cuDSS: A high-performance CUDA Library for Direct Sparse Solvers More...

#include <cudss.hpp>

Inheritance diagram for mfem::CuDSSSolver:

Collaboration diagram for mfem::CuDSSSolver:

Public Types
enum	MatType { NONSYMMETRIC = 0 , SYMMETRIC_INDEFINITE = 1 , SYMMETRIC_POSITIVE_DEFINITE = 2 }
	Specify the type of matrix we are applying the solver to. More...

enum	MatViewType { FULL = 0 , LOWER = 1 , UPPER = 2 }
	Specify the view type of matrix we are applying the solver to. More...

Public Types inherited from mfem::Operator
enum	DiagonalPolicy { DIAG_ZERO , DIAG_ONE , DIAG_KEEP }
	Defines operator diagonal policy upon elimination of rows and/or columns. More...

enum	Type { ANY_TYPE , MFEM_SPARSEMAT , Hypre_ParCSR , PETSC_MATAIJ , PETSC_MATIS , PETSC_MATSHELL , PETSC_MATNEST , PETSC_MATHYPRE , PETSC_MATGENERIC , Complex_Operator , MFEM_ComplexSparseMat , Complex_Hypre_ParCSR , Complex_DenseMat , MFEM_Block_Matrix , MFEM_Block_Operator }
	Enumeration defining IDs for some classes derived from Operator. More...

Public Member Functions
	CuDSSSolver ()
	Constructor.

	CuDSSSolver (MPI_Comm comm)
	Constructor with MPI_Comm parameter.

	CuDSSSolver (CuDSSSolver &&)=delete

CuDSSSolver &	operator= (CuDSSSolver &&)=delete

void	SetMatrixSymType (MatType mtype_)
	Set the matrix type.

void	SetMatrixViewType (MatViewType mvtype)
	Set the matrix view type.

void	SetReorderingReuse (bool reuse)
	Set the flag controlling reuse of the symbolic factorization for multiple operators.

void	SetOperator (const Operator &op) override
	Set/update the solver for the given operator.

void	Mult (const Vector &x, Vector &y) const override
	Solve \( y = Op^{-1} x \).

void	ArrayMult (const Array< const Vector * > &X, Array< Vector * > &Y) const override
	Solve \( Y_i = Op^{-1} X_i \).

	~CuDSSSolver ()

Public Member Functions inherited from mfem::Solver
	Solver (int s=0, bool iter_mode=false)
	Initialize a square Solver with size s.

	Solver (int h, int w, bool iter_mode=false)
	Initialize a Solver with height h and width w.

Public Member Functions inherited from mfem::Operator
void	InitTVectors (const Operator Po, const Operator Ri, const Operator *Pi, Vector &x, Vector &b, Vector &X, Vector &B) const
	Initializes memory for true vectors of linear system.

	Operator (int s=0)
	Construct a square Operator with given size s (default 0).

	Operator (int h, int w)
	Construct an Operator with the given height (output size) and width (input size).

int	Height () const
	Get the height (size of output) of the Operator. Synonym with NumRows().

int	NumRows () const
	Get the number of rows (size of output) of the Operator. Synonym with Height().

int	Width () const
	Get the width (size of input) of the Operator. Synonym with NumCols().

int	NumCols () const
	Get the number of columns (size of input) of the Operator. Synonym with Width().

virtual MemoryClass	GetMemoryClass () const
	Return the MemoryClass preferred by the Operator.

virtual void	AbsMult (const Vector &x, Vector &y) const
	Action of the absolute-value operator: `y=\|A\|(x)`. The default behavior in class Operator is to generate an error. If the Operator is a composition of several operators, the composition unfold into a product of absolute-value operators too.

virtual void	MultTranspose (const Vector &x, Vector &y) const
	Action of the transpose operator: `y=A^t(x)`. The default behavior in class Operator is to generate an error.

virtual void	AbsMultTranspose (const Vector &x, Vector &y) const
	Action of the transpose absolute-value operator: `y=\|A\|^t(x)`. The default behavior in class Operator is to generate an error.

virtual void	AddMult (const Vector &x, Vector &y, const real_t a=1.0) const
	Operator application: `y+=A(x)` (default) or `y+=a*A(x)`.

virtual void	AddMultTranspose (const Vector &x, Vector &y, const real_t a=1.0) const
	Operator transpose application: `y+=A^t(x)` (default) or `y+=a*A^t(x)`.

virtual void	ArrayMultTranspose (const Array< const Vector * > &X, Array< Vector * > &Y) const
	Action of the transpose operator on a matrix: `Y=A^t(X)`.

virtual void	ArrayAddMult (const Array< const Vector * > &X, Array< Vector * > &Y, const real_t a=1.0) const
	Operator application on a matrix: `Y+=A(X)` (default) or `Y+=a*A(X)`.

