About Me (刘杭达)

I’m a fourth-year Ph.D student in Computer Science and Technology at Institute of Computing Technology, Chinese Academy of Sciences, working on machine learning systems and tensor optimization. I received the B.E degree from BUPT in 2021. I am now advised by Professor Boyu Diao and Professor Yongjun Xu.

My research primarily focuses on developing efficient tensor computation methods and acceleration techniques for deep learning frameworks. My recent work focuses on the tensor compilation. I’m also interested in workload scheduling optimization for GPU computing and operator fusion techniques for inference acceleration. My research aims to bridge the gap between theoretical deep learning models performance and their practical implementation on edge devices.

Education Experience

Ph.D in Institute of Computing Technology, Chinese Academy of Sciences,
Beijing, 2021-now

B.E in School of Computer Science, Beijing University of Posts and Telecommunications,
Beijing, 2017-2021

Liaoning Province Shiyan High School,
Shenyang, 2014-2017

Publication

• [IPDPS-25, CCF-B] Gensor: A Graph-based Construction Tensor Compilation Method for Deep Learning

  Hangda Liu, Boyu Diao*, Yu Yang, Wenxin Chen, Xiaohui Peng, Yongjun Xu

• [CompJ-24, CCF-B] A resource-aware workload scheduling method for unbalanced GEMMs on GPUs

  Hangda Liu, Boyu Diao*, Wenxin Chen, Yongjun Xu

• [CCGrid-25, CCF-C] A Nonlinear Hash-based Optimization Method for SpMV on GPUs

  Chen Yan, Boyu Diao*, Hangda Liu, Zhulin An, Yongjun Xu

• [PR-25, CCF-B] Low-redundancy Distillation for continual learning

  Ruiqi Liu, Boyu Diao*, Libo Huang, Zijia An, Hangda Liu, Zhulin An, Yongjun Xu

• [NPC-24, CCF-C] DTuner: A Construction-Based Optimization Method for Dynamic Tensor Operators Accelerating

  Yu Yang, Boyu Diao*, Hangda Liu, Qiyun Chen, Qi Wang, Yongjun Xu

• [ICPR-24, CCF-C] An Evolutionary Search-Based Operator Fusion Method with Binary Representation for Deep Learning Inference Acceleration

  Wenxin Chen, Boyu Diao*, Hangda Liu, RuiSheng Wang, Yongjun Xu

Honors & Awards

• First Class Scholarship of University of Chinese Academy of Sciences, 2022&2023&2024
• ICT × E Fund Scholarship, 2022
• Merit Student of University of Chinese Academy of Sciences, 2022&2023&2025
• Outstanding graduate of Beijing, 2021
• Merit Student of Beijing, 2019
• First Class Scholarship of BUPT, 2018&2020