• 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
  • Legacy Products
  • TESLA M40 24GB
/data/products/article-large/603-20151123113332.png
 
picture next
  • 603-20151123113332.png.png
prev

TESLA M40 24GBTESLA M40 24GB
Part No. TCSM40M-24GB-PB
EAN: 3536403348922


Where To Buy For More Information
  • Overview

    The World’s Fastest Deep Learning Training Accelerator for Today’s Neural Networks

    The NVIDIA® Tesla® M40 is the world’s fastest deep learning training accelerator, purpose-built to train larger, more sophisticated neural networks within hours—versus days on CPU-only systems. It features an NVIDIA Maxwell GPU and 24 GB of large-capacity memory, letting users increase the detection and prediction accuracy of their deep learning models and accelerate time-to-deployment.

    Deep learning is redefining what’s possible. From early-stage startups to large web service providers, deep learning has become the fundamental building block in delivering amazing solutions for end users. Today’s leading deep learning models typically take days to weeks to train, forcing data scientists to make compromises between accuracy and time to deployment. The NVIDIA Tesla M40 24GB GPU accelerator is the world’s fastest accelerator for deep learning training, purpose-built to dramatically reduce training time. Running Caffe and Torch on the Tesla M40 delivers the same model within days versus weeks on CPU based compute systems. Some of the world’s largest data centers take advantage of Tesla accelerators to deliver unprecedented system throughput. The Tesla Platform supports industry-standard applications and system management tools, making it easier than ever before for IT managers to maximize uptime and system performance. Deliver faster discoveries and scientific insights to your users by deploying GPU accelerators in your data center. With broad support for HPC developer tools like MPI, scientific libraries, and OpenACC, most applications offer performance boost with GPUs today.

  • Specifications
    MEMORY SIZE (PER BOARD) 24 GB GDDR5 
    MEMORY INTERFACE 384-bit
    MEMORY BANDWIDTH 288 Gb/s 
    CUDA CORES 3072

    PEAK SINGLE PRECISION FLOATING POINT PERFORMANCE

    ~7 Tflops (GPU Boost Clocks)
    MEMORY INTERFACE  PCI Express 3.0 x16
    MAX POWER CONSUMPTION 250 W
    THERMAL SOLUTION passive Heatsink
    FORM FACTOR 111,15 mm (H) x 267,7 mm (L) Dual Slot, Full Height
    DISPLAY CONECTORS None
    POWER CONNECTORS  8-pin CPU power connector
    WEIGHT (W/O EXTENDER) 898g
    PACKAGE CONTENT 1x Power adapter (2 x PCIe 8-pin auf single CPU 8-pin)
    PART NUMBER AND EAN TCSM40M-L2R-PB    3536403348922
  • Resources

    Download Product Brochure

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

  • Certificates
      Download certificate RoHs
      Download certificate Reach
      Download certificate CE
      Download certificate PCN
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 AND PNY
 

Copyright © 2021 PNY Technologies Inc. All rights reserved.

This Website use cookies.
We use cookies to help us offer you the best online experience.
By continuing to use our website or clicking OK, you consent to the use of cookies in accordance with our PRIVACY POLICY