Knowledge driven AI speeds microchip architecture design space search

KD-DSE: A Knowledge-Driven LLM Framework for Fast Microarchitecture Design Space Exploration

Hardware Architecture

Summary

Designing computer processors involves testing many chip configurations, which takes a lot of time because each test is slow. The authors created KD-DSE, a system that uses artificial intelligence guided by expert knowledge to pick smarter tests and make better decisions during design. This means it can find good processor designs faster and with fewer tests than existing methods. Their results showed a significant improvement using real simulations and architectural insights.

What this means in practice

  • For chip design teams: Accelerate exploration of processor designs by reducing simulation counts needed to find optimal microarchitecture configurations.
  • For hardware verification engineers: Use guided AI-driven diagnosis to focus verification efforts on bottlenecks in microarchitecture prototypes efficiently.

Authors

Siqing Fu, Xin Liu, Yuhan Tang, Hanqing Li, Feng Guo

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.