Wednesday, 06 April 2016 13:13

Nvidia packs AI supercomputer into one box

By

Nvidia's DGX-1 is said to be equivalent in performance to a 250-node x86 system for deep learning applications.

Described by Nvidia co-founder and CEO Jen-Hsun Huang as "the world's first deep-learning supercomputer," the DGX-1 contains eight of the new Tesla P100 GPUs, together capable of delivering 170 16-bit teraflops.

Training the AlexNet neural network takes just two hours on a DGX-1, compared with 150 hours on a dual Xeon server. And because of the diminishing returns from adding nodes, it requires more than 250 Xeon servers to match the speed of the DGX-1, he said.

At the GPU Technology Conference 2015 Huang predicted the company would deliver a 10x speed improvement in a year, but it has actually delivered a 12x improvement. What a system with four Maxwell GPUs could achieve in 25 hours can now be done in 2 hours with the DGX-1's eight Pascal GPUs.

Other specifications include a 7TB SSD deep learning cache, and dual 10Gb Ethernet and Quad InfiniBand 100Gb networking. The 3U unit consumes 3,200W.

The DGX-1 is "the densest computing node ever made," added Huang.

Baidu senior researcher (and former Nvidia employee) Brian Catanzaro agreed that the Pascal chips will allow users to "churn through far more data more rapidly."

The DGX-1 isn't just about hardware. It includes the NVIDIA Deep Learning GPU Training System (DIGITS; a complete, interactive system for designing deep neural networks), the new NVIDIA CUDA Deep Neural Network library version 5 (cuDNN 5; a GPU-accelerated library of primitives for designing deep neural networks); optimised versions of the widely used Caffe, Theano and Torch deep learning frameworks; and access to cloud management tools, software updates and a repository for containerised applications.

Optional support services for the DGX-1 include cloud management services, software upgrades and updates, priority resolution of critical issues, and access to Nvidia's deep learning expertise.

The DGX-1 will be available in the US in June, and in other countries during the third quarter of 2016.

The creation of deep learning systems was "the big bang of modern AI," said Huang, leading to many advances in the last five years. It is the technology behind the Microsoft/Google ImageNet system that outperformed humans at image recognition even before Microsoft extended it to a "super-deep" network that doubled its accuracy again; Baidu's Deep Speech 2 English and Mandarin speech recognition system, Berkeley's Brett robot that was able to learn how to perform tasks such as screwing on a bottle cap or fitting a square peg into a square hole, and the human-beating AlphaGo system for playing go.

Rather than requiring human experts to create 'recipes' describing how a task is performed, "with deep learning it's one general algorithm" - but training that algorithm to do a specific task requires a massive amount of data and high-performance computing, said Huang.

Deep learning "is like Thor's hammer - it fell from the sky,' he said. The technology is relatively easy to apply thanks to the existence of frameworks, so most of the effort is in training a system with your own data. "It's approachable, it's powerful enough to achieve superhuman results without a superhuman to program them."

Huang pointed out that the US$129,000 list price of a DGX-1 was a fraction of the half-million dollar price tag for the interconnect hardware needed to link 250 servers, and that's without taking the cost of those servers into consideration.

Nvidia is taking orders for the DGX-1, but the first units will go to institutions that are doing pioneering AI work, including University of California Berkeley and Oxford University, Huang said.

He also announced that Nvidia is partnering with Massachusetts General Hospital's Center of Clinical Data Science. One project will see 10 billion medical images processed by a DGX-1 for radiology, pathology and genomics projects.

Disclosure: the writer attended the GPU Technology Conference as a guest of Nvidia


Subscribe to ITWIRE UPDATE Newsletter here

GRAND OPENING OF THE ITWIRE SHOP

The much awaited iTWire Shop is now open to our readers.

Visit the iTWire Shop, a leading destination for stylish accessories, gear & gadgets, lifestyle products and everyday portable office essentials, drones, zoom lenses for smartphones, software and online training.

PLUS Big Brands include: Apple, Lenovo, LG, Samsung, Sennheiser and many more.

Products available for any country.

We hope you enjoy and find value in the much anticipated iTWire Shop.

ENTER THE SHOP NOW!

INTRODUCING ITWIRE TV

iTWire TV offers a unique value to the Tech Sector by providing a range of video interviews, news, views and reviews, and also provides the opportunity for vendors to promote your company and your marketing messages.

We work with you to develop the message and conduct the interview or product review in a safe and collaborative way. Unlike other Tech YouTube channels, we create a story around your message and post that on the homepage of ITWire, linking to your message.

In addition, your interview post message can be displayed in up to 7 different post displays on our the iTWire.com site to drive traffic and readers to your video content and downloads. This can be a significant Lead Generation opportunity for your business.

We also provide 3 videos in one recording/sitting if you require so that you have a series of videos to promote to your customers. Your sales team can add your emails to sales collateral and to the footer of their sales and marketing emails.

See the latest in Tech News, Views, Interviews, Reviews, Product Promos and Events. Plus funny videos from our readers and customers.

SEE WHAT'S ON ITWIRE TV NOW!

BACK TO HOME PAGE
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.

Share News tips for the iTWire Journalists? Your tip will be anonymous

WEBINARS ONLINE & ON-DEMAND

GUEST ARTICLES

VENDOR NEWS

Guest Opinion

Guest Interviews

Guest Reviews

Guest Research

Guest Research & Case Studies

Channel News

Comments