McMaster, NVIDIA establish teaching centre in Canada

McMaster University and NVIDIA, a developer of graphics processing units, have established the first NVIDIA CUDA Teaching Centre in Canada. The Centre, one of only 12 worldwide, will teach electrical and computer engineering students how to tap into the processing resources available in graphics processing units (GPU), and use them in computationally demanding applications.

CUDA is a parallel computing architecture that enables dramatic increases in computing performance for graphics, 3D content, video and other processing-intensive applications by harnessing the power of GPUs. GPUs can potentially increase processing speeds by a factor of 10 to 100 times at a very minimal cost. This opens up a wide array of opportunities in multimedia, such as making computer games more lifelike, advancing production of 3D television and movies, developing new medical imaging technologies and surgical tools, and creating large simulation environments, such as those used in designing cars.

"CUDA has the potential to revolutionize the way parallel processing is done, and create the next generation of high-performance multimedia applications and services," said David Capson, chair, Department of Electrical and Computer Engineering at McMaster. "It all hinges on having the expertise that can tap into the processing power and then apply it to other applications. The centre’s job is to develop that expertise and use that knowledge."

A Master’s level course in CUDA began in September. NVIDIA is providing McMaster with teaching materials, high-end graphics cards for six workstations, as well as funding to start up the program. It is being taught by Alexandru Patriciu, assistant professor of electrical and computer engineering, and the principal investigator behind the initiative at McMaster. 

"It’s new technology and quite complex, so we’re first offering the program at the Master’s level," said Patriciu. "But, within four or five years, we plan to offer courses in CUDA at the undergraduate level as well."

Richard Fanson, a Master’s student in electrical and computer engineering working with Professor Patriciu, has already been using CUDA to accelerate the simulation of his research involving deformable object assembly and automated tissue manipulation, with a variety of potential applications including textile manufacturing and breast biopsies.

"Simulations that previously would have taken an hour or two, I could accomplish in seconds," noted Fanson.