More about HKUST
Construct System Software for Big-data Computation
Speaker: Dr. Lin GU Department of Computer Science & Engineering Hong Kong University of Science & Technology Title: "Construct System Software for Big-data Computation" Date: Monday, 13 May 2013 Time: 4:00pm - 5:00pm Venue: Lecture Theatre F (Leung Yat Sing Lecture Theatre, near lifts 25/26) HKUST Abstract: It has been widely speculated that “big data” will be an important development in the years to come. However, computing technology is not yet ready for conducting complex computation on petabytes of data at an easily affordable cost. Overcoming this challenge requires sophisticated system design and, very likely, significant innovations at several layers of the technological hierarchy. In this talk, we will first briefly review what big-data computation is, why it is important, and how the current technologies tackle the problem. Then we will introduce a new C-like programming language we have developed for large-scale distributed computation and compare its performance with MapReduce/Hadoop, which is the most widely accepted cloud and big-data computing technology today. Finally, we argue that a fine cloud computing system we should envision to build a few years from now should be able to conduct non-trivial computation on one petabyte data within one second. *************************** Biography: Lin Gu is an Assistant Professor at the Department of Computer Science and Engineering at the Hong Kong University of Science and Technology (HKUST). He received B.S. from Fudan University, M.S. from Peking University, and Ph.D. in Computer Science from the University of Virginia. His research interest includes cloud computing, operating systems, computer networks, and wireless sensor networks. His research has led to the development of several innovative systems, including Virtk (a.k.a. t-kernel), the Extended VigilNet, and CCMR, and attracted funding from leading industrial firms including Huawei Technologies and Microsoft. He participated in organizational and referee services in more than fifty academic conferences and journals.