In Russia, Supercomputers Start with GPU!

Posted 06/17/2011 at 6:34am | by Paul Lilly

5

Comments

Print

With the Cold War a thing of the past, Russian scientists are free to concentrate their efforts on projects other than the space race and building a stockpile of nuclear arms. These days Russian scientists are studying computationally heavy topics like global climate change, ocean modeling, post-genomic medicine, and galaxy formation, and they're tapping into Nvidia's Tesla GPUs to do the heavy lifting.

Mosco State University, for example, just upgraded its Lomonsov supercomputer with 1,554 Nvidia Tesla X2070 GPUs coupled with an identical number of quad-core processors. According to Nvidia, Lomonsov delivers 1.3 petaflops of peak performance, making it the No. 1 supercomputer in Russia and one of the fastest in the entire world.

"Our research requires enormous computation resources, and we need to deliver this performance as efficient as possible," said Victor Sadovnichy, academician, Rector of Moscow State University. "The only way for us to achieve these twin goals is with a hybrid GPU/CPU based system."

That's just fine by Nvidia, which points out that GPUs deliver high performance per watt. And it isn't just Russia that's jumping on board with GPU computing. The National Supercomputing Center in Tianjin, China, recently announced that they built Tianhe-1A, the world's fastest supercomputer based on Nvidia Tesla GPUs, while supercomputing giant Cray unveiled its first GPU supercomputer last month running -- what else? -- Tesla hardware.

Image Credit: Nvidia