H.P.C

CCF-HPC

  • HPC has the ability to process data and perform complex calculations at high speeds for scientific research.
  • HPC facility has a total of 400 CPU Cores comprised of 8 compute nodes and 2 GPU nodes that provide the performance of 25.6 TFLOPS and 29.8 TFLOPS Rpeak respectively.
  • The upper memory limit of 1920 GB RAM along with a 120 TB SAS-based storage system.
  • The nodes are connected with InfiniBand interconnect to support more tightly coupled parallel applications.

CCF-Virtualization

  • The Virtualization cluster will help to create and host new servers with the desired web services for the betterment of the Institute facilities.
  • Virtualization Cluster is divided into categories i.e. Gold (4 Nodes) and a Silver (9 Nodes) clusters having Dual Intel Xeon gold 5220 (18 cores x2 i.e.Total cores 36, Memory 256 GB / node) with 2.20 GHz frequency and Dual Intel Xeon Silver 4214 (12 cores x2 i.e. Total 24 cores, Memory 192 GB / node) with 2.20 GHz frequency respectively.

CCF-DGX A100

  • ​Universal system for all kinds of AI workloads—from analytics to training to inference.
  • Compute density of packing 5 petaFLOPS of AI performance or 10 petaOPS INT8 into a 6U form factor.
  • GPUs: 8x NVIDIA A100 Tensor Core GPUs.
  • GPU Memory: 40 GB x 8 i.e. 320 GB in total.
  • System Memory: 1TB.
  • System Storage: OS: 2x 1.92TB M.2 NVME drives Internal Storage: 15TB (4x 3.84TB) U.2 NVME drives.

Central Computting Facilities MANIT Bhopal