Chiplets for Automotive – Are We There Yet?
By Nir Sever, Sr. Director, Business Development, proteanTecs
For decades, Automotive Electronics were based on semiconductors manufactured on mature and stable process technologies. Designs were well characterized for robustness; tight screening at the production line enforced quality; using industry-standard test methodologies such as JEDEC JESD22 and JESD47 [1] assured reliability. Functional Safety (FuSa) relies on monitoring software, system redundancy, and safety protocols. Today, Electric Vehicles (EV) and Autonomous Driving (ADAS) require using the most advanced semiconductor technologies. Reliability requirements exceed those commonly used for commercial applications, device screening becomes a challenge, and safety measures that take effect after an error has already occurred may be insufficient.
Recently, chipletbased designs are driving the most advanced semiconductors for High-Performance Computing (HPC) and AI. Is chiplet-based design ready to be adopted by the Automotive industry?
To read the full article, click here
Related Chiplet
- Interconnect Chiplet
- 12nm EURYTION RFK1 - UCIe SP based Ka-Ku Band Chiplet Transceiver
- Bridglets
- Automotive AI Accelerator
- Direct Chiplet Interface
Related Technical Papers
- Chiplets Are The New Baseline for AI Inference Chips
- Leveraging Modularity of Chiplets to Form a 4×4 Automotive FMCW-Radar in an eWLB-Package
- Efficient ESD Verification For 2.5/3D Automotive ICs
- PICNIC: Silicon Photonic Interconnected Chiplets with Computational Network and In-memory Computing for LLM Inference Acceleration
Latest Technical Papers
- AccelStack: A Cost-Driven Analysis of 3D-Stacked LLM Accelerators
- ATMPlace: Analytical Thermo-Mechanical-Aware Placement Framework for 2.5D-IC
- Nanoelectromechanical Systems (NEMS) for Hardware Security in Advanced Packaging
- Ultrafast Semiconductor Chip Bonding Using Intense Pulsed Light Soldering for Chip-on-Glass Packaging
- Hemlet: A Heterogeneous Compute-in-Memory Chiplet Architecture for Vision Transformers with Group-Level Parallelism