A Review of the Applications of Artificial Intelligence in the Full-Process Design of Integrated Circuits
Main Article Content
Keywords
artificial intelligence, integrated circuit design, EDA, large language model, reinforcement learning, graph neural network
Abstract
In the post-Moore era, traditional integrated circuit (IC) design faces bottlenecks such as long design cycles, high costs, and difficulty in PPA convergence. Artificial intelligence (AI), with its data-driven and global optimization capabilities, has pene trated the entire IC design process. This paper systematically reviews the technological evolution of AI in full-process IC design, with emphasis on algorithmic representation mechanisms—from how Graph Neural Networks (GNNs) model congestion as node and edge features, to how Circuit Transformers capture long-range dependencies in directed acyclic graphs. We also analyze engineering practices of AI -EDA integration in industry and discuss technical challenges, including generalization, interpretability, and physical consistency, providing a reference for related research.
References
- [1] Islam G, et al. AI-Driven Integrated Circuit Design: A Survey of Techniques, Challenges, and Opportunities[J]. IEEE Access, 2025, 13: 58043-58059.
- [2] Li J, et al. Artificial Intelligence in VLSI Physical Design: A Survey[J]. IEEE TCAD, 2024, 43(12): 3689- 3708.
- [3] Zhang Y, et al. Generative AI for Analog Integrated Circuit Design: Methodologies and Applications[J]. IEEE Access, 2025, 13: 45123-45140.
- [4] Wang X, et al. ChipGPT: Large Language Model for End-to-End Chip Design[J]. IEEE TVLSI, 2025, 33(5): 987-1000.
- [5] Zhuo Z, et al. Machine Learning in Advanced IC Design: A Methodological Survey[J]. IEEE/CAA JAS, 2024, 11(3): 589-610.
- [6] Chen L, et al. Circuit Transformer: A Graph Transformer for Logic Synthesis Optimization[C]//DAC 2024. IEEE, 2024: 1-6.
- [7] Liu H, et al. Reinforcement Learning-Based Routing for Advanced Node Designs[C]//ICCAD 2024. IEEE, 2024: 1-8.
- [8] Sun W, et al. ChipMind: LLMs for Agile Chip Design[C]//VTS 2025. IEEE, 2025: 1-6.
- [9] Guo Y, et al. Fusion of Global Placement and Gate Sizing with Differentiable Optimization[C]//ICCAD 2024. IEEE, 2024: 1-7.
- [10] Zhou J, et al. A Survey of Circuit Foundation Model: Foundation AI Models for VLSI Circuit Design[C]//ICCAD 2025. IEEE, 2025: 1-10.
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.