DeepRTL2: A Versatile Model for RTL-Related Tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yi, Zhang, Hongji, Zhou, Yunhao, Shi, Zhengyuan, Xu, Changran, Xu, Qiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908414532124672
author Liu, Yi
Zhang, Hongji
Zhou, Yunhao
Shi, Zhengyuan
Xu, Changran
Xu, Qiang
author_facet Liu, Yi
Zhang, Hongji
Zhou, Yunhao
Shi, Zhengyuan
Xu, Changran
Xu, Qiang
contents The integration of large language models (LLMs) into electronic design automation (EDA) has significantly advanced the field, offering transformative benefits, particularly in register transfer level (RTL) code generation and understanding. While previous studies have demonstrated the efficacy of fine-tuning LLMs for these generation-based tasks, embedding-based tasks, which are equally critical to EDA workflows, have been largely overlooked. These tasks, including natural language code search, RTL code functionality equivalence checking, and performance prediction, are essential for accelerating and optimizing the hardware design process. To address this gap, we present DeepRTL2, a family of versatile LLMs that unifies both generation- and embedding-based tasks related to RTL. By simultaneously tackling a broad range of tasks, DeepRTL2 represents the first model to provide a comprehensive solution to the diverse challenges in EDA. Through extensive experiments, we show that DeepRTL2 achieves state-of-the-art performance across all evaluated tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15697
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepRTL2: A Versatile Model for RTL-Related Tasks
Liu, Yi
Zhang, Hongji
Zhou, Yunhao
Shi, Zhengyuan
Xu, Changran
Xu, Qiang
Hardware Architecture
Computation and Language
Machine Learning
The integration of large language models (LLMs) into electronic design automation (EDA) has significantly advanced the field, offering transformative benefits, particularly in register transfer level (RTL) code generation and understanding. While previous studies have demonstrated the efficacy of fine-tuning LLMs for these generation-based tasks, embedding-based tasks, which are equally critical to EDA workflows, have been largely overlooked. These tasks, including natural language code search, RTL code functionality equivalence checking, and performance prediction, are essential for accelerating and optimizing the hardware design process. To address this gap, we present DeepRTL2, a family of versatile LLMs that unifies both generation- and embedding-based tasks related to RTL. By simultaneously tackling a broad range of tasks, DeepRTL2 represents the first model to provide a comprehensive solution to the diverse challenges in EDA. Through extensive experiments, we show that DeepRTL2 achieves state-of-the-art performance across all evaluated tasks.
title DeepRTL2: A Versatile Model for RTL-Related Tasks
topic Hardware Architecture
Computation and Language
Machine Learning
url https://arxiv.org/abs/2506.15697