New Orleans, Louisiana
June 26, 2016
June 26, 2016
August 28, 2016
Engineering Physics & Physics
Computational skills are foundational in engineering physics education. Computational exercises, labs, and projects often employ instructive small-scale problems. These small- scale problems serve to introduce content and process, and as such, serve the purpose for which they were intended. Small-scale problems do not serve to introduce students to solving problems at industrial-scale or with research-quality as required in the workplace or graduate laboratory This paper describes the integration of industrial-scale and research-quality high-performance computing (HPC) into a senior/graduate level fluid dynamics course.
This paper focuses on a combined senior level-graduate level course (enrollment of 12) in fluid dynamics at the U__, a predominantly undergraduate institution (PUI) . A HPC cluster, B___ has been deployed recently at the U__. The first author operates and administers the B__ cluster and serves as instructor of the fluid dynamics course, providing an opportunity to advance the course outcomes to include a high impact project that takes advantage of distributed computing. These projects will be transformative for the students and expose them to HPC “at scale.” The projects require the use of computational fluid dynamics (CFD) on a HPC system; intentionally exposing students to a new way of doing things. The issues that students must confront include: 1) complex geometric modeling that result in very large file sizes, 2) meshing geometries that are large or require many nodes, 3) transitioning files generated on a desktop computer to a HPC environment, 4) understanding navigation and use of an HPC system, 5) understanding the use of parallelism in a distributed computing environment, 6) quantifying results, and 7) visualizing results.
The goal of this work is to impact the student’s long term ability to deal with computationally intensive problems. Although we cannot determine the impact long term yet, we are using a rubric to gauge the immediate impact and surveying the students to determine their perceptions.
Lemley, E. C., & Gillispie, A. M., & Dorety, A., & Meier, A., & Riahinezhad, S. (2016, June), Integration of High Performance Computing into Engineering Physics Education Paper presented at 2016 ASEE Annual Conference & Exposition, New Orleans, Louisiana. 10.18260/p.25426
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2016 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015