The Clark Science Center’s Computing and Technical Services group (CATS) maintains and supports an on-campus High Performance Computing (HPC) infrastructure consisting of three separate offerings described below.  CATS is also affiliated with the Massachusetts Green High Performance Computing Center (MGHPCC) in Holyoke, MA, and we are exploring an arrangement with the UNITY at UMass, enabling us to leverage additional computing resources as needed.

  1.  A Virtual HPC cluster consists of three Dell HPC Virtual Machine (VM) hosts. The virtualization and higher amount of RAM on the three VM hosts allow the flexibility of running either Windows or Linux VMs at the same time. This permits us to allocate only the resources that are needed. 
      • HPC-VM1 Server: 512GB RAM, 2 processors with 18 cores (72 total) 
      • HPC-VM2 Server: 512GB RAM, 2 processors with 18 cores (72 total), 1 NVIDIA Tesla M60 GPU with 16GB of Ram and 4096 GPU cores.
      • HPC-VM3 Server: 2TB RAM, 2 processors with 26 cores (104 total)

 

  1. A Bright Cluster consists of a management node, login node, twelve compute nodes, one RAM node and a GPU node. Software is loaded onto the management node by CATS using the EasyBuild module manager and shared throughout the compute nodes.  The cluster uses the Slurm Workload Manager to schedule and run the jobs. The Bright infrastructure is fully scalable and can accommodate additional compute nodes as needed.
      • Management Node: 384GB RAM, 2 processors with 32 cores
      • Login Node: 1024GB RAM, 2 processors with 32 cores
      • Compute Nodes (12): 192GB RAM, 2 processors with 32 cores each
      • RAM Node: 1500GB RAM, 2 processors with 35 cores each
      • GPU Node: 256GB RAM (8x32GB), 2 processors with 32 cores, 2 NVIDIA A100 GPU with 80GB of RAM and 6192 GPU cores each.

 

  1. A high-end Mac server for macOS specific software.
      • HPC-MAC: 384GB RAM, 2.5GHz 28‑core Intel Xeon W processor, Radeon Pro W5700X 16GB of GDDR6 memory 
    •  

Cluster management tools:  Hadoop, VMware, Bright Computing, Slurm, Easybuild

Current Uses

Bioinformatics
Biopython (https://biopython.org/)
DendroPy (https://dendropy.org/)
P4 (http://p4.nhm.ac.uk/)
Bioperl (https://bioperl.org/)
MAFFT (https://mafft.cbrc.jp/alignment/software/)
USEARCH (https://www.drive5.com/usearch/)
Guidance (http://guidance.tau.ac.il/)
trimAl (http://trimal.cgenomics.org/)
RAxML (https://cme.h-its.org/exelixis/web/software/raxml/index.html)
wt2dbg (https://github.com/ruanjue/wtdbg2/)
ABySS (https://www.bcgsc.ca/resources/software/abyss)

Other Computational Software

    • Biology — bioinformatics and genetic analyses using: Seqman NGen, Muscle, SOAPDenovo, SPAdes and other packages
    • Chemistry — calculational chemistry using: Gaussian, ORCA, ADF
    • Economics — Monte Carlo and other modeling simulations using: Matlab, Mathematica, NetLogo, Stata
    • Engineering —  modeling using Ansys
    • Physics — Monte Carlo simulations using: Matlab
    • Statistics and Data Sciences — R