Wraps a CUDA solver to work with CPU data.
More...
#include <SolverAdapter.hpp>
|
using | XGPU = Opm::gpuistl::GpuVector< real_type > |
|
|
template<class Comm > |
| SolverAdapter (Operator &op, Dune::ScalarProduct< X > &sp, std::shared_ptr< Dune::Preconditioner< X, X > > prec, scalar_real_type reduction, int maxit, int verbose, const Comm &comm) |
| constructor
|
|
virtual void | apply (X &x, X &b, double reduction, Dune::InverseOperatorResult &res) override |
|
virtual void | apply (X &x, X &b, Dune::InverseOperatorResult &res) override |
|
template<
class Operator,
template<
class >
class UnderlyingSolver,
class X>
class Opm::gpuistl::SolverAdapter< Operator, UnderlyingSolver, X >
Wraps a CUDA solver to work with CPU data.
- Template Parameters
-
Operator | the Dune::LinearOperator to use |
UnderlyingSolver | a Dune solver like class, eg Dune::BiCGSTABSolver |
X | the outer type to use (eg. Dune::BlockVector<Dune::FieldVector<...>>) |
◆ SolverAdapter()
constructor
- Parameters
-
op | the linear operator (assumed CPU, the output (matrix) of which will be converted to a GPU variant) |
sp | the scalar product (assumed CPU, this will be converted to a GPU variant) |
reduction | the reduction factor passed to the iterative solver |
maxit | maximum number of iterations for the linear solver |
verbose | verbosity level |
comm | the communication object. If this is Dune::Amg::SequentialInformation, we assume a serial setup |
- Todo:
- Use a std::forward in this function
The documentation for this class was generated from the following file: