Computes $Ma(x)b(x)\cdots\int\vec{s}(x)\cdot\nabla\phi(x)\,dx$ . More...

#include <Panzer_Integrator_GradBasisDotTensorTimesVector_decl.hpp>

Inheritance diagram for panzer::Integrator_GradBasisDotTensorTimesVector< EvalT, Traits >:

Classes
struct	FieldMultTag
	This empty struct allows us to optimize `operator()()` depending on the number of field multipliers. This is the version that does not use shared memory. More...

struct	SharedFieldMultTag
	This empty struct allows us to optimize `operator()()` depending on the number of field multipliers. This is the shared memory version. More...

Public Member Functions
	Integrator_GradBasisDotTensorTimesVector (const panzer::EvaluatorStyle &evalStyle, const std::string &resName, const std::string &fluxName, const panzer::BasisIRLayout &basis, const panzer::IntegrationRule &ir, const std::string &tensorName, const Teuchos::RCP< PHX::DataLayout > &vecDL=Teuchos::null)
	Main Constructor.

	Integrator_GradBasisDotTensorTimesVector (const Teuchos::ParameterList &p)
	`ParameterList` Constructor.

void	postRegistrationSetup (typename Traits::SetupData d, PHX::FieldManager< Traits > &fm)
	Post-Registration Setup.

void	evaluateFields (typename Traits::EvalData d)
	Evaluate Fields.

KOKKOS_INLINE_FUNCTION void	operator() (const FieldMultTag &tag, const Kokkos::TeamPolicy< PHX::exec_space >::member_type &team) const
	Perform the integration.

KOKKOS_INLINE_FUNCTION void	operator() (const SharedFieldMultTag &tag, const Kokkos::TeamPolicy< PHX::exec_space >::member_type &team) const
	Perform the integration.

Public Member Functions inherited from panzer::EvaluatorWithBaseImpl< Traits >
void	setDetailsIndex (const int di)
	An evaluator builder sets the details index.

Public Member Functions inherited from panzer::DomainEvaluator
	DomainEvaluator (DomainType domain=ALL)
	Constructor.

virtual	~DomainEvaluator ()=default
	Default destructor.

void	setDomain (const DomainType domain)
	Set the domain for the evaluator.

DomainType	getDomain ()
	Get the domain for the evaluator.

virtual int	cellStartIndex (const panzer::Workset &workset) const
	Returns the starting cell for the specified domain for a given workset.

virtual int	cellEndIndex (const panzer::Workset &workset) const
	Returns the non-inclusive end cell for the specified domain for a given workset.

Private Types
using	ScalarT = typename EvalT::ScalarT
	The scalar type.

using	scratch_view = Kokkos::View< ScalarT *,typename PHX::DevLayout< ScalarT >::type, typename PHX::exec_space::scratch_memory_space, Kokkos::MemoryUnmanaged >
	Type for shared memory.

Private Member Functions
Teuchos::RCP< Teuchos::ParameterList >	getValidParameters () const
	Get Valid Parameters.

Private Attributes
const panzer::EvaluatorStyle	evalStyle_
	An `enum` determining the behavior of this `Evaluator`.

PHX::MDField< ScalarT, panzer::Cell, panzer::BASIS >	field_
	A field to which we'll contribute, or in which we'll store, the result of computing this integral.

PHX::MDField< const ScalarT, panzer::Cell, panzer::IP, panzer::Dim >	vector_
	A field representing the vector-valued function we're integrating ( $\vec{s}$ ).

PHX::MDField< const ScalarT, panzer::Cell, panzer::IP, panzer::Dim, panzer::Dim >	tensor_
	The tensor field( ).

PHX::View< const ScalarT **** >	kokkosTensor_
	The `PHX::View` representation of the tensor fields that are multiplied out in front of the integral ( ).

std::string	basisName_
	The name of the basis we're using.

std::size_t	basisIndex_
	The index in the `Workset` bases for our particular `BasisIRLayout` name.

PHX::MDField< double, panzer::Cell, panzer::BASIS, panzer::IP, panzer::Dim >	basis_
	The gradient vector basis information necessary for integration.

PHX::View< ScalarT * >	tmp_
	Temporary used when shared memory is disabled.

Additional Inherited Members
Public Types inherited from panzer::DomainEvaluator
enum	DomainType : int { OWNED =0 , GHOST =1 , REAL =2 , VIRTUAL =3 , EXTERNAL =4 , ALL =5 }
	Domain types supported by worksets. More...

