gko::matrix::Csr< ValueType, IndexType >::load_balance Class Reference

load_balance is a strategy_type which uses the load balance algorithm. More...

#include <ginkgo/core/matrix/csr.hpp>

Inheritance diagram for gko::matrix::Csr< ValueType, IndexType >::load_balance:

Collaboration diagram for gko::matrix::Csr< ValueType, IndexType >::load_balance:

Public Member Functions
	load_balance ()
	Creates a load_balance strategy. More...
	load_balance (std::shared_ptr< const CudaExecutor > exec)
	Creates a load_balance strategy with CUDA executor. More...
	load_balance (std::shared_ptr< const HipExecutor > exec)
	Creates a load_balance strategy with HIP executor. More...
	load_balance (std::shared_ptr< const DpcppExecutor > exec)
	Creates a load_balance strategy with DPCPP executor. More...
	load_balance (int64_t nwarps, int warp_size=32, bool cuda_strategy=true, std::string strategy_name="none")
	Creates a load_balance strategy with specified parameters. More...
void	process (const array< index_type > &mtx_row_ptrs, array< index_type > *mtx_srow) override
	Computes srow according to row pointers. More...
int64_t	clac_size (const int64_t nnz) override
	Computes the srow size according to the number of nonzeros. More...
std::shared_ptr< strategy_type >	copy () override
	Copy a strategy. More...
Public Member Functions inherited from gko::matrix::Csr< ValueType, IndexType >::strategy_type
	strategy_type (std::string name)
	Creates a strategy_type. More...
std::string	get_name ()
	Returns the name of strategy. More...

Detailed Description

template<typename ValueType = default_precision, typename IndexType = int32>
class gko::matrix::Csr< ValueType, IndexType >::load_balance

load_balance is a strategy_type which uses the load balance algorithm.

Constructor & Destructor Documentation

load_balance() [1/5]

template<typename ValueType = default_precision, typename IndexType = int32>

gko::matrix::Csr< ValueType, IndexType >::load_balance::load_balance ( )

inline

Creates a load_balance strategy.

Warning

this is deprecated! Please rely on the new automatic strategy instantiation or use one of the other constructors.

load_balance() [2/5]

template<typename ValueType = default_precision, typename IndexType = int32>

gko::matrix::Csr< ValueType, IndexType >::load_balance::load_balance ( std::shared_ptr< const CudaExecutor >  exec )

inline

Creates a load_balance strategy with CUDA executor.

Parameters

exec	the CUDA executor

load_balance() [3/5]

template<typename ValueType = default_precision, typename IndexType = int32>

gko::matrix::Csr< ValueType, IndexType >::load_balance::load_balance ( std::shared_ptr< const HipExecutor >  exec )

inline

Creates a load_balance strategy with HIP executor.

Parameters

exec	the HIP executor

load_balance() [4/5]

template<typename ValueType = default_precision, typename IndexType = int32>

gko::matrix::Csr< ValueType, IndexType >::load_balance::load_balance ( std::shared_ptr< const DpcppExecutor >  exec )

inline

Creates a load_balance strategy with DPCPP executor.

Parameters

exec	the DPCPP executor

Note

TODO: porting - we hardcode the subgroup size is 32

load_balance() [5/5]

template<typename ValueType = default_precision, typename IndexType = int32>

gko::matrix::Csr< ValueType, IndexType >::load_balance::load_balance ( int64_t  nwarps, int  warp_size = 32, bool  cuda_strategy = true, std::string  strategy_name = "none"  )

inline

Creates a load_balance strategy with specified parameters.

Parameters

nwarps	the number of warps in the executor
warp_size	the warp size of the executor
cuda_strategy	whether the cuda_strategy needs to be used.

Note

The warp_size must be the size of full warp. When using this constructor, set_strategy needs to be called with correct parameters which is replaced during the conversion.

Member Function Documentation

clac_size()

template<typename ValueType = default_precision, typename IndexType = int32>

int64_t gko::matrix::Csr< ValueType, IndexType >::load_balance::clac_size ( const int64_t  nnz )

inlineoverridevirtual

Computes the srow size according to the number of nonzeros.

Parameters

nnz	the number of nonzeros

Returns

the size of srow

Implements gko::matrix::Csr< ValueType, IndexType >::strategy_type.

References gko::ceildiv(), and gko::min().

copy()

template<typename ValueType = default_precision, typename IndexType = int32>

std::shared_ptr<strategy_type> gko::matrix::Csr< ValueType, IndexType >::load_balance::copy ( )

inlineoverridevirtual

Copy a strategy.

This is a workaround until strategies are revamped, since strategies like automatical do not work when actually shared.

Implements gko::matrix::Csr< ValueType, IndexType >::strategy_type.

process()

template<typename ValueType = default_precision, typename IndexType = int32>

void gko::matrix::Csr< ValueType, IndexType >::load_balance::process ( const array< index_type > &  mtx_row_ptrs, array< index_type > *  mtx_srow  )

inlineoverridevirtual

Computes srow according to row pointers.

Parameters

mtx_row_ptrs	the row pointers of the matrix
mtx_srow	the srow of the matrix

Implements gko::matrix::Csr< ValueType, IndexType >::strategy_type.

References gko::ceildiv(), gko::array< ValueType >::get_const_data(), gko::array< ValueType >::get_data(), gko::array< ValueType >::get_executor(), and gko::array< ValueType >::get_size().

Referenced by gko::matrix::Csr< ValueType, IndexType >::automatical::process().

---

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

• ginkgo/core/matrix/csr.hpp