The US has overtaken Japan in the race to develop the world’s fastest supercomputer.
The Sequoia computer at Lawrence Livermoor National Laboratory was today named the most powerful supercomputer, capable of 16.32 petaflop/s.
It pushes Japan’s K Computer at the Riken Advanced Institute for Computational Science (AICS) in Kobe, Japan, into second place of the top 500 supercomputers, with a speed of 10.51petaflop/s.
By submitting your email address, you agree to receive emails regarding relevant topic offers from TechTarget and its partners. You can withdraw your consent at any time. Contact TechTarget at 275 Grove Street, Newton, MA.
Sequoia, developed by IBM, is used by the US National Nuclear Security Administration (NNSA) to run simulations to manage the US nuclear weapons stockpile. It is based on IBM’s BlueGene/Q System technology.
Receiving an award today at the International Supercomputer Conference in Hamburg, Brian Connors, vice-president of IBM's High Performance Computing business, said the computer would play a vital role in safeguarding the nuclear stockpile.
“This is just the start. The ability to deliver on the number one computer is important, but it's about the mission,” Connors said.
The Argonne National Laboratory’s Mira supercomputer, in Illinois, came in at third place in the Top 500 list , with 8.15 petaflop/s.
Europe also put in a strong performance this year.
Germany’s SuperMUC – an IBM iDataplex system installed at Leibniz Rechenzentrum in Germany (pictured) – came in fourth place and is Europe’s most powerful machine.
Another German machine, the JuQUEEN BlueGene/Q at Forschungszentrum Juelich, is in 8th place.
Italy appeared in the top 10 for the first time with an IBM BlueGene/Q system installed at Cineca, with a 1.72 petaflop/s performance.
France occupies the number nine spot with a homegrown Bull supercomputer.
Nearly 75% of the top performing computers use Intel processor chips, the list reveals, down slightly from last year. AMD Operon chips are used in 63 systems.
Image courtesy of IBM Research