#include <distributed_matrix.h>

Inheritance diagram for madness::DistributedMatrixDistribution:

[legend]

Collaboration diagram for madness::DistributedMatrixDistribution:

[legend]

Public Member Functions
	DistributedMatrixDistribution ()
	Default constructor makes an invalid distribution.
virtual	~DistributedMatrixDistribution ()
void	clear ()
	Resets state to same as default constructor.
int64_t	coldim () const
	Returns the column dimension of the matrix ... i.e., n for A(n,m).
int64_t	coltile () const
	Returns the column tile size.
const DistributedMatrixDistribution &	distribution () const
	Returns the distribution (aka *this).
void	get_colrange (int p, int64_t &ilow, int64_t &ihigh) const
	Returns the inclusive range of column indices on processor p.
void	get_range (int p, int64_t &ilow, int64_t &ihigh, int64_t &jlow, int64_t &jhigh) const
	Returns the inclusive ranges of column and row indicies on processor p.
void	get_rowrange (int p, int64_t &jlow, int64_t &jhigh) const
	Returns the inclusive range of row indices on processor p.
World &	get_world () const
	Returns the associated world.
bool	is_column_distributed () const
	Returns true if the matrix is column distributed (i.e., row dimension not distributed).
bool	is_row_distributed () const
	Returns true if the matrix is row distributed (i.e., column dimension not distributed).
int64_t	local_coldim () const
	Returns the no. of column elements stored on this processor.
void	local_colrange (int64_t &ilow, int64_t &ihigh) const
	Returns the inclusive range of column indices on this processor.
int64_t	local_ihigh () const
	Returns the last column index on this processor (-1 if no data present).
int64_t	local_ilow () const
	Returns the first column index on this processor (0 if no data present).
int64_t	local_jhigh () const
	Returns the last row index on this processor (0 if no data present).
int64_t	local_jlow () const
	Returns the first row index on this processor (0 if no data present).
int64_t	local_rowdim () const
	Returns the no. of row elements stored on this processor.
void	local_rowrange (int64_t &jlow, int64_t &jhigh) const
	Returns the inclusive range of row indices on this processor.
int64_t	local_size () const
	Returns the total no. of elements stored on this processor.
bool	operator== (const DistributedMatrixDistribution &d) const
ProcessID	owner (int64_t i, int64_t j) const
	Returns the number of the process that owns element (i,j).
int64_t	process_coldim () const
	Returns the no. of processors in the column dimension.
int64_t	process_rowdim () const
	Returns the no. of processors in the row dimension.
int64_t	rowdim () const
	Returns the row dimension of the matrix ... i.e., m for A(n,m).
int64_t	rowtile () const
	Returns the row tile size.

Protected Member Functions
	DistributedMatrixDistribution (World &world, int64_t n, int64_t m, int64_t coltile, int64_t rowtile)
	Constructs distribution and size info for a matrix (for use by factory functions only).

Protected Attributes
int64_t	idim
int64_t	ihi
	Range of column indices on this processor.
int64_t	ilo
int64_t	jdim
	Dimension of data on this processor.
int64_t	jhi
	Range of row indices on this processor.
int64_t	jlo
int64_t	m
	Row dimension of A(n,m).
int64_t	n
	Column dimension of A(n,m).
int64_t	P
	No. of processors.
int64_t	Pcol
	Column of processor grid for this processor.
int64_t	Pcoldim
	Column dimension of processor grid.
int64_t	Prow
	Row of processor grid for this processor.
int64_t	Prowdim
	Row dimension of processor grid.
World *	pworld
ProcessID	rank
	My processor rank.
int64_t	tilem
	Tile size for row.
int64_t	tilen
	Tile size for column.

Friends
DistributedMatrixDistribution	column_distributed_matrix_distribution (World &world, int64_t n, int64_t m, int64_t coltile)
	Generates distribution for an (n,m) matrix distributed by columns (row dimension is not distributed).
template<typename T>
class	DistributedMatrix
DistributedMatrixDistribution	row_distributed_matrix_distribution (World &world, int64_t n, int64_t m, int64_t rowtile)
	Generates an (n,m) matrix distribution distributed by rows (column dimension is not distributed).

Constructor & Destructor Documentation

◆ DistributedMatrixDistribution() [1/2]

madness::DistributedMatrixDistribution::DistributedMatrixDistribution	(	World &	world,
		int64_t	n,
		int64_t	m,
		int64_t	coltile,
		int64_t	rowtile )

inlineprotected

Constructs distribution and size info for a matrix (for use by factory functions only).

This routine is dumb and just copies the given arguments, hence it can easily make an invalid matrix. The smarts are in the factory functions, hence this constructor is not for general use.

The matrix is tiled over a grid of processes as specified by the tile sizes.

Parameters

[in]	world	The world
[in]	n	The matrix column dimension
[in]	m	The matrix row dimension
[in]	coltile	Tile size for the columns
[in]	rowtile	Tile size for the rows

References coltile(), idim, ihi, ilo, jdim, jhi, jlo, m, max, n, P, Pcol, Pcoldim, Prow, Prowdim, pworld, rank, rowtile(), tilem, and tilen.

