Time:10:00 ,DECEMBER 13th
Place: Room 446, 4th Floor, ICT, CAS
Speaker: Prof. Frank Mueller, North Carolina University
Performance modelling for scientific applications is an important task for assessing potential performance bottlenecks and assist in hardware procurement for HPC systems. Recent progress on communication tracing provides novel opportunities for communication modelling. We contribute a fundamentally novel approach. By extrapolating communication traces and execution time of a parallel application, a set of traces for smaller number of nodes provides the base to synthetically generate a trace for larger number of nodes. The extrapolated larger trace can subsequently be replayed to empirically detect scalability problems or analyzed to detect communication patterns or determine constraints on scalability, which is without precedence.
Frank Mueller is a Professor in Computer Science and a member of multiple research centers at North Carolina State University. Previously, he held positions at Lawrence Livermore National Laboratory and Humboldt University Berlin, Germany. He received his Ph.D. from Florida State University in 1994. He has published papers in the areas of parallel and distributed systems, embedded and real-time systems and compilers. He is a member of ACM SIGPLAN, ACM SIGBED and a senior member of the ACM and IEEE Computer Societies. He is a recipient of an NSF Career Award, an IBM Faculty Award, a Google Research Award and a Fellowship from the Humboldt Foundation. His current research interests include parallel and distributed systems, GPU computing, embedded and real-time systems and compilers.