Use Cases for Chiplets in AI Clusters
What's driving the surge in chiplet technology investment?
Tony Chan Carusone, Chief Technology Officer from Alphawave Semi, explains:
- AI is the primary driver, enabled by mature die-to-die interface technologies that allow multiple chiplets to function as one large chip
- High-performance compute chiplets require high bandwidth density and low latency interfaces to effectively communicate between dies
- IO and optical chiplets are crucial for scaling AI clusters to thousands of elements, enabling connectivity across vast distances
Related Videos
- Chiplets for generative AI
- Chiplets for the future of AI
- Connectivity for AI Everywhere: The Role of Chiplets
- Photonic Fabric Interface Chiplets for AI XPU Optical Connectivity
Latest Videos
- Custom Tool Development Strategies for Chiplet Reliability
- Imec Automotive Chiplet Forum 2025: Interview with Arm's John Kourentis
- Imec Automotive Chiplet Forum 2025: Interview with imec's Bart Plackle
- Chiplets for Automotive: Scalable Compute with Next-Gen Packaging
- Investigating Open Chiplets for HPC Beyond Exascale