NVIDIA DGX

ESSENTIAL INSTRUMENT OF AI RESEARCH

The Fastest Path to Deep Learning

Building a platform for deep learning goes well beyond selecting a server and GPUs. A commitment to implementing AI in your business involves carefully selecting and integrating complex software with hardware. NVIDIA® DGX fast-tracks your initiative with a solution that works right out of the box, so you can gain insights in hours instead of weeks or months.

 

GET DETAILED PRODUCT SPECIFICATIONS

Effortless Productivity

Today’s deep learning environments can cost hundreds of thousands of dollars in software engineering hours, and months of delays for the open source software to stabilize. With NVIDIA DGX you’re immediately productive, with simplified workflows and collaboration across your team. Save time and money with  a solution that’s up-to-date with the latest NVIDIA optimized software.

Revolutionary AI Performance

While many solutions offer GPU-accelerated performance, only NVIDIA DGX unlocks the full potential of the latest NVIDIA® Tesla® V100, including next generation NVIDIA NVLink, and new Tensor Core architecture. DGX delivers 3X faster training speed than other GPU-based systems by using the NVIDIA GPU Cloud Deep Learning Stack with optimized versions of today’s most popular frameworks.

Investment Protection

Get the full power of NVIDIA deep learning expertise backing your project, so you won’t waste time and money struggling to get the results you expect. NVIDIA’s enterprise-grade support saves you from the time consuming job of troubleshooting hardware and open source software. Spend less time tuning and optimizing and more time focused on discovery.

NVIDIA DGX

Explore the powerful components of DGX.
NVIDIA TESLA V100
The first GPU architecture to incorporate Tensor Core technology designed for AI.
QUAD EDR IB
High-bandwidth and low-latency, with a total of 800 GB/s of communication.
TWO INTEL XEON CPUS
For boot, storage management, and deep learning framework coordination.
NEXT GENERATION NVIDIA NVLINK
High-speed interconnect 300 GB/s per GPU, 10X faster than current PCIe Gen3 x16 interconnections.
THREE RACK-UNIT ENCLOSURE
Fits in a compact rack space, using 3,200 Watts of maximum system power.

DGX Architecture Advancements

System Level Specifications
NVIDIA DGX with Tesla P100
NVIDIA DGX with Tesla V100

TFLOPS (FP16)

170
960

CUDA Cores

28,672
40,960

Tensor Cores

--
5,120

NVLink vs PCIe Speed-up

5X
10X

Deep Learning Training Speed-up

1X
3X

Iterate And Innovate Faster

High-performance training accelerates your productivity, which means faster time to insight and faster time to market.

NVIDIA DGX Delivers 96X Faster Training

Learn how AI researchers are advancing deep learning and analytics with DGX

Turn Data Into Knowledge

The innovative NVIDIA DGX system lets you uncover patterns in large data sets to reveal new knowledge and insights in hours or minutes.

Read Whitepaper >
Download Datasheet >
Learn How to Build AI at Scale >

Stay Ahead Of The Competition

NVIDIA DGX is engineered to be the essential instrument that delivers the fastest solutions for your deep learning training and AI-accelerated analytics workloads.

Check Out the Infographic >
DGX Webcast >
Stay Ahead of the competition >

Maximize Your Investment

Get the support you need to improve productivity and reduce system downtime. Hardware and software support gives you access to NVIDIA deep learning expertise and includes cloud management services, software upgrades and updates, and priority resolution of your critical issues.

Learn More About Support >

Order NVIDIA DGX Today

NVIDIA DGX is available through select NPN Accelerated Computing partners.