cub/warp/warp_merge_sort.cuh

File members: cub/warp/warp_merge_sort.cuh

/******************************************************************************
 * Copyright (c) 2011-2021, 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.
 *
 ******************************************************************************/

#pragma once

#include <cub/config.cuh>

#if defined(_CCCL_IMPLICIT_SYSTEM_HEADER_GCC)
#  pragma GCC system_header
#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_CLANG)
#  pragma clang system_header
#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_MSVC)
#  pragma system_header
#endif // no system header

#include <cub/block/block_merge_sort.cuh>
#include <cub/util_ptx.cuh>
#include <cub/util_type.cuh>

#include <cuda/std/type_traits>

CUB_NAMESPACE_BEGIN

template <typename KeyT,
          int ITEMS_PER_THREAD,
          int LOGICAL_WARP_THREADS = CUB_WARP_THREADS(0),
          typename ValueT          = NullType,
          int LEGACY_PTX_ARCH      = 0>
class WarpMergeSort
    : public BlockMergeSortStrategy<KeyT,
                                    ValueT,
                                    LOGICAL_WARP_THREADS,
                                    ITEMS_PER_THREAD,
                                    WarpMergeSort<KeyT, ITEMS_PER_THREAD, LOGICAL_WARP_THREADS, ValueT>>
{
private:
  static constexpr bool IS_ARCH_WARP = LOGICAL_WARP_THREADS == CUB_WARP_THREADS(0);
  static constexpr bool KEYS_ONLY    = ::cuda::std::is_same<ValueT, NullType>::value;
  static constexpr int TILE_SIZE     = ITEMS_PER_THREAD * LOGICAL_WARP_THREADS;

  using BlockMergeSortStrategyT =
    BlockMergeSortStrategy<KeyT, ValueT, LOGICAL_WARP_THREADS, ITEMS_PER_THREAD, WarpMergeSort>;

  const unsigned int warp_id;
  const unsigned int member_mask;

public:
  WarpMergeSort() = delete;

  _CCCL_DEVICE _CCCL_FORCEINLINE WarpMergeSort(typename BlockMergeSortStrategyT::TempStorage& temp_storage)
      : BlockMergeSortStrategyT(temp_storage, IS_ARCH_WARP ? LaneId() : (LaneId() % LOGICAL_WARP_THREADS))
      , warp_id(IS_ARCH_WARP ? 0 : (LaneId() / LOGICAL_WARP_THREADS))
      , member_mask(WarpMask<LOGICAL_WARP_THREADS>(warp_id))
  {}

  _CCCL_DEVICE _CCCL_FORCEINLINE unsigned int get_member_mask() const
  {
    return member_mask;
  }

private:
  _CCCL_DEVICE _CCCL_FORCEINLINE void SyncImplementation() const
  {
    WARP_SYNC(member_mask);
  }

  friend BlockMergeSortStrategyT;
};

CUB_NAMESPACE_END