Keynote 1

Speaker: Professor Kai Hwang, University of Southern California, Los Angeles

“Massively Distributed Systems : From Grids and P2P to Clouds”

[Go]

Keynote 2

Speaker: M. Frans Kaashoek, Massachusetts Institute of Technology

“Building Distributed, Wide-Area Applications with WheelFS”

[Go]

Keynote 3

Speaker: Wen-Hann Wang, Vice President, Software and Solutions Group,

General Manager, Intel Asia-Pacific Research & Development Ltd.

General Manager, Software and Solutions and Product Development, China

[Go]

Massively Distributed Systems: From Grids and P2P to Clouds
Professor Kai Hwang
University of Southern California, Los Angeles

Abstract: This keynote describes the evolution of massively distributed computing systems and their key techniques. Clusters of computers now prevail, expand, and become the core components in large-scale computational/information/data Grids. The Open Grid Service Architecture, specifying the Grid software, protocol, and service standards, are only partially implemented in Globus and other Grid toolkits. Grid security demand globalization among various PKI authorities and interoperability between wired and wireless networks. Very little progress being made in special networks, hardware, languages, and operating systems for Grid/Cloud computing. Business Grids/Clouds are under development by Google, IBM, Sun, Microsoft, etc., and widespread acceptance is hindered by selfish behavior and security concerns. Briefly, the keynote includes rise and fall of computing technologies and hot paradigms in the last 35 Years, and presents the implication that computing clouds over the Internet will be the next battlefield among competitors.

Prof. Kai Huang’s Bio:

Kai Hwang is a Professor of Electrical Engineering and Computer Science and Director of Internet and Grid Computing Laboratory at the University of Southern California. He received the Ph.D. in Electrical Engineering and Computer Science from the University of California, Berkeley in 1972. Prior to joining USC in 1985, he has taught at Purdue University for many years. He has served as a distinguished Chair Professor during his sabbatical visits at the Univ. of Minnesota, National Taiwan Univ., and Univ. of Hong Kong. He is the founding Editor-in-Chief of the Journal of Parallel and Distributed Computing . He is also an editor of IEEE Transactions on Parallel and Distributed Systems.

Dr. Hwang has authored or coauthored 4 books and 200 scientific papers in refereed Journals and conferences. His past teaching and research work on scalable multiprocessors and parallel processing has been summarized in two of his latest books, Scalable Parallel Computing (McGraw-Hill, 1998) and Advanced Computer Architecture (McGraw-Hill 1993), which are worldwide used and translated into Spanish, Chinese, Japanese, and Korean editions. He was elected an IEEE Fellow in 1986 for making significant contributions in computer architecture, digital arithmetic, and parallel processing. His work was ranked by the CiteSeer. Continuity in August 2006 among the top 0.25% most cited authors in Computer Science out of 790,329 authors in the database. He received the K. S. Fu Award in 2004 from China Computer Federation for his outstanding achievements in high-performance computing research and higher education.

Building Distributed, Wide-Area Applications with WheelFS

M. Frans Kaashoek (MIT)

Abstract: It is a challenge to build applications that need to share data and are distributed across hundreds or thousands of computers in a wide-area network (e.g., PlanetLab or on a Grid). In order to cope with high latency, throughput bottlenecks, and temporary failures, such applications typically implement their own storage plan or use special-purpose storage solutions (e.g., DISC, Globus, Carbonite, etc.). Inspired by the success of the Google File System for cluster applications, this proposal investigates whether a general-purpose wide-area file system could simplify building distributed applications. In particular, this talk presents a preliminary design, called WheelFS. WheelFS's goal is to ease the development of distributed applications such as cooperative Web caches, data-intensive Grid applications, and PlanetLab measurements, perhaps reducing the storage management code to a simple script around the application's core logic. Towards this goal, WheelFS adopts many features from existing file systems, and adds two new ones: semantic cues, and write-locally-read-globally. This talk will also discuss several specific applications that can potentially benefit from using WheelFS.

Joint work with: Jeremy Stribling (MIT), Emil Sit (MIT), Jinyang Li (NYU), and Robert Morris (MIT)

Prof. M. Frans Kaashoek’s Bio:

M. Frans Kaashoek is a full professor in MIT's EECS department and a member of Computer Science and Artificial Intelligence Laboratory, where he coleads the parallel and distributed operating systems group (http://www.pdos.lcs.mit.edu/). He received a PhD (1992) from the Vrije Universiteit (Amsterdam, The Netherlands) for his work on group communication in the Amoeba distributed operating system, under the supervision of A.S. Tanenbaum. Frans's principal field of interest is designing and building computer systems. His past work includes the exokernel operating system, the Click modular router, the RON overlay, the self-certifying file system, the Chord distributed hash table, and the Asbestos secure operating system. Frans is a member of the National Academy of Engineering and the recipient of several awards, including the inaugural ACM SIGOPS Mark Weiser award for demonstrating creativity and innovation in operating systems research.

Virtualization Technology: Past, Present, and Future

Wen-Hann Wang (Intel)

Abstract: Effective sharing and utilization of machine resources have been an active research area since the early days of computing. Virtualization technology was a popular way toward effective resource sharing some four decades ago. It was later replaced by time-sharing systems which incur lower computing overhead. Recent advances in computing platform performance brought virtualization technology back to the main stage. Furthermore, innovations in architecture support for virtualization made many exciting usage models possible. In this presentation I will examine what the field had accomplished in the past. I will then briefly review the wide array of current virtualization technologies and how they are being deployed. I will conclude by projecting where future virtualization technologies might take us.

Dr. Wen-Hann Wang’s Bio:

Wen-Hann Wang is vice president of the Software and Solutions Group, General Manager of Intel Asia-Pacific Research & Development Ltd, and general manager of the Software and Solutions and Product Development in China. Prior to his current assignment, he served as general manager of the Middleware Products Division in the Intel Software and Solution Group. Wang joined Intel in 1991 as a PentiumPro Platform architect, working on the highly successful P6 product family. His platform architecture and analysis work was instrumental in the creation of the Xeon server product line. He served as platform infrastructure research manager of the newly formed Intel Microprocessor Research Lab (MRL) in 1995 and later became director of the Emerging Platforms Lab, delivering cutting-edge technologies and reference platforms for Intel product groups. In 2000, Wang relocated to Shanghai to head up the Technology Development Division of SSG, developing software technologies and reference designs to accelerate growth in emerging markets. Wang holds 15 patents and has received numerous technical awards. Prior to joining Intel, he was a research staff member at the IBM T. J. Watson Research Center. Wang received a bachelor's degree in electrical engineering from National Taiwan University in 1981, a master in electronic engineering from Philips International Institute of Technological Studies (Eindhoven, Netherlands) in 1985, and a Ph.D. in computer science from the University of Washington in 1989.