Fine-grain visualization algorithms in dataflow environments

Most of the current dataflow visualization systems are based on coarse-grain dataflow computing models. In this paper we propose a fine-grain dataflow model that takes advantage of data locality properties of many visualization algorithms. A fine-grain module works on small chunks of data one at a time by keeping a dynamically adjusted moving window on the input data stream. It is more memory efficient and has the potential of handling very large data sets without taking up all the memory resources. Two popular visualization algorithms, an iso-surface extraction algorithm 1 and a volume rendering algorithm 2, are implemented using the fine-grain model. The performance measurements showed faster speed, reduced memory usage, and improved CPU utilization over a typical coarse-grain system.