The Future of AI Scale-Up: Latest Advancements in UALink Technology
As AI compute demand continues to accelerate, Cloud Service Providers, System OEMs, and IP/Silicon Providers require an efficient, optimized approach to overcome scale-up challenges in next-generation AI systems. UALink introduces a low-latency, high-bandwidth interconnect designed to enable seamless communication between accelerators and switches within AI computing pods. By boosting performance, improving power and cost efficiency, and fostering supply chain diversity and interoperability, UALink supports the growth of advanced AI/ML applications.
In this session, a panel of UALink experts will share the latest advancements to UALink technology, including In-Network Collectives, Management and Chiplet specifications. Attendees will learn how UALink will help build scalable multi-node AI systems and will also have the opportunity to engage directly with the panel to discuss future applications and the benefits of UALink-enabled devices.
Related Semiconductor IP
- UALink PHY + Controller
- Simulation VIP for UALink
- UALink Subsystem
- UALink Controller
- UALink PCS IP Core
Related Videos
- Analog AI Chips for Energy-Efficient Machine Learning: The Future of AI Hardware?
- Ask the Experts: The State of AI
- Hardware Innovation in the World's First RISC-V 50 TOPS AI Compute for Mass Production Development
- Ask the Experts: AI at the Edge
Latest Videos
- The Future of AI Scale-Up: Latest Advancements in UALink Technology
- Evaluating Asynchronous Machine Learning and Scientific Computing Applications on RISC-V, Arm and X86
- When AI Meets Hardware Security
- Sameer Wasson: AI Is Flipping Chip Design Upside Down
- Interview with GlobalFoundries VP at MIPS ‘Physical AI is Agentic AI at the Edge’ Taipei Event