题目: Opportunities for Desktop Grids to move to Clouds and IoT

时间:2015年5月12日上午9:00

地点:东五楼210

Abstract: In this presentation we introduce the core areas of researches between CNIC Beijing / Wuhan and France (P13 & INRIA) on distributed systems. The key and historical architecture is the Desktop Grid architecture pushed by the Bitdew and BonjourGrid systems. We also call such architecture Volunteer computing, introduced about 15 years ago and we show how this architecture and the underlying middleware have evolved over time. From our side, during the past decade, we have worked on the management of data as well as the level of decentralization of such architecture. In our context, decentralization means that computing elements may appear on demand, each deploying a specific master-slave environment, all the elements are coordinated by an interaction protocol. We also underline why the volunteer computing paradigm is useful in the Cloud context, and soon in the Internet of Things context. We show some examples of our work related to workflow management that users can deploy on demand on the SlapOS cloud.

Bio: Christophe Cérin has been a professor of computer science at the University of Paris 13, France since 2005. This year, he initiated an infrastructure project related to big data and high performance computing for e-sciences for USPC (Université Sorbonne Paris Cité). At Paris13, he chairs the board for the cluster computing facility available to all campus scientists and also chairs the 'Expert Committee' in charge of recruiting and mentoring full time junior and senior professors in computer science. His industrial experience includes serving as local chair for the Wendelin project (Gaz de France, Mitsubishi, INRIA, Telecom ParisTech, Paris 13) related to Cloud and Big-Data. His previous industrial project was the Resilience project (Nexedi, Morpho, Alixen, Vifib — French SMEs) related to Cloud Computing where he was the local chair. His research focuses on High Performance Computing, including Grid Computing and he develops middleware, algorithms, tools and methods for distributed systems.