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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sheikholeslam, Seyed Arash, Ivanov, Andre
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913513325199360
author Sheikholeslam, Seyed Arash
Ivanov, Andre
author_facet Sheikholeslam, Seyed Arash
Ivanov, Andre
contents 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}
format Preprint
id arxiv_https___arxiv_org_abs_2405_16072
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SynthAI: A Multi Agent Generative AI Framework for Automated Modular HLS Design Generation
Sheikholeslam, Seyed Arash
Ivanov, Andre
Artificial Intelligence
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}
title SynthAI: A Multi Agent Generative AI Framework for Automated Modular HLS Design Generation
topic Artificial Intelligence
url https://arxiv.org/abs/2405.16072