The objective of the COLOC project is to reduce the time and cost of data transfer among the various processes of a compute and data intensive application. For this, the COLOC program consists on the one side to develop methods and tools enabling to profile applications and to build a hierarchical topology of the infrastructure (hardware resources and communication networks), and on the other side to enable resource and job managers (such as SLURM), as well as MPI libraries, performance analysis tools, and applications themselves to exploit this information (detailed infrastructure topology and execution data flow) in order to optimize the placement of processes and data.

Project partners :   Dassault Aviation, ESI-Efield AB, INRIA, ESI-Scilab Enterprises, FOI (Swedish Defence Research Agency), Teratec, UVSQ (Université de Versailles St-Quentin-en-Yvelines)

EoCoE uses the tremendous potential offered by the ever-growing computing infrastructure to foster and accelerate the European transition to a reliable and low carbon energy supply. EoCoE is assisting this transition via targeted support to four energy pillars: meteorology for energy, materials for energy, hydropower and geothermal energy and nuclear fusion. These four pillars are anchored within a strong transversal multidisciplinary basis providing high-end expertise in applied math and HPC.

Project partners :   ULB - FZJ - MPG - Fraunhauffer / IWES - RWTH - AACHEN - BSC - CEA - CERFACS - CNRS - EDF R&D - INRIA - Météo F / CNRM - UPSud - UVSQ - CYI - CNR - ENEA - UNITN - SUN - UNITOV - PSNC - BATH University

ESCAPE stands for Energy-efficient Scalable Algorithms for Weather Prediction at Exascale. The project will develop world-class, extreme-scale computing capabilities for European operational numerical weather prediction (NWP) and future climate models. The biggest challenge for state-of-the-art NWP arises from the need to simulate complex physical phenomena within tight production schedules. Existing extreme-scale application software of weather and climate services is ill-equipped to adapt to the rapidly evolving hardware. This is exacerbated by other drivers for hardware development, with processor arrangements not necessarily optimal for weather and climate simulations. ESCAPE will redress this imbalance through innovation actions that fundamentally reform Earth system modelling. The project will provide the necessary means to take a huge step forward in weather and climate modelling as well as interdisciplinary research on energy-efficient high-performance computing.

Project partners :   DMI, RMI, MeteoSwiss, DWD, Meteo-France, ICHEC, PSNC, U Lougborough, Atos/Bull, NVIDIA, Optalysy

A main goal of ESiWACE is to substantially improve efficiency and productivity of numerical weather and climate simulation on HPC platforms. Besides, we will establish demonstrator simulations run at highest affordable resolutions (target 1km). This will yield insights into the computability of configurations that will be sufficient to address key scientific challenges in weather and climate prediction. ESiWACE is a project funded by the European Commission under the Horizon 2020 Programme.

Project partners :   European Centre for Medium-Range Weather Forecasts (UK), Co-coordinator, Centre National de la Recherche Scientifique-Institut Pierre Simon Laplace (FR), Max-Planck-Institut für Meteorologie (DE) , Centre Européen de Recherche et de Formation Avancée en Calcul Scientifique (FR), Barcelona Supercomputing Center (ES), Science and Technology Facilities Council (UK), Met Office (UK), University of Reading (UK), Sveriges Meteorologiska och Hydrologiska Institut (SE), National University of Ireland Galway - Irish Centre for High End Computing (IE), Fondazione Centro Euro-Mediterraneo sui Cambiamenti Climatici (IT), Deutscher Wetterdienst (DE), Seagate Systems UK Limited (UK), BULL/ATOS (FR), Allinea (UK)

The INTERTWinE project addresses the problem of programming model design and implementation for the Exascale. Although there remains room for improvement in individual programming models and their implementations, the main challenges lie in interoperability between APIs. It is this interoperability, both at the specification level and at the implementation level, which this project seeks to address and to further the state of the art.

Project partners :   Fraunhofer ITWM (Germany), Barcelona Supercomputing Center (Spain), KTH Royal Institute of Technology (Sweden), German Aerospace DLR (Germany), T-Systems SRF (Germany), UJI - Universitat Jaume-I (Spain), Inria - French National Institute for Computer Science and Applied Mathematics (France), University of Manchester (UK)
        

Since 2011, project Mont-Blanc has been investigating a new type of energy efficient computer architecture for HPC, leveraging ARM processors. Now in its third phase and coordinated by Bull (Atos Group), Mont-Blanc is funded by the EC under the Horizon 2020 program. Its aim is to define the architecture of an Exascale-class compute node capable of being manufactured at industrial scale, while developing the matching software ecosystem.

Project partners :   ARM, AVL, BSC, CNRS/LIRMM, ETHZ, HLRS, University of Cantabria, University of Graz, University of Versailles

The mission of the POP Center of Excellence is to provide expert services to analyse the performance of an application (performance audit), explain its behavior, and propose solutions (recommandations of code modification) that should solve the problems identified during the audit. These services can be delivered to any kind of customer: Industrial, Research Center, University, ... and can be used to analyse proprietary as well as an open source software.

Project partners :  HLRS (High Performance Computing Center Stuttgart of the University of Stuttgart), JSC (Jülich Supercomputing Centre), NAG (Numerical Algorithms Group), RWTH (Rheinisch-Westfälische Technische Hochschule Aachen), Teratec (with 2 third parties: lNRIA and CNRS)"

The goal of the READEX project is to improve energy-efficiency of applications in the field of High-Performance Computing. The project brings together European experts from different ends of the computing spectrum to develop a tools-aided methodology for dynamic auto-tuning, allowing users to automatically exploit the dynamic behaviour of their applications by adjusting the system to the actual resource requirements.

Project partners :  Technische Universität München (TUM), Norwegian University of Science and Technology (NTNU), Innovations National Computing Center (IT4I), National University of Ireland (ICHEC), INTEL, Gesellschaft für numerische Simulation mbH (GNS)

The SAGE project, which incorporates research and innovation in hardware and enabling software, will significantly improve the performance of data I/O and enable computation and analysis to be performed more locally to data wherever it resides in the architecture, drastically minimising data movements between compute and data storage infrastructures. With a seamless view of data throughout the platform, incorporating multiple tiers of storage from memory to disk to long-term archive, it will enable API’s and programming models to easily use such a platform to efficiently utilize the most appropriate data analytics techniques suited to the problem space.

Project partners :  CEA - DFKI - ATOS - DIAMOND - STFC - CCFE - ALLINEA