► N gko The Ginkgo namespace
► N accessor The accessor namespace
C abs_operation
C abs_operaton
C add
C bitwise_and
C bitwise_not
C bitwise_or
C bitwise_xor
C conj_operation
C conj_operaton
C div
C equal
C greater
C greater_or_equal
C imag_operation
C imag_operaton
C left_shift
C less
C less_or_equal
C logical_and
C logical_not
C logical_or
C max_operation
C min_operation
C mmul_operation
C mod
C mul
C not_equal
C one_operation
C one_operaton
C real_operation
C real_operaton
C right_shift
C row_major A row_major accessor is a bridge between a range and the row-major memory layout
C squared_norm_operation
C squared_norm_operaton
C sub
C transpose_operation
C unary_minus
C unary_plus
C zero_operation
► N batch
► N log The logger namespace
C BatchConvergence Logs the final residuals and iteration counts for a batch solver
► N matrix
C Csr Csr is a general sparse matrix format that stores the column indices for each nonzero entry and a cumulative sum of the number of nonzeros in each row
C Dense Dense is a batch matrix format which explicitly stores all values of the matrix in each of the batches
C Ell Ell is a sparse matrix format that stores the same number of nonzeros in each row, enabling coalesced accesses
C Identity The batch Identity matrix, which represents a batch of Identity matrices
► N preconditioner
► C Jacobi A block-Jacobi preconditioner is a block-diagonal linear operator, obtained by inverting the diagonal blocks (stored in a dense row major fashion) of the source operator
C Factory
C parameters_type
► N solver
C BatchSolver The BatchSolver is a base class for all batched solvers and provides the common getters and setter for these batched solver classes
► C Bicgstab BiCGSTAB or the Bi-Conjugate Gradient-Stabilized is a Krylov subspace solver
C Factory
C parameters_type
► C Cg Cg or the Conjugate Gradient is a Krylov subspace solver
C Factory
C parameters_type
C enable_preconditioned_iterative_solver_factory_parameters
C EnableBatchSolver This mixin provides apply and common iterative solver functionality to all the batched solvers
C BatchLinOp
C BatchLinOpFactory A BatchLinOpFactory represents a higher order mapping which transforms one batch linear operator into another
C EnableBatchLinOp The EnableBatchLinOp mixin can be used to provide sensible default implementations of the majority of the BatchLinOp and PolymorphicObject interface
C MultiVector MultiVector stores multiple vectors in a batched fashion and is useful for batched operations
► N config
C pnode Pnode describes a tree of properties
C registry This class stores additional context for creating Ginkgo objects from configuration files
C type_descriptor This class describes the value and index types to be used when building a Ginkgo type from a configuration file
► N experimental
► N distributed The distributed namespace
► N preconditioner The Preconditioner namespace
► C Schwarz A Schwarz preconditioner is a simple domain decomposition preconditioner that generalizes the Block Jacobi preconditioner, incorporating options for different local subdomain solvers and overlaps between the subdomains
C Factory
C parameters_type
C DistributedBase A base class for distributed objects
C index_map This class defines mappings between global and local indices
C Matrix The Matrix class defines a (MPI-)distributed matrix
C Partition Represents a partition of a range of indices [0, size) into a disjoint set of parts
C Vector Vector is a format which explicitly stores (multiple) distributed column vectors in a dense storage format
► N factorization
► C Cholesky Computes a Cholesky factorization of a symmetric, positive-definite sparse matrix
C parameters_type
C Factorization Represents a generic factorization consisting of two triangular factors (upper and lower) and an optional diagonal scaling matrix
► C Lu Computes an LU factorization of a sparse matrix
C parameters_type
► N mpi The mpi namespace, contains wrapper for many MPI functions
C communicator A thin wrapper of MPI_Comm that supports most MPI calls
C contiguous_type A move-only wrapper for a contiguous MPI_Datatype
C environment Class that sets up and finalizes the MPI environment
C request Light, move-only wrapper around the MPI_Request handle
