lama::JDSSparseMatrix< T > Class Template Reference

Definition of a derived class for SparseMatrix that uses the JDS storage format for the local and halo data of the distributed sparse matrix. More...

#include <JDSSparseMatrix.hpp>

Inheritance diagram for lama::JDSSparseMatrix< T >:

Public Types
typedef T	ValueType
	type definition of the value type.
typedef JDSStorage< T >	StorageType
enum	SyncKind { ASYNCHRONOUS, SYNCHRONOUS }
	SyncKind describes if the communication and computation should be done synchronously or asynchronously. More...
enum	MatrixKind { DENSE, SPARSE }
	MatrixKind describes if a matrix is dense or sparse. More...
typedef const Matrix &	ExpressionMemberType
	ExpressionMemberType is the type that is used the template Expression to store a Vector.
Public Member Functions
	JDSSparseMatrix ()
	Default constructor, creates a replicated matrix of size 0 x 0.
	JDSSparseMatrix (const IndexType numRows, const IndexType numColumns)
	Constructor, creates a replicated zero-matrix of size numRows x numColums.
	JDSSparseMatrix (DistributionPtr rowDist, DistributionPtr colDist)
	Constructor, creates a distributed zero-matrix by given row and column distribution.
	JDSSparseMatrix (const Matrix &other, bool transposeFlag=false)
	JDSSparseMatrix (const Matrix &other, DistributionPtr rowDist, DistributionPtr colDist)
	JDSSparseMatrix (const _MatrixStorage &localData, DistributionPtr rowDist, DistributionPtr colDist)
	Constructor of a sparse matrix by local storage.
	JDSSparseMatrix (const std::string &filename)
	Constructor of a replicated sparse matrix by reading the matrix data from a file.
	JDSSparseMatrix (const Expression< Matrix, Matrix, Times > &expression)
	JDSSparseMatrix (const Expression< Scalar, Matrix, Times > &expression)
	JDSSparseMatrix (const Expression< Scalar, Expression< Matrix, Matrix, Times >, Times > &expression)
template<typename LocalValueType , typename HaloValueType >
	JDSSparseMatrix (const IndexType numLocalRows, const IndexType numLocalNonZeros, const IndexType numHaloNonZeros, const IndexType localIA[], const IndexType localJA[], const LocalValueType localValues[], const IndexType haloIA[], const IndexType haloJA[], const HaloValueType haloValues[], const std::vector< IndexType > &ownedIndexes, const CommunicatorPtr communicator)
	Constructor of a JDS sparse matrix with distributed JDS storage data.
virtual const StorageType &	getLocalStorage () const
	Override MatrixStorage<ValueType>::getLocalStorage with covariant return type.
virtual StorageType &	getLocalStorage ()
virtual const StorageType &	getHaloStorage () const
	Override MatrixStorage<ValueType>::getHaloStorage with covariant return type.
virtual void	swapLocalStorage (StorageType &localStorage)
	Swap local storage data, allows consistent write access to local storage.
virtual const char *	getTypeName () const
	Override Matrix::getTypeName with correct method.
template<>
const char *	typeName ()
	Getter for the type name of the class.
template<>
const char *	typeName ()
	Getter for the type name of the class.
virtual void	invert (const Matrix &other)
	Implementation of Matrix::invert for sparse matrices.
virtual void	setContext (const ContextPtr context)
	specifies on which compute back end the matrix operations should take place.
virtual void	setContext (const ContextPtr localContext, const ContextPtr haloContext)
	Only sparse matrices will override this method, others will ignore second argument.
virtual ContextPtr	getContextPtr () const
	Getter routine for the context.
virtual const Context &	getContext () const
template<typename OtherValueType >
void	setRawDenseData (const IndexType numRows, const IndexType numColumns, const OtherValueType values[], const OtherValueType eps=0.0)
	Set sparse matrix with global dense data.
virtual void	clear ()
	Implementation of pure method.
virtual void	allocate (const IndexType numRows, const IndexType numColumns)
	Implementation of pure method of class Matrix.
virtual void	allocate (DistributionPtr distribution, DistributionPtr colDistribution)
	Implementation of pure method of class Matrix.
virtual void	setIdentity ()
	Implementation of pure method of class Matrix.
virtual void	assign (const Matrix &other)
	Implementation of pure method of class Matrix.
void	assign (const _SparseMatrix &matrix)
	Method that assigns a sparse matrix, specialization of assign( const Matrix& )
void	assign (const _MatrixStorage &other)
	Setting (distributed) matrix with any global matrix storage.
void	assign (const _MatrixStorage &storage, DistributionPtr rowDist, DistributionPtr colDist)
	Setting (distributed) matrix with any local matrix data.
virtual void	buildLocalStorage (_MatrixStorage &storage) const
	Implementation of Matrix::buildLocalStorage.
void	swap (SparseMatrix< ValueType > &other)
	Swap will swap all member variables of the two sparse matrices.
virtual void	getDiagonal (Vector &diagonal) const
	This method returns the diagonal.
virtual void	getRow (Vector &row, const IndexType globalRowIndex) const
	This method returns one row of the matrix.
virtual void	setDiagonal (const Vector &diagonal)
	This method replaces the diagonal.
virtual void	setDiagonal (const Scalar scalar)
	This method replaces the diagonal by a diagonal value.
virtual void	scale (const Vector &scaling)
	This method scales all values with a vector.
virtual void	scale (const Scalar scaling)
	This method scales all matrix values with a scalar.
virtual void	matrixTimesScalar (const Matrix &other, const Scalar alpha)
	Set local data of the matrix.
void	matrixTimesVectorImpl (DenseVector< ValueType > &result, const ValueType alpha, const DenseVector< ValueType > &x, const ValueType beta, const DenseVector< ValueType > &y) const
virtual void	matrixTimesVectorNImpl (DenseMatrix< ValueType > &result, const ValueType alpha, const DenseMatrix< ValueType > &x, const ValueType beta, const DenseMatrix< ValueType > &y) const
	matrix times matrix for multiple dense vectors.
virtual void	matrixTimesVector (Vector &result, const Scalar alpha, const Vector &x, const Scalar beta, const Vector &y) const
	matrixTimesVector computes result = alpha * this * x + beta * y
virtual void	matrixTimesMatrix (Matrix &result, const Scalar alpha, const Matrix &B, const Scalar beta, const Matrix &C) const
