Fourteen PRACE members collaborated in the Preparatory Phase (PRACE-PP) project that complemented the national investments to accelerate the deployment of the PRACE service to users from academia and industry.
Start date: 01/01/2008
Duration: 30 months
Budget: 20.1 €M
EC contribution: 9.98 €M
Grant agreement number: RI-211528
Building a world-class pan-European High Performance Computing (HPC) Service was a highly ambitious undertaking that involved governments, funding agencies, centres capable to host and manage the supercomputers, and the scientific and industrial user communities with leading edge applications. In contrast to Research Infrastructures that focus on a single scientific instrument an HPC Infrastructure has two unique characteristics: supercomputers serve all scientific disciplines and Tier-0 supercomputers have a three year investment cycle as Tier-0 implies leading edge services. This requires a periodic renewal of the Tier-0 systems and a continuous upgrade of the infrastructure. Furthermore, novel architectures and system designs will be created by the vendors for leadership systems. At any given time there will be between three and five different systems each of them serving a particular application spectrum best. This fact mandated a distributed Research Infrastructure, since no single site can host all the necessary systems because of floor space, power, and cooling demands. PRACE, the Partnership for Advanced Computing in Europe, had the overall objective to create the prerequisites for such a pan-European HPC service satisfying the objectives mentioned above and to move into the implementation phase as early as end of 2009, beginning of 2010.
The infrastructure was complemented with network and grid access, and the services required to enable applications. These included development of parallel application software expertise, packages, and data handling. It was build on the partners’ experience and used concepts and services from EC-funded projects such as GÉANT2 and DEISA. The partnership collaborated with the European IT-industry to influence the development of emerging technologies and components for architectures promising for Petaflop/s systems and procurable after 2010.
During the two year project period the following work was carried out to prepare the creation of the permanent PRACE Research Infrastructure:
- PRACE selected an appropriate legal form for the permanent Research Infrastructure, defined its statutes, and its governance in relation with the partners, the European Commission and the scientific users. The targets were signature ready contracts.
- The project established funding strategies and usage models.
- PRACE defined a peer review process to support leading edge science and optimal use of the resources ensuring open, fair and unbiased access to the Research Infrastructure.
- The project defined a consistent operational model across the distributed Tier-0 sites.
- The PRACE project was managed using principles suitable for the permanent infrastructure.
- It focused on dissemination of project achievements, establishing and maintaining links with selected industries both as users of capability systems, technology providers, and creators of new technologies with HPC, and training of potential users.
Joint Research activities
- PRACE performed accompanying technical work to prepare for the production phase. It provided the tools for a consistent management of the tier-0 systems and for the integration of the tier-0 infrastructure into the European HPC ecosystem.
- The project deployed prototypes of leadership class systems at selected sites that were likely to become production level systems in 2009/2010.
- Selected applications were ported, optimized and petascaled to ready them for production on the tier-0 systems.
- A Benchmark suite was created.
- PRACE defined a consistent procurement strategy, associated technical specification, and selection criteria for the current and future generations of HPC services, and the requirements for the physical infrastructure to host tier-0 systems.
- The project started a permanent process of technology evaluation to transform user requirements into specifications for future leadership class systems. This process lasting throughout the lifetime of the infrastructure was done in close relations with vendors of components, systems, and software.
The project was managed by Forschungszentrum Jülich (FZJ).
Collaboration with other EC funded projects
- FZJ – Forschungszentrum Jülich GmbH (Germany, Coordinator)
- USTUTT-HLRS – Universitaet Stuttgart (Germany)
- BADW-LRZ – Bayerischen Akademie der Wissenschaften (Germany)
- GENCI – Grand Equipement National de Calcul Intensif (France)
- EPSRC – The Engineering and Physical Sciences Research Council (United Kingdom)
- BSC – Barcelona Supercomputing Center – Centro Nacional de Supercomputacion (Spain)
- CSC-Tieteellinen Laskenta OY (Finland)
- ETHZ – Eidgenössische Technische Hochschule Zuerich (Switzerland)
- NCF – Stichting Nationale Computerfaciliteiten (The Netherlands)
- JKU – Johannes Kepler Universitaet Linz (Austria)
- SNIC – Vetenskapsradet (Sweden)
- CINECA Consorzio Interuniversitario (Italy)
- PSNC – Instytut Chemii Bioorganicznej Pan WPoznaniu (Poland)
- SIGMA – UNINETT AS (Norway)
- GRNET – Greek Research and Technology Network S.A. (Greece)
- UC-LCA – Faculdade de Ciencias e Tecnologia da Universidade de Coimbra (Portugal)