COST Action 1305. NESUS. Final Action WGs and MC Meeting.


Welcome to the web page of the FINAL MEETING of the COST ACTION 1305 (NESUS).   In this web page, you will find information related to the agenda of the meeting, including Action presentations and Management Meeting, about the the speakers, and about the Venue and hotels for the meeting.

We hope you may find interesting and enjoy your visit to Madrid.

 

AGENDA

Final Action Meeting.  March 15th-16th. 2018

 

Date

March 15th

Time

Topic

9:00 – 9:30 Welcome. 

Action Chair:  Jesus Carretero, UC3M, Spain

Science Officer:  Ralph Stübner, COST Association, EU

9:30 – 10:15 Invited Speaker: Jean Thomas Acquavida.  DDN, France
Talk: “Performance analysis of a Flash based storage system”
10:15 – 11:00 Action Activities Presentation. 

Jesus Carretero, UC3M, Spain

11:00 – 11:30 Coffe break
11:30 – 13:00 WG Results Presentation

WG1.  Leonel Sousa.  INESC-D, Portugal

WG2.  Georges DaCosta, IRIT, France

WG3.  Sebastien Varrete, University of Luxembourg

13:00 – 14:00 Lunch
14:00 – 15:00 Research Roadmap presentation.

Pierre Kuonen. University of Applied Sciences Western, Switzerland

15:00 – 15:30 Coffe break

 

Date

March 16th

Time

Topic

9:00 – 11:00 WG Results Presentation

WG4.  Angelos Bilas. ICS-FORTH, Greece.

WG5.  Laurent Lefevre & Ariel Oletsiak, INRIA & PNSC, France & Poland

WG6. Svetozar Margenov. BAS, Bulgaria

11:00 – 11:30 Coffe break
11:30 – 12:45 In-Cooperation H2020 research projects panel.

Chair:  Jesus Carretero, University Carlos III of Madrid, Spain

Speakers:

  • Neki Fraskeri, Polytechnic University of Tirana, Albania.
  • Javier Garcia-Blas, University Carlos III of Madrid, Spain
  • Gabriel Conzalez-Castane, University College Cork, Ireland
  • Rafael Mayo, CIEMAT, Spain.
  • Radu Prodan, University of Innsbruck, Austria
12:45 – 13:00 Meeting Close

 

Management Committee Meeting.   March 15th. 2018

 

Time

Topic

Final Action Dissemination Book
15:30 – 17:00 Final Action Report
Future activities and cooperation

 

SOCIAL EVENT

 

Time

Event

20:30 – 22:30

Tapas at the “Basarri Gin Club”

Calle Toledo, No 82, Madrid.
Location in map

 

INVITED TALK

Dr. Jean Thomas Acquaviva.

DDN, France.

Talk: “Performance analysis of a Flash based storage system”

Summary:

The arrival of the Flash has pushed existing HPC file systems to their limits. Dealing with a drastic reduction of storage latency by a factor of 1000 is difficult for the existing software stack of parallel file systems. Therefore, DDN has initiated a complete design overhaul with its IME effort in order to bring to the market a native flash I/O Accelerator.

Taking this IME as an example we will details some performance subtleties of flash devices and how they can impact the performance of the end-user application.

Additionally, a driving force since the inception of the IME project has been the emerging requirements observed in the HPC community. The evolution of usages, the needs for more intense data sharing or collaborative access, the necessity of implementing not only file access but work-flows and specificities of HPDA were keys in the design decisions..

Taking the HPC IO500 as an illustration, we will debate of the relevance of several performance metrics, the way they reveal underlying mechanisms, and how they are correlated to technological orders of magnitudes. We will discuss how these technological parameters impact both metadata management and data payload capability.

 

SPEAKERS

 

Jean Thomas Acquaviva

DDN

Jean Thomas Acquaviva is a Research Engineer at DDN. He obtained his Ph.D in 2000 from CEA, DAM (French Atomic Commission, Military Dept.) and University of Versailles (France). After spending a couple of years at Intel Compiler group in Santa Clara, he joined the University of Versailles as a Research Engineer, and afterward joined CEA (civilian department) still as a Research Engineer. Jean-Thomas was one of the founding members of the Exascale Research Centre, a joint lab between between Intel, CEA and UVSQ, where he took the head of the performance group. He’s now actively participating to the development of DDN’s newly set Advanced Technology Center in France.