	Implemenation of abstract method Matrix::matrixTimesMatrix.
Scalar	maxDiffNorm (const Matrix &other) const
	Implementation of Matrix::maxDiffNorm for sparse matrices.
ValueType	maxDiffNormImpl (const SparseMatrix< ValueType > &other) const
	Get the maximal difference between two elements for sparse matrices of same type.
IndexType	getLocalNumValues () const
	Getter routine for the number of locally stored values.
IndexType	getLocalNumRows () const
	Getter routine for the local number of rows.
IndexType	getLocalNumColumns () const
	Getter routine for the local number of rows and columns.
virtual IndexType	getNumValues () const
	Get the total number of non-zero values in the matrix.
IndexType	getPartitialNumValues () const
Scalar	getValue (IndexType i, IndexType j) const
	returns a copy of the value at the passed global indexes.
const Halo &	getHalo () const
	Read access to the halo of the distributed matrix.
virtual void	writeAt (std::ostream &stream) const
	Write some information about this to the passed stream.
virtual void	prefetch () const
	Prefetch matrix data to its 'preferred' context location.
virtual void	wait () const
	wait for a possibly running prefetch.
virtual void	setComputeKind (SyncKind computeKind)
	set the compute kind.
virtual bool	hasDiagonalProperty () const
	hasDiagonalProperty returns the diagonalProperty of the local storage.
virtual void	resetDiagonalProperty ()
	resetDiagonalProperty rechecks the storages for their diagonal property
virtual Scalar::ScalarType	getValueType () const
	Query the value type of the matrix elements, e.g.
virtual std::auto_ptr< Matrix >	create () const
	Constructor function which creates a 'zero' matrix of same type as a given matrix.
std::auto_ptr< Matrix >	create (const IndexType numRows, const IndexType numColumns) const
	Constructor creates a replicated matrix of same type as a given matrix.
std::auto_ptr< Matrix >	create (const IndexType size) const
	Constructor creates a distributed zero matrix of same type as a given matrix.
std::auto_ptr< Matrix >	create (DistributionPtr rowDistribution, DistributionPtr colDistribution) const
	Constructor creates a distributed zero matrix of same type as a given matrix.
std::auto_ptr< Matrix >	create (DistributionPtr distribution) const
	Constructor creates a distributed zero matrix of same type as a given matrix.
virtual std::auto_ptr< Matrix >	copy () const
	Implementation of pure method.
void	redistribute (DistributionPtr rowDistribution, DistributionPtr colDistribution)
	This method allows any arbitrary redistribution of the matrix.
void	assignTranspose (const Matrix &matrix)
	Assign another matrix transposed to this matrix.
virtual size_t	getMemoryUsage () const
	getMemoryUsage returns the global memory that is allocated to hold this matrix.
void	writeToFile (const std::string &fileName, const File::FileType fileType=File::BINARY, const File::DataType dataType=File::INTERNAL, const File::IndexDataType indexDataTypeIA=File::INT, const File::IndexDataType indexDataTypeJA=File::INT) const
	Writes this sparse matrix to a file in CSR format.
void	readFromFile (const std::string &filename)
	Assigns this matrix with a replicated sparse matrix read from file.
Matrix::MatrixKind	getMatrixKind () const
	Copy constructor of a matrix with a new row and column distribution.
std::auto_ptr< _LAMAArray >	createArray () const
	This routine creates a LAMA array with the same value type as the matrix.
Scalar	operator() (IndexType i, IndexType j) const
	returns a copy of the value at the passed global indexes.
IndexType	getNumRows () const
	Returns the number of global rows.
IndexType	getNumColumns () const
	Returns the number of columns.
double	getSparsityRate () const
virtual void	matrix2CSRGraph (IndexType *xadj, IndexType *adjncy, IndexType *vwgt, CommunicatorPtr comm, const IndexType *globalRowIndices=NULL, IndexType *vtxdist=NULL) const
	transformation from matrix type to a csr graph
const Distribution &	getColDistribution () const
	gets a constant reference to the column distribution.
DistributionPtr	getColDistributionPtr () const
	gets a pointer to the column distribution.
SyncKind	getCommunicationKind () const
	get the communication kind.
SyncKind	getComputeKind () const
	get the compute kind.
void	setCommunicationKind (SyncKind communicationKind)
	set the communication kind.
void	inheritAttributes (const Matrix &other)
	Inherit context and kind arguments from another matrix.
VectorPtr	createDenseVector (DistributionPtr distribution, const Scalar value) const
	Constructor creates a distributed dense vector of same type as a given matrix.
const Distribution &	getDistribution () const
DistributionPtr	getDistributionPtr () const
Static Public Member Functions
static const char *	typeName ()
	Static method that returns the name of the matrix class.
Protected Member Functions
void	swap (Distributed &other)
void	checkSettings ()
	Test consistency of sparse matrix data, only used if ASSERT_DEBUG is enabled.
void	matrixTimesMatrixImpl (const ValueType alpha, const SparseMatrix< ValueType > &A, const SparseMatrix< ValueType > &B, const ValueType beta, const SparseMatrix< ValueType > &C)
	Set this matrix = alpha * A * B + beta * C.
void	setReplicatedMatrix (const IndexType numRows, const IndexType numColumns)
	Set the global/local size of replicated matrix.
void	setDistributedMatrix (DistributionPtr distribution, DistributionPtr colDistribution)
	Set the global and local size of distributed matrix.
void	swapMatrix (Matrix &other)
void	setDistributionPtr (DistributionPtr distributionPtr)
Protected Attributes
boost::shared_ptr < MatrixStorage< ValueType > >	mLocalData
	local columns of sparse matrix
boost::shared_ptr < MatrixStorage< ValueType > >	mHaloData
	local columns of sparse matrix
Halo	mHalo
	Exchange plans for halo part due to column distribution.
DistributionPtr	mColDistribution
IndexType	mNumRows
IndexType	mNumColumns
Private Member Functions
boost::shared_ptr < MatrixStorage< ValueType > >	createStorage ()
	This private routine provides empty JDS storage for a JDSSparseMatrix.
boost::shared_ptr < MatrixStorage< ValueType > >	createStorage (const IndexType numRows, const IndexType numColumns)
	LAMA_LOG_DECL_STATIC_LOGGER (logger)