C status The status struct is a light wrapper around the MPI_Status struct
C type_impl A struct that is used to determine the MPI_Datatype of a specified type
C type_impl< char >
C type_impl< double >
C type_impl< float >
C type_impl< int >
C type_impl< long >
C type_impl< long double >
C type_impl< long long >
C type_impl< unsigned >
C type_impl< unsigned char >
C type_impl< unsigned long >
C type_impl< unsigned long long >
C type_impl< unsigned short >
C window This class wraps the MPI_Window class with RAII functionality
► N reorder The Reorder namespace
► C Amd Computes a Approximate Minimum Degree (AMD) reordering of an input matrix
C parameters_type
► C Mc64 MC64 is an algorithm for permuting large entries to the diagonal of a sparse matrix
C parameters_type
► C Rcm Rcm (Reverse Cuthill-McKee) is a reordering algorithm minimizing the bandwidth of a matrix
C parameters_type
► C ScaledReordered Provides an interface to wrap reorderings like Rcm and diagonal scaling like equilibration around a LinOp like e.g
C Factory
C parameters_type
► N solver
► C Direct A direct solver based on a factorization into lower and upper triangular factors (with an optional diagonal scaling)
C Factory
C parameters_type
C EnableDistributedLinOp This mixin does the same as EnableLinOp , but for concrete types that are derived from distributed::DistributedBase
C EnableDistributedPolymorphicObject This mixin does the same as EnablePolymorphicObject , but for concrete types that are derived from distributed::DistributedBase
► N factorization The Factorization namespace
► C Ic Represents an incomplete Cholesky factorization (IC(0)) of a sparse matrix
C Factory
C parameters_type
► C Ilu Represents an incomplete LU factorization – ILU(0) – of a sparse matrix
C Factory
C parameters_type
► C ParIc ParIC is an incomplete Cholesky factorization which is computed in parallel
C Factory
C parameters_type
► C ParIct ParICT is an incomplete threshold-based Cholesky factorization which is computed in parallel
C Factory
C parameters_type
► C ParIlu ParILU is an incomplete LU factorization which is computed in parallel
C Factory
C parameters_type
► C ParIlut ParILUT is an incomplete threshold-based LU factorization which is computed in parallel
C Factory
C parameters_type
► N log The logger namespace
C Convergence Convergence is a Logger which logs data strictly from the criterion_check_completed
event
C criterion_data Struct representing Criterion related data
C EnableLogging EnableLogging is a mixin which should be inherited by any class which wants to enable logging
C executor_data Struct representing Executor related data
C iteration_complete_data Struct representing iteration complete related data
C linop_data Struct representing LinOp related data
C linop_factory_data Struct representing LinOp factory related data
C Loggable Loggable class is an interface which should be implemented by classes wanting to support logging
C Logger
C operation_data Struct representing Operator related data
C Papi Papi is a Logger which logs every event to the PAPI software
C PerformanceHint PerformanceHint is a Logger which analyzes the performance of the application and outputs hints for unnecessary copies and allocations
C polymorphic_object_data Struct representing PolymorphicObject related data
► C ProfilerHook This Logger can be used to annotate the execution of Ginkgo functionality with profiler-specific ranges
C nested_summary_entry
C NestedSummaryWriter Receives the results from ProfilerHook::create_nested_summary()
C summary_entry
C SummaryWriter Receives the results from ProfilerHook::create_summary()
C TableSummaryWriter Writes the results from ProfilerHook::create_summary() and ProfilerHook::create_nested_summary() to a ASCII table in Markdown format
C profiling_scope_guard Scope guard that annotates its scope with the provided profiler hooks
► C Record Record is a Logger which logs every event to an object
C logged_data Struct storing the actually logged data
C SolverProgress This Logger outputs the value of all scalar values (and potentially vectors) stored internally by the solver after each iteration
C Stream Stream is a Logger which logs every event to a stream
► N matrix The matrix namespace
C Coo COO stores a matrix in the coordinate matrix format
