Peano

Searching...

No Matches

A hard coded strategy that can realise a few standard tasking patterns. More...

#include <SamplingMulticoreOrchestration.h>

Inheritance diagram for tarch::multicore::orchestration::GeneticOptimisation:

[legend]

Collaboration diagram for tarch::multicore::orchestration::GeneticOptimisation:

[legend]

Data Structures
struct	Key

struct	Value

Public Member Functions
	GeneticOptimisation ()

virtual	~GeneticOptimisation ()=default

virtual void	startBSPSection () override

virtual void	endBSPSection () override

virtual int	getNumberOfTasksToHoldBack () override

virtual FuseInstruction	getNumberOfTasksToFuseAndTargetDevice () override

virtual bool	fuseTasksImmediatelyWhenSpawned () override

virtual ExecutionPolicy	paralleliseForkJoinSection (int nestedParallelismLevel, int numberOfTasks, int taskType) override
	Determine how to handle/realise parallelisation within fork/join region.

Public Member Functions inherited from tarch::multicore::orchestration::Strategy
virtual	~Strategy ()=default

virtual void	startBSPSection (int nestedParallelismLevel)=0
	Notifies the strategy that we enter a BSP section.

virtual void	endBSPSection (int nestedParallelismLevel)=0
	Notifies the strategy that we leave a BSP (fork-join) section.

virtual FuseInstruction	fuse (int taskType)=0
	How many tasks shall system hold back from tasking runtime in user-defined queues.

Private Member Functions
void	createInitialConfigurations ()

void	normalise ()

void	increaseProbabilityOfActiveConfiguration ()

void	removeUnreasonableProbabilities ()

void	pickNewActiveConfigurationRandomly ()

Private Attributes
std::map< Key, Value >	_configurationVariants

Key	_activeKey

tarch::timing::Watch	_currentWatch

double	_lastDuration

int	_bspRunThroughsWithActiveKey

int	_currentDevice

Static Private Attributes
static tarch::logging::Log	_log

Additional Inherited Members
Public Types inherited from tarch::multicore::orchestration::Strategy
enum class	ExecutionPolicy { RunSerially , RunParallel }
	Provide hint of execution policy. More...

Static Public Attributes inherited from tarch::multicore::orchestration::Strategy
static constexpr int	EndOfBSPSection = -1

Detailed Description

A hard coded strategy that can realise a few standard tasking patterns.

Definition at line 25 of file SamplingMulticoreOrchestration.h.

Constructor & Destructor Documentation

◆ GeneticOptimisation()

tarch::multicore::orchestration::GeneticOptimisation::GeneticOptimisation ( )

Definition at line 43 of file SamplingMulticoreOrchestration.cpp.

References createInitialConfigurations(), and normalise().

Here is the call graph for this function:

◆ ~GeneticOptimisation()

virtual tarch::multicore::orchestration::GeneticOptimisation::~GeneticOptimisation ( )

virtualdefault

Member Function Documentation

◆ createInitialConfigurations()

void tarch::multicore::orchestration::GeneticOptimisation::createInitialConfigurations ( )

private

Definition at line 53 of file SamplingMulticoreOrchestration.cpp.

References tarch::multicore::Core::getInstance().

Referenced by GeneticOptimisation().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ endBSPSection()

void tarch::multicore::orchestration::GeneticOptimisation::endBSPSection ( )

overridevirtual

Definition at line 98 of file SamplingMulticoreOrchestration.cpp.

◆ fuseTasksImmediatelyWhenSpawned()

bool tarch::multicore::orchestration::GeneticOptimisation::fuseTasksImmediatelyWhenSpawned ( )

overridevirtual

Definition at line 234 of file SamplingMulticoreOrchestration.cpp.

Referenced by tarch::multicore::orchestration::GeneticOptimisation::Key::operator<(), and tarch::multicore::orchestration::GeneticOptimisation::Key::toString().

Here is the caller graph for this function:

◆ getNumberOfTasksToFuseAndTargetDevice()

tarch::multicore::orchestration::GeneticOptimisation::FuseInstruction tarch::multicore::orchestration::GeneticOptimisation::getNumberOfTasksToFuseAndTargetDevice ( )

overridevirtual

Definition at line 225 of file SamplingMulticoreOrchestration.cpp.

References tarch::multicore::Core::getInstance().

Here is the call graph for this function:

◆ getNumberOfTasksToHoldBack()

int tarch::multicore::orchestration::GeneticOptimisation::getNumberOfTasksToHoldBack ( )

overridevirtual

Definition at line 221 of file SamplingMulticoreOrchestration.cpp.

◆ increaseProbabilityOfActiveConfiguration()

void tarch::multicore::orchestration::GeneticOptimisation::increaseProbabilityOfActiveConfiguration ( )

private

Definition at line 128 of file SamplingMulticoreOrchestration.cpp.

References logInfo, and tarch::multicore::orchestration::GeneticOptimisation::Key::toString().

Here is the call graph for this function:

◆ normalise()

void tarch::multicore::orchestration::GeneticOptimisation::normalise ( )

private

Definition at line 76 of file SamplingMulticoreOrchestration.cpp.

References logInfo.

Referenced by GeneticOptimisation().

Here is the caller graph for this function:

◆ paralleliseForkJoinSection()

tarch::multicore::orchestration::Strategy::ExecutionPolicy tarch::multicore::orchestration::GeneticOptimisation::paralleliseForkJoinSection	(	int	nestedParallelismLevel,
		int	numberOfTasks,
		int	taskType )

overridevirtual

Determine how to handle/realise parallelisation within fork/join region.

Peano models its execution with multiple parallel, nested fork/join sections. You could also think of these as mini-BSP sections. This routine guides the orchestration how to map those BSP sections onto tasks.

The decision can be guided by basically arbitrary contextual factors. The most important one for me is the nesting factor. As we work mainly with OpenMP, where tasks are tied to one core, it makes limited sense to have nested parallel fors. Notably, it makes stuff slower. So usually, I return ExecutionPolicy::RunSerially with anything with a nesting level greater than 1.

Parameters

nestedParallelismLevel	Please compare with tarch::multicore::spawnAndWait() which ensures that this flag equals 1 on the top level. A parameter of 0 would mean that no fork/join region has been opened. For such a parameter, the code would not query this function.
taskType	If we enter a fork-join section, this section logically spawns a set of tasks, which are all of the same type. So the task type here is given implicitly by the code location. But each BSP section has a unique identifier.

Implements tarch::multicore::orchestration::Strategy.

Definition at line 242 of file SamplingMulticoreOrchestration.cpp.

References tarch::multicore::orchestration::Strategy::RunParallel, and tarch::multicore::orchestration::Strategy::RunSerially.