Blame view
tools/cub-1.8.0/cub/block/block_discontinuity.cuh
53.3 KB
8dcb6dfcb
first commit
|
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 |
/******************************************************************************
* Copyright (c) 2011, Duane Merrill. All rights reserved.
* Copyright (c) 2011-2018, NVIDIA CORPORATION. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of the NVIDIA CORPORATION nor the
* names of its contributors may be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
* DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
******************************************************************************/
/**
* \file
* The cub::BlockDiscontinuity class provides [<em>collective</em>](index.html#sec0) methods for flagging discontinuities within an ordered set of items partitioned across a CUDA thread block.
*/
#pragma once
#include "../util_type.cuh"
#include "../util_ptx.cuh"
#include "../util_namespace.cuh"
/// Optional outer namespace(s)
CUB_NS_PREFIX
/// CUB namespace
namespace cub {
/**
* \brief The BlockDiscontinuity class provides [<em>collective</em>](index.html#sec0) methods for flagging discontinuities within an ordered set of items partitioned across a CUDA thread block. 
* \ingroup BlockModule
*
* \tparam T The data type to be flagged.
* \tparam BLOCK_DIM_X The thread block length in threads along the X dimension
* \tparam BLOCK_DIM_Y <b>[optional]</b> The thread block length in threads along the Y dimension (default: 1)
* \tparam BLOCK_DIM_Z <b>[optional]</b> The thread block length in threads along the Z dimension (default: 1)
* \tparam PTX_ARCH <b>[optional]</b> \ptxversion
*
* \par Overview
* - A set of "head flags" (or "tail flags") is often used to indicate corresponding items
* that differ from their predecessors (or successors). For example, head flags are convenient
* for demarcating disjoint data segments as part of a segmented scan or reduction.
* - \blocked
*
* \par Performance Considerations
* - \granularity
*
* \par A Simple Example
* \blockcollective{BlockDiscontinuity}
* \par
* The code snippet below illustrates the head flagging of 512 integer items that
* are partitioned in a [<em>blocked arrangement</em>](index.html#sec5sec3) across 128 threads
* where each thread owns 4 consecutive items.
* \par
* \code
* #include <cub/cub.cuh> // or equivalently <cub/block/block_discontinuity.cuh>
*
* __global__ void ExampleKernel(...)
* {
* // Specialize BlockDiscontinuity for a 1D block of 128 threads on type int
* typedef cub::BlockDiscontinuity<int, 128> BlockDiscontinuity;
*
* // Allocate shared memory for BlockDiscontinuity
* __shared__ typename BlockDiscontinuity::TempStorage temp_storage;
*
* // Obtain a segment of consecutive items that are blocked across threads
* int thread_data[4];
* ...
*
* // Collectively compute head flags for discontinuities in the segment
* int head_flags[4];
* BlockDiscontinuity(temp_storage).FlagHeads(head_flags, thread_data, cub::Inequality());
*
* \endcode
* \par
* Suppose the set of input \p thread_data across the block of threads is
* <tt>{ [0,0,1,1], [1,1,1,1], [2,3,3,3], [3,4,4,4], ... }</tt>.
* The corresponding output \p head_flags in those threads will be
* <tt>{ [1,0,1,0], [0,0,0,0], [1,1,0,0], [0,1,0,0], ... }</tt>.
*
* \par Performance Considerations
* - Incurs zero bank conflicts for most types
*
*/
template <
typename T,
int BLOCK_DIM_X,
int BLOCK_DIM_Y = 1,
int BLOCK_DIM_Z = 1,
int PTX_ARCH = CUB_PTX_ARCH>
class BlockDiscontinuity
{
private:
/******************************************************************************
* Constants and type definitions
******************************************************************************/
/// Constants
enum
{
/// The thread block size in threads
BLOCK_THREADS = BLOCK_DIM_X * BLOCK_DIM_Y * BLOCK_DIM_Z,
};
/// Shared memory storage layout type (last element from each thread's input)
struct _TempStorage
{
T first_items[BLOCK_THREADS];
T last_items[BLOCK_THREADS];
};
/******************************************************************************
* Utility methods
******************************************************************************/
/// Internal storage allocator
__device__ __forceinline__ _TempStorage& PrivateStorage()
{
__shared__ _TempStorage private_storage;
return private_storage;
}
/// Specialization for when FlagOp has third index param
template <typename FlagOp, bool HAS_PARAM = BinaryOpHasIdxParam<T, FlagOp>::HAS_PARAM>
struct ApplyOp
{
// Apply flag operator
static __device__ __forceinline__ bool FlagT(FlagOp flag_op, const T &a, const T &b, int idx)
{
return flag_op(a, b, idx);
}
};
/// Specialization for when FlagOp does not have a third index param
template <typename FlagOp>
struct ApplyOp<FlagOp, false>
{
// Apply flag operator
static __device__ __forceinline__ bool FlagT(FlagOp flag_op, const T &a, const T &b, int /*idx*/)
{
return flag_op(a, b);
}
};
/// Templated unrolling of item comparison (inductive case)
template <int ITERATION, int MAX_ITERATIONS>
struct Iterate
{
// Head flags
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
static __device__ __forceinline__ void FlagHeads(
int linear_tid,
FlagT (&flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
T (&preds)[ITEMS_PER_THREAD], ///< [out] Calling thread's predecessor items
FlagOp flag_op) ///< [in] Binary boolean flag predicate
{
preds[ITERATION] = input[ITERATION - 1];
flags[ITERATION] = ApplyOp<FlagOp>::FlagT(
flag_op,
preds[ITERATION],
input[ITERATION],
(linear_tid * ITEMS_PER_THREAD) + ITERATION);
Iterate<ITERATION + 1, MAX_ITERATIONS>::FlagHeads(linear_tid, flags, input, preds, flag_op);