C CooBuilder
► C Csr CSR is a matrix format which stores only the nonzero coefficients by compressing each row of the matrix (compressed sparse row format)
C automatical
C classical Classical is a strategy_type which uses the same number of threads on each row
C cusparse Cusparse is a strategy_type which uses the sparselib csr
C load_balance Load_balance is a strategy_type which uses the load balance algorithm
C merge_path Merge_path is a strategy_type which uses the merge_path algorithm
C sparselib Sparselib is a strategy_type which uses the sparselib csr
C strategy_type Strategy_type is to decide how to set the csr algorithm
C CsrBuilder
C Dense Dense is a matrix format which explicitly stores all values of the matrix
C Diagonal This class is a utility which efficiently implements the diagonal matrix (a linear operator which scales a vector row wise)
C Ell ELL is a matrix format where stride with explicit zeros is used such that all rows have the same number of stored elements
C Fbcsr Fixed-block compressed sparse row storage matrix format
C FbcsrBuilder
C Fft This LinOp implements a 1D Fourier matrix using the FFT algorithm
C Fft2 This LinOp implements a 2D Fourier matrix using the FFT algorithm
C Fft3 This LinOp implements a 3D Fourier matrix using the FFT algorithm
► C Hybrid HYBRID is a matrix format which splits the matrix into ELLPACK and COO format
C automatic Automatic is a strategy_type which decides the number of stored elements per row of the ell part automatically
C column_limit Column_limit is a strategy_type which decides the number of stored elements per row of the ell part by specifying the number of columns
C imbalance_bounded_limit Imbalance_bounded_limit is a strategy_type which decides the number of stored elements per row of the ell part
C imbalance_limit Imbalance_limit is a strategy_type which decides the number of stored elements per row of the ell part according to the percent
C minimal_storage_limit Minimal_storage_limit is a strategy_type which decides the number of stored elements per row of the ell part
C strategy_type Strategy_type is to decide how to set the hybrid config
C Identity This class is a utility which efficiently implements the identity matrix (a linear operator which maps each vector to itself)
C IdentityFactory This factory is a utility which can be used to generate Identity operators
C Permutation Permutation is a matrix format that represents a permutation matrix, i.e
C RowGatherer RowGatherer is a matrix "format" which stores the gather indices arrays which can be used to gather rows to another matrix
C ScaledPermutation ScaledPermutation is a matrix combining a permutation with scaling factors
C Sellp SELL-P is a matrix format similar to ELL format
C SparsityCsr SparsityCsr is a matrix format which stores only the sparsity pattern of a sparse matrix by compressing each row of the matrix (compressed sparse row format)
► N multigrid The multigrid components namespace
C EnableMultigridLevel The EnableMultigridLevel gives the default implementation of MultigridLevel with composition and provides set_multigrid_level
function
► C FixedCoarsening FixedCoarsening is a very simple coarse grid generation algorithm
C Factory
C parameters_type
C MultigridLevel This class represents two levels in a multigrid hierarchy
► C Pgm Parallel graph match (Pgm ) is the aggregate method introduced in the paper M
C Factory
C parameters_type
► N preconditioner The Preconditioner namespace
C block_interleaved_storage_scheme Defines the parameters of the interleaved block storage scheme used by block-Jacobi blocks
► C GaussSeidel This class generates the Gauss-Seidel preconditioner
C parameters_type
► C Ic The Incomplete Cholesky (IC) preconditioner solves the equation for a given lower triangular matrix L and the right hand side b (can contain multiple right hand sides)
C Factory
C parameters_type
► C Ilu The Incomplete LU (ILU) preconditioner solves the equation for a given lower triangular matrix L, an upper triangular matrix U and the right hand side b (can contain multiple right hand sides)
C Factory
C parameters_type
► C Isai The Incomplete Sparse Approximate Inverse (ISAI) Preconditioner generates an approximate inverse matrix for a given square matrix A, lower triangular matrix L, upper triangular matrix U or symmetric positive (spd) matrix B
