Optimizing High-Level Synthesis Designs with Retrieval-Augmented Large Language Models

TL;DR

This paper introduces RALAD, a retrieval-augmented LLM framework that significantly improves HLS code optimization by dynamically sourcing relevant knowledge, achieving high success rates and substantial latency improvements.

Contribution

The paper presents a novel retrieval-augmented LLM approach for HLS optimization, enhancing performance with domain-specific knowledge without extensive fine-tuning.

Findings

Achieves 80% success rate in compilation tasks.

Outperforms general LLMs by 3.7 to 19 times in latency.

Effective in two specialized domains with smaller models.

Abstract

High-level synthesis (HLS) allows hardware designers to create hardware designs with high-level programming languages like C/C++/OpenCL, which greatly improves hardware design productivity. However, existing HLS flows require programmers' hardware design expertise and rely on programmers' manual code transformations and directive annotations to guide compiler optimizations. Optimizing HLS designs requires non-trivial HLS expertise and tedious iterative process in HLS code optimization. Automating HLS code optimizations has become a burning need. Recently, large language models (LLMs) trained on massive code and programming tasks have demonstrated remarkable proficiency in comprehending code, showing the ability to handle domain-specific programming queries directly without labor-intensive fine-tuning. In this work, we propose a novel retrieval-augmented LLM-based approach to effectively optimize high-level synthesis (HLS) programs. Our proposed method leverages few-shot learning, enabling large language models to adopt domain-specific knowledge through natural language prompts. We propose a unique framework, Retrieve Augmented Large Language Model Aided Design (RALAD), designed to enhance LLMs' performance in HLS code optimization tasks. RALAD employs advanced embedding techniques and top-\emph{k} search algorithms to dynamically source relevant knowledge from extensive databases, thereby providing contextually appropriate responses to complex programming queries. Our implementation of RALAD on two specialized domains, utilizing comparatively smaller language models, achieves an impressive 80\% success rate in compilation tasks and outperforms general LLMs by 3.7 -- 19$\times$ in latency improvement.