Category: infrastructure

Call For Proposal For 20 PF Rudra Facility

CALL FOR PROPOSALS FOR COMPUTING TIME ON PARAM RUDRA HPC FACILITY (20 PF)

To encourage the scientists and engineers from the academic institutions and public/ private research labs/ industries (start-ups, MSME) to port their applications to state-of-the-art HPC system in order to open up new perspectives for their research, C-DAC invites the potential users to apply for computing time on PARAM Rudra System For Detailed Proposal Kindly Click And download 20 PF Call for Proposal

PARAM Rudra IIT Patna

About PARAM Rudra

PARAM Rudra, a cutting-edge supercomputing facility, was established under Phase-3 of the National Supercomputing Mission's build approach. It boasts a peak computing power of 838 TFLOPS and was designed and commissioned by C-DAC to meet the computational needs of IIT,Patna and various research and engineering institutes in the region. The system is valuable for research in various scientific domains, including materials science, earth science, chemical and biological sciences, high energy physics, cosmology and astrophysics and more.

System Specifications
Theoretical Peak Floating-point Performance Total (Rpeak) 838 TFLOPS
Base Specifications (Compute Nodes) 2X Intel Xeon GOLD 6240R, 24 Cores, 2.4 GHz Processors per node, 192 GB Memory, 800 GB SSD
Master/Service/Login Nodes 10 nos.
CPU only Compute Nodes (Memory) 96 nos. (192GB)
GPU Ready Nodes (Memory) 26 nos. (192GB)
High Memory Compute Nodes 32 nos. (768GB)
Total Memory 49.536 TB
Interconnect Primary: 100Gbps Mellanox Infiniband Interconnect
Network 100% non-blocking, fat tree topology
Secondary: 10G/1G Ethernet Network Management
Network: 1G Ethernet
Storage 1.0 PiB
CPU Only Compute Nodes
Nodes 96
Cores 4608
Compute Power of Rpeak 353.89 TFLOPS
Each Node with 2 X Intel Xeon GOLD 6240R, 24 Cores, 2.4 GHz
192 GB memory
800 GB SSD
GPU Only Compute Nodes
Nodes 8
CPU Cores 384
Rpeak 275.81 TFLOP
Each Node with 2 X Intel Xeon GOLD 6240R, 24 cores, 2.4 GHz
192 GB Memory
2 x NVIDIA A100
800 GB SSD
High Memory Compute Nodes
Nodes 32
CPU Cores 1536
Compute Power of Rpeak 117.964 TFLOPS
Each Node with 2 X Intel Xeon GOLD 6240R, 24 cores, 2.4 GHz
768 GB Memory
800 GB SSD
GPU Ready Nodes
Nodes 26
CPU Cores 1248
Rpeak 95.846 TFLOP
Each Node with 2 X Intel Xeon GOLD 6240R, 24 cores, 2.4 GHz
192 GB Memory
2 x NVIDIA A100
800 GB SSD

PARAM Rudra Details

Architecture Diagram:

Software Stack:

Installed Applications/Libraries

HPC Applications
  • Bio-informatics: MUMmer, HMMER, MEME, PHYLIP, mpiBLAST, ClustalW
  • Molecular Dynamics: NAMD (for CPU and GPU), LAMMPS, GROMACS
  • CFD: OpenFOAM, SU2
  • Material Modeling, Quantum Chemistry: Quantum-Espresso, Abinit, CP2K, NWChem
  • Weather, Ocean, Climate: WRF-ARW, WPS (WRF), ARWPost (WRF), RegCM, MOM, ROMS
Deep Learning Libraries
  • cuDNN, TensorFlow, Theano
Dependency Libraries
  • NetCDF, PNETCDF, Jasper, HDF5, Tcl, Boost, FFTW

Support

For any support, contact: rudrasupport@iitp.ac.in

PARAM Rudra Usage Report

Link To Be Added

*Note: The above data is coming from C-Chakshu (Multi Cluster Monitoring Platform)

PARAM Rudra IIT, Madras

About PARAM RUDRA

PARAM Rudra, a state-of-the-art supercomputing facility, was developed as part of Phase-3 of the National Supercomputing Mission's build initiative. Built using Rudra servers, which were designed and manufactured in India, it boasts a peak performance of 3.1 PFLOPS. The system was designed and deployed by C-DAC to address the computational needs of IIT, Madras, and other research and engineering institutions in the region. It plays a crucial role in advancing research across multiple scientific fields, with a special focus on enhancing studies in material science and atomic physics.

PARAM RUDRA Details

  • System Specifications
    Theoretical Peak Floating-point Performance Total (Rpeak) 3 PFLOPS
    Base Specifications (Compute Nodes) 2 X Intel Xeon Gold 6240R, 24 Cores, 2.4 GHz, Processors per node, 192 GB Memory, 800 GB SSD
    Master/Service/Login Nodes 20 nos.
    CPU only Compute Nodes (Memory) 473 nos. (192GB)
    GPU Nodes (Memory) 30 nos. (60 NVIDIA A100 PCle)
    GPU Ready Compute Nodes (Memory) 32 nos. (192GB)
    High Memory Compute Nodes 64 nos. (768GB)
    Total Memory 148.312 TB
    Interconnect Primary: 100Gbps Mellanox Infiniband Interconnect network 100% non-blocking, fat tree topology
    Secondary: 10G/1G Ethernet Network
    Management network: 1G Ethernet
    Storage 4.4 PiB
    CPU Only Compute Nodes
    Nodes 473
    Cores 22704
    Compute Power of Rpeak 1743.4 TFLOPS
    Each Node with 2 X Intel Xeon Gold 6240R, 24 cores, 2.4 GHz, processors
    192 GB memory
    800 GB SSD
    GPU Only Compute Nodes
    Nodes 30
    CPU Cores 1440
    Rpeak 924.12 TFLOPS
    Each Node with 2 X Intel Xeon GOLD 6240R, 24 cores, 2.4 GHz, processors
    192 GB Memory
    2 x NVIDIA A100
    800 GB SSD
    GPU Ready Compute Nodes
    Nodes 32
    CPU Cores 1536
    Rpeak 117.952 TFLOPS
    Each Node with 2 X Intel Xeon GOLD 6240R, 24 cores, 2.4 GHz, processors
    192 GB Memory
    800 GB SSD
    High Memory Compute Nodes
    Nodes 64
    CPU Cores 3072
    Compute Power of Rpeak 239.50 TFLOPS
    Each Node with 2 X Intel Xeon Gold 6240R, 24 cores, 2.4 GHz, processors
    768 GB Memory
    800 GB SSD
  • Architecture Diagram:
  • Software Stack:

    • Support

    For any support, contact: rudrasupport@iitm.ac.in

    PARAM Rudra Usage Report

    Link To Be Added

    *Note: The above data is coming from C-Chakshu (Multi Cluster Monitoring Platform)