#include <itkGPUFiniteDifferenceFunction.h>

Detailed Description

template<typename TImageType>
class itk::GPUFiniteDifferenceFunction< TImageType >

This is a base class of GPU finite difference function. Note that unlike most GPU classes, derived class of GPUFiniteDifferenceFunction does not have corresponding CPU class as its parent but only has CPU class FiniteDifferenceFunction as its base class. Therefore, only members of FiniteDifferenceFunction are reused by its derived GPU classes.

How to use this class: GPUFiniteDifferenceFunction must be subclassed to add functionality for GPUComputeUpdate.

Definition at line 47 of file itkGPUFiniteDifferenceFunction.h.

Inheritance diagram for itk::GPUFiniteDifferenceFunction< TImageType >:

Collaboration diagram for itk::GPUFiniteDifferenceFunction< TImageType >:

Public Types
using	ConstPointer = SmartPointer<const Self>

using	DefaultBoundaryConditionType

using	DifferenceFunctionType = Superclass

using	FloatOffsetType

using	ImageType

using	NeighborhoodType

using	PixelRealType

using	PixelType

using	Pointer = SmartPointer<Self>

using	RadiusType

using	Self = GPUFiniteDifferenceFunction

using	Superclass = FiniteDifferenceFunction<TImageType>

using	TimeStepType

Public Types inherited from itk::FiniteDifferenceFunction< TImageType >
using	ConstPointer = SmartPointer<const Self>

using	DefaultBoundaryConditionType = ZeroFluxNeumannBoundaryCondition<ImageType>

using	FloatOffsetType = Vector<float, Self::ImageDimension>

using	ImageType = TImageType

using	NeighborhoodScalesType = Vector<PixelRealType, Self::ImageDimension>

using	NeighborhoodType = ConstNeighborhoodIterator<TImageType, DefaultBoundaryConditionType>

using	PixelRealType = double

using	PixelType = typename ImageType::PixelType

using	Pointer = SmartPointer<Self>

using	RadiusType = typename ConstNeighborhoodIterator<TImageType>::RadiusType

using	Self = FiniteDifferenceFunction

using	Superclass = LightObject

using	TimeStepType = double

Public Types inherited from itk::LightObject
using	ConstPointer = SmartPointer<const Self>

using	Pointer = SmartPointer<Self>

using	Self = LightObject

Public Member Functions
PixelType	ComputeUpdate (const NeighborhoodType &neighborhood, void *globalData, const FloatOffsetType &offset=FloatOffsetType(0.0)) override

const char *	GetNameOfClass () const override

virtual void	GPUAllocateMetricData (unsigned int numPixels)

virtual void	GPUComputeUpdate (const typename TImageType::Pointer output, typename TImageType::Pointer update, void *gd)=0

virtual void	GPUReleaseMetricData ()

Public Member Functions inherited from itk::FiniteDifferenceFunction< TImageType >
virtual TimeStepType	ComputeGlobalTimeStep (void *GlobalData) const =0

const NeighborhoodScalesType	ComputeNeighborhoodScales () const

virtual void *	GetGlobalDataPointer () const =0

const RadiusType &	GetRadius () const

void	GetScaleCoefficients (PixelRealType vals[ImageDimension]) const

virtual void	InitializeIteration ()

virtual void	ReleaseGlobalDataPointer (void *GlobalData) const =0

void	SetRadius (const RadiusType &r)

void	SetScaleCoefficients (const PixelRealType vals[ImageDimension])

Public Member Functions inherited from itk::LightObject
Pointer	Clone () const

virtual Pointer	CreateAnother () const

virtual void	Delete ()

virtual int	GetReferenceCount () const

void	Print (std::ostream &os, Indent indent=0) const

virtual void	Register () const

virtual void	SetReferenceCount (int)

virtual void	UnRegister () const noexcept

Static Public Attributes
static constexpr unsigned int	ImageDimension = ImageType::ImageDimension

Static Public Attributes inherited from itk::FiniteDifferenceFunction< TImageType >
static constexpr unsigned int	ImageDimension = ImageType::ImageDimension

Protected Member Functions
	GPUFiniteDifferenceFunction ()

	~GPUFiniteDifferenceFunction () override=default

Protected Member Functions inherited from itk::FiniteDifferenceFunction< TImageType >
	FiniteDifferenceFunction ()

void	PrintSelf (std::ostream &os, Indent indent) const override

	~FiniteDifferenceFunction () override=default

Protected Member Functions inherited from itk::LightObject
virtual LightObject::Pointer	InternalClone () const

	LightObject ()

virtual void	PrintHeader (std::ostream &os, Indent indent) const

virtual void	PrintTrailer (std::ostream &os, Indent indent) const

virtual	~LightObject ()

Protected Attributes
int	m_ComputeUpdateGPUKernelHandle {}

GPUKernelManager::Pointer	m_GPUKernelManager {}

Protected Attributes inherited from itk::FiniteDifferenceFunction< TImageType >
RadiusType	m_Radius {}

PixelRealType	m_ScaleCoefficients [ImageDimension] {}

Protected Attributes inherited from itk::LightObject
std::atomic< int >	m_ReferenceCount {}

Additional Inherited Members
Static Public Member Functions inherited from itk::LightObject
static void	BreakOnError ()

static Pointer	New ()

Member Typedef Documentation

◆ ConstPointer

template<typename TImageType>

using itk::GPUFiniteDifferenceFunction< TImageType >::ConstPointer = SmartPointer<const Self>

Definition at line 57 of file itkGPUFiniteDifferenceFunction.h.

◆ DefaultBoundaryConditionType

template<typename TImageType>

using itk::FiniteDifferenceFunction< TImageType >::DefaultBoundaryConditionType

The default boundary condition for finite difference functions that is used unless overridden in the Evaluate() method.

Definition at line 93 of file itkFiniteDifferenceFunction.h.

◆ DifferenceFunctionType

template<typename TImageType>

using itk::GPUFiniteDifferenceFunction< TImageType >::DifferenceFunctionType = Superclass

Definition at line 55 of file itkGPUFiniteDifferenceFunction.h.

◆ FloatOffsetType

template<typename TImageType>

using itk::FiniteDifferenceFunction< TImageType >::FloatOffsetType

A floating point offset from an image grid location. Used for interpolation among grid values in a neighborhood.

Definition at line 108 of file itkFiniteDifferenceFunction.h.

◆ ImageType

template<typename TImageType>

using itk::FiniteDifferenceFunction< TImageType >::ImageType

Extract some parameters from the image type

Definition at line 81 of file itkFiniteDifferenceFunction.h.

◆ NeighborhoodType

template<typename TImageType>

using itk::FiniteDifferenceFunction< TImageType >::NeighborhoodType

The type of data structure that is passed to this function object to evaluate at a pixel that does not lie on a data set boundary.

Definition at line 100 of file itkFiniteDifferenceFunction.h.

◆ PixelRealType

template<typename TImageType>

using itk::FiniteDifferenceFunction< TImageType >::PixelRealType

Definition at line 83 of file itkFiniteDifferenceFunction.h.

◆ PixelType

template<typename TImageType>

using itk::FiniteDifferenceFunction< TImageType >::PixelType

Definition at line 82 of file itkFiniteDifferenceFunction.h.

◆ Pointer

template<typename TImageType>

using itk::GPUFiniteDifferenceFunction< TImageType >::Pointer = SmartPointer<Self>

Definition at line 56 of file itkGPUFiniteDifferenceFunction.h.

◆ RadiusType

template<typename TImageType>

using itk::FiniteDifferenceFunction< TImageType >::RadiusType

Neighborhood radius type

Definition at line 96 of file itkFiniteDifferenceFunction.h.

◆ Self

template<typename TImageType>

using itk::GPUFiniteDifferenceFunction< TImageType >::Self = GPUFiniteDifferenceFunction

Standard class type aliases.

Definition at line 53 of file itkGPUFiniteDifferenceFunction.h.

◆ Superclass

template<typename TImageType>

using itk::GPUFiniteDifferenceFunction< TImageType >::Superclass = FiniteDifferenceFunction<TImageType>

Definition at line 54 of file itkGPUFiniteDifferenceFunction.h.

◆ TimeStepType

template<typename TImageType>

using itk::FiniteDifferenceFunction< TImageType >::TimeStepType

Define the TimeStepType to always be double.

Definition at line 89 of file itkFiniteDifferenceFunction.h.

Constructor & Destructor Documentation

◆ GPUFiniteDifferenceFunction()

template<typename TImageType>

itk::GPUFiniteDifferenceFunction< TImageType >::GPUFiniteDifferenceFunction ( )

inlineprotected

Definition at line 116 of file itkGPUFiniteDifferenceFunction.h.

◆ ~GPUFiniteDifferenceFunction()

template<typename TImageType>

itk::GPUFiniteDifferenceFunction< TImageType >::~GPUFiniteDifferenceFunction ( )

overrideprotecteddefault

Member Function Documentation

◆ ComputeUpdate()

template<typename TImageType>

PixelType itk::GPUFiniteDifferenceFunction< TImageType >::ComputeUpdate	(	const NeighborhoodType &	neighborhood,
		void *	globalData,
		const FloatOffsetType &	offset = FloatOffsetType(0.0) )

inlineoverridevirtual

Empty implementation - this will not be used by GPU filters

Implements itk::FiniteDifferenceFunction< TImageType >.

