TAG: Learning Circuit Spatial Embedding From Layouts
This addresses the reliance on human expertise in circuit design automation, offering a novel paradigm for machine learning applications in industrial settings.
The paper tackles the problem of automating analog and mixed-signal circuit design by introducing TAG, a method that learns spatial embeddings from layouts without manual labeling, achieving accurate predictions of layout distances and demonstrating transferability to tasks like layout matching and parasitic capacitance prediction.
Analog and mixed-signal (AMS) circuit designs still rely on human design expertise. Machine learning has been assisting circuit design automation by replacing human experience with artificial intelligence. This paper presents TAG, a new paradigm of learning the circuit representation from layouts leveraging text, self-attention and graph. The embedding network model learns spatial information without manual labeling. We introduce text embedding and a self-attention mechanism to AMS circuit learning. Experimental results demonstrate the ability to predict layout distances between instances with industrial FinFET technology benchmarks. The effectiveness of the circuit representation is verified by showing the transferability to three other learning tasks with limited data in the case studies: layout matching prediction, wirelength estimation, and net parasitic capacitance prediction.