Infineon and NVIDIA collaborate on industry-first 800V power delivery architecture for AI data centres

2 mins read

Infineon Technologies, together with NVIDIA, is working to revolutionise the power delivery architecture required for future AI data centres.

800V power delivery architecture for AI data centres Credit: Infineon

The collaboration between the two companies is developing the next generation of power systems based on a new architecture with central power generation of 800 V high-voltage direct current (HVDC).

The new system architecture is said to significantly increase energy-efficient power distribution across the data centre and allows power conversion directly at the AI chip (Graphic Processing Unit, GPU) within the server board.

Infineon has considerable expertise in power conversion solutions from grid to core based on all the relevant semiconductor materials - silicon (Si), silicon carbide (SiC) and gallium nitride (GaN) – and is working to accelerate the roadmap to a full scale HVDC architecture.

This step paves the way for the implementation of advanced power delivery architectures in accelerated computing data centres and will enhance both reliability and efficiency.

As AI data centres already are going beyond 100,000 individual GPUs, the need for more efficient power delivery is becoming increasingly important. AI data centres will require power outputs of one megawatt (MW) and more per IT rack before the end of the decade. Consequently, the HVDC architecture coupled with high-density multiphase solutions will look to set a new standard for the industry, driving the development of high-quality components and power distribution systems.

“Infineon is driving innovation in artificial intelligence,” said Adam White, Division President Power & Sensor Systems at Infineon. “The combination of Infineon's application and system know-how in powering AI from grid to core, combined with NVIDIA’s expertise in accelerated computing, paves the way for a new standard for power architecture in AI data centres to enable faster, more efficient and scalable AI infrastructure.”

"The new 800V HVDC system architecture delivers high reliability, energy-efficient power distribution across the data centre,” said Gabriele Gorla, vice president of system engineering at NVIDIA. “Through this innovative approach, NVIDIA is able to optimise the energy consumption of our advanced AI infrastructure, which supports our commitment to sustainability while also delivering the performance and scalability required for the next generation of AI workloads.”

At present, the power supply in AI data centres is decentralised, which means that the AI chips are supplied with power by many power supply units (PSU). The future system architecture will be centralised, making the best possible use of the constraint space in a server rack. This will increase the importance of leading-edge power semiconductor solutions using fewest power conversion stages and allowing upgrades to even higher distribution voltages.

Infineon said that it expects the proportion of power semiconductors in a centralised HVDC architecture to be similar or higher than in today's AC distribution architecture.