The continuing decline of conventional fossil fuel has resulted in increasing energy costs all around the world. Meanwhile, fossil fuel-induced greenhouse gas emissions have profound implications for our environment. Renewable energy is generated from natural resources that are naturally replenished. Photovoltaic (PV) generation is gaining increased popularity due to its advantages such as absence of fuel cost, low maintenance, and no noise and wear due to the absence of moving parts. Designing renewable energy driven computer systems poses various challenges in terms of intelligent control strategies for better energy utilization, optimizations for reducing overhead and improving reliability. The proposed research will develop novel enabling technologies for high-performance computer architectures (e.g. multi-core CPU/GPU) that can achieve high efficiency and dependability in utilizing renewable energy. The research goal includes GPU power management schemes that can maximize a solar panel?s total energy output using load-matching and intelligently allocate the available solar power across multiple cores and threads so that maximum workload performance can be achieved. The proposed research project can greatly contribute to enabling high-performance computing systems to stay on track with its historic scaling and hence benefit numerous real-life applications. This project also contributes to society through engaging under-represented groups, research infrastructure dissemination for education and training, and outreach to renewable energy industries and research community.

Project Report

The continuing decline of conventional fossil fuel has resulted in increasing energy costs all around the world. Meanwhile, fossil fuel-induced greenhouse gas emissions have profound implications for our environment. Renewable energy is generated from natural resources that are naturally replenished. Photovoltaic (PV) generation is gaining increased popularity due to its advantages such as absence of fuel cost, low maintenance, and no noise and wear-out due to the absence of moving parts. Designing renewable energy driven computer systems poses various challenges in terms of intelligent control strategies for better energy utilization, optimizations for reducing overhead and improving reliability. The objective of this project is to develop novel enabling technologies for high-performance computer architectures (e.g. multi-core CPU/GPU) and systems (e.g. HPC servers) that can achieve high efficiency and dependability in utilizing renewable energy. This research project has produced 12 conference (IGCC-2014, MASCOTS (a, b)-2014, ICAC-2014, MICRO-2013, ISLPED-2013, RTCAS-2013, HPCA-2013, ISCA-2012, IISWC-2011, SIGMETRICS-2011, HPCA-2011 (Best Paper Award)) and 2 journal (CAL-2014, JCST-2014) publications. The graduated students have traveled to the topic conferences to present their work to the research community. Two Ph.D. students have participated into this project and have successfully defended their dissertation/thesis based on this research. A high school student also participated in this research project. An undergraduate student was also involved. The overall goal of this project is to enable high-performance computing systems to stay on track with its historic scaling and hence benefit numerous real-life applications. In addition, it aims at contributing to society through engaging under-represented groups, research infrastructure dissemination for education and training, and outreach to renewable energy industries and research community.

Agency
National Science Foundation (NSF)
Institute
Division of Computer and Network Systems (CNS)
Type
Standard Grant (Standard)
Application #
1117261
Program Officer
M. Mimi McClure
Project Start
Project End
Budget Start
2011-08-15
Budget End
2014-07-31
Support Year
Fiscal Year
2011
Total Cost
$200,000
Indirect Cost
Name
University of Florida
Department
Type
DUNS #
City
Gainesville
State
FL
Country
United States
Zip Code
32611