Juming Xian

Juming Xian

Auto-generated profile, based on publicly available information

Juming Xian

School of Integrated Circuits, School of Physics and Optoelectronic Engineering, Guangdong University of Technology, Guangzhou, 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
3 May 2024 in ACM Transactions on Design Automation of Electronic Systems
Verified
Journal Article
Open access
JXJuming Xian
Juming Xian
YXyan xing
yan xing
SCShuting Cai
Shuting Cai
WLWeijun Li
Weijun Li
XXXiaoming Xiong
Xiaoming Xiong
ZHZhengfa Hu
Zhengfa Hu
To speed up the design closure and improve the QoR of FPGA, supervised single-task machine learning techniques have been used to predict individual design metric based on placement results. However, the design objective is to achieve optimal performance while considering multiple conflicting metrics. The single-task approaches predict each metric in isolation and neglect the potential correlations or dependencies among them. To address the limitations, this article proposes a multi-task learning approach to jointly predict wirelength, congestion and power. By sharing the common feature representations and adopting the joint optimization strategy, the novel WCPNet models (including WCPNet-HS and WCPNet-SS) cannot only predict the three metrics of different scales simultaneously, but also outperform the majority of single-task models in terms of both prediction performance and time cost, which are demonstrated by the results of the cross design experiment. By adopting the cross-stitch structure in the encoder, WCPNet-SS outperforms WCPNet-HS in prediction performance, but WCPNet-HS is faster because of the simpler parameters sharing structure. The significance of the feature image pinUtilization on predicting power and wirelength are demonstrated by the ablation experiment.