PRACE Resources

The PRACE RI provides access to distributed persistent pan-European world class HPC computing and data management resources and services. Expertise in efficient use of the resources is available through participating centers throughout Europe.
Available resources are announced for each Call for Proposals.

PRACE Production systems:

• JUGENE

The Gauss Center for Supercomputing IBM Blue Gene/P system JUGENE (Juelicher Blue Gene/P) at Forschungzentrum Juelich (FZJ), Jülich, Germany is the first PRACE system and has been available since July 1, 2010 for successful PRACE resource applications.

JUGENE has a peak performance of 1 Petaflop. It is composed of 294,912 processing cores with 4 cores forming a node with 2 GB of memory for a total of 147 TB.

More information about JUGENE and its usage can be found at JUGENE’s home page.

• CURIE

CURIE, the French Tier0 system, funded by GENCI, installed at TGCC, Bruyères-Le-Châtel, France, designed and built by BULL, is the second PRACE system.

CURIE is based on a modular x86 architecture with a mix of thin, fat and hybrid nodes interconnected through a QDR Infiniband interconnect. It has more than 92 000 processing cores with 4 GB/core for a total of 360 TBytes of distributed memory. The peak performance of the global configuration of CURIE is 2.0 PetaFlops with 105 Teraflops for the fat nodes partition, around 200 Teraflops for the hybrid partition and 1704 Teraflops for the thin nodes partition.

Information on the storage facility associated with CURIE can be found at: http://www-hpc.cea.fr/en/complexe/tgcc-storage-system.htm

More information about CURIE and its usage can be found at: http://www-hpc.cea.fr/en/complexe/tgcc-curie.htm

• HERMIT

The Gauss Center for Supercomputing CRAY XE6 system HERMIT at Hoechstleistungsrechenzentrum Stuttgart (HLRS), Stuttgart, Germany is the third PRACE system and will be available in November 2011 for successful PRACE resource applications. As of now a test- and development system is available.

HERMIT has a peak performance of 1 Petaflop and is designed for sustained application performance and highly scalable applications. It is composed of 3552 dual socket nodes equipped with AMD Interlagos Processors leading to overall 113664 processing cores. Nodes are equipped with 32GB or 64GB main memory. The pre- and postprocessing infrastructure aims to support users with complex workflows and with advanced access methods including remote graphics rendering and simulation steering.

More information about HERMIT and its usage can be found at HERMIT’s platform page

• FERMI

The IBM BG/Q system FERMI installed at CINECA, Bologna, Italy, is the fourth PRACE system and will be available in July 2012 for successful PRACE resource applications.

FERMI is composed of 10.240 PowerA2 sockets running at 1.6GHz, with 16 cores each, for a total of 163.840 compute cores and a system peak performance of 2.1 PFlops. Each processor comes with 16Gbyte of RAM (1Gbyte per core).

More information about FERMI and its usage can be found at: http://www.cineca.it/en/hardware/FERMI