Harvard Named CUDA Center of Excellence
Harvard University has been named a CUDA Center of Excellence by Nvidia for teaching GPU computing and for integrating CUDA-enabled GPUs into research projects. The university last year received a $2 million grant from the National Science Foundation for developing GPU technologies for scientific computing.
CUDA is a suite of tools, including a C-compiler and SDK, for developing multi-core and parallel processing applications on Nvidia's GPUs. Forty-one universities are currently using CUDA for multi-core and parallel processing programming, which is about double the number of universities that were using it seven months ago.
Harvard is using GPUs in areas as diverse as exploring quantum chemistry, studying the human brain, and taking a whack at discovering the origins of the universe. It's also including the CUDA architecture in courses and in collaborative research projects conducted with Boston University faculty.
"With interest in the CUDA architecture spreading rapidly across the Harvard campus and the lively scientific landscape in Boston, there has never been a better time to announce this partnership," said Hanspeter Pfister, Gordon McKay Professor of the Practice of Computer Science in Harvard's School of Engineering and Applied Sciences and director of visual computing at the Initiative in Innovative Computing at Harvard, in a prepared statement. "This generous gift from NVIDIA will provide excellent learning opportunities for Harvard students, accelerate our research and expand the use of GPUs for computing in science and other advanced applications."
Universities that wish to become CUDA Centers of Excellence include CUDA technologies in their research efforts and teach at least one course in CUDA. Those institutions that are accepted as CUDA Centers of Excellence receive funding, equipment donations, and support for setting up a GPU computing cluster.
Further information on CUDA can be found here.