This class implements a rocsparse-based ilu0-bicgstab solver on GPU. More...

Inheritance diagram for Opm::Accelerator::rocsparseSolverBackend< Scalar, block_size >:

Public Member Functions
	rocsparseSolverBackend (int linear_solver_verbosity, int maxit, Scalar tolerance, unsigned int platformID, unsigned int deviceID, std::string linsolver)
	Construct a rocsparseSolver.
	rocsparseSolverBackend (int linear_solver_verbosity, int maxit, Scalar tolerance, bool opencl_ilu_reorder)
	For the CPR coarse solver.
	~rocsparseSolverBackend ()
	Destroy a openclSolver, and free memory.
SolverStatus	solve_system (std::shared_ptr< BlockedMatrix< Scalar > > matrix, Scalar *b, std::shared_ptr< BlockedMatrix< Scalar > > jacMatrix, WellContributions< Scalar > &wellContribs, GpuResult &res) override
	Solve linear system, A*x = b, matrix A must be in blocked-CSR format.
void	get_result (Scalar *x) override
	Get result after linear solve, and peform postprocessing if necessary.
Public Member Functions inherited from Opm::Accelerator::GpuSolver< Scalar, block_size >
	GpuSolver (int linear_solver_verbosity, int max_it, Scalar tolerance_)
	Construct a GpuSolver.
	GpuSolver (int linear_solver_verbosity, int max_it, Scalar tolerance_, unsigned int deviceID_)
	GpuSolver (int linear_solver_verbosity, int max_it, double tolerance_, unsigned int platformID_, unsigned int deviceID_)
virtual	~GpuSolver ()=default
	Define virtual destructor, so that the derivedclass destructor will be called.

Additional Inherited Members
Protected Attributes inherited from Opm::Accelerator::GpuSolver< Scalar, block_size >
int	verbosity = 0
int	maxit = 200
Scalar	tolerance = 1e-2
int	N
int	Nb
int	nnz
int	nnzb
unsigned int	platformID = 0
unsigned int	deviceID = 0
bool	initialized = false

Detailed Description

template<class Scalar, unsigned int block_size>
class Opm::Accelerator::rocsparseSolverBackend< Scalar, block_size >

This class implements a rocsparse-based ilu0-bicgstab solver on GPU.

Constructor & Destructor Documentation

template<class Scalar, unsigned int block_size>

Opm::Accelerator::rocsparseSolverBackend< Scalar, block_size >::rocsparseSolverBackend	(	int	linear_solver_verbosity,
		int	maxit,
		Scalar	tolerance,
		unsigned int	platformID,
		unsigned int	deviceID,
		std::string	linsolver )

Construct a rocsparseSolver.

Parameters

[in]	linear_solver_verbosity	verbosity of rocsparseSolver
[in]	maxit	maximum number of iterations for rocsparseSolver
[in]	tolerance	required relative tolerance for rocsparseSolver
[in]	platformID	the OpenCL platform to be used
[in]	deviceID	the device to be used
[in]	linsolver	indicating the preconditioner, equal to the –linear-solver cmdline argument

template<class Scalar, unsigned int block_size>

void Opm::Accelerator::rocsparseSolverBackend< Scalar, block_size >::get_result ( Scalar * x )

overridevirtual

Get result after linear solve, and peform postprocessing if necessary.

Parameters

[in,out] x resulting x vector, caller must guarantee that x points to a valid array

template<class Scalar, unsigned int block_size>

SolverStatus Opm::Accelerator::rocsparseSolverBackend< Scalar, block_size >::solve_system	(	std::shared_ptr< BlockedMatrix< Scalar > >	matrix,
		Scalar *	b,
		std::shared_ptr< BlockedMatrix< Scalar > >	jacMatrix,
		WellContributions< Scalar > &	wellContribs,
		GpuResult &	res )

overridevirtual

Solve linear system, A*x = b, matrix A must be in blocked-CSR format.

Parameters

[in]	matrix	matrix A
[in]	b	input vector, contains N values
[in]	jacMatrix	matrix for preconditioner
[in]	wellContribs	WellContributions, to apply them separately, instead of adding them to matrix A
[in,out]	res	summary of solver result

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