Tools for distributed graphs. More...

Functions
std::tuple< graph::AdjacencyList< std::int64_t >, std::vector< int >, std::vector< std::int64_t >, std::vector< int > >	distribute (MPI_Comm comm, const graph::AdjacencyList< std::int64_t > &list, const graph::AdjacencyList< std::int32_t > &destinations)
	Distribute adjacency list nodes to destination ranks. The global index of each node is assumed to be the local index plus the offset for this rank. More...

std::vector< std::int64_t >	compute_ghost_indices (MPI_Comm comm, const xtl::span< const std::int64_t > &global_indices, const xtl::span< const int > &ghost_owners)
	Compute ghost indices in a global IndexMap space, from a list of arbitrary global indices, where the ghosts are at the end of the list, and their owning processes are known. More...

template<typename T >
xt::xtensor< T, 2 >	distribute_data (MPI_Comm comm, const xtl::span< const std::int64_t > &indices, const xt::xtensor< T, 2 > &x)
	Distribute data to process ranks where it it required. More...

std::vector< std::int64_t >	compute_local_to_global_links (const graph::AdjacencyList< std::int64_t > &global, const graph::AdjacencyList< std::int32_t > &local)
	Given an adjacency list with global, possibly non-contiguous, link indices and a local adjacency list with contiguous link indices starting from zero, compute a local-to-global map for the links. Both adjacency lists must have the same shape. More...

std::vector< std::int32_t >	compute_local_to_local (const xtl::span< const std::int64_t > &local0_to_global, const xtl::span< const std::int64_t > &local1_to_global)
	Compute a local0-to-local1 map from two local-to-global maps with common global indices. More...

Detailed Description

Tools for distributed graphs.

Todo:: Add a function that sends data to the 'owner'

Function Documentation

◆ compute_ghost_indices()

std::vector< std::int64_t > dolfinx::graph::build::compute_ghost_indices	(	MPI_Comm	comm,
		const xtl::span< const std::int64_t > &	global_indices,
		const xtl::span< const int > &	ghost_owners
	)

Compute ghost indices in a global IndexMap space, from a list of arbitrary global indices, where the ghosts are at the end of the list, and their owning processes are known.

Parameters

[in]	comm	MPI communicator
[in]	global_indices	List of arbitrary global indices, ghosts at end
[in]	ghost_owners	List of owning processes of the ghost indices

Returns: Indexing of ghosts in a global space starting from 0 on process 0

◆ compute_local_to_global_links()

std::vector< std::int64_t > dolfinx::graph::build::compute_local_to_global_links	(	const graph::AdjacencyList< std::int64_t > &	global,
		const graph::AdjacencyList< std::int32_t > &	local
	)

Given an adjacency list with global, possibly non-contiguous, link indices and a local adjacency list with contiguous link indices starting from zero, compute a local-to-global map for the links. Both adjacency lists must have the same shape.

Parameters

[in]	global	Adjacency list with global link indices
[in]	local	Adjacency list with local, contiguous link indices

Returns: Map from local index to global index, which if applied to the local adjacency list indices would yield the global adjacency list

◆ compute_local_to_local()

std::vector< std::int32_t > dolfinx::graph::build::compute_local_to_local	(	const xtl::span< const std::int64_t > &	local0_to_global,
		const xtl::span< const std::int64_t > &	local1_to_global
	)

Compute a local0-to-local1 map from two local-to-global maps with common global indices.

Parameters

[in]	local0_to_global	Map from local0 indices to global indices
[in]	local1_to_global	Map from local1 indices to global indices

Returns: Map from local0 indices to local1 indices

◆ distribute()

std::tuple< graph::AdjacencyList< std::int64_t >, std::vector< int >, std::vector< std::int64_t >, std::vector< int > > dolfinx::graph::build::distribute	(	MPI_Comm	comm,
		const graph::AdjacencyList< std::int64_t > &	list,
		const graph::AdjacencyList< std::int32_t > &	destinations
	)

Distribute adjacency list nodes to destination ranks. The global index of each node is assumed to be the local index plus the offset for this rank.

Parameters

[in]	comm	MPI Communicator
[in]	list	The adjacency list to distribute
[in]	destinations	Destination ranks for the ith node in the adjacency list

Returns: Adjacency list for this process, array of source ranks for each node in the adjacency list, and the original global index for each node.

◆ distribute_data()

template<typename T >

xt::xtensor< T, 2 > dolfinx::graph::build::distribute_data	(	MPI_Comm	comm,
		const xtl::span< const std::int64_t > &	indices,
		const xt::xtensor< T, 2 > &	x
	)

Distribute data to process ranks where it it required.

Parameters

[in]	comm	The MPI communicator
[in]	indices	Global indices of the data required by this process
[in]	x	Data on this process which may be distributed (by row). The global index for the [0, ..., n) local rows is assumed to be the local index plus the offset for this rank

Returns: The data for each index in indices

Functions

Detailed Description

Function Documentation

◆ compute_ghost_indices()

◆ compute_local_to_global_links()

◆ compute_local_to_local()

◆ distribute()

◆ distribute_data()