WASHINGTON -- To make a point about China's interest in supercomputing, David Turek, IBM's vice president of deep computing, put a slide on the screen showing a large construction site for a building that will house one massive computer.
"That's a truck -- that's a big truck, that's a big hole, and that's going to be a big building," said Turek, pointing to the photo of a supercomputing center being built in Shenzhen, China for an audience at a Washington D.C. forum. "And that's only the first building they are going to build there."
[ Keep up on the day's tech news headlines with InfoWorld's Today's Headlines: Wrap Up newsletter. ]
Under construction: China's massive new supercomputing center site in Shenzhen.
It's not just China that is rushing ahead to build a supercomputing facility, but Europe and Japan as well, said Turek and others on Thursday at an IEEE-USA forum.
"You have sovereign nations making material investments of a tremendous magnitude to basically eat our lunch, eat our collective lunch," Turek said.
The intent of the forum was to update the effort to build the next generation of supercomputers, systems 1,000 times more powerful than current petaflop systems. A petaflop is a quadrillion, or 1,000 trillion sustained floating-point operations per second. One exaflop can perform 1 million trillion calculations per second, a quintillion.
The main message was that other nations are beginning to challenge U.S. supercomputing leadership, something that has implications for every aspect of U.S. leadership in science and product development, said experts at this forum.
Turek predicted that "within a year there will be more Top500 systems in China then there are in Europe collectively." The most recent Top500 list, maintained by academic researchers in the U.S. and Europe, notes that China has 24 systems powerful enough to make the list; France, 27; Germany, 24; United Kingdom, 38; and the United States has 282.
"The No. 1 goal is to maintain U.S. leadership in high-performance computing," said Rick Stevens, associate director for computing, environment and life sciences at the Argonne National Lab.
That means having an exascale system by 2020.
The benefits of such a system could be enormous and take science into areas "not possible today without more computing power," such as simulating everything that is going on inside a human cell, Stevens said.
There are about 1,000 scientist involved in the U.S. Exascale Initiative, said Stevens. But Europe and China, in particular, "have accelerated their investment" in deploying high-performance systems, he said.
Europe has "launched their own exascale program to compete with the U.S.," said Stevens, who added that Europeans are now on a faster development slope and may bypass the U.S. "if we don't sustain the investment to stay ahead."
But the approach to building an exascale system will be different than those systems in the past, Stevens said.
A petascale system today may have about 200,000 processing cores; an exascale system may use anywhere from 100 million to as many as one billion cores, he said.
The power demands for such a system, for instance, have the potential of being enormous. A two petaflop system needs about 2 megawatts, and keeping power needs from running out of control on a system many times more powerful requires improvements in power efficiency.