A load balanced SIMD polygon renderer

Abstract

This document describes a parallel polygon rendering algorit.hrn designed for a SIMD supercomputer architecture. The overall algorithm can be implemented on any SIMD machine; in this paper, we expand upon an implementation which is specific to the Princeton Engine, a product of the David Sarnoff Research Center. The algorithm has a number of improvements over previously developed SIMD renderers in that load balancing is considered and designed into the algorithm with minimal overhead.