Details | Implementation details of Tpetra |
MatrixMarket | Matrix Market file readers and writers for sparse and dense matrices (as CrsMatrix resp. MultiVector ) |
SortDetails | Implementation details of sort routines used by Tpetra |
Tpetra | Namespace Tpetra contains the class and methods constituting the Tpetra library |
KokkosRefactor | |
Details | |
Impl | Implementation details of implementation details |
OutOfBounds | Is x out of bounds? That is, is x less than zero, or greater than or equal to the given exclusive upper bound? |
Details | Nonmember function that computes a residual Computes R = B - A * X |
Impl | |
DetermineLocalTriangularStructure | Implementation of Tpetra::Details::determineLocalTriangularStructure (which see below) |
GetGraphDiagOffsets | Implementation detail of Tpetra::Details::getGraphDiagOffsets, which in turn is an implementation detail of Tpetra::CrsGraph |
CountLocalNumDiags | Kokkos::parallel_reduce functor for counting the local number of diagonal entries in a sparse graph |
GetLocalNumDiags | Implementation of Tpetra::Details::getLocalNumDiags (see below) |
GetLocalNumDiags< ::Tpetra::RowGraph< LO, GO, NT > > | Specialization of GetLocalNumDiags for RowGraph |
GetLocalNumDiags< ::Tpetra::CrsGraph< LO, GO, NT > > | Specialization of GetLocalNumDiags for CrsGraph |
DeferredActionCommRequest | Part of the Work-around for not having MPI >= 3 |
IallreduceCommRequest | Object representing a pending ::Tpetra::Details::iallreduce operation |
IallreduceCommRequest< PacketType, SendLayoutType, SendDeviceType, RecvLayoutType, RecvDeviceType, 1 > | Partial pecialization for rank-1 send and receive buffers |
IallreduceCommRequest< PacketType, SendLayoutType, SendDeviceType, RecvLayoutType, RecvDeviceType, 0 > | Partial pecialization for rank-0 (single-value) send and receive buffers |
Iallreduce | Implementation of ::Tpetra::Details::iallreduce |
Iallreduce< PacketType, SendLayoutType, SendDeviceType, RecvLayoutType, RecvDeviceType, 1 > | Partial specialization of Iallreduce for rank-1 send and receive buffers |
Iallreduce< PacketType, SendLayoutType, SendDeviceType, RecvLayoutType, RecvDeviceType, 0 > | Partial specialization of Iallreduce for rank-0 send and receive buffers |
CooGraphEntry | Type of each (row index, column index) pair in the Tpetra::Details::CooMatrix (see below) |
CompareCooGraphEntries | Function comparing two CooGraphEntry structs, lexicographically, first by row index, then by column index |
CooMatrixImpl | Implementation detail of Tpetra::Details::CooMatrix (which see below) |
ReadLine | Implementation of the readLine stand-alone function in this namespace (see below) |
ReadLine< SC, GO, true > | Complex-arithmetic partial specialization of ReadLine |
ReadLine< SC, GO, false > | Real-arithmetic partial specialization of ReadLine |
Blas | |
Impl | |
Fill | Implementation of ::Tpetra::Details::Blas::fill |
Fill< ViewType, ValueType, ExecutionSpace, IndexType, 1 > | Specialization for rank-1 Views |
Fill< ViewType, ValueType, ExecutionSpace, IndexType, 2 > | Specialization for rank-2 Views |
BlasSupportsScalar | Do BLAS libraries (all that are compliant with the BLAS Standard) support the given "scalar" (matrix entry) type? |
BlasSupportsLayout | Do BLAS libraries (all that are compliant with the BLAS Standard) support the given Kokkos array layout? |
DefaultTypes | Declarations of values of Tpetra classes' default template parameters |
FHT | |
CountBuckets | Parallel for functor for counting "buckets" in the FixedHashTable |
FillPairsResult | Reduction result for FillPairs functor below |
FillPairs | Parallel reduce functor for filling the FixedHashTable, and computing the min and max keys |
CheckForDuplicateKeys | Functor for checking whether a FixedHashTable has one or more duplicate entries |
PackCrsGraphImpl | |
NumPacketsAndOffsetsFunctor | Compute the number of packets and offsets for the pack procedure |
PackCrsMatrixImpl | |
NumPacketsAndOffsetsFunctor | Compute the number of packets and offsets for the pack procedure |
