Two HPE-built supercomputers recognized as world’s fastest



  • HPE-built supercomputers claim top two spots on Top500 list of the world’s fastest supercomputers
  • HPE continues to deliver the majority of the world’s most energy efficient supercomputers
  • HPE-built Frontier supercomputer named a TIME 2023 Best Invention
  • Finalist for Gordon Bell Prize for Climate Modeling ran on Frontier exascale system

HPE holds No. 1 performance share for world’s fastest supercomputers, delivers the majority of the top 10 most energy efficient systems, and wins accolades for enabling breakthrough research and innovation

On the heels of the fifth annual Exascale Day, Hewlett Packard Enterprise (HPE) continues to celebrate computing achievements, award wins, international rankings, and more. At SC23, the annual supercomputing conference, the brightest minds in research and discovery, academia, and manufacturing gather to share knowledge with the goal of advancing progress in supercomputing and scientific innovation.

As the builder of the world’s fastest supercomputers, HPE partners with research institutions, public sector organizations and the world’s largest companies to enable this progress. Today, HPE celebrates the latest advancements in supercomputing. 

HPE-Built Supercomputers Claim Top Spots on the TOP500 and GREEN500

The 62nd edition of the TOP500 announced today, featured three HPE-built supercomputers among the top 10. Notably, the Frontier system at Oak Ridge National Laboratory (ORNL), an HPE Cray EX supercomputer and the very first verified exascale system, ranked first place on the list for the fourth time. Argonne National Laboratory’s Aurora system entered the list at the No. 2 spot at 585.34 Pflops/s at half a system run. Built to leverage AI technologies to advance data-intensive research on aircraft design, cancer treatments, and sustainable energy, the Aurora system is currently being used by researchers in the Aurora Early Science Program to leverage generative AI for projects. This includes an open source materials science and chemistry code called QMCPACK which uses the Quantum Monte Carlo (QMC) method to predict how electrons interact with one another for a wide variety of materials. Supercomputing systems like Aurora will demonstrate the impact of research amplified by AI. The LUMI supercomputers built by HPE also placed on the top 10 list of the world’s fastest supercomputers, claiming the No. 5 spot. 

HPE Cray Supercomputers are not only built for speed and computational performance but are also designed with energy efficiency in mind. The 22nd installment of the GREEN500 recognizing systems for both power and efficiency, ranked six HPE systems within the top 10. Adastra, Setonix, Dardel, LUMI and Frontier systems, which are all built on HPE Cray EX235a, prove that the world’s most powerful supercomputers can be designed thoughtfully with energy efficiency in mind.

Through HPE’s ongoing private-public partnerships with the U.S. Department of Energy’s Argonne National Laboratory and Oak Ridge National Laboratory, HPE has co-designed and co-developed several supercomputing systems that are fueling research that is benefitting society as a whole.

Frontier named a TIME 2023 Best Invention

Each year, TIME recognizes 200 extraordinary inventions that change lives. Frontier, the world’s fastest and most powerful supercomputer capable of processing more than a billion-billion (18 zeros) calculations per second, was included in TIME's Best Inventions of 2023 list in the Experimental category.

Developed for the U.S. Department of Energy’s ORNL, Frontier is the first verified exascale system and has ushered in a new era in supercomputing worldwide. The incredible power and speed of Frontier will continue to propel scientific breakthroughs, unlock unprecedented societal benefits, and enable private sector companies to make strategic decisions based on data insights. Some of the research Frontier made possible includes:

  • Analyzing COVID-19 mutations to understand transmissibility, reducing the time-to-insight from one week to 24 hours
  • Making biomedical literature accessible to help accelerate patient diagnosis and care by making use of large-scale graph AI analytics for the first time

  • Simulating computational fluid dynamics of jet propulsions to design advanced jet engines that can sufficiently support hydrogen, a zero-CO2-emission fuel

As the first verified supercomputing system to reach this milestone speed barrier, Frontier is indicative of the breakthroughs in science and engineering that will be made possible with exascale systems.

ACM Gordon Bell Prize finalists runs on HPE-built systems  

The ACM Gordon Bell Prize (GBP), one of the most notable and sought-after accolades in supercomputing, is an annual award that recognizes outstanding achievements within the industry. This year, the 2023 GBP has six finalists, four of which ran their research on these world-class systems built by HPE. These include:

  • Frontier
    • Large-scale Materials Modeling at Quantum Accuracy: Ab Initio Simulations of Quasicrystals and Interacting Extended Defects in Metallic Alloys
    • Exascale Multiphysics Nuclear Reactor Simulations for Advanced Designs
  • LUMI
    • Exploring the Ultimate Regime of Turbulent Rayleigh–Bénard Convection Through Unprecedented Spectral-element Simulations along with other systems
  • Perlmutter
    • Scaling the Leading Accuracy of Deep Equivariant Models to Biomolecular Simulations of Realistic Size

Introduced this year, the Gordon Bell Prize in Climate Modeling highlights the critical climate work and research being carried out by supercomputers. The Energy Exascale Earth System Model (E3SM) team has been named a finalist for the first Gordon Bell Prize for Climate Modeling.

The award nomination recognizes work by the E3SM, powered by the HPE-built Frontier supercomputing system. The accolade acknowledges a global atmosphere model which obtained a record-setting performance of one simulated-year-per-day. The model was run on nearly a full exascale system, further demonstrating the breakthroughs exascale-class supercomputers can achieve. SC23 attendees can attend The Simple Cloud-Resolving E3SM Atmosphere Model Running on the Frontier Exascale System session on Wednesday, November 15th at 10:30 a.m. MT for more information.

From SC23 and beyond

Humanity’s ability to solve the world’s most complex challenges will be shaped by supercomputing-powered research being done now and in the future. SC23 is a moment to celebrate the amazing achievements of HPE’s customers and partners as they drive scientific breakthroughs and innovation forward.


Hewlett Packard Enterprise accelerates AI training with new turnkey solution powered by NVIDIA

Press Release

Celebrating one year of achieving exascale with Frontier, world’s fastest supercomputer

News Advisory

HPE and Tokyo Tech collaborate to build the next generation TSUBAME4.0 supercomputer for artificial intelligence, scientific research, and innovation

Press Release