BCYCLIC: A PARALLEL BLOCK TRIDIAGONAL MATRIX CYCLIC SOLVER

Journal Article · Thu Dec 31 23:00:00 EST 2009 · Journal of Computational Physics

DOI:https://doi.org/10.1016/j.jcp.2010.04.049· OSTI ID:1004423

Hirshman, Steven Paul ^[1]; Lynch, Vickie E ^[1]; Perumalla, Kalyan S ^[1]; Sanchez, Raul ^[1]

---

1. ORNL

A block tri-diagonal matrix is factored with minimal fill-in using a cyclic reduction algorithm that is easily parallelized. Storage of the factored blocks allows the application of the inverse to multiple right-hand sides which may not be known at factorization time. Scalability with the number of block rows is achieved with cyclic reduction, while scalability with the block size is achieved using multithreaded routines (OPENMP, GotoBLAS) for block matrix manipulation. This dual scalability is a noteworthy feature of this new solver, as well as its ability to handle arbitrary block row and processor numbers. Comparisons with other parallel block solvers are presented.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States). Oak Ridge Leadership Computing Facility (OLCF); Oak Ridge National Laboratory (ORNL)
• Sponsoring Organization: DOE Office of Science; SC USDOE - Office of Science (SC)
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 1004423
• Journal Information: Journal of Computational Physics, Journal Name: Journal of Computational Physics Journal Issue: 18 Vol. 229; ISSN 0021-9991
• Country of Publication: United States
• Language: English

Related Subjects

71 CLASSICAL AND QUANTUM MECHANICS
GENERAL PHYSICS
ALGORITHMS
FACTORIZATION
PHYSICS
STORAGE
block tridiagonal block solver cyclic reduction MPI