CHIA: An open-source framework for principled, agentic AI-driven hardware/software co-design research

2026-06-25

AI Summary

Existing AI-driven hardware/software co-design approaches are hindered by complex and irreproducible workflows, limiting their systematic deployment in real-world, large-scale scenarios. This work proposes CHIA, a novel framework that treats the co-design process itself as a first-class research object, modeling it as scalable directed cyclic graphs—termed CHIA loops. CHIA integrates diverse tools including Chipyard, gem5, Vivado, LLM-based agents, and evolutionary algorithms to enable fault-tolerant, isolated, and distributed execution across heterogeneous cloud-edge-device platforms. The framework’s efficacy and generality are demonstrated through five case studies: automatic RTL-simulator alignment, LLM-generated microarchitectures, IPC-aware optimization, architectural evolution, and automated GitHub issue resolution, collectively showcasing its capability to support agile development and autonomous hardware optimization.

Abstract

Agentic artificial intelligence shows great promise for radically improving the pace of innovation in hardware/software co-design research across computer architecture, systems, compilers, and VLSI. Thus far, however, applications of AI in these contexts have generally been demonstrated in isolated settings on small-scale problems, due to the difficulty of designing and deploying complex AI-infused hardware and software development workflows. This paper introduces CHIA, an open-source hardware/software co-design framework for agile and principled research on the application of AI to co-design. CHIA treats the productive construction and scalable deployment of the co-design flow itself as a first-class objective. In CHIA, agentic AI-driven hardware and software design flows are expressed as \textit{CHIA loops}: directed cyclic graphs whose nodes execute various system-on-chip design tools, microarchitectural simulators, software build systems, AI models, evolutionary coding agents, and more. The \textit{CHIA library} provides node implementations for many popular tools, including Chipyard, gem5, ChampSim, FireSim, Hammer (thus several commercial ASIC CAD tools), Vivado, AlphaEvolve, AdaEvolve, and many others. CHIA also provides a broad set of features to conduct principled science around these flows. These include isolation between AI models and hardware tools, profiling mechanisms, fault-tolerant execution, and reliability at scale across hundreds of heterogeneous systems (CPUs, FPGAs, GPUs, etc., across public cloud/on-prem.). To showcase CHIA, we present five CHIA loops as case studies: (1) automatic RTL-to-gem5 simulator alignment, (2) LLM-driven implementation of microarchitectural features in RTL, (3) agentic, IPC-aware critical path optimization, (4) evolutionary architectural discovery, and (5) maintainer-friendly agentic GitHub issue fixing.

Problem

• hardware/software co-design
• agentic AI
• AI-driven design
• design automation
• co-design workflows

Innovation

• agentic AI
• hardware/software co-design
• CHIA loops
• scalable workflow
• open-source framework