Editorial Feature

Frontera: An Overview of the World’s Fastest Academic Supercomputer

The Frontera supercomputer provides powerful computational capabilities to advance scientific discovery. This article provides an overview of this supercomputer. 

Image Credit: Gorodenkoff/Shutterstockcom

Many research efforts require complex computational models for predictions and analysis. For example, the study of viral infection requires very detailed mathematical simulations. Astrophysicists simulate the behavior of complex objects in the universe like black holes and neutron stars.

Environmental and geological engineers study hurricane storm surges and impacts to prevent natural disasters. All of these applications and many others can greatly benefit from high-performance computing (HPC). HPC is the practice of combining the processing power of many computers to implement parallel processing for solving complex computational problems. HPCs can compute significantly faster than any single device.

What is Frontera?

Frontera is the 9th fastest supercomputer in the world. It is situated at The Texas Advanced Computing Centre (TACC) at the University of Texas in Austin, Texas. Most other supercomputers, including the fastest supercomputer, the Fugaku supercomputer in Japan, are primarily tasked with commercial and industrial applications. However, Frontera is focused on computations for academic researchers and is the fastest academic supercomputer in the world.

Frontera is the result of a board partnership. The National Science Foundation (NSF) supported the creation of Frontera with 60 million dollars of initial funding. Dell EMC and Intel jointly designed the infrastructure of Frontera which was unveiled in September 2019. Supplemental funding from NSF and substantial contributions from Dell Technologies and Intel have expanded the capabilities of Frontera since its inception.

Make-up of Frontera

The Frontera supercomputer is made up of 8008 nodes. These nodes are DELL EMC Poweredge servers. 16, 016 Intel Zeon scalable processors provide the HPC power for Frontera. Mellanox HDR and HDR-100 interconnects are leveraged to transmit data across the nodes. Data speeds of up to 200Gbps per link are achieved between the switches that connect the nodes. Each node draws approximately 65 kilowatts of power. To mitigate the heat produced, Frontera employs liquid cooling. Water and oil cooling is supplied to Dell EMC from the system integration firm CoolIT and Green Revolution Cooling. About one-third of the power for Frontera is generated from wind and solar power.

Frontera features storage designed by DataDirect Networks. When distributed, each node has a storage capacity of about 480GB. Intel Optane DC persistent memory, a non-volatile memory technology developed by Intel and Micron Technology, is used as RAM in Frontera. This technology amounts to about 192GB per node of RAM.

At peak performance, Frontera achieves 23.5 petaflops. Flops, which is the abbreviation for Floating-Point Operations Per Second, is the measure of a computer's processing speed. One petaflop is equal to one quadrillion (one thousand trillion) flops. With such processing power, Frontera ranks as the top academic supercomputer in the world.

How to Get Computing Time on Frontera

To get computation time on the Frontera, researchers have to submit a proposal. Most government-funded research facilities operate such that research groups have to justify the use of resources. Similarly, proposals must outline a compelling science or engineering experiment that requires multi-petascale computing resources, to use Frontera.

Frontera - the Fastest Academic Supercomputer in the World

Video Credit: TACCuTexas/Youtube.com

Proposals for Frontera are evaluated by the Large Resource Allocation Committee (LRAC). LARC is a peer-review panel of computational science experts. LARC meets annually to evaluate the merit of all proposals submitted to Frontera. Projects that have achieved a threshold of readiness and appropriateness are allocated computing time on Frontera.

Applications That Use Frontera

Frontera is providing support for the most computationally demanding applications that scientists are undertaking. Some examples of projects approved by the LARC are to perform large-scale lattice quantum chromodynamics simulations of a variety of quarks.

Quarks are fundamental, subatomic particles that make up larger particles like protons and neutrons. The computation done at Frontera is expected to address open questions about nuclear and particle physics, such as the mass and spin decomposition of the proton.

AN NSF and NASA-funded project is using Frontera to improve space weather modeling. This research effort is working on making more accurate predictions of weather events. Thereby, extending the lead time for extreme weather conditions.

Another computation carried out at Frontera is uncovering fundamental properties of matter at extreme conditions. This research will advance the frontiers of high energy density science of materials at extreme pressures and temperatures.

Future Outlook

Discovery and scientific breakthrough drives the motivation for Frontera. Frontera will have a huge impact on the broader HPC ecosystem, pushing the boundaries of how researchers work together in a collaborative way. Such collaborative efforts are required for solving the biggest societal problems.

Frontera is expected to expand to its next phase in 2024. The upgrade will enable application-specific accelerators, including quantum simulators and tensor core systems that together can deliver a factor of 10 times faster overall computation speed.

References and Further Reading

Frontera. (n.d.). Frontera. https://frontera-portal.tacc.utexas.edu

New Discoveries in the Making for 2021–2022 - Latest News - Texas Advanced Computing Center. (n.d.). TACC. https://www.tacc.utexas.edu/-/new-discoveries-in-the-making-for-2021-2022

Ravi, R. (2021, December 15). Top 10 Most Powerful Supercomputers | Jumpstart. Jumpstart Magazine. https://www.jumpstartmag.com/top-10-most-powerful-supercomputers

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Written by

Ilamaran Sivarajah

Ilamaran Sivarajah is an experimental atomic/molecular/optical physicist by training who works at the interface of quantum technology and business development.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Sivarajah, Ilamaran. (2021, December 24). Frontera: An Overview of the World’s Fastest Academic Supercomputer. AZoQuantum. Retrieved on April 28, 2024 from https://www.azoquantum.com/Article.aspx?ArticleID=267.

  • MLA

    Sivarajah, Ilamaran. "Frontera: An Overview of the World’s Fastest Academic Supercomputer". AZoQuantum. 28 April 2024. <https://www.azoquantum.com/Article.aspx?ArticleID=267>.

  • Chicago

    Sivarajah, Ilamaran. "Frontera: An Overview of the World’s Fastest Academic Supercomputer". AZoQuantum. https://www.azoquantum.com/Article.aspx?ArticleID=267. (accessed April 28, 2024).

  • Harvard

    Sivarajah, Ilamaran. 2021. Frontera: An Overview of the World’s Fastest Academic Supercomputer. AZoQuantum, viewed 28 April 2024, https://www.azoquantum.com/Article.aspx?ArticleID=267.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this article?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.