NVIDIA DGX-1

AI 研究適用的深度學習伺服器

深度學習的最快途徑

打造深度學習平台比選擇適當的伺服器和 GPU 更重要。若您規劃在公司裡實作人工智慧,則須謹慎選擇並整合複雜的應用軟體和硬體。NVIDIA® DGX-1 透過立即可用的解決方案加快您的計畫,讓您可以在數小時內獲得見解,而非數週或數個月。

DISCOVER THE BENEFITS

TURN DATA INTO KNOWLEDGE

NVIDIA DGX-1 lets you quickly uncover patterns in large data sets leading to new knowledge and insights in hours or minutes.

EFFORTLESS PRODUCTIVITY

簡化工作流程並改善團隊合作,立即提升生產力。 DGX-1 is designed to save you from the typical deep learning setup costs, which can be hundreds of thousands of dollars in software engineering hours, and months of delays for the open source software to stabilize.

REVOLUTIONARY AI PERFORMANCE

Unlock 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 than other GPU-based systems by using the NVIDIA GPU Cloud Deep Learning Stack with optimized versions of today’s most popular frameworks.

INVESTMENT PROTECTION

Get the full power of NVIDIA deep learning expertise backing your project, so you won’t waste time and money struggling to get the results you expect. NVIDIA enterprise-grade support saves you from troubleshooting hardware and open source software so you spend less time tuning and optimizing and more time focused on discovery.

NVIDIA DGX-1 DEEP LEARNING SERVER

Explore the powerful components of DGX-1.
NVIDIA TESLA V100
The first GPU architecture to incorporate Tensor Core technology designed for deep learning, now with 32GB of memory.
QUAD EDR IB
High-bandwidth and low-latency, with a total of 800 Gb/s of communication.
TWO INTEL XEON CPUS
For boot, storage management, and deep learning framework coordination.
NEXT GENERATION NVIDIA NVLINK
High-speed interconnect 300 GB/s per GPU, 10X faster than current PCIe Gen3 x16 interconnections.
THREE RACK-UNIT ENCLOSURE
Fits in a compact rack space, using 3,500 Watts of maximum system power.

DGX-1 Architecture Advancements

System Level Specifications
NVIDIA DGX-1 with Tesla V100

TFLOPS (deep learning)

1000

CUDA Cores

40,960

Tensor Cores

5,120

NVLink vs PCIe Speed-up

10X

Deep Learning Training Speed-up

3X

NVIDIA® DGX-1 系統上的 Red Hat® Enterprise Linux®

ITERATE AND INNOVATE FASTER

High-performance training accelerates your productivity, which means faster time to insight and faster time to market.

NVIDIA DGX-1 Delivers 140X Faster Deep Learning Training

NVIDIA DGX POD

適合人工智慧企業的 IT 認可基礎架構

開始使用

NVIDIA DGX 的共置服務

立即 訂購 NVIDIA DGX

提供彈性租用選擇