Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design

Andre Nakkab, Sai Qian Zhang, Ramesh Karri, Siddharth Garg

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Large Language Models (LLMs) are effective in computer hardware synthesis via hardware description language (HDL) generation. However, LLM-assisted approaches for HDL generation struggle when handling complex tasks. We introduce a suite of hierarchical prompting techniques which facilitate efficient stepwise design methods, and develop a generalizable automation pipeline for the process. To evaluate these techniques, we present a benchmark set of hardware designs which have solutions with or without architectural hierarchy. Using these benchmarks, we compare various open-source and proprietary LLMs, including our own fine-tuned Code Llama-Verilog model. Our hierarchical methods automatically produce successful designs for complex hardware modules that standard flat prompting methods cannot achieve, allowing smaller open-source LLMs to compete with large proprietary models. Hierarchical prompting reduces HDL generation time and yields savings on LLM costs. Our experiments detail which LLMs are capable of which applications, and how to apply hierarchical methods in various modes. We explore case studies of generating complex cores using automatic scripted hierarchical prompts, including the first-ever LLM-designed processor with no human feedback.

Original languageEnglish (US)
Title of host publicationMLCAD 2024 - Proceedings of the 2024 ACM/IEEE International Symposium on Machine Learning for CAD
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9798400706998
DOIs
StatePublished - Sep 9 2024
Event6th ACM/IEEE International Symposium on Machine Learning for CAD, MLCAD 2024 - Snowbird, United States
Duration: Sep 9 2024Sep 11 2024

Publication series

NameMLCAD 2024 - Proceedings of the 2024 ACM/IEEE International Symposium on Machine Learning for CAD

Conference

Conference6th ACM/IEEE International Symposium on Machine Learning for CAD, MLCAD 2024
Country/TerritoryUnited States
CitySnowbird
Period9/9/249/11/24

Keywords

  • Automation
  • Hardware design
  • Hierarchy
  • LLM

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Graphics and Computer-Aided Design
  • Control and Optimization
  • Modeling and Simulation

Fingerprint

Dive into the research topics of 'Rome was Not Built in a Single Step: Hierarchical Prompting for LLM-based Chip Design'. Together they form a unique fingerprint.

Cite this