TECHNIQUES AND APPLICATIONS FOR
To be held at EUROPAR 2014, Porto, Portugal , August 25-26, 2014
Invited Speaker: Dr. Isabelle Perseil. Head of the Computational Science Coordination at Inserm (CISI). INSERM, FRANCE
At INSERM (15 000 people, 300 research units), the french National Institute of Health and Medical Research, the computational science coordination implements an efficient strategy for sharing the data and the computing resources, which relies on an intensive use of VREs (Virtual Research Environments). Virtual research environments are ecosystems that are providing software, data, system and administration resources to users via a web interface. They allow for more efficient collaboration between research teams, through the concept of communities and they allow to share data and computing resources. They can hide the heterogeneity of e-infrastructures (e-infrastructures are the foundation for these environments: hardware/software and networks) and they aim at providing a single access though a web portal, therefore, as frameworks, they improve the access and re-use of data, resulting in higher productivity of our researchers. Moreover, innovation is accelerated via access to integrated digital research resources across disciplines, thanks to web services composition and orchestration. We will illustrate these concepts with concrete case studies borrowed from the medical imaging and bioinformatics fields.
The PerSyst Monitoring tool. A transport system for performance data using quantiles.
A Cloudification Methodology for Numerical Simulations
Paralldroid: Performance analysis of GPU executions
Accurate blind predictions of OpenFOAM energy consumption using the LBM prediction model
High-Level Topology Oblivious Optimization of MPI Broadcast Algorithms on Extreme-Scale Platforms
The ever-increasing data and processing requirements of applications from various domains are constantly pushing for dramatic increases in computational and storage capabilities. Today, we have reached a point where computer systems’ growth cannot be addressed anymore in an incremental way, due to the huge challenges lying ahead, in particular scalability, energy barrier, data management, programmability, and reliability.
Ultrascale computing systems (UCS) are envisioned as a large-scale complex system joining parallel and distributed computing systems, maybe located at multiple sites, that cooperate to provide solutions to the users. As a growth of two or three orders of magnitude of today’s computing systems is expected, including systems with unprecedented amounts of heterogeneous hardware, lines of source code, numbers of users, and volumes of data, sustainability is critical to ensure the feasibility of those systems. Due to those needs, currently there is an emerging cross-domain interaction between high-performance in clouds or the adoption of distributed programming paradigms, such as Map-Reduce, in scientific applications, the cooperation between HPC and distributed system communities still poses many challenges towards building the ultrascale systems of the future. Especially in unifying the services to deploy sustainable applications portable to HPC systems, multi-clouds, data centers, and big data.
TASUS workshop focuses on the software side, aiming at bringing together researchers from academia and industry interested in the design, implementation, and evaluation of services and system software mechanisms to improve sustainability in ultrascale computing systems with a holistic approach.
We are looking for original high quality research and position papers on applications, services, and system software for sustainable ultrascale systems. Topics of interest include:
- Existing and emerging designs to achieve sustainable ultrascale systems.
- High-level parallel programming
tools and programmability techniques to improve applications sustainability
- Synergies among emerging
programming models and run-times from HPC, distributed systems, and big data
- New energy efficiency techniques
for monitoring, analyzing, and modeling ultrascale systems, including energy
- Eco-design of ultrascale
components and applications, with special emphasis on energy-aware software
- Sustainable resilience and fault-tolerant mechanisms that can cooperate throughout the whole software stack to handle errors.
- Fault tolerance techniques in partitioned global address space (e.g. PGAS, MPI, hybrid) and federated cooperative environments.
- Data management optimization
techniques through cross layer adaptation of the I/O stack to provide global
- Enhanced data management lifecycle on scalable architectures combining HPC and distributed computing (clouds and data centers).
- Experiences with applications, high-level algorithms, and services amenable to ultrascale systems.
Š Workshop papers due: May 30, 2014
Š Workshop author notification: July 4, 2014
Š Workshop early registration: July 25, 2014
Š Workshop camera-ready papers due: October 3, 2014
Prof. Jesus Carretero. University Carlos III of Madrid. Spain.
Dr. Laurent Lefevre. INRIA, ENS of Lyon. France
Prof. Gudula Rünger. Technical University of Chemnitz. Germany.
