US Plans To Build World's Fastest Supercomputers


WASHINGTON: U.S. Secretary of Energy Ernest Moniz Friday announced two awards worth $ 425 million to build two supercomputers three times faster than China's Tianhe-2, the most powerful system in the world, as well as research extreme scale supercomputing technologies.

The US government will invest $ 325 million to build "Summit" at the Department of Energy's ( DOE) Oak Ridge National Laboratory in Tennessee and "Sierra" at its Lawrence Livermore Laboratory in California, Xinhua quoted Moniz as saying in a statement. 

Another $100 million will further be used to develop extreme scale supercomputing technologies as part of a research and development programme titled FastForward 2, he said.

"High-performance computing (HPC) is an essential component of the science and technology portfolio required to maintain U.S. competitiveness and ensure our economic and national security," Moniz said.

According to the DOE, Summit and Sierra will be five to seven times more powerful than Oak Ridge's Titan, today's fastest supercomputer in the U.S. that operates at 17.59 petaflop/s, or quadrillions of calculations per second.

The supercomputers, to be installed in 2017, will also be at least three times than the current world's fastest, Tianhe-2 at China's National Super Computer Center, in Guangzhou, which delivers 33.86 petaflop/s.

Both systems will be based on next-generation IBM POWER servers with NVIDIA's GPU accelerators and Mellanox's Interconnected technologies "to advance key research initiatives for national nuclear deterrence, technology advancement and scientific discovery", the DOE said.

The department said a third laboratory, Argonne National Laboratory in Illinois, will announce its supercomputer award at a later time.

The joint project between DOE Office of Science and National Nuclear Security Administration will be led by computing industry leaders AMD, Cray, IBM, Intel and NVIDIA, it added. 

Read More: Revealed: Redmi To Launch A 1GB Smartphone At  4, 000 and Social Media Use At Work Hampers Productivity

Source: IANS