|
Discontinuous Galerkin Library
#include "dg/algorithm.h"
|
#include <map>#include <thrust/host_vector.h>#include "index.h"#include "mpi_datatype.h"#include "tensor_traits.h"#include "tensor_traits_scalar.h"#include "tensor_traits_thrust.h"#include "tensor_traits_std.h"Go to the source code of this file.
Namespaces | |
| namespace | dg |
| This is the namespace for all functions and classes defined and used by the discontinuous Galerkin library. | |
Functions | |
| template<class MessageType > | |
| std::map< int, MessageType > | dg::mpi_permute (const std::map< int, MessageType > &messages, MPI_Comm comm) |
| Exchange messages between processes in a communicator. | |
| template<class ContainerType > | |
| void | dg::mpi_gather (const thrust::host_vector< std::array< int, 2 > > &gather_map, const ContainerType &gatherFrom, ContainerType &result, MPI_Comm comm) |
| Un-optimized distributed gather operation. | |
| template<class ContainerType > | |
| void | dg::mpi_scatter (const thrust::host_vector< std::array< int, 2 > > &scatter_map, const ContainerType &toScatter, ContainerType &result, MPI_Comm comm, bool resize_result=false) |
| Un-optimized distributed scatter operation. | |
| template<class Integer > | |
| thrust::host_vector< std::array< Integer, 2 > > | dg::mpi_invert_permutation (const thrust::host_vector< std::array< Integer, 2 > > &p, MPI_Comm comm) |
| Invert a globally bijective index map. | |