Issue No. 02 - March/April (2003 vol. 23)
Charles Hansen , University of Utah
Chris Johnson , University of Utah
The following quote from Sid Karen (the former director of the San Diego Supercomputing Center) aptly describes the state of distributed computing over a grid:
As we enter the 21st century, the traditional model of stand-alone, centralized computer systems is rapidly evolving toward grid-based computing across a ubiquitous, continuous, and pervasive national computational infrastructure.
While many application scenarios are not yet possible, grid computing will provide access to distributed resources with the same ease we now access electrical power. Consider the following scenarios described by Dan Reed, director of the National Center for Supercomputing Applications and professor of computer science at the University of Illinois at Urbana-Champaign, in his recent Computer article: 1
Imagine correlating petabytes of imagery and data from multiple optical, radio, infrared, and x-ray telescopes and their associated data archives to study the initial formation of large-scale structures of matter in the early universe. Imagine combining real-time Doppler radar data from multiple sites with high-resolution weather models to predict storm formation and movement through individual neighborhoods. Imagine developing custom drugs tailored to specific genotypes based on statistical analysis of single nucleotide polymorphisms across individuals and their correlation with gene functions.
Clearly, the ability to analyze data within this distributed environment is critical to the success of the grid. To successfully analyze data, we need visualization tools. This special issue provides a glimpse at the future of grid visualization by exploring working prototypes that exploit distributed resources.
About the Articles
The first article, "Enabling View-Dependent Progressive Volume Visualization on the Grid" by Alan Norton and Alyn Rockwood describes and evaluates the communication in a progressive, visibility-driven compression scheme for distributing volumetric data from grid resources to volume-rendering clients.
In "Visualization Systems on the Information-Technology-Based Laboratory," Yoshio Suzuki et al. explore a local grid called the Information-Technology-Based Laboratory and two visualization systems developed for that environment. Using their system, they explored real-time collaborative visualization of a coupled multiphysics numerical simulation, executed on their local grid, which possibly has simulation steering applications.
In the next article, "Deploying Web-Based Visual Exploration Tools on the Grid," T.J. Jankun-Kelly et al. discuss a Web portal, VisPortal, tailored to the exploration, encapsulation, and dissemination of visualization results over the grid. Their approach uses standard Web technologies tied together into a functional system. This let them develop a visualization application called AMRWebSheet used to analyze a grid-enabled adaptive mesh refinement simulation.
In "Grid-Distributed Visualizations Using Connectionless Protocols," E. Wes Bethel and John Shalf explore using the user datagram protocol for remote visualization (with the Visapult system) for the analysis of a grid-enabled, high-performance physics simulation for studying gravitational waveforms of colliding black holes (the Cactus code).
Finally, "Treemaps for Workload Visualization" by Steve Heisig describes an information visualization of grid resources. By using an information visualization technique called treemaps applied to resource utilization data, more effective analysis of grid services management is possible.
These articles provide an insight into how visualization can effectively use, analyze, and explore grid-based data and applications.
We thank the authors who submitted 15 high-quality articles for this special issue. The submission quality made the selection of the included articles difficult. An international set of reviewers—renowned in the field of graphics, visualization, and grid computing—reviewed the submissions. We thank these reviewers for giving us careful and thoughtful comments. We also thank the IEEE CG&A staff for helping with the editorial aspects of this special issue. We hope you enjoy the articles.
Charles Hansen is an associate professor of computer science at the University of Utah. His research interests include large-scale scientific visualization and computer graphics. He received a BS in computer science from Memphis State University and a PhD in computer science from the University of Utah. He was a technical staff member in the Advanced Computing Laboratory (ACL) located at Los Alamos National Laboratory, where he formed and directed the visualization efforts in the ACL. He is a member of the IEEE Computer Society, ACM, and SIAM.
Chris Johnson directs the Scientific Computing and Imaging Institute at the University of Utah where he is a professor of computer science and holds faculty appointments in the departments of physics and bioengineering. His research interests are in the area of scientific computing and include inverse and imaging problems, adaptive methods, problem-solving environments, large-scale computational problems in medicine, and scientific visualization. He received a PhD in biophysics from the University of Utah. In 1996, he received a Department of Energy Computational Science Award and in 1997 the Par Excellence Award from the University of Utah Alumni Association and the Presidential Teaching Scholar Award. In 1999, he was awarded the Governor's Medal for Science and Technology. He is a member of the IEEE Computer Society, ACM, and SIAM.