The design of reliable VLSI electronic systems for digital signal processing

The author reviews number-theoretic techniques for achieving hardware modularity in order to facilitate high data rates, testability, reliability, and fault tolerance, in VLSI digital signal processing systems. The theory of RNS (residue number system) error detection and correction is reviewed, and the special properties of modular systems are discussed for providing a rich environment for fault tolerant designs. Questions of reliability and fault tolerance on both the integrated circuit level and higher systems levels are discussed. The design of a convolutional back-projection digital processor for synthetic aperture radar (SAR) image processing is used as an example to investigate appropriate interactions between circuit-level error checking and system-level fault tolerance