}
// Tail flags
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
static __device__ __forceinline__ void FlagTails(
int linear_tid,
FlagT (&flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
FlagOp flag_op) ///< [in] Binary boolean flag predicate
{
flags[ITERATION] = ApplyOp<FlagOp>::FlagT(
flag_op,
input[ITERATION],
input[ITERATION + 1],
(linear_tid * ITEMS_PER_THREAD) + ITERATION + 1);
Iterate<ITERATION + 1, MAX_ITERATIONS>::FlagTails(linear_tid, flags, input, flag_op);
}
};
/// Templated unrolling of item comparison (termination case)
template <int MAX_ITERATIONS>
struct Iterate<MAX_ITERATIONS, MAX_ITERATIONS>
{
// Head flags
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
static __device__ __forceinline__ void FlagHeads(
int /*linear_tid*/,
FlagT (&/*flags*/)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
T (&/*input*/)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
T (&/*preds*/)[ITEMS_PER_THREAD], ///< [out] Calling thread's predecessor items
FlagOp /*flag_op*/) ///< [in] Binary boolean flag predicate
{}
// Tail flags
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
static __device__ __forceinline__ void FlagTails(
int /*linear_tid*/,
FlagT (&/*flags*/)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
T (&/*input*/)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
FlagOp /*flag_op*/) ///< [in] Binary boolean flag predicate
{}
};
/******************************************************************************
* Thread fields
******************************************************************************/
/// Shared storage reference
_TempStorage &temp_storage;
/// Linear thread-id
unsigned int linear_tid;
public:
/// \smemstorage{BlockDiscontinuity}
struct TempStorage : Uninitialized<_TempStorage> {};
/******************************************************************//**
*
ame Collective constructors
*********************************************************************/
//@{
/**
* \brief Collective constructor using a private static allocation of shared memory as temporary storage.
*/
__device__ __forceinline__ BlockDiscontinuity()
:
temp_storage(PrivateStorage()),
linear_tid(RowMajorTid(BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z))
{}
/**
* \brief Collective constructor using the specified memory allocation as temporary storage.
*/
__device__ __forceinline__ BlockDiscontinuity(
TempStorage &temp_storage) ///< [in] Reference to memory allocation having layout type TempStorage
:
temp_storage(temp_storage.Alias()),
linear_tid(RowMajorTid(BLOCK_DIM_X, BLOCK_DIM_Y, BLOCK_DIM_Z))
{}
//@} end member group
/******************************************************************//**
*
ame Head flag operations
*********************************************************************/
//@{
#ifndef DOXYGEN_SHOULD_SKIP_THIS // Do not document
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
__device__ __forceinline__ void FlagHeads(
FlagT (&head_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
T (&preds)[ITEMS_PER_THREAD], ///< [out] Calling thread's predecessor items
FlagOp flag_op) ///< [in] Binary boolean flag predicate
{
// Share last item
temp_storage.last_items[linear_tid] = input[ITEMS_PER_THREAD - 1];
CTA_SYNC();
if (linear_tid == 0)
{
// Set flag for first thread-item (preds[0] is undefined)
head_flags[0] = 1;
}
else
{
preds[0] = temp_storage.last_items[linear_tid - 1];
head_flags[0] = ApplyOp<FlagOp>::FlagT(flag_op, preds[0], input[0], linear_tid * ITEMS_PER_THREAD);
}
// Set head_flags for remaining items
Iterate<1, ITEMS_PER_THREAD>::FlagHeads(linear_tid, head_flags, input, preds, flag_op);
}
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
__device__ __forceinline__ void FlagHeads(
FlagT (&head_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
T (&preds)[ITEMS_PER_THREAD], ///< [out] Calling thread's predecessor items
FlagOp flag_op, ///< [in] Binary boolean flag predicate
T tile_predecessor_item) ///< [in] <b>[<em>thread</em><sub>0</sub> only]</b> Item with which to compare the first tile item (<tt>input<sub>0</sub></tt> from <em>thread</em><sub>0</sub>).
{
// Share last item
temp_storage.last_items[linear_tid] = input[ITEMS_PER_THREAD - 1];
CTA_SYNC();
// Set flag for first thread-item
preds[0] = (linear_tid == 0) ?
tile_predecessor_item : // First thread
temp_storage.last_items[linear_tid - 1];
head_flags[0] = ApplyOp<FlagOp>::FlagT(flag_op, preds[0], input[0], linear_tid * ITEMS_PER_THREAD);
// Set head_flags for remaining items
Iterate<1, ITEMS_PER_THREAD>::FlagHeads(linear_tid, head_flags, input, preds, flag_op);
}
#endif // DOXYGEN_SHOULD_SKIP_THIS
/**
* \brief Sets head flags indicating discontinuities between items partitioned across the thread block, for which the first item has no reference and is always flagged.
*
* \par
* - The flag <tt>head_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(</tt><em>previous-item</em><tt>, input<sub><em>i</em></sub>)</tt>
* returns \p true (where <em>previous-item</em> is either the preceding item
* in the same thread or the last item in the previous thread).
* - For <em>thread</em><sub>0</sub>, item <tt>input<sub>0</sub></tt> is always flagged.
* - \blocked
* - \granularity
* - \smemreuse
*
* \par Snippet
* The code snippet below illustrates the head-flagging of 512 integer items that
* are partitioned in a [<em>blocked arrangement</em>](index.html#sec5sec3) across 128 threads
* where each thread owns 4 consecutive items.
* \par
* \code
* #include <cub/cub.cuh> // or equivalently <cub/block/block_discontinuity.cuh>
*
* __global__ void ExampleKernel(...)