Protected Attributes inherited from panzer::EvaluatorWithBaseImpl< Traits >
WorksetDetailsAccessor	wda

Detailed Description

template<typename EvalT, typename Traits>
class panzer::Integrator_GradBasisDotTensorTimesVector< EvalT, Traits >

Computes $Ma(x)b(x)\cdots\int\vec{s}(x)\cdot\nabla\phi(x)\,dx$ .

Evaluates the integral

$\int (a(x)\cdots\vec{s}(x)) \cdot \nabla\phi(x)\,dx,$

where $ a(x) $ is a tensor valued field that depends on position, $\vec{s}$ is some vector- valued function, and $\phi$ is some scalar basis.

Definition at line 78 of file Panzer_Integrator_GradBasisDotTensorTimesVector_decl.hpp.

Member Typedef Documentation

◆ ScalarT

template<typename EvalT , typename Traits >

using panzer::Integrator_GradBasisDotTensorTimesVector< EvalT, Traits >::ScalarT = typename EvalT::ScalarT

private

The scalar type.

Definition at line 278 of file Panzer_Integrator_GradBasisDotTensorTimesVector_decl.hpp.

◆ scratch_view

template<typename EvalT , typename Traits >

using panzer::Integrator_GradBasisDotTensorTimesVector< EvalT, Traits >::scratch_view = Kokkos::View<ScalarT* ,typename PHX::DevLayout<ScalarT>::type,typename PHX::exec_space::scratch_memory_space,Kokkos::MemoryUnmanaged>

private

Type for shared memory.

Definition at line 281 of file Panzer_Integrator_GradBasisDotTensorTimesVector_decl.hpp.

Constructor & Destructor Documentation

◆ Integrator_GradBasisDotTensorTimesVector() [1/2]

template<typename EvalT , typename Traits >

panzer::Integrator_GradBasisDotTensorTimesVector< EvalT, Traits >::Integrator_GradBasisDotTensorTimesVector	(	const panzer::EvaluatorStyle &	evalStyle,
		const std::string &	resName,
		const std::string &	fluxName,
		const panzer::BasisIRLayout &	basis,
		const panzer::IntegrationRule &	ir,
		const std::string &	tensorName,
		const Teuchos::RCP< PHX::DataLayout > &	vecDL = `Teuchos::null`
	)

Main Constructor.

Creates an Evaluator to evaluate the integral

$\int (a(x)\cdots\vec{s}(x)) \cdot \nabla\phi(x)\,dx,$

where $ a(x) $ is a tensor valued field that depends on position, $\vec{s}$ is some vector- valued function, and $\phi$ is some scalar basis.

Parameters

[in]	evalStyle	An `enum` declaring the behavior of this `Evaluator`, which is to either: compute and contribute (`CONTRIBUTES`), or compute and store (`EVALUATES`).
[in]	resName	The name of either the contributed or evaluated field, depending on `evalStyle`.
[in]	fluxName	The name of the vector-valued function being integrated ( $\vec{s}$ ).
[in]	basis	The basis that you'd like to use ( $\phi$ ).
[in]	ir	The integration rule that you'd like to use.
[in]	tensorName	The tensors name ( ).
[in]	vecDL	The vector data layout that you'd like to use. If not specified, this defaults to `Teuchos::null` and the vector data layout from the given `ir` is used.

Exceptions

std::invalid_argument	If any of the inputs are invalid.
std::logic_error	If the `basis` supplied does not support the gradient operator, or if the dimension of the space exceeds the dimension of the vector data layout.

Definition at line 66 of file Panzer_Integrator_GradBasisDotTensorTimesVector_impl.hpp.

◆ Integrator_GradBasisDotTensorTimesVector() [2/2]

template<typename EvalT , typename Traits >

panzer::Integrator_GradBasisDotTensorTimesVector< EvalT, Traits >::Integrator_GradBasisDotTensorTimesVector ( const Teuchos::ParameterList & p )

ParameterList Constructor.

Creates an Evaluator to evaluate the integral

$Ma(x)b(x)\cdots\int\vec{s}(x)\cdot\nabla\phi(x)\,dx,$

where $ M $ is some constant, $ a(x) $ , $ b(x) $ , etc., are some fields that depend on position, $\vec{s}$ is some vector-valued function, and $\phi$ is some basis.

Note: This constructor exists to preserve the older way of creating an Evaluator with a ParameterList; however, it is strongly advised that you not use this ParameterList Constructor, but rather that you favor the main constructor with its compile-time argument checking instead.

