Abstract
The shifting of the data analysis and visualization applications by University of Minnesota from small clusters of PCs within the Laboratory for Computational Science & Engineering (LCSE) to a Grid-based approach using multiple PC clusters with dynamically varying ability is discussed. The visualization software develped at LCSE deals with hv-file and each hv-file is made up of a hierarchically organized collection of bricks of bytes along with metadata. The hierarchical volume rendering (HVR) utility is used to interactively designate a complex visual tour through the data as a sequence of key frames. A data movement orchestration utility is also built which allows users to specify extremely large and complex sequences of file movements.
| Original language | English (US) |
|---|---|
| Article number | 13 |
| Pages (from-to) | 115-125 |
| Number of pages | 11 |
| Journal | Proceedings of SPIE - The International Society for Optical Engineering |
| Volume | 5669 |
| DOIs | |
| State | Published - 2005 |
| Event | Proceedings of SPIE-IS and T Electronic Imaging - Visualization and Data Analysis 2005 - San Jose, CA, United States Duration: Jan 17 2005 → Jan 18 2005 |
Keywords
- Parallel and distributed volume visualization
- Visualization of extremely large datasets