Mean Time to Failure Analysis in Shuffle Exchange Systems

Multistage Interconnection Network (MIN) has been researched for the interconnection implementation of switches and multiprocessors. The topology of the interconnection, the number of stage and the switching element used in the network distinguish between each MIN's tolerance of failure.This paper introduces a topology called Replicated Shuffle Exchange Network and Replicated Augmented Shuffle Exchange Network. A replicated technique is described for making the network more reliable. The replicated technique results in reduced the Mean Time to Failure in the network. Performance measurement shows that replicated network achieve a significant improvement over a basic network have been measured.

Design of Fault Tolerant Shuffle Exchange Gamma Interconnection Network Layouts

Advancement in technology has resulted in increased computing power with the use of multiple processors within a system. These multiple processors need to communicate with each other and with memory modules. Multistage Interconnection Networks (MINs) provide a communication medium in such multi-processor systems by interconnecting a number of processors and memory modules. Besides, MINs also provide a cost effective substitute to costly crossbars in parallel computers and switching systems in telephone industry. This paper introduces two new fault-tolerant MINs named as Shuffle Exchange Gamma Interconnection Networks (SEGIN-1 and SEGIN-2). SEGIN-1 and SEGIN-2 can be obtained by altering Shuffle Exchange Network with one extra stage (SEN+) and provide two disjoint paths similar to it. Performance of SEGIN-1 and SEGIN-2 has been evaluated in terms of alternative paths, disjoint paths, reliability and hardware cost, and is compared with some very famous MINs like Shuffle Exchange Network (SEN), Shuffle Exchange Network with one extra stage (SEN+), Shuffle Exchange Network with two extra stage (SEN+2), Extra Stage Cube (ESC) and Gamma Interconnection Network (GIN). Results suggest that SEGINs surpass all the compared networks; hence, the proposed designs seem to be suitable for implementing practical interconnection networks.