libMesh
Public Member Functions | Static Public Member Functions | Public Attributes | Protected Member Functions | Protected Attributes | Static Protected Attributes | List of all members
libMesh::SubdomainPartitioner Class Reference

The SubdomainPartitioner partitions the elements in "chunks" of user-specified subdomain ids. More...

#include <subdomain_partitioner.h>

Inheritance diagram for libMesh::SubdomainPartitioner:
[legend]

Public Member Functions

 SubdomainPartitioner ()
 Constructors. More...
 
 SubdomainPartitioner (const SubdomainPartitioner &other)
 
SubdomainPartitioneroperator= (const SubdomainPartitioner &)=delete
 This class contains a unique_ptr member, so it can't be default copy assigned. More...
 
 SubdomainPartitioner (SubdomainPartitioner &&)=default
 Move ctor, move assignment operator, and destructor are all explicitly defaulted for this class. More...
 
SubdomainPartitioneroperator= (SubdomainPartitioner &&)=default
 
virtual ~SubdomainPartitioner ()=default
 
virtual std::unique_ptr< Partitionerclone () const override
 
std::unique_ptr< Partitioner > & internal_partitioner ()
 Get a reference to the Partitioner used internally by the SubdomainPartitioner. More...
 
virtual void partition (MeshBase &mesh, const unsigned int n)
 Partitions the MeshBase into n parts by setting processor_id() on Nodes and Elems. More...
 
virtual void partition (MeshBase &mesh)
 Partitions the MeshBase into mesh.n_processors() by setting processor_id() on Nodes and Elems. More...
 
virtual void partition_range (MeshBase &, MeshBase::element_iterator, MeshBase::element_iterator, const unsigned int)
 Partitions elements in the range (it, end) into n parts. More...
 
void repartition (MeshBase &mesh, const unsigned int n)
 Repartitions the MeshBase into n parts. More...
 
void repartition (MeshBase &mesh)
 Repartitions the MeshBase into mesh.n_processors() parts. More...
 
virtual void attach_weights (ErrorVector *)
 Attach weights that can be used for partitioning. More...
 

Static Public Member Functions

static void partition_unpartitioned_elements (MeshBase &mesh)
 These functions assign processor IDs to newly-created elements (in parallel) which are currently assigned to processor 0. More...
 
static void partition_unpartitioned_elements (MeshBase &mesh, const unsigned int n)
 
static void set_parent_processor_ids (MeshBase &mesh)
 This function is called after partitioning to set the processor IDs for the inactive parent elements. More...
 
static void set_node_processor_ids (MeshBase &mesh)
 This function is called after partitioning to set the processor IDs for the nodes. More...
 
static void processor_pairs_to_interface_nodes (MeshBase &mesh, std::map< std::pair< processor_id_type, processor_id_type >, std::set< dof_id_type >> &processor_pair_to_nodes)
 On the partitioning interface, a surface is shared by two and only two processors. More...
 
static void set_interface_node_processor_ids_linear (MeshBase &mesh)
 Nodes on the partitioning interface is linearly assigned to each pair of processors. More...
 
static void set_interface_node_processor_ids_BFS (MeshBase &mesh)
 Nodes on the partitioning interface is clustered into two groups BFS (Breadth First Search)scheme for per pair of processors. More...
 
static void set_interface_node_processor_ids_petscpartitioner (MeshBase &mesh)
 Nodes on the partitioning interface is partitioned into two groups using a PETSc partitioner for each pair of processors. More...
 

Public Attributes

std::vector< std::set< subdomain_id_type > > chunks
 Each entry of "chunks" represents a set of subdomains which are to be partitioned together. More...
 

Protected Member Functions

virtual void _do_partition (MeshBase &mesh, const unsigned int n) override
 Partition the MeshBase into n subdomains. More...
 
void single_partition (MeshBase &mesh)
 Trivially "partitions" the mesh for one processor. More...
 
void single_partition_range (MeshBase::element_iterator it, MeshBase::element_iterator end)
 Slightly generalized version of single_partition which acts on a range of elements defined by the pair of iterators (it, end). More...
 
virtual void _do_repartition (MeshBase &mesh, const unsigned int n)
 This is the actual re-partitioning method which can be overridden in derived classes. More...
 
virtual void _find_global_index_by_pid_map (const MeshBase &mesh)
 Construct contiguous global indices for the current partitioning. More...
 
virtual void build_graph (const MeshBase &mesh)
 Build a dual graph for partitioner. More...
 
void assign_partitioning (const MeshBase &mesh, const std::vector< dof_id_type > &parts)
 Assign the computed partitioning to the mesh. More...
 