Parameters

[in]

p

A ParameterList of the form

<ParameterList>
  <Parameter name = "Residual Name"      type = "std::string"                         value = (required)    />
  <Parameter name = "Flux Name"          type = "std::string"                         value = (required)    />
  <Parameter name = "Basis"              type = "RCP<panzer::BasisIRLayout>"          value = (required)    />
  <Parameter name = "IR"                 type = "RCP<panzer::IntegrationRule>"        value = (required)    />
  <Parameter name = "Tensor Name"       type = "std::string"                         value = (required)    />
  <Parameter name = "Vector Data Layout" type = "RCP<PHX::DataLayout>"                value = null (default)/>
</ParameterList>

where

"Residual Name" is the name for the term this Evaluator is evaluating,
"Flux Name" is the name of the vector-valued function being integrated ( $\vec{s}$ ),
"Basis" is the basis that you'd like to use ( $\phi$ ),
"IR" is the integration rule that you'd like to use,
"Tensor Name" is the name of the tensor field ( ).
"Vector Data Layout" is the vector data layout that you'd like to use.

Definition at line 142 of file Panzer_Integrator_GradBasisDotTensorTimesVector_impl.hpp.

Member Function Documentation

◆ postRegistrationSetup()

template<typename EvalT , typename Traits >

void panzer::Integrator_GradBasisDotTensorTimesVector< EvalT, Traits >::postRegistrationSetup	(	typename Traits::SetupData	d,
		PHX::FieldManager< Traits > &	fm
	)

Post-Registration Setup.

Sets the basis index, and gets the PHX::View versions of the field multiplier, if there are any.

Parameters

[in]	sd	Essentially a list of `Workset`s, which are collections of cells (elements) that all live on a single process.
[in]	fm	This is an unused part of the `Evaluator` interface.

Definition at line 172 of file Panzer_Integrator_GradBasisDotTensorTimesVector_impl.hpp.

◆ evaluateFields()

template<typename EvalT , typename Traits >

void panzer::Integrator_GradBasisDotTensorTimesVector< EvalT, Traits >::evaluateFields ( typename Traits::EvalData d )

Evaluate Fields.

This actually performs the integration by calling operator()() in a Kokkos::parallel_for over the cells in the Workset.

Parameters

[in] workset The Workset on which you're going to do the integration.

Definition at line 316 of file Panzer_Integrator_GradBasisDotTensorTimesVector_impl.hpp.

◆ operator()() [1/2]

template<typename EvalT , typename Traits >

KOKKOS_INLINE_FUNCTION void panzer::Integrator_GradBasisDotTensorTimesVector< EvalT, Traits >::operator()	(	const FieldMultTag &	tag,
		const Kokkos::TeamPolicy< PHX::exec_space >::member_type &	team
	)		const

Perform the integration.

Generally speaking, for a given cell in the Workset, this routine loops over quadrature points, vector dimensions, and bases to perform the integration, scaling the vector field to be integrated by the multiplier ( $ M $ ) and any field multipliers ( $ a(x) $ , $
b(x) $ , etc.).

Note: Optimizations are made for the cases in which we have no field multipliers or only a single one.

Parameters

[in]	tag	An indication of the number of field multipliers we have; either 0, 1, or something else.
[in]	cell	The cell in the `Workset` over which to integrate.

Definition at line 206 of file Panzer_Integrator_GradBasisDotTensorTimesVector_impl.hpp.

◆ operator()() [2/2]

template<typename EvalT , typename Traits >

KOKKOS_INLINE_FUNCTION void panzer::Integrator_GradBasisDotTensorTimesVector< EvalT, Traits >::operator()	(	const SharedFieldMultTag &	tag,
		const Kokkos::TeamPolicy< PHX::exec_space >::member_type &	team
	)		const

Perform the integration.

Generally speaking, for a given cell in the Workset, this routine loops over quadrature points, vector dimensions, and bases to perform the integration, scaling the vector field to be integrated by the multiplier ( $ M $ ) and any field multipliers ( $ a(x) $ , $
b(x) $ , etc.). Uses Shared memory.

Note: Optimizations are made for the cases in which we have no field multipliers or only a single one.

Parameters

[in]	tag	An indication of the number of field multipliers we have; either 0, 1, or something else.
[in]	cell	The cell in the `Workset` over which to integrate.

Definition at line 249 of file Panzer_Integrator_GradBasisDotTensorTimesVector_impl.hpp.