Program, Best Papers, Keynotes > Invited Speaker

Title of the Keynote Talk:  Reengineering for Parallelism in C++

 

Abstract: In the laste decade processors clock frequency has not seen any major improvements while at the same time energy consumption has become a concern. As a consequence there has been a paradigm shift in many domains from sequential computing towards parallel processing with a transition to parallel heterogeneous computers. However the use of multiple divergent architectures with different programming models has made programming increasingly difficult and costly. To overcome this difficulties software reegineering may help to simplify the development process. In this talk I will explore what are the some of the challenges and provide some examples to overcome them. During the talk I will focus in examples using latest version of the C++ programming language, paying attention to its current status and evolution roadmap.

 

Bio: J. Daniel Garcia is an Associate Professor of Computer Architecture at Universidad Carlos III of Madrid since 2006. J. Daniel Garcia is a Senior Member of the IEEE and a member of the ACM. He has worked in industry for major companies in Spain and Germany including Telefonica, British Telecom, ING Bank and SIEMENS, having the opportunity to participate in large scale international projects. He has published more than 50 international journal and conference papers and has edited several special issues. He has participated in 10 technology transfer contracts and 12 publicly funded research projects, as well as many others before joining academia. He is currently the Project Coordinator of the FP7 project REPARA. He also leads the participation of UC3M in the H2020 project RePhrase. He has been Visiting Researcher at University of Modena, Italy, and VisitingFaculty at University of Texas, A&M. He was General Chair of IEEE ISPA 2012 and ICA3PP 2010 and has served in PC of more that 30 other related conferences. Since 2008 he is the Spanish Head of delegation in the ISO C++ Standards Committee where he actively participated in the development of the C++11 and C++14 standards. He participates with special intensity in the C++ Evolution Working Group and the special Group on Concurrency and Parallelism. 

 

 

Bio: Julien Bourgeois is professor of computer science at the University of Franche-Comté (UFC) in France. He is part of the FEMTO-ST institute (UMR CNRS 6174) where he is leading the complex networks team. His research interests are in distributed intelligent MEMS (DiMEMS), programmable matter and nanocommunication networks. He has been invited professor at Carnegie Mellon University (US) from 9/2012 to 8/2013, at Emory University (US) in 2011 and in Hong Kong Polytechnic University in 2010, 2011 and 2015. He led different funded research projects (Smart Surface, Smart Blocks, Computation and coordination for DiMEMS). All these projects are funded by research agencies. He is currently leading the topic “System architecture, communication, networking” in the LABEX ACTION, a 10 M€ funded program whose aims at building integrated smart systems (http://www.labex-action.fr/). He has also worked in the Centre for Parallel Computing at the University of Wetsminster (UK) and in the Consiglio Nazionale delle Richerche (CNR) in Genova. He collaborated with several other institutions (Lawrence Livermore National Lab, Oak Ridge National Lab, etc.). He created and chaired the workshop on Distributed MEMS (dMEMS 2010, 2012). In 2005, he created and then chaired all the editions of the Workshop on Modeling, Simulation and Optimization of Peer-to-peer environments (MSOP2P) collocated with PDP until 2013. He has worked for more than 10 years on these topics has co-authored more than 120 international publications and communications and has served as PC members and chaired various conferences (IEEE iThings, IEEE HPCC, Euromicro PDP IEEE GreenCom , IEEE CPSCom, GPC, etc. Apart from its research activities, he is acting as a consultant for the French government and for companies.