Protected Attributes

std::unique_ptr< Partitioner_internal_partitioner
 The internal Partitioner we use. More...
 
ErrorVector_weights
 The weights that might be used for partitioning. More...
 
std::unordered_map< dof_id_type, dof_id_type_global_index_by_pid_map
 Maps active element ids into a contiguous range, as needed by parallel partitioner. More...
 
std::vector< dof_id_type_n_active_elem_on_proc
 The number of active elements on each processor. More...
 
std::vector< std::vector< dof_id_type > > _dual_graph
 A dual graph corresponds to the mesh, and it is typically used in paritioner. More...
 
std::vector< Elem * > _local_id_to_elem
 

Static Protected Attributes

static const dof_id_type communication_blocksize
 The blocksize to use when doing blocked parallel communication. More...
 

Detailed Description

The SubdomainPartitioner partitions the elements in "chunks" of user-specified subdomain ids.

Once all the chunks are partitioned, the overall mesh partitioning is simply the union of the chunk partitionings. For example, if the "chunks" vector is given by: chunks[0] = {1, 2, 4} chunks[1] = {3, 7, 8} chunks[2] = {5, 6} then we will call the internal Partitioner three times, once for subdomains 1, 2, and 4, once for subdomains 3, 7, and 8, and once for subdomains 5 and 6.

Note
This Partitioner may produce highly non-optimal communication patterns and is likely to place geometrically disjoint sets of elements on the same processor. Its intended use is to help facilitate load balancing. That is, if the user knows that certain subdomains (or groups of subdomains) are more expensive to compute than others, he/she can ensure that they are partitioned more or less evenly among the available processors by specifying them together in a single entry of the "chunk" vector.
Author
John W. Peterson
Date
2017 Independently partitions chunks of subdomains and combines the results.

Definition at line 55 of file subdomain_partitioner.h.

Constructor & Destructor Documentation

◆ SubdomainPartitioner() [1/3]

libMesh::SubdomainPartitioner::SubdomainPartitioner ( )

Constructors.

The default ctor initializes the internal Partitioner object to a MetisPartitioner so the class is usable, although this type can be customized later.

◆ SubdomainPartitioner() [2/3]

libMesh::SubdomainPartitioner::SubdomainPartitioner ( const SubdomainPartitioner other)

◆ SubdomainPartitioner() [3/3]

libMesh::SubdomainPartitioner::SubdomainPartitioner ( SubdomainPartitioner &&  )
default

Move ctor, move assignment operator, and destructor are all explicitly defaulted for this class.

◆ ~SubdomainPartitioner()

virtual libMesh::SubdomainPartitioner::~SubdomainPartitioner ( )
virtualdefault

Member Function Documentation

◆ _do_partition()

virtual void libMesh::SubdomainPartitioner::_do_partition ( MeshBase mesh,
const unsigned int  n 
)
overrideprotectedvirtual

Partition the MeshBase into n subdomains.

Implements libMesh::Partitioner.

◆ _do_repartition()

virtual void libMesh::Partitioner::_do_repartition ( MeshBase mesh,
const unsigned int  n 
)
protectedvirtualinherited

This is the actual re-partitioning method which can be overridden in derived classes.

Note
The default behavior is to simply call the partition function.

Reimplemented in libMesh::ParmetisPartitioner.

Definition at line 237 of file partitioner.h.

References libMesh::Partitioner::_do_partition().

238  { this->_do_partition (mesh, n); }
virtual void _do_partition(MeshBase &mesh, const unsigned int n)=0
This is the actual partitioning method which must be overridden in derived classes.

◆ _find_global_index_by_pid_map()

virtual void libMesh::Partitioner::_find_global_index_by_pid_map ( const MeshBase mesh)
protectedvirtualinherited

Construct contiguous global indices for the current partitioning.

The global indices are ordered part-by-part

◆ assign_partitioning()

void libMesh::Partitioner::assign_partitioning ( const MeshBase mesh,
const std::vector< dof_id_type > &  parts 
)
protectedinherited

Assign the computed partitioning to the mesh.

◆ attach_weights()

virtual void libMesh::Partitioner::attach_weights ( ErrorVector )
virtualinherited

Attach weights that can be used for partitioning.

This ErrorVector should be exactly the same on every processor and should have mesh->max_elem_id() entries.

Reimplemented in libMesh::MetisPartitioner.

Definition at line 203 of file partitioner.h.

203 { libmesh_not_implemented(); }

◆ build_graph()

virtual void libMesh::Partitioner::build_graph ( const MeshBase mesh)
protectedvirtualinherited

Build a dual graph for partitioner.

Reimplemented in libMesh::ParmetisPartitioner.

