Oak Ridge National Laboratory (ORNL) has announced plans to design a supercomputer powered by Nvidia’s next-generation Fermi GPU. The machine – which will be used to research topics such as energy and climate change – is expected to be 10-times more powerful than today’s fastest supercomputer.
ORNL’s Jeff Nichols explained that the Fermi GPU will enable “substantial” scientific breakthroughs that would be “impossible” to achieve without Nvidia’s advanced GPU technology.
“This would be the first co-processing architecture that Oak Ridge has deployed for open science, and we are extremely excited about the opportunities it creates to solve huge scientific challenges,” said Nichols.
“With the help of Nvidia, Oak Ridge proposes to create a computing platform that will deliver exascale computing within ten years.”
Nvidia chief scientist Bill Dally expressed similar sentiments.
“The first two generations of the CUDA GPU architecture enabled [us] to make real in-roads into the scientific computing space, delivering dramatic performance increases across a broad spectrum of applications,” said Dally. “The ‘Fermi’ architecture is a true engine of science and with the support of national research facilities such as ORNL, the possibilities are endless.”
It should be noted that ORNL will also be forming a Hybrid Multicore Consortium to prepare various applications for the next-generation of GPU-based supercomputers.