The GpuSparseMatrixGeneric class uses cuSPARSE Generic API for sparse matrix operations. More...

#include <GpuSparseMatrixGeneric.hpp>

Inheritance diagram for Opm::gpuistl::GpuSparseMatrixGeneric< T >:

Public Types
using	field_type = T

Public Member Functions
	GpuSparseMatrixGeneric (const T nonZeroElements, const int rowIndices, const int *columnIndices, size_t numberOfNonzeroBlocks, size_t blockSize, size_t numberOfRows)

	GpuSparseMatrixGeneric (const GpuVector< int > &rowIndices, const GpuVector< int > &columnIndices, size_t blockSize)

	GpuSparseMatrixGeneric (const GpuSparseMatrixGeneric &)

void	preprocessSpMV ()
	Preprocess SpMV operation to optimize for sparsity pattern. More...

GpuSparseMatrixGeneric &	operator= (const GpuSparseMatrixGeneric &)=delete

virtual	~GpuSparseMatrixGeneric ()

size_t	N () const
	N returns the number of rows (which is equal to the number of columns) More...

size_t	nonzeroes () const
	nonzeroes behaves as the Dune::BCRSMatrix::nonzeros() function and returns the number of non zero blocks More...

GpuVector< T > &	getNonZeroValues ()
	getNonZeroValues returns the GPU vector containing the non-zero values (ordered by block) More...

const GpuVector< T > &	getNonZeroValues () const
	getNonZeroValues returns the GPU vector containing the non-zero values (ordered by block) More...

GpuVector< int > &	getRowIndices ()
	getRowIndices returns the row indices used to represent the BSR structure. More...

const GpuVector< int > &	getRowIndices () const
	getRowIndices returns the row indices used to represent the BSR structure. More...

GpuVector< int > &	getColumnIndices ()
	getColumnIndices returns the column indices used to represent the BSR structure. More...

const GpuVector< int > &	getColumnIndices () const
	getColumnIndices returns the column indices used to represent the BSR structure. More...

size_t	dim () const
	dim returns the dimension of the vector space on which this matrix acts More...

size_t	blockSize () const
	blockSize size of the blocks More...

virtual void	mv (const GpuVector< T > &x, GpuVector< T > &y) const
	mv performs matrix vector multiply y = Ax More...

virtual void	umv (const GpuVector< T > &x, GpuVector< T > &y) const
	umv computes y=Ax+y More...

virtual void	usmv (T alpha, const GpuVector< T > &x, GpuVector< T > &y) const
	umv computes y=alpha * Ax + y More...

template<class MatrixType >
void	updateNonzeroValues (const MatrixType &matrix, bool copyNonZeroElementsDirectly=false)
	updateNonzeroValues updates the non-zero values by using the non-zero values of the supplied matrix More...

void	updateNonzeroValues (const GpuSparseMatrixGeneric< T > &matrix)
	updateNonzeroValues updates the non-zero values by using the non-zero values of the supplied matrix More...

Static Public Member Functions
template<class MatrixType >
static GpuSparseMatrixGeneric< T >	fromMatrix (const MatrixType &matrix, bool copyNonZeroElementsDirectly=false)
	fromMatrix creates a new matrix with the same block size and values as the given matrix More...

Detailed Description

template<typename T>
class Opm::gpuistl::GpuSparseMatrixGeneric< T >

The GpuSparseMatrixGeneric class uses cuSPARSE Generic API for sparse matrix operations.

Note: We support raw primitives for T (double and float). Block size is handled through the blockSize parameter.

Template Parameters

T	the type to store. Can be either float or double.

Note: we only support square matrices.

Member Typedef Documentation

◆ field_type

template<typename T >

using Opm::gpuistl::GpuSparseMatrixGeneric< T >::field_type = T

Constructor & Destructor Documentation

◆ GpuSparseMatrixGeneric() [1/3]

template<typename T >

Opm::gpuistl::GpuSparseMatrixGeneric< T >::GpuSparseMatrixGeneric	(	const T *	nonZeroElements,
		const int *	rowIndices,
		const int *	columnIndices,
		size_t	numberOfNonzeroBlocks,
		size_t	blockSize,
		size_t	numberOfRows
	)

Create the sparse matrix specified by the raw data.