---

Detailed Description

template<typename T>
class lama::JDSSparseMatrix< T >

Definition of a derived class for SparseMatrix that uses the JDS storage format for the local and halo data of the distributed sparse matrix.

As the storage format is known here this class can offer more advanced constructors that do not exist for SparseMatrix as there the storage format is not fixed.

---

Member Typedef Documentation

typedef const Matrix& lama::Matrix::ExpressionMemberType [inherited]

ExpressionMemberType is the type that is used the template Expression to store a Vector.

template<typename T >

typedef JDSStorage<T> lama::JDSSparseMatrix< T >::StorageType

template<typename T >

typedef T lama::JDSSparseMatrix< T >::ValueType

type definition of the value type.

Reimplemented from lama::SparseMatrix< T >.

---

Member Enumeration Documentation

enum lama::Matrix::MatrixKind [inherited]

MatrixKind describes if a matrix is dense or sparse.

Enumerator:

DENSE	matrix kind for a dense matrix
SPARSE	matrix kind for a sparse matrix

enum lama::Matrix::SyncKind [inherited]

SyncKind describes if the communication and computation should be done synchronously or asynchronously.

Enumerator:

ASYNCHRONOUS
SYNCHRONOUS

---

Constructor & Destructor Documentation

template<typename T >

lama::JDSSparseMatrix< T >::JDSSparseMatrix

(

)

[inline]

Default constructor, creates a replicated matrix of size 0 x 0.

template<typename T >

lama::JDSSparseMatrix< T >::JDSSparseMatrix	(	const IndexType	numRows,
		const IndexType	numColumns
	)		[inline]

Constructor, creates a replicated zero-matrix of size numRows x numColums.

template<typename T >

lama::JDSSparseMatrix< T >::JDSSparseMatrix	(	DistributionPtr	rowDist,
		DistributionPtr	colDist
	)		[inline]

Constructor, creates a distributed zero-matrix by given row and column distribution.

template<typename T >

lama::JDSSparseMatrix< T >::JDSSparseMatrix	(	const Matrix &	other,
		bool	transposeFlag = false
	)		[inline]

template<typename T >

lama::JDSSparseMatrix< T >::JDSSparseMatrix	(	const Matrix &	other,
		DistributionPtr	rowDist,
		DistributionPtr	colDist
	)		[inline]

template<typename T >

lama::JDSSparseMatrix< T >::JDSSparseMatrix	(	const _MatrixStorage &	localData,
		DistributionPtr	rowDist,
		DistributionPtr	colDist
	)		[inline]

Constructor of a sparse matrix by local storage.

Parameters:

[in]	localData	contains local rows of the distributed matrix
[in]	rowDist	is distribution of localData
[in]	colDist	specifies how to split local rows for halo

This constructor works also fine if localData is the full global matrix; in this case only local rows will be taken on this processor.

template<typename T >

lama::JDSSparseMatrix< T >::JDSSparseMatrix

(

const std::string &

filename

)

[inline]

Constructor of a replicated sparse matrix by reading the matrix data from a file.

Next releases will also support distributed/parallel I/O. In the meantime this constructor should be used with a following call of the redistribute method.

template<typename T >

lama::JDSSparseMatrix< T >::JDSSparseMatrix

(

const Expression< Matrix, Matrix, Times > &

expression

)

[inline]

template<typename T >

lama::JDSSparseMatrix< T >::JDSSparseMatrix

(

const Expression< Scalar, Matrix, Times > &

expression

)

[inline]

template<typename T >

lama::JDSSparseMatrix< T >::JDSSparseMatrix

(

const Expression< Scalar, Expression< Matrix, Matrix, Times >, Times > &

expression

)

[inline]

template<typename T >

template<typename LocalValueType , typename HaloValueType >

lama::JDSSparseMatrix< T >::JDSSparseMatrix	(	const IndexType	numLocalRows,
		const IndexType	numLocalNonZeros,
		const IndexType	numHaloNonZeros,
		const IndexType	localIA[],
		const IndexType	localJA[],
		const LocalValueType	localValues[],
		const IndexType	haloIA[],
		const IndexType	haloJA[],
		const HaloValueType	haloValues[],
		const std::vector< IndexType > &	ownedIndexes,
		const CommunicatorPtr	communicator
	)		[inline]

Constructor of a JDS sparse matrix with distributed JDS storage data.

Parameters:

[in]	numRows	the number of rows of the matrix
[in]	numLocalNonZeros	the number of local none zeros of the matrix
[in]	numHaloNonZeros	the number of halo none zeros of the matrix
[in]	localIA	row pointer of the input csr sparse matrix (local)
[in]	localJA	column indexes of the input csr sparse matrix (local)
[in]	localValues	the none zero values of the input csr sparse matrix (local)
[in]	haloIA	row pointer of the input csr sparse matrix (halo)
[in]	haloJA	column indexes of the input csr sparse matrix (halo)
[in]	haloValues	the none zero values of the input csr sparse matrix (halo)
[in]	globalIndexes	the global Indexes of the local rows
[in]	communicator	communicator of the distribution

References lama::Matrix::setDistributedMatrix().

---

Member Function Documentation

template<typename ValueType >

void lama::SparseMatrix< ValueType >::allocate	(	const IndexType	numRows,
		const IndexType	numColumns
	)		[virtual, inherited]

Implementation of pure method of class Matrix.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

Referenced by lama::MatrixCreator< T >::buildRandom().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::allocate	(	DistributionPtr	distribution,
		DistributionPtr	colDistribution
	)		[virtual, inherited]

Implementation of pure method of class Matrix.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::assign

(

const Matrix &

other

)

[virtual, inherited]

Implementation of pure method of class Matrix.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Matrix::buildLocalStorage(), lama::Matrix::getColDistributionPtr(), lama::Matrix::getContextPtr(), and lama::Distributed::getDistributionPtr().

Referenced by lama::MatrixCreator< T >::buildPoisson().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::assign

(

const _SparseMatrix< T > &

matrix

)

[inherited]

Method that assigns a sparse matrix, specialization of assign( const Matrix& )

References lama::Matrix::getColDistributionPtr(), lama::Distributed::getDistributionPtr(), lama::_SparseMatrix::getHalo(), lama::_SparseMatrix::getHaloStorage(), and lama::_SparseMatrix::getLocalStorage().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::assign

(

const _MatrixStorage &

other

)

[virtual, inherited]

Setting (distributed) matrix with any global matrix storage.

Parameters:

[in]

other

is replicated (sparse) matrix data containing all values to be set

Size of other matrix must be exactly the same as this matrix. This routine might imply type and storage format conversions as well as distributing the data according to the current distribution of this matrix.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::_MatrixStorage::getNumColumns(), and lama::_MatrixStorage::getNumRows().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::assign	(	const _MatrixStorage &	storage,
		DistributionPtr	rowDist,
		DistributionPtr	colDist
	)		[virtual, inherited]

Setting (distributed) matrix with any local matrix data.

Parameters:

[in]

other

is local (sparse) matrix data containing all values to be set

Size of other matrix must be exactly the same as this matrix. This routine might imply type and storage format changes.

void assignLocal( const _MatrixStorage& { LAMA_THROWEXCEPTION( "not available yet" ); } Assignment of local storage that fits a given row distribution. The columns of the local storage will be splitted according to the column distribution.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::MatrixStorage< T >::assign(), lama::_MatrixStorage::getNumColumns(), lama::_MatrixStorage::getNumRows(), LAMA_ASSERT_EQUAL_ERROR, and LAMA_THROWEXCEPTION.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::assignTranspose

(

const Matrix &

matrix

)

[inherited]

Assign another matrix transposed to this matrix.

References LAMA_THROWEXCEPTION.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::buildLocalStorage

(

_MatrixStorage &

storage

)

const [virtual, inherited]

Implementation of Matrix::buildLocalStorage.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::checkSettings

(

)

[protected, inherited]

Test consistency of sparse matrix data, only used if ASSERT_DEBUG is enabled.

Reimplemented from lama::Matrix.

