Abstract
We propose a parallel Gauss-Seidel (GS) iterative algorithm for solving large systems of linear equations on a 2D torus network-con-chip (NoC) architecture. The proposed parallel algorithm is of O(Nn2/k2) time complexity for solving a system with matrix of order n on a k×k torus NoC architecture requiring N iterations assuming n and N are large compared to k (i.e. for large linear systems that require a large number of iterations). We show that under these conditions the proposed parallel GS algorithm has near optimal speedup and efficiency.
| Original language | English |
|---|---|
| Title of host publication | IASTED Multiconferences - Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2013 |
| Pages | 608-612 |
| Number of pages | 5 |
| DOIs | |
| Publication status | Published - 2013 |
| Event | 11th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2013 - Innsbruck, Austria Duration: Feb 11 2013 → Feb 13 2013 |
Other
| Other | 11th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2013 |
|---|---|
| Country | Austria |
| City | Innsbruck |
| Period | 2/11/13 → 2/13/13 |
Fingerprint
Keywords
- 2D torus
- Gauss-seidel
- Linear system of equations
- Network-on-Chip
- Parallel processing
ASJC Scopus subject areas
- Computer Networks and Communications
- Software
Cite this
Parallel gauss-seidel on a torus NOC architecture. / Day, Khaled; Al-Towaiq, Mohammad H.
IASTED Multiconferences - Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2013. 2013. p. 608-612.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Parallel gauss-seidel on a torus NOC architecture
AU - Day, Khaled
AU - Al-Towaiq, Mohammad H.
PY - 2013
Y1 - 2013
N2 - We propose a parallel Gauss-Seidel (GS) iterative algorithm for solving large systems of linear equations on a 2D torus network-con-chip (NoC) architecture. The proposed parallel algorithm is of O(Nn2/k2) time complexity for solving a system with matrix of order n on a k×k torus NoC architecture requiring N iterations assuming n and N are large compared to k (i.e. for large linear systems that require a large number of iterations). We show that under these conditions the proposed parallel GS algorithm has near optimal speedup and efficiency.
AB - We propose a parallel Gauss-Seidel (GS) iterative algorithm for solving large systems of linear equations on a 2D torus network-con-chip (NoC) architecture. The proposed parallel algorithm is of O(Nn2/k2) time complexity for solving a system with matrix of order n on a k×k torus NoC architecture requiring N iterations assuming n and N are large compared to k (i.e. for large linear systems that require a large number of iterations). We show that under these conditions the proposed parallel GS algorithm has near optimal speedup and efficiency.
KW - 2D torus
KW - Gauss-seidel
KW - Linear system of equations
KW - Network-on-Chip
KW - Parallel processing
UR - http://www.scopus.com/inward/record.url?scp=84875488254&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84875488254&partnerID=8YFLogxK
U2 - 10.2316/P.2013.795-025
DO - 10.2316/P.2013.795-025
M3 - Conference contribution
AN - SCOPUS:84875488254
SN - 9780889869431
SP - 608
EP - 612
BT - IASTED Multiconferences - Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2013
ER -