Fault tolerant and fault testable hardware design
Fault tolerant and fault testable hardware design
A fault tolerant massively parallel processing architecture
Journal of Parallel and Distributed Computing
An O(logN) deterministic packet routing scheme
STOC '89 Proceedings of the twenty-first annual ACM symposium on Theory of computing
The design of a high performance packet-switched network
Journal of Parallel and Distributed Computing
A complexity theory for VLSI
Optical Switching and Networking
Hi-index | 0.00 |
The butterfly parallel system has a regular and simple interconnection pattern, making itsuitable for VLSI or WSI implementation. The authors propose an effective fault-toleranttechnique for the circular butterfly parallel system to ensure its rigid full butterflystructure even in the presence of failures, addressing reconfiguration in detail. Theresulting butterfly system has L levels, involves (1/log/sub 2/ L)% spare processingelements (PEs), and approximately 50% additional links. The reconfiguration process ofthe design in response to any operational fault is easy and can be performed in adistributed manner. The reliability and layout of this proposed design are evaluatedanalytically. This design, due to its specific configuration, exhibits significant improvement in reliability while taking only moderately more layout area.