Parameters

[in]	nonZeroElements	the non-zero values of the matrix
[in]	rowIndices	the row indices of the non-zero elements
[in]	columnIndices	the column indices of the non-zero elements
[in]	numberOfNonzeroBlocks	number of nonzero elements
[in]	blockSize	size of each block matrix (typically 3)
[in]	numberOfRows	the number of rows

◆ GpuSparseMatrixGeneric() [2/3]

template<typename T >

Opm::gpuistl::GpuSparseMatrixGeneric< T >::GpuSparseMatrixGeneric	(	const GpuVector< int > &	rowIndices,
		const GpuVector< int > &	columnIndices,
		size_t	blockSize
	)

Create a sparse matrix by copying the sparsity structure of another matrix, not filling in the values

Parameters

[in]	rowIndices	the row indices of the non-zero elements
[in]	columnIndices	the column indices of the non-zero elements
[in]	blockSize	size of each block matrix (typically 3)

◆ GpuSparseMatrixGeneric() [3/3]

template<typename T >

Opm::gpuistl::GpuSparseMatrixGeneric< T >::GpuSparseMatrixGeneric ( const GpuSparseMatrixGeneric< T > & )

◆ ~GpuSparseMatrixGeneric()

template<typename T >

virtual Opm::gpuistl::GpuSparseMatrixGeneric< T >::~GpuSparseMatrixGeneric ( )

virtual

Member Function Documentation

◆ blockSize()

template<typename T >

size_t Opm::gpuistl::GpuSparseMatrixGeneric< T >::blockSize ( ) const

inline

blockSize size of the blocks

References Opm::gpuistl::detail::to_size_t().

◆ dim()

template<typename T >

size_t Opm::gpuistl::GpuSparseMatrixGeneric< T >::dim ( ) const

inline

dim returns the dimension of the vector space on which this matrix acts

This is equivalent to matrix.N() * matrix.blockSize()

Returns: matrix.N() * matrix.blockSize()

References Opm::gpuistl::detail::to_size_t().

◆ fromMatrix()

template<typename T >

template<class MatrixType >

static GpuSparseMatrixGeneric< T > Opm::gpuistl::GpuSparseMatrixGeneric< T >::fromMatrix	(	const MatrixType &	matrix,
		bool	copyNonZeroElementsDirectly = `false`
	)

static

fromMatrix creates a new matrix with the same block size and values as the given matrix

Parameters

matrix	the matrix to copy from
copyNonZeroElementsDirectly	if true will do a memcpy from matrix[0][0][0][0], otherwise will build up the non-zero elements by looping over the matrix. Note that setting this to true will yield a performance increase, but might not always yield correct results depending on how the matrix has been initialized. If unsure, leave it as false.

Template Parameters

MatrixType is assumed to be a Dune::BCRSMatrix compatible matrix.

◆ getColumnIndices() [1/2]

template<typename T >

GpuVector< int > & Opm::gpuistl::GpuSparseMatrixGeneric< T >::getColumnIndices ( )

inline

getColumnIndices returns the column indices used to represent the BSR structure.

Returns: Read the CuSPARSE documentation on Block Compressed Sparse Row Format (BSR) for the exact ordering.

◆ getColumnIndices() [2/2]

template<typename T >

const GpuVector< int > & Opm::gpuistl::GpuSparseMatrixGeneric< T >::getColumnIndices ( ) const

inline

getColumnIndices returns the column indices used to represent the BSR structure.

Returns: Read the CuSPARSE documentation on Block Compressed Sparse Row Format (BSR) for the exact ordering.

◆ getNonZeroValues() [1/2]

template<typename T >

GpuVector< T > & Opm::gpuistl::GpuSparseMatrixGeneric< T >::getNonZeroValues ( )

inline

getNonZeroValues returns the GPU vector containing the non-zero values (ordered by block)

Note: Read the CuSPARSE documentation on Block Compressed Sparse Row Format (BSR) for the exact ordering.

◆ getNonZeroValues() [2/2]

template<typename T >

const GpuVector< T > & Opm::gpuistl::GpuSparseMatrixGeneric< T >::getNonZeroValues ( ) const

inline

getNonZeroValues returns the GPU vector containing the non-zero values (ordered by block)

Note: Read the CuSPARSE documentation on Block Compressed Sparse Row Format (BSR) for the exact ordering.

◆ getRowIndices() [1/2]

template<typename T >

GpuVector< int > & Opm::gpuistl::GpuSparseMatrixGeneric< T >::getRowIndices ( )

inline

getRowIndices returns the row indices used to represent the BSR structure.

Note: Read the CuSPARSE documentation on Block Compressed Sparse Row Format (BSR) for the exact ordering.

◆ getRowIndices() [2/2]

template<typename T >

const GpuVector< int > & Opm::gpuistl::GpuSparseMatrixGeneric< T >::getRowIndices ( ) const

inline

getRowIndices returns the row indices used to represent the BSR structure.

Note: Read the CuSPARSE documentation on Block Compressed Sparse Row Format (BSR) for the exact ordering.