UnpackAndCombineCrsGraphImpl | |
UnpackAndCombineFunctor | Unpacks and combines a single row of the CrsGraph |
UnpackAndCombineCrsMatrixImpl | |
UnpackCrsMatrixAndCombineFunctor | Unpacks and combines a single row of the CrsMatrix |
NumEntriesFunctor | Kokkos::parallel_reduce functor to determine the number of entries (to unpack) in a KokkosSparse::CrsMatrix to pack |
AbsMax | Functor for the the ABSMAX CombineMode of Import and Export operations |
Behavior | Description of Tpetra's behavior |
CrsPadding | Keep track of how much more space a CrsGraph or CrsMatrix needs, when the graph or matrix is the target of a doExport or doImport |
LocalTriangularStructureResult | Return value of determineLocalTriangularStructure |
EquilibrationInfo | Struct storing results of Tpetra::computeRowAndColumnOneNorms |
FixedHashTable | |
CrsMatrixGetDiagCopyFunctor | Functor that implements much of the one-argument overload of Tpetra::CrsMatrix::getLocalDiagCopy, for the case where the matrix is fill complete |
Hash | The hash function for FixedHashTable |
Hash< KeyType, DeviceType, OffsetType, int > | Specialization for ResultType = int |
CommRequest | Base class for the request (more or less a future) representing a pending nonblocking MPI operation |
LeftScaleLocalCrsMatrix | Kokkos::parallel_for functor that left-scales a KokkosSparse::CrsMatrix |
LocalMap | "Local" part of Map suitable for Kokkos kernels |
LocalRowOffsetsResult | Result returned by localRowOffsets (see below) |
OptColMap | Implementation detail of makeOptimizedColMap, and makeOptimizedColMapAndImport |
PackTraits | Traits class for packing / unpacking data of type T |
ProfilingRegion | Profile the given scope |
RightScaleLocalCrsMatrix | Kokkos::parallel_for functor that right-scales a KokkosSparse::CrsMatrix |
ScalarViewTraits | Traits class for allocating a Kokkos::View<T*, D> |
Transfer | Common base class of Import and Export |
Directory | Computes the local ID and process ID corresponding to given global IDs |
ReplicatedDirectory | Implementation of Directory for a locally replicated Map |
ContiguousUniformDirectory | Implementation of Directory for a contiguous, uniformly distributed Map |
DistributedContiguousDirectory | Implementation of Directory for a distributed contiguous Map |
DistributedNoncontiguousDirectory | Implementation of Directory for a distributed noncontiguous Map |
InvalidGlobalIndex | Exception thrown by CrsMatrix on invalid global index |
InvalidGlobalRowIndex | Exception thrown by CrsMatrix on invalid global row index |
ForEach | Specialize this class to implement Tpetra::for_each for specific GlobalDataStructure types |
ForEach< ExecutionSpace,::Tpetra::MultiVector< SC, LO, GO, NT >, UserFunctionType > | Implementation of Tpetra::for_each for Tpetra::MultiVector |
ForEach< ExecutionSpace,::Tpetra::Vector< SC, LO, GO, NT >, UserFunctionType > | Implementation of Tpetra::for_each for Tpetra::Vector |
HashTable | |
MapCloner | Implementation detail of Map::clone() |
TieBreak | Interface for breaking ties in ownership |
Triplet | Representation of a global index on a process |
Transform | Specialize this class to implement Tpetra::transform for specific GlobalDataStructure types |
Transform< ExecutionSpace,::Tpetra::MultiVector< SC, LO, GO, NT > > | Implementation of Tpetra::transform for Tpetra::MultiVector |
Transform< ExecutionSpace,::Tpetra::Vector< SC, LO, GO, NT > > | Implementation of Tpetra::transform for Tpetra::Vector |
Access | Tag class for declaring access intent |
DefaultMemorySpace | Given a global object, get its default memory space (both the type and the default instance thereof) |
DefaultExecutionSpace | Given a global object, get its default execution space (both the type and the default instance thereof) |
GetMasterLocalObject | Mapping from LocalAccess to the "master" local object type |
GetNonowningLocalObject | Mapping from "master" local object type to the nonowning "local view" type that users see (as arguments to the function that they give to withLocalAccess) |
