HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Jinwei, Qin, Jiayin, Thorat, Kiran, Zhu-Tian, Chen, Cao, Yu, Yang, Zhao, Ding, Caiwen
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915540027572224
author Tang, Jinwei
Qin, Jiayin
Thorat, Kiran
Zhu-Tian, Chen
Cao, Yu
Yang
Zhao
Ding, Caiwen
author_facet Tang, Jinwei
Qin, Jiayin
Thorat, Kiran
Zhu-Tian, Chen
Cao, Yu
Yang
Zhao
Ding, Caiwen
contents With Large Language Models (LLMs) recently demonstrating impressive proficiency in code generation, it is promising to extend their abilities to Hardware Description Language (HDL). However, LLMs tend to generate single HDL code blocks rather than hierarchical structures for hardware designs, leading to hallucinations, particularly in complex designs like Domain-Specific Accelerators (DSAs). To address this, we propose HiVeGen, a hierarchical LLM-based Verilog generation framework that decomposes generation tasks into LLM-manageable hierarchical submodules. HiVeGen further harnesses the advantages of such hierarchical structures by integrating automatic Design Space Exploration (DSE) into hierarchy-aware prompt generation, introducing weight-based retrieval to enhance code reuse, and enabling real-time human-computer interaction to lower error-correction cost, significantly improving the quality of generated designs.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05393
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design
Tang, Jinwei
Qin, Jiayin
Thorat, Kiran
Zhu-Tian, Chen
Cao, Yu
Yang
Zhao
Ding, Caiwen
Machine Learning
Artificial Intelligence
Hardware Architecture
With Large Language Models (LLMs) recently demonstrating impressive proficiency in code generation, it is promising to extend their abilities to Hardware Description Language (HDL). However, LLMs tend to generate single HDL code blocks rather than hierarchical structures for hardware designs, leading to hallucinations, particularly in complex designs like Domain-Specific Accelerators (DSAs). To address this, we propose HiVeGen, a hierarchical LLM-based Verilog generation framework that decomposes generation tasks into LLM-manageable hierarchical submodules. HiVeGen further harnesses the advantages of such hierarchical structures by integrating automatic Design Space Exploration (DSE) into hierarchy-aware prompt generation, introducing weight-based retrieval to enhance code reuse, and enabling real-time human-computer interaction to lower error-correction cost, significantly improving the quality of generated designs.
title HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design
topic Machine Learning
Artificial Intelligence
Hardware Architecture
url https://arxiv.org/abs/2412.05393