Have a Question?
Intro to ARCC
Intro to ARCC
Workshop Video: Intro to ARC resources~ HPC computing/analysis tools for research and education
What is an HPC Cluster?
Broadly speaking, a high performance computing (HPC) cluster is a collection of networked computers and data storage with the ability to process and perform complex calculations at high speed. We refer to individual servers in this network as nodes. The algorithms are run simultaneously on these servers , which are networked to a data storage to capture the results. Different servers (or nodes) have different types of tasks:
- Head or Login node – where users login and submit the requests for resource allocation.
- Compute nodes – powerful nodes where all the computation is done.
- GPU nodes – on these nodes computations can be run both on CPU cores and on a Graphical Processing Unit.
- Infiniband Switch – a switch to connect all the nodes together.
All nodes have the same components as a typical desktop but are much more powerful. Also, there are thousands of these nodes which allows you to run your algorithms more efficiently.

Our clusters are only accessible to researchers remotely; your gateways to the cluster are the login nodes. From these nodes, you view files and dispatch jobs to other nodes across the cluster configured for computation, called compute nodes. The tool we use to manage these jobs is called a job scheduler. All compute nodes on a cluster mount a shared filesystem; a file server or set of servers store files on a large array of disks. This allows your jobs to access and edit your data from any compute node. See our summary of the compute and storage hardware we maintain.
Why Use an HPC Cluster?
A typical desktop system has 16GB of memory, a few CPU cores and some TB of disk space.
During the execution of a typical program, the following happens:
- Data gets loaded from disk to memory.
- Program executes on the CPU cores.
- The results written back to the disk.
If during any of these steps, the requirement exceeds the available capacity, your system will crash! An HPC cluster can be advantageous in the following scenarios:
- Your program requires more resources (memory, disk, cores etc.) than available on your system.
- A single code needs to be run multiple times on different inputs.
- The code can run more efficiently in a parallel setting (using OpenMPI and MPI).
- You wish to use a GPU accelerator for your code.
What is ARCC?
The Advanced Research Computing Cluster (ARCC) is a HPC service at UC.
Request an Account (consider linking to the New Users Guide instead)
Be a Good Cluster Citizen
While using HPC resources, here are some important things to remember:
- Do not run jobs or computation on a login node, instead submit jobs.
- Never give your password or ssh key to anyone else.
- Do not store any high risk data on the clusters.