irdtop.gif (3124 bytes)

Support Request for Computational Science and Engineering Transitional Activities, 15-9069

Printer Friendly Version

Principal Investigators
Ernest A. Franke
Christopher J. Freitas
Richard L. Murphy
J. David Winningham

Inclusive Dates: 01/08/98 - Current

Background - Distributed parallel computing has become the dominant approach to solving complex scientific and engineering problems. The introduction of more advanced central processing units to the marketplace will further improve the price/performance ratio, making a network of workstations (NOWs) a truly affordable supercomputer. Clearly, advanced computational and data visualization techniques are vital to research at the Institute. Fortunately, distributed parallel processing provides affordable computing and effective visualization. This project is the first step toward providing Institute-wide resources and a cadre of trained staff members prepared to create more cost-effective modeling, data mining, and simulation solutions for SwRI clients.

Approach - SwRI senior management recognized the importance of computation science and engineering as a discipline fundamental to many Institute activities and funded the creation of a four-node, high-speed network in 1996. This network was based on first-generation asynchronous transfer mode (ATM) technology and provided valuable experience with a heterogeneous set of workstations. Subsequently, funding was provided to greatly expand the ATM network and the number of workstations (37) supported. This expansion includes a new ATM switch for Building 139. The three general targets of this program can be summarized as documentation, education, and facilitation. The program activities are classified as follows:

Facilitation

  • Establish a uniform Parallel Virtual Machine (PVM) base across all clustered workstations
  • Compile a comprehensive library of Computational Science and Engineering (CSE) software tools
  • Construct a CSE intranet web server to provide the most current documentation to the Institute staff
  • Import or develop computing resource management tools
  • Produce a promotional brochure for use by any cost code center
  • Support the design of an advanced high-performance computer network within the Institute
  • Seek external funding for both high-performance networking and CSE research programs

Education

  • Begin a training program for Institute staff

Documentation

  • Document the ATM network and workstation configuration
  • Examine the technological trends shaping SwRI’s CSE infrastructure and write a white paper projecting future directions
  • Create and document a method for integrating CSE support into projects
  • Specify standards for the future expansion of distributed parallel computing and advanced visualization for project support and competitiveness

Accomplishments - This project has operated for seven quarters, including a one-year, no-cost extension. A synopsis of activities touches upon all the targeted areas and includes other activities derived from this project. The high-performance network infrastructure at SwRI continues to expand, partially due to the stimulus of this program. The need to add or maintain computers connected to the Distributed Computing Facility (DCF) has led to additional ATM switches being deployed in the Mechanical and Materials Engineering Division. More than 30 workstations can now participate as computing or visualization nodes within the DCF, although not all are available at one time.

The on-line documentation of the network of workstations (NOW) is available on the Institute intranet (I2Net) http://moe.space.swri.edu/CSE/. An extended course called Introduction to Distributed Parallel Computing will be offered through the Staff Development Office. This course consists of five weeks of lectures on PVM, network technologies, and techniques for writing parallel applications.

Software tools to manage DCF resources grow in importance as the DCF itself expands. The Resource Finder tool has evolved into an extendable application and points out the need for an entire suite of management tools. Because each workstation participating in the DCF is under independent administration, the availability of particular resources fluctuates. Users need an easy way to adapt available resources to their needs.

Intelligent Systems, Advanced Computer and
Electronic Technology, and Automation Program
1999 IR&D Home SwRI Home