Getting Started
New to ARC? See the content below to get started, but don’t hesitate to reach out to us if you have questions or need assistance.
The Basics
The following are the basic steps to getting started with ARC resources (and at most research computing centers):
Get an account (More detail on accounts is available here)
Get an allocation (if you are a faculty member/PI) or get access to one (if you are a student)
Decide which hardware you want to use
Develop your workflow, possibly via interactive jobs
Submit your production research via batch jobs
In addition to the text documentation linked above, we offer video tutorials of most of these steps as well as training courses to help people get started.
Learning Curve
There can be a learning curve in using high-performance computing (HPC) resources. In particular:
ARC systems run Linux, and traditional use is via the command line. However, the latter has become less true in recent years. For example, via Open OnDemand ARC users can now access our systems from their browser and start many popular applications such as Jupyter notebooks via the click of a button.
To run on ARC systems, you must submit your work through the scheduler. This is different from running on, e.g., a lab workstation. However, this mostly just involves writing down a list of commands you want the system to run and how many resources you want it to use – it is not difficult once you get used to it.
To leverage HPC resources, your program needs to be able to leverage parallel computing in some way. However, may third party programs or libraries exist to make this easier and ARC computational scientists are available if you need assistance.
Familiar with HPC, new to ARC
If you are an experienced HPC user who is new to ARC, you may just need to know the following:
ARC uses the Slurm scheduler.
You will need to have an allocation to charge your jobs to. This is free of charge unless you would like to invest in priority access.
Descriptions of our compute and storage resources can be found here.
Training
To help users get started, we offer introductory training sessions throughout the year via the Professional Development Network. Our computational scientists are also available for classroom presentations on high-performance, parallel, scientific, or other research computing topics – this is a great way to get a research group up to speed.
If you prefer to do things at your own pace, we offer video tutorials that walk through each of the steps of getting started with ARC.
Getting Help
If you are interested in using ARC’s resources for your current or future projects, or if you would just like to learn more about our computing systems and services, please request a consultation or drop by our office hours. You do not need to have any prior experience with high-performance computing — our team can assist you in determining the right system for your project.