In-Network Coherence Techniques for Scalable Shared Memory
Speaker: Niket Agarwal
Series: Final Public Orals
Location: Engineering Quadrangle J401
Date/Time: Friday, May 13, 2011, 9:00 a.m. - 11:00 a.m.
Moore's law has led to rapid advancements in the field of computing. However, programming parallel architectures as well as mobile devices is still not easy. My dissertation seeks to address the parallel programming challenge existing in the domain of multi-core systems, and the distributed programming problem associated with mobile ad-hoc networks. Specifically, it looks at providing scalable shared memory for both parallel and distributed mobile computing. My dissertation takes an in-network approach to address the many-core cache coherence problem and develops a programming abstraction layer, that provides consistent shared memory objects to mobile devices.