◆ mv()

template<typename T >

virtual void Opm::gpuistl::GpuSparseMatrixGeneric< T >::mv	(	const GpuVector< T > &	x,
		GpuVector< T > &	y
	)		const

virtual

mv performs matrix vector multiply y = Ax

Parameters

[in]	x	the vector to multiply the matrix with
[out]	y	the output vector

◆ N()

template<typename T >

size_t Opm::gpuistl::GpuSparseMatrixGeneric< T >::N ( ) const

inline

N returns the number of rows (which is equal to the number of columns)

References Opm::gpuistl::detail::to_size_t().

◆ nonzeroes()

template<typename T >

size_t Opm::gpuistl::GpuSparseMatrixGeneric< T >::nonzeroes ( ) const

inline

nonzeroes behaves as the Dune::BCRSMatrix::nonzeros() function and returns the number of non zero blocks

Returns: number of non zero blocks.

References Opm::gpuistl::detail::to_size_t().

◆ operator=()

template<typename T >

GpuSparseMatrixGeneric & Opm::gpuistl::GpuSparseMatrixGeneric< T >::operator= ( const GpuSparseMatrixGeneric< T > & )

delete

◆ preprocessSpMV()

template<typename T >

void Opm::gpuistl::GpuSparseMatrixGeneric< T >::preprocessSpMV ( )

Preprocess SpMV operation to optimize for sparsity pattern.

This function preprocesses the sparsity pattern of the matrix to optimize for the SpMV operation.

◆ umv()

template<typename T >

virtual void Opm::gpuistl::GpuSparseMatrixGeneric< T >::umv	(	const GpuVector< T > &	x,
		GpuVector< T > &	y
	)		const

virtual

umv computes y=Ax+y

Parameters

[in]	x	the vector to multiply with A
[in,out]	y	the vector to add and store the output in

◆ updateNonzeroValues() [1/2]

template<typename T >

void Opm::gpuistl::GpuSparseMatrixGeneric< T >::updateNonzeroValues ( const GpuSparseMatrixGeneric< T > & matrix )

updateNonzeroValues updates the non-zero values by using the non-zero values of the supplied matrix

Parameters

matrix the matrix to extract the non-zero values from

Note: This assumes the given matrix has the same sparsity pattern.

◆ updateNonzeroValues() [2/2]

template<typename T >

template<class MatrixType >

void Opm::gpuistl::GpuSparseMatrixGeneric< T >::updateNonzeroValues	(	const MatrixType &	matrix,
		bool	copyNonZeroElementsDirectly = `false`
	)

updateNonzeroValues updates the non-zero values by using the non-zero values of the supplied matrix

Parameters

matrix	the matrix to extract the non-zero values from
copyNonZeroElementsDirectly	if true will do a memcpy from matrix[0][0][0][0], otherwise will build up the non-zero elements by looping over the matrix. Note that setting this to true will yield a performance increase, but might not always yield correct results depending on how the matrix matrix has been initialized. If unsure, leave it as false.

Note: This assumes the given matrix has the same sparsity pattern.

Template Parameters

MatrixType is assumed to be a Dune::BCRSMatrix compatible matrix.

◆ usmv()

template<typename T >

virtual void Opm::gpuistl::GpuSparseMatrixGeneric< T >::usmv	(	T	alpha,
		const GpuVector< T > &	x,
		GpuVector< T > &	y
	)		const

virtual

umv computes y=alpha * Ax + y

Parameters

[in]	alpha	The scaling factor for the matrix-vector product
[in]	x	the vector to multiply with A
[in,out]	y	the vector to add and store the output in

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

Public Types

Public Member Functions

Static Public Member Functions

Detailed Description

Member Typedef Documentation

◆ field_type

Constructor & Destructor Documentation

◆ GpuSparseMatrixGeneric() [1/3]

◆ GpuSparseMatrixGeneric() [2/3]

◆ GpuSparseMatrixGeneric() [3/3]

◆ ~GpuSparseMatrixGeneric()

Member Function Documentation

◆ blockSize()

◆ dim()

◆ fromMatrix()

◆ getColumnIndices() [1/2]

◆ getColumnIndices() [2/2]

◆ getNonZeroValues() [1/2]

◆ getNonZeroValues() [2/2]

◆ getRowIndices() [1/2]

◆ getRowIndices() [2/2]

◆ mv()

◆ N()

◆ nonzeroes()

◆ operator=()

◆ preprocessSpMV()

◆ umv()

◆ updateNonzeroValues() [1/2]

◆ updateNonzeroValues() [2/2]

◆ usmv()