = numVertices-1;\n"
" for (int i=0;i<numVertices;i++)\n"
" {\n"
" float4 v0 = verticesA[i];\n"
" float4 v1 = verticesA[prevVertex];\n"
" \n"
" float4 edgeNormal = normalize(cross(normal,v1-v0));\n"
" float c = -dot(edgeNormal,v0);\n"
" \n"
" facesA[fidx].m_numIndices = 2;\n"
" facesA[fidx].m_indexOffset=curUsedIndices;\n"
" indicesA[curUsedIndices++]=i;\n"
" indicesA[curUsedIndices++]=prevVertex;\n"
" \n"
" facesA[fidx].m_plane.x = edgeNormal.x;\n"
" facesA[fidx].m_plane.y = edgeNormal.y;\n"
" facesA[fidx].m_plane.z = edgeNormal.z;\n"
" facesA[fidx].m_plane.w = c;\n"
" fidx++;\n"
" prevVertex = i;\n"
" }\n"
" }\n"
" convexPolyhedronA.m_numFaces = TRIANGLE_NUM_CONVEX_FACES;\n"
" convexPolyhedronA.m_localCenter = localCenter*(1.f/3.f);\n"
" \n"
" \n"
" float4 posA = rigidBodies[bodyIndexA].m_pos;\n"
" posA.w = 0.f;\n"
" float4 posB = rigidBodies[bodyIndexB].m_pos;\n"
" posB.w = 0.f;\n"
" \n"
" float4 ornA = rigidBodies[bodyIndexA].m_quat;\n"
" float4 ornB =rigidBodies[bodyIndexB].m_quat;\n"
" \n"
" \n"
" \n"
" \n"
" ///////////////////\n"
" ///compound shape support\n"
" \n"
" if (collidables[collidableIndexB].m_shapeType==SHAPE_COMPOUND_OF_CONVEX_HULLS)\n"
" {\n"
" int compoundChild = concavePairs[pairIdx].w;\n"
" int childShapeIndexB = compoundChild;//collidables[collidableIndexB].m_shapeIndex+compoundChild;\n"
" int childColIndexB = gpuChildShapes[childShapeIndexB].m_shapeIndex;\n"
" float4 childPosB = gpuChildShapes[childShapeIndexB].m_childPosition;\n"
" float4 childOrnB = gpuChildShapes[childShapeIndexB].m_childOrientation;\n"
" float4 newPosB = transform(&childPosB,&posB,&ornB);\n"
" float4 newOrnB = qtMul(ornB,childOrnB);\n"
" posB = newPosB;\n"
" ornB = newOrnB;\n"
" shapeIndexB = collidables[childColIndexB].m_shapeIndex;\n"
" }\n"
" //////////////////\n"
" \n"
" float4 c0local = convexPolyhedronA.m_localCenter;\n"
" float4 c0 = transform(&c0local, &posA, &ornA);\n"
" float4 c1local = convexShapes[shapeIndexB].m_localCenter;\n"
" float4 c1 = transform(&c1local,&posB,&ornB);\n"
" const float4 DeltaC2 = c0 - c1;\n"
" \n"
" \n"
" bool sepA = findSeparatingAxisLocalA( &convexPolyhedronA, &convexShapes[shapeIndexB],\n"
" posA,ornA,\n"
" posB,ornB,\n"
" DeltaC2,\n"
" verticesA,uniqueEdgesA,facesA,indicesA,\n"
" vertices,uniqueEdges,faces,indices,\n"
" &sepAxis,&dmin);\n"
" hasSeparatingAxis = 4;\n"
" if (!sepA)\n"
" {\n"
" hasSeparatingAxis = 0;\n"
" } else\n"
" {\n"
" bool sepB = findSeparatingAxisLocalB( &convexShapes[shapeIndexB],&convexPolyhedronA,\n"
" posB,ornB,\n"
" posA,ornA,\n"
" DeltaC2,\n"
" vertices,uniqueEdges,faces,indices,\n"
" verticesA,uniqueEdgesA,facesA,indicesA,\n"
" &sepAxis,&dmin);\n"
" \n"
" if (!sepB)\n"
" {\n"
" hasSeparatingAxis = 0;\n"
" } else\n"
" {\n"
" hasSeparatingAxis = 1;\n"
" }\n"
" } \n"
" \n"
