Chao Li Department of Electrical and Computer Engineering University of Florida 327 Benton Hall, 946 Center Drive Gainesville, FL 32611 Email: chaol@ufl.edu Phone: +1 352-222-4889 Web: http://plaza.ufl.edu/chaol RESEARCH EDUCATION HONORS Data Center Ecosystem: Interaction among emerging workload, server architecture, and the next-generation cloud infrastructure Smart Power Management: Cooperative power optimization across multiple layers of computing stack and hardware components Green Computing Techniques: Power-aware workload scheduling and carbon-conscious high-performance data processing/hosting Architecture of Sustainable System: Design, implementation, and performance evaluation of green energy powered computing systems University of Florida, Gainesville, FL, August to Present Ph.D. Candidate in Computer Engineering Dissertation Project: Enabling Renewable Energy Powered Sustainable High-Performance Computing M.Sc. in Electrical and Computer Engineering, June Zhejiang University, Hangzhou, China, September 2005 to June B.E. (with highest honors) in Electrical Engineering, June 2007 2014 Chinese Government Award for Outstanding Students Abroad The most prestigious annual government award given by the China Scholarship Council Given to up to 500 outstanding Chinese oversea doctoral students across 29 countries Alec Courtelis Award Nominee Each college can nominate two international students for this award at the University of Florida Facebook Graduate Fellowship The only winner in computer architecture area in the -2014 Facebook Fellowship Program Yahoo! Key Scientific Challenges Program Award The only winner in green computing area in the Yahoo! Key Scientific Challenges Program ACM A.M. Turing Centenary Celebration Student Scholarship Attended a once-in-a-lifetime ceremony with 34 Turing Award winners participating in the event Only 7 students in the computer architecture area are selected by the ACM SIGARCH
2011 2010 2010 2008 2007 2006 2005 2004 2003 IEEE HPCA Best Paper Award Ranked No.1 among 227 submissions in the premier computer architecture conference HPCA Engineering Outstanding International Student Award One of 15 students selected from across the ten departments in the College of Engineering at UF Attributes of a Gator Engineer Recognition Award The highest honor in the College of Engineering at UF ( only 5 graduate recipients every year ) University of Florida Graduate Alumni Fellowship (4 consecutive years) One of the most prestigious graduate student awards available at the University of Florida Chu Kochen Certificate of Honors, Zhejiang University For completing the highly selective (top 5%) Chu Kochen honors program at Zhejiang University Outstanding Bachelor Thesis Award, Zhejiang University Received the highest thesis evaluation score in the College of Electrical Engineering (top 10%) Outstanding Graduate Award, Zhejiang University National Undergraduate Innovative Research Scholarship, Ministry of Education of China National Encouragement Scholarship, Ministry of Education of China National Scholarship, Ministry of Education of China National Scholarship, Ministry of Education of China 1 st Prize, Annual National High School Physics Olympiad, the Chinese Physical Society 1 st Prize, Annual National High School Math Competition, the Chinese Mathematical Society PUBLICATIONS [C1] [C2] [C3] [C4] [C5] C. Li, Y. Hu, R. Zhou, M. Liu, L. Liu, J. Yuan, and T. Li, Enabling Datacenter Servers to Scale Out Economically and Sustainably, Proceedings of the 46 th ACM/IEEE International Symposium on Microarchitecture (MICRO), December Acceptance Ratio: 39/269 = 14.5% C. Li, R. Wang, N. Goswami, X. Li, T. Li, and D. Qian, Chameleon: Adapting Throughput Server to Time-Varying Green Power Budget Using Online Learning, Proceedings of the ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED), pp. 100-105, September Acceptance Ratio: 39/167 = 23.4% R. Zhou, F. Liu, C. Li, and T. Li, Optimizing Virtual Machine Live Storage Migration in Heterogeneous Storage Environment, Proceedings of the ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments (VEE), pp. 73-84, March Acceptance Ratio: 18/42 = 42.9% C. Li, R. Zhou, and T. Li, Enabling Distributed Generation Powered Sustainable High-Performance Data Center, Proceedings of the 19 th IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 35-46, February Acceptance Ratio: 51/249 = 20.5% C. Li, A. Qouneh, and T. Li, iswitch: Coordinating and Optimizing Renewable Energy Powered Server Clusters, Proceedings of the 39 th Annual ACM/IEEE International Symposium on Computer Architecture (ISCA), pp. 512-523, June Acceptance Ratio: 47/257 = 18.2% Page 2 of 6
