cub/device/device_memcpy.cuh

File members: cub/device/device_memcpy.cuh

/******************************************************************************
 * Copyright (c) 2011-2022, 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/detail/nvtx.cuh>
#include <cub/device/dispatch/dispatch_batch_memcpy.cuh>

#include <cstdint>
#include <type_traits>

CUB_NAMESPACE_BEGIN

struct DeviceMemcpy
{
  template <typename InputBufferIt, typename OutputBufferIt, typename BufferSizeIteratorT>
  CUB_RUNTIME_FUNCTION static cudaError_t Batched(
    void* d_temp_storage,
    size_t& temp_storage_bytes,
    InputBufferIt input_buffer_it,
    OutputBufferIt output_buffer_it,
    BufferSizeIteratorT buffer_sizes,
    uint32_t num_buffers,
    cudaStream_t stream = 0)
  {
    CUB_DETAIL_NVTX_RANGE_SCOPE_IF(d_temp_storage, "cub::DeviceMemcpy::Batched");
    static_assert(std::is_pointer<cub::detail::value_t<InputBufferIt>>::value,
                  "DeviceMemcpy::Batched only supports copying of memory buffers."
                  "Please consider using DeviceCopy::Batched instead.");
    static_assert(std::is_pointer<cub::detail::value_t<OutputBufferIt>>::value,
                  "DeviceMemcpy::Batched only supports copying of memory buffers."
                  "Please consider using DeviceCopy::Batched instead.");

    // Integer type large enough to hold any offset in [0, num_buffers)
    using BufferOffsetT = uint32_t;

    // Integer type large enough to hold any offset in [0, num_thread_blocks_launched), where a safe
    // upper bound on num_thread_blocks_launched can be assumed to be given by
    // IDIV_CEIL(num_buffers, 64)
    using BlockOffsetT = uint32_t;

    return detail::DispatchBatchMemcpy<
      InputBufferIt,
      OutputBufferIt,
      BufferSizeIteratorT,
      BufferOffsetT,
      BlockOffsetT,
      detail::batch_memcpy::policy_hub<BufferOffsetT, BlockOffsetT>,
      true>::Dispatch(d_temp_storage,
                      temp_storage_bytes,
                      input_buffer_it,
                      output_buffer_it,
                      buffer_sizes,
                      num_buffers,
                      stream);
  }
};

CUB_NAMESPACE_END