Accelerated Infrastructure for the AI Era

Data Infrastructure for the AI Era
Accelerated infrastructure for connectivity and custom compute

Marvell Enables AI Infrastructure


To realize the promise of AI, hyperscalers are undertaking one of the largest infrastructure buildouts in history—and they rely on Marvell as a critical AI infrastructure partner. Marvell designs custom silicon tailored for any application and offers the industry’s most comprehensive portfolio of interconnects and network switch products. From custom compute to rack, row, data center, campus and multi-campus connectivity, Marvell enables the world’s most advanced AI infrastructure.

 

Investor Event


At this custom AI investor event, the Marvell leadership team shares its perspective on the rapidly evolving AI market and technology landscape, with a particular focus on custom silicon and custom cloud solutions for hyperscalers.

 

Ra6XrUHULNtk1nredHEPnJ
NVIDIA and Marvell: Powering Accelerated Computing

NVIDIA and Marvell: Powering Accelerated Computing


Accelerated computing requires tremendous bandwidth. NVIDIA is working with Marvell to deliver it. Achyut Shah, SVP & GM, Connectivity Business Unit at Marvell, describes the history of the collaboration.

 

The Rise of Customized AI Factories


Marvell President and COO Chris Koopmans joins Daniel Newman at the SixFive Summit to explore the rapidly evolving AI market landscape, including emerging hyperscalers and sovereign AI. Chris discusses the rise of custom silicon and the role Marvell plays in powering the next generation of AI factories.

 

The Rise of Customized AI Factories
Custom HBM Compute Architecture

Marvell Custom HBM Compute Architecture

Marvell has developed a new custom HBM compute architecture that optimizes custom XPU performance and TCO. In collaboration with industry leaders like Micron, Samsung and SK Hynix, Marvell is setting new benchmarks for AI accelerators.

Connectivity for the Million XPU Era


Xi Wang, Marvell SVP & GM, Connectivity BU joins Will Townsend from SixFive Media to explore the role of high-bandwidth connectivity in the rapid evolution of AI infrastructure and data centers. Xi discusses the innovations and challenges that are unfolding at every level, from the XPU and rack to the data center to multi-site AI clusters.

 

 

Connectivity for the Million XPU Era

Marvell optical DSPs: Powering the future of AI infrastructure


AI and cloud computing are pushing network demands to unprecedented levels, requiring optical DSPs to deliver ultra-high bandwidth, low latency, and energy efficiency. Marvell is leading this transformation with advanced PAM4 and coherent DSP solutions that power AI fabrics, data center interconnects, and telecom networks—driving the future of high-performance connectivity.

 

The Evolution of AI Interconnects


The rapid expansion in the size and capacity of AI workloads is significantly impacting both computing and network technologies in the modern data center. 

The desire for larger clusters with shorter compute times has driven heightened focus on networking interconnects, with designers embracing state-of-the-art technologies to ensure efficient data movement and communication between the components comprising the AI cloud.

 

Marvell Launches Next-generation CXL Switch, Enabling Memory Pooling to Break Through the AI “Memory Wall”

Marvell Launches Next-generation CXL Switch, Enabling Memory Pooling to Break Through the AI “Memory Wall”

Learn More

Marvell at OFC 2025

Marvell Launches Industry’s First 260-lane PCIe 6.0 Switch for AI Data Center Scale-up Infrastructure

Learn More

Custom Compute in the AI Era

Inside Marvell’s Expanding Custom Silicon Opportunity

Learn More

Contact Us

We believe better partnerships help to build better technologies. Let’s connect and see what we can design together!

Thank You for Your Interest

We will be in touch with you soon!