NESUS: Network for Research on Sustainable Ultrascale Computing Systems
By Prof. Jesus Carretero
Computer Architecture Professor
Computer Science and Engineering Dep. University Carlos III of Madrid
Abstract: In this talk, I´ll present the NESUS COST Action, which was created to establish an open research network targeting sustainable solutions for ultrascale computing systems. Ultrascale systems are envisioned as large-scale complex systems joining parallel and distributed computing systems that will be two to three orders of magnitude larger that today´s systems. In an effort to cope with this systems, the NESUS Action aims at collaboratively rethinking the current basis of development of system software for scalable computing systems in order to pave the way towards a sustainable future scale growth by improving the coordination of efforts between complementary communities. Cross fertilization among High Performance Computing (HPC), large scale distributed systems, and big data management is pursued to provide common activities in research topics such as sustainable software solutions (applications and system software stack), data management, energy efficiency, and resilience. These efforts will be translated to applications amenable to ultra scale provided by institutions (academy and industry) members of the network. In this speech, NESUS COST action will be presented, together with some examples of the effort being made in the ARCOS research group to enhance sustainability of ultrascale applications.
Short Bio: Jesus Carretero is a Full Professor of Computer Architecture and Technology at Universidad Carlos III de Madrid (Spain), where he is responsible for that knowledge area since 2000. He is also Director of the Master in Administration and Management of Computer Systems, which he founded in 2004.
His research activity is centered on high-performance computing systems, large-scale distributed systems and real-time systems. He is Action Chair of the IC1305 COST Action “Network for Sustainable Ultrascale Computing Systems (NESUS)”, and he is also currently involved in the FP7 program REPARA “Reengineering and Enabling Performance And poweR of Applications”. He has participated and leaded several national and international research projects in these areas, founded by Madrid Regional Government, Spanish Education Ministry and the European union.
Prof. Carretero is Associated Editor of the journal Computer and Electrical Engeneering and International Journal of Distributed Sensor Networks. He has published more than 180 papers in journals and international conferences, editor of several books of proceedings, and guest editor for special issues of journals as Intenational Journal of Parallel Processing, Cluster Computing, Computers and Electrical Engineering, and New Generation Computing, and he is coauthor of several text books related to Operationg Systems and Computer Architecture. He has participated in many conference organization committees, and he has been General chair of HPCC 2011 and MUE 2012, and Program Chair of ISPA 2012, EuroMPI 2013, C4Bio 2014, and ESAA 2014. Prof. Carretero is a senior member of the IEEE Computer Society and member of the ACM. He also serves and has served as a Technology Advisor and in applied projects with several companies such as RENFE, EADS, INDRA, SIEMENS or ISOLUX, developing research and innovation projects. He is a project reviewer for Spanish research ministry and also European Union.
HPC as a Service: Challenges and Limitations
By Prof. Dana Petcu
Computer Science Professor
Computer Science Department and vice-rector at West University of Timisoara, Romania
Abstract: HPC landscape is dramatically changing nowadays by the race towards exascale, the performance busting through mastering the hardware heterogeneity, or the impetuous request to reduce of the energy consumption. In the same time, the Cloud computing is evolving from its primary aim of providing services for web applications towards serving Big Data applications. While HPC as a Service (HPCaaS) concept has appear in the earliest days of Cloud as appropriate to serve the long tail of scientific and engineering activities, the latest technology trends are promising a fruitful engagement between Cloud and HPC concepts in order to reach the critical mass of users and significant applications. We will review the current technologies and efforts that are supporting the HPCaaS concept. We will also identify the challenges and limitations that are posed to achieve the potential of the HPCaaS. In particular, we will discuss how the lesson learned from mastering the heterogeneity in Multi-Clouds services can be applied to HPC services and how a service brokerage system exposing services running on heterogeneous computing environments can support HPC applications.
Short Bio: Dana Petcu is Professor at Computer Science Department and vice-rector at West University of Timisoara, scientific manager of its supercomputing center, and CEO of the research spin-off Institute e-Austria Timisoara. Her interest in distributed and parallel computing is reflected in more than two hundred papers about Cloud, Grid, Cluster or HPC computing. She is and was involved in several projects funded by European Commission and other research funding agencies, as coordinator, scientific coordinator, or local team leader. She is chief editor of the open-access journal Scalable Computing: Practice and Experience. Home page: http://web.info.uvt.ro/~petcu.