unspecified_type | Tag indicating an unspecified type in LocalAccessTraits |
LocalAccessTraits | Deduce types from parameter pack of LocalAccess |
LocalAccess | Declaration of access intent for a global object |
WithLocalAccess | Implementation of withLocalAccess |
WithLocalAccess<> | Specialization of WithLocalAccess that implements the "base class" of the user providing no GlobalObject arguments, and a function that takes no arguments |
WithLocalAccess< FirstLocalAccessType, Rest...> | Specialization of WithLocalAccess that implements the "recursion case." |
GetMasterLocalObject< LocalAccess< Tpetra::MultiVector< SC, LO, GO, NT >, Args...> > | Specialization of GetMasterLocalObject for Tpetra::MultiVector |
GetMasterLocalObject< LocalAccess< Tpetra::Vector< SC, LO, GO, NT >, Args...> > | Specialization of GetMasterLocalObject for Tpetra::Vector |
GetNonowningLocalObject< LocalAccess< Tpetra::MultiVector< SC, LO, GO, NT >, Args...> > | Specialization of GetNonowningLocalObject for Tpetra::MultiVector |
GetNonowningLocalObject< LocalAccess< Tpetra::Vector< SC, LO, GO, NT >, Args...> > | Specialization of GetNonowningLocalObject for Tpetra::Vector |
CooMatrix | Sparse matrix used only for file input / output |
details | |
ApplyOp | A class for wrapping an Operator apply in a Operator |
Impl | Namespace for new Tpetra features that are not ready for public release, but are ready for evaluation by friendly expert users |
AbsMax | Implementation of Tpetra's ABSMAX CombineMode for the small dense blocks in BlockCrsMatrix, or the small dense vectors in BlockMultiVector and BlockVector |
AbsMax< ViewType1, ViewType2, 2 > | Implementation of Tpetra's ABSMAX CombineMode for the small dense blocks in BlockCrsMatrix |
AbsMax< ViewType1, ViewType2, 1 > | Implementation of Tpetra's ABSMAX CombineMode for the small dense vectors in BlockMultiVector and BlockVector |
SCAL | Implementation of Tpetra::SCAL function |
SCAL< ViewType, CoefficientType, LayoutType, IndexType, 1 > | Implementation of Tpetra::SCAL function, for ViewType rank 1 (i.e., a vector) |
SCAL< ViewType, CoefficientType, LayoutType, IndexType, 2 > | Implementation of Tpetra::SCAL function, for ViewType rank 2 (i.e., a matrix) |
SCAL< ViewType, CoefficientType, Kokkos::LayoutRight, IndexType, 2 > | Implementation of Tpetra::SCAL function, for ViewType rank 2 (i.e., a matrix), and LayoutType = LayoutRight |
FILL | Implementation of Tpetra::FILL function |
FILL< ViewType, InputType, LayoutType, IndexType, 1 > | Implementation of Tpetra::FILL function, for ViewType rank 1 (i.e., a vector) |
FILL< ViewType, InputType, LayoutType, IndexType, 2 > | Implementation of Tpetra::FILL function, for ViewType rank 2 (i.e., a matrix) |
AXPY | Implementation of Tpetra::AXPY function |
AXPY< CoefficientType, ViewType1, ViewType2, LayoutType1, LayoutType2, IndexType, 1 > | Implementation of Tpetra::AXPY function, for ViewType1 and ViewType2 rank 1 (i.e., vectors) |
AXPY< CoefficientType, ViewType1, ViewType2, LayoutType1, LayoutType2, IndexType, 2 > | Implementation of Tpetra::AXPY function, for ViewType1 and ViewType2 rank 2 (i.e., matrices) |
AXPY< CoefficientType, ViewType1, ViewType2, Kokkos::LayoutRight, Kokkos::LayoutRight, IndexType, 2 > | Implementation of Tpetra::AXPY function, for ViewType1 and ViewType2 rank 2 (i.e., matrices), when both ViewType1 and ViewType2 have LayoutRight |
AXPY< CoefficientType, ViewType1, ViewType2, Kokkos::LayoutLeft, Kokkos::LayoutLeft, IndexType, 2 > | Implementation of Tpetra::AXPY function, for ViewType1 and ViewType2 rank 2 (i.e., matrices), when both ViewType1 and ViewType2 have LayoutLeft |
COPY | Implementation of Tpetra::COPY function |
COPY< ViewType1, ViewType2, LayoutType1, LayoutType2, IndexType, 1 > | Implementation of Tpetra::COPY function, for ViewType1 and ViewType2 rank 1 (i.e., vectors) |
COPY< ViewType1, ViewType2, LayoutType1, LayoutType2, IndexType, 2 > | Implementation of Tpetra::COPY function, for ViewType1 and ViewType2 rank 2 (i.e., matrices) |
