Optimizing tridiagonal solvers for alternating direction methods on Boolean cube multiprocessors
Journal Article
·
· SIAM Journal on Scientific and Statistical Computing (Society for Industrial and Applied Mathematics); (USA)
- IBM Almaden Research Center, San Jose, CA (US)
- Dept. of Computer Science and Electrical Engineering, Yale Univ., New Haven, CT (US)
Sets of tridiagonal systems occur in many applications. Fast Poisson solvers and Alternate Direction Methods make use of tridiagonal system solvers. Network-based multiprocessors provide a cost-effective alternative to traditional supercomputer architectures. The complexity of concurrent algorithms for the solution of multiple tridiagonal systems on Boolean-cube-configured multiprocessors with distributed memory are investigated. Variations of odd-even cyclic reduction, parallel cyclic reduction, and algorithms making use of data transposition with or without substructuring and local elimination, or pipelined elimination, are considered. A simple performance model is used for algorithm comparison, and the validity of the model is verified on an Intel iPSC/1. For many combinations of machine and system parameters, pipelined elimination, or equation transposition with or without substructuring is optimum. Hybrid algorithms that at any stage choose the best algorithm among the considered ones for the remainder of the problem are presented. It is shown that the optimum partitioning of a set of independent tridiagonal systems among a set of processors yields the embarrassingly parallel case.
- OSTI ID:
- 6411089
- Journal Information:
- SIAM Journal on Scientific and Statistical Computing (Society for Industrial and Applied Mathematics); (USA), Journal Name: SIAM Journal on Scientific and Statistical Computing (Society for Industrial and Applied Mathematics); (USA) Vol. 11:3; ISSN 0196-5204; ISSN SIJCD
- Country of Publication:
- United States
- Language:
- English
Similar Records
A parallel algorithm for solving periodic tridiagonal Toeplitz linear systems
Two portable parallel tridiagonal solvers
Gigaflop speed algorithm for the direct solution of large block-tridiagonal systems in 3-D physics applications
Conference
·
Thu Dec 30 23:00:00 EST 1993
·
OSTI ID:54446
Two portable parallel tridiagonal solvers
Conference
·
Fri Jul 15 00:00:00 EDT 1994
·
OSTI ID:10183835
Gigaflop speed algorithm for the direct solution of large block-tridiagonal systems in 3-D physics applications
Journal Article
·
Tue Feb 28 23:00:00 EST 1989
· Comput. Phys.; (United States)
·
OSTI ID:6635997