* {
* // Specialize BlockDiscontinuity for a 1D block of 128 threads on type int
* typedef cub::BlockDiscontinuity<int, 128> BlockDiscontinuity;
*
* // Allocate shared memory for BlockDiscontinuity
* __shared__ typename BlockDiscontinuity::TempStorage temp_storage;
*
* // Obtain a segment of consecutive items that are blocked across threads
* int thread_data[4];
* ...
*
* // Collectively compute head flags for discontinuities in the segment
* int head_flags[4];
* BlockDiscontinuity(temp_storage).FlagHeads(head_flags, thread_data, cub::Inequality());
*
* \endcode
* \par
* Suppose the set of input \p thread_data across the block of threads is
* <tt>{ [0,0,1,1], [1,1,1,1], [2,3,3,3], [3,4,4,4], ... }</tt>.
* The corresponding output \p head_flags in those threads will be
* <tt>{ [1,0,1,0], [0,0,0,0], [1,1,0,0], [0,1,0,0], ... }</tt>.
*
* \tparam ITEMS_PER_THREAD <b>[inferred]</b> The number of consecutive items partitioned onto each thread.
* \tparam FlagT <b>[inferred]</b> The flag type (must be an integer type)
* \tparam FlagOp <b>[inferred]</b> Binary predicate functor type having member <tt>T operator()(const T &a, const T &b)</tt> or member <tt>T operator()(const T &a, const T &b, unsigned int b_index)</tt>, and returning \p true if a discontinuity exists between \p a and \p b, otherwise \p false. \p b_index is the rank of b in the aggregate tile of data.
*/
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
__device__ __forceinline__ void FlagHeads(
FlagT (&head_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
FlagOp flag_op) ///< [in] Binary boolean flag predicate
{
T preds[ITEMS_PER_THREAD];
FlagHeads(head_flags, input, preds, flag_op);
}
/**
* \brief Sets head flags indicating discontinuities between items partitioned across the thread block.
*
* \par
* - The flag <tt>head_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(</tt><em>previous-item</em><tt>, input<sub><em>i</em></sub>)</tt>
* returns \p true (where <em>previous-item</em> is either the preceding item
* in the same thread or the last item in the previous thread).
* - For <em>thread</em><sub>0</sub>, item <tt>input<sub>0</sub></tt> is compared
* against \p tile_predecessor_item.
* - \blocked
* - \granularity
* - \smemreuse
*
* \par Snippet
* The code snippet below illustrates the head-flagging of 512 integer items that
* are partitioned in a [<em>blocked arrangement</em>](index.html#sec5sec3) across 128 threads
* where each thread owns 4 consecutive items.
* \par
* \code
* #include <cub/cub.cuh> // or equivalently <cub/block/block_discontinuity.cuh>
*
* __global__ void ExampleKernel(...)
* {
* // Specialize BlockDiscontinuity for a 1D block of 128 threads on type int
* typedef cub::BlockDiscontinuity<int, 128> BlockDiscontinuity;
*
* // Allocate shared memory for BlockDiscontinuity
* __shared__ typename BlockDiscontinuity::TempStorage temp_storage;
*
* // Obtain a segment of consecutive items that are blocked across threads
* int thread_data[4];
* ...
*
* // Have thread0 obtain the predecessor item for the entire tile
* int tile_predecessor_item;
* if (threadIdx.x == 0) tile_predecessor_item == ...
*
* // Collectively compute head flags for discontinuities in the segment
* int head_flags[4];
* BlockDiscontinuity(temp_storage).FlagHeads(
* head_flags, thread_data, cub::Inequality(), tile_predecessor_item);
*
* \endcode
* \par
* Suppose the set of input \p thread_data across the block of threads is
* <tt>{ [0,0,1,1], [1,1,1,1], [2,3,3,3], [3,4,4,4], ... }</tt>,
* and that \p tile_predecessor_item is \p 0. The corresponding output \p head_flags in those threads will be
* <tt>{ [0,0,1,0], [0,0,0,0], [1,1,0,0], [0,1,0,0], ... }</tt>.
*
* \tparam ITEMS_PER_THREAD <b>[inferred]</b> The number of consecutive items partitioned onto each thread.
* \tparam FlagT <b>[inferred]</b> The flag type (must be an integer type)
* \tparam FlagOp <b>[inferred]</b> Binary predicate functor type having member <tt>T operator()(const T &a, const T &b)</tt> or member <tt>T operator()(const T &a, const T &b, unsigned int b_index)</tt>, and returning \p true if a discontinuity exists between \p a and \p b, otherwise \p false. \p b_index is the rank of b in the aggregate tile of data.
*/
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
__device__ __forceinline__ void FlagHeads(
FlagT (&head_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
FlagOp flag_op, ///< [in] Binary boolean flag predicate
T tile_predecessor_item) ///< [in] <b>[<em>thread</em><sub>0</sub> only]</b> Item with which to compare the first tile item (<tt>input<sub>0</sub></tt> from <em>thread</em><sub>0</sub>).
{
T preds[ITEMS_PER_THREAD];
FlagHeads(head_flags, input, preds, flag_op, tile_predecessor_item);
}
//@} end member group
/******************************************************************//**
*
ame Tail flag operations
*********************************************************************/
//@{
/**
* \brief Sets tail flags indicating discontinuities between items partitioned across the thread block, for which the last item has no reference and is always flagged.
*
* \par
* - The flag <tt>tail_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(input<sub><em>i</em></sub>, </tt><em>next-item</em><tt>)</tt>
* returns \p true (where <em>next-item</em> is either the next item
* in the same thread or the first item in the next thread).
* - For <em>thread</em><sub><em>BLOCK_THREADS</em>-1</sub>, item
* <tt>input</tt><sub><em>ITEMS_PER_THREAD</em>-1</sub> is always flagged.
