NVLink

NVLink is a communications protocol developed by Nvidia. NVLink specifies a point-to-point connection between a CPU and a GPU and also between a GPU and another GPU rated at 80 GB/s.[1] NVLink products introduced to date focus on the high-performance application space.

On 5 April 2016, Nvidia announced that NVLink will be implemented in the forthcoming Pascal-microarchitecture-based GP100 GPU, which will be used in, for example, Nvidia Tesla P100 products.[2]

The US Department of Energy contracted Nvidia and IBM to build two supercomputers named "Summit" and "Sierra",[3] which will use NVLink for the node interconnects, while a variant of InfiniBand will be used for the system interconnects.[4] These systems will combine Nvidia's Volta architecture with the POWER9 family of CPUs.

See also

References

  1. ↑ "What Is NVLink?". Nvidia. 2014-11-14.
  2. ↑ "Inside Pascal: NVIDIA's Newest Computing Platform". 2016-04-05.
  3. ↑ "Whitepaper: Summit and Sierra Supercomputers" (PDF). 2014-11-01.
  4. ↑ "Nvidia Volta, IBM POWER9 Land Contracts For New US Government Supercomputers". AnandTech. 2014-11-17.
This article is issued from Wikipedia - version of the 11/10/2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.