C Factory
C parameters_type
► C Jacobi A block-Jacobi preconditioner is a block-diagonal linear operator, obtained by inverting the diagonal blocks of the source operator
C Factory
C parameters_type
► C Sor This class generates the (S)SOR preconditioner
C parameters_type
► N reorder The Reorder namespace
► C Rcm Rcm (Reverse Cuthill-McKee) is a reordering algorithm minimizing the bandwidth of a matrix
C Factory
C parameters_type
C ReorderingBase The ReorderingBase class is a base class for all the reordering algorithms
C ReorderingBaseArgs This struct is used to pass parameters to the EnableDefaultReorderingBaseFactory::generate() method
► N solver The ginkgo Solve namespace
C ApplyWithInitialGuess ApplyWithInitialGuess provides a way to give the input guess for apply function
► C Bicg BICG or the Biconjugate gradient method is a Krylov subspace solver
C Factory
C parameters_type
► C Bicgstab BiCGSTAB or the Bi-Conjugate Gradient-Stabilized is a Krylov subspace solver
C Factory
C parameters_type
► C CbGmres CB-GMRES or the compressed basis generalized minimal residual method is an iterative type Krylov subspace method which is suitable for nonsymmetric linear systems
C Factory
C parameters_type
► C Cg CG or the conjugate gradient method is an iterative type Krylov subspace method which is suitable for symmetric positive definite methods
C Factory
C parameters_type
► C Cgs CGS or the conjugate gradient square method is an iterative type Krylov subspace method which is suitable for general systems
C Factory
C parameters_type
C enable_iterative_solver_factory_parameters
C enable_preconditioned_iterative_solver_factory_parameters
C EnableApplyWithInitialGuess EnableApplyWithInitialGuess providing default operation for ApplyWithInitialGuess with correct validation and log
C EnableIterativeBase A LinOp deriving from this CRTP class stores a stopping criterion factory and allows applying with a guess
C EnablePreconditionable Mixin providing default operation for Preconditionable with correct value semantics
C EnablePreconditionedIterativeSolver A LinOp implementing this interface stores a system matrix and stopping criterion factory
C EnableSolverBase A LinOp deriving from this CRTP class stores a system matrix
► C Fcg FCG or the flexible conjugate gradient method is an iterative type Krylov subspace method which is suitable for symmetric positive definite methods
C Factory
C parameters_type
► C Gcr GCR or the generalized conjugate residual method is an iterative type Krylov subspace method similar to GMRES which is suitable for nonsymmetric linear systems
C Factory
C parameters_type
► C Gmres GMRES or the generalized minimal residual method is an iterative type Krylov subspace method which is suitable for nonsymmetric linear systems
C Factory
C parameters_type
C has_with_criteria Helper structure to test if the Factory of SolverType has a function with_criteria
► C Idr IDR(s) is an efficient method for solving large nonsymmetric systems of linear equations
C Factory
C parameters_type
► C Ir Iterative refinement (IR) is an iterative method that uses another coarse method to approximate the error of the current solution via the current residual
C Factory
C parameters_type
C IterativeBase A LinOp implementing this interface stores a stopping criterion factory
► C LowerTrs LowerTrs is the triangular solver which solves the system L x = b, when L is a lower triangular matrix
C Factory
C parameters_type
► C Multigrid Multigrid methods have a hierarchy of many levels, whose corase level is a subset of the fine level, of the problem
C Factory
C parameters_type
C SolverBase
► C UpperTrs UpperTrs is the triangular solver which solves the system U x = b, when U is an upper triangular matrix
C Factory
C parameters_type
C workspace_traits Traits class providing information on the type and location of workspace vectors inside a solver
C workspace_traits< Bicg< ValueType > >
C workspace_traits< Bicgstab< ValueType > >
C workspace_traits< Cg< ValueType > >
C workspace_traits< Cgs< ValueType > >
C workspace_traits< Fcg< ValueType > >
C workspace_traits< Gcr< ValueType > >
C workspace_traits< gko::experimental::solver::Direct< ValueType, IndexType > >
