distinct_hash_join.hpp

Go to the documentation of this file.

/*
 * SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA CORPORATION.
 * SPDX-License-Identifier: Apache-2.0
 */
 
#pragma once
 
#include <cudf/hashing.hpp>
#include <cudf/table/table_view.hpp>
#include <cudf/types.hpp>
#include <cudf/utilities/default_stream.hpp>
#include <cudf/utilities/export.hpp>
#include <cudf/utilities/memory_resource.hpp>
 
#include <rmm/cuda_stream_view.hpp>
#include <rmm/device_uvector.hpp>
 
#include <utility>
 
namespace CUDF_EXPORT cudf {
 
namespace detail {
class distinct_hash_join;
}  // namespace detail
 
class distinct_hash_join {
 public:
  distinct_hash_join() = delete;
  ~distinct_hash_join();
  distinct_hash_join(distinct_hash_join const&)            = delete;
  distinct_hash_join(distinct_hash_join&&)                 = delete;
  distinct_hash_join& operator=(distinct_hash_join const&) = delete;
  distinct_hash_join& operator=(distinct_hash_join&&)      = delete;
 
  distinct_hash_join(cudf::table_view const& build,
                     null_equality compare_nulls  = null_equality::EQUAL,
                     double load_factor           = 0.5,
                     rmm::cuda_stream_view stream = cudf::get_default_stream());
 
  [[nodiscard]] std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
                          std::unique_ptr<rmm::device_uvector<size_type>>>
  inner_join(cudf::table_view const& probe,
             rmm::cuda_stream_view stream      = cudf::get_default_stream(),
             rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref()) const;
 
  [[nodiscard]] std::unique_ptr<rmm::device_uvector<size_type>> left_join(
    cudf::table_view const& probe,
    rmm::cuda_stream_view stream      = cudf::get_default_stream(),
    rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref()) const;
 
 private:
  using impl_type = cudf::detail::distinct_hash_join;  
 
  std::unique_ptr<impl_type> _impl;  
};
  // end of group
 
}  // namespace CUDF_EXPORT cudf