Keynote: Trends in Post-petascale computing

Professor Mitsuhisa Sato

University of Tsukuba and RIKEN AICS, Japan


About the keynote speaker

    ChiaShen Mitsuhisa Sato received the M.S. degree and the Ph.D. degree in information science from the University of Tokyo in 1984 and 1990. He was a senior researcher at Electrotechnical Laboratory from 1991 to 1996, and a chief of Parallel and distributed system performance laboratory in Real World Computing Partnership, Japan, from 1996 to 2001. Currently, he is a professor of Graduate School of Systems and Information Engineering, University of Tsukuba. He is a director of Center for computational sciences, University of Tsukuba since 2007. He is a research team leader on programming environment in AISC(Advanced institute of Computational Science) of RIKEN since 2010. His research interests include computer architecture, compilers and performance evaluation for parallel computer systems, OpenMP and parallel programming. Dr. Sato is a member of IEEE CS and IPSJ (the Information Processing Society of Japan), JSIAM.


Abstract

Computational science through applications of high performance computing enables us to explore uncharted fields of science, and has now become indispensable for the development of science and technology of the 21st century. High performance computing systems used for cutting-edge of advanced computational science have reached to petaflops (a million billion calculations per second) performance, and will be targeted to the next generation of exascale systems as a post petascale system. For some years ahead, peta-scale high performance computing systems which have over peta-FLOPS performance, are being built and installed in US, Japan and Europe. In Japan, the next generation supercomputer (NGS) project lead by RIKEN is one of the most ambitious projects in the world to install a 10 petaflop system by 2012.

Post-petascale systems and future exascale computers are expected to have an ultra large-scale and highly hierarchical architecture with nodes of many-core processors and accelerators. That implies that existing systems, language, programming paradigms and parallel algorithms should be reconsidered. To manage these ultra large-scale parallel systems, we require new adaptive runtime systems, allowing to manage huge distributed data, minimizing the energy consumption, and with fault resilient properties. Moreover, accelerating technology such as GPGPU and many-core processors, is a crucial domain for post petascale computing. Their efficient programming in these large scale systems is also an important challenge. Recently the International exascale software project (IESP) was organized to paves the road to the future exascale computing, as a consequence of Post-petascale researches.

In this talk, I will talk about trends in post-petascale computing with the Japanese NGS project, and address challenges, constraints and opportunities to exascale computing in future.


Keynote: Context Sensing for Ubiquitous Computing

Professor Hans Gellersen

Lancaster University, UK


About the keynote speaker

    ChiaShen Hans Gellersen is a Professor of Interactive Systems in the School of Computing and Communications at Lancaster University, UK. He has a long-standing track record in ubiquitous computing where his work is focused on context sensing, location systems and user interface technologies. Hans has led European research collaborations on topics such as smart objects and relative positioning and is widely cited for work on augmentation of everyday objects, multi-modal sensing of context, and novel devices for interaction. His recent work includes research on eye movement as a context for ubiquitous computing, ad hoc location systems for use in emergency response, and sensor-based device authentication. Hans is closely involved with the International Conference on Ubiquitous Computing, which he founded in 1999, and the International Conference on Pervasive Computing, for which he served as Chair of the Steering Committee from 2007-2009. He is also an Editorial Board Member of IEEE Pervasive Computing Magazine, and an Editor of the Journal on Personal and Ubiquitous Computing. Hans holds a PhD in Computer Science from the University of Karlsruhe, Germany.


Abstract

Whereas digital worlds were once seen as something largely separate from the everyday physical world, they are now increasingly interwoven. Context sensing has become a central feature of mobile and ubiquitous computing systems, employing sensors to observe real world activity, and data analysis to extract contextual information. This talk briefly reflects on how context sensing has evolved in ubiquitous computing. It then discusses research projects at Lancaster that, in very different ways, employ embedded sensing and analysis of movement: of devices, for the purposes of secure pairing; of users, for tracking in unknown environments; and of people's eyes, for activity inference.


Keynote: Finding the Real Source of Internet Crimes

Professor Wanlei Zhou

Chair Professor of Information Technology,

Head, School of Information Technology,

Deakin University, Melbourne, Australia.


