Machine instructions of a data-driven architecture - Design considerations

A major trend in the future use of computers is in the artificial intelligence (AI) field. There is a strong need for a new class of concurrent parallel computer architectures for solving complicated problems. Natural candidates for a parallel implementation are the data driven architectures. The existing data driven machines have some critical shortcomings for the implementation of AI systems. This paper deals with the design considerations of the instructions set, and their execution algorithms, of a new machine which was designed by the authors to be efficient in List processing and parallel execution even on large data structures. The proposed architecture manipulates data and instructions in a similar way which contributes to the machine's regularity and ability to execute AI programs. This paper presents the unusual concepts which were introduced into the system architecture from the viewpoints of its data structure and machine instructions.