Compression-Based Ray Casting of Very Large Volume Data in Distributed Environments

摘要

This paper proposes a new parallel/distributed ray-casting scheme for very large volume data that can be effec-tively used in distributed environments. Our method, based on data compression, attempts to enhance the rendering speedups by quickly reconstruction voxel data form local memory rather than expensively fetching them from remote memory spaces. Our compression-based volume render-ing scheme minimizes communications between processing elements during rendering computation, hence is very ap-propriate for both distributed-memory multiprocessors and PC/workstation clusters, where the relatively high commu-nication costs often hinder efficient parallel/distributed pro-cessing. We riport experimental results on both a Cray T3E and a PC/workstation cluster for the Visible Man dataset.