Angelos Bilas

University of Crete

Angelos Bilas is currently a Professor and Chair of Computer Science at the University of Crete, Greece, where he has also held an Associate Professor position between 2002-2011. Prof. Bilas received his diploma in Computer Engineering from the University of Patras in 1993, and the M.S and Ph.D. degrees in Computer Science from Princeton University, NJ in 1995 and 1998 respectively. Between 1998-2002 he held an Assistant Professor position with the ECE Department at the University of Toronto. His current interests include architectures and systems software support for efficient storage systems, low-latency high-bandwidth communication protocols, and runtime-system support for multicore processors. His work has been published in prestigious conferences in computer architecture and systems. Prof. Bilas is the recipient of a Marie Curie Excellent Teams Award (2005-2009), has served in the Program Committees of more than 80 conferences and workshops in his area, as the Program Chair for IEEE Cluster 2010, in the Editorial Board of IEEE Computer Architecture Letters (CAL) [2007-2011], currently serves in the Editorial Board of the Journal of Parallel and Distributed Computing (JPDC) [May 2011-], has participated in more than 18 EU or nationally funded projects, and has been the coordinator of the FP7 EU project IOLanes [2010-2013].

Jesus Carretero

University Carlos III of Madrid

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 and leader of the Computer Architecture Research Group (ARCOS). His research activity is centered on high-performance computing systems, large-scale distributed systems, data-intensive computing, IoT and real-time systems. He is Action Chair of the IC1305 COST Action “Network for Sustainable Ultrascale Computing Systems (NESUS)”. 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. 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 HPCC2011, MUE2012, ICA3PP2016 and CGRID 2017, and Program Chair of ISPA 2012, EuroMPI 2013, C4Bio 2014, and ESAA 2014 and CGRID 2017. Prof. Carretero is a senior member of the IEEE Computer Society and member of the ACM.

 

Georges Da Costa

University of Toulouse

Georges Da Costa is a Associate Professor in Computer Science at the University of Toulouse. He received his PhD from the LIG HPC research laboratory (Grenoble, France) in 2005 and his Habilitation at the University of Toulouse in 2015. He is member of the IRIT Laboratory. His main interests are related to large-scale distributed systems (HPC, Clouds), algorithmic, performance evaluation and energy-aware systems. He is working group chair on ‘Runtimes and Programming Models’ of the COST1305 Action Nesus (Network for Sustainable Ultrascale Computing) and was working group chair of the European COST0804 Action on ‘Energy efficiency in large scale distributed systems’. He was Work Package leader of the European project CoolEmAll which aims at providing advanced simulation, visualization and decision support tools along with blueprints of computing building blocks for modular data center environment. His research currently focus on energy aware distributed systems. He serves on several PCs in the Energy aware systems, Cluster, Grid, Cloud and Peer to Peer fields. His research highlights are grid cluster & cloud computing, hybrid computing (CPU/GPU), large scale energy aware distributed systems, performance evaluation and ambient systems.

Pierre Kuonen

University of Applied Scisences Western Switzerland

Pierre Kuonen obtained the Master degree in electrical engineering from the Ecole Polytechnique Fédérale de Lausanne (EPFL) in 1982. After six years of experience in the industry (oil exploration in Africa, then development of computer-assisted manufacturing tools in Geneva), he joined laboratory of the computer science theory at EPFL in 1988 and began working in the field of parallel and distributed systems for high-performance computing. He obtained the PhD in computer science in 1993. Since then he has been working in the field of parallel and distributed computing. First at EPFL, where he founded and directed the GRIP (Parallel Computing Research Group), then at the University of Applied Sciences of Western Switzerland (HES-SO) in Valais, which he joined in 2000. Since 2003, he has been a full professor at the University of Applied Sciences and Architecture in Fribourg, where he managed the GRID & Cloud Computing Group. Since 2013 he has been co-director of the Institute for Complex Systems (iCoSys). In addition to his teaching activities in computer science, he is actively involved in national and international research projects in the field of parallel and distributed systems and high-performance computing. In 2014, in collaboration with Prof. Jean Hennebert (HES-SO//Fribourg) and Prof. Philippe Cudre-Mauroux (uni. Fribourg) he founded DAPLAB (Data Analysis and Processing Lab). With a model similar to fablabs, DAPLAB aims at facilitating the access for enterprises and universities to emerging technologies in the area of big data and intelligent data analysis.

