Marvell早年跳級押注晶片製程，受惠AI需求見成效

Marvell’s early chipmaking gamble pays off amid AI demand

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.”

Chu spoke with theCUBE’s John Furrier for theCUBE + NYSE Wired: AI Factories – Data Centers of the Future interview series, during an exclusive broadcast on theCUBE, SiliconANGLE Media’s livestreaming studio. He was joined by David Lazovsky (right), executive vice president and general manager of the Data Center Networking Business Group at Marvell, and they discussed how the company has built its business around improving efficiency for enterprise AI architectures. (* Disclosure below.)

Optical solutions for AI architectures

A cornerstone of Marvell’s platform is serializer/deserializer (SerDes) technology, which provides high-speed, multi-gigabit data transmission for AI clusters, cloud data centers, and enterprise networking. Scaling AI infrastructure is a critical challenge in today’s data centers, and Marvell has been using SerDes to improve power efficiency.

In September, the company unveiled 2-nanometer optical interconnect technologies designed to support AI scale-up architectures, which tightly connect multiple computing and memory resources to operate as a larger system.

“Why interconnectivity with scale-up moving from copper to optics is so important is because processor-to-processor data transmission, roughly 85% of total data transmission, is happening inside of these scale-up networks, and only 15% across the scale-out network,” Lazovsky told theCUBE. “If you can positively impact the energy efficiency, you can move the needle significantly. We’re developing technologies that leverage optics and SerDes … that significantly reduce the total power consumption.”

Marvell’s focus on efficient architecture has also led to advances in high-bandwidth memory. In August, the company announced a Photonic Fabric Memory Module designed to enable a shared-memory tier across AI infrastructure. The technology combines DDR5 memory, high-bandwidth memory caching and optical connectivity to allow memory resources to be shared across AI systems.

“For the first time ever, Marvell has developed optically interconnected high capacity, high bandwidth memory,” Lazovsky said. “There are two stacks of high bandwidth memory, and this supports a module with up to eight stacks of Double Data Rate 5. It provides you the ability to decouple memory capacity from compute for the first time.”

Marvell’s advances in memory and optical networking have strengthened its position in the AI infrastructure market. Nvidia Corp. announced a $2 billion investment in the firm earlier this year, and Marvell recently announced an agreement that it would design custom AI chips for Google LLC.

“This is the biggest buildout in CapEx in human history,” Chu said. “In terms of our connectivity business, our networking business, and our custom business, we’re attached to the fastest growing part of those markets. We have the leading technology, we have the customer credibility, a track record of execution.”

Here’s the complete video interview, part of SiliconANGLE’s and theCUBE’s coverage of theCUBE + NYSE Wired: AI Factories – Data Centers of the Future interview series:

(* Disclosure: TheCUBE is a paid media partner for theCUBE + NYSE Wired: AI Factories – Data Centers of the Future interview series. Neither Marvell, the sponsor of theCUBE’s event coverage, nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE

A message from John Furrier, co-founder of SiliconANGLE:

Support our mission to keep content open and free by engaging with theCUBE community. Join theCUBE’s Alumni Trust Network, where technology leaders connect, share intelligence and create opportunities.

• 15M+ viewers of theCUBE videos, powering conversations across AI, cloud, cybersecurity and more
• 11.4k+ theCUBE alumni — Connect with more than 11,400 tech and business leaders shaping the future through a unique trusted-based network

SiliconANGLE Media is a recognized leader in digital media innovation, uniting breakthrough technology, strategic insights and real-time audience engagement. As the parent company of SiliconANGLE, theCUBE Network, theCUBE Research, CUBE365, theCUBE AI and theCUBE SuperStudios — with flagship locations in Silicon Valley and the New York Stock Exchange — SiliconANGLE Media operates at the intersection of media, technology and AI.

Founded by tech visionaries John Furrier and Dave Vellante, SiliconANGLE Media has built a dynamic ecosystem of industry-leading digital media brands that reach 15+ million elite tech professionals. Our new proprietary theCUBE AI Video Cloud is breaking ground in audience interaction, leveraging theCUBEai.com neural network to help technology companies make data-driven decisions and stay at the forefront of industry conversations.