Teach Cluster

The Teach cluster provides dedicated resources for instructional activities. It offers a stable environment for students to learn HPC concepts, run assignments, and develop workflows without competing for resources with production research workloads. No research work permitted on the Teach cluster.

Specifications

Nodes are grouped by partition, in node-number order.

Partition Nodes GPU VRAM GPU/Node --constraint CPU Cores/Node Mem/Node Scratch Network Node Names
cpu 47 -- -- -- -- Intel Xeon Gold 6126 24 192 GB 480 GB NVMe 1GbE teach-cpu-n[0-46]
cpu 1 -- -- -- -- Intel Xeon Gold 6132 28 192 GB 480 GB NVMe 1GbE teach-cpu-n47
gpu 7 NVIDIA GeForce GTX TITAN X 11 GB 4 titanx Intel Xeon E5-2620 12 128 GB 960 GB NVMe 1GbE teach-gpu-n[0-6]
gpu 8 NVIDIA GeForce GTX 1080 8 GB 4 gtx1080 Intel Xeon E5-2620 12 128 GB 822 GB NVMe 1GbE teach-gpu-n[7-14]
gpu 9 NVIDIA GeForce GTX 1080 Ti 11 GB 4 gtx1080 Intel Xeon Silver 4112 8 96 GB 480 GB NVMe 1GbE teach-gpu-n[17-25]
gpu 2 NVIDIA L4 24 GB 8 l4 Intel Xeon Platinum 8592+ 128 512 GB 733 GB NVMe 10GbE teach-gpu-n[15-16]

Additional Features

To request a particular feature (such as a specific GPU type), add the following directive to your job script:

#SBATCH --constraint=l4

Multiple features can be requested by providing a comma-separated list (without intervening spaces).

  • Access for courses


    Notebooks on the Teach cluster for classroom use, in your browser.

    JupyterHub on Teach

  • Request resources


    Choose cores, memory, GPUs, and time for an interactive or batch job.

    Requesting Resources

  • Limits & priority


    QoS walltimes, per-group limits, and how priority is computed.

    Job Scheduling Policy