• PNY Global
  • PNY Partner Portal
PNY
  • Consumer
      • Mobile Solutions
      • USB Flash Drives

        USB Flash Drives

        MicroSD Cards

        MicroSD Cards

        Cables & Adapters

        Cables & Adapters

        Mobile Accessories

        Mobile Accessories

        Apple Accessories

        Apple Accessories

      • Photo/Video Solutions
      • Flash Memory

        Flash Memory

        Readers

        Readers

        Photo Accessories

        Photo Accessories

      • Power Solutions
      • Power banks

        Power banks

        Wall Chargers

        Wall Chargers

        Car Chargers

        Car Chargers

        QI Wireless Chargers

        QI Wireless Chargers

      • Gaming Solutions
      • Graphics Cards

        Graphics Cards

        Solid State Drives

        Solid State Drives

        Memory

        Memory

    • Explore Imation
    • Discover Our Customization Service
    • HPPNY is a proud partner of HP Explore HP Products
  • Professional
        • Professional Visualization
          NVIDIA Quadro Graphic Cards

          NVIDIA Quadro Graphic Cards

          GPU Virtualization

          GPU Virtualization

          Warranty Extension Service

          Warranty Extension Service

          • Datacenter - HPC & AI
            NVIDIA Tesla Cards

            NVIDIA Tesla Cards

            NVIDIA Quadro for Datacenters

            NVIDIA Quadro for Datacenters

            NVIDIA DGX Systems

            NVIDIA DGX Systems

            PNY GPU Servers

            PNY GPU Servers

            AI Storage Server

            AI Storage Server

            Pod Architecture

            Pod Architecture

            Networking solutions

            Networking solutions

            • Edge & Embedded
              NVIDIA Jetson Solutions

              NVIDIA Jetson Solutions

              NVIDIA Quadro MXM

              NVIDIA Quadro MXM

              ADLINK Embedded Solutions

              ADLINK Embedded Solutions

              PNY EGX Server

              PNY EGX Server

      • Explore PNY
        • Discover Benefits
        • Quadro Configurator
        • DXG A100 Test Now
        • Markets
        • PNY Lab
        • Quadro View
        • Quadro Experience
        • VR Ready
        • RTX Studio
        • RTX Server
        • Grid Configurator
        • Data Science Workstations
        • Where To Buy
        • Warranty Extension
        • Legacy
        • Contact Us
      • New
      • Programs
        • PNY Partner Hub
        • Partnerships
        • PNY Business Privilege
      • Technology
        • WhitepapersAdvanced Product Design for Industry 4.0 Series
  • Support
  • News
  • Home
  • Professional
  • Explore All Products
  • NVIDIA DGX Systems
  • NVIDIA DGX-2 - THE WORLD’S MOST POWERFUL DEEP LEARNING SYSTEM
/data/products/article-large/1016-20180517100415.png
 
picture next
  • 1016-20180517100415.png.png
  • 1016-20180517134458.png.png
  • 1016-20180517134500.png.png
  • 1016-20180517134502.png.png
prev

NVIDIA DGX-2 - THE WORLD’S MOST POWERFUL DEEP LEARNING SYSTEMNVIDIA DGX-2 - THE WORLD’S MOST POWERFUL DEEP LEARNING SYSTEM
Part No. TCSDGX2-PB


Where To Buy For More Information End Of Sales
  • Overview

    The Challenge of Scaling to Meet the Demands of Modern AI and Deep Learning

    Deep neural networks are rapidly growing in size and complexity, in response to the most pressing challenges in business and research. The computational capacity needed to support today’s modern AI workloads has outpaced traditional data centre architectures. Modern techniques that exploit increasing use of model parallelism are colliding with the limits of inter-GPU bandwidth, as developers build increasingly large accelerated computing clusters, pushing the limits of data centre scale. A new approach is needed - one that delivers almost limitless AI computing scale in order to break through the barriers to achieving faster insights that can transform the world.


    Performance to Train the Previously Impossible

    Increasingly complex AI demands unprecedented levels of compute. NVIDIA® DGX-2TM is the world’s first 2 petaFLOPS system,  packing the power of 16 of the world’s most advanced GPUs, accelerating the newest deep learning model types that were previously untrainable. With groundbreaking GPU scale, you can train models 4X bigger on a single node. In comparison with legacy x86  architectures, DGX-2’s ability to train ResNet-50 would require the equivalent of 300 servers with dual Intel Xeon Gold CPUs costing over $2.7 million dollars.

