This site may earn chapter commissions from the links on this page. Terms of use.

Nvidia-SC-Feature

The Supercomputing 2017 (SC17) conference has been in full swing this week, with major announcements from a number of players in the HPC manufacture. Nvidia has been no exception — the visitor has feathered its cap with announcements that information technology now has major co-processors in 87 of the TOP500 supercomputers worldwide, likewise equally six of the ten most efficient supercomputers in the world (listed as the GREEN500). Now, Nvidia is putting its hard work on Volta back into its ain hardware, with a massive upgrade to the SaturnV supercomputer it built for its ain use.

A year agone, the SaturnV was the most power-efficient arrangement in the TOP500, with a rated adequacy of ix.46GFLOPS/watt. Today, that same rating only qualifies the organisation for #14. That'southward respectable, to be sure, but Volta does appear to deliver a fair kick — though we can't estimate how much. The new SaturnV machine is a fraction the size of the old model, with 22,440 cores versus 60,512 and 16.5TB of memory as opposed to 62TB.

SaturnVSpecs

Even so, the TOP500 comparing doesn't really capture the scope of the upgrade. It's admittedly true that the new SaturnV iteration has fewer cores and less total RAM, but it packs far more GPUs. The 2016 model had 125 nodes with eight GPUs per node, for a total of 1,000 GPUs and iii.3PFLOPS of processing power. The SaturnV 2017 Edition has 660 nodes with eight GPUs per node, for a total of five,280 Volta GPUs.

DGX-1-Server

The building block of the system, in both 2016 and 2017, is the Nvidia DGX-1, a supercomputer-in-a-box that contains 8 Volta GPUs per chassis. Nvidia also engineered Volta for supercomputing and AI workloads and has made functioning in those areas a critical component of the production's marketing and positioning. That's in-line with what nosotros've seen from multiple other companies over the past twelvemonth, whether we're talking about AMD, Fujitsu, Google, or Intel. Anybody and their child sister has gone racing towards the magic of AI and deep learning, and multiple hardware companies are working on their own custom silicon to drive these new experiences (or create them in the starting time place).

It's going to exist genuinely interesting to see how this shakes out. High-stop AI battles between rival semiconductor companies might not seem to have much impact on the consumer market, but the technologies these companies are trying to develop — amend AI, cocky-driving cars, medical advances, and many others — could revolutionize man life on Earth just equally much as the beginning PCs did. Nvidia knows that early on movers have the best shot at being part of a market long-term, which is why they're pushing then difficult to stay on meridian of this fast-moving space.