COLLOQUIUM Department of Computer Science and Engineering University of South Carolina High Performance Cluster Modeling and Development Amy Apon Department of Computer Science and Engineering University of Arkansas Date: October 11, 2010 (Monday) Time: 1400-1530 (2-3:30pm) Place: Swearingen 1A03 (Faculty Lounge) Abstract The talk begins with a short overview of the science and engineering of high performance cluster computing and areas of research of Dr. Apon. Two areas of current investigation with her students and collaborators are covered in more detail, including the GIRAF project, and research in the area of cache contention and VM placement in multicore systems. The GIRAF (Robust Geospatial Image Registration and Alignment with Features) project addresses the problem of massive new volumes of high resolution image data. The system being developed will handle large amounts of data from disparate sources and autonomously process and register new data against existing data. The problem motivates investigation in several interesting computer science and computer engineering areas, including parallel implementation of the algorithms on hybrid platforms, algorithm development for multimode matching, and management of very large scale image repositories. Research in the area of cluster node architecture examines the effects of multi-core cache structure on applications running inside Xen virtual machines. Results show that performance is significantly impacted by a good or poor placement of VMs on multi-core systems. These results have implications for cloud computing environments that utilize VMs, and provide insight for a new model of shared cache architectures based on a natural competition model from ecology. Amy Apon is a Professor of Computer Science and Computer Engineering at the University of Arkansas. She holds a Ph.D. from Vanderbilt University in performance analysis of parallel and distributed systems. Her current research focuses on high performance cluster computing, including scheduling in cluster systems, management of large-scale data-intensive applications, and accelerator architectures. Apon has more than 70 peer-reviewed publications, and is PI or co-PI on more than $10M of external research funding. She is the Principal Investigator of the four National Science Foundation grants that have acquired the shared supercomputer resources at the University of Arkansas. She has directed high performance computing activities at the University of Arkansas since 2004.