plb::ExplicitThreadAttribution Class Reference

#include <threadAttribution.h>

Inheritance diagram for plb::ExplicitThreadAttribution:

[legend]

Collaboration diagram for plb::ExplicitThreadAttribution:

[legend]

List of all members.

Public Member Functions
	ExplicitThreadAttribution ()
	ExplicitThreadAttribution (std::map< plint, plint > const &mpiProcessAttribution_)
	ExplicitThreadAttribution (std::map< plint, plint > const &mpiProcessAttribution_, std::map< plint, plint > const &localThreadAttribution_)
void	addBlock (plint blockId, plint mpiProcess, plint localThread=0)
virtual bool	isLocal (plint blockId) const
	Specifies if the block "blockId" is located on the current MPI thread.
virtual bool	allBlocksAreLocal () const
virtual int	getMpiProcess (plint blockId) const
	Specifies on which MPI process a given block is located.
virtual int	getLocalThreadId (plint blockId) const
virtual ThreadAttribution *	merge (ThreadAttribution const &rhs, std::map< plint, std::vector< plint > > const &remappedIds) const
virtual ThreadAttribution *	extend (std::vector< plint > const &ids, std::vector< plint > const &mpiProcesses, std::vector< plint > const &localThreads) const
virtual bool	hasCoProcessors () const
virtual void	setCoProcessors (std::map< plint, int > processorHandles)
virtual int	getCoProcessorHandle (plint id) const
virtual ThreadAttribution *	clone () const

---

Constructor & Destructor Documentation

plb::ExplicitThreadAttribution::ExplicitThreadAttribution

(

)

Referenced by clone(), extend(), and merge().

plb::ExplicitThreadAttribution::ExplicitThreadAttribution

(

std::map< plint, plint > const &

mpiProcessAttribution_

)

plb::ExplicitThreadAttribution::ExplicitThreadAttribution	(	std::map< plint, plint > const &	mpiProcessAttribution_,
		std::map< plint, plint > const &	localThreadAttribution_
	)

---

Member Function Documentation

void plb::ExplicitThreadAttribution::addBlock	(	plint	blockId,
		plint	mpiProcess,
		plint	localThread = 0
	)

Referenced by plb::generateLattices(), plb::generateTensorFields(), merge(), plb::OneToOneThreadAttribution::merge(), and plb::RandomRedistribute3D::redistribute().

bool plb::ExplicitThreadAttribution::allBlocksAreLocal

(

)

const [virtual]

True means that all blocks are local, false means we don't know if all of them are local or not.

Implements plb::ThreadAttribution.

ThreadAttribution * plb::ExplicitThreadAttribution::clone

(

)

const [virtual]

Implements plb::ThreadAttribution.

References ExplicitThreadAttribution().

ThreadAttribution * plb::ExplicitThreadAttribution::extend	(	std::vector< plint > const &	ids,
		std::vector< plint > const &	mpiProcesses,
		std::vector< plint > const &	localThreads
	)			const [virtual]

Extend the current attribution by a selection of new identifiers, with explicitly specified mpiProcess and thread attribution.

Implements plb::ThreadAttribution.

References ExplicitThreadAttribution(), and PLB_PRECONDITION.

virtual int plb::ExplicitThreadAttribution::getCoProcessorHandle

(

plint

id

)

const [inline, virtual]

Reimplemented from plb::ThreadAttribution.

int plb::ExplicitThreadAttribution::getLocalThreadId

(

plint

blockId

)

const [virtual]

Specifies to which of the local shared-memory threads the blockId belongs.

Implements plb::ThreadAttribution.

int plb::ExplicitThreadAttribution::getMpiProcess

(

plint

blockId

)

const [virtual]

Specifies on which MPI process a given block is located.

Implements plb::ThreadAttribution.

virtual bool plb::ExplicitThreadAttribution::hasCoProcessors

(

)

const [inline, virtual]

Reimplemented from plb::ThreadAttribution.

bool plb::ExplicitThreadAttribution::isLocal

(

plint

blockId

)

const [virtual]

Specifies if the block "blockId" is located on the current MPI thread.

Implements plb::ThreadAttribution.

References plb::global::mpi().

ThreadAttribution * plb::ExplicitThreadAttribution::merge	(	ThreadAttribution const &	rhs,
		std::map< plint, std::vector< plint > > const &	remappedIds
	)			const [virtual]

Merge current attribution with rhs. From rhs, select explicitly the specified blocks, and remap them to fit into the new attribution, as specified by the parameter remappedIds.

Implements plb::ThreadAttribution.

References addBlock(), ExplicitThreadAttribution(), plb::ThreadAttribution::getLocalThreadId(), and plb::ThreadAttribution::getMpiProcess().

virtual void plb::ExplicitThreadAttribution::setCoProcessors

(

std::map< plint, int >

processorHandles

)

[inline, virtual]

Reimplemented from plb::ThreadAttribution.

---

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

• threadAttribution.h
• threadAttribution.cpp