Nvidia DGX-1

Nvidia DGX-1 is a line of Nvidia produced servers and workstations which specialize in using GPGPU to accelerate deep learning applications. The servers feature 8 GPUs based on the Pascal or Volta daughter cards[1] with HBM 2 memory, connected by an NVLink mesh network.[2]

The product line is intended to bridge the gap between GPUs and AI accelerators in that the device has specific features specializing it for deep learning workloads.[3] The initial Pascal based DGX-1 delivered 170 teraflops of half precision processing,[4] while the Volta-based upgrade increased this to 960 teraflops.[5]

Successor

The successor of the Nvidia DGX-1 is the Nvidia DGX-2. Featuring higher performance of up to 2 Petaflops and new technologies such as NVSwitch.

References

  1. ↑ "nvidia dgx-1" (PDF).
  2. ↑ "inside pascal". Eight GPU hybrid cube mesh architecture with NVLink
  3. ↑ "deep learning supercomputer".
  4. ↑ "DGX-1 deep learning system" (PDF). NVIDIA DGX-1 Delivers 75X Faster Training...Note: Caffe benchmark with AlexNet, training 1.28M images with 90 epochs
  5. ↑ "DGX Server". DGX Server. Nvidia. Retrieved 7 September 2017.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.