Coordination and synchronization in networked collaborative environments and system services in multiprocessor systems
|Ομιλήτρια||Μαρίνα Παπατριανταφύλλου, Chalmers University of Technology, Sweden|
|Τίτλος||Coordination and synchronization in networked collaborative environments and system services in multiprocessor systems|
|Ημερομηνία||Πέμπτη 03/11/2005, ώρα 13:00|
|Χώρος||Αμφιθέατρο Σαράτση, στο Κτίριο Δελμούζου, Παραλιακό Συγκρότημα Παπαστράτου|
|Διεύθυνση||Αργοναυτών και Φιλελλήνων, Βόλος|
The first part of the talk will be on our recent research efforts and results on multi-peer information-dissemination and consistency support for networked collaborative environments and distributed objects suitable for such environments, together with efficient data structures and algorithms for their realization. Application domains which are of interest include telecommunication systems and distributed infrastructures for collaborative activities, such as distributed monitoring and steering systems, interactive collaborative environments for training and entertainment, and more. The second part of the talk will be on lock-free memory allocation in multiprocessor systems. The motivation fpr this work relies on the observation that the potential of multiprocessor systems is frequently not fully realized by their system services. Certain synchronization methods, such as lock-based ones, may limit the parallelism. It is significant to see the impact of wait/lock-free synchronization design in key services for multiprocessor systems, such as the memory allocation service. Efficient, scalable memory allocators for multithreaded applications in multiprocessor systems is a significant goal of recent research projects. We proposed a lock-free memory allocator, to enhance the parallelism in the system. Its architecture is inspired by Hoard, a successful concurrent memory allocator, with a modular, scalable design that preserves scalability and helps avoiding false sharing and heap blowup. Within our effort on designing appropriate lock-free algorithms for the synchronization in this system, we propose a new non-blocking data structure called flat-sets, supporting conventional “internal” operations as well as “inter-object” operations, for moving elements between flat-sets. In both parts we will also see results from our implementations of the presented algorithms and protocols on actual network and multiprocessor systems.