HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908874122985472 |
|---|---|
| author | Zheng, Pingqing Qin, Jiayin Zhang, Fuqi Chitla, Niraj Wan, Zishen Wu, Shang Cao, Yu Ding, Caiwen Yang Zhao |
| author_facet | Zheng, Pingqing Qin, Jiayin Zhang, Fuqi Chitla, Niraj Wan, Zishen Wu, Shang Cao, Yu Ding, Caiwen Yang Zhao |
| contents | Retrieval Augmented Generation (RAG) is an essential agent for Large Language Model (LLM) aided Description Language (HDL) tasks, addressing the challenges of limited training data and prohibitively long prompts. However, its performance in handling ambiguous queries and real-world, repository-level HDL projects containing thousands or even tens of thousands of code lines remains limited. Our analysis demonstrates two fundamental mismatches, structural and vocabulary, between conventional semantic similarity-based RAGs and HDL codes. To this end, we propose HDLxGraph, the first framework that integrates the inherent graph characteristics of HDLs with RAGs for LLM-assisted tasks. Specifically, HDLxGraph incorporates Abstract Syntax Trees (ASTs) to capture HDLs' hierarchical structures and Data Flow Graphs (DFGs) to address the vocabulary mismatch. In addition, to overcome the lack of comprehensive HDL search benchmarks, we introduce HDLSearch, an LLM generated dataset derived from real-world, repository-level HDL projects. Evaluations show that HDLxGraph improves search, debugging, and completion accuracy by 12.04%/12.22%/5.04% and by 11.59%/8.18%/4.07% over state-of-the-art similarity-based RAG and software-code Graph RAG baselines, respectively. The code of HDLxGraph and HDLSearch benchmark are available at https://github.com/UMN-ZhaoLab/HDLxGraph. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_15701 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases Zheng, Pingqing Qin, Jiayin Zhang, Fuqi Chitla, Niraj Wan, Zishen Wu, Shang Cao, Yu Ding, Caiwen Yang Zhao Hardware Architecture Computation and Language Machine Learning Retrieval Augmented Generation (RAG) is an essential agent for Large Language Model (LLM) aided Description Language (HDL) tasks, addressing the challenges of limited training data and prohibitively long prompts. However, its performance in handling ambiguous queries and real-world, repository-level HDL projects containing thousands or even tens of thousands of code lines remains limited. Our analysis demonstrates two fundamental mismatches, structural and vocabulary, between conventional semantic similarity-based RAGs and HDL codes. To this end, we propose HDLxGraph, the first framework that integrates the inherent graph characteristics of HDLs with RAGs for LLM-assisted tasks. Specifically, HDLxGraph incorporates Abstract Syntax Trees (ASTs) to capture HDLs' hierarchical structures and Data Flow Graphs (DFGs) to address the vocabulary mismatch. In addition, to overcome the lack of comprehensive HDL search benchmarks, we introduce HDLSearch, an LLM generated dataset derived from real-world, repository-level HDL projects. Evaluations show that HDLxGraph improves search, debugging, and completion accuracy by 12.04%/12.22%/5.04% and by 11.59%/8.18%/4.07% over state-of-the-art similarity-based RAG and software-code Graph RAG baselines, respectively. The code of HDLxGraph and HDLSearch benchmark are available at https://github.com/UMN-ZhaoLab/HDLxGraph. |
| title | HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases |
| topic | Hardware Architecture Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2505.15701 |