Package no.uib.cipr.matrix.sparse

Unstructured sparse matrices and vectors with iterative solvers and preconditioners.

See: Description

Interface Summary

Interface	Description
ISparseVector
IterationMonitor	Monitors the iterative solution process for convergence and divergence.
IterationReporter	Reports on the progress of an iterative solver
IterativeSolver	Iterative linear solver.
Preconditioner	Preconditioner interface.

Class Summary

Class	Description
AbstractIterationMonitor	Partial implementation of an iteration reporter
AbstractIterativeSolver	Partial implementation of an iterative solver
AMG	Algebraic multigrid preconditioner.
ArpackSym	Uses ARPACK to partially solve symmetric eigensystems (ARPACK is designed to compute a subset of eigenvalues/eigenvectors).
BiCG	BiCG solver.
BiCGstab	BiCG stablized solver.
CG	Conjugate Gradients solver.
CGS	Conjugate Gradients squared solver.
Chebyshev	Chebyshev solver.
CompColMatrix	Compressed column storage (CCS) matrix
CompDiagMatrix	Compressed diagonal storage (CDS) matrix
CompRowMatrix	Compressed row storage (CRS) matrix
DefaultIterationMonitor	Default iteration monitor.
DiagonalPreconditioner	Diagonal preconditioner.
FlexCompColMatrix	Matrix stored column-wise into sparse vectors
FlexCompRowMatrix	Matrix stored row-wise into sparse vectors
GMRES	GMRES solver.
ICC	Incomplete Cholesky preconditioner without fill-in using a compressed row matrix as internal storage
ILU	ILU(0) preconditioner using a compressed row matrix as internal storage
ILUT	ILU preconditioner with fill-in.
IR	Iterative Refinement.
LinkedSparseMatrix	A Linked List (with shortcuts to important nodes) implementation of an n x m Matrix with z elements that has a typical O(z / m) insertion / lookup cost and an iterator that traverses columns then rows: a good fit for unstructured sparse matrices.
MatrixIterationMonitor	Iteration monitor based on matrix norms.
NoIterationReporter	An iteration reporter which does nothing.
OutputIterationReporter	Outputs iteration information to an output stream.
QMR	Quasi-Minimal Residual method.
SparseVector	Sparse vector
SSOR	SSOR preconditioner.

Enum Summary

Enum	Description
ArpackSym.Ritz

Exception Summary

Exception	Description
IterativeSolverNotConvergedException	Exception for lack of convergence in a linear problem.

Package no.uib.cipr.matrix.sparse Description

Unstructured sparse matrices and vectors with iterative solvers and preconditioners. The classes and interfaces can be grouped as follows:

• General sparse matrices
  • CompRowMatrix - Compressed row storage. Generally the best sparse matrix if the non-zero structure is known.
  • CompColMatrix - Compressed column storage.
  • CompDiagMatrix - Compressed diagonal storage.
  • FlexCompRowMatrix - Flexible compressed row storage. Stores each row as a growable sparse vector.
  • FlexCompColMatrix - Flexible compressed column storage. Stores each column as a growable sparse vector.
  • SparseVector - Growable sparse vector.
• Iterative solvers
  • BiCG - BiConjugate gradients.
  • BiCGstab - BiConjugate gradients stabilized.
  • CG - Conjugate gradients.
  • CGS - Conjugate gradients squared.
  • Chebyshev - The Chebyshev iteration for symmetrical, positive definite matrices.
  • GMRES - Generalized minimal residual using restart.
  • IR - Iterative refinement (Richardson's method).
  • QMR - Quasi-minimal residual.
• Preconditioners
  • DiagonalPreconditioner - Diagonal preconditioning.
  • SSOR - Symmetrical sucessive overrelaxation.
  • ICC - Incomplete Cholesky without fill-in.
  • ILU - Incomplete LU without fill-in.
  • ILUT - Incomplete LU with fill-in using a threshold approach.
  • AMG - Algebraic multigrid by smoothed aggregation.