DGX-1

ast-track your initiative with a solution that works right out of the box, so you can gain insights in hours instead of weeks or months. NVIDIA® DGX-1™ is the integrated software and hardware system that supports your commitment to AI research with an optimized combination of compute power, software and deep learning performance.

NVIDIA DGX-1 removes the burden of continually optimizing your deep learning software and delivers a ready-to-use, optimized software stack that can save you hundreds of thousands of dollars. It includes access to today’s most popular deep learning frameworks, NVIDIA DIGITS™ deep learning training application, third-party accelerated solutions, the NVIDIA Deep Learning SDK (e.g. cuDNN, cuBLAS, NCCL), CUDA® toolkit, NVIDIA Docker and NVIDIA drivers.

NVIDIA GPUs 8X Tesla V100 8X Tesla P100
TFLOPS
(GPU FP16)
960 170
GPU Memory System up to 128GB
CPU Dual 20-Core Intel Xeon
E5-2698 v4 2.2 GHz
NVIDIA CUDA® Core 40,960 28,672
NVIDIA Tensor Core
(V100 Standard System)
5,120 N/A
Max. Power Cost 3,200 W
System Memory 512GB2,133MHzDDR4
LRDIMM
Storage 4X 1.92 TB SSD RAID 0
Network Dual 10GbE, 최대 4 IB EDR
Software Ubuntu Linux Host OS
Check Software Stack for details
System Weight 134 lbs
System Size 866D x 444W x 131H(mm)
Package Size 1,180D x 730W x 284H(mm)
Operating Temperature 10 ~ 35℃