Laurent Lefevre

INRIA

Laurent Lefevre is a permanent researcher in computer science at Inria (the French Institute for Research in Computer Science and Control) since 2001. He is a member of the Algorithms and Software Architectures for Distributed and HPC Platforms (Avalon) team from the LIP laboratory in Ecole Normale Superieure of Lyon, France. He has organized several conferences in high performance networking and computing and he has been member of several program committees. He has co-authored more than 100 papers published in refereed journals and conference proceedings. His interests include energy efficiency in large-scale distributed systems, high performance computing, distributed computing and networking, high performance networks protocols and services.

Ariel Oleksiak

PNSC

Ariel Oleksiak is a head of the Energy-efficient ICT Department at Poznań Supercomputing and Networking Center (PSNC) in Poznań, Poland. He received his M.Sc. degree in Computer Science, Intelligent Decision Support Systems, from the Poznan University of Technology, Poland in 2001 and PhD in Computer Science from the same institution in 2009. His research interests include mainly energy efficient technologies, distributed systems, resource management & scheduling, and simulations. He has actively contributed to many research projects including coordination of EU-funded projects: CoolEmAll – dealing with energy-efficiency of data centers and M2DC – developing a modular, highly efficient, cost-optimized server architecture composed of heterogeneous microservers. He has been also a member of the management committee of the European COST Actions IC0804. In Nesus he is a chair of the energy-efficiency working group (WG5).

Svetozar Margenov

Institute of Information and Communication Technologies, Bulgarian Academy of Sciences

Svetozar Margenov is a Full Professor in Computational Mathematics at the Institute of Information and Communication Technologies (IICT), Bulgarian Academy of Sciences. He has a PhD in Computational Mathematics (BAS, 1984) and DSc (IICT, 2002). Prof. Margenov is Head of Scientific Computing Department, and Director of IICT. He is coordinator of the Bulgarian NSF Centre of Excellence on “Supercomputing Applications” and coordinator of the National Center for High Performance and Distributed Computing. Prof. Margenov is one of the founders of the Bulgarian section of SIAM, being its first Chairman for the first two mandates. He is also organizer of the highly ranked series of International Conferences on Large Scale Scientific Computations: http://parallel.bas.bg/Conferences/SciCom17/. Prof. Margenov has internationally recognized scientific achievements in the fields of computer modelling, multilevel methods, robust FEM, multilevel PCG solvers, parallel algorithms. He has published more than 150 scientific papers and two monographs. In the past 5 years he has lead 2 national (Bulgarian NSF), 2 FP7 and 1 Horizon 2020 projects. He is member of the editorial boards of several international journals, including: Numerical Linear Algebra with Applications (NLAA), and Scalable Computing: Practice and Experience (SCPE).

 

Leonel Sousa

Universidade de Lisboa – INESC

Leonel Sousa received a Ph.D. degree in Electrical and Computer Engineering (ECE) from the Instituto Superior Tecnico (IST), Universidade de Lisboa (UL), Lisbon, Portugal, in 1996, where he is  Full Professor and currently ECE Department Chair. He is also a Senior Researcher with the R&D Instituto de Engenharia de Sistemas e Computadores (INESCID). His research interests include high performance computing, parallel computing, computer architecture. Dr. Sousa has contributed to more than 250 papers in journals and international conferences, for which he got several awards. He is Fellow of the IET, Distinguished Scientist of ACM and Member of the IFIP Working Group 10.3 on Concurrent Systems.

Sebastien Varrette

University of Luxembourg – UL

Sebastien Varrette is research associate at the University of Luxembourg (UL). Expert in the deployment and management of High Performance Computing (HPC) systems, he is leading with Prof. Pascal Bouvry the developments of the UL HPC platform and the associated expert team of system administrators since 2007.
His main research interests lie in the domains of the security and performance of parallel and distributed computing platforms, such as HPC or Cloud Computing infrastructures.
He is active as general chair, track chair or as scientific committee member for various reference conferences within his area of expertise (IEEE CloudNet, CloudCom, OPTIM, Europar, PCGrid, ICPADS, IPDPS, HPCS etc.) Involved in several technical workgroups (Grid5000, ISO/TC 307 on “Blockchain and distributed ledger technologies”) or EU projects, he also takes part and represents Luxembourg for the management committee of several strategic EU projects, such as PRACE, ETP4HPC or several COST action (for instance IC1305 “Network for Sustainable Ultrascale Computing (NESUS)”. Up to now, Dr. Varrette co-authored four books and more than nine book chapters in Computer Science. He also wrote about 80 research or popularization articles in scientific journals, or international conference proceedings.

