NVIDIA DGX SYSTEMS
Purpose-Built for the Unique Demands of AI
SETTING THE BAR FOR ENTERPRISE AI INFRASTRUCTURE
Whether creating quality customer experiences, delivering better patient outcomes, or streamlining the supply chain, enterprises need infrastructure that can deliver AI-powered insights. NVIDIA DGX™ systems deliver the world’s leading solutions for enterprise AI infrastructure at scale.
THE WORLD’S LEADING PORTFOLIO OF PURPOSE-BUILT AI SYSTEMS
NVIDIA DGX Station™ A100
AI Workgroup Appliance
Server-class workstation ideal for experimentation and development by teams. No data center required.
NVIDIA DGX™ A100
AI Training, Inference, and Analytics
The third generation of the world’s most advanced AI system, unifying all AI workloads.
NVIDIA DGX POD™
Scaled AI Infrastructure Solution
Industry-standard infrastructure designs for the AI enterprise.
NVIDIA DGX SUPERPOD™
Turnkey AI Infrastructure
Full-cycle, industry-leading infrastructure for the fastest path to AI innovation at scale.
OEM Server
SUPERCHARGE YOUR WORKLOADS
The qualified server catalog provides you with easy access to GPU-accelerated servers from our comprehensive partner network. These servers have been purpose-built to accelerate a variety of applications across HPC, deep learning, machine learning, and visualization applications.
With a comprehensive list of configuration details, you can pick the right system for your application needs and simplify the overall purchasing process. Backed by enterprise support from both NVIDIA and our partners, you can deploy your applications with the highest confidence possible.
FEATURES
NGC-Ready™: A validation program, backed with enterprise support, for single-node systems running on NVIDIA V100 Tensor Core, T4 Tensor Core, Quadro RTX™ 6000, and Quadro RTX 8000 GPUs.
NVIDIA-Certified: A formal certification program, backed with enterprise support, for both single and cluster-based systems consisting of NVIDIA Ampere architecture GPUs, NVIDIA Mellanox® ConnectX-6, Connect X-6 Dx, and BlueField-2 DPU.
Storage
AI infrastructure requires extremely high-speed storage to handle a variety of data types in parallel, such as text, tabular data, audio and video. The NVIDIA DGX System and SuperPOD Solution for Enterprise features all-flash storage that is optimized to meet customers’ specific requirements as well as the unique demands of AI workloads. To support this, we partnership with Global Network of Certified Partners storage provider.
Fully Integrated AI Deployments Across Systems to Software
From customized capacity planning and data center design services to application performance testing and developer operations training, the DGX SuperPOD Solution for Enterprise provides the fastest path to AI innovation at scale. Each DGX SuperPOD is fully racked, stacked and configured by NVIDIA-Certified partners. These NVIDIA AI experts ensure installs are easy, even when building out AI infrastructure with dozens or hundreds of nodes connected by extensive cabling.
Following installation, NVIDIA and certified experts work with customers to ensure their AI workloads are optimized with the latest NVIDIA software available on the NGC hub of cloud-native, GPU-optimized containers, models and industry-specific SDK.
Network
Accelerating Compute and Data
Modern data centers run distributed applications across a composable infrastructure consisting of disaggregated GPUs, CPUs, memory and storage that require flexible, high-speed connections. NVIDIA networking accelerates and offloads data transfers to ensure compute resources never “go hungry” due to lack of data or bandwidth. Smart adapters and switches reduce latency, increase efficiency, enhance security, and simplify data center automation so applications run faster.
Ethernet
DPU / SMARTNICS
The NVIDIA® BlueField-2® data processing unit (DPU) is modern data center infrastructure on a chip, delivering accelerated software-defined networking, storage, security, and management services.
Switches
Best-in-class Ethernet switch portfolio, in Edge, Leaf, and Spine form factors, ranging in speeds from 10 to 400Gbps.
Interconnect
LinkX Ethernet DACs, AOCs and Optical Transceivers meet or exceed all of the IEEE 802.3xx industry standards for 1G, 10G, 25G, 50G and 100G products.
Infiniband
Smart Adapters
ConnectX InfiniBand smart adapters with acceleration engines deliver best-in-class network performance and efficiency and enable low-latency.
Switches
NVIDIA InfiniBand switch systems deliver the highest performance and port density for HPC AI, Web 2.0, big data, cloud infrastructure and enterprise data centers.
Interconnect
LinkX Ethernet DACs, AOCs and Optical Transceivers meet or exceed all of the IEEE 802.3xx industry standards for 1G, 10G, 25G, 50G and 100G products.
Software And Drivers
Accelerator
Select the right tool to utilize your server to its fullest.
Management
End-to-end network management solutions enabling monitoring, management, analytics and visibility.
Firmware Download
Downloads for ConnectX® Adapter Cards, switch systems, and gateway systems.
