The World’s First Deep Learning Artificial Intelligence Supercomputer in a Box

Data scientists and artificial intelligence (AI) researchers require accuracy, simplicity, and speed for deep learning success. Faster training and iteration ultimately means faster innovation and timeto- market/time to solution.

The NVIDIA® DGX-1™ is the world’s first purpose-built system optimized for deep learning, with fully integrated hardware and software that can be deployed quickly and easily. Its revolutionary performance significantly accelerates training time, making it the world's first deep learning supercomputer in a box.

Infinite Computing for Infinite Opportunities
NVIDIA DGX-1 is the first system built with groundbreaking Pascal™-powered NVIDIA Tesla® P100 GPU accelerators, interconnected with NVIDIA NVLink™. NVIDIA Pascal architecture was designed as the engine of computers that learn, see, and simulate our world—a world with an infinite appetite for computing.

Supercharge Deep Learning Performance
The NVIDIA DGX-1 software stack includes major deep learning frameworks, the nVIDIA Deep Learning SDK, the DIGITS™ GPU training system, drivers, and CUDA®, for designing the most accurate deep neural networks (DNN). This powerful system includes access to cloud management services for container creation and deployment, system updates, and an application repository. The combination of these software capabilities running on Pacal-powered Tesla GPUs allows applications to run up to 12x faster than any previous GPU-accelerated solutions.

Iterate and Innovate Faster
High-performance training accelerates your productivity, which means faster time-to-insight, and faster time-to market/time-to solution.

Deploy Quickly and Simply
The turnkey NVIDIA DGX-1 system provides plug-and-play setup and takes you from power-on to deep learning in just minutes.

Maximize Your Investment
NVIDIA DGX-1 support lets you improve productivity and reduce system downtime. Hardware and software support provides access to NVIDIA deep learning expertise and includes cloud management essentials, software upgrades and updates, and priority resolution of your critical issues.

Stay Ahead of the Competition
NVIDIA DGX-1 is engineered with groundbreaking technologies that deliver the fastest solutions for your deep learning training.

GPUs 8x Tesla P100
TFLOPS (GPU FP16 /CPU FP32)170/3
GPU Memory 16 GB per GPU
CPU Dual 20-core Intel® Xeon® E5-2698 v4 2.2 GHz
NVIDIA CUDA® Cores 28672
System Memory 512 GB 2133 MHz DDR4 LRDIMM
Storage 4x 1.92 TB SSD RAID 0
Network Dual 10 GbE, 4 IB EDR
Software Ubuntu Server Linux OS DGX-1 Recommended GPU Driver
System Weight 134 lbs
System Dimensions 3U, 866 D x 444 W x 131 H (mm)
Packing Dimensions 1180 D x 730 W x 284 H (mm)
Maximum Power Requirements 3200W
Operating Temperature Range1 0 - 35 °C

Net Direct Advantage
Est. in 1995, Net Direct's HPC practice bridges scientific objectives to the most optimal platform requirements. Through our partnerships with the leading HPC platform and sub component technology mfg, we offer the broadest range of HPC solution options available. This ensure your custom engineered HPC solution is ideally suited, tightly integrated, of high quality and comes with the level of support you need for all for significantly less.

For more including pricing contact Net Direct today!
Net Direct Inc. is a member of the NVIDIA Partner Network as a Preferred Solution Provider and previously (since 2008/the dawn of GP-GPU computing) a NVIDIA Tesla Preferred Partner.