The NON-VON Supercomputer

NON-VON is a highly parallel, non-von Neumann supercomputer, portions of which are now being implemented in the Computer Science Department at Columbia University. The machine is intended to support the extremely rapid execution of large scale data manipulation tasks, including relational database operations and many other functions relevant to commercial data processing. The NON-VON architecture includes a tree-structured Primary Processing Subsystem (PPS), which we are implementing using custom nMOS VLSI circuits, along with a Secondary Processing Subsystem (SPS) based on a bank of intelligent disk drives. A high-bandwidth parallel interface provides for rapid data transfer between the two subsystems. This paper describes the organization of the NON-VON machine, with particular emphasis on the structure and function of the PPS. Some of the most important NON-VON programming techniques are then outlined, and their application to typical data processing applications illustrated with simple examples