Nvidia DGX-1
From HandWiki
Revision as of 15:06, 23 July 2021 by imported>Gametune (add)
 | The topic of this article may not meet Wikipedia's general notability guideline. (May 2018) (Learn how and when to remove this template message) |
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
- ↑ "nvidia dgx-1". https://images.nvidia.com/content/technologies/deep-learning/pdf/61681-DB2-Launch-Datasheet-Deep-Learning-Letter-WEB.pdf.
- ↑ "inside pascal". https://devblogs.nvidia.com/parallelforall/inside-pascal/. "Eight GPU hybrid cube mesh architecture with NVLink"
- ↑ "deep learning supercomputer". https://www.engadget.com/2016/04/05/nvidia-dgx-1-deep-learning-supercomputer/.
- ↑ "DGX-1 deep learning system". http://images.nvidia.com/content/technologies/deep-learning/pdf/Datasheet-DGX1.pdf. "NVIDIA DGX-1 Delivers 75X Faster Training...Note: Caffe benchmark with AlexNet, training 1.28M images with 90 epochs"
- ↑ "DGX Server". Nvidia. https://www.nvidia.com/en-us/data-center/dgx-server/. Retrieved 7 September 2017.
 |
