#include <Kokkos_BaseSparseSolve.hpp>
Public Member Functions | |
Constructors/Destructor | |
BaseSparseSolve () | |
BaseSparseSolve constuctor with variable number of indices per row. | |
BaseSparseSolve (const BaseSparseSolve &source) | |
Copy constructor. | |
virtual | ~BaseSparseSolve () |
BaseSparseSolve Destructor. | |
Abstract Kokkos::CisMatrix Interface Initialization Methods | |
virtual int | initializeStructure (const CisMatrix< OrdinalType, ScalarType > &A, bool willKeepStructure=false) |
Initialize structure of matrix. | |
virtual int | initializeValues (const CisMatrix< OrdinalType, ScalarType > &A, bool willKeepValues=false, bool checkStructure=false) |
Initialize values of matrix. | |
Computational methods | |
virtual int | apply (const Vector< OrdinalType, ScalarType > &x, Vector< OrdinalType, ScalarType > &y, bool transA=false, bool conjA=false) const |
Returns the result of a Kokkos_BaseSparseSolve multiplied by a vector x in y. | |
virtual int | apply (const MultiVector< OrdinalType, ScalarType > &x, MultiVector< OrdinalType, ScalarType > &y, bool transA=false, bool conjA=false) const |
Returns the result of a Kokkos_BaseSparseSolve multiplied by multiple vectors in x, results in y. | |
Operator attribute access methods | |
virtual bool | getCanUseStructure () const |
Returns true if this implementation of Kokkos::BaseSparseSolve can benefit from the user keeping the passed in structure. | |
virtual bool | getCanUseValues () const |
Returns true if this implementation of Kokkos::BaseSparseSolve can benefit from the user keeping the passed in values. | |
virtual const CisMatrix < OrdinalType, ScalarType > & | getMatrix () const |
Returns a reference to the most recent Kokkos::CisMatrix that was passed into the this object. | |
virtual const Permutation < OrdinalType, ScalarType > & | getLeftPermutation () const |
Returns a reference to the left Kokkos::Permutation object, which is the identity for this implementation. | |
virtual const Permutation < OrdinalType, ScalarType > & | getRightPermutation () const |
Returns a reference to the right Kokkos::Permutation object, which is the identity for this implementation. | |
Protected Member Functions | |
void | copyProfile () |
void | copyStructure () |
void | deleteStructureAndProfile () |
void | copyOrdinals (OrdinalType len, OrdinalType *vecIn, OrdinalType *vecOut) |
void | copyScalars (OrdinalType len, ScalarType *vecIn, ScalarType *vecOut) |
void | copyValues () |
void | deleteValues () |
Protected Attributes | |
CisMatrix< OrdinalType, ScalarType > * | matrixForStructure_ |
CisMatrix< OrdinalType, ScalarType > * | matrixForValues_ |
Permutation< OrdinalType, ScalarType > | leftPermutation_ |
Permutation< OrdinalType, ScalarType > | rightPermutation_ |
bool | willKeepStructure_ |
bool | willKeepValues_ |
bool | isRowOriented_ |
bool | haveStructure_ |
bool | haveValues_ |
bool | isUpper_ |
bool | hasUnitDiagonal_ |
OrdinalType | numRows_ |
OrdinalType | numCols_ |
OrdinalType | numRC_ |
OrdinalType | numEntries_ |
ScalarType ** | values_ |
OrdinalType ** | indices_ |
OrdinalType * | profile_ |
ScalarType * | allValues_ |
OrdinalType * | allIndices_ |
double | costOfSolve_ |
The Kokkos::BaseSparseSolve provide basic functionality for computing sparse triangular solves with one or more right-hand-side vectors. This class is templated on the ordinal (integer) and scalar (floating point) types, so it can compute using any reasonable data type. It implements the Kokkos::SparseOperation base class.
Constructing Kokkos::BaseSparseSolve objects
Constructing Kokkos::BaseSparseSolve objects is a multi-step process. The basic steps are as follows:
Counting Floating Point Operations
Each Kokkos::BaseSparseSolve object keeps track of the number of floating point operations performed using the specified object as the this argument to the function. The getFlops() function returns this number as a double precision number. Using this information, in conjunction with the Kokkos::Time class, one can get accurate performance numbers. The resetFlops() function resets the floating point counter.
int Kokkos::BaseSparseSolve< OrdinalType, ScalarType >::apply | ( | const MultiVector< OrdinalType, ScalarType > & | x, | |
MultiVector< OrdinalType, ScalarType > & | y, | |||
bool | transA = false , |
|||
bool | conjA = false | |||
) | const [inline, virtual] |
Returns the result of a Kokkos_BaseSparseSolve multiplied by multiple vectors in x, results in y.
