LLM-Driven High-Level Synthesis Optimization for Application-Specific Integrated Circuits

Authors

  • Paride Farnese Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA. Author
  • Isidro Dalmau Department of Computer Science, Colorado State University, Fort Collins, CO, USA. Author
  • Quinten Cornelissen Department of Computer Science, University of Central Florida, Orlando, FL, USA. Author

Keywords:

high-level synthesis, application-specific integrated circuits, large language models, electronic design automation, design-space exploration, verification, governance, sustainability

Abstract

High-level synthesis has long promised to raise the abstraction level of application-specific integrated circuit design, yet practical adoption remains constrained by the difficulty of mapping behavioral intent to efficient power, performance, and area outcomes. Large language models introduce a new socio-technical layer into this process: they can generate, refactor, explain, and search hardware descriptions, but they also introduce uncertainty, provenance ambiguity, and infrastructure dependency. This paper examines LLM-driven high-level synthesis optimization for application-specific integrated circuits from a system-level perspective. It argues that the central challenge is not simply model accuracy but the co-design of model capability, compiler and synthesis feedback, verification infrastructure, data governance, and deployment economics. The paper reviews foundational high-level synthesis and electronic design automation work, then develops an architecture in which language models act as interface agents, transformation proposers, and design-space explorers rather than autonomous replacements for synthesis tools. It analyzes structural trade-offs among abstraction, predictability, resource efficiency, verification burden, and organizational accountability. It further considers robustness under distribution shift, fairness in access to models and compute, sustainability of repeated inference, and policy implications for safety-critical silicon. Case illustrations from ASIC, FPGA, and embedded systems contexts show that LLM-driven optimization is most credible when tightly coupled to formal checks, simulation, and human review. The conclusion outlines a governance-aware research agenda for reliable, measurable, and equitable LLM-assisted ASIC design.

References

1. Gajski, D. D., Dutt, N. D., Wu, A. C. J., & Lin, S. Y. (1992). High-level synthesis: Introduction to chip and system design. Springer.

2. Micheli, G. (1994). Synthesis and optimization of digital circuits. McGraw-Hill.

3. Coussy, P., Gajski, D. D., Meredith, M., & Takach, A. (2009). An introduction to high-level synthesis. IEEE Design & Test of Computers, 26(4), 8–17.

4. Nane, R., Sima, V. M., Pilato, C., Choi, J., Fort, B., Canis, A., ... & Bertels, K. (2016). A survey and evaluation of FPGA high-level synthesis tools. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 35(10), 1591–1604.

5. Canis, A., Choi, J., Aldham, M., Zhang, V., Kammoona, A., Anderson, J. H., Brown, S., & Czajkowski, T. (2011). LegUp: High-level synthesis for FPGA-based processor/accelerator systems. In Proceedings of the 19th ACM/SIGDA International Symposium on Field Programmable Gate Arrays (pp. 33–36). ACM.

6. Cong, J., Lau, J., Liu, G., Neuendorffer, S., Pan, P., Vissers, K., & Zhang, Z. (2022). FPGA HLS today: Successes, challenges, and opportunities. ACM Transactions on Reconfigurable Technology and Systems, 15(4), 1–42.

7. Bacon, D. F., Graham, S. L., & Sharp, O. J. (1994). Compiler transformations for high-performance computing. ACM Computing Surveys, 26(4), 345–420.

8. Teich, J. (2012). Hardware/software codesign: The past, present, and future. Proceedings of the IEEE, 100(Special Centennial Issue), 1417–1430.

9. Lee, E. A. (2008). Cyber physical systems: Design challenges. In 2008 11th IEEE International Symposium on Object and Component-Oriented Real-Time Distributed Computing (ISORC) (pp. 363–369). IEEE.

10. Thorat, K., Zhao, J., Liu, Y., Hasan, A., Peng, H., Xie, X., ... & Ding, C. (2025, September). LLM-VeriPPA: Power, Performance, and Area Optimization aware Verilog Code Generation with Large Language Models. In 2025 ACM/IEEE 7th Symposium on Machine Learning for CAD (MLCAD) (pp. 1-7). IEEE.

11. Pearce, H., Tan, B., & Karri, R. (2020). DAVE: Deriving automatically Verilog from English. In Proceedings of the 2020 ACM/IEEE Workshop on Machine Learning for CAD (pp. 27–32). ACM.

12. Thakur, S., Ahmad, B., Pearce, H., Tan, B., Dolan-Gavitt, B., Karri, R., & Garg, S. (2024). VeriGen: A large language model for Verilog code generation. ACM Transactions on Design Automation of Electronic Systems, 29(3), 1–31.

13. Liu, M., Ene, T., Xu, M., et al. (2023). ChipNeMo: Domain-adapted LLMs for chip design. arXiv preprint arXiv:2311.00176.

14. Lu, Y., Liu, S., Zhang, Q., & Xie, Z. (2024). RTLLM: An open-source benchmark for design RTL generation with large language model. In 2024 29th Asia and South Pacific Design Automation Conference (ASP-DAC) (pp. 722–727). IEEE.

15. Blocklove, J., Garg, S., Karri, R., & Pearce, H. (2023). Chip-Chat: Challenges and opportunities in conversational hardware design. In 2023 ACM/IEEE 5th Workshop on Machine Learning for CAD (MLCAD) (pp. 1–6). IEEE.

16. Sculley, D., Holt, G., Golovin, D., Davydov, E., Phillips, T., Ebner, D., ... & Dennison, D. (2015). Hidden technical debt in machine learning systems. In Advances in Neural Information Processing Systems 28 (pp. 2503–2511). Curran Associates.

17. Mittelstadt, B. D., Allo, P., Taddeo, M., Wachter, S., & Floridi, L. (2016). The ethics of algorithms: Mapping the debate. Big Data & Society, 3(2), 1–21.

18. Strubell, E., Ganesh, A., & McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (pp. 3645–3650). ACL.

19. Patterson, D., Gonzalez, J., Le, Q., Liang, C., Munguia, L.-M., Rothchild, D., So, D., Texier, M., & Dean, J. (2021). Carbon emissions and large neural network research. arXiv preprint arXiv:2104.10350.

20. Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., ... & Horvitz, E. (2019). Guidelines for human-AI interaction. In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (pp. 1–13). ACM.

Downloads

Published

2026-11-06