cudf::hashing Namespace Reference

Hash APIs. More...

Functions
std::unique_ptr< column >	murmurhash3_x86_32 (table_view const &input, uint32_t seed=DEFAULT_HASH_SEED, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Computes the MurmurHash3 32-bit hash value of each row in the given table. More...
std::unique_ptr< table >	murmurhash3_x64_128 (table_view const &input, uint64_t seed=DEFAULT_HASH_SEED, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Computes the MurmurHash3 64-bit hash value of each row in the given table. More...
std::unique_ptr< column >	md5 (table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Computes the MD5 hash value of each row in the given table. More...
std::unique_ptr< column >	sha1 (table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Computes the SHA-1 hash value of each row in the given table. More...
std::unique_ptr< column >	sha224 (table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Computes the SHA-224 hash value of each row in the given table. More...
std::unique_ptr< column >	sha256 (table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Computes the SHA-256 hash value of each row in the given table. More...
std::unique_ptr< column >	sha384 (table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Computes the SHA-384 hash value of each row in the given table. More...
std::unique_ptr< column >	sha512 (table_view const &input, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Computes the SHA-512 hash value of each row in the given table. More...
std::unique_ptr< column >	xxhash_64 (table_view const &input, uint64_t seed=DEFAULT_HASH_SEED, rmm::cuda_stream_view stream=cudf::get_default_stream(), rmm::device_async_resource_ref mr=rmm::mr::get_current_device_resource())
	Computes the XXHash_64 hash value of each row in the given table. More...

Detailed Description

Hash APIs.

Function Documentation

md5()

std::unique_ptr<column> cudf::hashing::md5	(	table_view const &	input,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Computes the MD5 hash value of each row in the given table.

Parameters

input	The table of columns to hash
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns

A column where each row is the hash of a row from the input

murmurhash3_x64_128()

std::unique_ptr<table> cudf::hashing::murmurhash3_x64_128	(	table_view const &	input,
		uint64_t	seed = DEFAULT_HASH_SEED,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Computes the MurmurHash3 64-bit hash value of each row in the given table.

This function takes a 64-bit seed value and returns hash values using the MurmurHash3_x64_128 algorithm. The hash produces in two uint64 values per row.

Parameters

input	The table of columns to hash
seed	Optional seed value to use for the hash function
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns

A table of two UINT64 columns

murmurhash3_x86_32()

std::unique_ptr<column> cudf::hashing::murmurhash3_x86_32	(	table_view const &	input,
		uint32_t	seed = DEFAULT_HASH_SEED,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Computes the MurmurHash3 32-bit hash value of each row in the given table.

This function computes the hash of each column using the seed for the first column and the resulting hash as a seed for the next column and so on. The result is a uint32 value for each row.

Parameters

input	The table of columns to hash
seed	Optional seed value to use for the hash function
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns

A column where each row is the hash of a row from the input

sha1()

std::unique_ptr<column> cudf::hashing::sha1	(	table_view const &	input,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Computes the SHA-1 hash value of each row in the given table.

Parameters

input	The table of columns to hash
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns

A column where each row is the hash of a row from the input

sha224()

std::unique_ptr<column> cudf::hashing::sha224	(	table_view const &	input,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Computes the SHA-224 hash value of each row in the given table.

Parameters

input	The table of columns to hash
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns

A column where each row is the hash of a row from the input

sha256()

std::unique_ptr<column> cudf::hashing::sha256	(	table_view const &	input,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Computes the SHA-256 hash value of each row in the given table.

Parameters

input	The table of columns to hash
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns

A column where each row is the hash of a row from the input

sha384()

std::unique_ptr<column> cudf::hashing::sha384	(	table_view const &	input,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Computes the SHA-384 hash value of each row in the given table.

Parameters

input	The table of columns to hash
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns

A column where each row is the hash of a row from the input

sha512()

std::unique_ptr<column> cudf::hashing::sha512	(	table_view const &	input,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Computes the SHA-512 hash value of each row in the given table.

Parameters

input	The table of columns to hash
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns

A column where each row is the hash of a row from the input

xxhash_64()

std::unique_ptr<column> cudf::hashing::xxhash_64	(	table_view const &	input,
		uint64_t	seed = DEFAULT_HASH_SEED,
		rmm::cuda_stream_view	stream = cudf::get_default_stream(),
		rmm::device_async_resource_ref	mr = rmm::mr::get_current_device_resource()
	)

Computes the XXHash_64 hash value of each row in the given table.

This function takes a 64-bit seed value and returns a column of type UINT64.

Parameters

input	The table of columns to hash
seed	Optional seed value to use for the hash function
stream	CUDA stream used for device memory operations and kernel launches
mr	Device memory resource used to allocate the returned column's device memory

Returns

A column where each row is the hash of a row from the input