cudf::hash_join Class Reference

Hash join that builds hash table in creation and probes results in subsequent *_join member functions. More...

#include <join.hpp>

Public Member Functions
	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=rmm::cuda_stream_default)
	Construct a hash join object for subsequent probe calls. More...
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=rmm::cuda_stream_default, rmm::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource()) const
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=rmm::cuda_stream_default, rmm::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource()) const
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=rmm::cuda_stream_default, rmm::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource()) const
std::size_t	inner_join_size (cudf::table_view const &probe, rmm::cuda_stream_view stream=rmm::cuda_stream_default) const
std::size_t	left_join_size (cudf::table_view const &probe, rmm::cuda_stream_view stream=rmm::cuda_stream_default) const
std::size_t	full_join_size (cudf::table_view const &probe, rmm::cuda_stream_view stream=rmm::cuda_stream_default, rmm::mr::device_memory_resource *mr=rmm::mr::get_current_device_resource()) const

Detailed Description

Hash join that builds hash table in creation and probes results in subsequent *_join member functions.

This class enables the hash join scheme that builds hash table once, and probes as many times as needed (possibly in parallel).

Definition at line 504 of file join.hpp.

Constructor & Destructor Documentation

hash_join()

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

Construct a hash join object for subsequent probe calls.

Note

The hash_join object must not outlive the table viewed by build, else behavior is undefined.

Parameters

build	The build table, from which the hash table is built.
compare_nulls	Controls whether null join-key values should match or not.
stream	CUDA stream used for device memory operations and kernel launches

Member Function Documentation

full_join()

std::pair<std::unique_ptr<rmm::device_uvector<size_type> >, std::unique_ptr<rmm::device_uvector<size_type> > > cudf::hash_join::full_join	(	cudf::table_view const &	probe,
		std::optional< std::size_t >	output_size = {},
		rmm::cuda_stream_view	stream = rmm::cuda_stream_default,
		rmm::mr::device_memory_resource *	mr = rmm::mr::get_current_device_resource()
	)		const

Returns the row indices that can be used to construct the result of performing a full join between two tables.

See also

cudf::full_join(). Behavior is undefined if the provided output_size is smaller than the actual output size.

Parameters

probe	The probe table, from which the tuples are probed.
output_size	Optional value which allows users to specify the exact output size.
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned table and columns' device memory.

Returns

A pair of columns [left_indices, right_indices] that can be used to construct the result of performing a full join between two tables with build and probe as the the join keys .

full_join_size()

std::size_t cudf::hash_join::full_join_size	(	cudf::table_view const &	probe,
		rmm::cuda_stream_view	stream = rmm::cuda_stream_default,
		rmm::mr::device_memory_resource *	mr = rmm::mr::get_current_device_resource()
	)		const

Returns the exact number of matches (rows) when performing a full join with the specified probe table.

Parameters

probe	The probe table, from which the tuples are probed.
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the intermediate table and columns' device memory.

Returns

The exact number of output when performing a full join between two tables with build and probe as the the join keys .

inner_join()

std::pair<std::unique_ptr<rmm::device_uvector<size_type> >, std::unique_ptr<rmm::device_uvector<size_type> > > cudf::hash_join::inner_join	(	cudf::table_view const &	probe,
		std::optional< std::size_t >	output_size = {},
		rmm::cuda_stream_view	stream = rmm::cuda_stream_default,
		rmm::mr::device_memory_resource *	mr = rmm::mr::get_current_device_resource()
	)		const

Returns the row indices that can be used to construct the result of performing an inner join between two tables.

See also

cudf::inner_join(). Behavior is undefined if the provided output_size is smaller than the actual output size.

Parameters

probe	The probe table, from which the tuples are probed.
output_size	Optional value which allows users to specify the exact output size.
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned table and columns' device memory.

Returns

A pair of columns [left_indices, right_indices] that can be used to construct the result of performing an inner join between two tables with build and probe as the the join keys .

inner_join_size()

std::size_t cudf::hash_join::inner_join_size	(	cudf::table_view const &	probe,
		rmm::cuda_stream_view	stream = rmm::cuda_stream_default
	)		const

Returns the exact number of matches (rows) when performing an inner join with the specified probe table.

Parameters

probe	The probe table, from which the tuples are probed.
stream	CUDA stream used for device memory operations and kernel launches

Returns

The exact number of output when performing an inner join between two tables with build and probe as the the join keys .

left_join()

std::pair<std::unique_ptr<rmm::device_uvector<size_type> >, std::unique_ptr<rmm::device_uvector<size_type> > > cudf::hash_join::left_join	(	cudf::table_view const &	probe,
		std::optional< std::size_t >	output_size = {},
		rmm::cuda_stream_view	stream = rmm::cuda_stream_default,
		rmm::mr::device_memory_resource *	mr = rmm::mr::get_current_device_resource()
	)		const

Returns the row indices that can be used to construct the result of performing a left join between two tables.

See also

cudf::left_join(). Behavior is undefined if the provided output_size is smaller than the actual output size.

Parameters

probe	The probe table, from which the tuples are probed.
output_size	Optional value which allows users to specify the exact output size.
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned table and columns' device memory.

Returns

A pair of columns [left_indices, right_indices] that can be used to construct the result of performing a left join between two tables with build and probe as the the join keys .

left_join_size()

std::size_t cudf::hash_join::left_join_size	(	cudf::table_view const &	probe,
		rmm::cuda_stream_view	stream = rmm::cuda_stream_default
	)		const

Returns the exact number of matches (rows) when performing a left join with the specified probe table.

Parameters

probe	The probe table, from which the tuples are probed.
stream	CUDA stream used for device memory operations and kernel launches

Returns

The exact number of output when performing a left join between two tables with build and probe as the the join keys .

---

The documentation for this class was generated from the following file:

• join.hpp