* - \blocked
* - \granularity
* - \smemreuse
*
* \par Snippet
* The code snippet below illustrates the tail-flagging of 512 integer items that
* are partitioned in a [<em>blocked arrangement</em>](index.html#sec5sec3) across 128 threads
* where each thread owns 4 consecutive items.
* \par
* \code
* #include <cub/cub.cuh> // or equivalently <cub/block/block_discontinuity.cuh>
*
* __global__ void ExampleKernel(...)
* {
* // Specialize BlockDiscontinuity for a 1D block of 128 threads on type int
* typedef cub::BlockDiscontinuity<int, 128> BlockDiscontinuity;
*
* // Allocate shared memory for BlockDiscontinuity
* __shared__ typename BlockDiscontinuity::TempStorage temp_storage;
*
* // Obtain a segment of consecutive items that are blocked across threads
* int thread_data[4];
* ...
*
* // Collectively compute tail flags for discontinuities in the segment
* int tail_flags[4];
* BlockDiscontinuity(temp_storage).FlagTails(tail_flags, thread_data, cub::Inequality());
*
* \endcode
* \par
* Suppose the set of input \p thread_data across the block of threads is
* <tt>{ [0,0,1,1], [1,1,1,1], [2,3,3,3], ..., [124,125,125,125] }</tt>.
* The corresponding output \p tail_flags in those threads will be
* <tt>{ [0,1,0,0], [0,0,0,1], [1,0,0,...], ..., [1,0,0,1] }</tt>.
*
* \tparam ITEMS_PER_THREAD <b>[inferred]</b> The number of consecutive items partitioned onto each thread.
* \tparam FlagT <b>[inferred]</b> The flag type (must be an integer type)
* \tparam FlagOp <b>[inferred]</b> Binary predicate functor type having member <tt>T operator()(const T &a, const T &b)</tt> or member <tt>T operator()(const T &a, const T &b, unsigned int b_index)</tt>, and returning \p true if a discontinuity exists between \p a and \p b, otherwise \p false. \p b_index is the rank of b in the aggregate tile of data.
*/
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
__device__ __forceinline__ void FlagTails(
FlagT (&tail_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity tail_flags
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
FlagOp flag_op) ///< [in] Binary boolean flag predicate
{
// Share first item
temp_storage.first_items[linear_tid] = input[0];
CTA_SYNC();
// Set flag for last thread-item
tail_flags[ITEMS_PER_THREAD - 1] = (linear_tid == BLOCK_THREADS - 1) ?
1 : // Last thread
ApplyOp<FlagOp>::FlagT(
flag_op,
input[ITEMS_PER_THREAD - 1],
temp_storage.first_items[linear_tid + 1],
(linear_tid * ITEMS_PER_THREAD) + ITEMS_PER_THREAD);
// Set tail_flags for remaining items
Iterate<0, ITEMS_PER_THREAD - 1>::FlagTails(linear_tid, tail_flags, input, flag_op);
}
/**
* \brief Sets tail flags indicating discontinuities between items partitioned across the thread block.
*
* \par
* - The flag <tt>tail_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(input<sub><em>i</em></sub>, </tt><em>next-item</em><tt>)</tt>
* returns \p true (where <em>next-item</em> is either the next item
* in the same thread or the first item in the next thread).
* - For <em>thread</em><sub><em>BLOCK_THREADS</em>-1</sub>, item
* <tt>input</tt><sub><em>ITEMS_PER_THREAD</em>-1</sub> is compared
* against \p tile_successor_item.
* - \blocked
* - \granularity
* - \smemreuse
*
* \par Snippet
* The code snippet below illustrates the tail-flagging of 512 integer items that
* are partitioned in a [<em>blocked arrangement</em>](index.html#sec5sec3) across 128 threads
* where each thread owns 4 consecutive items.
* \par
* \code
* #include <cub/cub.cuh> // or equivalently <cub/block/block_discontinuity.cuh>
*
* __global__ void ExampleKernel(...)
* {
* // Specialize BlockDiscontinuity for a 1D block of 128 threads on type int
* typedef cub::BlockDiscontinuity<int, 128> BlockDiscontinuity;
*
* // Allocate shared memory for BlockDiscontinuity
* __shared__ typename BlockDiscontinuity::TempStorage temp_storage;
*
* // Obtain a segment of consecutive items that are blocked across threads
* int thread_data[4];
* ...
*
* // Have thread127 obtain the successor item for the entire tile
* int tile_successor_item;
* if (threadIdx.x == 127) tile_successor_item == ...
*
* // Collectively compute tail flags for discontinuities in the segment
* int tail_flags[4];
* BlockDiscontinuity(temp_storage).FlagTails(
* tail_flags, thread_data, cub::Inequality(), tile_successor_item);
*
* \endcode
* \par
* Suppose the set of input \p thread_data across the block of threads is
* <tt>{ [0,0,1,1], [1,1,1,1], [2,3,3,3], ..., [124,125,125,125] }</tt>
* and that \p tile_successor_item is \p 125. The corresponding output \p tail_flags in those threads will be
* <tt>{ [0,1,0,0], [0,0,0,1], [1,0,0,...], ..., [1,0,0,0] }</tt>.
*
* \tparam ITEMS_PER_THREAD <b>[inferred]</b> The number of consecutive items partitioned onto each thread.
* \tparam FlagT <b>[inferred]</b> The flag type (must be an integer type)
* \tparam FlagOp <b>[inferred]</b> Binary predicate functor type having member <tt>T operator()(const T &a, const T &b)</tt> or member <tt>T operator()(const T &a, const T &b, unsigned int b_index)</tt>, and returning \p true if a discontinuity exists between \p a and \p b, otherwise \p false. \p b_index is the rank of b in the aggregate tile of data.
