Central Computing Facilities

The HPC Facility (SURYA) has 16 CPU (640 cores) compute node clusters and 4 GPU (160 cores with 2×4 Nvidia Tesla-V100 having 40,960‬ CUDA core) node clusters along with 8.5TB of RAM. The BigData Facility (DHYAN) has 20 CPU (800 cores) data node clusters with 8TB of RAM and ~250 TB of HDFS Storage. HPC and BigData Facility usage General Parallel File System (GPFS) for storage (~450TB) connected via Mellanox 56Gb/s passive copper cables (15 GBps throughput) based on DDN GRIDScaler Storage. Cloud Facility has 6 cloud nodes (240 cores), 2.3TB of RAM with 150TB of storage. The CCF facility has 100 Gbps inter-connectivity, 10 Gbps external-connectivity and 2x100KVA UPS backup. Two additional servers has been set up for Virtual Machine – HP DL580 having 4 socket 92 core and Nvidia Tesla-M60 with 40TB of storage and HP DL380 having 24 core and 2x Nvidia Quadro M6000 with 4TB of storage.