" if (hasSeparatingAxis)\n"
" {\n"
" dmins[i] = dmin;\n"
" concaveSeparatingNormalsOut[pairIdx]=sepAxis;\n"
" concaveHasSeparatingNormals[i]=1;\n"
" \n"
" } else\n"
" { \n"
" //mark this pair as in-active\n"
" concavePairs[pairIdx].w = -1;\n"
" }\n"
" }\n"
" else\n"
" { \n"
" //mark this pair as in-active\n"
" concavePairs[pairIdx].w = -1;\n"
" }\n"
"}\n"
"// work-in-progress\n"
"__kernel void findConcaveSeparatingAxisEdgeEdgeKernel( __global int4* concavePairs,\n"
" __global const BodyData* rigidBodies,\n"
" __global const btCollidableGpu* collidables,\n"
" __global const ConvexPolyhedronCL* convexShapes,\n"
" __global const float4* vertices,\n"
" __global const float4* uniqueEdges,\n"
" __global const btGpuFace* faces,\n"
" __global const int* indices,\n"
" __global const btGpuChildShape* gpuChildShapes,\n"
" __global btAabbCL* aabbs,\n"
" __global float4* concaveSeparatingNormalsOut,\n"
" __global int* concaveHasSeparatingNormals,\n"
" __global int4* clippingFacesOut,\n"
" __global float4* worldVertsA1GPU,\n"
" __global float4* worldNormalsAGPU,\n"
" __global float4* worldVertsB1GPU,\n"
" __global float* dmins,\n"
" int vertexFaceCapacity,\n"
" int numConcavePairs\n"
" )\n"
"{\n"
" \n"
" int i = get_global_id(0);\n"
" if (i>=numConcavePairs)\n"
" return;\n"
" \n"
" if (!concaveHasSeparatingNormals[i])\n"
" return;\n"
" \n"
" int pairIdx = i;\n"
" \n"
" int bodyIndexA = concavePairs[i].x;\n"
" int bodyIndexB = concavePairs[i].y;\n"
" \n"
" int collidableIndexA = rigidBodies[bodyIndexA].m_collidableIdx;\n"
" int collidableIndexB = rigidBodies[bodyIndexB].m_collidableIdx;\n"
" \n"
" int shapeIndexA = collidables[collidableIndexA].m_shapeIndex;\n"
" int shapeIndexB = collidables[collidableIndexB].m_shapeIndex;\n"
" \n"
" \n"
" int numFacesA = convexShapes[shapeIndexA].m_numFaces;\n"
" int numActualConcaveConvexTests = 0;\n"
" \n"
" int f = concavePairs[i].z;\n"
" \n"
" bool overlap = false;\n"
" \n"
" ConvexPolyhedronCL convexPolyhedronA;\n"
" \n"
" //add 3 vertices of the triangle\n"
" convexPolyhedronA.m_numVertices = 3;\n"
" convexPolyhedronA.m_vertexOffset = 0;\n"
" float4 localCenter = make_float4(0.f,0.f,0.f,0.f);\n"
" \n"
" btGpuFace face = faces[convexShapes[shapeIndexA].m_faceOffset+f];\n"
" float4 triMinAabb, triMaxAabb;\n"
" btAabbCL triAabb;\n"
" triAabb.m_min = make_float4(1e30f,1e30f,1e30f,0.f);\n"
" triAabb.m_max = make_float4(-1e30f,-1e30f,-1e30f,0.f);\n"
" \n"
" float4 verticesA[3];\n"
" for (int i=0;i<3;i++)\n"
" {\n"
" int index = indices[face.m_indexOffset+i];\n"
" float4 vert = vertices[convexShapes[shapeIndexA].m_vertexOffset+index];\n"
" verticesA[i] = vert;\n"
" localCenter += vert;\n"
" \n"
" triAabb.m_min = min(triAabb.m_min,vert);\n"
" triAabb.m_max = max(triAabb.m_max,vert);\n"
" \n"
" }\n"
" \n"
" overlap = true;\n"
