Zhiling Lan, associate professor of computer science, has recently been awarded a research grant of $498,800 from the National Science Foundation (NSF) Division of Computer and Communication Foundations (CCF) to support her research proposal entitled “Toward Smart HPC through Active Learning and Intelligent Scheduling” (August 15, 2014 – August 14, 2017). This three-year award was competitively awarded through NSF’s merit-review process and is supported by the NSF CCF Core program.
Being analogous to smart grids, this project aims to develop critical technologies toward smart supercomputing by incorporating intelligence into resource management and job scheduling. Specifically, it will develop a framework named SPEaR (Scheduling for Performance, Energy, and Resilience efficiency) for dynamically optimizing the three-dimensional performance, energy, and resilience scheduling. The research focuses on two thrusts. One is active learning to automatically extract valuable performance, energy, and resilience patterns and tradeoffs out of application and system data; the other is intelligent scheduling to adaptively control performance, resilience, and energy efficiency in resource management and scheduling. Completion of the project will make important advances toward efficient use of extreme scale systems. The close partnership with national laboratories and application scientists will enable the integration of this work into broader programs and activities of national interests.