◆ clone()

virtual std::unique_ptr<Partitioner> libMesh::SubdomainPartitioner::clone ( ) const
overridevirtual
Returns
A copy of this partitioner wrapped in a smart pointer.

Implements libMesh::Partitioner.

Definition at line 84 of file subdomain_partitioner.h.

85  {
86  return libmesh_make_unique<SubdomainPartitioner>(*this);
87  }

◆ internal_partitioner()

std::unique_ptr<Partitioner>& libMesh::SubdomainPartitioner::internal_partitioner ( )

Get a reference to the Partitioner used internally by the SubdomainPartitioner.

Note
The internal Partitioner cannot also be a SubdomainPartitioner, otherwise an infinite loop will result. To have this class use e.g. the space-filling curve Partitioner internally, one could do:
sp.internal_partitioner().reset(new SFCPartitioner);

Definition at line 111 of file subdomain_partitioner.h.

References _internal_partitioner.

111 { return _internal_partitioner; }
std::unique_ptr< Partitioner > _internal_partitioner
The internal Partitioner we use.

◆ operator=() [1/2]

SubdomainPartitioner& libMesh::SubdomainPartitioner::operator= ( const SubdomainPartitioner )
delete

This class contains a unique_ptr member, so it can't be default copy assigned.

◆ operator=() [2/2]

SubdomainPartitioner& libMesh::SubdomainPartitioner::operator= ( SubdomainPartitioner &&  )
default

◆ partition() [1/2]

virtual void libMesh::Partitioner::partition ( MeshBase mesh,
const unsigned int  n 
)
virtualinherited

Partitions the MeshBase into n parts by setting processor_id() on Nodes and Elems.

Note
If you are implementing a new type of Partitioner, you most likely do not want to override the partition() function, see instead the protected virtual _do_partition() method below. The partition() function is responsible for doing a lot of libmesh-internals-specific setup and finalization before and after the _do_partition() function is called. The only responsibility of the _do_partition() function, on the other hand, is to set the processor IDs of the elements according to a specific partitioning algorithm. See, e.g. MetisPartitioner for an example.

◆ partition() [2/2]

virtual void libMesh::Partitioner::partition ( MeshBase mesh)
virtualinherited

Partitions the MeshBase into mesh.n_processors() by setting processor_id() on Nodes and Elems.

Note
If you are implementing a new type of Partitioner, you most likely do not want to override the partition() function, see instead the protected virtual _do_partition() method below. The partition() function is responsible for doing a lot of libmesh-internals-specific setup and finalization before and after the _do_partition() function is called. The only responsibility of the _do_partition() function, on the other hand, is to set the processor IDs of the elements according to a specific partitioning algorithm. See, e.g. MetisPartitioner for an example.

◆ partition_range()

virtual void libMesh::Partitioner::partition_range ( MeshBase ,
MeshBase::element_iterator  ,
MeshBase::element_iterator  ,
const unsigned int   
)
virtualinherited

Partitions elements in the range (it, end) into n parts.

The mesh from which the iterators are created must also be passed in, since it is a parallel object and has other useful information in it.

Although partition_range() is part of the public Partitioner interface, it should not generally be called by applications. Its main purpose is to support the SubdomainPartitioner, which uses it internally to individually partition ranges of elements before combining them into the final partitioning. Most of the time, the protected _do_partition() function is implemented in terms of partition_range() by passing a range which includes all the elements of the Mesh.

Reimplemented in libMesh::CentroidPartitioner, libMesh::SFCPartitioner, libMesh::MappedSubdomainPartitioner, libMesh::LinearPartitioner, and libMesh::MetisPartitioner.

Definition at line 127 of file partitioner.h.

131  { libmesh_not_implemented(); }

◆ partition_unpartitioned_elements() [1/2]

static void libMesh::Partitioner::partition_unpartitioned_elements ( MeshBase mesh)
staticinherited

These functions assign processor IDs to newly-created elements (in parallel) which are currently assigned to processor 0.

◆ partition_unpartitioned_elements() [2/2]

static void libMesh::Partitioner::partition_unpartitioned_elements ( MeshBase mesh,
const unsigned int  n 
)
staticinherited

◆ processor_pairs_to_interface_nodes()

static void libMesh::Partitioner::processor_pairs_to_interface_nodes ( MeshBase mesh,
std::map< std::pair< processor_id_type, processor_id_type >, std::set< dof_id_type >> &  processor_pair_to_nodes 
)
staticinherited

On the partitioning interface, a surface is shared by two and only two processors.

Try to find which pair of processors corresponds to which surfaces, and store their nodes.

◆ repartition() [1/2]

void libMesh::Partitioner::repartition ( MeshBase mesh,
const unsigned int  n 
)
inherited

Repartitions the MeshBase into n parts.

