graphic link to the special report landing page "src =" "/>

<img alt= I n November 2012, The Top500 supercomputer’s semiannual rankings gave the highest rating to a machine built in Oak Ridge National Laboratory in Tennessee. Well named Titan, the machine had a maximum performance of more than 27 × 1015 floating point operations per second, or 27 petaflops. It was a huge IT resource for government, industry and academia researchers, and being at the pinnacle of supercomputing, it helped boost pride in the high-performance computing community in the United States.

 graphic link to the landing page of the special report "src =" "/> 

<p> The satisfaction was short-lived. Only seven months later, Titan lost the world crown of supercomputers to a Chinese machine called  Tianhe-2  (Milky Way-2). And three years later, another Chinese giant, the Sunway TaihuLight </a> took the title of the most powerful supercomputer in the world. His maximum performance was 125 petaflops. After that, Titan did not seem so titanic anymore. </p>
<p> Using the Sunway TaihuLight, Chinese researchers captured the Gordon Bell Prize  2016  [PDF] for their work modeling atmospheric dynamics. "This shows that it was not just a stuntman," says Jack Dongarra of the University of Tennessee, one of the Top500 ranking creators. </p>
<p> You may be wondering why, in the last five years, the United States has apparently given up trying to recover first place. In fact, there was no surrender. In 2014, US engineers drafted proposals for a new generation of supercomputers. The first of them will bear fruit later this year in the form of  a supercomputer named Summit  that will replace Titan in Oak Ridge. The maximum performance of the new machine will be about 200 petaflops when it will be put online in a few months, making it the most powerful supercomputer on the planet. </p>
<p> Maybe. </p>
<p> "We are very open to the United States with our machines," says Arthur "Buddy" Bland, project director of the Oak Ridge Leadership Computing Plant. That is to say, he is confident that the summit will be accomplished as planned and that it will be the most powerful supercomputer in the United States. But in the meantime, China, or another country from elsewhere, could set up a new supercomputer or upgrade an existing one to surpass Summit's performance. Could this really happen? "We have no idea," says Bland. </p>
<p> He and his colleagues at Oak Ridge are not losing their sleep because of the issue – and they need all the sleep they can find these days because they have still a lot of work before them to replace Titan. However, they do not follow the pattern that they used to build Titan, which was created as a result of a series of more and more elaborate upgrades of a computer supercomputer. Oak Ridge  called Jaguar .</p>
<p> Jaguar was installed in 2005, when computer hardware became obsolete very quickly (as will be proven by anyone who bought a personal computer at that time). "We would do an upgrade every year," recalls Bland. Jaguar became the world's most powerful supercomputer in 2009. An even bigger upgrade that began in 2011 allowed  Jaguar to be reborn as a Titan  in 2012. </p>
<p> Why not just upgrade the internal hardware of the machine instead of building a new supercomputer? "We think scalability is a worthwhile goal," says Bland – but not the one that works in this case because Titan uses Cray's hardware. "Now we go to an IBM machine: it would not have been possible or reasonable to recycle." While Titan will continue to operate for the moment, but it will be closed about a year after the new Oak Ridge supercomputer will be operational. </p>
<p><img alt=Photo: Oak Ridge National Laboratory
Filtered in: A technician installs cables for the internal data network of the Summit supercomputer at Oak Ridge National Laboratory, Tennessee.

An advantage that the all new supercomputer will bring to Oak Ridge is a significant improvement in energy efficiency. Summit should be able to run simulations of researchers 5 to 10 times faster than Titan, using only twice the power. The typical requirements will be around 15 megawatts. Fortunately, the power will come from the Tennessee Valley Authority’s fully-equipped electricity grid. Others may find it more difficult to power a modern supercomputer, Bland notes. “Go to your local power company and ask,” Where can I plug in my 15-⁠MW computer? “And see what they tell you,” he says ironically.

Although Summit is the best performer, it is not the only US supercomputer in its class to enter service in 2018. A supercomputer named Sierra expected to exceed 120 petaflops of peak performance , will be completed at Lawrence Livermore National Laboratory, California. The Argonne National Laboratory was also to operate in 2018 a new supercomputer, one offering 180 petaflops of maximum performance. But plans from the Illinois laboratory for the construction of this machine, called Aurora, were delayed until 2021 to attempt to ] expand its capabilities and make it the first US supercomputer “exascale” (1000 petaflops or 1 exaflop).

These huge numbers refer to peak performance, but real-world applications only use a fraction of that potential. The Linpack benchmark, often cited, typically runs to 75% of the top of a supercomputer, Dongarra says. “Our little secret is that most real apps are at 3%.”

Clearly, finding intelligent ways to improve actual performance is as important as the number of peak flops theoretically available. And specialists in Oak Ridge supercomputers are also putting a lot of energy into this effort. Joseph Oefelein, who will use Summit in his studies on physics and chemistry of combustion at Georgia Tech succinctly summarizes it: “This game does not boil down to saying that you have the computer the most fast. “

This article appears in the print magazine of January 2018 under the title “U.S. Intensive Computing Counter Attack.”

Source link


Please enter your comment!
Please enter your name here