Definition at line 90 of file itkGPUFiniteDifferenceFunction.h.

◆ GetNameOfClass()

template<typename TImageType>

const char * itk::GPUFiniteDifferenceFunction< TImageType >::GetNameOfClass ( ) const

overridevirtual

See also: LightObject::GetNameOfClass()

Reimplemented from itk::FiniteDifferenceFunction< TImageType >.

Reimplemented in itk::GPUGradientNDAnisotropicDiffusionFunction< TImage >, itk::GPUPDEDeformableRegistrationFunction< TFixedImage, TMovingImage, TDisplacementField >, itk::GPUPDEDeformableRegistrationFunction< FixedImageType, MovingImageType, DisplacementFieldType >, itk::GPUPDEDeformableRegistrationFunction< FixedImageType, MovingImageType, DisplacementFieldType >, and itk::GPUScalarAnisotropicDiffusionFunction< TImage >.

◆ GPUAllocateMetricData()

template<typename TImageType>

virtual void itk::GPUFiniteDifferenceFunction< TImageType >::GPUAllocateMetricData ( unsigned int numPixels )

inlinevirtual

Allocate GPU buffers for computing metric statistics

Reimplemented in itk::GPUDemonsRegistrationFunction< TFixedImage, TMovingImage, TDisplacementField >, itk::GPUDemonsRegistrationFunction< FixedImageType, MovingImageType, DisplacementFieldType >, and itk::GPUDemonsRegistrationFunction< FixedImageType, MovingImageType, DisplacementFieldType >.

Definition at line 106 of file itkGPUFiniteDifferenceFunction.h.

◆ GPUComputeUpdate()

template<typename TImageType>

virtual void itk::GPUFiniteDifferenceFunction< TImageType >::GPUComputeUpdate	(	const typename TImageType::Pointer	output,
		typename TImageType::Pointer	update,
		void *	gd )

pure virtual

GPU function to compute update buffer

Implemented in itk::GPUGradientNDAnisotropicDiffusionFunction< TImage >.

◆ GPUReleaseMetricData()

template<typename TImageType>

virtual void itk::GPUFiniteDifferenceFunction< TImageType >::GPUReleaseMetricData ( )

inlinevirtual

Release GPU buffers for computing metric statistics

Reimplemented in itk::GPUDemonsRegistrationFunction< TFixedImage, TMovingImage, TDisplacementField >, itk::GPUDemonsRegistrationFunction< FixedImageType, MovingImageType, DisplacementFieldType >, and itk::GPUDemonsRegistrationFunction< FixedImageType, MovingImageType, DisplacementFieldType >.

Definition at line 112 of file itkGPUFiniteDifferenceFunction.h.

Member Data Documentation

◆ ImageDimension

template<typename TImageType>

unsigned int itk::GPUFiniteDifferenceFunction< TImageType >::ImageDimension = ImageType::ImageDimension

staticconstexpr

Save image dimension.

Definition at line 68 of file itkGPUFiniteDifferenceFunction.h.

◆ m_ComputeUpdateGPUKernelHandle

template<typename TImageType>

int itk::GPUFiniteDifferenceFunction< TImageType >::m_ComputeUpdateGPUKernelHandle {}

protected

GPU kernel handle for GPUComputeUpdate()

Definition at line 123 of file itkGPUFiniteDifferenceFunction.h.

◆ m_GPUKernelManager

template<typename TImageType>

GPUKernelManager::Pointer itk::GPUFiniteDifferenceFunction< TImageType >::m_GPUKernelManager {}

protected

GPU kernel manager for GPUFiniteDifferenceFunction class

Definition at line 120 of file itkGPUFiniteDifferenceFunction.h.

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

itkGPUFiniteDifferenceFunction.h

Detailed Description

Public Types

Public Member Functions

Static Public Attributes

Protected Member Functions

Protected Attributes

Additional Inherited Members

Member Typedef Documentation

◆ ConstPointer

◆ DefaultBoundaryConditionType

◆ DifferenceFunctionType

◆ FloatOffsetType

◆ ImageType

◆ NeighborhoodType

◆ PixelRealType

◆ PixelType

◆ Pointer

◆ RadiusType

◆ Self

◆ Superclass

◆ TimeStepType

Constructor & Destructor Documentation

◆ GPUFiniteDifferenceFunction()

◆ ~GPUFiniteDifferenceFunction()

Member Function Documentation

◆ ComputeUpdate()

◆ GetNameOfClass()

◆ GPUAllocateMetricData()

◆ GPUComputeUpdate()

◆ GPUReleaseMetricData()

Member Data Documentation

◆ ImageDimension

◆ m_ComputeUpdateGPUKernelHandle

◆ m_GPUKernelManager