References LAMA_ASSERT_EQUAL_DEBUG.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::clear

(

)

[virtual, inherited]

Implementation of pure method.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

template<typename ValueType >

std::auto_ptr< Matrix > lama::SparseMatrix< ValueType >::copy

(

)

const [virtual, inherited]

Implementation of pure method.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

template<typename ValueType >

std::auto_ptr< Matrix > lama::SparseMatrix< ValueType >::create

(

)

const [virtual, inherited]

Constructor function which creates a 'zero' matrix of same type as a given matrix.

 void sub( ..., const Matrix& matrix, ...)
 {
     ...
     // Create a copy of the input matrix

     std::auto_ptr<Matrix> newMatrix = matrix.create();
     *newMatrix = matrix;

     // Create a unity matrix of same type and same row distribution as matrix

     std::auto_ptr<Matrix> newMatrix = matrix.create();
     newMatrix->allocate( matrix.getRowDistributionPtr(), matrix.getRowDistributionPtr() );
     newMatrix->setIdentity();  
     ...
 }

This method is a workaround to call the constructor of a derived matrix class where the derived class is not known at compile time.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::SparseMatrix< T >::setContext().

std::auto_ptr< Matrix > lama::Matrix::create	(	const IndexType	numRows,
		const IndexType	numColumns
	)		const [inherited]

Constructor creates a replicated matrix of same type as a given matrix.

References lama::Matrix::create().

std::auto_ptr< Matrix > lama::Matrix::create

(

const IndexType

size

)

const [inherited]

Constructor creates a distributed zero matrix of same type as a given matrix.

References lama::Matrix::create().

std::auto_ptr< Matrix > lama::Matrix::create	(	DistributionPtr	rowDistribution,
		DistributionPtr	colDistribution
	)		const [inherited]

Constructor creates a distributed zero matrix of same type as a given matrix.

References lama::Matrix::create().

std::auto_ptr< Matrix > lama::Matrix::create

(

DistributionPtr

distribution

)

const [inherited]

Constructor creates a distributed zero matrix of same type as a given matrix.

References lama::Matrix::create().

std::auto_ptr< _LAMAArray > lama::Matrix::createArray

(

)

const [inherited]

This routine creates a LAMA array with the same value type as the matrix.

: returns an auto pointer to the LAMA array.

Same as _LAMAArray::create( this.getValueType() )

Value type is known only at runtime, so pointer to the base class is returned. Auto pointer indicates that calling routine takes ownership of the allocated array.

References lama::Matrix::create(), and lama::Matrix::getValueType().

VectorPtr lama::Matrix::createDenseVector	(	DistributionPtr	distribution,
		const Scalar	value
	)		const [inherited]

Constructor creates a distributed dense vector of same type as a given matrix.

References lama::Scalar::DOUBLE, lama::Scalar::FLOAT, lama::Scalar::getValue(), lama::Matrix::getValueType(), and LAMA_THROWEXCEPTION.

template<typename T >

boost::shared_ptr<MatrixStorage< ValueType> > lama::JDSSparseMatrix< T >::createStorage

(

)

[inline, private]

This private routine provides empty JDS storage for a JDSSparseMatrix.

template<typename T >

boost::shared_ptr<MatrixStorage< ValueType> > lama::JDSSparseMatrix< T >::createStorage	(	const IndexType	numRows,
		const IndexType	numColumns
	)		[inline, private]

const Distribution & lama::Matrix::getColDistribution

(

)

const [inline, inherited]

gets a constant reference to the column distribution.

Returns:

a constant reference to the column distribution.

References LAMA_ASSERT_ERROR, and lama::Matrix::mColDistribution.

Referenced by lama::DenseMatrix< T >::assignSparse(), lama::Matrix::checkSettings(), lama::LUSolver::computeLUFactorization(), lama::InverseSolver::decompose(), lama::DenseMatrix< T >::DenseMatrix(), lama::DenseMatrixOps::invert(), lama::InverseSolver::invert(), lama::DenseMatrixOps::invertReplicated(), lama::SpecializedJacobi::iterateTyped(), lama::Matrix::Matrix(), lama::DenseMatrix< T >::matrixTimesMatrix(), lama::SparseMatrix< T >::matrixTimesMatrixImpl(), lama::CRTPMatrix< DenseMatrix< T >, T >::matrixTimesVector(), lama::SparseMatrix< T >::matrixTimesVectorNImpl(), lama::DenseMatrix< T >::maxDiffNorm(), lama::SparseMatrix< T >::maxDiffNorm(), lama::DenseMatrix< T >::maxDiffNormImpl(), lama::SparseMatrix< T >::maxDiffNormImpl(), lama::Matrix::operator=(), lama::LUSolver::solve(), and lama::Solver::solveInit().

DistributionPtr lama::Matrix::getColDistributionPtr

(

)

const [inline, inherited]

gets a pointer to the column distribution.

Returns:

a pointer to the column distribution.

References LAMA_ASSERT_ERROR, and lama::Matrix::mColDistribution.

Referenced by lama::SparseMatrix< T >::assign(), lama::DenseMatrix< T >::assign(), lama::DenseMatrix< T >::assignSparse(), lama::SparseMatrix< T >::assignTransposeImpl(), lama::DenseMatrix< T >::copyDenseMatrix(), lama::MatrixCreator< T >::fillRandom(), lama::DenseMatrixOps::invert(), lama::DenseMatrix< T >::invert(), lama::DenseMatrix< T >::matrixTimesMatrix(), lama::SparseMatrix< T >::matrixTimesMatrixImpl(), and lama::SparseMatrix< T >::matrixTimesVectorNImpl().

Matrix::SyncKind lama::Matrix::getCommunicationKind

(

)

const [inline, inherited]

get the communication kind.

Returns:

the communication kind.

References lama::Matrix::mCommunicationKind.

Referenced by lama::Matrix::inheritAttributes(), lama::SpecializedJacobi::iterateTyped(), and lama::DenseMatrix< T >::matrixTimesVectorImpl().

Matrix::SyncKind lama::Matrix::getComputeKind

(

)

const [inline, inherited]

get the compute kind.

Returns:

the compute kind.

References lama::Matrix::mComputeKind.

Referenced by lama::Matrix::inheritAttributes().

template<typename T>

virtual const Context& lama::SparseMatrix< T >::getContext

(

)

const [inline, virtual, inherited]

Reimplemented from lama::Matrix.

template<typename T>

virtual ContextPtr lama::SparseMatrix< T >::getContextPtr

(

)

const [inline, virtual, inherited]

Getter routine for the context.

Note: Only for SparseMatrix the context of the halo can be queried.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::getDiagonal

(

Vector &

diagonal

)

const [virtual, inherited]

This method returns the diagonal.

Parameters:

[out]

diagonal

is the destination array

Calculations are dependent to the diagonal property

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References LAMA_THROWEXCEPTION, lama::Vector::resize(), and lama::Vector::setValues().

const Distribution & lama::Distributed::getDistribution

(

)

const [inline, inherited]

References lama::Distributed::mDistribution.

