RAG-Enhanced Kernel-Based Heuristic Synthesis (RKHS): A Structured Methodology Using Large Language Models for Hardware Design
For EDA practitioners, this provides a structured way to leverage LLMs for heuristic synthesis, though the improvement is incremental over existing methods.
The paper proposes RKHS, a methodology using LLMs with RAG and iterative refinement to synthesize optimization heuristics for hardware design, achieving up to 11% reduction in schedule length for HLS list scheduling with 1.3x runtime overhead.
Heuristic design upholds modern electronic design automation (EDA) tools, yet crafting effective placement, routing, and scheduling strategies entails substantial expertise. We study how large language models (LLMs) can systematically synthesize reusable optimization heuristics beyond one-shot code generation. We propose RAG-Enhanced Kernel-Based Heuristic Synthesis (RKHS), which integrates retrieval-augmented generation (RAG), compact kernel heuristic templates, and an LLM-driven refinement loop inspired by iterative self-feedback. Applied to latency-minimizing list scheduling in high-level synthesis (HLS), a prototype reduces average schedule length by up to 11 percent over a baseline scheduler with only 1.3x runtime overhead, and the structured retrieval-synthesis loop generalizes to other EDA optimization problems.