 

PANELIST

 

Neki Fraskeri, Polytechnic

University of Tirana, Albania

.Prof. Dr. Neki Frasheri is graduated at Department of Mathematics of the Faculty of Natural Sciences, University of Tirana in 1971-1976. Doctorate Thesis on finite elements applied in plate bending, University of Tirana in 1984-85. Studied on Operating Systems and Computer Networks at Training Centres of BULL HN, Paris France, in 1984-85 and 1988. Lecturer on applied mathematics (finite elements) at Chair of Mathematics and informatics (theory of languages and compilation) at Chair of Informatics in University of Tirana, 1981-1996. System engineer at Institute of Informatics and Applied Mathematics (INIMA) in 1985-1993. Received title “Research Leader (Professor)” from High Council of Attestation in 1994. Vice-director and head of software department of INIMA, 1993-2007. In 2008 elected member of Academy of Sciences of Albania. From 2008 lecturer on distributed systems in Faculty of Information Technology of UPT, and on operating systems in Faculty of Economy, University of Tirana. From 2003 technical leader of local teams in European framework projects SEEREN-1-2, SEE-GRID-1-2-SCI, HP-SEE and VI-SEEM.

 

Javier Garcia-Blas

University Carlos III of Madrid, Spain

Javier Garcia-Blas has been a visiting professor at University Carlos III of Madrid since 2005. He has cooperated in several projects with researchers from various high performance research institutions including HLRS (funded by HPC-Europe program) DKRZ, and Argonne National Laboratory. He is currently involved in various projects on topics including parallel I/O and parallel architectures. He received the MS degree in Computer Science in 2007 at the University Carlos III of Madrid. He also received a PhD in Computer Science from University Carlos III in 2010.

Gabriel Conzalez-Castane

University College Cork, Ireland

Gabriel González Castañé is a Senior Postdoctoral Researcher in University College of Cork. He holds a PhD in Computer science on the topic of Energy Aware Cloud Computing simulations, and a Masters in Distributed Systems. He has participated in several Spanish National Projects and he led a simulation workpackage in CACTOS FP7 project. He was the technical coordinator of CloudLightning H2020 project leading several activities such as Integration and Evaluation, and several technical tasks across workpackages. Currently he is working in Insight-centre at UCC as part of the EU Big Data network team. His interests are simulation and modelling, cloud computing, edge computing and distributed systems at scale.

 

Rafael Mayo

CIEMAT, Spain.

Rafael Mayo García es Investigador Científico en el Centro de Investigaciones Energéticas Medioambientales y Tecnológicas (CIEMAT) y miembro del Instituo de Ciencias de la Compuacion Aplicadas de la Universidad de Harvard. Sus principales líneas de investigación son la computación de altas prestaciones, informática científica y física computacional. Recibió su doctorado por la Universidad Complutense de Madrid, España.

Radu Prodan

University of Innsbruck, Austria

Radu Prodan is Associate Professor of computer science at the University of Innsbruck and recently appointed as Full Professor in distributed systems at the University of Klagenfurt, Austria. His research interests in the areas of parallel and distributed systems comprise programming methods, compiler technology, performance analysis, and scheduling for high-performance scientific computing and industrial online gaming applications. He held previous research positions at ETH Zurich, University of Basel, Swiss Scientific Computing Centre, and University of Vienna. He participated in several national and European projects and is currently coordinating three Austrian projects in the areas of multicore and Cloud computing. Prodan was WP leader in the IST-034601 edutain@grid and 26185 (SHIWA) European projects, and is currently scientific coordinator of the H2020-ICT-2014-1 644179 project ENTICE. Currently he is co-chair of the “state-of-the-art and continuous learning in UCS” working group of the Network for Sustainable Ultrascale Computing (NESUS) COST Action funded by the EU. He is the author of one book, over 150 journal and conference publications, and is the recipient of two IEEE best paper awards.