COPY< ViewType1, ViewType2, Kokkos::LayoutRight, Kokkos::LayoutRight, IndexType, 2 > | Implementation of Tpetra::COPY function, for ViewType1 and ViewType2 rank 2 (i.e., matrices), where both have LayoutRight (row-major order, with contiguous storage) |
COPY< ViewType1, ViewType2, Kokkos::LayoutLeft, Kokkos::LayoutLeft, IndexType, 2 > | Implementation of Tpetra::COPY function, for ViewType1 and ViewType2 rank 2 (i.e., matrices), where both have LayoutLeft (row-major order, with contiguous storage) |
GETRS | Computes the solution to Ax=b |
GETRS< LittleBlockType, LittleIntVectorType, LittleScalarVectorType, 1 > | Special case of GETRS for a single right-hand side |
GETRS< LittleBlockType, LittleIntVectorType, LittleScalarVectorType, 2 > | Special case of GETRS for multiple right-hand sides |
Ext | Namespace for external Tpetra functionality |
TypeStackBottom | Implementation of a Tpetra::Ext::TypeStack, supporting the last entry |
TypeStack | Implementation of a Tpetra::Ext::TypeStack, supporting the next to last entry |
TypeStack< T, TypeStack< S, SS > > | Generic implementation of a Tpetra::Ext::TypeStack. This is the model that should be programmed to |
MatrixMatrix | Distributed sparse matrix-matrix multiply and add |
TripleMatrixMultiply | Distributed sparse triple matrix product |
MatrixMarket | |
Reader | Matrix Market file reader for CrsMatrix and MultiVector |
Writer | Matrix Market file writer for CrsMatrix and MultiVector |
BlockCrsMatrix | Sparse matrix whose entries are small dense square blocks, all of the same dimensions |
BlockMultiVector | MultiVector for multiple degrees of freedom per mesh point |
BlockVector | Vector for multiple degrees of freedom per mesh point |
project1st | Binary function that returns its first argument |
project2nd | Binary function that returns its second argument |
ScopeGuard | Scope guard whose destructor automatically calls Tpetra::finalize for you |
RowInfo | Allocation information for a locally owned row in a CrsGraph or CrsMatrix |
CrsGraph | A distributed graph accessed by rows (adjacency lists) and stored sparsely |
CrsMatrix | Sparse matrix that presents a row-oriented interface that lets users read or modify entries |
CrsMatrixMultiplyOp | A class for wrapping a CrsMatrix multiply in a Operator |
Directory | Implement mapping from global ID to process ID and local ID |
DistObject | Base class for distributed Tpetra objects that support data redistribution |
Distributor | Sets up and executes a communication plan for a Tpetra DistObject |
Export | Communication plan for data redistribution from a (possibly) multiply-owned to a uniquely-owned distribution |
FECrsGraph | A distributed graph accessed by rows (adjacency lists) and stored sparsely |
Import | Communication plan for data redistribution from a uniquely-owned to a (possibly) multiply-owned distribution |
ImportExportData | Implementation detail of Import and Export |
LocalCrsMatrixOperator | Abstract interface for local operators (e.g., matrices and preconditioners) |
LocalOperator | Abstract interface for local operators (e.g., matrices and preconditioners) |
Map | A parallel distribution of indices over processes |
MultiVector | One or more distributed dense vectors |
Operator | Abstract interface for operators (e.g., matrices and preconditioners) |
Packable | Abstract base class for objects that can be the source of an Import or Export operation, and that also know how to pack their data to send to the target object |
RowGraph | An abstract interface for graphs accessed by rows |
RowMatrix | A read-only, row-oriented interface to a sparse matrix |
RowMatrixTransposer | Construct and (optionally) redistribute the explicitly stored transpose of a CrsMatrix |
SrcDistObject | Abstract base class for objects that can be the source of an Import or Export operation |
Vector | A distributed dense vector |
CrsMatrixStruct | Struct that holds views of the contents of a CrsMatrix |
TpetraExamples | Namespace for Tpetra example classes and methods |