Yifang Zhao

Yifang Zhao

Auto-generated profile, based on publicly available information

Yifang Zhao

School of Cyber Science and Technology, University of Science and Technology of China, Hefei, Anhui, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 November 2024 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
WFWeimin Fu
Weimin Fu
SLShijie Li
Shijie Li
YZYifang Zhao
Yifang Zhao
KYKaichen Yang
Kaichen Yang
XZXuan Zhang
Xuan Zhang
XGXiaolong Guo
Xiaolong Guo
Large Language Models (LLMs) have precipitated emerging trends towards intelligent automation. However, integrating LLMs into the hardware debug domain encounters challenges: the datasets for LLMs for hardware are often plagued by a dual dilemma – scarcity and subpar quality. Traditional hardware debug approaches that rely on experienced labor to generate detailed prompts are not cheaply scalable. Similarly, strategies that depend on existing LLMs and randomly generated prompts fail to achieve sufficient reliability. We propose a directed, semi-synthetic data synthetic method that leverages version control information and journalistic event descriptions. To produce high-quality data, this approach utilizes version control data from hardware projects combined with the 5W1H (Who, What, When, Where, Why, How) journalistic principles. It facilitates the linear scaling of dataset volumes without depending on skilled labor. We have implemented this method on a collected dataset of open-source hardware designs and fine-tuned fifteen general-purpose LLMs to enable their capability in hardware debugging tasks, thereby validating the efficacy of our approach.

2 December 2024
Verified
Conference Paper
Open access
WFWeimin Fu
Weimin Fu
YZYifang Zhao
Yifang Zhao
YJYier Jin
Yier Jin
XGXiaolong Guo
Xiaolong Guo
To enhance the performance of large language models (LLMs) on hardware design tasks, we focus on training with reinforcement learning(RL) to improve LLMs' syntax synthesis and functional verification performance. We observed significant gains in power, performance, and area (PPA) metrics by applying RL. Specifically, DeepSeek Code saw a 23.6% performance increase, while the RTLCoder improved by 7.86%. Our findings demonstrate the effectiveness of RL in refining LLMs for more accurate hardware generation, considering power and area consumption. This approach offers a promising direction for generating hardware resilient to side-channel attacks in computer systems.