| Real-Time Visualization of Wake-Vortex Simulations using Computational Steering and Beowulf Clusters |
|---|
| Anirudh Modi - Institute for High Performance Computing Applications (IHPCA), Penn State University Lyle N. Long - Institute for High Performance Computing Applications (IHPCA), Penn State University Paul E. Plassmann - Institute for High Performance Computing Applications (IHPCA), Penn State University |
In this paper, we present the design and implementation of POSSE, a new, lightweight computational steering system based on a client/server programming model. We demonstrate the effectiveness of this software system by illustrating its use for a visualization client designed for a particularly demanding real-time application---wake-vortex simulations for multiple aircraft running on a parallel Beowulf cluster. We describe how POSSE is implemented as an object-oriented, class-based software library and illustrate its ease of use from the perspective of both the server and client codes. We discuss how POSSE handles the issue of data coherency of distributed data structures, data transfer between different hardware representations, and a number of other implementation issues. Finally, we consider how this approach could be used to augment AVOSS (an air traffic control system currently being developed by the FAA) to significantly increase airport utilization while reducing the risks of accidents. |