Get started
Work

MicroEvo: Knowledge-Guided LLM Sampling for Efficient Microarchitecture Design Space Exploration

Year: 2026
Type: preprint
Abstract: Microarchitecture design space exploration suffers from expansive search spaces and expensive PPA evaluation, leaving only a small simulation budget for design decision-making. Existing methods perform blind search without considering microarchitectural dependencies and fail to learn from the iterative search effectively, leading to wasted evaluations and weak Pareto convergence. In this paper, we propose MicroEvo, a knowledge-guided framework that couples off-the-shelf LLMs with Monte Carlo Tree Search (MCTS) for multi-objective microarchitecture optimization. MicroEvo combines LLM-driven evolutionary operators, a Pareto-aware tree policy that balances Pareto contribution and diversity, an active knowledge accumulation mechanism that extracts and reuses optimization insights, and state-aware directives that adapt the search behavior online. Experiments show that MicroEvo improves Pareto-front quality by up to 36.2% over NSGA-II and achieves 10.6x higher search efficiency, and also demonstrates strong scalability to a complex industrial-scale core. The code repository is available at: https://github.com/GEAR-SEU/MicroEvo-ICCAD-26.
DOI: 10.48550/arxiv.2608.06183
Authors: Xiong, Jia, Li, Runkai, Niu, Chenxu, Gao, Guangyuan, Xing, Changwen, Zhang, Yifan, Wan, Xinlai, Cui, Jieran, Bai, Chen, Hua, Yusheng, Wang, Ying, Ling, Ming, Wang, Xi, Xie, Tao
Institutions: Southeast University, Nvidia (United States), Fudan University, Nanjing University of Posts and Telecommunications, Chinese Academy of Sciences, Institute of Computing Technology, Peking University
Open Access status: green
OpenAlex ID: W7201858250
Cites:
Cited by:
Related to: