Deadlock-Free Message Routing in Multiprocessor Interconnection Networks
IEEE Transactions on Computers
The Computer Journal
Space-Efficient and Fault-Tolerant Message Routing in Outerplanar Networks
IEEE Transactions on Computers
“Hypermeshes”: optical interconnection networks for parallel computing
Journal of Parallel and Distributed Computing
Optical networks: a practical perspective
Optical networks: a practical perspective
The Offset Cube: A Three-Dimensional Multicomputer Network Topology Using Through-Wafer Optics
IEEE Transactions on Parallel and Distributed Systems
Efficient Fault-Tolerant Routing in Multihop Optical WDM Networks
IEEE Transactions on Parallel and Distributed Systems
A genetic-based fault-tolerant routing strategy for multiprocessor networks
Future Generation Computer Systems - Special issue on bio-impaired solutions to parallel processing problems
IEEE Transactions on Parallel and Distributed Systems
Fault-tolerance schemes for WDM-based multiprocessor networks
MPPOI '95 Proceedings of the Second Workshop on Massively Parallel Processing Using Optical Interconnections
Optical design of a fault tolerant self-routing switch for massively parallel processing networks
MPPOI '95 Proceedings of the Second Workshop on Massively Parallel Processing Using Optical Interconnections
Handbook of Fiber Optic Data Communication, Third Edition: A Practical Guide to Optical Networking
Handbook of Fiber Optic Data Communication, Third Edition: A Practical Guide to Optical Networking
High-speed CMOS switch designs for free-space optoelectronic MIN's
IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Fault tolerant multiwavelength optical rings with limited wavelength conversion
IEEE Journal on Selected Areas in Communications
Hi-index | 0.00 |
This paper proposes and analyses a cost-effective fault-tolerant routing strategy for optical-based grid networks. We present the design of a fully adaptive, fault-tolerant routing strategy for multi-hop grid networks based on wavelength-division multiplexing. The routing strategy is both deadlock-free and livelock-free. Regardless of the number and type of faults and size of the grid network, only three buffer sets and two routing tables of size O(d) are required at each node, where d is the grid dimension. In the absence of faults, minimal paths with the least congestion are chosen to minimise latency. In the presence of faults or congestion, misrouting is selectively constrained to prevent livelock. The routing strategy requires only local fault information at each node, and does not require component redundancy or the isolation of healthy nodes and channels.