Marvell and NVIDIA partner to integrate NVLink Fusion with custom silicon for AI Infrastructure
Marvell Technology partnering with NVIDIA to integrate NVIDIA NVLink Fusion technology into Marvell’s custom cloud platform silicon. NVLink Fusion enables customers to combine custom XPU silicon with NVIDIA’s NVLink connectivity, rack-scale hardware, software, and other technologies to develop AI infrastructure.
Marvell’s custom platform leverages its expertise in system and semiconductor design, advanced manufacturing processes, and a portfolio of technologies, including electrical and optical serializer/deserializers (SerDes), die-to-die interconnects for 2D and 3D devices, advanced packaging, silicon photonics, co-packaged copper, custom high-bandwidth memory (HBM), system-on-chip (SoC) fabrics, optical IO, and PCIe Gen 7 interfaces. This allows Marvell to collaborate with customers to create tailored platforms for infrastructure performance and efficiency.
You've read this far — sign in to keep reading