join.hpp

转到此文件的文档。

/*
 * Copyright (c) 2019-2025, NVIDIA CORPORATION.
 *
 * Licensed under the Apache License, Version 2.0 (the "License");
 * you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at
 *
 * https://apache.ac.cn/licenses/LICENSE-2.0
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */

#pragma once

#include <cudf/ast/expressions.hpp>
#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 <cudf/utilities/span.hpp>

#include <rmm/cuda_stream_view.hpp>
#include <rmm/device_uvector.hpp>

#include <optional>
#include <utility>
#include <vector>

namespace CUDF_EXPORT cudf {

// forward declaration
namespace hashing::detail {

template <typename T>
class MurmurHash3_x86_32;
} // namespace hashing::detail
namespace detail {

template <typename T>
class hash_join;

class distinct_hash_join;
} // namespace detail

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_keys,
 cudf::table_view const& right_keys,
 null_equality compare_nulls = null_equality::EQUAL,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
 std::unique_ptr<rmm::device_uvector<size_type>>>
left_join(cudf::table_view const& left_keys,
 cudf::table_view const& right_keys,
 null_equality compare_nulls = null_equality::EQUAL,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
 std::unique_ptr<rmm::device_uvector<size_type>>>
full_join(cudf::table_view const& left_keys,
 cudf::table_view const& right_keys,
 null_equality compare_nulls = null_equality::EQUAL,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::unique_ptr<rmm::device_uvector<size_type>> left_semi_join(
 cudf::table_view const& left_keys,
 cudf::table_view const& right_keys,
 null_equality compare_nulls = null_equality::EQUAL,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::unique_ptr<rmm::device_uvector<size_type>> left_anti_join(
 cudf::table_view const& left_keys,
 cudf::table_view const& right_keys,
 null_equality compare_nulls = null_equality::EQUAL,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::unique_ptr<cudf::table> cross_join(
 cudf::table_view const& left,
 cudf::table_view const& right,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

enum class nullable_join : bool { YES, NO };

class hash_join {
 public
 using impl_type = typename cudf::detail::hash_join<
 cudf::hashing::detail::MurmurHash3_x86_32<cudf::hash_value_type>>;

 hash_join() = delete;
 ~hash_join();
 hash_join(hash_join const&) = delete;
 hash_join(hash_join&&) = delete;
 hash_join& operator=(hash_join const&) = delete;
 hash_join& operator=(hash_join&&) = delete;

 hash_join(cudf::table_view const& build,
 null_equality compare_nulls,
 rmm::cuda_stream_view stream = cudf::get_default_stream());

 hash_join(cudf::table_view const& build,
 nullable_join has_nulls,
 null_equality compare_nulls,
 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,
 std::optional<std::size_t> output_size = {},
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref()) const;

 [[nodiscard]] std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
 std::unique_ptr<rmm::device_uvector<size_type>>>
 left_join(cudf::table_view const& probe,
 std::optional<std::size_t> output_size = {},
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref()) const;

 [[nodiscard]] std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
 std::unique_ptr<rmm::device_uvector<size_type>>>
 full_join(cudf::table_view const& probe,
 std::optional<std::size_t> output_size = {},
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref()) const;

 [[nodiscard]] std::size_t inner_join_size(
 cudf::table_view const& probe, rmm::cuda_stream_view stream = cudf::get_default_stream()) const;

 [[nodiscard]] std::size_t left_join_size(
 cudf::table_view const& probe, rmm::cuda_stream_view stream = cudf::get_default_stream()) const;

 [[nodiscard]] std::size_t full_join_size(
 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
 std::unique_ptr<impl_type const> _impl;
};

