Parallel and Distributed Computing Systems (ISCA) 

Abstract: This paper addresses the application of distributed constraint optimization problems (DCOPs) to large-scale dynamic environments. We introduce a decomposition of DCOP into a graphical game and investigate the evolution of various stochastic and deterministic algorithms. We also develop techniques that allow for coordinated negotiation while maintaining distributed control of variables. We prove monotonicity properties of certain approaches and detail arguments about equilibrium sets that offer insight into the tradeoffs involved in leveraging efficiency and solution quality. The algorithms and ideas were tested and illustrated on several graph coloring domains.

Abstract: A promising anti-spam technique consists in collecting users opinions that given email messages are spam and using this collective judgment to block message propagation to other users. To be effective, this strategy requires a way to identify similarity among email messages, even if the program used by the spammer to generate the messages may try to obfuscate their common origin. In this paper, we investigate the issues arising in the design of a digest-based spam detection mechanism, which has to satisfy many conflicting requirements: protect message confidentiality, be public, and prove difficult or expensive to fool by obfuscation techniques that automatically introduce differences into the same base spam message. We show that an open digest function is able to satisfy the above requirements and contribute to the fight against spam.

Abstract: Clustering of data has numerous applications and has been studied extensively. Though most of the algorithms in the literature are sequential, many parallel algorithms have also been designed. In this paper, we present parallel algorithms with better performance than known algorithms. We consider algorithms that work well in the worst case as well as algorithms with good expected performance.

Abstract: Hyperthreaded (HT) and simultaneous multithreaded (SMT) processors are now available in commodity workstations and servers. This technology is designed to increase throughput by executing multiple concurrent threads on a single physical processor. These multiple threads share the processor’s functional units and on-chip memory hierarchy in an attempt to make better use of idle resources. This work focuses on tuning the behavior of OpenMP applications executing on SMPs with SMT processors. We propose a self-tuning OpenMP loop scheduler designed to react to behavior caused by inter-thread data locality, instruction mix and SMT-related load imbalance. This adaptive loop scheduler automatically selects the number of threads that should be used for each parallel loop and a good scheduling policy for the iterations. It is shown that this scheduler outperforms all other OpenMP schedulers, and because it can dynamically select the number of threads to use for each region, it even outperforms the best combination of runtime schedulers for any fixed number of threads.