Referenced by lama::SparseMatrix< T >::assignTransposeImpl(), lama::Matrix::checkSettings(), lama::LUSolver::computeLUFactorization(), lama::InverseSolver::decompose(), lama::DenseMatrix< T >::DenseMatrix(), lama::DenseVector< T >::DenseVector(), lama::DenseVector< T >::dotProduct(), lama::MatrixCreator< T >::fillRandom(), lama::SparseMatrix< T >::getLocalRow(), lama::SparseMatrix< T >::getRow(), lama::DenseMatrix< T >::getRow(), lama::DenseMatrixOps::invert(), lama::InverseSolver::invert(), lama::DenseMatrixOps::invertCyclic(), lama::DenseMatrixOps::invertReplicated(), lama::Matrix::Matrix(), lama::DenseMatrix< T >::matrixTimesMatrix(), lama::SparseMatrix< T >::matrixTimesMatrixImpl(), lama::CRTPMatrix< DenseMatrix< T >, T >::matrixTimesVector(), lama::SparseMatrix< T >::matrixTimesVector(), lama::SparseMatrix< T >::matrixTimesVectorNImpl(), lama::DenseMatrix< T >::maxDiffNorm(), lama::SparseMatrix< T >::maxDiffNorm(), lama::DenseMatrix< T >::maxDiffNormImpl(), lama::SparseMatrix< T >::maxDiffNormImpl(), lama::Matrix::operator=(), lama::SparseMatrix< T >::scale(), lama::SparseMatrix< T >::setDiagonal(), lama::LUSolver::solve(), lama::Solver::solveInit(), lama::Vector::Vector(), and lama::Vector::~Vector().

DistributionPtr lama::Distributed::getDistributionPtr

(

)

const [inline, inherited]

References lama::Distributed::mDistribution.

Referenced by lama::SparseMatrix< T >::assign(), lama::DenseMatrix< T >::assign(), lama::DenseVector< T >::assign(), lama::DenseMatrix< T >::assignSparse(), lama::SparseMatrix< T >::assignTransposeImpl(), lama::DenseMatrix< T >::copyDenseMatrix(), lama::DenseVector< T >::DenseVector(), lama::MatrixCreator< T >::fillRandom(), lama::SingleGridSetup::initialize(), lama::CG::initialize(), lama::DefaultJacobi::initialize(), lama::GMRES::initialize(), lama::DenseMatrixOps::invert(), lama::DenseMatrix< T >::invert(), lama::DenseMatrixOps::invertCyclic(), lama::GMRES::iterate(), lama::SparseMatrix< T >::matrixTimesMatrixImpl(), lama::CRTPMatrix< DenseMatrix< T >, T >::matrixTimesVector(), lama::Vector::operator=(), lama::Vector::size(), and lama::Vector::writeAt().

template<typename ValueType >

const Halo & lama::SparseMatrix< ValueType >::getHalo

(

)

const [virtual, inherited]

Read access to the halo of the distributed matrix.

Implements lama::_SparseMatrix.

Referenced by lama::SparseMatrix< T >::assignTransposeImpl(), lama::SOR::iterateImpl(), lama::SpecializedJacobi::iterateTyped(), lama::SparseMatrix< T >::matrixTimesMatrixImpl(), and lama::SparseMatrix< T >::SparseMatrix().

template<typename ValueType >

const JDSSparseMatrix< ValueType >::StorageType & lama::JDSSparseMatrix< ValueType >::getHaloStorage

(

)

const [virtual]

Override MatrixStorage<ValueType>::getHaloStorage with covariant return type.

Reimplemented from lama::SparseMatrix< T >.

References LAMA_ASSERT_ERROR.

template<typename ValueType >

IndexType lama::SparseMatrix< ValueType >::getLocalNumColumns

(

)

const [virtual, inherited]

Getter routine for the local number of rows and columns.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Matrix::getNumColumns().

template<typename ValueType >

IndexType lama::SparseMatrix< ValueType >::getLocalNumRows

(

)

const [virtual, inherited]

Getter routine for the local number of rows.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Matrix::getNumRows().

template<typename ValueType >

IndexType lama::SparseMatrix< ValueType >::getLocalNumValues

(

)

const [virtual, inherited]

Getter routine for the number of locally stored values.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::SparseMatrix< T >::getNumValues().

template<typename ValueType >

const JDSSparseMatrix< ValueType >::StorageType & lama::JDSSparseMatrix< ValueType >::getLocalStorage

(

)

const [virtual]

Override MatrixStorage<ValueType>::getLocalStorage with covariant return type.

Reimplemented from lama::SparseMatrix< T >.

References LAMA_ASSERT_ERROR.

template<typename ValueType >

JDSSparseMatrix< ValueType >::StorageType & lama::JDSSparseMatrix< ValueType >::getLocalStorage

(

)

[virtual]

Todo:

this getter should be removed as write access to local strage is dangerous

References LAMA_ASSERT_ERROR.

Matrix::MatrixKind lama::_SparseMatrix::getMatrixKind

(

)

const [inline, virtual, inherited]

Copy constructor of a matrix with a new row and column distribution.

_SparseMatrix( const Matrix& other, DistributionPtr distribution, DistributionPtr colDistribution ) :

Matrix( other, distribution, colDistribution ) {} Implementation of pure method Matrix::getMatrixKind

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Matrix::SPARSE.

template<typename ValueType >

size_t lama::SparseMatrix< ValueType >::getMemoryUsage

(

)

const [virtual, inherited]

getMemoryUsage returns the global memory that is allocated to hold this matrix.

getMemoryUsage returns the global memory that is allocated to hold this matrix. For a distributed matrix all partitions are summed together.

Returns:

the memory consumption of this matrix.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::SparseMatrix< T >::getMemoryUsage().

Referenced by lama::SparseMatrix< T >::getMemoryUsage().

IndexType lama::Matrix::getNumColumns

(

)

const [inline, inherited]

Returns the number of columns.

Returns:

the number of columns.

References lama::Matrix::mNumColumns.

Referenced by lama::DenseMatrix< T >::assignSparse(), lama::LUSolver::computeLUFactorization(), lama::InverseSolver::decompose(), lama::DenseMatrix< T >::DenseMatrix(), lama::MatrixCreator< T >::fillRandom(), lama::SparseMatrix< T >::getLocalNumColumns(), lama::InverseSolver::invert(), lama::DenseMatrix< T >::invert(), lama::DenseMatrixOps::invertCyclic(), lama::MatrixConfigGrammar::MatrixConfigGrammar(), lama::Matrix::operator=(), lama::LUSolver::solve(), and lama::Solver::solveInit().

IndexType lama::Matrix::getNumRows

(

)

const [inline, inherited]

Returns the number of global rows.

Returns:

the number of rows.

References lama::Matrix::mNumRows.

Referenced by lama::InverseSolver::computeInverse(), lama::LUSolver::computeLUFactorization(), lama::InverseSolver::decompose(), lama::SparseMatrix< T >::getLocalNumRows(), lama::LUSolver::initialize(), lama::DenseMatrixOps::invert(), lama::InverseSolver::invert(), lama::DenseMatrix< T >::invert(), lama::DenseMatrixOps::invertCyclic(), lama::SpecializedJacobi::iterateTyped(), lama::MatrixConfigGrammar::MatrixConfigGrammar(), lama::Matrix::operator=(), lama::LUSolver::solve(), and lama::Solver::solveInit().

template<typename ValueType >

IndexType lama::SparseMatrix< ValueType >::getNumValues

(

)

const [virtual, inherited]

Get the total number of non-zero values in the matrix.

