CRS4 offers high-performance computing support to the scientific community and industry through the its constantly updated computing center.
The CRS4 computing center, in the various active clusters, includes over 400 computing nodes, for a total of over 5500 cores.
Available clusters
- Dell cluster, 16 compute nodes with Infiniband EDR 100 Gbps
- Huawei cluster, 32 nodes with Infiniband FDR 56 Gbps
- Joint Innovation Center (JIC) cluster, a total of 104 compute nodes with Infiniband FDR 56 Gbps and 10 Gbps Ethernet; this cluster groups hpc compute nodes, Big Data nodes and GPU compute nodes (with Nvidia Kepler K40)
- Dell GPU cluster, 10 nodes with Infiniband FDR 56 Gbps and GPU AMD firepro
- Supermicro hybrid cluster, 10 nodes with Infiniband QDR 40 Gbps and dual Nvidia Kepler K10 or Intel Phi accelerator
- Supermicro GPU cluster, 6 nodes with Infiniband FDR 56 Gbps with GPU Nvidia Kepler K40
- HP Cluster, 256 nodes with Infiniband DDR 20 Gbps
- Access and interactive nodes, graphical nodes and service nodes
Our newer most significant HPC acquisitions is a 16 nodes Dell cluster, based on Sky Lake architecture Xeon Gold 6142, with Infiniband EDR 100 Gbps and 10 Gbps Ethernet.
For more information, please visit the sector Computational Infrastructure and Smart Projects page.