Modern GPUs are massively parallel, many-core processors. The growing performance difference between parallel and sequential execution is motivating an increasing number of developers port their applications for GPU computing. Through teaching parallel programming and working on domain application libraries, we have identified eight major fundamental algorithm patterns, or classes of techniques, for efficient many-core computation. These patterns allow programmers to systematize their efforts in developing highly scalable parallel applications. They also provide a framework for developing high-value programming tools for many-core systems. In this talk, I will describe the current collection of eight major algorithm patterns and comment on their practice use in the Parboil 2 benchmarks.

Bio:

Wen-mei W. Hwu is a Professor and holds the Sanders-AMD Endowed Chair in the Department of Electrical and Computer Engineering, University of Illinois at Urbana-Champaign. His research interests are in the area of architecture, implementation, and software for high performance computer systems. He is the director of the IMPACT research group (www.crhc.uiuc.edu/Impact). For his contributions in research and teaching, he received the ACM SigArch Maurice Wilkes Award, the ACM Grace Murray Hopper Award, and ISCA Most Influential Paper Award. He is a fellow of IEEE and ACM. He leads the GSRC Concurrent Systems Theme. He is the director of the CUDA Center of Excellence at the University of Illinois. He also co-directs the new $18M UIUC Intel/Microsoft Universal Parallel Computing Research Center with Marc Snir and serves as one of the principal investigators of the $208M NSF Blue Waters Petascale computer project. Dr. Hwu received his Ph.D. degree in Computer Science from the University of California, Berkeley.

Webinar Details:

This meeting has expired. Below are the online resources available from this session:

• PDF
• Video
• Forum

______________________________________________________________________________________________________________________

To receive notifications of future GPU Computing Research Forum meetings, join gpucomputing.net and specifically the GPU Computing Research Forum community.