Something big is coming for science—the largest by far academic supercomputer in the U.S., called Horizon, as part of the U.S. National Science Foundation Leadership-Class Computing Facility (NSF LCCF), a project awarded to the Texas Advanced Computing Center (TACC).

In July 2024, the NSF announced that TACC will begin construction of the NSF LCCF, which will be a distributed facility with six partners providing unique computational and data analytics capabilities, as well as critical software and services, for the nation’s science and engineering research community to enable discoveries that would not be possible otherwise.

TACC will build and operate the Horizon supercomputer as part of the NSF LCCF. When it comes online in 2026, the supercomputer will be 10 times as powerful as the current leading academic supercomputer in the U.S.—Frontera—also operated by TACC.

On the podcast to discuss the NSF LCCF and Horizon supercomputer is Dan Stanzione, executive director of TACC and principal investigator of the NSF LCCF. 

Highlights from the podcast include:

•	The NSF has elevated the LCCF, a computing facility with sustained, large-scale funding, to be on par with other large, strategic scientific initiatives such as the James Webb Space Telescope and the IceCube Neutrino Observatory.
•	The LCCF will have partners distributed throughout the country, including Atlanta University Center (AUC) Data Science Initiative at the AUC Consortium, a collaboration of four historically Black colleges and universities: Clark Atlanta University, Spelman College, Morehouse College and Morehouse School of Medicine; National Center for Supercomputing Applications at the University of Illinois Urbana-Champaign; Pittsburgh Supercomputing Center, a joint center of Carnegie Mellon University and the University of Pittsburgh; San Diego Supercomputer Center at the University of California San Diego; Cornell University; and Ohio State University.
•	The Horizon supercomputer will be a key universal instrument for a wide range of scientific domains, helping scientists investigate nature in time steps from the picoseconds of atoms to the gigayears cosmological galaxy clusters.
•	TACC is currently constructing Horizon with Sabey Data Centers in Round Rock, Texas, scheduled to come online in early 2026.
•	Horizon will support traditional 64-bit HPC computation as well as have a large supply of lower precision graphics processing units (GPU) tailored especially for artificial intelligence.
•	Horizon is expected to achieve 400 petaflops of HPC performance, about 10 times that of the NSF Frontera system, and the AI component will deliver 100x of Frontera performance.
•	The AI GPUs will offer tremendous power savings compared to the traditional HPC central processing unit (CPU) architecture.
•	The LCCF will offer workforce training opportunities with partners such as Moorehouse College, as well as other education and outreach services serving K-12, undergraduate, and graduate students through camps, internships, fellowships, and more.
•	Horizon will be used by academic researchers awarded allocations through a process similar to NSF Frontera awards.
•	Supercomputers bridging the gap at TACC between Frontera and Horizon include Stampede3 and Vista, which launched in 2024, as well as Lonestar6, launched in 2022.

New Heights: The U.S. NSF Leadership-Class Computing Facility and Horizon

This podcast episode focuses on a recent XSEDE Campus Bridging Success involving a site visit.

The National Science Foundation-funded eXtreme Science and Engineering Discovery Environment (XSEDE) is a single virtual system that scientists can use to interactively share computing resources, data and expertise. People around the world use these resources and services—things like supercomputers, collections of data and new tools—to improve our planet.

XSEDE’s Campus Bridging aims to make cyberinfrastructure—whether local, regional, national, or international—feel close at hand to students, researchers, and staff. Computational systems, data and information management, advanced instruments, visualization environments, and people are all linked together by software for a sense of virtual proximity akin to accessing a peripheral device plugged into the back of a laptop.

Campus Bridging helps institutions with their computer clusters, or sets of computers that work together, by providing an open-source toolkit called Rocks for deploying, managing, upgrading, and scaling applications in parallel across the cluster. Each release of Rocks has core and optional “Rolls” that provide the operating system and other applications integral to cluster computing. So, Rocks Rolls helps institutions build an XSEDE-compatible basic cluster, or XCBC. 

Campus Bridging also offers on-site visits for software installations.  

The first of such visits took place in April at Marshall University in Huntington, West Virginia. The project involved increasing the cluster’s capabilities and enhancing system management. 


An XSEDE Campus Bridging Success Story: Installation at Marshall University

Scientists will use the $30 million system to work on data-intensive problems in life sciences, economics and genomics.

New UT Supercomputer Stampede2 Is The Fastest On Any U.S. Campus

The Supersized Science podcast highlights research and discoveries nationwide enabled by advanced computing technology and expertise at the Texas Advanced Computing Center of the University of Texas at Austin. TACC science writer Jorge Salazar hosts Supersized Science.

Supersized Science is part of the Texas Podcast Network, brought to you by The University of Texas at Austin. Podcasts are produced by faculty members and staffers at UT Austin who work with University Communications to craft content that adheres to journalistic best practices. The University of Texas at Austin offers these podcasts at no charge. Podcasts appearing on the network and this webpage represent the views of the hosts, not of The University of Texas at Austin.

New Heights: The U.S. NSF Leadership-Class Computing Facility and Horizon

Supersized Science Podcast

Related tracks