Referenced by madness::DistributedMatrix< double >::DistributedMatrix(), madness::DistributedMatrix< double >::DistributedMatrix(), madness::DistributedMatrix< double >::DistributedMatrix(), madness::DistributedMatrix< double >::DistributedMatrix(), column_distributed_matrix_distribution, distribution(), operator==(), and row_distributed_matrix_distribution.

◆ DistributedMatrixDistribution() [2/2]

madness::DistributedMatrixDistribution::DistributedMatrixDistribution ( )

inline

Default constructor makes an invalid distribution.

References idim, ihi, ilo, jdim, jhi, jlo, m, n, P, Pcol, Pcoldim, Prow, Prowdim, pworld, rank, tilem, and tilen.

◆ ~DistributedMatrixDistribution()

virtual madness::DistributedMatrixDistribution::~DistributedMatrixDistribution ( )

inlinevirtual

Member Function Documentation

◆ clear()

void madness::DistributedMatrixDistribution::clear ( )

inline

Resets state to same as default constructor.

References idim, ihi, ilo, jdim, jhi, jlo, m, n, P, Pcol, Pcoldim, Prow, Prowdim, pworld, rank, tilem, and tilen.

Referenced by madness::DistributedMatrix< double >::clear().

◆ coldim()

int64_t madness::DistributedMatrixDistribution::coldim ( ) const

inline

Returns the column dimension of the matrix ... i.e., n for A(n,m).

Returns: Column dimension of the matrix ... i.e., n for A(n,m)

References n.

Referenced by madness::DistributedMatrix< double >::extract_columns().

◆ coltile()

int64_t madness::DistributedMatrixDistribution::coltile ( ) const

inline

Returns the column tile size.

Returns: Column tile size

References tilen.

Referenced by madness::DistributedMatrix< double >::DistributedMatrix(), DistributedMatrixDistribution(), column_distributed_matrix_distribution, madness::DistributedMatrix< double >::extract_columns(), and owner().

◆ distribution()

const DistributedMatrixDistribution & madness::DistributedMatrixDistribution::distribution ( ) const

inline

Returns the distribution (aka *this).

References DistributedMatrixDistribution().

Referenced by madness::Kinetic< T, NDIM >::kinetic_energy_matrix(), madness::Kinetic< T, NDIM >::kinetic_energy_matrix(), and madness::SCF::kinetic_energy_matrix().

◆ get_colrange()

void madness::DistributedMatrixDistribution::get_colrange	(	int	p,
		int64_t &	ilow,
		int64_t &	ihigh ) const

inline

Returns the inclusive range of column indices on processor p.

If is no data on processor p it returns ilow=0 and ihigh=-1

Parameters

[in]	p	The processor p of interest
[out]	ilow	The first column index on the processor
[out]	ihigh	The last column index on the processor (-1 if none)

References get_range(), and p().

◆ get_range()

void madness::DistributedMatrixDistribution::get_range	(	int	p,
		int64_t &	ilow,
		int64_t &	ihigh,
		int64_t &	jlow,
		int64_t &	jhigh ) const

inline

Returns the inclusive ranges of column and row indicies on processor p.

If is no data on processor p it returns ilow=jlow=0 and ihigh=jhigh=-1

Parameters

[in]	p	The processor p of interest
[out]	ilow	The first column index on the processor
[out]	ihigh	The last column index on the processor (-1 if none)
[out]	jlow	The first row index on the processor
[out]	jhigh	The last row index on the processor (-1 if none)

References m, n, p(), pi, process_coldim(), process_rowdim(), Prowdim, tilem, and tilen.

Referenced by get_colrange(), and get_rowrange().

◆ get_rowrange()

void madness::DistributedMatrixDistribution::get_rowrange	(	int	p,
		int64_t &	jlow,
		int64_t &	jhigh ) const

inline

Returns the inclusive range of row indices on processor p.

If is no data on processor p it returns jlow=0 and jhigh=-1

Parameters

[in]	p	The processor p of interest
[out]	jlow	The first row index on the processor
[out]	jhigh	The last row index on the processor (-1 if none)

References get_range(), and p().

◆ get_world()

World & madness::DistributedMatrixDistribution::get_world ( ) const

inline

Returns the associated world.

Returns: The world

References pworld.

Referenced by madness::DistributedMatrix< double >::copy_to_replicated(), and madness::DistributedMatrix< double >::copy_to_replicated_patch().

◆ is_column_distributed()

bool madness::DistributedMatrixDistribution::is_column_distributed ( ) const

inline

Returns true if the matrix is column distributed (i.e., row dimension not distributed).

Returns: True if the matrix is column distributed (i.e., row dimension not distributed)

References process_rowdim().

Referenced by madness::DistributedMatrix< double >::extract_columns().

◆ is_row_distributed()

bool madness::DistributedMatrixDistribution::is_row_distributed ( ) const

inline

Returns true if the matrix is row distributed (i.e., column dimension not distributed).

