US hangs on to lead in supercomputing, barely
- By Susan Miller
- Jun 18, 2019
The Summit and Sierra supercomputers at Oak Ridge National Lab held onto the first and second place slots in the latest list of the top 500 supercomputers in the world. The 53rd edition of list also represents the first time all 500 machines deliver a petaflop or more on the performance benchmark.
China has 219 TOP500 systems, making up 43.8% of all systems listed. Although the U.S. trails with 116 -- near the all-time low – the size of those systems kept the U.S. close to China in terms of installed performance.
In a May 2108 blog post, Energy Secretary Rick Perry acknowledged the U.S. has slipped in the rankings of the world's fastest machines, but reiterated the administration's commitment to expanding the use of exascale systems. See the TOP500 list here.
Other recent news in high-performance computing includes:
Exabyte storage. Oak Ridge National Laboratory and Cray Inc. announced development of a first-of-a-kind exabyte storage solution for the lab's Frontier exascale supercomputer, being built on Cray’s Shasta architecture.
The storage solution will include over 1 exabyte of hybrid flash and high-capacity storage so that diverse modeling, simulation analytics and artificial intelligence workloads can run and scale simultaneously. The storage will be directly connected to Frontier by the company's Slingshot high-speed network, eliminating the need for storage routers and lowering cost, complexity and latency.
The Frontier system is anticipated to debut in 2021 as the world’s most powerful computer with a performance of greater than 1.5 exaflops. Read more here.
Weather forecasting. The National Oceanic and Atmospheric Administration revved up the nation's weather forecasting model, the Global Forecast System, with a new dynamical core called the Finite-Volume Cubed-Sphere that computes wind and air pressure. The new model was made possible after weather and climate supercomputing systems were upgraded to increase performance by nearly 50%. Sixty percent more storage capacity was added to collect and process weather, water and climate observations. More from NOAA here.
Big Red 200. Indiana University announced it is installing the fastest university-owned supercomputer in the nation. The Big Red 200 system is an exascale-class Cray Shasta supercomputer, larger versions of which are being installed at Argonne and Oak Ridge National Laboratories. It will be used for artificial intelligence, machine learning, data analytics, and scientific and medical research. Read more here.
Super GIS. Researchers working in geospatial AI -- the data science that uses AI, deep learning and machine learning to deliver new applications and insights based on geospatial data – have a new suite of workflow and analysis tools available from Cray. Municipal governments can use the tools to detect changes in satellite imagery as they develop infrastructure and disaster response plans. Cray said the tools can reduce training times for complex neural network models, speeding application development.
The company also said the US Geological Survey had selected a Cray CS Series system to further the use of AI in natural sciences and earth observation, including numerical weather prediction, hydrology, solid earth geoscience and land imaging. More from Cray.
Susan Miller is executive editor at GCN.
Over a career spent in tech media, Miller has worked in editorial, print production and online, starting on the copy desk at IDG’s ComputerWorld, moving to print production for Federal Computer Week and later helping launch websites and email newsletter delivery for FCW. After a turn at Virginia’s Center for Innovative Technology, where she worked to promote technology-based economic development, she rejoined what was to become 1105 Media in 2004, eventually managing content and production for all the company's government-focused websites. Miller shifted back to editorial in 2012, when she began working with GCN.
Miller has a BA and MA from West Chester University and did Ph.D. work in English at the University of Delaware.
Connect with Susan at [email protected] or @sjaymiller.