    NVIDIA NVSwitch—A Revolutionary AI Network Fabric

    Leading edge research demands the freedom to leverage model parallelism and requires never-before-seen levels of inter-GPU  bandwidth. NVIDIA has created NVSwitch to address this need. Like the evolution from dial-up to ultra-high speed broadband,  NVSwitch delivers a networking fabric for the future, today. With NVIDIA DGX-2, model complexity and size are no longer constrained by the limits of traditional architectures. Embrace model-parallel training with a networking fabric in DGX-2 that delivers 2.4TB/s of bisection bandwidth for a 24X increase over prior generations. This new interconnect “superhighway” enables limitless possibilities for model types that can reap the power of distributed training across 16 GPUs at once.

     

    AI Scale on a Whole New Level

    Modern enterprises need to rapidly deploy AI  power in response to business imperatives, and need to scaleout AI, without scaling-up cost or complexity. We’ve built DGX-2 and powered it  with DGX software that enables accelerated  deployment, simplified operations – at scale. DGX-2 delivers a ready-to-go solution that offers the fastest path to scaling-up AI, along with virtualization support, to enable you to build your own private enterprise grade AI cloud. Now  businesses can harness unrestricted AI power in a solution that scales effortlessly with a fraction of the networking infrastructure needed to bind accelerated computing resources together. With an accelerated deployment model, and an architecture purpose-built for ease of scale, your team can spend more time driving insights and less time building infrastructure.

     

     

     

     

     

     

    Enterprise Grade AI Infrastructure

    If your AI platform is critical to your business, you need one designed with reliability,  availability and serviceability (RAS) in mind.  DGX-2 is enterprise-grade, built for rigorous  round-the-clock AI operations, and is purpose- built for RAS to reduce unplanned downtime,  streamline serviceability, and maintain operation continuity. Spend less time tuning and optimizing and more time focused on discovery. NVIDIA’s enterprise-grade support saves you from the time-consuming job of troubleshooting hardware and open source software. With every DGX system, get started fast, train faster, and remain faster with an integrated solution that includes software, tools and NVIDIA  expertise.

  • Specifications
    DGX-2 - System Specifications
     
    GPUs 16x NVIDIA® Tesla V100
    GPU Memory 512 GB total
    Performance 2 petaFLOPS
    NVIDIA CUDA® Cores 81 920
    NVIDIA Tensor Cores 10 240
    NVSwitches 12
    Maximum Power Usage 10 kW
    CPU Dual Intel Xeon Platinum
    8168, 2.7 GHz, 24-cores
    System Memory 1,5 TB
    Network 8x 100Gb/sec
    Infiniband/100GigE
    Dual 10/25Gb/sec Ethernet
    Storage OS: 2X 960GB NVME SSDs
    Internal Storage: 30TB
    (8X 3.84TB) NVME SSDs
    Software Ubuntu Linux OS
    See Software stack
    for details
    System Weight 340 lbs (154.2 kgs)
    System Dimensions Height: 17.3 in (440.0 mm)
    Width: 19.0 in (482.3 mm)
    Length: 31.3 in (795.4 mm)
    - No Front Bezel
    32.8 in (834.0 mm)
    - With Front Bezel
    Operating Temperature
    Range
    5°C to 35°C (41°F to 95°F)
     
    DGX-2 - SKUs
    DGX-1 1 Year Support DGX2-1YS  
    DGX-1 3 Year Support DGX2-3YS  
    Installation DGX2NV-INST  

     

  • Resources

    Click here for the latest FAQs, Help & Tutorials, Downloads, and Brochures & Manuals.

  • Certificates
      Download certificate RoHs
      Download certificate Reach
      Download certificate CE
Large Product
PNY
Facebook Twitter Youtube linked-in
PNY PRO
XLR8 GAMING
Technical Support
  • Contact Us
Customer Support
  • Email Us
Support
  • Glossary
  • Contact Us
Company
  • About PNY
  • Press Center
  • Events
  • Careers
  • Where To Buy
  • Contact Us
Legal
  • Your Privacy
  • Terms of Use
  • RGPD & PNY
  • Manage Cookies
 

Copyright © 2021 PNY Technologies Inc. All rights reserved.