" overlap = (triAabb.m_min.x > aabbs[bodyIndexB].m_max.x || triAabb.m_max.x < aabbs[bodyIndexB].m_min.x) ? false : overlap;\n"
" overlap = (triAabb.m_min.z > aabbs[bodyIndexB].m_max.z || triAabb.m_max.z < aabbs[bodyIndexB].m_min.z) ? false : overlap;\n"
" overlap = (triAabb.m_min.y > aabbs[bodyIndexB].m_max.y || triAabb.m_max.y < aabbs[bodyIndexB].m_min.y) ? false : overlap;\n"
" \n"
" if (overlap)\n"
" {\n"
" float dmin = dmins[i];\n"
" int hasSeparatingAxis=5;\n"
" float4 sepAxis=make_float4(1,2,3,4);\n"
" sepAxis = concaveSeparatingNormalsOut[pairIdx];\n"
" \n"
" int localCC=0;\n"
" numActualConcaveConvexTests++;\n"
" \n"
" //a triangle has 3 unique edges\n"
" convexPolyhedronA.m_numUniqueEdges = 3;\n"
" convexPolyhedronA.m_uniqueEdgesOffset = 0;\n"
" float4 uniqueEdgesA[3];\n"
" \n"
" uniqueEdgesA[0] = (verticesA[1]-verticesA[0]);\n"
" uniqueEdgesA[1] = (verticesA[2]-verticesA[1]);\n"
" uniqueEdgesA[2] = (verticesA[0]-verticesA[2]);\n"
" \n"
" \n"
" convexPolyhedronA.m_faceOffset = 0;\n"
" \n"
" float4 normal = make_float4(face.m_plane.x,face.m_plane.y,face.m_plane.z,0.f);\n"
" \n"
" btGpuFace facesA[TRIANGLE_NUM_CONVEX_FACES];\n"
" int indicesA[3+3+2+2+2];\n"
" int curUsedIndices=0;\n"
" int fidx=0;\n"
" \n"
" //front size of triangle\n"
" {\n"
" facesA[fidx].m_indexOffset=curUsedIndices;\n"
" indicesA[0] = 0;\n"
" indicesA[1] = 1;\n"
" indicesA[2] = 2;\n"
" curUsedIndices+=3;\n"
" float c = face.m_plane.w;\n"
" facesA[fidx].m_plane.x = normal.x;\n"
" facesA[fidx].m_plane.y = normal.y;\n"
" facesA[fidx].m_plane.z = normal.z;\n"
" facesA[fidx].m_plane.w = c;\n"
" facesA[fidx].m_numIndices=3;\n"
" }\n"
" fidx++;\n"
" //back size of triangle\n"
" {\n"
" facesA[fidx].m_indexOffset=curUsedIndices;\n"
" indicesA[3]=2;\n"
" indicesA[4]=1;\n"
" indicesA[5]=0;\n"
" curUsedIndices+=3;\n"
" float c = dot(normal,verticesA[0]);\n"
" float c1 = -face.m_plane.w;\n"
" facesA[fidx].m_plane.x = -normal.x;\n"
" facesA[fidx].m_plane.y = -normal.y;\n"
" facesA[fidx].m_plane.z = -normal.z;\n"
" facesA[fidx].m_plane.w = c;\n"
" facesA[fidx].m_numIndices=3;\n"
" }\n"
" fidx++;\n"
" \n"
" bool addEdgePlanes = true;\n"
" if (addEdgePlanes)\n"
" {\n"
" int numVertices=3;\n"
" int prevVertex = numVertices-1;\n"
" for (int i=0;i<numVertices;i++)\n"
" {\n"
" float4 v0 = verticesA[i];\n"
" float4 v1 = verticesA[prevVertex];\n"
" \n"
" float4 edgeNormal = normalize(cross(normal,v1-v0));\n"
" float c = -dot(edgeNormal,v0);\n"
" \n"
" facesA[fidx].m_numIndices = 2;\n"
" facesA[fidx].m_indexOffset=curUsedIndices;\n"
" indicesA[curUsedIndices++]=i;\n"
" indicesA[curUsedIndices++]=prevVertex;\n"
" \n"
" facesA[fidx].m_plane.x = edgeNormal.x;\n"
" facesA[fidx].m_plane.y = edgeNormal.y;\n"
" facesA[fidx].m_plane.z = edgeNormal.z;\n"
" facesA[fidx].m_plane.w = c;\n"
" fidx++;\n"
