Nvidia recently invested $2 billion into the semiconductor company Marvell Technology. This strategic partnership aims to link the latter’s custom silicon and networking technologies with the tech giant’s AI ecosystem.
The partnership targets scalable AI data centres and telecom networks, including 5G and 6G AI‑RAN deployments, by combining Marvell’s custom XPU accelerator chips and optical expertise with Nvidia’s GPUs, CPUs and networking platforms.
The two companies will also collaborate on silicon photonics and optical interconnects.
The pact takes advantage of Nvidia’s NVLink Fusion, which allows customers to build custom XPUs that work with its systems, integrating GPUs, networking, storage and software into a single AI infrastructure.
Nvidia CEO and founder Jensen Huang explained the partnership will enable “customers to leverage Nvidia’s AI infrastructure ecosystem and scale to build specialised AI compute”.
Marvell chair and CEO Matt Murphy stated by connecting its “high-performance analogue, optical DSP, silicon photonics and custom silicon to Nvidia’s expanding AI ecosystem through NVLink Fusion, we are enabling customers to build scalable, efficient AI infrastructure”.
Financial terms and the length of the agreement were not disclosed.
Source: Mobile World Live
Image Credit: Nvidia
