China Supercomputer Takes Number 1 Spot
China’s Tianhe-1A has taken over first place for the world’s fastest supercomputer.
The machine is capable of carrying out over 2.5 thousands trillion calculations a second.
The supercomputer draws on over 7,000 graphics processors and 14,000 Intel chips.
The Top 500 Organization, which maintains a list of the most powerful machines, has confirmed Tianhe-1A has taken the new spot.
China’s Tianhe-1A (also known as Milky Way) has taken the place from U.S. XT5 Jaguar at the Oak Ridge National Laboratory (ORNL) in Tennessee that can carry out only 1.75 calculations per second. One petaflop is the equivalent of 1,000 trillion calculations every second.
The news about the machine broke just before the publication of the biennial Top 500 Supercomputer list.
Professor Jack Dongarra from the University of Tennessee, who is one of the computer scientists who helps compile the list, said China’s claim was legitimate.
“This is all true,” he told BBC News. “I was in China last week and talked with the designers, saw the system, and verified the results.”
He added: “I would say it’s 47% faster than the Oak Ridge National Laboratory’s machine, 1.7 Pflops (ORNL system) to 2.5 Pflops (Chinese system).”
The supercomputer unites thousands of Intel processors with thousands of graphic cards made by Nvidia.
The chips inside graphics cards are typically made up of small arithmetical units that carry out simple sums very quickly. Intel chips are typically used to carry out more complicated operations.
The Tianhe-1A houses its processors in over 100 fridge-sized cabinets and together these weigh over 330,000 pounds.
The computer is based in China’s National Center for Supercomputing in the city of Tianjin. It has already started to do work for the local weather service and the National Offshore Oil Corporation.
Dongarra told The New York Times that the Tanhe-1A “blows away the existing number 1 machine.”
Image Caption: The Tianhe-1A Supercomputer, located at National Supercomputer Center, Tianjin. Credit: NVIDIA
On the Net: