streaming_hash_join.hpp

Go to the documentation of this file.

/*
 * SPDX-FileCopyrightText: Copyright (c) 2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 * SPDX-License-Identifier: Apache-2.0
 */
 
#pragma once
 
#include <cudf/join/join.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/device_uvector.hpp>
 
#include <cuda/stream_ref>
 
#include <memory>
#include <optional>
#include <span>
#include <utility>
 
namespace CUDF_EXPORT cudf {
 
namespace detail {
class streaming_hash_join_impl;
}  // namespace detail
 
class streaming_hash_join {
 public:
  streaming_hash_join() = delete;
  ~streaming_hash_join();
  streaming_hash_join(streaming_hash_join const&)            = delete;
  streaming_hash_join& operator=(streaming_hash_join const&) = delete;
 
  streaming_hash_join(streaming_hash_join&&) noexcept;
 
  streaming_hash_join& operator=(streaming_hash_join&&) noexcept;
 
  streaming_hash_join(cudf::table_view const& right_schema,
                      std::span<size_type const> right_key_indices,
                      size_type total_right_rows,
                      size_type max_num_batches,
                      nullable_join has_nulls,
                      null_equality compare_nulls,
                      double load_factor        = 0.5,
                      cuda::stream_ref stream   = cudf::get_default_stream(),
                      cudf::memory_resources mr = cudf::get_current_device_resource_ref());
 
  void insert(cudf::table_view const& right_partition,
              cuda::stream_ref stream = cudf::get_default_stream());
 
  [[nodiscard]] cudf::table_view get_partition(size_type batch_id) const;
 
  [[nodiscard]] std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
                          std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
                                    std::unique_ptr<rmm::device_uvector<size_type>>>>
  inner_join(cudf::table_view const& left,
             std::optional<std::size_t> output_size = {},
             cuda::stream_ref stream                = cudf::get_default_stream(),
             cudf::memory_resources mr = cudf::get_current_device_resource_ref()) const;
 
 private:
  std::unique_ptr<cudf::detail::streaming_hash_join_impl> _impl;
};
  // end of group
 
}  // namespace CUDF_EXPORT cudf