IICPilot: An Intelligent Integrated Circuit Backend Design Framework Using Open EDA

TL;DR

The paper addresses the barrier to adopting open-source EDA tools for IC backend design by introducing IICPilot, an LLM-based, multi-agent framework that automates script generation, tool invocation, design space exploration, and container-based resource management. It combines specialized agents with a unified EDA interface to support OpenROAD and iEDA, enabling flexible, scalable backend design workflows. Key contributions include the first end-to-end backend automation framework for open EDA, a container agent for dynamic resource allocation, a DSE agent for automatic tool parameter tuning, and a workflow that leverages Kubernetes for distributed computation with self-correction via a fault list. Empirical evaluations demonstrate automated EDA task execution, DSE-driven performance improvements across multiple designs, and cost-efficient resource provisioning, highlighting the framework’s practical impact on accelerating IC backend design with open tools.

Abstract

Open-source EDA tools are rapidly advancing, fostering collaboration, innovation, and knowledge sharing within the EDA community. However, the growing complexity of these tools, characterized by numerous design parameters and heuristics, poses a significant barrier to their widespread adoption. This complexity is particularly pronounced in integrated circuit (IC) backend designs, which place substantial demands on engineers' expertise in EDA tools. To tackle this challenge, we introduce IICPilot, an intelligent IC backend design system based on LLM technology. IICPilot automates various backend design procedures, including script generation, EDA tool invocation, design space exploration of EDA parameters, container-based computing resource allocation, and exception management. By automating these tasks, IICPilot significantly lowers the barrier to entry for open-source EDA tools. Specifically, IICPilot utilizes LangChain's multi-agent framework to efficiently handle distinct design tasks, enabling flexible enhancements independently. Moreover, IICPilot separates the backend design workflow from specific open-source EDA tools through a unified EDA calling interface. This approach allows seamless integration with different open-source EDA tools like OpenROAD and iEDA, streamlining the backend design and optimization across the EDA tools.

Figures (7)

• Figure 1: IICPilot Overview.
• Figure 2: An example explains how an agent executes the task based on essential and optional information.
• Figure 3: Examples of using IICPilot.
• Figure 4: The fault list used for self-correction..
• Figure 5: Automated execution of EDA tasks generated by IICPilot.