Abstract
Network-on-chip multicore architectures with a large number of processing elements are becoming a reality with the recent developments in technology. In these modern systems the processing elements are interconnected with regular network-on-chip (NoC) topologies such as meshes and trees. In this paper we propose a parallel Gauss-Seidel (GS) iterative algorithm for solving large systems of linear equations on a torus NoC architecture. The proposed parallel algorithm is O(Nn2/k2) time complexity for solving a system with matrix of order n on a k × k torus NoC architecture with 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.
Original language | English |
---|---|
Article number | 1250001 |
Journal | Journal of Interconnection Networks |
Volume | 13 |
Issue number | 1-2 |
DOIs | |
Publication status | Published - Mar 2012 |
Fingerprint
Keywords
- Gauss-Seidel
- iterative method
- linear system of equations
- Network-on-chip
- torus, parallel algorithm
ASJC Scopus subject areas
- Computer Networks and Communications
Cite this
Parallel gauss-seidel on a torus network-on-chip architecture. / Al-Towaiq, Mohammad H.; Day, Khaled.
In: Journal of Interconnection Networks, Vol. 13, No. 1-2, 1250001, 03.2012.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Parallel gauss-seidel on a torus network-on-chip architecture
AU - Al-Towaiq, Mohammad H.
AU - Day, Khaled
PY - 2012/3
Y1 - 2012/3
N2 - Network-on-chip multicore architectures with a large number of processing elements are becoming a reality with the recent developments in technology. In these modern systems the processing elements are interconnected with regular network-on-chip (NoC) topologies such as meshes and trees. In this paper we propose a parallel Gauss-Seidel (GS) iterative algorithm for solving large systems of linear equations on a torus NoC architecture. The proposed parallel algorithm is O(Nn2/k2) time complexity for solving a system with matrix of order n on a k × k torus NoC architecture with 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.
AB - Network-on-chip multicore architectures with a large number of processing elements are becoming a reality with the recent developments in technology. In these modern systems the processing elements are interconnected with regular network-on-chip (NoC) topologies such as meshes and trees. In this paper we propose a parallel Gauss-Seidel (GS) iterative algorithm for solving large systems of linear equations on a torus NoC architecture. The proposed parallel algorithm is O(Nn2/k2) time complexity for solving a system with matrix of order n on a k × k torus NoC architecture with 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.
KW - Gauss-Seidel
KW - iterative method
KW - linear system of equations
KW - Network-on-chip
KW - torus, parallel algorithm
UR - http://www.scopus.com/inward/record.url?scp=84874799178&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84874799178&partnerID=8YFLogxK
U2 - 10.1142/S0219265912500016
DO - 10.1142/S0219265912500016
M3 - Article
AN - SCOPUS:84874799178
VL - 13
JO - Advanced healthcare materials
JF - Advanced healthcare materials
SN - 2192-2640
IS - 1-2
M1 - 1250001
ER -