ScaLAPACK (SCAlable Linear Algebra PACKage) is a library of parallelized Linear Algebra routines. It contains routines for solving systems of linear equations, least squares problems, and eigenvalue problems.
ScaLAPACK is free available from http://www.netlib.org/scalapack/ , and is highly portable.
Contents of ScaLAPACK
ScaLAPACK contains routines for:
- the solution of linear systems of equations
- general and symmetric positive definite band linear systems of equations
- general and symmetric positive definite tridiagonal linear systems of equations
- condition estimation and iterative refinement for LU and Cholesky factorization
- matrix inversion
- full-rank linear least squares problems
- orthogonal and generalized orthogonal factorizations
- orthogonal transformation routines
- reductions to upper Hessenberg, bidiagonal and tridiagonal form
- reduction of a symmetric-definite generalized eigenproblem to standard form
- the symmetric/Hermitian eigenproblem
- the generalized symmetric/Hermitian eigenproblem
- the nonsymmetric eigenproblem
- the singular value decomposition
ScaLAPACK contains two-dimensional distributed memory versions of common LAPACK routines. It relies on calls to BLAS for local computations and calls to PBLAS for global computations.
For portability reasons, communications takes place inside the PBLAS routines through calls to the BLACS library.