Parallel Computing on Arrays with Reconfigurable Optical Buses -------------------------------------------------------------- Yi Pan, University of Cincinnati Abstract -------- Fiber optic communications offer a combination of high bandwidth, low error probability, and gigabit transmission capacity and have been used extensively in wide-area networks. Advances in optical and optoelectronic technologies indicates that they could also be used as interconnects in parallel computers. Based on the characteristics of an optical bus and results obtained on arrays with reconfigurable electronic buses, we recently proposed a new computational model called linear array with a reconfigurable pipelined bus system (LARPBS). In the LARPBS model, messages can be transmitted concurrently on a pipelined optical bus without partitioning the bus into several segments, while the time delay between the furthest processors is only the end-to-end propagation delay of light over a waveguided bus. On the other hand, a bus can also be dynamically segmented into several subsystems, and each subsystem can perform operations independently. Hence, many divide-and-conquer algorithms fit naturally into this model. In this talk, the main features of the LARPBS model and several basic data movement operations on the model will be described. These operations include broadcast, multicast, compression, split, binary prefix sum, quicksort, integer sort, and maximum finding. We show that all the algorithms can be executed efficiently on the LARPBS model. The scalability issue of the model will also be discussed. It is our hope that the LARPBS model can be used as a new and practical parallel computational model for designing parallel algorithms. ----------------------------------------------------------------- ----------------------------------------------------------------- Yi Pan was born in Jiangsu, China. He entered Tsinghua University in March 1978 with the highest college entrance examination score among all 1977 high school graduates in Jiangsu Province. He received his B.Eng. degree in computer engineering from Tsinghua University, China, in 1982, and his Ph.D. degree in computer science from the University of Pittsburgh, USA, in 1991. Dr. Pan joined the Department of Computer Science at the University of Dayton, Ohio, USA, in 1991 and has been an associate professor since 1996. His research interests include parallel algorithms and architectures, optical communication and computing, distributed computing, task scheduling, and networking. He has published more than 50 papers in international journals and conference proceedings. He has received several awards including NSF Research Opportunity Award, AFOSR Summer Faculty Fellowship, Andrew Mellon Fellowship from Mellon Foundation, the best paper award from PDPTA '96, and Summer Research Fellowship from the Research Council of the University of Dayton. His research has been supported by NSF, AFOSR, U.S. Air Force, and the state of Ohio. Dr. Pan is currently on the editorial board of the Journal of Parallel and Distributed Computing Practices and is an associate editor of the International Journal of Parallel and Distributed Systems and Networks. He has served as a guest editor of special issues for four international journals: Information Sciences, Parallel Processing Letters, Informatica, and International Journal of Parallel and Distributed Systems and Networks. He will be the program chair of the tenth International Conference on Parallel and Distributed Computing and Systems and the conference co-chair of the Fourth International Conference on Computer Science & Informatics. He has also served as a session chair or a committee member for various international conferences. Dr. Pan is a senior member of IEEE and a member of the IEEE Computer Society. Currently, he is the Chairman of the IEEE Computer Society Student Activities Committee in Region 2 (Mideastern USA) and the Secretary of IEEE Computer Society Dayton Chapter. He is listed in Men of Achievement and Marquis Who's Who in Midwest. -----------------------------------------------------------