Products & Solutions
NVIDIA GPU Compute and Accelerators Overview
Enquire about this solution

NVIDIA DGX SuperPOD


NVIDIA DGX SuperPOD™ offers a proven design approach for building your GPU-accelerated AI data centre with NVIDIA DGX™ systems, leveraging NVIDIA’s best practices and insights gained from real-world deployments. The SuperPOD reference architectures provide proven implementation plans for multiple DGX systems, networking and storage which allows for supercomputers to be built quickly and efficiently, and with known performance parameters. This delivers AI ready infrastructure faster, accelerating your ROI.

XENON is APAC’s only NVIDIA Certified SuperPOD Specialist. This reflects XENON’s decades long expertise in rolling out NVIDIA GPU solutions, and builds on our previous certification as DGX-Ready Managed Service Provider (again, the only one in APAC!). The XENON team offers advanced expertise in the SuperPOD reference architectures and installation, cluster management, AI frameworks and job scheduling, and deploying NVIDIA NIMs on large multi-node supercomputers.

The DGX SuperPOD is an optimised high performance storage, networking and NVIDIA Blackwell powered DGX Systems. Combined in a tested reference architecture, the SuperPOD is designed and optimised to provide maximum performance at scale.

The SuperPOD is the foundation of the new AI Factories which are delivering foundational AI solutions for government departments and private enterprises, and are the building blocks for AI Cloud providers.

SuperPOD deployment provides:

  • A turnkey AI supercomputer, ready to go.
  • A modular architecture that can scale to 10,000+ GPUs and tackle trillion parameter models.
  • Enterprise grade cluster management and workload scheduling that accelerates developer productivity.

The DGX SuperPOD is also designed to be compatible with leading storage and networking technology providers. XENON offers a portfolio of NVIDIA DGX SuperPOD reference architecture solutions with leading storage vendors including: NetApp, IBM Spectrum, DDN, Pure Storage, VAST Data, and WEKA. All incorporate the best practice of NVIDIA DGX SuperPOD design and are delivered as fully-integrated and ready-to-deploy solutions to make your data centre AI deployments simpler and faster.

Talk to a Solutions Architect

Reference Architecture Whitepaper

Request the NVIDIA DGX SuperPOD Reference Architecture Whitepaper for more detailed information on the architecture and design background to the NVIDIA DGX SuperPOD.

  • This field is for validation purposes and should be left unchanged.

DGX SuperPOD Video

Take a tour of the NVIDIA data centre, and their DGX SuperPOD that is one of the fastest supercomputer in the world, and built in the shortest amount of time!