*/
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
__device__ __forceinline__ void FlagTails(
FlagT (&tail_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity tail_flags
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
FlagOp flag_op, ///< [in] Binary boolean flag predicate
T tile_successor_item) ///< [in] <b>[<em>thread</em><sub><tt>BLOCK_THREADS</tt>-1</sub> only]</b> Item with which to compare the last tile item (<tt>input</tt><sub><em>ITEMS_PER_THREAD</em>-1</sub> from <em>thread</em><sub><em>BLOCK_THREADS</em>-1</sub>).
{
// Share first item
temp_storage.first_items[linear_tid] = input[0];
CTA_SYNC();
// Set flag for last thread-item
T successor_item = (linear_tid == BLOCK_THREADS - 1) ?
tile_successor_item : // Last thread
temp_storage.first_items[linear_tid + 1];
tail_flags[ITEMS_PER_THREAD - 1] = ApplyOp<FlagOp>::FlagT(
flag_op,
input[ITEMS_PER_THREAD - 1],
successor_item,
(linear_tid * ITEMS_PER_THREAD) + ITEMS_PER_THREAD);
// Set tail_flags for remaining items
Iterate<0, ITEMS_PER_THREAD - 1>::FlagTails(linear_tid, tail_flags, input, flag_op);
}
//@} end member group
/******************************************************************//**
*
ame Head & tail flag operations
*********************************************************************/
//@{
/**
* \brief Sets both head and tail flags indicating discontinuities between items partitioned across the thread block.
*
* \par
* - The flag <tt>head_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(</tt><em>previous-item</em><tt>, input<sub><em>i</em></sub>)</tt>
* returns \p true (where <em>previous-item</em> is either the preceding item
* in the same thread or the last item in the previous thread).
* - For <em>thread</em><sub>0</sub>, item <tt>input<sub>0</sub></tt> is always flagged.
* - The flag <tt>tail_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(input<sub><em>i</em></sub>, </tt><em>next-item</em><tt>)</tt>
* returns \p true (where <em>next-item</em> is either the next item
* in the same thread or the first item in the next thread).
* - For <em>thread</em><sub><em>BLOCK_THREADS</em>-1</sub>, item
* <tt>input</tt><sub><em>ITEMS_PER_THREAD</em>-1</sub> is always flagged.
* - \blocked
* - \granularity
* - \smemreuse
*
* \par Snippet
* The code snippet below illustrates the head- and tail-flagging of 512 integer items that
* are partitioned in a [<em>blocked arrangement</em>](index.html#sec5sec3) across 128 threads
* where each thread owns 4 consecutive items.
* \par
* \code
* #include <cub/cub.cuh> // or equivalently <cub/block/block_discontinuity.cuh>
*
* __global__ void ExampleKernel(...)
* {
* // Specialize BlockDiscontinuity for a 1D block of 128 threads on type int
* typedef cub::BlockDiscontinuity<int, 128> BlockDiscontinuity;
*
* // Allocate shared memory for BlockDiscontinuity
* __shared__ typename BlockDiscontinuity::TempStorage temp_storage;
*
* // Obtain a segment of consecutive items that are blocked across threads
* int thread_data[4];
* ...
*
* // Collectively compute head and flags for discontinuities in the segment
* int head_flags[4];
* int tail_flags[4];
* BlockDiscontinuity(temp_storage).FlagTails(
* head_flags, tail_flags, thread_data, cub::Inequality());
*
* \endcode
* \par
* Suppose the set of input \p thread_data across the block of threads is
* <tt>{ [0,0,1,1], [1,1,1,1], [2,3,3,3], ..., [124,125,125,125] }</tt>
* and that the tile_successor_item is \p 125. The corresponding output \p head_flags
* in those threads will be <tt>{ [1,0,1,0], [0,0,0,0], [1,1,0,0], [0,1,0,0], ... }</tt>.
* and the corresponding output \p tail_flags in those threads will be
* <tt>{ [0,1,0,0], [0,0,0,1], [1,0,0,...], ..., [1,0,0,1] }</tt>.
*
* \tparam ITEMS_PER_THREAD <b>[inferred]</b> The number of consecutive items partitioned onto each thread.
* \tparam FlagT <b>[inferred]</b> The flag type (must be an integer type)
* \tparam FlagOp <b>[inferred]</b> Binary predicate functor type having member <tt>T operator()(const T &a, const T &b)</tt> or member <tt>T operator()(const T &a, const T &b, unsigned int b_index)</tt>, and returning \p true if a discontinuity exists between \p a and \p b, otherwise \p false. \p b_index is the rank of b in the aggregate tile of data.
*/
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
__device__ __forceinline__ void FlagHeadsAndTails(
FlagT (&head_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
FlagT (&tail_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity tail_flags
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
FlagOp flag_op) ///< [in] Binary boolean flag predicate
{
// Share first and last items
temp_storage.first_items[linear_tid] = input[0];
temp_storage.last_items[linear_tid] = input[ITEMS_PER_THREAD - 1];
CTA_SYNC();
T preds[ITEMS_PER_THREAD];
// Set flag for first thread-item
preds[0] = temp_storage.last_items[linear_tid - 1];
if (linear_tid == 0)
{
head_flags[0] = 1;
}
else
{
head_flags[0] = ApplyOp<FlagOp>::FlagT(
flag_op,
preds[0],
input[0],
linear_tid * ITEMS_PER_THREAD);
}
// Set flag for last thread-item
tail_flags[ITEMS_PER_THREAD - 1] = (linear_tid == BLOCK_THREADS - 1) ?
1 : // Last thread
ApplyOp<FlagOp>::FlagT(
flag_op,
input[ITEMS_PER_THREAD - 1],
temp_storage.first_items[linear_tid + 1],
(linear_tid * ITEMS_PER_THREAD) + ITEMS_PER_THREAD);
// Set head_flags for remaining items
Iterate<1, ITEMS_PER_THREAD>::FlagHeads(linear_tid, head_flags, input, preds, flag_op);
// Set tail_flags for remaining items
Iterate<0, ITEMS_PER_THREAD - 1>::FlagTails(linear_tid, tail_flags, input, flag_op);
}
/**
* \brief Sets both head and tail flags indicating discontinuities between items partitioned across the thread block.
