QiMeng: Fully Automated Hardware and Software Design for Processor Chip

2025-06-05

AI Summary

Processor chip design confronts three fundamental challenges: physical scaling limits, exponential resource growth, and ecosystem fragmentation—rendering conventional manual methodologies unsustainable. This paper introduces LPCM, the first domain-specific large language model for chip design, and proposes a three-layer automated co-design system. It integrates knowledge representation alignment, few-shot trustworthy reasoning, and hardware-software co-verification to enable end-to-end closed-loop automation—from instruction-set architecture definition and RTL generation to compiler auto-adaptation. Innovatively, LPCM is coupled with design agents, formal verification, and an iterative, context-aware reasoning framework. Evaluated across multiple real-world applications, the system reduces design cycle time significantly while substantially improving functional correctness and ecosystem compatibility. To our knowledge, this constitutes the first system-level, fully automated chip design solution grounded in domain-specific foundation models.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: (Large) Language Models

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Processor chip design technology serves as a key frontier driving breakthroughs in computer science and related fields. With the rapid advancement of information technology, conventional design paradigms face three major challenges: the physical constraints of fabrication technologies, the escalating demands for design resources, and the increasing diversity of ecosystems. Automated processor chip design has emerged as a transformative solution to address these challenges. While recent breakthroughs in Artificial Intelligence (AI), particularly Large Language Models (LLMs) techniques, have opened new possibilities for fully automated processor chip design, substantial challenges remain in establishing domain-specific LLMs for processor chip design. In this paper, we propose QiMeng, a novel system for fully automated hardware and software design of processor chips. QiMeng comprises three hierarchical layers. In the bottom-layer, we construct a domain-specific Large Processor Chip Model (LPCM) that introduces novel designs in architecture, training, and inference, to address key challenges such as knowledge representation gap, data scarcity, correctness assurance, and enormous solution space. In the middle-layer, leveraging the LPCM's knowledge representation and inference capabilities, we develop the Hardware Design Agent and the Software Design Agent to automate the design of hardware and software for processor chips. Currently, several components of QiMeng have been completed and successfully applied in various top-layer applications, demonstrating significant advantages and providing a feasible solution for efficient, fully automated hardware/software design of processor chips. Future research will focus on integrating all components and performing iterative top-down and bottom-up design processes to establish a comprehensive QiMeng system.

Problem

• Automating processor chip design to overcome fabrication constraints
• Addressing resource demands and ecosystem diversity in chip design
• Developing domain-specific LLMs for hardware/software design automation

Innovation

• Domain-specific Large Processor Chip Model (LPCM)
• Automated Hardware and Software Design Agents
• Hierarchical system for full automation