14 DAY TRIAL // GPU computing in HPC applications has come a long way these past few years, so, naturally, NVIDIA is going to take advantage of every opportunity to point out its growing role in this area.
As some might know, the TOP500 project always has a list ready of the world's 500 best supercomputers.
Russia has its own version of the list, one might say, although it is much shorter (50 instead of 500).
Still, 50 is a very large number, which means that the two in the lead are definitely something to fawn over.
As it turns out, NVIDIA is definitely fawning over those systems, since its graphics processing units are used by both.
Speaking of which, the HPC installations (HPC = high-performance computing) are located in the same area: Lomonosov Moscow State University.
"The challenges of modern science can only be addressed by applying huge computational resources," said Vladimir Voevodin, coordinator of the Supercomputing Consortium of Russian Universities and deputy director of the MSU Research Computing Center.
"NVIDIA GPU technologies are one of the most efficient and cost-effective ways to address these challenges."
Lomonosov Moscow State University was recently named a CUDA Center of Excellence and employs the supercomputers for various scientific research projects (everything from cancer treatment to space exploration).
On a related note, ten other HPCs in the Russia Top 50 list use NVIDIA GPU accelerators in their computations.
"NVIDIA GPUs are enabling game-changing research on some of the most powerful supercomputers around the world, including systems in China, Italy, Japan, Russia, Spain, and the U.S.," said Sumit Gupta, senior director of Tesla business at NVIDIA.
"This tremendous growth is not only due to the vast computational performance and power efficiency GPUs provide, but also because of industry innovations like the OpenACC programming model that make GPU programming easier than ever before."