Parallel Polygon Rendering with Precomputed Surface Patches

Abstract

We describe an algorithm for rendering a restricted class of trapeziums, and hence arbitrary polygons, in parallel on an NxN SIMD array processor. The algorithm achieves good performance by precomputing “surface patches” (finite portions of half -planes), thus trading storage for increased speed. The number of surface patches that are precomputed grows only linearly with the size of the array processor but as the square of the subpixel accuracy desired. NxN texture patterns can be added at very little extra cost additional to filling a trapezium with a particular colour.