About the keynote speaker

    Wanlei Zhou Professor Wanlei Zhou received the B. Eng (Computer Science and Engineering) and M. Eng (Computer Science and Engineering) degrees from Harbin Institute of Technology, Harbin, China, in 1982 and 1984, respectively, and the Ph.D. degree from the Australian National University, Canberra, Australia, in 1991. He also received a DS.c. degree (a higher Doctorate degree) from Deakin University in 2002 for his substantial contribution to knowledge and authoritative standing in the field of distributed computing. He is currently the Chair Professor in Information Technology and Head of School, School of Information Technology, Deakin University. Before joining Deakin University, he has been a system programmer in HP at Massachusetts, USA; a lecturer in Monash University, Melbourne, Australia; and a lecturer in National University of Singapore, Singapore. His research interests include theory and practical issues of building distributed systems, security and reliability of computer networks, bioinformatics, and e-learning.Professor Zhou has published more than 200 papers in refereed international journals and refereed international conferences proceedings. He has also edited 5 books and authored 1 book. He has also chaired a number of international conferences. He is also a Senior Member of the IEEE.


Abstract

Internet crimes can result in serious consequences such as disrupting critical infrastructure; causing significant financial losses; and threatening public life. Although a number of countermeasures and legislations against Internet crimes are developed, the crimes are still on the rise. One critical reason is that researchers and law enforcement agencies still can not answer a simple question easily: who and where is the real source of Internet crimes? With the support of a number of Australian Research Council grants, my research group has developed effective ways to discover the real source of Internet crimes. In this talk, I will try to explain how we achieveed this research goal through traceback schemes that we have developed. This talk will be based on the following two papers: (1). Shui Yu, Wanlei Zhou, Robin Doss, and Weijia Jia, "Traceback of DDoS Attacks using Entropy Variations", Accepted by IEEE Transactions on Parallel and Distributed Systems, accepted 09/2009. Published online 30 Apr. 2010, http://doi.ieeecomputersociety.org/10.1109/TPDS.2010.97. (2). Yang Xiang, Wanlei Zhou, and Minyi Guo, "Flexible Deterministic Packet Marking: An IP Traceback System to Find the Real Source of Attacks", IEEE Transactions on Parallel and Distributed Systems, vol. 20, no. 4, pp. 567-580, April 2009.


Keynote: Multi-touch HCI: A hardware and software co-evolution

Director, Scientists Discovery Room Lab

School of Engineering and Applied Sciences (SEAS)

Harvard University, USA


About the keynote speaker

    ChiaShen Chia Shen is Director of the SDR Lab and Senior Research Fellow at the School of Engineering and Applied Sciences (SEAS) at Harvard University. She was a Senior Research Scientist at MERL (the Mitsubishi Electric Research Labs) in Cambridge, Massachusetts, where she also served as Associate Director of the Research Lab from 2003 to 2006. She is the Principle Investigator of a new National Science Foundation-funded $2.3M project "Life on Earth". For the past ten years, much of her research has focused on multi-touch tabletop computing, on its user interface and interaction techniques, and on its utility, benefits, pitfalls, and applications. DiamondSpin, developed at MERL under her direction during 2001-2003, is the first open toolkit made available to the tabletop research community and academic institutes throughout the world for the construction of experimental multi-user tabletop concepts and applications. Her co-authored paper on the PDH (Personal Digital Historian), a tabletop story-sharing system, has been ranked as the most cited paper for the 2002 ACM CSCW (ACM Conference on Computer Supported Cooperative Work). Chia Shen is on the Editorial Board of ACM Computers in Entertainment, and on the Steering Committee of the ACM International Conference on Interactive Tabletops and Surfaces.


Abstract

The emerging growth of multi-touch technology, from its birth in innovators' sandboxes, to embryonic prototypes in isolated labs, to today's world-wide commercial availability, reflects a journey of technology-enabled HCI. At the core is the inseparable process of HCI hardware and software coevolution that has enabled the expansion of the multi-touch horizon in terms of device innovation and the associated user population and demographics. The first part of this talk illustrates the R&D trajectory of this HCI micro-world by looking back at a sample set of research projects that have marched hand-inhand with technological advances in this journey. The second part of the talk then looks ahead to describe ongoing multi-disciplinary research projects in the Scientists' Discovery Room Lab at Harvard University that are set out to push the HCI application boundaries of this expanding horizon.