Marvell Unveils 2nm Optical Interconnects for AI Scale-Up
Marvell has unveiled 2-nanometer optical interconnect technologies for AI scale-up architectures that connect computing and memory resources as part of a larger system. It also introduced the Photonic Fabric Memory Module, which combines DDR5 memory, high-bandwidth memory caching and optical connectivity to support a shared-memory tier. Marvell executive David Lazovsky said the company’s optics and SerDes technologies are intended to reduce total power consumption, but the report provides no independent benchmarks. The report also says Nvidia made a $2 billion investment in Marvell and that the company agreed to design custom AI chips for Google.
The report presents Marvell’s memory and optical networking advances as strengthening its position in AI infrastructure. Its technologies address power efficiency and resource sharing in AI systems, areas the company says are important as AI infrastructure scales.
Eight years ago, chipmaker Marvell Technology Inc. decided to play leapfrog with nanometers, and its trajectory has been steadily upward since.
In semiconductor manufacturing, nanometer designations identify generations of chipmaking technology, known as process nodes, rather than the exact physical dimensions of transistors. Advanced process nodes generally enable greater transistor density and improvements in performance and power efficiency.
Chipmakers have usually followed a set progression downward in nanometer sizes, and skipping a level constituted a significant risk. Marvell decided to make that bet.
“Back around 2018, 2019 ,we made a decision that if we wanted to do data infrastructure, we needed to be a leader and not a follower, and that meant jumping to the latest process node with the best technology,” said Will Chu (pictured, left), executive vice president and general manager of the Custom Cloud Solutions Business Unit, at Marvell. “So, we skipped 7 nanometer. We had products like 12 and 16 nanometer and the next logical one would have been 7. We jumped all the way to 5…we kept going – 3 nanometer, 2 nanometer, 14 angstrom. We’ve been running that playbook, and it’s really served as the foundation for our growth to be a leader in the cloud.”
#Marvell Technology#Marvell 2nm optical interconnect technologies#Photonic Fabric Memory Module#Google#Nvidia