Skip to main content
Frontier, the fastest supercomputer in the world, provides expansive and energy-efficient power, which gives scientists the capability to train large AI models in a responsible way.

ORNL is home to the world's fastest exascale supercomputer, Frontier, which was built in part to facilitate energy-efficient and scalable AI-based algorithms and simulations. 

Researchers have shown how an all-solid lithium-based electrolyte material can be used to develop fast charging, long-range batteries for electric vehicles that are also safer than conventional designs. Credit: ORNL, U.S. Dept. of Energy

Currently, the biggest hurdle for electric vehicles, or EVs, is the development of advanced battery technology to extend driving range, safety and reliability.

The DEMAND single crystal diffractometer at the High Flux Isotope Reactor, or HFIR, is the latest neutron instrument at the Department of Energy’s Oak Ridge National Laboratory to be equipped with machine learning-assisted software, called ReTIA. Credit: Jeremy Rumsey/ORNL, U.S. Dept. of Energy

Neutron experiments can take days to complete, requiring researchers to work long shifts to monitor progress and make necessary adjustments. But thanks to advances in artificial intelligence and machine learning, experiments can now be done remotely and in half the time.

ORNL’s award-winning ultraclean condensing high-efficiency natural gas furnace features an affordable add-on technology that can remove more than 99.9% of acidic gases and other emissions. The technology can also be added to other natural gas-driven equipment. Credit: Jill Hemman/ORNL

Natural gas furnaces not only heat your home, they also produce a lot of pollution. Even modern high-efficiency condensing furnaces produce significant amounts of corrosive acidic condensation and unhealthy levels of nitrogen oxides

Paul Langan will oversee ORNL's research directorate focused on biological and environmental systems science. Credit: ORNL, U.S. Dept. of Energy

Paul Langan will join ORNL in the spring as associate laboratory director for the Biological and Environmental Systems Science Directorate.

A pure lipid membrane formed using lipid-coated water droplets exhibits long-term potentiation, or LTP, associated with learning and memory, emulating hippocampal LTP observed in the brains of mammals and birds. Credit: Jill Hemman/ORNL, U.S. Dept. of Energy

While studying how bio-inspired materials might inform the design of next-generation computers, scientists at ORNL achieved a first-of-its-kind result that could have big implications for both edge computing and human health.

The AI-driven HyperCT platform has three primary points of articulation that can rotate a sample in almost any direction, eliminating the need for human intervention and significantly reducing lengthy experiment times. Credit: Genevieve Martin, ORNL/U.S. Dept. of Energy

Oak Ridge National Laboratory researchers are developing a first-of-its-kind artificial intelligence device for neutron scattering called Hyperspectral Computed Tomography, or HyperCT.

The ORNL researchers’ findings may enable better detection of uranium tetrafluoride hydrate, a little-studied byproduct of the nuclear fuel cycle, and better understanding of how environmental conditions influence the chemical behavior of fuel cycle materials. Credit: Kevin Pastoor/Colorado School of Mines

ORNL researchers used the nation’s fastest supercomputer to map the molecular vibrations of an important but little-studied uranium compound produced during the nuclear fuel cycle for results that could lead to a cleaner, safer world.

Dongarra in 2019 with Oak Ridge National Laboratory's Summit supercomputer

A force within the supercomputing community, Jack Dongarra developed software packages that became standard in the industry, allowing high-performance computers to become increasingly more powerful in recent decades.

An open-source code developed by an ORNL-led team could provide new insights into the everyday operation of the nation’s power grid. Credit: Pixabay

Oak Ridge National Laboratory, University of Tennessee and University of Central Florida researchers released a new high-performance computing code designed to more efficiently examine