Guest Speaker: Jianfeng Zhan
Talk Abstract: As architecture, system, and data management communities pay greater attention to innovative big data systems and architectures, the pressure of benchmarking and evaluating these systems rises. However, the complexity, diversity, frequently changed workloads, and rapid evolution of big data systems raise great challenges in big data benchmarking.
This talk presents our joint research efforts on this issue with several industrial partners. Our big data benchmark suite - BigDataBench not only covers broad application scenarios, but also includes diverse and representative data sets. BigDataBench is publicly available from http://prof.ict.ac.cn/BigDataBench.
So as to explore Big Data systems and architectures, we quantify characteristics of comprehensive big data workload performance and energy efficiency on four representative state-of-practice platforms with brawny-core, wimpy multi-core, and wimpy many-core processors. Our evaluations show: (1) none of the microprocessors we study consistently wins in terms of both performance and energy efficiency for all of our Big Data workloads, and (2) there are different classes of Big Data workloads, and each class of workload realizes better performance and energy efficiency on different Big Data architectures. We should eschew one-size-fits-all solutions, and instead tailor system designs to specific workload requirements.
About the Speaker: Jianfeng Zhan is a Professor of Computer Science and Engineering at Institute of Computing Technology, Chinese Academy of Sciences and University of Chinese Academy of Sciences. He is Deputy Director of Computer Systems Research Center, ICT, Chinese Academy of Sciences. His research interests include computer architecture, operating systems, data management, parallel and distributed systems. He has published over 60 papers in major journals and international conferences related to these research areas, and filed 40 patents.
From 2004 to 2010, he leaded the R&D efforts of innovative cluster and cloud systems software for the dawning-series super computers (which ranked top 2 and top 10 on the top 500 list in 2010 and 2004, respectively). Among them, GridView was transferred to Sugon, which is a premier supercomputing company in China, and becomes its popular software product. Currently, he is leading the research efforts for ICT datacenter and big data software stacks, including BigDataBenchóan open source big data benchmarking project, and RainForest--- an operating system for Internet services.
He received the second-class Chinese National Technology Promotion Prize in 2006, the Distinguished Achievement Award of the Chinese Academy of Sciences in 2005, IISWC Best paper award in 2013, and Huawei Contribution Prize in 2013, respectively. He is a CCF senior member, an IEEE member, and an ACM member. More details about Prof. Zhan are available at http://prof.ict.ac.cn/jfzhan
Host: Dhabaleswar Panda