Initial experiences with grid-based volume visualization of fluid flow simulations on PC clusters

Research output: Contribution to journalConference articlepeer-review

5 Scopus citations

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 languageEnglish (US)
Article number13
Pages (from-to)115-125
Number of pages11
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume5669
DOIs
StatePublished - 2005
EventProceedings of SPIE-IS and T Electronic Imaging - Visualization and Data Analysis 2005 - San Jose, CA, United States
Duration: Jan 17 2005Jan 18 2005

Keywords

  • Parallel and distributed volume visualization
  • Visualization of extremely large datasets

Fingerprint Dive into the research topics of 'Initial experiences with grid-based volume visualization of fluid flow simulations on PC clusters'. Together they form a unique fingerprint.

Cite this