New supercomputer Titan can process more than 20,000 trillion
calculations, or 20 petaflops, in a mere blink by employing a series of
graphic processing units first created for computer gaming.
Launched
by the Oak Ridge National Lab (ORNL), Titan will be 10 times as powerful
as ORNL's last world-leading system, Jaguar, overcoming power and space
limitations inherent in the previous generation of high-performance
computers.
Using a grid of 14-km cells, the new system will be
able to simulate from one to five years per day of computing time, up
from the three months or so that Jaguar was able to churn through in a
day, according to an ORNL statement.
Titan, which is supported by
the US Department of Energy, will provide unprecedented computing power
for research in energy, climate change, efficient engines, materials and
other disciplines and pave the way for a wide range of achievements in
science and technology.
Titan also has more than 700 terabytes of
memory. The combination of central processing units, the traditional
foundation of high-performance computers, and more recent graphics
processing unit (GPUs) will allow Titan to occupy the same space as its
Jaguar predecessor while using only marginally more electricity.
"One
challenge in supercomputers today is power consumption," said Jeff
Nichols, associate lab director for computing and computational
sciences.
"Combining GPUs and CPUs in a single system requires
less power than CPUs alone and is a responsible move toward lowering our
carbon footprint. Titan will provide unprecedented computing power for
research in energy, climate change, materials and other disciplines to
enable scientific leadership," he added.
By relying on its 299,008
CPU cores to guide simulations and allowing its new NVIDIA GPUs to do
the heavy lifting, Titan will enable researchers to run scientific
calculations with greater speed and accuracy.
"Titan will allow
scientists to simulate physical systems more realistically and in far
greater detail," said James Hack, director of ORNL's National Centre for
Computational Sciences.