Nvidia has unveiled a new supercomputer, the DGX SaturnV, that it has claimed is the most energy efficient supercomputer of all time.
The machine boasts an impressive 63,488GB of RAM and 60,512 Intel Xeon E5-2698v4 CPU cores. It also houses many of Nvidia's 125 DGX-1s, the so-called 'AI supercomputer in a box' modules designed for deep learning. It also uses the graphics card and chip manufacturer's Tesla P100 GPUs.
But its energy efficiency does not come at a huge cost to its performance, as the DGX SaturnV is also ranked as the world's 28th fastest supercomputer.
Nvidia said in a blog post that the company designed the computer to drive its artificial intelligence (AI) programme.
"We're convinced AI can give every company a competitive advantage. That's why we've assembled the world's most efficient, and one of the most powerful, supercomputers to aid us in our own work," the firm said.
"Assembled by a team of a dozen engineers using 124 DGX-1s, the AI supercomputer in a box we unveiled in April, SaturnV helps us build the autonomous driving software that's a key part of our Nvidia DRIVE PX 2 self-driving vehicle platform.
"We're also training neural networks to understand chipset design and very large-scale integration, so our engineers can work more quickly and efficiently. Yes, we're using GPUs to help us design GPUs.
"Most importantly, SaturnV's power will give us the ability to train and design new deep learning networks quickly."
IBM promised in June to deliver a computer which would top the world's supercomputer rankings. The firm's new 200-petaflop machine, called Summit, will be delivered to the US Department of Energy's Oak Ridge National Laboratory in early 2018.
This was in part a response to a supercomputer from China, the Sunway TaihuLight System, taking the overall top spot away from the US for the first time earlier that month.
Newbies will be thrown in with the big boys on Sanhok as Kar98 fodder
Data is the perfect intersection of logic and emotion
Support for RTX Technology and new version of GPU Boost algorithm coming in next-gen Nvidia GPUs
Is Sony's Xperia XZ2 Compact a big step forward against last year's XZ1 Compact?