x | (In) A Kokkos::MultiVector to solve with. | |
y | (Out) A Kokkos::MultiVector containing results. Note that any implementation must support x and y being the same object. | |
transA | (In) If true, solve using the transpose of matrix, otherwise just use matrix. | |
conjA | (In) If true, solve using the conjugate of matrix values, otherwise just use matrix values. |
Implements Kokkos::SparseOperation< OrdinalType, ScalarType >.
int Kokkos::BaseSparseSolve< OrdinalType, ScalarType >::apply | ( | const Vector< OrdinalType, ScalarType > & | x, | |
Vector< OrdinalType, ScalarType > & | y, | |||
bool | transA = false , |
|||
bool | conjA = false | |||
) | const [inline, virtual] |
Returns the result of a Kokkos_BaseSparseSolve multiplied by a vector x in y.
x | (In) A Kokkos::Vector to solve with. | |
y | (Out) A Kokkos::Vector containing results. Note that any implementation must support x and y being the same object. | |
transA | (In) If true, solve using the transpose of matrix, otherwise just use matrix. | |
conjA | (In) If true, solve using the conjugate of matrix values, otherwise just use matrix values. |
Implements Kokkos::SparseOperation< OrdinalType, ScalarType >.
virtual bool Kokkos::BaseSparseSolve< OrdinalType, ScalarType >::getCanUseStructure | ( | ) | const [inline, virtual] |
Returns true if this implementation of Kokkos::BaseSparseSolve can benefit from the user keeping the passed in structure.
Some implementations of optimized kernels do not rely on the user's data except for the initial analysis of structure. Other implementations, in order to reduce memory requirements, may find it beneficial to rely on the user's data. Since it is very possible that the user would retain this data anyway, we want to allow for this possibility. This method is related to the willKeepStructure parameter passed in to the initializeStructure() method.
Implements Kokkos::SparseOperation< OrdinalType, ScalarType >.
virtual bool Kokkos::BaseSparseSolve< OrdinalType, ScalarType >::getCanUseValues | ( | ) | const [inline, virtual] |
Returns true if this implementation of Kokkos::BaseSparseSolve can benefit from the user keeping the passed in values.
Some implementations of optimized kernels do not rely on the user's data except for the initial copying of values. Other implementations, in order to reduce memory requirements, may find it beneficial to rely on the user's data. Since it is very possible that the user would retain this data anyway, we want to allow for this possibility. This method is related to the willKeepValues parameter passed in to the initializeValues() method.
Implements Kokkos::SparseOperation< OrdinalType, ScalarType >.
int Kokkos::BaseSparseSolve< OrdinalType, ScalarType >::initializeStructure | ( | const CisMatrix< OrdinalType, ScalarType > & | A, | |
bool | willKeepStructure = false | |||
) | [inline, virtual] |
Initialize structure of matrix.
This interface supports matrices that implement the Kokkos::CisMatrix matrix interface.
A | (In) An instance of a class that implements the Kokkos::CisMatrix. All necessary information about the matrix can be obtained via this interface, including whether or not the matrix is upper or lower triangular, and whether or not the diagonal is part of the structure, or should be implicitly assume to be unit diagonal. | |
willKeepStructure | (In) If set to true, the user is asserting that the strucuture of the matrix, as defined in the getIndices() method of the CisMatrix object A will be kept. Specifically, the pointer to an array of indices returned for each i in that method will continue to point to valid index data. By default, this argument is set to false, implying that the calling routine is not required to maintain the validity of this data. If the calling routine is planning to keep this data anyway, setting this argument to true can reduce the overall memory requirements. |
Implements Kokkos::SparseOperation< OrdinalType, ScalarType >.
int Kokkos::BaseSparseSolve< OrdinalType, ScalarType >::initializeValues | ( | const CisMatrix< OrdinalType, ScalarType > & | A, | |
bool | willKeepValues = false , |
|||
bool | checkStructure = false | |||
) | [inline, virtual] |
Initialize values of matrix.
This interface supports matrices that implement the Kokkos::CisMatrix matrix interface
A | (In) An instance of a class that implements the Kokkos::CisMatrix. All necessary information about the matrix can be obtained via this interface, including whether or not the matrix is upper or lower triangular, and whether or not the diagonal is part of the structure, or should be implicitly assume to be unit diagonal. | |
willKeepValues | (In) If set to true, the user is asserting that the strucuture of the matrix, as defined in the getIndices() method of the CisMatrix object A will be kept. Specifically, the pointer to an array of indices returned for each i in that method will continue to point to valid index data. By default, this argument is set to false, implying that the calling routine is not required to maintain the validity of this data. If the calling routine is planning to keep this data anyway, setting this argument to true can reduce the overall memory requirements. | |
checkStructure | (In) If set to true, the structure of A will be checked against the structure of the matrix passed in to the initializeStructure() methods. This parameter is false by default. |
Implements Kokkos::SparseOperation< OrdinalType, ScalarType >.