Getting Started

Important Terms

• Login Node: A node intended as a launching point to compute nodes. Login nodes have minimal resources and should not be used for any application that consumes a lot of CPU or memory—also known as a head node.

• Compute Node: Nodes intended for heavy computing. This is where all heavy processing should be done

• RC: Short for Research Computing, the team that manages the ASU HPC supercomputer.

• HPC: Short for “High Performance Computing” it refers to a group (cluster) of computers designed for parallelism across many computers at once. Publicly these are often called “supercomputers”

• Cluster: A group of interconnected computers that can work cooperatively or independently.

• Job: Work assigned to be done on a compute node. Any time a compute node is assigned a job is created.

• Interactive Job: A job that allows the user to continue interacting with the node through the shell/terminal while the job is running. This is necessary for graphical programs like Jupyter, RStudio, and MATLAB, but can also be used directly in the shell.

• Batch Job: A job that is submitted as a complete script and runs unattended.

• Scheduler: The application on our end that assigns compute resources for jobs.

• Slurm: The brand name of our scheduler which manages and allocates resources.

Quick Start

For those who wish to get started quickly, follow the basic steps:

1. Connect to the ASU VPN.

2. Choose a connection method (Web Portal or SSH).

3. Transfer files as needed.

4. Log in with your ASURITE and password.

5. Run an interactive session or submit an SBATCH script.

Detailed Start

Connect through the Cisco VPN

All Aloe resources require the user to be connected to the ASU Cisco VPN. Be sure to connect to sslvpn.asu.edu/2fa, and if prompted for a “second password,” provide either push to receive a DUO push request, phoneto authenticate via a phone call, or sms to authenticate via a text message.

For additional details or to install the software, please go to the SSL VPN page.

Choosing a Connection Method

RC provides two methods for connecting to the supercomputer: the web portal and SSH. Each has its advantages and disadvantages.

Our web portals have become the standard for new users. These interfaces provide a file system viewer and editor, a job submission tool, the ability to view the job queue, and a collection of interactive applications including a virtual desktop, Jupyter, and RStudio. In the file manager, uploading files is as easy as dragging and dropping through the interface! The web portals are accessible through https://aloe.asre.rc.asu.edu/. Access is requested individually, see this guide on User Accounts for additional details.

The virtual desktop can be provided and it is the best way to use graphical applications on the supercomputer. However, please try to avoid using graphical sessions unless you are first learning how to work with the supercomputer or you’re working with software that is only accessible through a graphical user interface. The goal of any interactive session on the supercomputer should be to develop a working job script (sbatch) so that you may properly begin to take advantage of what supercomputing offers.

Connecting to a supercomputer with SSH is the most versatile method as it allows for unattended use. It does have its drawbacks with interactive graphical applications as tends to be slower. For example, if you intend to use MATLAB graphically (as opposed to MATLAB command line only) the screen draw will take additional time. For graphical applications, we recommend our web portal instead.

Transfer Files

This is optional, however, most research is likely to require datasets to be imported. For details, see these guides on Transferring Files to and from the Supercomputer or using Google Drive & Globus.

Log in to the Supercomputer

You should now be ready to reach the login node. The login node is running software called arbiter2. Arbiter2 monitors and protects interactive nodes with cgroups. It records the activity on nodes, automatically sets limits on the resources available to each user, and notifies users and administrators by email when users are penalized for using excessive resources.

Run Interactive or SBATCH

If you are using RC’s Jupyter or RStudio this section can be skipped. If using a personally installed version of RStudio or Jupyter, please continue reviewing this section.

Once you have a command prompt, there are two ways to get to a compute node:

Starting an Interactive Session: This will assign a compute node and connect your command prompt to it. This is good when working by hand to establish the commands needed to run your work. When your session disconnects, the interactive session also closes. Any unsaved work will be lost.

Scheduling Batch Scripts (Example): This is a method of telling the scheduler you want to run an unattended job. When a sbatch script is submitted, the job will run until it either completes, fails, or runs out of time. Once submitted, sbatch jobs will run without remaining connected to the supercomputer.

Recommended Reading

The page linked above will cover additional details on the supercomputer which will assist in maximizing your results.

Helpful Tips!

If your job fails, providing a JobID in your support ticket helps us significantly as we can pull detailed information about the job using the ID.

For a great reference on building proficiency with command-line tools, we provide the following MIT link from CSAIL.