SynthAI: A Multi Agent Generative AI Framework for Automated Modular HLS Design Generation

TL;DR

SynthAI is an innovative framework that automates the generation of complex High-Level Synthesis hardware designs by combining multi-agent systems, reasoning techniques, and web-based knowledge retrieval, resulting in efficient, modular, and user-aligned hardware solutions.

Contribution

SynthAI introduces a novel multi-agent, reasoning, and retrieval-based framework for automated HLS design generation, enabling systematic decomposition and high fidelity to user specifications.

Findings

Successfully generates complex multi-module hardware designs

Produces designs that closely match user-specified objectives

Demonstrates effectiveness through multiple case studies

Abstract

In this paper, we introduce SynthAI, a new method for the automated creation of High-Level Synthesis (HLS) designs. SynthAI integrates ReAct agents, Chain-of-Thought (CoT) prompting, web search technologies, and the Retrieval-Augmented Generation (RAG) framework within a structured decision graph. This innovative approach enables the systematic decomposition of complex hardware design tasks into multiple stages and smaller, manageable modules. As a result, SynthAI produces synthesizable designs that closely adhere to user-specified design objectives and functional requirements. We further validate the capabilities of SynthAI through several case studies, highlighting its proficiency in generating complex, multi-module logic designs from a single initial prompt. The SynthAI code is provided via the following repo: \url{https://github.com/sarashs/FPGA_AGI}