Paper Authors

Abstract

NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract

I .— - Session 1626 .. —-

-—. . . . . . . Curriculum Development in Advanced Computation* . Philip J. Morris, Lyle N. Long, Ali Haghighat, Martin L. Brady The Pennsylvania State University

Introduction For U.S. industry to remain competitive in the global market place it must update its approaches to product development. The concept of “concurrent engineering,” in which design and manufacturing procedures are integrated has been shown to lead to decreases in development time, engineering changes, and time to market and to increases in overall quality, productivity, dollar sales and return on assets [1]. Central to the reduced design cost are the use of numerical simulations. This is especially true in the aerospace field. Hoist et. al. [2] argue that the development costs for advanced vehicles are escalating ‘- due the constant desire in the commercial field for advancement in aerodynamic, fuel, and propulsion efficiency, weight reduction, flight stability and control, and environment al factors. One way to contain these costs is to place a greater emphasis on computer simulations. However, the simulation of the performance of complex aerospace vehicles is beyond current computing capabilities. This has resulted in the HPCC program: a multi-agency effort to advance the scientific computational capabilities of the U.S. by a factor of 1000 by the end of present decade. The achievement of “scaled teraFLOP performance” must rely on the use of massively parallel computer architecture. The U.S. is no longer the leader in vector computing. The Japanese have drawn even. The conversion of supercomputing from sequential/vector to parallel would be valuable as that is where the U.S. leads; however, the U.S. lead has been jeopardized by our failure to get large parallel machines and parallel software technology into the hands of users. Thus, the training of our university students in the capabilities and use of advanced parallel computers, is an essential component in the establishment of our industry’s competitive edge. In response to this need, faculty in the Colleges of Engineering, Science, and Earth and Mineral Sciences at the Pennsylvania State University have combined to develop a curriculum in advanced computation that emphasizes the capabilities and uses of parallel computers. The goal and method of approach can be summarized as:

Goal: - To train undergraduate and graduate students in advanced computation with an emphasis on the capabilities and uses of parallel computers.

Approach - Through the introduction of a sequence of courses at the senior and introductory graduate level in advanced computation; through the development of software demonstrations for classroom use; and through the use of high-technology classrooms and laboratories.

Course Development As an initial undertaking we have developed and taught three new lecture courses and have a offered a seminar series in high performance computing. The courses are described here. The course specification * %lpported by NSF Grant EEC-9420592

$iiia-’ > 1996 ASEE Annual Conference Proceedings ‘..qllllllc..’ .

• Citation

• Format
  • APA
  • APA - LaTeX bibitem
  • MLA
  • MLA - LaTeX bibitem
  • Bibtex
  • EndNote - RIS

Morris, P. J., & Brady, M. L., & Long, L. N., & Haghighat, A. (1996, June), Curriculum Development In Advanced Computation Paper presented at 1996 Annual Conference, Washington, District of Columbia. 10.18260/1-2--5954