*
* \par
* - The flag <tt>head_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(</tt><em>previous-item</em><tt>, input<sub><em>i</em></sub>)</tt>
* returns \p true (where <em>previous-item</em> is either the preceding item
* in the same thread or the last item in the previous thread).
* - For <em>thread</em><sub>0</sub>, item <tt>input<sub>0</sub></tt> is always flagged.
* - The flag <tt>tail_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(input<sub><em>i</em></sub>, </tt><em>next-item</em><tt>)</tt>
* returns \p true (where <em>next-item</em> is either the next item
* in the same thread or the first item in the next thread).
* - For <em>thread</em><sub><em>BLOCK_THREADS</em>-1</sub>, item
* <tt>input</tt><sub><em>ITEMS_PER_THREAD</em>-1</sub> is compared
* against \p tile_predecessor_item.
* - \blocked
* - \granularity
* - \smemreuse
*
* \par Snippet
* The code snippet below illustrates the head- and tail-flagging of 512 integer items that
* are partitioned in a [<em>blocked arrangement</em>](index.html#sec5sec3) across 128 threads
* where each thread owns 4 consecutive items.
* \par
* \code
* #include <cub/cub.cuh> // or equivalently <cub/block/block_discontinuity.cuh>
*
* __global__ void ExampleKernel(...)
* {
* // Specialize BlockDiscontinuity for a 1D block of 128 threads on type int
* typedef cub::BlockDiscontinuity<int, 128> BlockDiscontinuity;
*
* // Allocate shared memory for BlockDiscontinuity
* __shared__ typename BlockDiscontinuity::TempStorage temp_storage;
*
* // Obtain a segment of consecutive items that are blocked across threads
* int thread_data[4];
* ...
*
* // Have thread127 obtain the successor item for the entire tile
* int tile_successor_item;
* if (threadIdx.x == 127) tile_successor_item == ...
*
* // Collectively compute head and flags for discontinuities in the segment
* int head_flags[4];
* int tail_flags[4];
* BlockDiscontinuity(temp_storage).FlagTails(
* head_flags, tail_flags, tile_successor_item, thread_data, cub::Inequality());
*
* \endcode
* \par
* Suppose the set of input \p thread_data across the block of threads is
* <tt>{ [0,0,1,1], [1,1,1,1], [2,3,3,3], ..., [124,125,125,125] }</tt>
* and that the tile_successor_item is \p 125. The corresponding output \p head_flags
* in those threads will be <tt>{ [1,0,1,0], [0,0,0,0], [1,1,0,0], [0,1,0,0], ... }</tt>.
* and the corresponding output \p tail_flags in those threads will be
* <tt>{ [0,1,0,0], [0,0,0,1], [1,0,0,...], ..., [1,0,0,0] }</tt>.
*
* \tparam ITEMS_PER_THREAD <b>[inferred]</b> The number of consecutive items partitioned onto each thread.
* \tparam FlagT <b>[inferred]</b> The flag type (must be an integer type)
* \tparam FlagOp <b>[inferred]</b> Binary predicate functor type having member <tt>T operator()(const T &a, const T &b)</tt> or member <tt>T operator()(const T &a, const T &b, unsigned int b_index)</tt>, and returning \p true if a discontinuity exists between \p a and \p b, otherwise \p false. \p b_index is the rank of b in the aggregate tile of data.
*/
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
__device__ __forceinline__ void FlagHeadsAndTails(
FlagT (&head_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
FlagT (&tail_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity tail_flags
T tile_successor_item, ///< [in] <b>[<em>thread</em><sub><tt>BLOCK_THREADS</tt>-1</sub> only]</b> Item with which to compare the last tile item (<tt>input</tt><sub><em>ITEMS_PER_THREAD</em>-1</sub> from <em>thread</em><sub><em>BLOCK_THREADS</em>-1</sub>).
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
FlagOp flag_op) ///< [in] Binary boolean flag predicate
{
// Share first and last items
temp_storage.first_items[linear_tid] = input[0];
temp_storage.last_items[linear_tid] = input[ITEMS_PER_THREAD - 1];
CTA_SYNC();
T preds[ITEMS_PER_THREAD];
// Set flag for first thread-item
if (linear_tid == 0)
{
head_flags[0] = 1;
}
else
{
preds[0] = temp_storage.last_items[linear_tid - 1];
head_flags[0] = ApplyOp<FlagOp>::FlagT(
flag_op,
preds[0],
input[0],
linear_tid * ITEMS_PER_THREAD);
}
// Set flag for last thread-item
T successor_item = (linear_tid == BLOCK_THREADS - 1) ?
tile_successor_item : // Last thread
temp_storage.first_items[linear_tid + 1];
tail_flags[ITEMS_PER_THREAD - 1] = ApplyOp<FlagOp>::FlagT(
flag_op,
input[ITEMS_PER_THREAD - 1],
successor_item,
(linear_tid * ITEMS_PER_THREAD) + ITEMS_PER_THREAD);
// Set head_flags for remaining items
Iterate<1, ITEMS_PER_THREAD>::FlagHeads(linear_tid, head_flags, input, preds, flag_op);
// Set tail_flags for remaining items
Iterate<0, ITEMS_PER_THREAD - 1>::FlagTails(linear_tid, tail_flags, input, flag_op);
}
/**
* \brief Sets both head and tail flags indicating discontinuities between items partitioned across the thread block.
*
* \par
* - The flag <tt>head_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(</tt><em>previous-item</em><tt>, input<sub><em>i</em></sub>)</tt>
* returns \p true (where <em>previous-item</em> is either the preceding item
* in the same thread or the last item in the previous thread).
