A Comparison of Spatial Subdivision Algorithms for Sort-First Rendering

This paper describes and experimentally evaluates three adap-tive spatial subdivision heuristics for sort-rst parallel graphics rendering on distributed-memory multicomputers. In sort-rst rendering, image-space, or screen, is divided into regions. Each processor is assigned one or multiple regions to render. Primitives in the scene are redistributed among the processors according to region assignments. The total number of primitives in the system may increase due to duplication of primi-tives crossing multiple regions assigned to diierent processors. The common characteristic of the algorithms discussed in this paper is that a 2-dimensional mesh is superimposed on the screen and screen is subdivided using the primitive distribution on this mesh. Each processor is assigned a single region to render. The rst algorithm uses summed area table for subdividing the screen. The second algorithm uses quadtrees for subdivision. The third algorithm utilizes a graph partitioning approach. The second and the third algorithms are new approaches to adaptive screen subdivision in sort-rst rendering. We compare the algorithms in terms of load balancing performance, execution time of the algorithms, and percent increase in the total number of primitives after redistribution step. In this paper, we do not target a speciic rendering method such as polygon rendering or volume rendering. Our load balancing criteria is the number of primitives in each processor. We present experimental results on a Parsytec's CC parallel system.