High Performance Computing School Set for September

I'm interested in attending

August 20, 2008

A two-day high performance computing workshop for graduate students, postdocs, faculty and other interested researchers from on and off campus will be offered in September with support from five high-tech organizations at Purdue.

The Purdue School on High Performance Parallel Scientific Computing will take place Sept. 4 and 5 at the Burton D. Morgan Center for Entrepreneurship in Purdue’s Discovery Park, 1201 West State St., West Lafayette, IN, 47907-2057, and the Information Technology at Purdue (ITaP) computer lab in the Engineering Administration Building, 400 Centennial Mall Drive, West Lafayette, IN, 47907-2016.

The event is cosponsored by the Rosen Center for Advanced Computing, ITaP’s research and discovery computing arm, the Computing Research Institute, the Center for the Prediction of Reliability, Integrity and Survivability of Microdevices (PRISM), the Network for Computational Nanotechnology (NCN), and the Computational Science and Engineering Program.

For more information and to register, visit www.cri.purdue.edu/workshops.cfm.

Thursday morning’s session will present participants with a big-picture overview of what can be achieved with high performance computing. It features internationally recognized leaders in the field, said Faisal Saied, a senior research scientist at the Rosen Center, who’s leading the organization of the school with Purdue Professor Alejandro Strachan.

Strachan, assistant professor of materials engineering, said the session is designed to give participants “a glimpse of what is the state of the art today.”

Invited speakers include Steve Plimpton of Sandia National Laboratories, known for his work with the widely used LAMMPS molecular dynamics simulation software, and Andrew Lumsdaine of Indiana University, a parallel programming researcher who’s developed the open source message passing interface Open MPI, a system that allows many computer processors to communicate with each other and work in concert.

Other speakers will be Blaise Barney, a senior high performance computing researcher at Lawrence Livermore National Laboratory; Purdue mechanical engineering Professor Steve Frankel, an expert in computational fluid dynamics; and Purdue computer science Professor Ananth Grama, whose research focuses on parallel and distributed computing. Parallel computing parcels problems over more than one processor—thousands of which can be available in high performance computing—to solve bigger problems faster, from tricks viruses use to invade cells to secrets of the origins of the universe.

Thursday afternoon and Friday, school participants will get hands-on experience working with high performance computing hardware and software, Saied and Strachan said.

“That part will be (taught) primarily by Rosen Center staff,” Saied said. “Thursday afternoon and Friday are real how-to.”

Strachan said the school has a slightly different focus than previous Rosen Center high performance computing workshops. He said the September session is geared in particular to getting Purdue graduate students and post-doctoral researchers ready to work for the PRISM center and other research operations at Purdue as the school year begins, with an emphasis on making efficient use of high performance computing resources.

Strachan said most of the presentations will be recorded and made available on nanoHUB, www.nanohub.org.

The Rosen Center for Advanced Computing (RCAC) is the discovery and research arm of Information Technology at Purdue (ITaP). RCAC supplies high performance computing systems and storage—reliably and securely—for measured and computed data to faculty and staff doing computationally intensive cutting-edge science, engineering, and social science research.

The Center for Prediction of Reliability, Integrity and Survivability of Microsystems at Purdue, or PRISM, funded by the National Nuclear Security Administration, focuses on the behavior and reliability of microelectromechanical systems (MEMS), particularly miniature switches, developing advanced simulations for defense and commercial purposes.

The Network for Computational Nanotechnology uses advanced theory and simulations to explore new ideas for nanoscale devices, such as innovative types of transistors, that promise to help create future electronics. It operates nanoHUB, a Web-based toolbox and community for nanotechnology research.

The Computing Research Institute facilitates research in high performance computing at Purdue developing technology that realizes computational simulations to predict climate change, design new drugs, and explore the building blocks of matter, among many other things.

The Computational Science and Engineering Program is an interdisciplinary graduate program offering specializations in computational science and computational engineering for graduate students in the participating departments across the colleges of Science, Engineering, Pharmacy, Agriculture, Liberal Arts, and Technology. Specializations are offered at both master’s and doctoral levels.

Writer: Greg Kline. 765-494-8167, kline@purdue.edu.

Sources: Faisal Saied, 765-494-1583, fsaied@purdue.edu

Alejandro Strachan, 765-496-3551, strachan@purdue.edu

Originally posted: August 20, 2008