An element is considered to be non-zero if its absolute value is greater equal than mEpsilon. Zero diagonal elements are also counted if this->hasDiagonalProperty() is given.

This routine does not count zero elements even if they are stored (e.g. for dense or dia storage data).

Returns:

the number of non-zero values in this matrix.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

Referenced by lama::SparseMatrix< T >::getLocalNumValues(), and lama::SparseMatrix< T >::getPartitialNumValues().

template<typename ValueType >

IndexType lama::SparseMatrix< ValueType >::getPartitialNumValues

(

)

const [inherited]

References lama::SparseMatrix< T >::getNumValues().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::getRow	(	Vector &	row,
		const IndexType	globalRowIndex
	)		const [virtual, inherited]

This method returns one row of the matrix.

Parameters:

[out]

row

is a replicated vector with all values of the row

Note: the value type of the vector should be the same type as the matrix (otherwise conversion) and it should be a replicated vector (otherwise reallocation)

Unclear: should the distribution always be unchanged ?

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Communicator::bcast(), lama::Distributed::getDistribution(), lama::Communicator::getRank(), lama::Distribution::isReplicated(), LAMA_ASSERT_ERROR, lama::nIndex, and lama::Communicator::sum().

double lama::Matrix::getSparsityRate

(

)

const [inherited]

References lama::Matrix::getNumValues(), lama::Matrix::mNumColumns, and lama::Matrix::mNumRows.

template<typename ValueType >

const char * lama::JDSSparseMatrix< ValueType >::getTypeName

(

)

const [virtual]

Override Matrix::getTypeName with correct method.

Reimplemented from lama::SparseMatrix< T >.

template<typename ValueType >

Scalar lama::SparseMatrix< ValueType >::getValue	(	IndexType	i,
		IndexType	j
	)		const [virtual, inherited]

returns a copy of the value at the passed global indexes.

Parameters:

[in]	i	the global row index
[in]	j	the global column index

Returns:

a copy of the value at the passed global position.

As this operation requires communication ins SPMD mode it can be very inefficient in some situations.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Distribution::getCommunicator(), lama::Distribution::global2local(), lama::nIndex, and lama::Communicator::sum().

template<typename ValueType >

Scalar::ScalarType lama::SparseMatrix< ValueType >::getValueType

(

)

const [virtual, inherited]

Query the value type of the matrix elements, e.g.

DOUBLE or FLOAT.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

template<typename ValueType >

bool lama::SparseMatrix< ValueType >::hasDiagonalProperty

(

)

const [virtual, inherited]

hasDiagonalProperty returns the diagonalProperty of the local storage.

Returns:

if the diagonal property is full filled.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

void lama::Matrix::inheritAttributes

(

const Matrix &

other

)

[inherited]

Inherit context and kind arguments from another matrix.

This routine will also be used by copy constructors in base classes.

References lama::Matrix::getCommunicationKind(), lama::Matrix::getComputeKind(), lama::Matrix::getContextPtr(), lama::Matrix::setCommunicationKind(), lama::Matrix::setComputeKind(), and lama::Matrix::setContext().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::invert

(

const Matrix &

other

)

[virtual, inherited]

Implementation of Matrix::invert for sparse matrices.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::DenseMatrix< T >::invert(), and LAMA_UNSUPPORTED.

template<typename T >

lama::JDSSparseMatrix< T >::LAMA_LOG_DECL_STATIC_LOGGER

(

logger

)

[private]

Reimplemented from lama::SparseMatrix< T >.

void lama::Matrix::matrix2CSRGraph	(	IndexType *	xadj,
		IndexType *	adjncy,
		IndexType *	vwgt,
		CommunicatorPtr	comm,
		const IndexType *	globalRowIndices = NULL,
		IndexType *	vtxdist = NULL
	)		const [virtual, inherited]

transformation from matrix type to a csr graph

transformation from matrix type to a csr graph, so that it (Par)Metis can work with it.

Parameters:

[out]	xadj	the ia array of the csr graph
[out]	adjncy	the ja array of the csr graph

References LAMA_THROWEXCEPTION.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::matrixTimesMatrix	(	Matrix &	result,
		const Scalar	alpha,
		const Matrix &	B,
		const Scalar	beta,
		const Matrix &	C
	)		const [virtual, inherited]

Implemenation of abstract method Matrix::matrixTimesMatrix.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::DENSE, lama::Matrix::getMatrixKind(), lama::Scalar::getValue(), LAMA_ASSERT_ERROR, and lama::SparseMatrix< T >::matrixTimesMatrixImpl().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::matrixTimesMatrixImpl	(	const ValueType	alpha,
		const SparseMatrix< ValueType > &	A,
		const SparseMatrix< ValueType > &	B,
		const ValueType	beta,
		const SparseMatrix< ValueType > &	C
	)		[protected, inherited]

Set this matrix = alpha * A * B + beta * C.

References lama::MatrixStorage< T >::exchangeHalo(), lama::Matrix::getColDistribution(), lama::Matrix::getColDistributionPtr(), lama::Distribution::getCommunicator(), lama::Distributed::getDistribution(), lama::Distributed::getDistributionPtr(), lama::SparseMatrix< T >::getHalo(), lama::SparseMatrix< T >::getLocalStorage(), lama::Distribution::isReplicated(), LAMA_ASSERT_EQUAL_DEBUG, LAMA_ASSERT_ERROR, LAMA_THROWEXCEPTION, lama::SparseMatrix< T >::mHaloData, and lama::SparseMatrix< T >::mLocalData.

Referenced by lama::SparseMatrix< T >::matrixTimesMatrix().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::matrixTimesScalar	(	const Matrix &	other,
		const Scalar	alpha
	)		[virtual, inherited]

Set local data of the matrix.

The local part of the distributed matrix will be splitted into local / halo part. corresponding to the column distribution, builds new halo this matrix = other * alpha

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Scalar::getValue().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::matrixTimesVector	(	Vector &	result,
		const Scalar	alpha,
		const Vector &	x,
		const Scalar	beta,
		const Vector &	y
	)		const [virtual, inherited]

matrixTimesVector computes result = alpha * this * x + beta * y

Parameters:

[out]	result	the Vector to store the result to
[in]	alpha	the Scalar alpha of the expression
[in]	x	the Vector x of the expression
[in]	beta	the Scalar beta of the expression
[in]	y	the Vector y of the expression

matrixTimesVector computes result = alpha * this * x + beta * y. If result == x or result == y new storage is allocated to store the result.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Distributed::getDistribution(), lama::Scalar::getValue(), LAMA_ASSERT, LAMA_ASSERT_EQUAL, LAMA_REGION, LAMA_THROWEXCEPTION, and lama::Vector::resize().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::matrixTimesVectorImpl	(	DenseVector< ValueType > &	result,
		const ValueType	alpha,
		const DenseVector< ValueType > &	x,
		const ValueType	beta,
		const DenseVector< ValueType > &	y
	)		const [inherited]

References lama::DenseVector< T >::getHaloValues(), lama::DenseVector< T >::getLocalValues(), LAMA_REGION, lama::DenseVector< T >::prefetch(), lama::WriteAccess< T >::resize(), lama::_LAMAArray::size(), and lama::zero.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::matrixTimesVectorNImpl	(	DenseMatrix< ValueType > &	result,
		const ValueType	alpha,
		const DenseMatrix< ValueType > &	x,
		const ValueType	beta,
		const DenseMatrix< ValueType > &	y
	)		const [virtual, inherited]

matrix times matrix for multiple dense vectors.