Prof. Domenico Talia. Universitá della Callabria. Italy.
Francisco Almeida. Universidad de la Laguna. Tenerife. Spain.
Angelos Bilas. ICS. FORTH. Greece.
Harold Castro. Universidad de los Andes. Colombia.
Alok Choudhary. Northwestern University. USA.
Raimondas Ciegis. Vilnius Gediminas Technical University. Lithuania.
Michele Colajanni. Universitą di Modena e Reggio Emilia. Italy
Toni Cortes. BSC. Spain.
Georges DaCosta. Université Paul Sabatier. Tolouse 3. France.
Jack Dongarra. University of Tennessee. USA.
Skevos Evripidou. University of Cyprus. Cyprus.
Thomas Fahringer. University of Innsbruck. Austria.
Sonja Filiposka. University of Ss Cyril and Methodius. FYR Macedonia.
Javier Garcia-Blas. University Carlos III of Madrid. Spain.
Jose D. Garcia. University Carlos III of Madrid. Spain.
Florin Isaila. Argonne National Labs. USA.
Emmanuel Jeannot. INRIA Bordeaux Sud-Ouest, France.
Helen Karatza. Aristotle University of Thessaloniki. Greece.
Alexey Lastovetsky. University College Dublin. Ireland.
Dimitar Lukarski. Uppsala University. Sweden.
Pierre Manneback. University of Mons. Belgium.
Svetozar Margenov. Bulgarian Academic of Sciences. Bulgaria.
Attila Marosi. Hungarian Academy of Sciences. Hungary.
María José Martín Santamaría. University of CoruĖa. Spain.
Anastas Mishev. University of Ss Cyril and Methodius. FYR Macedonia.
Ricardo Morla. Universidade de Porto. Portugal.
Maya Neytcheva. Uppsala University. Sweden.
Ariel Oleksiak. Poznan Supercomputing Center. Poland.
Dana Petcu. West University of Timisoara. Romania.
Jean Marc Pierson. Université Paul Sabatier. Tolouse 3. France.
Radu Prodan. University of Innsbruck. Austria.
Gudula Ruenger. Technische Universität Chemnitz .Germany.
Enrique S. Quintana-Orti. Universitat Jaume I. Spain.
Thomas Rauber. University of Bayreuth. Germany.
Karolj Skala. Ruđer Bošković Institute. Croatia.
Victor J. Sosa. CINVESTAV. Mexico.
Leonel Sousa. INESC. Portugal.
Roman Trobec. Jozef Stefan Institute. Slovenia.
Trinh Anh Tuan. Budapest University of Technology and Economics. Hungary.
Eero Vainikko. University of Tartu. Estonia.
Pascal Bouvry. University of Luxembourg. Luxembourg.
Roman Wyrzykowski. Czestochowa University of Technology. Poland.
Laurence T. Yang. St.Francis University. Canada.
Julius Zilinskas. Vilnius University. Lithuania.
Albert Zomaya. University of Sydney. Australia.
Paper submission guidelines
Full papers should not exceed 12 pages in the Springer LNCS style. The usage of LaTeX for preparation of the contribution as well as the submission in camera ready format is strongly recommended. The 12 pages limit is a hard limit. It includes everything (text, figures, references) and will be strictly enforced by the submission system. Download LNCS Latex style HERE.
Paper submission has to be performed electronically via the conference Web site in PDF format. Papers accepted for publication must also be supplied in source form (LaTeX). Use the PAPER SUBMISSION ONLINE SYSTEM to submit a paper.
Papers must offer original contributions regarding the theory and practice of parallel and distributed computing. Full submission guidelines are available on the conference website. Only contributions not submitted elsewhere for publication will be considered.
Workshop proceedings will be published in a separate LNCS Euro-Par 2014 volume after the conference. Authors of accepted papers will be requested to sign a Springer copyright form.
Journal special issue
Extended versions of distinguished selected papers accepted and presented in TASUS 2014, after further revisions, will be published in special issues of the journal Concurrency and Computation: Practice & Experience ( CCPE ) that is indexed in JCR.
Mail to: firstname.lastname@example.org