The package PARDISO is a thread-safe, high-performance, robust, memory efficient and easy to use software for solving large sparse symmetric and unsymmetric linear systems of equations on shared-memory and distributed-memory multiprocessors. The solver has has been licensed to thousands of researchers at international scientific laboratories and universities since its first release in 2004.
Features of the library version: Unsymmetric, structurally symmetric or symmetric systems, real or complex, positive definite or indefinite, hermitian. LU with complete pivoting. Parallel on SMPs and Cluster of SMPs. Automatic combination of iterative and direct solver algorithms to accelerate the solution process for very large three-dimensional systems.
Publications related to PARDISO are available here.
Jennifer Scott and Yifan Hu provide an independent review and study of the excellent performance of PARDISO and other sparse solvers.
The PARDISO Version 4.1.2 has been released (April 2011). It contains support for distributed-memory architectures. The MPI-based numerical factorization and parallel forward/backward substitution on distributed-memory architectures is available for symmetric indefinite matrices. PARDISO 4.1.2 has the unique feature among all solvers that it can compute the exact bit-identical solution on multicores and cluster of multicores.