Getting Started at the Center for High Performance Computing

1

Accounts

To get started, apply for a CHPC account using our online application form. 

Note: You must be provisioned at the University of Utah campus level with a valid, active uNID (University of Utah ID number) in order to be provisioned at CHPC. Visit our Accounts page for more information on how to obtain a uNID and managing your account.

2

Logging in

After creating your account, connect to a cluster. Here are a few ways to log in:  

• Connecting to Linux systems
  • SSH
    • SSH is a common method for logging into a node if you are familiar with using a command line.
  • FastX
    • Similar to the SSH method; however, FastX can support graphical software, in a web browser or it can be installed on your computer.
  • Open OnDemand
    • Open OnDemand, which works in your web browser, includes many commonly used graphical applications; this is a great way to interact with the CHPC’s resources, especially if you are not yet comfortable with the command line.
• Connecting to Windows systems (Beehive/Narwhal)
  • Using a remote desktop connection, Beehive (for the general environment) and Narwhal (for the PE (protected environment)) allow users to access CHPC resources, such as files and statistical desktop applications, within a familiar Windows environment.

For more information, visit our Accessing CHPC Resources page.

3

Storing Files

Most CHPC users will be interested in the following storage options:

• Home directories. By default, every CHPC user has 50 GB of home directory space. Research groups may purchase home directory space, which includes backups to archive storage.
  

  Home directories are not backed up by default. Only purchased home directory space includes backups to the VAST storage system. More information about purchasing space and backups is available on our Storage page.

• Group Space. Group storage is available for purchase at CHPC for both general and protected environments. Shared storage, like the home directory space, is not designed for running jobs like the Scratch Space.
• Scratch Space. Scratch space is available to all users; there is no cost to use it. Scratch space is used for the storage of intermediate files while a job is running. Files are removed if they have not been accessed within 60 days. The scratch space is not backed up.

CHPC has dedicated data transfer nodes so you can transfer data at high speed.

Here are the different methods you can use to transfer data through the data transfer nodes:

• Rclone. Command-line tool that lets you easily transfer and sync files between your computer and various cloud storage services, such as Google Drive, Box, Dropbox, and S3-compatible providers.
• Globus. Provides tools for efficient and secure data transfers, enabling parallel, load-balanced, and fault-tolerant data movement.
• SCP. Linux command-line tool used to securely transfer files on CHPC's interactive nodes or on a Data Transfer Node (DTN).

4

Accessing Software

You can utilize Modules to load or unload software needed to run your programs into the environment. Details on available software and usage instructions are available on our Software page. 

5

Running a Job on Slurm

Slurm is the cluster's job scheduling system. All large computational workloads are managed through Slurm. Access our Slurm documentation to learn how to write scripts for scheduling your job to the cluster.

6

Knowing your Allocation

To conduct research on the Granite, Notchpeak, and Redwood clusters at the CHPC with priority access to CHPC-owned nodes, an allocation is required. To find out what resources you can access, type 'mychpc batch' command in your terminal after logging in to a cluster. Older clusters (Kingspeak and Lonepeak) in the General Environment do not require allocation.

7

Training and support

We understand that our users come from different academic backgrounds and have different levels of experience with research computing. Regardless of whether you’re an undergraduate student participating in your first research experience or a faculty member already familiar with computational research—or if you find yourself anywhere in between—we’re here to support you.

• Please contact us at helpdesk@chpc.utah.edu if you have any questions or concerns. 
• We encourage you to attend our presentation series to learn how to effectively utilize these computing tools.

For more information, visit our FAQ page.