References lama::DenseMatrix< T >::allocate(), lama::Matrix::getColDistribution(), lama::Matrix::getColDistributionPtr(), lama::Distributed::getDistribution(), lama::DenseMatrix< T >::getLocalStorage(), LAMA_ASSERT, and LAMA_ASSERT_DEBUG.

template<typename ValueType >

Scalar lama::SparseMatrix< ValueType >::maxDiffNorm

(

const Matrix &

other

)

const [virtual, inherited]

Implementation of Matrix::maxDiffNorm for sparse matrices.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Matrix::getColDistribution(), lama::Distributed::getDistribution(), lama::Matrix::getValueType(), lama::Distribution::isReplicated(), LAMA_ASSERT_DEBUG, LAMA_THROWEXCEPTION, and LAMA_UNSUPPORTED.

template<typename ValueType >

ValueType lama::SparseMatrix< ValueType >::maxDiffNormImpl

(

const SparseMatrix< ValueType > &

other

)

const [inherited]

Get the maximal difference between two elements for sparse matrices of same type.

References lama::Matrix::getColDistribution(), lama::Distributed::getDistribution(), lama::SparseMatrix< T >::getLocalStorage(), lama::Distribution::isReplicated(), LAMA_ASSERT_EQUAL_ERROR, LAMA_ASSERT_ERROR, and lama::Communicator::max().

Scalar lama::Matrix::operator()	(	IndexType	i,
		IndexType	j
	)		const [inherited]

returns a copy of the value at the passed global indexes.

Parameters:

[in]	i	the global row index
[in]	j	the global column index

Returns:

a copy of the value at the passed global position.

As this operator requires communication ins SPMD mode it can be very inefficient in some situations.

References lama::Matrix::getValue().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::prefetch

(

)

const [virtual, inherited]

Prefetch matrix data to its 'preferred' context location.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::SparseMatrix< T >::prefetch().

Referenced by lama::SparseMatrix< T >::prefetch().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::readFromFile

(

const std::string &

filename

)

[inherited]

Assigns this matrix with a replicated sparse matrix read from file.

Creates a replicated sparse matrix read from file. Currently supported is the matrix market format, XDR, formatted, unformatted, binary.

ToDo: set reference to description in StorageIO.

Parameters:

[in]

filename

the filename to read from

Note: Derived classes might use this routine within a constructor for convenience. This class does not support such a constructor as no file format is known.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::redistribute	(	DistributionPtr	rowDistribution,
		DistributionPtr	colDistribution
	)		[virtual, inherited]

This method allows any arbitrary redistribution of the matrix.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References LAMA_ASSERT_ERROR.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::resetDiagonalProperty

(

)

[virtual, inherited]

resetDiagonalProperty rechecks the storages for their diagonal property

Returns:

if the diagonal property is full filled.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References LAMA_THROWEXCEPTION.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::scale

(

const Vector &

scaling

)

[virtual, inherited]

This method scales all values with a vector.

Parameters:

[in]

scaling

is the vector with scale value for each row

row wise calculations

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Vector::buildValues(), lama::Distributed::getDistribution(), and LAMA_THROWEXCEPTION.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::scale

(

const Scalar

scaling

)

[virtual, inherited]

This method scales all matrix values with a scalar.

Parameters:

[in]

value

is the source value

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References LAMA_THROWEXCEPTION.

void lama::Matrix::setCommunicationKind

(

SyncKind

communicationKind

)

[inherited]

set the communication kind.

Parameters:

[in]

communicationKind

the communication kind.

References lama::Matrix::mCommunicationKind.

Referenced by lama::Matrix::inheritAttributes().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::setComputeKind

(

SyncKind

computeKind

)

[virtual, inherited]

set the compute kind.

Parameters:

[in]

computeKind

the compute kind.

Reimplemented from lama::Matrix.

References lama::WriteAccess< T >::reserve().

template<typename T>

virtual void lama::SparseMatrix< T >::setContext

(

const ContextPtr

context

)

[inline, virtual, inherited]

specifies on which compute back end the matrix operations should take place.

Parameters:

[in]

context

the compute back to use for calculations with matrix

Note: Only for sparse matrices it is possible to specify separate locations for local and halo computations.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

Referenced by lama::SparseMatrix< T >::create().

template<typename T>

virtual void lama::SparseMatrix< T >::setContext	(	const ContextPtr	localContext,
		const ContextPtr	haloContext
	)		[inline, virtual, inherited]

Only sparse matrices will override this method, others will ignore second argument.

Reimplemented from lama::Matrix.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::setDiagonal

(

const Vector &

diagonal

)

[virtual, inherited]

This method replaces the diagonal.

Parameters:

[in]

diagonal

is the source array

Calculations are dependent to the diagonal property

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::Vector::buildValues(), lama::Distributed::getDistribution(), and LAMA_THROWEXCEPTION.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::setDiagonal

(

const Scalar

scalar

)

[virtual, inherited]

This method replaces the diagonal by a diagonal value.

Parameters:

[in]

scalar

is the source value

Calculations are dependent to the diagonal property

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References LAMA_THROWEXCEPTION.

void lama::Matrix::setDistributedMatrix	(	DistributionPtr	distribution,
		DistributionPtr	colDistribution
	)		[protected, inherited]

Set the global and local size of distributed matrix.

Parameters:

[in]	distribution	is distribution for rows
[in]	colDistribution	is distribution for columns

Global and local size is given implicitly by the distributions itself.

References LAMA_ASSERT_ERROR, lama::Matrix::mColDistribution, lama::Matrix::mNumColumns, lama::Matrix::mNumRows, and lama::Distributed::setDistributionPtr().

Referenced by lama::DenseMatrix< T >::allocate(), lama::SimpleStorageStrategy< ValueType >::applyStrategy(), lama::DenseMatrix< T >::assign(), lama::DenseMatrix< T >::assignSparse(), lama::COOSparseMatrix< T >::COOSparseMatrix(), lama::DenseMatrix< T >::copyDenseMatrix(), lama::CSRSparseMatrix< T >::CSRSparseMatrix(), lama::DIASparseMatrix< T >::DIASparseMatrix(), lama::ELLSparseMatrix< T >::ELLSparseMatrix(), lama::JDSSparseMatrix< T >::JDSSparseMatrix(), lama::Matrix::Matrix(), lama::Matrix::setReplicatedMatrix(), lama::DenseMatrix< T >::splitColumns(), and lama::XXXSparseMatrix< T >::XXXSparseMatrix().

void lama::Distributed::setDistributionPtr

(

DistributionPtr

distributionPtr

)

[protected, inherited]

References lama::Distributed::mDistribution.

