Innoscience announced a collaboration with NVIDIA, a global leader in AI technology, to jointly promote the large-scale implementation of an 800 VDC power architecture in AI data centers.

NVIDIA's 800 VDC architecture is the latest generation of power systems, specifically designed to power future megawatt-scale computing infrastructure efficiently. Compared to traditional 54 V power systems, the 800 VDC architecture offers significant advantages in system efficiency, heat dissipation, and reliability, enabling it to support a 100x to 1000x increase in AI computing power.

As the world's leading GaN IDM, Innoscience's third-generation GaN devices offer exceptional high frequency, high efficiency, and high power density. They provide NVIDIA's 800 VDC architecture with a full-link GaN power supply solution, from 800 V input to GPU terminals, covering 15 V to 1200 V. With the deep integration of 800 VDC power architecture and GaN technology, AI data centers will achieve a quantum leap from kilowatts to megawatts in the coming years, ushering in an era of more efficient, reliable, and greener AI computing.

The synergy between Innoscience’s cutting-edge GaN technology and NVIDIA’s forward-looking 800 VDC architecture marks a significant leap forward for AI data center design. Together, the two companies aim to accelerate the industry’s transition from kilowatt-scale systems to megawatt-class infrastructure, paving the way for a new era of highly efficient, scalable, and sustainable AI computing.

Click here to know more about the GaN hub in everything PE.