Two computers provide CERFACS with an aggregate peak capacity of about 600 Tflop/s for processing our main simulation requirements. To these internal resources are added those of our partners (Meteo-France and CCRT). To afford an additional Support to our research activities (thesis and ANR projects), the resources allocated through Genci’s calls on the three national centers (Cines, Idris and CCGT) significantly extend our academic resources. These resources are complemented by our participation in international calls (ex. Prace and Incite programs).
CERFACS Internal resources
The Nemo cluster includes 288 compute nodes, each of them with two Intel E5-2680 processors (12 cores haswell processor at 2.5 Ghz) and 64 GB DDR4 memory.
The 288 node of this “compute partition” are completed by 12 post-processing nodes with 256 GB memory and one node with 512 GB memory used for large mesh generation.
A for nodes partition of Intel Knight Landing processors allow researchers to port and optimize their codes in this environment.
The interconnection network is a non-blocking FDR Infiniband network. An internal GPFS file system offers to users a 0.5 PO scratch dir capacity. Software environment includes intel development compilers, libraries and tools; TotalView and DDT debuggers; and SLURM job manager. Integrated by Lenovo and serviware, this cluster has been inaugurated on September 30th, 2015.
The Kraken cluster includes 119 compute nodes, each of them with two Intel Xeon Gold 6140 processors (18 cores skylake processor at 2.3 Ghz) and 96 GB DDR4 memory.
The 119 node of this “compute partition” are completed by 3 post-processing nodes with 384 GB memory with a Nvidia Tesla M60 and one node with 768 GB memory used for large mesh generation.
The interconnection network is a non-blocking Omnipath Network. An internal GPFS file system offers to users a 0.25 PO scratch dir capacity. Software environment includes intel development compilers, libraries and tools; TotalView and DDT debuggers; and SLURM job manager. Integrated by Lenovo and serviware, this cluster is in production mode since May 2018.
Central NAS Server
A central NFS server with a capacity of 1.2 PO is accessible from all clusters and workstations. Its function is to provide a secondary archiving service used by internal and external servers hosting the results of numerical simulation. This technical solution is supported by a 2 LENOVO GPFS Servers associated to a DDN SFA7700 storage solution.
Support for technology watch activities
Technology partners support our technology watch activities through the provision of resources:
- two Intel Xeon-PHI platforms (KNC & KNL) made available by Intel Corporation as part of Intel Parallel Computing Centers programs.
- an ARM server loaned by Lenovo
These resources allow us to carry our solvers on these new technologies with the support of our technology partners.
Météo-France and CEA CCRT extend our simulation capacity through the access to their supercomputers. Through numerous collaboration and support of Genci, Prace and Incite CERFACS accesses multiple external computers. Genci allows our doctoral students to access national resources centers:
- Bull Occigen (3.5 PFlop / s – 36 ° in the Top 500 global ranking of June 2015) at CINES
- IBM iDataPlex (233 Tflop / s) and BG / Q (1.3 Pflop / s – 60 ° in the Top 500 global ranking of June 2015) with Idris
- Bull Curie (1.6 PFlop / s – 44 ° in the Top 500 global ranking of June 2015) at the CEA
Prace attributes the resources to support our borders simulations:
- Fermi: IBM BG / Q (2 PFlop / s – 32 ° in the Top 500 global ranking of June 2015) to CINECA
- Curie: BULL (1.6 Pflop / ss – 33 ° in the Top 500 global ranking of June 2015) at the CEA