C workspace_traits< Gmres< ValueType > >
C workspace_traits< Idr< ValueType > >
C workspace_traits< Ir< ValueType > >
C workspace_traits< LowerTrs< ValueType, IndexType > >
C workspace_traits< Multigrid >
C workspace_traits< UpperTrs< ValueType, IndexType > >
► N stop The Stopping criterion namespace
► C AbsoluteResidualNorm The AbsoluteResidualNorm class is a stopping criterion which stops the iteration process when the residual norm is below a certain threshold, i.e
C Factory
C parameters_type
► C Combined Used to combine multiple criterions together through an OR operation
C Factory
C parameters_type
► C Criterion Base class for all stopping criteria
C Updater Serves for convenient argument passing to the Criterion 's check function
C CriterionArgs This struct is used to pass parameters to the EnableDefaultCriterionFactoryCriterionFactory::generate() method
► C ImplicitResidualNorm The ImplicitResidualNorm class is a stopping criterion which stops the iteration process when the implicit residual norm is below a certain threshold relative to
C Factory
C parameters_type
► C Iteration Stopping criterion which stops the iteration process after a preset number of iterations
C Factory
C parameters_type
► C RelativeResidualNorm The RelativeResidualNorm class is a stopping criterion which stops the iteration process when the residual norm is below a certain threshold relative to the norm of the right-hand side, i.e
C Factory
C parameters_type
► C ResidualNorm The ResidualNorm class is a stopping criterion which stops the iteration process when the actual residual norm is below a certain threshold relative to
C Factory
C parameters_type
C ResidualNormBase The ResidualNormBase class provides a framework for stopping criteria related to the residual norm
► C ResidualNormReduction The ResidualNormReduction class is a stopping criterion which stops the iteration process when the residual norm is below a certain threshold relative to the norm of the initial residual, i.e
C Factory
C parameters_type
► C Time Stopping criterion which stops the iteration process after a certain amount of time has passed
C Factory
C parameters_type
► N syn The Synthesizer namespace
C range Range records start, end, step in template
C type_list Type_list records several types in template
C value_list Value_list records several values with the same type in template
C AbsoluteComputable The AbsoluteComputable is an interface that allows to get the component wise absolute of a LinOp
C AbstractFactory The AbstractFactory is a generic interface template that enables easy implementation of the abstract factory design pattern
C AllocationError AllocationError is thrown if a memory allocation fails
C Allocator Provides generic allocation and deallocation functionality to be used by an Executor
C amd_device Amd_device handles the number of executor on Amd devices and have the corresponding recursive_mutex
C are_all_integral Evaluates if all template arguments Args fulfill std::is_integral
C are_all_integral< First, Args... >
C array An array is a container which encapsulates fixed-sized arrays, stored on the Executor tied to the array
C BadDimension BadDimension is thrown if an operation is being applied to a LinOp with bad dimensions
C batch_dim A type representing the dimensions of a multidimensional batch object
C BlockOperator A BlockOperator represents a linear operator that is partitioned into multiple blocks
C BlockSizeError Error that denotes issues between block sizes and matrix dimensions
C Combination The Combination class can be used to construct a linear combination of multiple linear operators c1 * op1 + c2 * op2 + ... + ck * opk
C Composition The Composition class can be used to compose linear operators op1, op2, ..., opn
and obtain the operator op1 * op2 * ... * opn
C ConvertibleTo ConvertibleTo interface is used to mark that the implementer can be converted to the object of ResultType
C CpuAllocator Allocator using new/delete
C CpuAllocatorBase Implement this interface to provide an allocator for OmpExecutor or ReferenceExecutor
C CpuTimer A timer using std::chrono::steady_clock for timing
C cpx_real_type Access the underlying real type of a complex number
