Great Lakes Cluster

Service Description 

High-performance computing is essential to many researcher’s work. To support this need, ITS Advanced Research Computing (ARC) offers the Great Lakes Cluster, the university’s flagship open-science, high-performance, high-throughput, computing cluster. It’s as much at 10 times faster than its predecessor, Flux. There are hundreds of nodes and approximately 13,000 cores in this system, and it can expand to hundreds more depending as needed. The Great Lakes Cluster is available to researchers on all U-M campuses: UM-Ann Arbor, UM-Flint, UM-Dearborn, and Michigan Medicine.

Compliance 

Applications and data are protected by secure physical facilities and infrastructure as well as a variety of network and security monitoring systems. These systems provide basic but important security measures including:

  • Secure access. All access to the Great Lakes Cluster is via SSH or Globus. SSH has a long history of high-security (OpenSSH Features).
  • Built-in firewalls. All of the Great Lakes Cluster servers have firewalls that restrict access to only what is needed.
  • Unique users. The Great Lakes Cluster adheres to the university guideline of one person per login ID and one login ID per person.
  • Multi-factor authentication (MFA). For all interactive sessions, the Great Lakes Cluster requires a UMICH (Level-1) password plus two-factor authentication (Duo). File transfer sessions require a UMICH password.
  • Private subnets. Other than the login and file transfer computers that are part of the Great Lakes Cluster, all of the computers are on a network that is private within the university network and are unreachable from the internet.
  • Flexible data storage. Researchers can control the security of their own data storage by securing their storage as they require and having it mounted via Network File System (NFS) v3 or v4 on the Great Lakes Cluster. Another option is to make use of the Great Lakes Cluster’s local scratch storage, which is considered secure for many types of data.