Fault and Defect Tolerant Computer Architectures: Reliable Computing with Unreliable Devices

摘要

This research addresses design of a reliable computer from unreliable device technologies. A system architecture is developed for a 'fault and defect tolerant' (FDT) computer. Trade-offs between different techniques are studied and yield and hardware cost models are developed. Fault and defect tolerant designs are created for the processor and the cache memory. Simulation results for the content-addressable memory (CAM)-based cache show 90% yield with device failure probabilities of 3 x 10(-6), three orders of magnitude better than non fault tolerant caches of the same size. The entire processor achieves 70% yield with device failure probabilities exceeding 10(-6). The required hardware redundancy is approximately 15 times that of a non-fault tolerant design. While larger than current FT designs, this architecture allows the use of devices much more likely to fail than silicon CMOS. As part of model development, an improved model is derived for NAND Multiplexing. The model is the first accurate model for small and medium amounts of redundancy. Previous models are extended to account for dependence between the inputs and produce more accurate results.