A parallel program execution model supporting modular software construction

Abstract

A watershed is near in the architecture of computer systems. There is overwhelming demand for systems that support a universal format for computer programs and software components so users may benefit from their use on a wide variety of computing platforms. At present this demand is being met by commodity microprocessors together with standard operating system interfaces. However current systems do not offer a standard API (application program interface) for parallel programming, and the popular interfaces for parallel computing violate essential principles of modular or component-based software construction. Moreover microprocessor architecture is reaching the limit of what can be done usefully within the framework of superscalar and VLIW processor models. The next step is to put several processors (or the equivalent) on a single chip. This paper presents a set of principles for modular software construction and describes a program execution model based on functional programming that satisfies the set of principles. The implications of the principles for computer system architecture are discussed together with a sketch of the architecture of a multithread processing chip which promises to provide efficient execution of parallel computations while providing a sound base for modular software construction.