HYPERHEURIST: A Simulated Annealing-Based Control Framework for LLM-Driven Code Generation in Optimized Hardware Design

TL;DR

HYPERHEURIST leverages simulated annealing to refine LLM-generated RTL designs, improving functional correctness and PPA optimization stability in hardware design.

Contribution

It introduces a control framework that treats LLM outputs as intermediate candidates, enhancing reliability and optimization in hardware design.

Findings

More stable and repeatable optimization behavior than single-pass LLM generation.

Effective filtering of RTL candidates through compilation and simulation.

Improved PPA optimization for hardware designs.

Abstract

Large Language Models (LLMs) have shown promising progress for generating Register Transfer Level (RTL) hardware designs, largely because they can rapidly propose alternative architectural realizations. However, single-shot LLM generation struggles to consistently produce designs that are both functionally correct and power-efficient. This paper proposes HYPERHEURIST, a simulated annealing-based control framework that treats LLM-generated RTL as intermediate candidates rather than final designs. The suggested system not only focuses on functionality correctness but also on Power-Performance-Area (PPA) optimization. In the first phase, RTL candidates are filtered through compilation, structural checks, and simulation to identify functionally valid designs. PPA optimization is restricted to RTL designs that have already passed compilation and simulation. Evaluated across eight RTL benchmarks, this staged approach yields more stable and repeatable optimization behavior than single-pass LLM-generated RTL.