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 Chiplet
- Optical Chiplet
- Reverse Gearbox Chiplet
- FlexGen Multi-Die Smart Network-on-Chip (NoC) IP
- Ncore Multi-Die Interconnect IP
- Integrated voltage regulator (IVR) chiplet
Related Videos
- Photonic Fabric Interface Chiplets for AI XPU Optical Connectivity
- AI-Driven Thermal Prediction for Enhanced Reliability in 3D HBM Chiplets
- Chiplets for generative AI
- Chiplets for the future of AI
Latest Videos
- The European Chip Ecosystem
- Scaling up AI Compute, Memory and Connectivity
- CURIE: A Cycle-Accurate and Synthesizable UCIe Interface for the Agile Design and Co-Simulation of Chiplets
- Federated Chiplet Design and Simulation
- Custom HBM as a System: Co-designing the Base Die, Die to Die Power, and Package Thermals for AI Accelerators