Referenced by lama::Vector::resize(), and lama::Matrix::setDistributedMatrix().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::setIdentity

(

)

[virtual, inherited]

Implementation of pure method of class Matrix.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References LAMA_THROWEXCEPTION.

template<typename ValueType >

template<typename OtherValueType >

void lama::SparseMatrix< ValueType >::setRawDenseData	(	const IndexType	numRows,
		const IndexType	numColumns,
		const OtherValueType	values[],
		const OtherValueType	eps = 0.0
	)		[inherited]

Set sparse matrix with global dense data.

void lama::Matrix::setReplicatedMatrix	(	const IndexType	numRows,
		const IndexType	numColumns
	)		[protected, inherited]

Set the global/local size of replicated matrix.

Parameters:

[in]	numRows	number of rows, must be non-negative.
[in]	numColumns	number of columns, must be non-negative.

References lama::Matrix::setDistributedMatrix().

Referenced by lama::DenseMatrix< T >::allocate(), lama::DenseMatrix< T >::assign(), lama::DenseMatrix< T >::clear(), and lama::DenseMatrix< T >::DenseMatrix().

void lama::Distributed::swap

(

Distributed &

other

)

[protected, inherited]

References lama::Distributed::mDistribution.

Referenced by lama::Matrix::swapMatrix().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::swap

(

SparseMatrix< ValueType > &

other

)

[inherited]

Swap will swap all member variables of the two sparse matrices.

This operation might be useful in iteration loops where a sparse matrix is updated each iteration. It is more convenient than a solution that is based on using pointers in the application.

References lama::SparseMatrix< T >::mHalo, lama::SparseMatrix< T >::mHaloData, and lama::SparseMatrix< T >::mLocalData.

template<typename ValueType >

void lama::JDSSparseMatrix< ValueType >::swapLocalStorage

(

StorageType &

localStorage

)

[virtual]

Swap local storage data, allows consistent write access to local storage.

References lama::_MatrixStorage::getNumColumns(), lama::_MatrixStorage::getNumRows(), LAMA_ASSERT_EQUAL_ERROR, and LAMA_ASSERT_ERROR.

void lama::Matrix::swapMatrix

(

Matrix &

other

)

[protected, inherited]

References lama::Matrix::mColDistribution, lama::Matrix::mNumColumns, lama::Matrix::mNumRows, and lama::Distributed::swap().

Referenced by lama::DenseMatrix< T >::swap().

template<typename T >

static const char* lama::JDSSparseMatrix< T >::typeName

(

)

[static]

Static method that returns the name of the matrix class.

Reimplemented from lama::SparseMatrix< T >.

template<>

const char * lama::JDSSparseMatrix< float >::typeName

(

)

Getter for the type name of the class.

Reimplemented from lama::SparseMatrix< T >.

template<>

const char * lama::JDSSparseMatrix< double >::typeName

(

)

Getter for the type name of the class.

Reimplemented from lama::SparseMatrix< T >.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::wait

(

)

const [virtual, inherited]

wait for a possibly running prefetch.

Implements lama::Matrix.

Reimplemented in lama::SimpleStorageStrategy< ValueType >.

References lama::SparseMatrix< T >::wait().

Referenced by lama::SparseMatrix< T >::wait().

template<typename ValueType >

void lama::SparseMatrix< ValueType >::writeAt

(

std::ostream &

stream

)

const [virtual, inherited]

Write some information about this to the passed stream.

Parameters:

[out]

stream

the stream to write to.

Reimplemented from lama::Matrix.

template<typename ValueType >

void lama::SparseMatrix< ValueType >::writeToFile	(	const std::string &	fileName,
		const File::FileType	fileType = File::BINARY,
		const File::DataType	dataType = File::INTERNAL,
		const File::IndexDataType	indexDataTypeIA = File::INT,
		const File::IndexDataType	indexDataTypeJA = File::INT
	)		const [inherited]

Writes this sparse matrix to a file in CSR format.

References lama::Communicator::getRank(), lama::Communicator::getSize(), lama::MatrixStorage< T >::joinHalo(), LAMA_THROWEXCEPTION, lama::Communicator::synchronize(), and lama::MatrixStorage< T >::writeToFile().

---

Field Documentation

DistributionPtr lama::Matrix::mColDistribution [protected, inherited]

Referenced by lama::Matrix::checkSettings(), lama::Matrix::getColDistribution(), lama::Matrix::getColDistributionPtr(), lama::DenseMatrix< T >::redistribute(), lama::Matrix::setDistributedMatrix(), and lama::Matrix::swapMatrix().

template<typename T>

Halo lama::SparseMatrix< T >::mHalo [protected, inherited]

Exchange plans for halo part due to column distribution.

Referenced by lama::SparseMatrix< T >::SparseMatrix(), and lama::SparseMatrix< T >::swap().

template<typename T>

boost::shared_ptr<MatrixStorage<ValueType> > lama::SparseMatrix< T >::mHaloData [protected, inherited]

local columns of sparse matrix

Referenced by lama::SparseMatrix< T >::matrixTimesMatrixImpl(), lama::SparseMatrix< T >::SparseMatrix(), and lama::SparseMatrix< T >::swap().

template<typename T>

boost::shared_ptr<MatrixStorage<ValueType> > lama::SparseMatrix< T >::mLocalData [protected, inherited]

local columns of sparse matrix

Referenced by lama::SparseMatrix< T >::matrixTimesMatrixImpl(), and lama::SparseMatrix< T >::swap().

IndexType lama::Matrix::mNumColumns [protected, inherited]

Referenced by lama::Matrix::checkSettings(), lama::DenseMatrix< T >::DenseMatrix(), lama::Matrix::getNumColumns(), lama::Matrix::getSparsityRate(), lama::Matrix::Matrix(), lama::Matrix::setDistributedMatrix(), lama::Matrix::swapMatrix(), and lama::Matrix::writeAt().

IndexType lama::Matrix::mNumRows [protected, inherited]

Referenced by lama::Matrix::checkSettings(), lama::DenseMatrix< T >::DenseMatrix(), lama::Matrix::getNumRows(), lama::Matrix::getSparsityRate(), lama::Matrix::Matrix(), lama::Matrix::setDistributedMatrix(), lama::Matrix::swapMatrix(), and lama::Matrix::writeAt().

---

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

• /home/brandes/workspace/LAMA/src/lama/matrix/JDSSparseMatrix.hpp
• /home/brandes/workspace/LAMA/src/lama/matrix/JDSSparseMatrix.cpp