Educational Cluster

The Research Computing group provides a Redhat Linux based high performance computing environment in support of the educational cirriculum. There are two educational partitions: Centaurus, and GPU. There is 73 TBs dedicated, usable RAID storage (192 TBs raw). For more information on usage, please read the Centaurus/GPU User Notes

Centaurus

The Centaurus partition is dedicated to supporting the integration of HPC resources into the educational cirriculum. It is a traditional batch scheduling environment based on Slurm. It is a scaled down replica of our research computing environment.

10 nodes / 360 compute cores

  • 10 nodes with
    • Dual 18-Core Intel Xeon Gold 6154 CPU @ 3.00GHz (36 cores / node)
    • 388GB RAM (10.7GB / core)
    • 100Gbit EDR Infiniband Interconnect

GPU

The GPU partition is also dedicated to supporting the integration of HPC resources into the educational cirriculum. It is exclusively made up of GPU compute nodes, for use by classes that require GPU computing resources.

6 nodes / 40 NVIDIA GPUs / 72 compute cores

  • 2 GPU nodes with
    • Dual 8-Core Intel Xeon Silver 4215R CPU @ 3.2 GHz (16 cores / node)
    • 192 GBs RAM (12 GBs / core)
    • 100Gbit EDR infiniband interconnect
    • 4 x Nvidia Titan RTX GPU Accelerator w/ 24GB GDDR6 GPU Memory
  • 1 GPU node with
    • Dual 8-Core Intel Xeon Silver 4215R CPU @ 3.2 GHz (16 cores / node)
    • 192 GBs RAM (12 GBs / core)
    • 100Gbit EDR infiniband interconnect
    • 8 x Nvidia Titan V GPU Accelerator w/ 12GB HBM2 GPU Memory
  • 3 GPU nodes with
    • Dual 4-Core Intel Xeon Silver 4112 CPU @ 2.60GHz (8 cores / node)
    • 192GB RAM (24GB / core)
    • 8 x NVIDIA GeForce GTX-1080Ti GPUs w/ 11GB GDDR5X GPU Memory