An echo-back protocol for a fault tolerant bus architecture

A bus protocol for detecting and avoiding latent faults and multiple faults on buses is presented. The hardware overhead is small, and the design is easily implementable by extensions to existing bus systems. The theoretical maximum performance degradation can be up to 33% in communication bound tasks if no other activity interferes with the operation of the system. The results of the simulation, however, show that the actual degradation of performance is substantially lower.<>