gem5 Co-Pilot: AI Assistant Agent for Architectural Design Space Exploration

TL;DR

This paper introduces gem5 Co-Pilot, an AI assistant leveraging Large Language Models to automate and accelerate computer architecture design space exploration, optimizing parameters efficiently with minimal user input.

Contribution

We developed gem5 Co-Pilot, a novel AI agent with a GUI, a dedicated language, and a database system to enhance design space exploration in computer architecture.

Findings

Successfully identified optimal parameters for design constraints

Reduced time and user effort in exploration process

Compared favorably with baseline models in experiments

Abstract

Generative AI is increasing the productivity of software and hardware development across many application domains. In this work, we utilize the power of Large Language Models (LLMs) to develop a co-pilot agent for assisting gem5 users with automating design space exploration. Computer architecture design space exploration is complex and time-consuming, given that numerous parameter settings and simulation statistics must be analyzed before improving the current design. The emergence of LLMs has significantly accelerated the analysis of long-text data as well as smart decision making, two key functions in a successful design space exploration task. In this project, we first build gem5 Co-Pilot, an AI agent assistant for gem5, which comes with a webpage-GUI for smooth user interaction, agent automation, and result summarization. We also implemented a language for design space exploration, as well as a Design Space Database (DSDB). With DSDB, gem5 Co-Pilot effectively implements a Retrieval Augmented Generation system for gem5 design space exploration. We experiment on cost-constraint optimization with four cost ranges and compare our results with two baseline models. Results show that gem5 Co-Pilot can quickly identify optimal parameters for specific design constraints based on performance and cost, with limited user interaction.