* - For <em>thread</em><sub>0</sub>, item <tt>input<sub>0</sub></tt> is compared
* against \p tile_predecessor_item.
* - The flag <tt>tail_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(input<sub><em>i</em></sub>, </tt><em>next-item</em><tt>)</tt>
* returns \p true (where <em>next-item</em> is either the next item
* in the same thread or the first item in the next thread).
* - For <em>thread</em><sub><em>BLOCK_THREADS</em>-1</sub>, item
* <tt>input</tt><sub><em>ITEMS_PER_THREAD</em>-1</sub> is always flagged.
* - \blocked
* - \granularity
* - \smemreuse
*
* \par Snippet
* The code snippet below illustrates the head- and tail-flagging of 512 integer items that
* are partitioned in a [<em>blocked arrangement</em>](index.html#sec5sec3) across 128 threads
* where each thread owns 4 consecutive items.
* \par
* \code
* #include <cub/cub.cuh> // or equivalently <cub/block/block_discontinuity.cuh>
*
* __global__ void ExampleKernel(...)
* {
* // Specialize BlockDiscontinuity for a 1D block of 128 threads on type int
* typedef cub::BlockDiscontinuity<int, 128> BlockDiscontinuity;
*
* // Allocate shared memory for BlockDiscontinuity
* __shared__ typename BlockDiscontinuity::TempStorage temp_storage;
*
* // Obtain a segment of consecutive items that are blocked across threads
* int thread_data[4];
* ...
*
* // Have thread0 obtain the predecessor item for the entire tile
* int tile_predecessor_item;
* if (threadIdx.x == 0) tile_predecessor_item == ...
*
* // Have thread127 obtain the successor item for the entire tile
* int tile_successor_item;
* if (threadIdx.x == 127) tile_successor_item == ...
*
* // Collectively compute head and flags for discontinuities in the segment
* int head_flags[4];
* int tail_flags[4];
* BlockDiscontinuity(temp_storage).FlagTails(
* head_flags, tile_predecessor_item, tail_flags, tile_successor_item,
* thread_data, cub::Inequality());
*
* \endcode
* \par
* Suppose the set of input \p thread_data across the block of threads is
* <tt>{ [0,0,1,1], [1,1,1,1], [2,3,3,3], ..., [124,125,125,125] }</tt>,
* that the \p tile_predecessor_item is \p 0, and that the
* \p tile_successor_item is \p 125. The corresponding output \p head_flags
* in those threads will be <tt>{ [0,0,1,0], [0,0,0,0], [1,1,0,0], [0,1,0,0], ... }</tt>.
* and the corresponding output \p tail_flags in those threads will be
* <tt>{ [0,1,0,0], [0,0,0,1], [1,0,0,...], ..., [1,0,0,1] }</tt>.
*
* \tparam ITEMS_PER_THREAD <b>[inferred]</b> The number of consecutive items partitioned onto each thread.
* \tparam FlagT <b>[inferred]</b> The flag type (must be an integer type)
* \tparam FlagOp <b>[inferred]</b> Binary predicate functor type having member <tt>T operator()(const T &a, const T &b)</tt> or member <tt>T operator()(const T &a, const T &b, unsigned int b_index)</tt>, and returning \p true if a discontinuity exists between \p a and \p b, otherwise \p false. \p b_index is the rank of b in the aggregate tile of data.
*/
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
__device__ __forceinline__ void FlagHeadsAndTails(
FlagT (&head_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
T tile_predecessor_item, ///< [in] <b>[<em>thread</em><sub>0</sub> only]</b> Item with which to compare the first tile item (<tt>input<sub>0</sub></tt> from <em>thread</em><sub>0</sub>).
FlagT (&tail_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity tail_flags
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
FlagOp flag_op) ///< [in] Binary boolean flag predicate
{
// Share first and last items
temp_storage.first_items[linear_tid] = input[0];
temp_storage.last_items[linear_tid] = input[ITEMS_PER_THREAD - 1];
CTA_SYNC();
T preds[ITEMS_PER_THREAD];
// Set flag for first thread-item
preds[0] = (linear_tid == 0) ?
tile_predecessor_item : // First thread
temp_storage.last_items[linear_tid - 1];
head_flags[0] = ApplyOp<FlagOp>::FlagT(
flag_op,
preds[0],
input[0],
linear_tid * ITEMS_PER_THREAD);
// Set flag for last thread-item
tail_flags[ITEMS_PER_THREAD - 1] = (linear_tid == BLOCK_THREADS - 1) ?
1 : // Last thread
ApplyOp<FlagOp>::FlagT(
flag_op,
input[ITEMS_PER_THREAD - 1],
temp_storage.first_items[linear_tid + 1],
(linear_tid * ITEMS_PER_THREAD) + ITEMS_PER_THREAD);
// Set head_flags for remaining items
Iterate<1, ITEMS_PER_THREAD>::FlagHeads(linear_tid, head_flags, input, preds, flag_op);
// Set tail_flags for remaining items
Iterate<0, ITEMS_PER_THREAD - 1>::FlagTails(linear_tid, tail_flags, input, flag_op);
}
/**
* \brief Sets both head and tail flags indicating discontinuities between items partitioned across the thread block.
*
* \par
* - The flag <tt>head_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(</tt><em>previous-item</em><tt>, input<sub><em>i</em></sub>)</tt>
* returns \p true (where <em>previous-item</em> is either the preceding item
* in the same thread or the last item in the previous thread).
* - For <em>thread</em><sub>0</sub>, item <tt>input<sub>0</sub></tt> is compared
* against \p tile_predecessor_item.
