/
AI Supercomputer

AI Supercomputer

Owned by Karker, Nicholas
Last updated: Feb 06, 2025
2 min read

The AI Supercomputer runs intensive machine learning and deep learning workloads. It consists of on-premise NVIDIA DGX systems (sometimes referred to as the DGX On-Prem system) to run these workloads in a highly scalable fashion. By requesting access to the system, users will be able to run Jupyter notebooks, JupyterLab, as well as Python scripts that are particularly GPU-intensive. Additionally, any of the available containers that are provided by NVidia on the DGC Cloud can be pulled and used with the system.

Features

  • 24 NVIDIA DGX A100 systems (each with 8 NVIDIA A100 GPUs)

  • 3 Lambda scalers (each with 8 NVIDIA L40s) 

  • Over 6 petabytes of NetApp storage

  • Paid, prioritized GPU access

Available to

UAlbany Researchers

Access Tiers & Pricing

Two tiers of access are offered to accommodate different research needs:

1. Free Tier Access

  • Cost: No charge for UAlbany faculty

  • Access to GPU resources on a first-come, first-served basis

  • Workloads may be preempted by prioritized jobs

  • Suitable for research projects with flexible timelines

  • Full access to all system features and containers

2. Prioritized Access

  • Cost: $1,200 annually per prioritized GPU

  • Priority scheduling of your workloads over free-tier jobs

  • Predictable resource allocation for time-sensitive research projects

Request access

1. Complete the Research Storage Request Form to provision your lab directory.

2. Complete the DGX On-Prem Computation Request form for access to the NVIDIA On-Prem resources.

More Information

  • Documentation about how to use the NVIDIA on-premise system is present on the DGX On-Prem How-To page 

  • Tutorials for running AI workloads are available here.

  • For more information on AI Plus Supercomputing Cluster, contact the ITS Service Desk