What is high-performance computing?
Computational research often requires resources that exceed those of a personal laptop or desktop computer. High-performance computing (HPC) aggregates the resources from individual computers (known as nodes) into a cluster that works together to perform advanced, specialized computing jobs.
Many academic fields, including epigenetics, geophysics, materials science, engineering, natural language translation, and health sciences, utilize high-performance computing to advance their research beyond what would be possible with a personal computer.
As the amount of data used in research continues to grow with the popularity of such technologies as artificial intelligence (AI) and advanced data analysis, high-performance computing is becoming increasingly necessary for technological advancement.
The Center for Advanced Research Computing launched its new high-performance computing cluster, Discovery, in August 2020. This new cluster includes additional compute nodes and a rebuilt software stack, as well as new system configurations to better serve CARC users. Discovery marks a significant upgrade to CARC's cyberinfrastructure, and the first step in a major, user-focused overhaul of the program. The Discovery cluster consists of 2 shared login nodes and a total of around 21,000 CPU cores in around 600 compute nodes. Of these, over 200 nodes are equipped with graphics processing units (GPUs) witha total of over 180 NVIDIA GPUs available. The typical compute node has dual 8 to 16 core processors and resides on a 200 gigabit NDR InfiniBand backbone.
Discovery includes an array of scientific software packages, both licensed and open source, for engineering, molecular simulation, and computational chemistry. Researchers can also install software packages or develop their own code within their project’s allotted storage.
Discovery is free to use for all USC faculty, research staff, and graduate students (with the approval of their faculty advisor). For information on how to set up your account and start using the cluster, see the Accounts page. If you anticipate working with legally restricted or sensitive data (e.g., HIPAA-, FERPA-, or CUI-regulated data), see the Secure Computing page.
Researchers also have the option of participating in the Condo Cluster Program (CCP).
Each user has access to four file systems for their CARC account: /home1, /project, /scratch1, and /scratch2.
Nearly 100 GB of storage space is provided for each user to store important code and configuration files in their home directories. Additionally, the BeeGFS/ZFS parallel project file system has a capacity of 8.4 PB of usable space, with a default storage quota of 10 TB per Principal Investigator across their projects. A rapidly growing fleet of state-of-the art multicore compute nodes is available for data-intensive research jobs, backed by two 800 TB, high-throughput scratch file systems. A low-latency, high-bandwidth InfiniBand network fabric facilitates intense research workloads on large data sets.
More information on the different file systems and their intended uses can be found in our Storage File Systems user guide.
CARC uses a customized distribution of the Community Enterprise Operating System (CentOS), built using the publicly available RPM Package Manager (RPM). CentOS is a high-quality Linux distribution that gives CARC complete control of its open-source software packages and is fully customized to suit advanced research computing needs, without the need for license fees.
CARC’s distribution of CentOS was modified for minor bug fixes and desired localized behavior. Many desktop and clustering-related packages were also added to CARC's CentOS installation.
A number of white papers, tutorials, FAQs, and other documentation on CentOS can be found on the official CentOS website.