Home 9 Semiconductors 9 GlobalFoundries Expands Vermont SiGe Capacity for Marvell

GlobalFoundries Expands Vermont SiGe Capacity for Marvell

by | Sep 21, 2026

The multiyear agreement supports optical transceivers, near-packaged optics and co-packaged optics as AI and cloud bandwidth demand grows.
Image: Globalfoundries

MALTA, NY, Sep 21, 2026 – GlobalFoundries (GF) will expand silicon germanium (SiGe) manufacturing capacity at its Burlington, Vermont, facility to meet Marvell Technology’s optical connectivity demand. The multiyear agreement between GF and Marvell supports pluggable optical transceivers, near-packaged optics (NPO) and co-packaged optics (CPO).

GF’s SiGe technology supports 200G-per-lane optical connectivity. Its roadmap addresses higher-speed generations as AI and cloud data centers require more bandwidth. The SiGe portfolio provides high-frequency performance, signal integrity and power efficiency for optical networking applications.

GF also continues to co-integrate SiGe, silicon photonics and advanced packaging for optical connectivity architectures, including NPO and CPO. The capacity agreement builds on existing production and collaboration with Marvell.

“AI is fundamentally changing the way data centers are built, and connectivity is becoming increasingly critical to unlocking the performance of these systems,” said Robb Johnson, vice president, Foundry Technology, Marvell. “As the industry moves toward higher-bandwidth optical architectures, including NPO and CPO, Marvell is investing aggressively to lead this transition. Our expanded collaboration with GF will help ensure we have the SiGe technology and manufacturing capacity to support the significant growth we see ahead.”

“SiGe is where GF’s decades of high-performance radio frequency and analog leadership translate directly into breakthrough optical performance,” said Shankaran Janardhanan, senior vice president of Photonics & RF businesses at GF. “This agreement reinforces our long-standing relationship with Marvell and reflects the critical role SiGe technology plays in enabling high-speed optical networking for AI infrastructure. We will continue investing in our technology roadmap and manufacturing capabilities both in the U.S. and around the world to support our customers’ future growth.”

Source: GlobalFoundries

About GlobalFoundries

GlobalFoundries is a semiconductor foundry that provides advanced manufacturing services for integrated circuits. It offers a range of technologies, including CMOS, RF, embedded memory, silicon photonics, and FinFET, catering to automotive, communications, defense, data center, industrial, and consumer electronics applications. Founded in 2009 after being spun off from AMD, GlobalFoundries has over a decade of experience delivering tailored semiconductor solutions. The company supports fabless chipmakers with design enablement, IP services, and process technologies to accelerate innovation and meet global demand. Headquartered in Malta, New York, it operates manufacturing sites in the U.S., Germany, and Singapore. The company develops technologies for emerging markets, supporting digital applications that demand energy efficiency and reliable performance.

About Marvell Technology

Marvell Technology, established in 1995, is based in Santa Clara, CA. The company develops semiconductors used in data infrastructure, including ASICs, data processing units (DPUs), storage controllers, and connectivity solutions. Its products are deployed across sectors such as data centers, 5G networks, cloud services, automotive, and enterprise systems. Marvell operates globally, with key markets in China, the United States, and Southeast Asia. It has expanded its capabilities through acquisitions, including Cavium, Aquantia, and Inphi, which added technologies in areas like AI acceleration, high-speed data transfer, and silicon photonics. With more than 7,000 employees and over 10,000 patents, Marvell focuses on delivering components supporting high-performance compute, storage, and networking applications, including those that enable AI workloads and infrastructure scaling.