Performance of the Direct Binary n-Cube Network for Multiprocessors
IEEE Transactions on Computers
On the design of deadlock-free adaptive routing algorithms for multicomputers: design methodologies
PARLE '91 Proceedings on Parallel architectures and languages Europe : volume I: parallel architectures and algorithms: volume I: parallel architectures and algorithms
An Adaptive and Fault Tolerant Wormhole Routing Strategy for k-ary n-cubes
IEEE Transactions on Computers
A New Theory of Deadlock-Free Adaptive Routing in Wormhole Networks
IEEE Transactions on Parallel and Distributed Systems
A comprehensive analytical model for wormhole routing in multicomputer systems
Journal of Parallel and Distributed Computing
A Performance Model for Duato's Fully Adaptive Routing Algorithm in k$k$-Ary n$n$-Cubes
IEEE Transactions on Computers
Interconnection Networks: An Engineering Approach
Interconnection Networks: An Engineering Approach
IEEE Transactions on Parallel and Distributed Systems
Theory, Volume 1, Queueing Systems
Theory, Volume 1, Queueing Systems
The Message Flow Model for Routing in Wormhole-Routed Networks
ICPP '93 Proceedings of the 1993 International Conference on Parallel Processing - Volume 01
| Hi-index | 0.00 |
In recent years, many researchers have devoted much efforts to construct high performance interconnect networks resilient to faults. Their studies motivated by the fact that a network can be a major performance bottleneck in parallel processors; such as multiprocessors system-on-chip (Mp-SoCs), multicomputers and cluster computers. This paper proposes a new analytical model to predict message latency in 2-dimensional wormhole-switched mesh with a routing scheme suggested by Linder and Harden [1], as an instance of a faulttolerant routing widely used in literature to achieve high adaptivity. Furthermore, the validity of the proposed model is demonstrated by comparing analytical results to those conducted through simulation experiments of the actual system and show a good degree of accuracy with as many as 10% nodes faulty.