virtual void	ArrayAddMultTranspose (const Array< const Vector * > &X, Array< Vector * > &Y, const real_t a=1.0) const
	Operator transpose application on a matrix: `Y+=A^t(X)` (default) or `Y+=a*A^t(X)`.

virtual void	MultMV (const MultiVector &x, MultiVector &y) const
	Operator application, y = A(x), where the input x and the output y are MultiVector objects, i.e. they generally use non-contiguous memory representation.

virtual void	MultTransposeMV (const MultiVector &x, MultiVector &y) const
	Action of the transpose operator, y = A^t(x), where the input x and the output y are MultiVector objects, i.e. they generally use non-contiguous memory representation.

virtual Operator &	GetGradient (const Vector &x) const
	Evaluate the gradient operator at the point x. The default behavior in class Operator is to generate an error.

virtual Operator &	GetGradientMV (const MultiVector &x) const
	Evaluate the gradient operator at the point x. The input x is provided as a MultiVector, i.e. it generally uses non-contiguous memory representation.

virtual void	AssembleDiagonal (Vector &diag) const
	Computes the diagonal entries into diag. Typically, this operation only makes sense for linear Operators. In some cases, only an approximation of the diagonal is computed.

virtual const Operator *	GetProlongation () const
	Prolongation operator from linear algebra (linear system) vectors, to input vectors for the operator. `NULL` means identity.

virtual const Operator *	GetRestriction () const
	Restriction operator from input vectors for the operator to linear algebra (linear system) vectors. `NULL` means identity.

virtual const Operator *	GetOutputProlongation () const
	Prolongation operator from linear algebra (linear system) vectors, to output vectors for the operator. `NULL` means identity.

virtual const Operator *	GetOutputRestrictionTranspose () const
	Transpose of GetOutputRestriction, directly available in this form to facilitate matrix-free RAP-type operators.

virtual const Operator *	GetOutputRestriction () const
	Restriction operator from output vectors for the operator to linear algebra (linear system) vectors. `NULL` means identity.

void	FormLinearSystem (const Array< int > &ess_tdof_list, Vector &x, Vector &b, Operator *&A, Vector &X, Vector &B, int copy_interior=0)
	Form a constrained linear system using a matrix-free approach.

void	FormRectangularLinearSystem (const Array< int > &trial_tdof_list, const Array< int > &test_tdof_list, Vector &x, Vector &b, Operator *&A, Vector &X, Vector &B)
	Form a column-constrained linear system using a matrix-free approach.

virtual void	RecoverFEMSolution (const Vector &X, const Vector &b, Vector &x)
	Reconstruct a solution vector x (e.g. a GridFunction) from the solution X of a constrained linear system obtained from Operator::FormLinearSystem() or Operator::FormRectangularLinearSystem().

void	FormSystemOperator (const Array< int > &ess_tdof_list, Operator *&A)
	Return in A a parallel (on truedofs) version of this square operator.

void	FormRectangularSystemOperator (const Array< int > &trial_tdof_list, const Array< int > &test_tdof_list, Operator *&A)
	Return in A a parallel (on truedofs) version of this rectangular operator (including constraints).

void	FormDiscreteOperator (Operator *&A)
	Return in A a parallel (on truedofs) version of this rectangular operator.

void	PrintMatlab (std::ostream &out, int n, int m=0) const
	Prints operator with input size n and output size m in Matlab format.

virtual void	PrintMatlab (std::ostream &out) const
	Prints operator in Matlab format.

virtual	~Operator ()
	Virtual destructor.

Type	GetType () const
	Return the type ID of the Operator class.

Additional Inherited Members
Public Attributes inherited from mfem::Solver
bool	iterative_mode
	If true, use the second argument of Mult() as an initial guess.

Protected Member Functions inherited from mfem::Operator
void	FormConstrainedSystemOperator (const Array< int > &ess_tdof_list, ConstrainedOperator *&Aout)
	see FormSystemOperator()

void	FormRectangularConstrainedSystemOperator (const Array< int > &trial_tdof_list, const Array< int > &test_tdof_list, RectangularConstrainedOperator *&Aout)
	see FormRectangularSystemOperator()

Operator *	SetupRAP (const Operator Pi, const Operator Po)
	Returns RAP Operator of this, using input/output Prolongation matrices Pi corresponds to "P", Po corresponds to "Rt".

Protected Attributes inherited from mfem::Operator
int	height
	Dimension of the output / number of rows in the matrix.

int	width
	Dimension of the input / number of columns in the matrix.

Detailed Description

cuDSS: A high-performance CUDA Library for Direct Sparse Solvers

Interface for the distributed cuDSS solver

Definition at line 37 of file cudss.hpp.

