Product Overview
The NVIDIA DGX-1 deep learning system comprises a combination of hardware and software that delivers faster and more accurate training of neural networks. Purpose built for deep learning and AI analytics, the DGX-1 delivers performance equivalent to 250 conventional CPU-only servers.
While many solutions offer GPU-accelerated performance, only NVIDIA DGX-1 unlocks the full potential of the latest NVIDIA Tesla V100, including next generation NVIDIA NVLink, and new Tensor Core architecture.
DGX-1 delivers 4X faster training speed than other GPU-based systems by using the NVIDIA GPU Cloud Deep Learning Stack with optimised versions of today’s most popular frameworks.
Furthermore, the latest update to the DGX-1 architecture is powered by eight NVIDIA Tesla V100 GPU accelerators - based on the Volta architecture, but with 5120 CUDA cores, 640 Tensor Cores plus 32GB of HBM2 memory.
Key Features
Quad EDR IB NVIDIA Tesla V100 Next Generation NVIDIA NVLink Two Intel Xeon CPUs 3U Rackmount Case
-
CPU Family
Intel Xeon
-
CPU Manufacturer
Intel
-
CPU Quantity (Installed)
2
-
Form Factor
3U
-
GPU Family
NVIDIA Tesla Series
-
GPU Manufacturer
NVIDIA
-
GPU Model
V100
-
Infiniband Controller
4 x EDR Infiniband
-
Manufacturer
NVIDIA