NVIDIA DGX-2

The world's most powerful AI system for the most complex AI challenges.

美国a片

WORLD’S MOST POWERFUL AI SYSTEM

Experience 10X the deep learning performance with NVIDIA? DGX-2?, the world’s first 2 petaFLOPS system that combines 16 interconnected GPUs for the highest levels of speed and scale from NVIDIA. Powered by NVIDIA? DGX? software and the scalable architecture of NVIDIA NVSwitch, DGX-2 is the platform of choice for taking on the world’s most complex AI challenges.

Watch Webinar
Download Datasheet

DISCOVER THE BENEFITS

Unbeatable Compute Power for Unprecedented Training

AI is getting increasingly complex demanding unprecedented levels of compute power. NVIDIA DGX-2 packs 16 of the world’s most powerful GPUs to accelerate new AI model types that were previously untrainable. Groundbreaking GPU scalability, lets you train 4X bigger models on a single node with 10X the performance of an 8-GPU system.

NVIDIA DGX-2 is now available in two models, including a new enhanced DGX-2H - specifically engineered for maximum performance for the most demanding applications. Learn how DGX-2H is the compute building block of DGX-2 POD - the first AI supercomputing infrastructure to achieve Top 500 performance.

A Revolutionary AI Network Fabric

With DGX-2, model complexity and size are no longer constrained by the limits of traditional architectures. Now, you can take advantage of model-parallel training with the NVIDIA NVSwitch networking fabric. It’s the innovative technology behind the world’s first 2-petaFLOPS GPU accelerator with 2.4 TB/s of bisection bandwidth, delivering a 24X increase over prior generations.

AI Scale on a Whole New Level

DGX-2 delivers a ready-to-go solution for rapidly scaling up AI. Flexible networking options for building the largest deep learning compute clusters, combined with virtualization speed scaling and improve user and workload isolation in shared infrastructure environments. With an accelerated deployment model and an architecture purpose-built to scale easily, your team can spend more time driving insights and less time building infrastructure.

Enterprise-Grade AI Infrastructure

DGX-2 is purpose-built for reliability, availability and serviceability (RAS) to reduce unplanned downtime, streamline serviceability and maintain operational continuity. Supported by NVIDIA expertise, and built for the rigor of around-the-clock operations, DGX-2  keeps your most important AI endeavors running around the clock.

Learn more about our enterprise-grade support.

SETTING AI BENCHMARKS

10X Performance Gain In Less Than a Year

Performance gain through hardware and software improvements across the stack. Workload: FairSeq, 55 epochs to accuracy. PyTorch training performance.

The New Standard in Backtesting

NVIDIA DGX-2 with accelerated Python processed 20 million trading simulations and set a new standard in the latest STAC-A3 backtesting benchmark report.

LEARN MORE

Raising the Bar for AI Infrastructure

NVIDIA DGX Systems set eight AI performance records in MLPerf 0.61—a set of benchmarks that enable the machine learning (ML) field to measure training performance across a diverse set of usages.

READ MORE

Shattering World
Records

Learn how the world’s 22nd fastest supercomputer, the NVIDIA DGX SuperPOD – built with DGX systems, is being used to accelerate autonomous vehicle development.

LEARN MORE

1 MLPerf 0.6 submission information: Per accelerator comparison using reported performance for NVIDIA DGX-2H servers (16 Tesla V100 GPUs) compared to other submissions at same scale except for MiniGo where the NVIDIA DGX-1 servers (8 Tesla V100 GPUs) submission was used. | MLPerf ID Max Scale: Mask R-CNN: 0.6-23, GNMT: 0.6-26, MiniGo: 0.6-11 | MLPerf ID Per Accelerator: Mask R-CNN, SSD, GNMT, Transformer: all use 0.6-20, MiniGo: 0.6-10. See mlperf.org.

NVIDIA DGX-2

Explore the powerful components of DGX-2.
16X FULLY CONNECTED TESLA V100 32GB
0.5 TB total high-bandwidth memory for more complex deep learning models
12X NVSWITCHES
Delivering 2.4TB/s bisection bandwidth
8X EDR INFINIBAND/100 GigE
1600Gb/sec total bi-directional bandwidth with low-latency
NVLINK PLANE CARD
Innovative 2 GPU baseboard interconnect
2X XEON PLATINUM
Latest Generation CPU for faster, more resilient boot and storage management
1.5TB SYSTEM MEMORY
More system memory to handle larger Deep Learning workloads
TWO HIGH SPEED ETHERNET NETWORKING CARDS
High I/O throughput for your AI data
30TB NVME SSDs
Rapidly ingest the largest datasets into cache

Red Hat? Enterprise Linux? on NVIDIA? DGX? Systems

Download Datasheet
Get Solution Brief

NVIDIA DGX POD

IT-Approved Infrastructure for the AI Enterprise

Learn More

SETTING THE PERFORMANCE STANDARD FOR AI INFRASTRUCTURE

NVIDIA DGX-2 outperforms the industry, incorporating our greatest innovations, solving the world’s most complex AI challenges.

Learn More

GET STARTED

Colocation Services for NVIDIA DGX

Learn more

ORDER NVIDIA DGX TODAY

CONTACT US

Flexible Leasing Options Available

LEARN MORE

THE NVIDIA DGX-2 IS AVAILABLE TO ORDER

CONTACT US TO LEARN MORE

Products
Technologies
Resources