Brief

Researchers have developed a novel method to overcome the significant time and resource costs associated with circuit validation in semiconductor design. Their approach utilizes a foundation model pre-trained on millions of regression tasks, which learns to adapt to new circuits instantly without requiring hyperparameter tuning. This learned prior model, combined with an automated feature selector, achieves state-of-the-art accuracy while reducing validation costs by over tenfold. AI

Researchers have developed OpenACMv2, an open-source framework designed to optimize Digital Compute-in-Memory (DCiM) hardware for neural networks. This framework employs a two-level optimization strategy to balance power, performance, and area (PPA) with accuracy constraints. The first level searches for optimal architecture configurations, while the second refines transistor-level parameters, enabling significant efficiency gains with minimal accuracy loss. AI