arXiv · 2611.22411
KD-DSE: A Knowledge-Driven LLM Framework for Fast Microarchitecture Design Space Exploration
Abstract
Domain-specific architectures have made design space exploration (DSE) a bottleneck of processor design, yet each candidate costs a full simulation, so exhaustive search is out of reach. Surrogate models need thousands of simulations before they predict reliably, and LLM agents that search directly hallucinate, lack cold-start architectural knowledge, and follow a fixed per-round policy. We present KD-DSE, a knowledge- driven LLM framework for fast microarchitecture DSE. KD- DSE couples a five-state constrained agent with real gem5- McPAT evaluation, retrieves architect-curated guidance from an Architecture Knowledge Base conditioned on the current search state and bottleneck diagnosis, and allocates its budget with a diagnosis-guided two-phase exploration strategy. On a 29- parameter out-of-order core with a budget of 18 simulations, KD-DSE achieves about 4.8% higher hypervolume and about 21.7% lower ADRS than the state-of-the-art MicroEvo, and the ablation attributes the gain chiefly to the Knowledge Base. These results indicate that constraining LLM reasoning and grounding it in architectural knowledge can drive fast and effective microarchitecture DSE. The code will be open-sourced upon acceptance.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Siqing Fu, Xin Liu, Yuhan Tang, Hanqing Li, Feng Guo. 2026-11-17. KD-DSE: A Knowledge-Driven LLM Framework for Fast Microarchitecture Design Space Exploration. https://searcharxiv.com/abs/2611.22411
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.