C2HLSC: Can LLMs Bridge the Software-to-Hardware Design Gap?

TL;DR

This paper explores using Large Language Models to automatically refactor standard C code into hardware description language compatible code, aiming to bridge the gap between software algorithms and hardware implementation.

Contribution

It demonstrates the feasibility of LLMs in transforming regular C code into HLS-synthesizable code through iterative prompts and case studies.

Findings

LLMs can successfully refactor C code for hardware synthesis.

The approach enables automatic adaptation of algorithms for hardware implementation.

Potential to accelerate hardware design processes using AI.

Abstract

High Level Synthesis (HLS) tools offer rapid hardware design from C code, but their compatibility is limited by code constructs. This paper investigates Large Language Models (LLMs) for refactoring C code into HLS-compatible formats. We present several case studies by using an LLM to rewrite C code for NIST 800-22 randomness tests, a QuickSort algorithm and AES-128 into HLS-synthesizable c. The LLM iteratively transforms the C code guided by user prompts, implementing functions like streaming data and hardware-specific signals. This evaluation demonstrates the LLM's potential to assist hardware design refactoring regular C code into HLS synthesizable C code.