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,
 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;
};

std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
 std::unique_ptr<rmm::device_uvector<size_type>>>
conditional_inner_join(table_view const& left,
 table_view const& right,
 ast::expression const& binary_predicate,
 std::optional<std::size_t> output_size = {},
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
 std::unique_ptr<rmm::device_uvector<size_type>>>
conditional_left_join(table_view const& left,
 table_view const& right,
 ast::expression const& binary_predicate,
 std::optional<std::size_t> output_size = {},
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
 std::unique_ptr<rmm::device_uvector<size_type>>>
conditional_full_join(table_view const& left,
 table_view const& right,
 ast::expression const& binary_predicate,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::unique_ptr<rmm::device_uvector<size_type>> conditional_left_semi_join(
 table_view const& left,
 table_view const& right,
 ast::expression const& binary_predicate,
 std::optional<std::size_t> output_size = {},
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::unique_ptr<rmm::device_uvector<size_type>> conditional_left_anti_join(
 table_view const& left,
 table_view const& right,
 ast::expression const& binary_predicate,
 std::optional<std::size_t> output_size = {},
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
 std::unique_ptr<rmm::device_uvector<size_type>>>
mixed_inner_join(
 table_view const& left_equality,
 table_view const& right_equality,
 table_view const& left_conditional,
 table_view const& right_conditional,
 ast::expression const& binary_predicate,
 null_equality compare_nulls = null_equality::EQUAL,
 std::optional<std::pair<std::size_t, device_span<size_type const>>> output_size_data = {},
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
 std::unique_ptr<rmm::device_uvector<size_type>>>
mixed_left_join(
 table_view const& left_equality,
 table_view const& right_equality,
 table_view const& left_conditional,
 table_view const& right_conditional,
 ast::expression const& binary_predicate,
 null_equality compare_nulls = null_equality::EQUAL,
 std::optional<std::pair<std::size_t, device_span<size_type const>>> output_size_data = {},
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::pair<std::unique_ptr<rmm::device_uvector<size_type>>,
 std::unique_ptr<rmm::device_uvector<size_type>>>
mixed_full_join(
 table_view const& left_equality,
 table_view const& right_equality,
 table_view const& left_conditional,
 table_view const& right_conditional,
 ast::expression const& binary_predicate,
 null_equality compare_nulls = null_equality::EQUAL,
 std::optional<std::pair<std::size_t, device_span<size_type const>>> output_size_data = {},
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::unique_ptr<rmm::device_uvector<size_type>> mixed_left_semi_join(
 table_view const& left_equality,
 table_view const& right_equality,
 table_view const& left_conditional,
 table_view const& right_conditional,
 ast::expression const& binary_predicate,
 null_equality compare_nulls = null_equality::EQUAL,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::unique_ptr<rmm::device_uvector<size_type>> mixed_left_anti_join(
 table_view const& left_equality,
 table_view const& right_equality,
 table_view const& left_conditional,
 table_view const& right_conditional,
 ast::expression const& binary_predicate,
 null_equality compare_nulls = null_equality::EQUAL,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::pair<std::size_t, std::unique_ptr<rmm::device_uvector<size_type>>> mixed_inner_join_size(
 table_view const& left_equality,
 table_view const& right_equality,
 table_view const& left_conditional,
 table_view const& right_conditional,
 ast::expression const& binary_predicate,
 null_equality compare_nulls = null_equality::EQUAL,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::pair<std::size_t, std::unique_ptr<rmm::device_uvector<size_type>>> mixed_left_join_size(
 table_view const& left_equality,
 table_view const& right_equality,
 table_view const& left_conditional,
 table_view const& right_conditional,
 ast::expression const& binary_predicate,
 null_equality compare_nulls = null_equality::EQUAL,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::size_t conditional_inner_join_size(
 table_view const& left,
 table_view const& right,
 ast::expression const& binary_predicate,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::size_t conditional_left_join_size(
 table_view const& left,
 table_view const& right,
 ast::expression const& binary_predicate,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::size_t conditional_left_semi_join_size(
 table_view const& left,
 table_view const& right,
 ast::expression const& binary_predicate,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());

std::size_t conditional_left_anti_join_size(
 table_view const& left,
 table_view const& right,
 ast::expression const& binary_predicate,
 rmm::cuda_stream_view stream = cudf::get_default_stream(),
 rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref()); // end of group
} // namespace CUDF_EXPORT cudf