DeepCircuitX: A Comprehensive Repository-Level Dataset for RTL Code Understanding, Generation, and PPA Analysis

2025-02-25

AI Summary

Existing RTL datasets are limited to file-level code or physical layouts, lacking multi-granularity benchmarks supporting RTL understanding, generation, and joint PPA (Power-Performance-Area) analysis. Method: DeepCircuitX introduces the first structured RTL dataset spanning four hierarchical levels—repository, file, module, and block—integrated with Chain-of-Thought functional annotations, Yosys-synthesized netlists, and OpenSTA-extracted PPA metrics. Contribution/Results: It enables unified repository-level RTL modeling and multi-level semantic annotation; supports end-to-end PPA prediction directly from RTL source code, bridging the abstraction gap between high-level description and physical implementation. Experiments demonstrate significant performance gains for mainstream open-source LLMs on RTL understanding, generation, and PPA prediction tasks; human evaluation confirms high annotation quality. The dataset is publicly released and has been widely adopted by the hardware design community.

Technology Category

• Machine Learning: Hardware-aware ML
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Knowledge Representation and Reasoning: Description Logics

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

This paper introduces DeepCircuitX, a comprehensive repository-level dataset designed to advance RTL (Register Transfer Level) code understanding, generation, and power-performance-area (PPA) analysis. Unlike existing datasets that are limited to either file-level RTL code or physical layout data, DeepCircuitX provides a holistic, multilevel resource that spans repository, file, module, and block-level RTL code. This structure enables more nuanced training and evaluation of large language models (LLMs) for RTL-specific tasks. DeepCircuitX is enriched with Chain of Thought (CoT) annotations, offering detailed descriptions of functionality and structure at multiple levels. These annotations enhance its utility for a wide range of tasks, including RTL code understanding, generation, and completion. Additionally, the dataset includes synthesized netlists and PPA metrics, facilitating early-stage design exploration and enabling accurate PPA prediction directly from RTL code. We demonstrate the dataset's effectiveness on various LLMs finetuned with our dataset and confirm the quality with human evaluations. Our results highlight DeepCircuitX as a critical resource for advancing RTL-focused machine learning applications in hardware design automation.Our data is available at https://zeju.gitbook.io/lcm-team.

Problem

• Enhance RTL code understanding and generation.
• Enable accurate PPA analysis from RTL code.
• Provide a comprehensive multilevel RTL dataset.

Innovation

• Comprehensive multi-level RTL dataset
• Chain of Thought annotations included
• Synthesized netlists with PPA metrics