Comparative Study of AI-Based Optimization Techniques in VLSI Circuit Design Using Python

Successful design of very large scale integration (VLSI) circuits requires the use of various optimizations—power reduction, area, and time optimization. This requires the involvement of AI-based optimization techniques, such as machine learning (ML), deep learning (DL), genetic algorithms (GA), particle swarm optimization (PSO), and reinforcement learning (RL), to fulfill such tasks where traditional approaches fail to do so. The abundant libraries and ease of implementation have made Python a widely used platform in AIbased VLSI optimization. The methodology used in this study is a comparative study of different AI-based optimization algorithms used in the VLSI circuits. This research is structured in the following way: problem definition, data collection & preprocessing, implementation on Python, and performance evaluation. The best number was obtained using DL (CNN) and RL (95%) for the complex tasks (floorplanning and dynamic power management). ML (SVM) achieved high accuracy (90%) on well-defined problems but was not scalable for large designs. GA and PSO were good in performing global optimizations for problems like area minimization and routing but required fine-tuning of parameters. DL and RL had the highest computational complexity (GPU acceleration) and the lowest resource requirements, with easier implementation, with ML techniques. We found that DL and RL are better suited to large and complex designs and are slow for small and simple designs, whereas ML (SVM) and PSO are better suited to small and simple designs and are often slow given large and complex designs. Therefore, additional research is needed on the use of multiple AI techniques in a hybrid way to overcome limitations of the different techniques and enhance design efficiency. The results of this study can be applied in the following areas: AI-based Electronic Design Automation (EDA) tools, Power and performance optimization in semiconductor industries, Automated circuit design for advanced computing and development of Python-based AI stacks for VLSI research.