• Resources
  • Directory
  • Webinars
  • CAD Models
  • Video
  • Blogs
  • EDGE Awards
  • Advertise
    • Gtc Grace Promo 6077370f139ae
    1. Markets
    2. Automation

    Grace CPU Links with GPUs for Faster AI Processing

    April 14, 2021
    NVIDIA’s Grace CPU, replete with NVLinks, was revealed at GTC 2021—sort of.
    Related To: Electronic Design

    >> Top Stories of the Week
    .. >> GTC 2021 digital issue

    NVIDIA’s massive cluster of announcements at GTC 2021 included a very significant one: the Grace processor (Fig. 1). There aren’t a lot of details yet and it will not hit the racks for a while. Still, between NVIDIA’s acquisition of Arm and Arm’s latest ARMv9 announcement, this is a major move into the cloud and enterprise space.

    1. The Grace CPU will be the core of NVIDIA’s enterprise and high-performance processing systems.
    1. The Grace CPU will be the core of NVIDIA’s enterprise and high-performance processing systems.

    One of the main features of Grace is the inclusion of NVLinks (Fig. 2). These are high-speed links that are already used with high-end, enterprise NVIDIA GPGPUs. NVLinks provide a cache-coherent connection between chips allowing memory to be shared. This was limited to GPGPUs until Grace arrived.

    2. Memory tends to be a bottleneck with a conventional CPU/GPU mix (left), but Grace incorporates high-speed NVLinks compatible with NVIDIA GPUs.
    2. Memory tends to be a bottleneck with a conventional CPU/GPU mix (left), but Grace incorporates high-speed NVLinks compatible with NVIDIA GPUs.

    NVLink support is key because platforms like NVIDIA’s DGX include some NVLink NVSwitch switches. A system can include multiple switch chips to provide connectivity for a large number of GPUs and now CPUs. The interface is faster than PCI Express, thus NVLink will be the backbone for most large systems rather than PCIe-based solutions like CCIX and CXL.

    Grace will be NVIDIA’s enterprise processor taking on its x86 cousins, but it will also be incorporated into platforms like Bluefield (Fig. 3).

    3. Grace will be showing up in a number of NVIDIA platforms going forward, including the blending of the Grace CPU and Ampere GPU in Bluefield.
    3. Grace will be showing up in a number of NVIDIA platforms going forward, including the blending of the Grace CPU and Ampere GPU in Bluefield.
    About the Author

    William G. Wong | Senior Content Director - Electronic Design and Microwaves & RF

    I am Editor of Electronic Design focusing on embedded, software, and systems. As Senior Content Director, I also manage Microwaves & RF and I work with a great team of editors to provide engineers, programmers, developers and technical managers with interesting and useful articles and videos on a regular basis. Check out our free newsletters to see the latest content.

    You can send press releases for new products for possible coverage on the website. I am also interested in receiving contributed articles for publishing on our website. Use our template and send to me along with a signed release form. 

    Check out my blog, AltEmbedded on Electronic Design, as well as his latest articles on this site that are listed below. 

    You can visit my social media via these links:

    I earned a Bachelor of Electrical Engineering at the Georgia Institute of Technology and a Masters in Computer Science from Rutgers University. I still do a bit of programming using everything from C and C++ to Rust and Ada/SPARK. I do a bit of PHP programming for Drupal websites. I have posted a few Drupal modules.  

    I still get a hand on software and electronic hardware. Some of this can be found on our Kit Close-Up video series. You can also see me on many of our TechXchange Talk videos. I am interested in a range of projects from robotics to artificial intelligence. 

    Email

    Continue Reading

    Sponsored Recommendations

    Comments

    To join the conversation, and become an exclusive member of Electronic Design, create an account today!