Mary Hall, associate professor in the School of Computing, is designing computer program tools for high-end systems and supercomputers. Her project for the U.S. Department of Energy (DOE) uses her skills for developing compiler technology (computer programs that translate source code from one computer language into another computer language) for DOE application programmers to build their own software for faster, better computing. “We work with application scientists to develop software applications with our own eye to the way we view things,” says Hall, who joined the U of U last fall from ihe University of Southern California.
The DOE uses the software tools for projects such as climate modeling or studying nuclear fusion. “The DOE is seeking the best performance for their high-end supercomputers,” says Hall. “Because they do large-scale simulations, they are always looking for faster, better, more precise tools.” Hall is also teaching a new class in the School of Computing, called Parallel Programming for GPUs (graphics processing units), that involves training students from across campus to use special-purpose hardware originally designed for graphics and games to solve general-purpose computing problems. The technology for the class was donated by the organization NVIDEA, inventor of the GPU, who recently named the University of Utah as a Compute Unified Device Architechure (CUDA) Center of Excellence.