Tuesday, 13 November 2018 09:21

Nvidia increases Top500 presence


Graphics processor manufacturer Nvidia has further boosted its credentials in the high performance computing space with the latest Top500 list showing that the company's GPUs power 127 of the world's fastest 500 supercomputers.

The latest Top500 list shows 127 of the world's fastest supercomputers use Nvidia GPUs, up from 86 last year.

Among them are the two fastest computers in the world (both in the US), and the fastest in Europe and Japan.

The two leading supercomputers are Oak Ridge National Laboratory's Summit (200,794.9 Tflops) and Lawrence Livermore National Laboratory's Sierra (125,712.0 Tflops), both of which use IBM Power CPUs as well as Nvidia Volta GPUs.

China's Sunway-based TaihuLight supercomputer was the world's fastest until it was overtaken by Summit earlier this year, and has now been relegated to third place by Sierra.

Europe's fastest is the Swiss National Supercomputing Centre's Piz Daint (100,678.7 Tflops, Intel Xeon plus Nvidia Tesla), which came in at number five.

Two places behind that is Japan's fastest supercomputer, the National Institute of Advanced Industrial Science and Technology's ABCI (32,576.6 Tflops, Intel Xeon and Nvidia Tesla).

One of the newcomers to the Top500 is the Nvidia DGX-2 Pod, a cluster of 36 DGX-2 systems (pictured) delivering more than three double-precision petaflops. Nvidia estimates that a cluster of just 11 DGX-2s would qualify for the latest Top500 list.

Nvidia GPUs are also used in eight out of the top ten and 22 of the top 25 supercomputers on the Green500 list. Nvidia's own DGX SaturnV Volta system took second place by achieving 15.113 Gflops/watt, behind Shoubu system B, a Pezy/Exascaler system at Japan's Advanced Center for Computing and Communication which recorded 17.604Gflops/watt.

"This is a breakout year for Nvidia in the world of supercomputing," said Nvidia founder and chief executive Jensen Huang.

"With the end of Moore's law, a new HPC market has emerged, fuelled by new AI and machine learning workloads. These rely as never before on our high performance, highly efficient GPU platform to provide the power required to address the most challenging problems in science and society."


26-27 February 2020 | Hilton Brisbane

Connecting the region’s leading data analytics professionals to drive and inspire your future strategy

Leading the data analytics division has never been easy, but now the challenge is on to remain ahead of the competition and reap the massive rewards as a strategic executive.

Do you want to leverage data governance as an enabler?Are you working at driving AI/ML implementation?

Want to stay abreast of data privacy and AI ethics requirements? Are you working hard to push predictive analytics to the limits?

With so much to keep on top of in such a rapidly changing technology space, collaboration is key to success. You don't need to struggle alone, network and share your struggles as well as your tips for success at CDAO Brisbane.

Discover how your peers have tackled the very same issues you face daily. Network with over 140 of your peers and hear from the leading professionals in your industry. Leverage this community of data and analytics enthusiasts to advance your strategy to the next level.

Download the Agenda to find out more


Stephen Withers

joomla visitors

Stephen Withers is one of Australia¹s most experienced IT journalists, having begun his career in the days of 8-bit 'microcomputers'. He covers the gamut from gadgets to enterprise systems. In previous lives he has been an academic, a systems programmer, an IT support manager, and an online services manager. Stephen holds an honours degree in Management Sciences and a PhD in Industrial and Business Studies.



Recent Comments