" prevVertex = i;\n"
" }\n"
" }\n"
" convexPolyhedronA.m_numFaces = TRIANGLE_NUM_CONVEX_FACES;\n"
" convexPolyhedronA.m_localCenter = localCenter*(1.f/3.f);\n"
" \n"
" \n"
" float4 posA = rigidBodies[bodyIndexA].m_pos;\n"
" posA.w = 0.f;\n"
" float4 posB = rigidBodies[bodyIndexB].m_pos;\n"
" posB.w = 0.f;\n"
" \n"
" float4 ornA = rigidBodies[bodyIndexA].m_quat;\n"
" float4 ornB =rigidBodies[bodyIndexB].m_quat;\n"
" \n"
" \n"
" \n"
" \n"
" ///////////////////\n"
" ///compound shape support\n"
" \n"
" if (collidables[collidableIndexB].m_shapeType==SHAPE_COMPOUND_OF_CONVEX_HULLS)\n"
" {\n"
" int compoundChild = concavePairs[pairIdx].w;\n"
" int childShapeIndexB = compoundChild;//collidables[collidableIndexB].m_shapeIndex+compoundChild;\n"
" int childColIndexB = gpuChildShapes[childShapeIndexB].m_shapeIndex;\n"
" float4 childPosB = gpuChildShapes[childShapeIndexB].m_childPosition;\n"
" float4 childOrnB = gpuChildShapes[childShapeIndexB].m_childOrientation;\n"
" float4 newPosB = transform(&childPosB,&posB,&ornB);\n"
" float4 newOrnB = qtMul(ornB,childOrnB);\n"
" posB = newPosB;\n"
" ornB = newOrnB;\n"
" shapeIndexB = collidables[childColIndexB].m_shapeIndex;\n"
" }\n"
" //////////////////\n"
" \n"
" float4 c0local = convexPolyhedronA.m_localCenter;\n"
" float4 c0 = transform(&c0local, &posA, &ornA);\n"
" float4 c1local = convexShapes[shapeIndexB].m_localCenter;\n"
" float4 c1 = transform(&c1local,&posB,&ornB);\n"
" const float4 DeltaC2 = c0 - c1;\n"
" \n"
" \n"
" {\n"
" bool sepEE = findSeparatingAxisEdgeEdgeLocalA( &convexPolyhedronA, &convexShapes[shapeIndexB],\n"
" posA,ornA,\n"
" posB,ornB,\n"
" DeltaC2,\n"
" verticesA,uniqueEdgesA,facesA,indicesA,\n"
" vertices,uniqueEdges,faces,indices,\n"
" &sepAxis,&dmin);\n"
" \n"
" if (!sepEE)\n"
" {\n"
" hasSeparatingAxis = 0;\n"
" } else\n"
" {\n"
" hasSeparatingAxis = 1;\n"
" }\n"
" }\n"
" \n"
" \n"
" if (hasSeparatingAxis)\n"
" {\n"
" sepAxis.w = dmin;\n"
" dmins[i] = dmin;\n"
" concaveSeparatingNormalsOut[pairIdx]=sepAxis;\n"
" concaveHasSeparatingNormals[i]=1;\n"
" \n"
" float minDist = -1e30f;\n"
" float maxDist = 0.02f;\n"
" \n"
" findClippingFaces(sepAxis,\n"
" &convexPolyhedronA,\n"
" &convexShapes[shapeIndexB],\n"
" posA,ornA,\n"
" posB,ornB,\n"
" worldVertsA1GPU,\n"
" worldNormalsAGPU,\n"
" worldVertsB1GPU,\n"
" vertexFaceCapacity,\n"
" minDist, maxDist,\n"
" verticesA,\n"
" facesA,\n"
" indicesA,\n"
" vertices,\n"
" faces,\n"
" indices,\n"
" clippingFacesOut, pairIdx);\n"
" \n"
" \n"
" } else\n"
" { \n"
" //mark this pair as in-active\n"
" concavePairs[pairIdx].w = -1;\n"
" }\n"
" }\n"
" else\n"
" { \n"
" //mark this pair as in-active\n"
" concavePairs[pairIdx].w = -1;\n"
" }\n"
" \n"
" concavePairs[i].z = -1;//for the next stage, z is used to determine existing contact points\n"
"}\n"
;
|