Returns: True if the matrix is row distributed (i.e., column dimension not distributed)

References process_coldim().

◆ local_coldim()

int64_t madness::DistributedMatrixDistribution::local_coldim ( ) const

inline

Returns the no. of column elements stored on this processor.

Returns: No. of column elements stored on this processor (may be zero)

References idim.

◆ local_colrange()

void madness::DistributedMatrixDistribution::local_colrange	(	int64_t &	ilow,
		int64_t &	ihigh ) const

inline

Returns the inclusive range of column indices on this processor.

If there is no data on this processor it returns ilow=0 and ihigh=-1

Parameters

[out]	ilow	First column index on this processor (0 if no data)
[out]	ihigh	Last column index on this processor (-1 if no data)

References ihi, and ilo.

◆ local_ihigh()

int64_t madness::DistributedMatrixDistribution::local_ihigh ( ) const

inline

Returns the last column index on this processor (-1 if no data present).

References ihi.

◆ local_ilow()

int64_t madness::DistributedMatrixDistribution::local_ilow ( ) const

inline

Returns the first column index on this processor (0 if no data present).

References ilo.

◆ local_jhigh()

int64_t madness::DistributedMatrixDistribution::local_jhigh ( ) const

inline

Returns the last row index on this processor (0 if no data present).

References jhi.

◆ local_jlow()

int64_t madness::DistributedMatrixDistribution::local_jlow ( ) const

inline

Returns the first row index on this processor (0 if no data present).

References jlo.

◆ local_rowdim()

int64_t madness::DistributedMatrixDistribution::local_rowdim ( ) const

inline

Returns the no. of row elements stored on this processor.

Returns: No. of row elements stored on this processor

References jdim.

◆ local_rowrange()

void madness::DistributedMatrixDistribution::local_rowrange	(	int64_t &	jlow,
		int64_t &	jhigh ) const

inline

Returns the inclusive range of row indices on this processor.

If there is no data on this processor it returns jlow=0 and jhigh=-1

Parameters

[out]	jlow	First row index on this processor (0 if no data)
[out]	jhigh	Last row index on this processor (-1 if no data)

References jhi, and jlo.

◆ local_size()

int64_t madness::DistributedMatrixDistribution::local_size ( ) const

inline

Returns the total no. of elements stored on this processor.

Returns: Total no. of elements stored on this processor

References idim, and jdim.

Referenced by madness::DistributedMatrix< double >::copy_from_replicated(), and madness::DistributedMatrix< double >::copy_to_replicated().

◆ operator==()

bool madness::DistributedMatrixDistribution::operator== ( const DistributedMatrixDistribution & d ) const

inline

References DistributedMatrixDistribution(), d, idim, ihi, ilo, jdim, jhi, jlo, m, n, P, Pcol, Pcoldim, Prow, Prowdim, pworld, rank, tilem, and tilen.

Referenced by madness::DistributedMatrix< double >::has_same_dimension_and_distribution().

◆ owner()

ProcessID madness::DistributedMatrixDistribution::owner	(	int64_t	i,
		int64_t	j ) const

inline

Returns the number of the process that owns element (i,j).

References coltile(), process_rowdim(), and rowtile().

◆ process_coldim()

int64_t madness::DistributedMatrixDistribution::process_coldim ( ) const

inline

Returns the no. of processors in the column dimension.

Returns: No. of processors in the column dimension

References Pcoldim.

Referenced by get_range(), and is_row_distributed().

◆ process_rowdim()

int64_t madness::DistributedMatrixDistribution::process_rowdim ( ) const

inline

Returns the no. of processors in the row dimension.

Returns: No. of processors in the rown dimension

References Prowdim.

Referenced by get_range(), is_column_distributed(), and owner().

◆ rowdim()

int64_t madness::DistributedMatrixDistribution::rowdim ( ) const

inline

Returns the row dimension of the matrix ... i.e., m for A(n,m).

Returns: Row dimension of the matrix ... i.e., m for A(n,m)

References m.

Referenced by madness::DistributedMatrix< double >::extract_columns().

◆ rowtile()

int64_t madness::DistributedMatrixDistribution::rowtile ( ) const

inline

Returns the row tile size.

Returns: Row tile size

References tilem.

Referenced by madness::DistributedMatrix< double >::DistributedMatrix(), DistributedMatrixDistribution(), owner(), and row_distributed_matrix_distribution.

◆ column_distributed_matrix_distribution

DistributedMatrixDistribution column_distributed_matrix_distribution	(	World &	world,
		int64_t	n,
		int64_t	m,
		int64_t	coltile )

friend

Generates distribution for an (n,m) matrix distributed by columns (row dimension is not distributed).

Quietly forces an even column tile size for ease of use in the systolic matrix algorithms

Parameters

[in]	world	The world
[in]	n	The column (first) dimension
[in]	m	The row (second) dimension
[in]	coltile	Tile size for columns forced to be even (default is to use all processes)