Bilkent University
Department of Computer Engineering


GPU Computing


Sanjay Ranka
Distinguished Professor and Chair
Computer and Information Science and Engineering
University of Florida
Gainesville, FL, USA

The Graphics Processing Unit is a parallel computing device known for its high throughput and relatively low cost. GPUs can be purchased for few hundred to a thousand dollars and can achieve a few teraflops of computing power. The throughput of GPUs can be attributed to their high degree of thread parallelism. Typically these threads are arranged into blocks that have to be executed using SIMD mechanism. The support for large numbers of threads allows memory access latencies to be masked, since other threads may operate while paused threads wait for IO operations to complete. The main challenges for achieving high performance on a GPU is that there is two to three orders of magnitude performance difference between local and global memory and that the overall bandwidth of the bus is limited.

We present our research on parallelization of data mining, signal processing and matrix multiplication that address the above issues to achieve high performance.

Bio: Sanjay Ranka is a Professor in the Department of Computer Information Science and Engineering at University of Florida. His current research interests are energy efficient computing, high performance computing, data mining and informatics. Most recently he was the Chief Technology Officer at Paramark where he developed real-time optimization software for optimizing marketing campaigns. Sanjay has also held positions as a tenured faculty positions at Syracuse University and as a researcher/visitor at IBM T.J. Watson Research Labs and Hitachi America Limited. Sanjay earned his Ph.D. (Computer Science) from the University of Minnesota and a B. Tech. in Computer Science from IIT, Kanpur, India. He has coauthored two books: Elements of Neural Networks (MIT Press) and Hypercube Algorithms (Springer Verlag), 200+ journal and refereed conference articles. His recent work has received a student best paper award at ACM-BCB 2010, best paper runner up award at KDD-2009, a nomination for the Robbins Prize for the best paper in journal of Physics in Medicine and Biology for 2008, and a best paper award at ICN 2007. He is a fellow of the IEEE and AAAS, and a member of IFIP Committee on System Modeling and Optimization. He is the associate Editor-in-Chief of the Journal of Parallel and Distributed Computing and an associate editor for IEEE Transactions on Parallel and Distributed Computing, Sustainable Computing: Systems and Informatics, Knowledge and Information Systems, and International Journal of Computing. He is co-general chair for 2011 International Conference on Green Computing and 2011 ACM Health Informatics Symposium.


DATE: 5 April, 2011, Tuesday @ 11:40