Member Enumeration Documentation

◆ MatType

enum mfem::CuDSSSolver::MatType

Specify the type of matrix we are applying the solver to.

Enumerator
NONSYMMETRIC	CUDSS_MTYPE_GENERAL: General matrix [default].
SYMMETRIC_INDEFINITE	CUDSS_MTYPE_SYMMETRIC: Real symmetric matrix.
SYMMETRIC_POSITIVE_DEFINITE	CUDSS_MTYPE_SPD: Symmetric positive-definite matrix.

Definition at line 41 of file cudss.hpp.

◆ MatViewType

enum mfem::CuDSSSolver::MatViewType

Specify the view type of matrix we are applying the solver to.

Enumerator
FULL	CUDSS_MVIEW_FULL: Full matrix [default].
LOWER	CUDSS_MVIEW_LOWER: Lower-triangular matrix (including the diagonal).
UPPER	CUDSS_MVIEW_UPPER: Upper-triangular matrix (including the diagonal).

Definition at line 52 of file cudss.hpp.

Constructor & Destructor Documentation

◆ CuDSSSolver() [1/3]

mfem::CuDSSSolver::CuDSSSolver ( )

Constructor.

Definition at line 60 of file cudss.cpp.

◆ CuDSSSolver() [2/3]

mfem::CuDSSSolver::CuDSSSolver ( MPI_Comm comm )

Constructor with MPI_Comm parameter.

Definition at line 63 of file cudss.cpp.

◆ CuDSSSolver() [3/3]

mfem::CuDSSSolver::CuDSSSolver ( CuDSSSolver && )

delete

◆ ~CuDSSSolver()

mfem::CuDSSSolver::~CuDSSSolver ( )

Definition at line 88 of file cudss.cpp.

Member Function Documentation

◆ ArrayMult()

void mfem::CuDSSSolver::ArrayMult	(	const Array< const Vector * > &	X,
		Array< Vector * > &	Y ) const

overridevirtual

Solve \( Y_i = Op^{-1} X_i \).

Parameters

X	Array of RHS vectors
Y	Array of Solution vectors

Reimplemented from mfem::Operator.

Definition at line 410 of file cudss.cpp.

◆ Mult()

void mfem::CuDSSSolver::Mult	(	const Vector &	x,
		Vector &	y ) const

overridevirtual

Solve \( y = Op^{-1} x \).

Parameters

x	RHS vector
y	Solution vector

Implements mfem::Operator.

Definition at line 401 of file cudss.cpp.

◆ operator=()

CuDSSSolver & mfem::CuDSSSolver::operator= ( CuDSSSolver && )

delete

◆ SetMatrixSymType()

void mfem::CuDSSSolver::SetMatrixSymType ( MatType mtype_ )

Set the matrix type.

Supported matrix types: CuDSSSolver::NONSYMMETRIC, CuDSSSolver::SYMMETRIC_INDEFINITE, and CuDSSSolver::SYMMETRIC_POSITIVE_DEFINITE

Parameters

mtype_ Matrix type

Note: This method has to be called before SetOperator

Definition at line 151 of file cudss.cpp.

◆ SetMatrixViewType()

void mfem::CuDSSSolver::SetMatrixViewType ( MatViewType mvtype )

Set the matrix view type.

Supported matrix types: CuDSSSolver::FULL, CuDSSSolver::LOWER, and CuDSSSolver::UPPER

Parameters

mvtype Matrix view type

Note: This method has to be called before SetOperator

Definition at line 167 of file cudss.cpp.

◆ SetOperator()

void mfem::CuDSSSolver::SetOperator ( const Operator & op )

overridevirtual

Set/update the solver for the given operator.

Implements mfem::Solver.

Definition at line 350 of file cudss.cpp.

◆ SetReorderingReuse()

void mfem::CuDSSSolver::SetReorderingReuse ( bool reuse )

Set the flag controlling reuse of the symbolic factorization for multiple operators.

Parameters

reuse Flag to reuse symbolic factorization

Note: This method has to be called before repeated calls to SetOperator

Definition at line 191 of file cudss.cpp.

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

linalg/cudss.hpp
linalg/cudss.cpp

Public Types

Public Member Functions

Additional Inherited Members

Detailed Description

Member Enumeration Documentation

◆ MatType

◆ MatViewType

Constructor & Destructor Documentation

◆ CuDSSSolver() [1/3]

◆ CuDSSSolver() [2/3]

◆ CuDSSSolver() [3/3]

◆ ~CuDSSSolver()

Member Function Documentation

◆ ArrayMult()

◆ Mult()

◆ operator=()

◆ SetMatrixSymType()

◆ SetMatrixViewType()

◆ SetOperator()

◆ SetReorderingReuse()