(Some partitioning algorithms can repartition more efficiently than computing a new partitioning from scratch.) The default behavior is to simply call this->partition(mesh,n).

◆ repartition() [2/2]

void libMesh::Partitioner::repartition ( MeshBase mesh)
inherited

Repartitions the MeshBase into mesh.n_processors() parts.

This is required since some partitioning algorithms can repartition more efficiently than computing a new partitioning from scratch.

◆ set_interface_node_processor_ids_BFS()

static void libMesh::Partitioner::set_interface_node_processor_ids_BFS ( MeshBase mesh)
staticinherited

Nodes on the partitioning interface is clustered into two groups BFS (Breadth First Search)scheme for per pair of processors.

◆ set_interface_node_processor_ids_linear()

static void libMesh::Partitioner::set_interface_node_processor_ids_linear ( MeshBase mesh)
staticinherited

Nodes on the partitioning interface is linearly assigned to each pair of processors.

◆ set_interface_node_processor_ids_petscpartitioner()

static void libMesh::Partitioner::set_interface_node_processor_ids_petscpartitioner ( MeshBase mesh)
staticinherited

Nodes on the partitioning interface is partitioned into two groups using a PETSc partitioner for each pair of processors.

◆ set_node_processor_ids()

static void libMesh::Partitioner::set_node_processor_ids ( MeshBase mesh)
staticinherited

This function is called after partitioning to set the processor IDs for the nodes.

By definition, a Node's processor ID is the minimum processor ID for all of the elements which share the node.

◆ set_parent_processor_ids()

static void libMesh::Partitioner::set_parent_processor_ids ( MeshBase mesh)
staticinherited

This function is called after partitioning to set the processor IDs for the inactive parent elements.

A parent's processor ID is the same as its first child.

◆ single_partition()

void libMesh::Partitioner::single_partition ( MeshBase mesh)
protectedinherited

Trivially "partitions" the mesh for one processor.

Simply loops through the elements and assigns all of them to processor 0. Is is provided as a separate function so that derived classes may use it without reimplementing it.

◆ single_partition_range()

void libMesh::Partitioner::single_partition_range ( MeshBase::element_iterator  it,
MeshBase::element_iterator  end 
)
protectedinherited

Slightly generalized version of single_partition which acts on a range of elements defined by the pair of iterators (it, end).

Member Data Documentation

◆ _dual_graph

std::vector<std::vector<dof_id_type> > libMesh::Partitioner::_dual_graph
protectedinherited

A dual graph corresponds to the mesh, and it is typically used in paritioner.

A vertex represents an element, and its neighbors are the element neighbors.

Definition at line 288 of file partitioner.h.

◆ _global_index_by_pid_map

std::unordered_map<dof_id_type, dof_id_type> libMesh::Partitioner::_global_index_by_pid_map
protectedinherited

Maps active element ids into a contiguous range, as needed by parallel partitioner.

Definition at line 272 of file partitioner.h.

◆ _internal_partitioner

std::unique_ptr<Partitioner> libMesh::SubdomainPartitioner::_internal_partitioner
protected

The internal Partitioner we use.

Public access via the internal_partitioner() member function.

Definition at line 118 of file subdomain_partitioner.h.

Referenced by internal_partitioner().

◆ _local_id_to_elem

std::vector<Elem *> libMesh::Partitioner::_local_id_to_elem
protectedinherited

Definition at line 291 of file partitioner.h.

◆ _n_active_elem_on_proc

std::vector<dof_id_type> libMesh::Partitioner::_n_active_elem_on_proc
protectedinherited

The number of active elements on each processor.

Note
ParMETIS requires that each processor have some active elements; it will abort if any processor passes a nullptr _part array.

Definition at line 281 of file partitioner.h.

◆ _weights

ErrorVector* libMesh::Partitioner::_weights
protectedinherited

The weights that might be used for partitioning.

Definition at line 267 of file partitioner.h.

Referenced by libMesh::MetisPartitioner::attach_weights().

◆ chunks

std::vector<std::set<subdomain_id_type> > libMesh::SubdomainPartitioner::chunks

Each entry of "chunks" represents a set of subdomains which are to be partitioned together.

The internal Partitioner will be called once for each entry of chunks, and the resulting partitioning will simply be the union of all these partitionings.

Definition at line 95 of file subdomain_partitioner.h.

◆ communication_blocksize

const dof_id_type libMesh::Partitioner::communication_blocksize
staticprotectedinherited

The blocksize to use when doing blocked parallel communication.

This limits the maximum vector size which can be used in a single communication step.

Definition at line 244 of file partitioner.h.


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