Title :
A parallel sewing method for solving tridiagonal Toeplitz strictly diagonally dominant systems
Author :
Majedi, M. ; Shaw, R.E. ; Garey, L.E.
Author_Institution :
Dept. of Comput. Sci. & Appl. Stat., Univ. of New Brunswick, Saint John, NB
Abstract :
The large scale of linear systems of equations results in costly solving time. These systems usually have specific properties that can be used for designing fast algorithms. In addition, using parallel programming on distributed memory clusters enables us to get the results even faster. This work introduces a new fast parallel algorithm for solving systems with a strictly diagonally dominant three-band Toeplitz coefficient matrix. We call this new method the sewing method because the boundaries sew the adjacent subsystems together.
Keywords :
parallel algorithms; parallel programming; distributed memory clusters; parallel programming; parallel sewing method; tridiagonal toeplitz strictly diagonally dominant systems; Algorithm design and analysis; Clustering algorithms; Computer science; Equations; Large-scale systems; Linear systems; Matrix decomposition; Niobium; Parallel algorithms; Statistical distributions; Parallel algorithms; The sewing method; Tridiagonal; strictly diagonally dominant; tridiagonal Toeplitz systems;
Conference_Titel :
Parallel and Distributed Processing, 2008. IPDPS 2008. IEEE International Symposium on
Conference_Location :
Miami, FL
Print_ISBN :
978-1-4244-1693-6
Electronic_ISBN :
1530-2075
DOI :
10.1109/IPDPS.2008.4536466