High Performance Computing

Security framework for protected data allows researchers to tap Oak Ridge supercomputers

CITADEL opens up new opportunities for big data researchers who previously could not access Summit, the nation’s most powerful scientific supercomputer, because of privacy rules.

DOE investing in machine learning tools for data analysis

The Department of Energy is dedicating $29 million to develop new tools and advanced algorithms that will benefit multiple scientific fields and inform cutting-edge solutions for a variety of complex problems.

A real-time mapping platform built from volunteered information

The ground-up approach makes PlanetSense a scalable, location-based intelligence-gathering platform.

Traffic estimation tool makes predictions from sparse public data

TranSEC delivers real-time estimations of street-level traffic that engineers can use to manage citywide traffic flow.

Maximizing a vaccine campaign by analyzing social interactions

Researchers have developed an algorithm that may optimize vaccine distribution by targeting the people that have the maximum reachability into their social network.

Traffic forecasting for every city?

Using a new transfer learning approach, researchers were able to analyze traffic data from the San Francisco region and forecast traffic flow in the Los Angeles region and vice versa.

Los Alamos unwraps next-gen supercomputer

Crossroads will replace the existing Trinity supercomputer and will be used by scientists to support the Stockpile Stewardship Program.

AI defends supercomputers from bitcoin miners

Researchers at Los Alamos National Laboratory have developed an artificial intelligence system that can detect malicious codes that hijack supercomputers for illicit applications such as cryptocurrency mining.

High-performance computing from anywhere

GPU-accelerated virtual workstations allow scientists to continue working with massive datasets from almost anywhere.

More efficient flight with flexible, morphing wings

Army researchers have developed a tool that will quickly compute how the wings on vertical-lift aircraft can adjust their shape during flight to optimize performance.

Scientists tap the world’s most powerful computers in the race to understand and stop the coronavirus

High-performance computing has been critical in powering computational drug discovery, and Oak Ridge National Lab’s next machine, the exascale system Frontier, will push that work further, faster.

Can machine learning predict coronavirus spread?

Using datasets on climate, health and social movement, researchers at Lawrence Berkeley National Lab want to identify what influences COVID-19 transmission.

Energy looks for exascale storage

Argonne National Lab wants a storage system that can keep up with the Aurora, the nation’s first exascale supercomputer.

Game generates training data for supercomputer mapping coral reefs

Researchers at NASA’s Ames Research Center are combining remote sensing data with an online game to produce training data for a machine-learning algorithm running on a supercomputer.

HPC resources for COVID-19 research

The COVID-19 High Performance Computing Consortium will give researchers access to government, academic and industry supercomputers.

NOAA to triple weather forecasting capacity

When the two new Cray systems come online, the combined high-performance computing resources will be triple the capacity and double the storage and interconnect speed of current systems.

Quantum internet: The next global network is already being laid

Instead of replacing the current infrastructure of optical fibers, data centers and base stations, the quantum internet will build on top of and make maximum use of the existing, classical internet.