* - The flag <tt>tail_flags<sub><em>i</em></sub></tt> is set for item
* <tt>input<sub><em>i</em></sub></tt> when
* <tt>flag_op(input<sub><em>i</em></sub>, </tt><em>next-item</em><tt>)</tt>
* returns \p true (where <em>next-item</em> is either the next item
* in the same thread or the first item in the next thread).
* - For <em>thread</em><sub><em>BLOCK_THREADS</em>-1</sub>, item
* <tt>input</tt><sub><em>ITEMS_PER_THREAD</em>-1</sub> is compared
* against \p tile_successor_item.
* - \blocked
* - \granularity
* - \smemreuse
*
* \par Snippet
* The code snippet below illustrates the head- and tail-flagging of 512 integer items that
* are partitioned in a [<em>blocked arrangement</em>](index.html#sec5sec3) across 128 threads
* where each thread owns 4 consecutive items.
* \par
* \code
* #include <cub/cub.cuh> // or equivalently <cub/block/block_discontinuity.cuh>
*
* __global__ void ExampleKernel(...)
* {
* // Specialize BlockDiscontinuity for a 1D block of 128 threads on type int
* typedef cub::BlockDiscontinuity<int, 128> BlockDiscontinuity;
*
* // Allocate shared memory for BlockDiscontinuity
* __shared__ typename BlockDiscontinuity::TempStorage temp_storage;
*
* // Obtain a segment of consecutive items that are blocked across threads
* int thread_data[4];
* ...
*
* // Have thread0 obtain the predecessor item for the entire tile
* int tile_predecessor_item;
* if (threadIdx.x == 0) tile_predecessor_item == ...
*
* // Have thread127 obtain the successor item for the entire tile
* int tile_successor_item;
* if (threadIdx.x == 127) tile_successor_item == ...
*
* // Collectively compute head and flags for discontinuities in the segment
* int head_flags[4];
* int tail_flags[4];
* BlockDiscontinuity(temp_storage).FlagTails(
* head_flags, tile_predecessor_item, tail_flags, tile_successor_item,
* thread_data, cub::Inequality());
*
* \endcode
* \par
* Suppose the set of input \p thread_data across the block of threads is
* <tt>{ [0,0,1,1], [1,1,1,1], [2,3,3,3], ..., [124,125,125,125] }</tt>,
* that the \p tile_predecessor_item is \p 0, and that the
* \p tile_successor_item is \p 125. The corresponding output \p head_flags
* in those threads will be <tt>{ [0,0,1,0], [0,0,0,0], [1,1,0,0], [0,1,0,0], ... }</tt>.
* and the corresponding output \p tail_flags in those threads will be
* <tt>{ [0,1,0,0], [0,0,0,1], [1,0,0,...], ..., [1,0,0,0] }</tt>.
*
* \tparam ITEMS_PER_THREAD <b>[inferred]</b> The number of consecutive items partitioned onto each thread.
* \tparam FlagT <b>[inferred]</b> The flag type (must be an integer type)
* \tparam FlagOp <b>[inferred]</b> Binary predicate functor type having member <tt>T operator()(const T &a, const T &b)</tt> or member <tt>T operator()(const T &a, const T &b, unsigned int b_index)</tt>, and returning \p true if a discontinuity exists between \p a and \p b, otherwise \p false. \p b_index is the rank of b in the aggregate tile of data.
*/
template <
int ITEMS_PER_THREAD,
typename FlagT,
typename FlagOp>
__device__ __forceinline__ void FlagHeadsAndTails(
FlagT (&head_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity head_flags
T tile_predecessor_item, ///< [in] <b>[<em>thread</em><sub>0</sub> only]</b> Item with which to compare the first tile item (<tt>input<sub>0</sub></tt> from <em>thread</em><sub>0</sub>).
FlagT (&tail_flags)[ITEMS_PER_THREAD], ///< [out] Calling thread's discontinuity tail_flags
T tile_successor_item, ///< [in] <b>[<em>thread</em><sub><tt>BLOCK_THREADS</tt>-1</sub> only]</b> Item with which to compare the last tile item (<tt>input</tt><sub><em>ITEMS_PER_THREAD</em>-1</sub> from <em>thread</em><sub><em>BLOCK_THREADS</em>-1</sub>).
T (&input)[ITEMS_PER_THREAD], ///< [in] Calling thread's input items
FlagOp flag_op) ///< [in] Binary boolean flag predicate
{
// Share first and last items
temp_storage.first_items[linear_tid] = input[0];
temp_storage.last_items[linear_tid] = input[ITEMS_PER_THREAD - 1];
CTA_SYNC();
T preds[ITEMS_PER_THREAD];
// Set flag for first thread-item
preds[0] = (linear_tid == 0) ?
tile_predecessor_item : // First thread
temp_storage.last_items[linear_tid - 1];
head_flags[0] = ApplyOp<FlagOp>::FlagT(
flag_op,
preds[0],
input[0],
linear_tid * ITEMS_PER_THREAD);
// Set flag for last thread-item
T successor_item = (linear_tid == BLOCK_THREADS - 1) ?
tile_successor_item : // Last thread
temp_storage.first_items[linear_tid + 1];
tail_flags[ITEMS_PER_THREAD - 1] = ApplyOp<FlagOp>::FlagT(
flag_op,
input[ITEMS_PER_THREAD - 1],
successor_item,
(linear_tid * ITEMS_PER_THREAD) + ITEMS_PER_THREAD);
// Set head_flags for remaining items
Iterate<1, ITEMS_PER_THREAD>::FlagHeads(linear_tid, head_flags, input, preds, flag_op);
// Set tail_flags for remaining items
Iterate<0, ITEMS_PER_THREAD - 1>::FlagTails(linear_tid, tail_flags, input, flag_op);
}
//@} end member group
};
} // CUB namespace
CUB_NS_POSTFIX // Optional outer namespace(s)
|