Lawrence Berkeley National Laboratory

In one view, high performance and large data visualization is largely an exercise in the efficient use of bandwidth. Terascale visualization problems involve movement of large amounts of data from spinning disk to software components that transform the data into visible pixels. End-to-end, problems of this magnitude require a staggering amount of bandwidth and processing power. When the data, software components used for visualization, and users are separated by a network, then efficient bandwidth management becomes an even more critical concern. This chapter describes a highly specialized visualization application, Visapult, which performs high performance remote and distributed visualization. Visaput is perhaps best known for its ability to effectively utilize the network, having been used to win the High Performance Network Bandwidth Challenge at the annual IEEE/ACM Conference on Supercomputing three years in a row (2000-2002).