Distributing display lists on a multicomputer

Abstract

We have developed techniques for distributing a hierarchical display list from a PHIGS-like library across a multicomputer. By storing a portion of the database at each processor, inter-processor communication is reduced. This reduction promises traversal of the display list at rates supporting rendering speeds of one million polygons/second or more, as we hope to achieve on our new machine, Pixel-Planes 5 (under construction). Our distribution techniques support order-dependent primitives and allow general display list editing.