Multiprocessor Architecture Using Modular Arithmetic for Very High Precision Computation

摘要

This document outlines a multiprocessor architecture that uses modular arithmetic to implement numerical computation with 900 bits of intermediate precision. A proposed prototype, to be implemented with off-the-shelf parts, will perform high-precision arithmetic as fast as some workstations and mini-computers can perform IEEE double-precision arithmetic. The author discusses how the structure of modular arithmetic conveniently maps into a simple, pipelined multiprocessor architecture. He presents techniques developed to overcome a few classical drawbacks of modular arithmetic. This architecture is suitable to and essential for the study of chaotic dynamical systems. (kr)