Please use this identifier to cite or link to this item:
https://hdl.handle.net/11681/10819| Title: | Interactive computational steering in distributed, heterogeneous high performance computing environments |
| Authors: | Carrillo, Alejandro R. West, John E. |
| Keywords: | Discrete element method DEM Interactive simulation Distributed visualization Ray casting High-performance computing Soil dynamics Soil mechanics Mathematical models Numerical models |
| Publisher: | Information Technology Laboratory (U.S.) Engineer Research and Development Center (U.S.) |
| Series/Report no.: | Technical report (U.S. Army Engineer Waterways Experiment Station) ; ITL-98-2. |
| Description: | Technical Report Abstract: The ability to visually interact with and guide a running simulation can greatly enhance understanding of both the nature of a numerical model and the characteristics of the underlying physical process. Until recently, interaction with large-scale simulations was inhibited not only by computational limitations, but by network and graphics capabilities as well. However, the increasing power of large high performance computing (HPC) systems, coupled with the advent of new network hardware and innovative techniques for displaying large data sets, has eliminated many of the barriers. It is now possible to link large computational resources with powerful remote graphics workstations to create fully interactive, distributed applications. This report discusses the development of a distributed, interactive modeling system capable of providing responsive visual feedback to user input The system is built around a discrete element soil model being used to simulate the behavior of soil masses under large deformations. During the process of designing this system to be interactively responsive to the user for systems of several hundred thousand particles, a range of technical problems were encountered, including the computational burden of the discrete element method (DEM), real-time visualization of large particle masses, and communication of data over large distances between heterogeneous resources using a variety of networks. This report highlights how each of those obstacles was addressed and discusses the effectiveness of the final system. |
| Rights: | Approved for public release; distribution is unlimited. |
| URI: | http://hdl.handle.net/11681/10819 |
| Appears in Collections: | Technical Report |
