Enabling New HDLs with Agents

TL;DR

This work introduces HDLAgent, an AI agent optimized for LLMs with limited knowledge of various HDLs, which significantly enhances off-the-shelf LLMs.

Abstract

Large Language Models (LLMs) based agents are transforming the programming language landscape by facilitating learning for beginners, enabling code generation, and optimizing documentation workflows. Hardware Description Languages (HDLs), with their smaller user community, stand to benefit significantly from the application of LLMs as tools for learning new HDLs. This paper investigates the challenges and solutions of enabling LLMs for HDLs, particularly for HDLs that LLMs have not been previously trained on. This work introduces HDLAgent, an AI agent optimized for LLMs with limited knowledge of various HDLs. It significantly enhances off-the-shelf LLMs.

Figures (12)

• Figure 1: HDLAgent flow leveraging compiler feedback.
• Figure 2: HDLAgent Main and Compiler context prompt components.
• Figure 3: HDLAgent improves Chisel across all LLMs.
• Figure 4: HDLAgent improves PyRTL across all LLMs.
• Figure 5: HDLAgent improves DSLX HDLEval-Comb across all LLMs.