Class papers become prize winners for supercomputer-building Purdue students

August 13, 2008

For two students in Jeffrey Evans’ high-performance computing class at Purdue, homework turned out to have an unintentional, and lucrative, benefit.

Andy Howard and Alex Younts, both of West Lafayette, Ind., walked away with the top student prize for a paper they presented at the Linux Cluster Institute (LCI) conference April 29 to May 1 at the National Center for Supercomputing Applications in Urbana, Ill. They won the best student paper award, and a $600 prize.

“We weren’t expecting that,” said Howard of the award from the premier international organization on building and managing supercomputing clusters running the open-source Linux operating system. “We were pretty excited.”

Clustering, the way supercomputers predominantly are built now, involves linking basically off-the-shelf computers with powerful processors -- the kind found on a lot of desktops and in a lot of laps these days -- to work in concert on big tasks from studying the behavior of thousands of molecules in the body to studying millions of stars in the cosmos.

Howard and Younts, currently working for the Rosen Center for Advanced Computing at Purdue, were part of the Purdue SuperComputing 2007 Cluster Challenge team, which competed at SC07 in Reno, Nev., last fall. The conference is the international supercomputing community’s major annual gathering.

The students built their cluster in Purdue Professor Evans’ course from machines provided by partner HP. AMD and Matrix Integration also helped sponsor the project. The class is normally graduate level but was opened to undergraduates on the team, said Evans, an assistant professor in the Department of Electrical and Computer Engineering Technology.

Among the challenges presented by the competition rules: the student-built clusters had to run a variety of benchmarking and working applications as optimally as possible. The programs stressed features ranging from memory handling to the speed at which data moves through the pipeline. Team members became the resident expert for an application, in essence, and did a paper about it for class.

Purdue junior Howard, for example, concentrated on Parallel Ocean Program, a simulator covering factors in the behavior and health of the oceans, which weighs into studies of global warming and climate change. Younts worked with POV-Ray, a heavyweight 3-D graphics and animation creation program, the kind of thing used to create the special effects magic in summer blockbuster movies.

Evans encouraged Howard and Younts to combine their class papers into a presentation for the Linux Cluster Institute conference this spring. They used their experience with specific programs to discuss building and operating a cluster in general. Younts presented the paper.

“There were several graduate students there with different papers on various topics,” said Younts, a Purdue sophomore who actually started working for the Rosen Center in high school. “But I guess everyone liked our presentation best.”

Originally posted: August 13, 2008