[C6] [C7] [C8] A. Qouneh, C. Li, and T. Li, A Quantitative Analysis of Cooling Power in Container-based Data Centers, Proceedings of the 2011 IEEE International Symposium on Workload Characterization (IISWC), pp. 61-71, November 2011 Acceptance Ratio: 19/62 = 30.6% C. Li, A. Qouneh, and T. Li, Characterizing and Analyzing Renewable Energy Driven Data Centers (short paper), Proceedings of the 2011 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS), pp. 131-132, June 2011 Acceptance Ratio: 48/177 = 27.1% C. Li, W. Zhang, C. Cho, and T. Li, SolarCore: Solar Energy Driven Multi-core Architecture Power Management, Proceedings of the 17 th IEEE International Symposium on High-Performance Computer Architecture (HPCA), pp. 205-216, February 2011, (Best Paper Award) Acceptance Ratio: 42/227 = 18.5% KEY PROJECTS 09/ 04/2010 04/2010 08/2011 07/2011 08/ 04/2011 04/ 09/2011 06/ Solar Energy Driven Multi-Core Architecture Power Management [HPCA 11] We first explore renewable energy integration opportunities at the server level. We propose SolarCore, a multi-core power management scheme that can cooperatively optimize solar energy utilization and server performance. SolarCore features novel heuristic control that enables multi-core system to track the maximal power output of solar panels. Meanwhile, it intelligently allocates the time-varying solar power budget across heterogeneous workloads. Optimizing Renewable Energy Powered Server Clusters [SIGMETRICS 11, ISCA 12] We take the lead to analyze the cluster-level power management efficiency in a renewable energy powered data center. Our characterization result shows that existing power management schemes incur up to 4X overhead due to inefficient and redundant load matching activities. To this end, we propose iswitch, a novel optimization strategy that could maintains a balance between energy utilization and load performance while minimize the control overhead. Enabling Distributed Energy Powered Sustainable HPC Datacenter [HPCA 13] In this study we look at such an emerging trend in the IT industry: using onsite distributed generation (DG) to provide premium clean energy to computing load. We propose data center power demand shaping (PDS) to solve the low efficiency issue in DG-powered datacenters. The key novelty of our approach is that we emphasize enabling power supply to follow datacenter power demand, rather than forcing the IT load to track the variable renewable power budget. Managing Green Power on Throughput Servers Using Online-Learning [ISLPED 13] We step up our efforts to make server-level green energy management more efficient. We propose Chameleon, a many-core system that explores intelligent adaptation of power management policy. Chameleon consists of multiple power management modes and leverages learning algorithm to select the optimal operating mode during runtime. The proposed design outperforms existing approaches by 13% on performance and could improve system MTBF by 42%. Enabling Datacenter Servers to Scale Out Economically and Sustainably [MICRO 13] In this project we take the first step towards designing an incremental power capacity expansion scheme for scale-out datacenters. Our design leverages modular renewable energy source and emerging distributed energy storage architecture to achieve sustainable and flexible datacenter power provisioning. We have implemented our design as a prototype system and we propose energy source management strategy so that the overall efficiency and reliability are optimized. Page 3 of 6
PATENTS [P1] [P2] [P3] [P4] A Controller for Optimizing Performance-Per-Watt in Renewable Energy-Driven Computers Chinese Patent, No. 10019554, -08-01 Solar Energy Driven Computer Power Management Systems and Methods Chinese Patent, No. 10019241, -07-25 Renewable Energy Control Systems and Methods U.S. Utility Patent Pending, Method and Apparatus for Data Center Power Management using On-site Distributed Generation U.S. Utility Patent Pending, GRANTS 2011 2011 2008 NSF Travel Grant, Int l Symposium on Microarchitecture (MICRO) Graduate Student Council Travel Grant, University of Florida Research Grant for Facebook Graduate Fellows, Facebook Inc. NSF Travel Grant, Int l Symposium on High-Performance Computer Architecture (HPCA) Yahoo! Key Scientific Challenges Program Research Seed Funding, Yahoo! Inc. NSF Travel Grant, Int l Symposium on Computer Architecture (ISCA) NSF Travel Grant, Int l Symposium on Computer Architecture (ISCA) NSF Travel Grant, Int l Symposium on High-Performance Computer Architecture (HPCA) Student Research Training Program (SRTP) Grant, Zhejiang University National Undergraduate Innovative Research Grant, Ministry of Education of China TALKS [T1] [T2] [T3] [T4] [T5] [T6] [T7] Enabling Renewable Energy Powered Sustainable High-Performance Computing Shanghai Jiao Tong University, Shanghai, China, 1/3/2014 Peking University, Beijing, China, 12/17/ Beihang University, Beijing, China, 09/05/ Enabling Datacenter Servers to Scale Out Economically and Sustainably MICRO, Davis, CA, USA, 12/10/ Adapting Throughput Server to Time-Varying Green Power Budget Using Online Learning ISLPED, Beijing, China, 09/04/ Enabling Distributed Generation Powered Sustainable High-Performance Data Center HPCA, Shenzhen, China, 02/24/ Managing Renewable Energy Powered Computing Systems Wuhan University of Technology, Wuhan, China, 09/24/ iswitch: Coordinating and Optimizing Renewable Energy Powered Server Clusters ISCA, Portland, OR, USA, 06/13/ SolarCore: Solar Energy Driven Multi-core Architecture Power Management HPCA, San Antonio, TX, USA, 02/14/2011 Page 4 of 6
SERVICES EXPERIENCES TEACHING Organization Committee Web Chair, IEEE Int l Symp. on High-Performance Computer Architecture (HPCA), 2014 Publicity Chair, IEEE Int l Conf. on Networking, Architecture, and Storage (NAS), Reviewer IEEE Transactions on Parallel and Distributed Systems (TPDS) IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS) Elsevier Journal of Cleaner Production (JCLEPRO) ACM/IEEE Design Automation Conference (DAC, 2014) Sub-Reviewer IEEE TC, IEEE CAL, Elsevier SUSCOM, ACM/IEEE ISCA 2014, IEEE HPCA, IEEE ISPASS 2010, IEEE ISPASS 2011, IEEE ISPASS, IEEE IISWC 2010, IGCC: Research Assistant, University of Florida, Gainesville, FL, August to August Intelligent Design of Efficient Architectures Laboratory (08/ 08/) Developed cooperative power management schemes for the next-generation green data centers Wuhan University of Technology, Wuhan, China (06/ 09/) Implemented a prototype solar energy integration and management system for server clusters Institute of Computing Technology, Beijing, China (09/2011 11/2011) Worked on the conceptual design and initial prototype of a solar energy powered computer Research Assistant, Zhejiang University, Hangzhou, China, November 2006 to May Institute of VLSI Design, Zhejiang University (03/2008 05/) Analyzed parallel computing algorithm for design for manufacturability (DFM) Funded by the Student Research Training Program of Zhejiang University Institute of Information and Communication Engineering, Zhejiang University (11/2006 03/2008) Implemented a pitch extraction algorithm for human voice recognition Funded by the National Undergraduate Innovative Research Program of China Visiting Student, UCLA, Los Angeles, CA, August 2008 Summer Session C: Scholarly Writing Guest Lecturer, Department of Electrical & Computer Engineering, University of Florida EEL 6935 - Billion Transistor Computer Architecture, Spring 2010 Gave a tutorial on clean energy technology and its applications to computing systems Gave a tutorial on emerging green computing techniques EEL 6935 - Billion Transistor Computer Architecture, Spring Gave a series of lectures on energy-aware advanced computer system design Mentor, Department of Electrical & Computer Engineering, University of Florida Mentored one bachelor s thesis, and co-advised several visiting scholars, MS and Ph.D. students Page 5 of 6
COURSES SKILLS VLSI Circuits & Technology; Computer Architecture; Parallel Computer Architecture; Billion Transistor Computer Architecture; Autonomic Computing; Cloud Computing and Storage; Virtual Computer; Cyber-Physical Systems. Programming languages C/C++, MATLAB, Python, Perl, Bash, UPC, MPI, HTML, Verilog HDL Mathematical Modeling MATLAB/SIMULINK, MAPLE Architectural Simulators M-Sim, Simics Digital and Analog Design Tools Modelsim, NI Multisim, Xilinx ISE, Cadence Virtuoso, OrCAD/PSpice System Design and Implementation Experiences in assembling, deploying, and troubleshooting server hardware Experiences in installing, configuring, and troubleshooting networked systems Ph.D. COMMITTEE Tao Li (Advisor), Associate Professor, UF Department of Electrical & Computer Engineering José A. B. Fortes, Professor, UF Department of Electrical & Computer Engineering Renato J. Figueiredo, Associate Professor, UF Department of Electrical & Computer Engineering Prabir Barooah, Associate Professor, UF Department of Mechanical and Aerospace Engineering REFERENCES Tao Li, http://www.taoli.ece.ufl.edu/ Associate Professor, Department of Electrical & Computer Engineering University of Florida, Gainesville, FL Additional references available upon request Page 6 of 6