SAGEProject ID: 671500
Gesamtkosten:EUR 7 882 531,25
EU-Beitrag:EUR 7 882 531
Koordiniert in:United Kingdom
Thema(en):FETHPC-1-2014 - HPC Core Technologies, Programming Environments and Algorithms for Extreme Parallelism and Extreme Data Applications
Aufruf zur Vorschlagseinreichung:H2020-FETHPC-2014See other projects for this call
Finanzierungsprogramm:RIA - Research and Innovation action
Worldwide data volumes are exploding and islands of storage remote from compute will not scale. We will demonstrate the first instance of intelligent data storage, uniting data processing and storage as two sides of the same rich computational model. This will enable sophisticated, intention-aware data processing to be integrated within a storage systems infrastructure, combined with the potential for Exabyte scale deployment in future generations of extreme scale HPC systems.
Enabling only the salient data to flow in and out of compute nodes, from a sea of devices spanning next generation solid state to low performance disc we enable a vision of a new model of highly efficient and effective HPC and Big Data demonstrated through the SAGE project.
- Provide a next-generation multi-tiered object-based data storage system (hardware and enabling software) supporting future-generation multi-tier persistent storage media supporting integral computational capability, within a hierarchy.
- Significantly improve overall scientific output through advancements in systemic data access performance and drastically reduced data movements.
- Provides a roadmap of technologies supporting data access for both Exascale/Exabyte and High Performance Data Analytics.
- Provide programming models, access methods and support tools validating their usability, including ‘Big-Data’ access and analysis methods
- Co-Designing and validating on a smaller representative system with earth sciences, meteorology, clean energy, and physics communities
- Projecting suitability for extreme scaling through simulation based on evaluation results.
Call Alignment: We address storage data access with optimised systems for converged Big Data and HPC use, in a co-design process with scientific partners and applications from many domains. System effectiveness and power efficiency are dramatically improved through minimized data transfer, with extreme scaling and resilience.
EU-Beitrag: EUR 2 587 061
PO9 1SA HAVANT
EU-Beitrag: EUR 770 450
WARWICK TECHNOLOGY PARK
CV34 6UW WARWICK
EU-Beitrag: EUR 916 900
RUE JEAN JAURES 68
78340 LES CLAYES SOUS BOIS
EU-Beitrag: EUR 248 750
CULHAM SCIENCE CENTRE
OX14 3DB ABINGDON
EU-Beitrag: EUR 974 245
RUE LEBLANC 25
75015 PARIS 15
EU-Beitrag: EUR 675 000
TRIPPSTADTER STRASSE 122
EU-Beitrag: EUR 248 750
Diamond House, Harwell Science & Innovation Campus
0X11 0DE DIDCOT
EU-Beitrag: EUR 711 260
WILHELM JOHNEN STRASSE
EU-Beitrag: EUR 501 875
100 44 STOCKHOLM
EU-Beitrag: EUR 248 240
Polaris House North Star Avenue
SN2 1SZ SWINDON