Rich Vuduc (CSE) has received an NSF CAREER Award for his work in tuning software to run on parallel systems.

Software engineers long have "tuned" existing programs to run on more parallel systems, but the work is laborious and very time consuming. Vuduc, assistant professor in the School of Computational Science and Engineering, develops ways to perform this work automatically, hence "autotuning." He received the CAREER award for his proposal, "Autotuning Foundations for Exascale Systems."

"The major research goal is to study the major parallel programming and performance tuning problems that arise on these very large systems, which are projected to have many millions of processing cores," Vuduc said. "We hope to discover new techniques for overcoming these problems, and plan to work on them with collaborators at Intel, among other places."

To learn more about Vuduc's proposal or read the full abstract, visit the NSF website.