cudf::hash_join Class Reference

Hash join that builds a hash table with the right table on construction and probes results in subsequent *_join member functions. More...

#include <hash_join.hpp>

Public Types
using	impl_type = typename cudf::detail::hash_join< cudf::hashing::detail::MurmurHash3_x86_32< cudf::hash_value_type > >
	Implementation type.

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 &right, null_equality compare_nulls, rmm::cuda_stream_view stream=cudf::get_default_stream())
	Construct a hash join object for subsequent probe calls. More...
	hash_join (cudf::table_view const &right, nullable_join has_nulls, null_equality compare_nulls, double load_factor, rmm::cuda_stream_view stream=cudf::get_default_stream())
	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 &left, 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
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, 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
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, 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
std::size_t	inner_join_size (cudf::table_view const &left, rmm::cuda_stream_view stream=cudf::get_default_stream()) const
std::size_t	left_join_size (cudf::table_view const &left, rmm::cuda_stream_view stream=cudf::get_default_stream()) const
std::size_t	full_join_size (cudf::table_view const &left, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref()) const
cudf::join_match_context	inner_join_match_context (cudf::table_view const &left, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref()) const
	Returns context information about matches between the left and right tables. More...
cudf::join_match_context	left_join_match_context (cudf::table_view const &left, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref()) const
	Returns context information about matches between the left and right tables. More...
cudf::join_match_context	full_join_match_context (cudf::table_view const &left, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=cudf::get_current_device_resource_ref()) const
	Returns context information about matches between the left and right tables. More...

Detailed Description

Hash join that builds a hash table with the right table on construction and probes results in subsequent *_join member functions.

This class enables the hash join scheme that builds with the right table once and probes with many left tables (possibly in parallel).

Definition at line 64 of file hash_join.hpp.

Constructor & Destructor Documentation

hash_join() [1/2]

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

Construct a hash join object for subsequent probe calls.

Note

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

Exceptions

std::invalid_argument

if the right table has no columns

Parameters

right	The right 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

hash_join() [2/2]

cudf::hash_join::hash_join	(	cudf::table_view const &	right,
		nullable_join	has_nulls,
		null_equality	compare_nulls,
		double	load_factor,
		rmm::cuda_stream_view	stream = cudf::get_default_stream()
	)

Construct a hash join object for subsequent probe calls.

Note

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

Exceptions

std::invalid_argument

if the right table has no columns

Parameters

right	The right 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

Exceptions

std::invalid_argument

if load_factor is not greater than 0 and less than or equal to 1

Parameters

has_nulls	Flag to indicate if there exists any nulls in the right table or any left table that will be used later for join
load_factor	The hash table occupancy ratio in (0,1]. A value of 0.5 means 50% desired occupancy.

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 &	left,
		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

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.

Exceptions

std::invalid_argument

If the input left table has nulls while this hash_join object was not constructed with null check.

Parameters

left	The left 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 left and right as the join keys .

full_join_match_context()

cudf::join_match_context cudf::hash_join::full_join_match_context	(	cudf::table_view const &	left,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = cudf::get_current_device_resource_ref()
	)		const

Returns context information about matches between the left and right tables.

This method computes, for each row in the left table, how many matching rows exist in the right table according to full join semantics, and returns the number of matches through a join_match_context object.

For full join, this includes matches for left table rows, and the result may need to be combined with unmatched rows from the right table to get the complete picture.

Exceptions

std::invalid_argument

If the input left table has nulls while this hash_join object was not constructed with null check.

Parameters

left	The left table to join with the pre-processed right table
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the result device memory

Returns

A join_match_context object containing the left table view and a device vector of match counts for each row in the left table

full_join_size()

std::size_t cudf::hash_join::full_join_size	(	cudf::table_view const &	left,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = cudf::get_current_device_resource_ref()
	)		const

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

Exceptions

std::invalid_argument

If the input left table has nulls while this hash_join object was not constructed with null check.

Parameters

left	The left 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 left and right as 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 &	left,
		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

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.

Exceptions

std::invalid_argument

If the input left table has nulls while this hash_join object was not constructed with null check.

Parameters

left	The left 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 left and right as the join keys .

inner_join_match_context()

cudf::join_match_context cudf::hash_join::inner_join_match_context	(	cudf::table_view const &	left,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = cudf::get_current_device_resource_ref()
	)		const

Returns context information about matches between the left and right tables.

This method computes, for each row in the left table, how many matching rows exist in the right table according to inner join semantics, and returns the number of matches through a join_match_context object.

This is particularly useful for:

• Determining the total size of a potential join result without materializing it
• Planning partitioned join operations for large datasets

Exceptions

std::invalid_argument

If the input left table has nulls while this hash_join object was not constructed with null check.

Parameters

left	The left table to join with the pre-processed right table
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the result device memory

Returns

A join_match_context object containing the left table view and a device vector of match counts for each row in the left table

inner_join_size()

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

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

Exceptions

std::invalid_argument

If the input left table has nulls while this hash_join object was not constructed with null check.

Parameters

left	The left 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 left and right as 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 &	left,
		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

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.

Exceptions

std::invalid_argument

If the input left table has nulls while this hash_join object was not constructed with null check.

Parameters

left	The left 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 left and right as the join keys.

left_join_match_context()

cudf::join_match_context cudf::hash_join::left_join_match_context	(	cudf::table_view const &	left,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = cudf::get_current_device_resource_ref()
	)		const

Returns context information about matches between the left and right tables.

This method computes, for each row in the left table, how many matching rows exist in the right table according to left join semantics, and returns the number of matches through a join_match_context object.

For left join, every row in the left table will have at least one match (either with a matching row from the right table or with a null placeholder).

Exceptions

std::invalid_argument

If the input left table has nulls while this hash_join object was not constructed with null check.

Parameters

left	The left table to join with the pre-processed right table
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the result device memory

Returns

A join_match_context object containing the left table view and a device vector of match counts for each row in the left table

left_join_size()

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

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

Exceptions

std::invalid_argument

If the input left table has nulls while this hash_join object was not constructed with null check.

Parameters

left	The left 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 left and right as the join keys .

---

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

• hash_join.hpp