CUDA compatiable variant of Dune::OwnerOverlapCopyCommunication. More...

#include <GpuOwnerOverlapCopy.hpp>

Public Types
using	X = GpuVector<field_type>

Public Member Functions
	GpuOwnerOverlapCopy (std::shared_ptr< GPUSender< field_type, OwnerOverlapCopyCommunicationType > > sender)
void	copyOwnerToAll (const X &source, X &dest) const
void	dot (const X &x, const X &y, field_type &output) const
field_type	norm (const X &x) const
void	project (X &x) const
const ::Dune::Communication< MPI_Comm > &	communicator () const
	communicator returns the MPI communicator used by this GpuOwnerOverlapCopy

Detailed Description

template<class field_type, class OwnerOverlapCopyCommunicationType>
class Opm::gpuistl::GpuOwnerOverlapCopy< field_type, OwnerOverlapCopyCommunicationType >

CUDA compatiable variant of Dune::OwnerOverlapCopyCommunication.

This class can essentially be seen as an adapter around Dune::OwnerOverlapCopyCommunication, and should work as a Dune::OwnerOverlapCopyCommunication on GpuVectors

Note: This currently only has the functionality to parallelize the linear solve.

Template Parameters

field_type	should be a field_type supported by GpuVector (double, float)
OwnerOverlapCopyCommunicationType	should mimic Dune::OwnerOverlapCopyCommunication.

Member Function Documentation

◆ communicator()

template<class field_type, class OwnerOverlapCopyCommunicationType>

const ::Dune::Communication< MPI_Comm > & Opm::gpuistl::GpuOwnerOverlapCopy< field_type, OwnerOverlapCopyCommunicationType >::communicator ( ) const

inline

communicator returns the MPI communicator used by this GpuOwnerOverlapCopy

Returns: the MPI communicator

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

opm/simulators/linalg/gpuistl/GpuOwnerOverlapCopy.hpp

Public Types

Public Member Functions

Detailed Description

Member Function Documentation

◆ communicator()