Exploration and Visualization of Very Large Datasets with the Active Data Repository

Abstract

The analysis and exploration of scientific datasets is a challenging and increasingly important part of scientific research. Visualization is a powerful analysis tool that converts numerical values into an image, which can be more easily analyzed by a human. We have developed a framework, called the Active Data Repository, that is designed to provide support for applications that analyze, explore and visualize very large multi-dimensional datasets. ADR targets distributed memory parallel machines with one or more disks attached to each node. In this paper, we present implementations of ray-casting based volume rendering and iso-surface rendering methods using ADR for visualizing out-of-core datasets, and describe experimental performance results. (Also cross-referenced as UMIACS-TR-2001-04)