C CublasError CublasError is thrown when a cuBLAS routine throws a non-zero error code
C cuda_stream An RAII wrapper for a custom CUDA stream
C CudaAllocator Allocator using cudaMalloc
C CudaAllocatorBase Implement this interface to provide an allocator for CudaExecutor
C CudaAsyncAllocator
C CudaError CudaError is thrown when a CUDA routine throws a non-zero error code
C CudaExecutor This is the Executor subclass which represents the CUDA device
C CudaHostAllocator
C CudaTimer A timer using events for timing on a CudaExecutor
C CudaUnifiedAllocator
C CufftError CufftError is thrown when a cuFFT routine throws a non-zero error code
C CurandError CurandError is thrown when a cuRAND routine throws a non-zero error code
C CusparseError CusparseError is thrown when a cuSPARSE routine throws a non-zero error code
C default_converter Used to convert objects of type S
to objects of type R
using static_cast
C deferred_factory_parameter Represents a factory parameter of factory type that can either initialized by a pre-existing factory or by passing in a factory_parameters object whose .on(exec)
will be called to instantiate a factory
► C device_matrix_data This type is a device-side equivalent to matrix_data
C arrays Stores the internal arrays of a device_matrix_data object
C DiagonalExtractable The diagonal of a LinOp implementing this interface can be extracted
C DiagonalLinOpExtractable The diagonal of a LinOp can be extracted
C dim A type representing the dimensions of a multidimensional object
C dim< 1u, DimensionType >
C DimensionMismatch DimensionMismatch is thrown if an operation is being applied to LinOps of incompatible size
C DpcppExecutor This is the Executor subclass which represents a DPC++ enhanced device
C DpcppTimer A timer using kernels for timing on a DpcppExecutor in profiling mode
C enable_parameters_type The enable_parameters_type mixin is used to create a base implementation of the factory parameters structure
C EnableAbsoluteComputation The EnableAbsoluteComputation mixin provides the default implementations of compute_absolute_linop
and the absolute interface
C EnableAbstractPolymorphicObject This mixin inherits from (a subclass of) PolymorphicObject and provides a base implementation of a new abstract object
C EnableCreateMethod This mixin implements a static create()
method on ConcreteType
that dynamically allocates the memory, uses the passed-in arguments to construct the object, and returns an std::unique_ptr to such an object
C EnableDefaultFactory This mixin provides a default implementation of a concrete factory
C EnableLinOp The EnableLinOp mixin can be used to provide sensible default implementations of the majority of the LinOp and PolymorphicObject interface
C EnablePolymorphicAssignment This mixin is used to enable a default PolymorphicObject::copy_from() implementation for objects that have implemented conversions between them
C EnablePolymorphicObject This mixin inherits from (a subclass of) PolymorphicObject and provides a base implementation of a new concrete polymorphic object
C err
C Error Used to report exceptional behaviour in library functions
C Executor The first step in using the Ginkgo library consists of creating an executor
C executor_deleter This is a deleter that uses an executor's free
method to deallocate the data
C executor_deleter< T[]>
C half A class providing basic support for half precision floating point types
C hip_stream An RAII wrapper for a custom HIP stream
C HipAllocator
C HipAllocatorBase Implement this interface to provide an allocator for HipExecutor
C HipAsyncAllocator
C HipblasError HipblasError is thrown when a hipBLAS routine throws a non-zero error code
C HipError HipError is thrown when a HIP routine throws a non-zero error code
C HipExecutor This is the Executor subclass which represents the HIP enhanced device
C HipfftError HipfftError is thrown when a hipFFT routine throws a non-zero error code
C HipHostAllocator
C HiprandError HiprandError is thrown when a hipRAND routine throws a non-zero error code
C HipsparseError HipsparseError is thrown when a hipSPARSE routine throws a non-zero error code
C HipTimer A timer using events for timing on a HipExecutor
C HipUnifiedAllocator
C index_set An index set class represents an ordered set of intervals
