The NVIDIA® DGX-1™ is the world’s first purpose-built system for artificial intelligence (AI) and deep learning with fully integrated hardware and software that can be deployed quickly and easily.
- Built with groundbreaking new NVIDIA® Pascal-powered Tesla P100 accelerators, interconnected with NVIDIA® NVLink™.
- Its revolutionary performance significantly accelerates training time and most major frameworks making the NVIDIA® DGX-1 the world’s first deep learning supercomputer in a box.
- NVIDIA® DGX-1 is available at XENON® a valued NVIDIA® partner who has demonstrated competency in deep learning and supporting large systems.
Comprehensive Deep Learning Software Suite
The NVIDIA® DGX-1 system includes a complete suite of optimized deep learning software that allows researchers and data scientists to quickly and easily train deep neural networks.
The DGX-1 software includes the NVIDIA Deep Learning GPU Training System (DIGITS™), a complete, interactive system for designing deep neural networks (DNNs). It also includes the newly released NVIDIA®CUDA® Deep Neural Network library (cuDNN) version 5, a GPU-accelerated library of primitives for designing DNNs.
It also includes optimized versions of several widely used deep learning frameworks — Caffe, Theano and Torch. The DGX-1 additionally provides access to cloud management tools, software updates and a repository for containerized applications.
8x Tesla P100
TFLOPS (GPU FP16 / CPU FP32)
16 GB per GPU
Dual 20-core Intel® Xeon® E5-2698 v4 2.2 GHz
NVIDIA® CUDA® Cores
512 GB 2133 MHz DDR4
4x 1.92 TB SSD RAID 0
Dual 10 GbE, 4 IB EDR
Ubuntu Server Linux OS DGX-1 Recommended GPU Driver
- Height: 131mm
- Width: 444mm
- Depth: 866mm
- Height: 284mm
- Width: 730mm
- Depth: 1180mm
Maximum Power Requirements
Operating Temperature Range
10 – 35 °C