The U.S. Department of Energy (DoE) has announced that its Argonne National Laboratory will be home to the world’s first exascale supercomputer.
Named Aurora, the supercomputing collaboration between the DoE, Intel and Cray will be 1,000 times more powerful than current petascale supercomputers, making it possible to run more granular, accurate and complex simulations.
As currently planned, Aurora will be powered by a future generation of Intel Xeon processors that will allow the machine to perform one quintillion floating point operations per second. To put that in perspective, the most powerful supercomputer operating today, another DoE machine named Summit, can perform 200,000 trillion floating point calculations per second.
According to Argonne National Laboratory Director Paul Kearns, Aurora will be a transformational resource for American research.
“Argonne’s Aurora system is built for next-generation artificial intelligence and will accelerate scientific discovery by combining high-performance computing and artificial intelligence to address real world problems, such as improving extreme weather forecasting, accelerating medical treatments, mapping the human brain, developing new materials and further understanding the universe—and that is just the beginning.”
The DoE expects that Aurora will be ready to begin receiving instruction in 2021.
For more on supercomputers, check out our article What's the Future of Supercomputing?