The University of Adelaide
Smart Content Delivery on The Internet
As the ever-growing Internet applications in the emerging e-society are centered in sharing of various types of digital contents, content delivery on the Internet as a hot topic has been attracting most attentions. Web caching is an important technology for improving the efficiency of content delivery. As a recent technology in Web caching, en-route caching computes locations among caches on access paths to store copies of an object such that specified objectives (such as satisfying future access demands to the object) are achieved. In this talk, I will first give an overview on recent developments in efficient content delivery. I will then introduce our recent work in tackling this problem by applying the technique of en-route caching, and present efficient solutions to the problem in systems containing single server and multiple servers respectively. While the problem is NP-hard in the general case, our solutions deploying dynamic programming techniques run in polynomial-time in the worst case for both unconstrained and constrained cases in the network topologies of trees (for broadcast delivery) and linear arrays (for point-to-point delivery) respectively, and are shown theoretically either optimal or convergent to optimal. Finally, I will show some possible extensions of our solutions to other system settings.
Hong Shen is Professor (Chair of Computer Science) in The University of Adelaide, Australia. Prior to join to Adelaide, he was Professor and Chair of Computer Networks Laboratory in Japan Advanced Institute of Science and Technology (JAIST) during 2001-2006, and Professor of Computer Science at Griffith University, Australia, where he taught 9 years. He has also held several awards, titles, and special appointments, including specially-appointed Professor in University of Science and Technology of China and "100 Talents" of Chinese Academy of Sciences. His main research interests lie in parallel and distributed computing, algorithms, high performance networks, data mining and multimedia systems. Received his Bachelor of Engineering degree from Beijing University of Science and Technology of China, Master of Engineering degree from University of Science and Technology of China, Ph.Lic. and Ph.D. degrees from Abo Akademi University in Finland, Prof. Shen has published 200+ papers, with 100+ papers in international journals including a variety of IEEE and ACM transactions. He has served on editorial boards of 7 international journals, and chaired several international conferences.
The University of Texas at San Antonio
San Antonio, TX 78249
Symbolic Analysis for Increased Program Execution Performance
High end parallel and multi-core processors rely on compilers to perform the necessary optimizations and exploit concurrency in order to achieve higher performance. However, source code for high performance computers is extremely complex to analyze and optimize. In particular, program analysis techniques often do not take into account complex expressions during the data dependence analysis phase. Most data dependence tests are only able to analyze linear expressions, even though non-linear expressions occur very often in practice. Therefore, considerable amounts of potential parallelism remain unexploited. In this talk we propose new data dependence analysis techniques to handle such complex instances of the dependence problem and increase program parallelization. Our method is based on a set of polynomial time techniques that can prove or disprove dependences in source codes with non-linear and symbolic expressions, complex loop bounds, arrays with coupled subscripts, and if-statement constraints. In addition our algorithm can produce accurate and complete direction vector information, enabling the compiler to apply further transformations. To validate our method we performed an experimental evaluation and comparison against the I-Test, the Omega test and the Range test in the Perfect and SPEC benchmarks. The experimental results indicate that our dependence analysis tool is accurate, efficient and more effective in program parallelization than the other dependence tests. The improved parallelization results into higher speedups and better program execution performance in several benchmarks.
Kleanthis Psarris is Professor and Chair of the Department of Computer Science at the University of Texas at San Antonio. His research interests are in the areas of Parallel and Distributed Systems, Compilers and Programming Languages. He received his B.S. degree in Mathematics from the National University of Athens, Greece in 1984. He received his M.S. degree in Computer Science in 1987, his M.Eng. degree in Electrical Engineering in 1989 and his Ph.D. degree in Computer Science in 1991, all from Stevens Institute of Technology in Hoboken, New Jersey. He has published extensively in top journals and conferences in the field and his research has been funded by the National Science Foundation and Department of Defense agencies. He is an Editor of the Parallel Computing journal. He has served on the Program Committees of several international conferences including the ACM International Conference on Supercomputing (ICS) in 1995, 2000, 2006 and 2008, the IEEE International Conference on High Performance Computing and Communications (HPCC) in 2008, and the ACM Symposium on Applied Computing in 2003, 2004, 2005 and 2006. He is a member of ACM and a Senior Member of IEEE.
Using Multi-core to Support Security-Related Applications
This tutorial introduces the challenges of modern security-related applications and the opportunities that multi-core technology brings. We envision that multi-core supported security applications will become the killer applications for next generation personal computers.
This tutorial is divided into four parts. The first part gives an overview of the multi-core technology. The related development of both multi-core hardware and software is introduced.
The second part gives the background knowledge of multiprocessing. Although multi-core technology has just emerged in very recent years, people have done research in multiprocessing for many years. Computer system technology, computer performance, computer architecture, and high-performance multiprocessing are discussed in this part.
Part three, security-related applications, is structured by the attacks and the defense systems. First, the Internet threats and attacks are introduced. Second, the defense systems or countermeasures and their effectiveness are discussed. We will see that unfortunately all these security-related applications are computing intensive applications, which can be difficult to run on today’s personal computers without performance penalties, and cost huge CPU time and memory if they can. More inconveniently, they prohibit other applications running simultaneously or significantly slow down other applications.
Part four discusses how we can leverage the power of multi-core to support security-related applications. We will discuss five important research areas: partitioning and distributing workload of security-related applications, fine-grained multi-threading, smartly using the memory system, communications between cores, and new software architecture for multi-core. After that, we propose an innovative idea of software personal computer bodyguard that can protect future personal computers from various threats at all time and in real-time, with the support from multi-core. Finally, we point out future research directions and conclude this tutorial.
The audience of this tutorial includes researchers, practitioners, and technical workers who are interested in network and system security from academic, businesses and governments. No specific knowledge is required. Anyone with a basic knowledge of the Internet and computers will be able to understand the materials presented in the tutorial.
Bios of the presenters
Professor Wanlei Zhou received his PhD degree from The Australian National University, Canberra, Australia, in October 1991. He also received the DSc degree from Deakin University, Victoria, Australia in 2002. He is currently the Chair Professor of Information Technology and the Associate Dean (International), Faculty of Science and Technology, Deakin University, Melbourne, Australia. His research interests include distributed and parallel systems, network security, mobile computing, bioinformatics and e-learning. Professor Zhou has published more than 170 papers in refereed international journals and refereed international conferences proceedings. Since 1997 Professor Zhou has been involved in more than 50 international conferences as General Chair, Steering Chair, PC Chair, Session Chair, Publication Chair, and PC member. Professor Zhou is a member of the IEEE.
Dr Yang Xiang received his PhD in computer science from Deakin University, Melbourne, Australia, in April 2007. He is currently with School of Management and Information Systems, Central Queensland University. His research interests include network and system security, and wireless systems. In particular, he is currently working in a research group developing active defense systems against large-scale network attacks and new Internet security countermeasures. He has served as guest co-editor for Journal of Network and Computer Applications special issue on network and system security, and the International Journal of Computer Systems Science and Engineering special issue on network attack and defense systems. He has served as PC co-chair for 2007 IFIP International Workshop on Network and System Security and PC member for many international conferences such as IEEE GLOBECOM 2006/2008 and IEEE ICC 2007. He is a member of the IEEE.