AGENDA

Programming Cloud Computers with High Level Abstractions

Doug Thain, Shantenu Jha

Abstract: For many years, brave users have programmed distributed systems in an assembly language that consists of batch jobs and file transfers. For workloads of any significant size, this is a time consuming and error prone method. Instead, we propose that users should employ "abstractions", which are constrained but optimized frameworks that allow users to easily scale problems to very large sizes. In this talk, I will present several examples of abstractions we have developed at the University of Notre Dame, along with applications in biometrics and data mining.

Bio: Douglas Thain is an Assistant Professor in Computer Science and Engineering at the University of Notre Dame, where he conducts research on large distributed systems such as grids and clouds. He received a BS in physics from the University of Minnesota, and then the PhD in computer sciences at the University of Wisconsin, where he contributed to the Condor distributred processing system. He received an NSF CAREER award in 2006.