Date: 21 December 2005 Time: 15:00 - 16:30
Location: Mediterranean Studies Seminar Room - FORTH
Host: Angelos Bilas
High compute density is a recently coined term, used to characterize minimally packaged compute nodes, which integrate several multicore/multithreaded processors and the associated networking and storage components, while occupying no more than one rack unit.
In the first part of this talk I will present challenges and open problems for system software on high compute density systems, with respect to performance, power dissipation, and reliability. I will also motivate the use of multithreading as a unified methodology for exploiting granular parallelism, reducing energy consumption under performance guarantees, and providing adaptive fault tolerance on dense systems.
In the second part of the talk I will present ongoing research in runtime environments for dense systems and focus on two topics, polymorphic multithreading, and power-aware thread-level granularity control. Polymorphic multithreading integrates multiple forms of non-speculative and speculative multithreaded execution in the same binary. Integration happens at runtime, in response to live phase analysis and performance analysis performed by a continuous hardware monitor. Power-aware thread granularity control uses the same continuous monitoring substrate for online phase, timing, and power analysis, to trigger power optimizations under performance guarantees specified by the user and/or the runtime system. I will demonstrate that the aforementioned live optimizations of the multithreaded execution environment achieve performance improvements and, simultaneously, substantial energy savings, using a multi-SMT system as a case study.
Dimitris Nikolopoulos is an Assistant Professor of Computer Science at the College of William and Mary. Before joining W&M he was a Visiting Assistant Professor of the Department of Electrical and Computer Engineering and a Visiting Research Assistant Professor of the Coordinated Science Laboratory at the University of Illinois in Urbana-Champaign. His research interests include programming environments and runtime support for emerging parallel architectures, autonomic computing systems, operating systems, and memory hierarchies. Dr. Nikolopoulos is a recipient of two early faculty development CAREER awards from the National Science Foundation (2004) and the United States Department of Energy (2005), and five best paper awards from leading conferences on supercomputing and parallel computing technologies. He received his Diploma of Engineering in 1996 and his Doctorate degree in 2000, both from the Department of Computer Engineering and Informatics at the University of Patras.