Pico

Pico located at Cineca in Italy.
How to get access to Pico
CINECA

Pico at CINECA

Architecture  Linux Infiniband Cluster
System configuration 74 nodes with in total 1080 cores

51 compute nodes with 20 cores each and 128 GB memory. Processor: Intel Xeon (Ten-Core) E5-2670v2 2.50 GHz
A standard scientific computational environment, pre-installed applications  in the visualization domain, as well as data analysis, post-processing and bioinformatics; access via ssh; submitting of large analysis in a PBS batch environment

2 big memory Nodes: two nodes, big1 and big2, equipped with 32 cores and 0.5 TB/ 40 cores -and1 TB of RAM for specific activities, which require a remarkable quantity of memory. Both are HP DL980 servers. Can be accessed upon request.

  • Big1 node: 8 Quad-Core ARK Intel(R) Xeon(R) E7520 processors with a clock of 1.87GHz and 512 GB of RAM, and a NVIDIA Quadro 6000 graphics card.
  • Big2 node: 4 Ten-Core Intel(R) Xeon(R) E7-2860 with a clock of 2.26GHz  and 1024 GB of RAM.

Viz nodes: 2 x (20 core, 128 GB memory, 2 x GPU NVIDIA K40) + 2 x (16 core, 512 GB memory, 1 x GPU NVIDIA K20); remote visualization environment is defined on this partition, taking advantage from the large memory and the GPU acceleration.

BigInsights nodes: 4 x 16 core nodes, 64 GB memory/node, 32 TB local disk space/node + 1 x 20 core node, 128 GB memory); IBM solution for Hadoop applications is available; InfoSphere BigInsights is available for special projects to be agreed upon with our staff.

Other nodes: 13 x 20 core nodes, 128 GB memory; used for internal activities in the domain of Cloud computing, large Scientific Databases, hadoop for science. Special projects can be activated on this partition, selected by special calls.

Operating system  Linux
Job scheduler  PBS
Login nodes 2 x 20 core nodes, 128 GB memory.
Both nodes are reachable through the following URL: login.pico.cineca.it
More information  http://www.hpc.cineca.it/content/pico-user-guide
Contact  Giovanni Erbacci (g.erbacci@cineca.it)