Keynote I

Topic: Resource Management in Parallel Architectures
Per Stenström
Prof. Per Stenström
Chalmers university of technology, Sweden

Per Stenström is professor at Chalmers University of Technology. His research interests are in parallel computer architecture. He has authored or co-authored three textbooks and more than 130 publications in this area. He has been program chairman of the IEEE/ACM Symposium on Computer Architecture, the IEEE High-Performance Computer Architecture Symposium, and the IEEE Parallel and Distributed Processing Symposium and acts as Senior Associate Editor of ACM TACO and Associate Editor-in-Chief of JPDC. He is a Fellow of the ACM and the IEEE and a member of Academia Europaea and the Royal Swedish Academy of Engineering Sciences.


Prof. Per Stenstörm is a member of the ACM A.M. Turing Award Committee. Here is the home page of the ACM A.M. Turing Award Committee.


Abstract: As we have embarked on the multi/many-core roadmap resource management, especially managing parallelism, is left in the hands of programmers. A major challenge moving forward is therefore how to off-load programmers from the daunting task of managing hardware resources in future parallel architectures to meet higher demands on performance and power efficiency.
    In this talk I will focus on a number of emerging technologies being developed at Chalmers and elsewhere to off-load programmers from tedious resource management. These include propagating semantic information for more effective communication, adaptive transactional memory systems, and exploitation of value locality for more efficient memory access.


Keynote II

Topic: Big Data Challenges in Alibaba e-Commerce

Dr. Wensong Zhang
Dr. Wensong Zhang
Alibaba Group, China

Dr. Wensong Zhang is Vice President and Senior Researcher of Alibaba Group, where he is responsible for building next-generation highly scalable low-cost e-commerce infrastructure. He is also open source and Linux kernel developer, the founder and developer of the Linux Virtual Server project, an open source project to building advanced server clustering software for Linux. The LVS software was included in official Linux kernel 2.4, 2.6 and above, and there are about several 10,000 deployments of LVS clusters in this world. Before joining Alibaba, he was chief scientist and co-founder of TelTel. He was an associate professor at National University of Defense Technology. He received a Ph.D. degree in Computer Science from National University of Defense Technology in 2000.


Abstract: Alibaba Group is one of the largest e-commerce companies in the world. This talk will give a brief introduction about Alibaba Group, and present its e-commerce platforms and big data challenges in system design and implementation. First,  overall system architecture of its major e-commerce platform of taobao.com and tmall.com is described, in which we can see different type of data is generated in the systems and how data flows between online systems and offline processing systems. Second, different types of online data storage systems and their scale are described, such as TFS for non-structure data, TAIR for semi-structure data, and MySQL/OceanBase for structure data. Third, offline data is now mainly stored in Hadoop systems,  more efforts is put to resolve the scalability issues of Hadoop when the systems are getting bigger and bigger, and also work on possible solution of cold data storage. Fourth, online and offline data growth rate is given, offline part grows more rapidly than online part now, major challenges in system level is how to reduce storage cost for data, how to minimize computing cost for business tasks,  and how to provide services and computing models  for rapid restructuring as business evolves. Finally, system challenges in big data is concluded, and cooperation with academic research is welcomed.


Keynote III

Topic: The Mont-Blanc project: Are mobile processors ready for HPC?

Alex Ramirez
Dr. Alex Ramirez
Barcelona Supercomputer Center, Spain

Alex Ramirez is an associated professor in the Computer Architecture Department at the Universitat Politecnica de Catalunya, and leader of the Heterogeneous Architectures group at BSC. He has a BSc ('95), MSc ('97) and PhD ('02), awarded the UPC extraordinary award to the best PhD in computer science) in Computer Science from the Universitat Politecnica de Catalunya (UPC), Barcelona, Spain. He has co-authored over 150 papers in international conferences and journals, supervised 10 PhD students, and participated as principal investigator in the ACOTES, SARC, ENCORE and HiPEAC European Projects. He currently leads the Mont-Blanc project. In 2010 he was awarded the first Agustin de Betancourt award of the Spanish Royal Academy of Engineering to a young researcher.


Abstract: High Performance Computing was initially built on vector processors and data level parallelism. During the 1990's, processors targeted at personal computers and workstations integrated the floating point unit, which made them capable of running HPC workloads.
   These commodity processors were 10 times slower, but they were 50 times cheaper. That fact, coupled with the transition from DLP and shared memory programming to message passing programming models, changed HPC replacing vector systems for more cost-efficient distributed systems built on commodity processors.
   Smartphone processors now have integrated floating point units. They are still 10 times slower than today’s HPC commodity processors, but they are also 50 times cheaper, and they do not require a fundamental change in the parallel programming model to use.
   We may be about to see another step in HPC evolution, when a new class of super-commodity processor replaces the current established technology for a more cost-efficient alternative.


Keynote IV

Topic: Swedish e-Science and the Quest for Exascale

Professor Erwin Laure

Prof. Erwin Laure

Director PDC-Center for High Performance Computing, KTH

Professor Erwin Laure is Director of PDC-Center for High Performance Computing Center at KTH, Stockholm. Prior to this position he was the Technical Director of the "Enabling Grids for E-Science in Europe (EGEE)" project working at CERN. He is the Coordinator of the EC-funded "ScalaLife" project and actively involved in major e-infrastructure projects (EGI, PRACE, EUDAT). His research interests include programming environments, languages, compilers and runtime systems for parallel and distributed computing, particularly exascale computing, as well as grid and cloud computing with a focus on data management.


Abstract: Swedish e-Science has got a major push through the creation of two large scale e-Science collaborations: the Swedish e-Science Research Center (SeRC) and eSCCENCE. These collaborations as well as Sweden's engagements in international projects have propelled the use of e-Science infrastructure and methods in many scientific fields. In this talk we review the successes of Swedish e-Science, its contributions to international developments and discuss the challenges ahead on the road to exascale.