NVIDIA, in partnership with BSI, has announced an update to to the DGX system software and infrastructure portfolio. The NVIDIA DGX GH200 system is now available for order. The NVIDIA ecosystem building blocks support our range of full-stack enterprise AI solutions.
With 128 petaflops of performance at FP8 precision, NVIDIA DGX GH200 delivers a leap in efficiency for enterprise AI development, offering lower total cost of ownership and 3.5x more energy efficiency compared to the previous H100 generation. Alongside the DGX systems release, is the latest evolution of the NVIDIA DGX BasePOD and the new NVIDIA Base Command.
DGX Grace Hopper Superchip
The new DGX GH200 features a new class of AI superchip, the NVIDIA Grace Hopper™ which interconnects into a singular GPU. The NVIDIA DGX™ GH200 is designed to handle terabyte-class models for massive recommender systems, generative AI, and graph analytics, offering a massive shared memory space with linear scalability for giant AI models.
Customers already using NVIDIA DGX POD to power the development of a broad range of enterprise applications, will see a 4x performance increase to last last generation. DGX GH200 reference architecture builds on the success of DGX, with new industry solutions targeting the biggest AI opportunities, including quantitative forecasting, natural language processing (NLP), healthcare and life sciences, and fraud detection.
Delivered as fully integrated and ready-to-deploy, the DGX BasePOD solutions range in size, from two to hundreds of DGX systems, with certified high-performance storage from our NVIDIA DGX storage technology partners including VAST Data, Dell, DDN, NetApp and WEKA.
BSI is an NVIDIA Elite Solution Provider and has received the Nvidia AI Champion and NVIDIA Star Performer in Northern Europe awards.
The new DGX GH200 can be viewed and ordered here.
To learn more...
Our AI solutions can be viewed here and our AI inception programme here.
Get in touch to discover how we could optimise your business with AI.