The fastest Italian cluster based on GPU for industrial and public research

This system is no longer available

The new PLX-GPU supercomputer introduced in June 2011 by SCS S.r.l - SuperComputing Solutions and CINECA is the fastest supercomputer available today to Italian industrial and public researchers. It is ranked at the 82nd position in the top500 (as November 2011), the list of the most powerful supercomputers in the world.
This supercomputer will initially be used to optimize and develop applications targeted at hybrid architectures, leveraging software applications in the fields of computational fluid dynamics, material and life science, and geophysics. The computing system will also been made available to European researchers as a Tier-1 system of the PRACE infrastructure.




Technical References

Model: IBM PLX (iDataPlex DX360M3)
Architecture: Linux Infiniband Cluster
Nodes: 274 IBM iDataPlex M3
Processors: 2 six-cores Intel Westmere 2.40 GHz per node (548 processors, 3288 cores in total)
GPU: 2 NVIDIA Tesla M2070 per node (for 264 nodes) + 2 NVIDIA Tesla M2070Q per node (for 10 nodes) for a total of 548 GPUs
RAM: 48 Gb/node
Internal Network: Infiniband with 4x QDR switches
Disk Space: 100 TB
Operating System: Red Hat RHEL 5.6
Peak Performance: 300 TFlop/s (142 TFlops sustained - Linpack benchmark)
Available compilers: Fortran F90, C, C++ (intel, pgi and gnu suites)
Parallel libraries: MPI, OpenMP