C InvalidStateError Exception thrown if an object is in an invalid state
C KernelNotFound KernelNotFound is thrown if Ginkgo cannot find a kernel which satisfies the criteria imposed by the input arguments
C LinOp
C LinOpFactory A LinOpFactory represents a higher order mapping which transforms one linear operator into another
C machine_topology The machine topology class represents the hierarchical topology of a machine, including NUMA nodes, cores and PCI Devices
C matrix_assembly_data This structure is used as an intermediate type to assemble a sparse matrix
C matrix_data This structure is used as an intermediate data type to store a sparse matrix
C matrix_data_entry Type used to store nonzeros
C MetisError MetisError is thrown when METIS routine throws an error code
C MpiError MpiError is thrown when a MPI routine throws a non-zero error code
C NotCompiled NotCompiled is thrown when attempting to call an operation which is a part of a module that was not compiled on the system
C NotImplemented NotImplemented is thrown in case an operation has not yet been implemented (but will be implemented in the future)
C NotSupported NotSupported is thrown in case it is not possible to perform the requested operation on the given object type
C null_deleter This is a deleter that does not delete the object
C null_deleter< T[]>
C nvidia_device Nvidia_device handles the number of executor on Nvidia devices and have the corresponding recursive_mutex
C OmpExecutor This is the Executor subclass which represents the OpenMP device (typically CPU)
C Operation Operations can be used to define functionalities whose implementations differ among devices
C OutOfBoundsError OutOfBoundsError is thrown if a memory access is detected to be out-of-bounds
C OverflowError OverflowError is thrown when an index calculation for storage requirements overflows
C Permutable Linear operators which support permutation should implement the Permutable interface
C Perturbation The Perturbation class can be used to construct a LinOp to represent the operation (identity + scalar * basis * projector)
C PolymorphicObject A PolymorphicObject is the abstract base for all "heavy" objects in Ginkgo that behave polymorphically
C precision_reduction This class is used to encode storage precisions of low precision algorithms
C Preconditionable A LinOp implementing this interface can be preconditioned
C ptr_param This class is used for function parameters in the place of raw pointers
C range A range is a multidimensional view of the memory
C ReadableFromMatrixData A LinOp implementing this interface can read its data from a matrix_data structure
C ReferenceExecutor This is a specialization of the OmpExecutor , which runs the reference implementations of the kernels used for debugging purposes
C ScaledIdentityAddable Adds the operation M <- a I + b M for matrix M, identity operator I and scalars a and b, where M is the calling object
C scoped_device_id_guard This move-only class uses RAII to set the device id within a scoped block, if necessary
C segmented_array A minimal interface for a segmented array
C span A span is a lightweight structure used to create sub-ranges from other ranges
C stopping_status This class is used to keep track of the stopping status of one vector
C StreamError StreamError is thrown if accessing a stream failed
C time_point An opaque wrapper for a time point generated by a timer
C Timer Represents a generic timer that can be used to record time points and measure time differences on host or device streams
C Transposable Linear operators which support transposition should implement the Transposable interface
C truncated
C UnsupportedMatrixProperty Exception throws if a matrix does not have a property required by a numerical method
C UseComposition The UseComposition class can be used to store the composition information in LinOp
C ValueMismatch ValueMismatch is thrown if two values are not equal
C version This structure is used to represent versions of various Ginkgo modules
C version_info Ginkgo uses version numbers to label new features and to communicate backward compatibility guarantees:
C WritableToMatrixData A LinOp implementing this interface can write its data to a matrix_data structure
C hwloc_obj_t
C hwloc_obj_type_t