Fast Stable Solvers for Sequentially Semi-Seperable Linear Systems of Equations

Technical Report · Fri Jan 17 04:00:00 EST 2003

DOI:https://doi.org/10.2172/15003389· OSTI ID:15003389

Chandrasekaran, S; DeWilde, P; Gu, M; Pals, T; van der Veen, A J; White, D A

We define the class of sequentially semi-separable matrices in this paper. Essentially this is the class of matrices which have low numerical rank on their off diagonal blocks. Examples include banded matrices, semi-separable matrices, their sums as well as inverses of these sums. Fast and stable algorithms for solving linear systems of equations involving such matrices and computing Moore-Penrose inverses are presented. Supporting numerical results are also presented. In addition, fast algorithms to construct and update this matrix structure for any given matrix are presented. Finally, numerical results that show that the coefficient matrices resulting from global spectral discretizations of certain integral equations indeed have this matrix structure are given.

• Research Organization: Lawrence Livermore National Lab., CA (US)
• Sponsoring Organization: US Department of Energy (US)
• DOE Contract Number: W-7405-ENG-48
• OSTI ID: 15003389
• Report Number(s): UCRL-CR-151499
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
ALGORITHMS
INTEGRAL EQUATIONS
MATRICES