Xin He

Lecturer   graduate teacher

Academic Titles:华山准聘副教授

Gender:Male

Alma Mater:湖南大学

Education Level:With Certificate of Graduation for Doctorate Study

Degree:Doctoral Degree in Engineering

Status:On duty

School/Department:广州研究院

Date of Employment:2022-05-07

Business Address:广州市黄埔区中新广州知识城海丝中心B7栋406

Contact Information:15674868747

E-Mail:


Education Background

2016.9 -- 2021.12

湖南大学       Computer Science and Technology       With Certificate of Graduation for Doctorate Study       Doctoral Degree in Engineering

2018.9 -- 2020.10

University of California, Merced       EECS       Visiting Ph.D. Candidate       Visiting Ph.D. Candidate

2014.9 -- 2016.6

湖南大学       Computer Science and Technology       With Certificate of Graduation for Study as Master's Candidates       硕士研究生

Social Affiliations

CCF高性能计算专委会委员

CCF体系结构专委会委员

Research Focus

高性能计算、并行与分布式系统、深度学习系统

Work Experience

2022.2 -- Now

西安电子科技大学      广州研究院      在岗

Profile:

何鑫(Xin He),工学博士,西安电子科技大学华山准聘副教授,硕士研究生导师,中组部国家特聘专家盛凯教授团队骨干成员,CCF高性能计算及体系结构专委会委员。2022年4月获得湖南大学计算机科学与技术专业博士学位(导师:陈浩教授),2018年9月-2020年10月,美国加利福尼亚大学美熹德分校(University of California, Merced)博士联合培养(合作导师:Prof. Dong Li)。目前主要研究方向为高性能计算、并行与分布式系统、深度学习。参与国家自然科学基金面上、国家重点研发计划等项目3项。累计已发表学术论文 9 篇,其中包括分别以第一作者在USENIX ATC、ICS、FGCS、ICPADS等高性能计算和计算机系统领域高水平国际会议和期刊上发表论文。同时受邀参与ICPP、IPDPS、ICPADS、NPC、CLUSTER、NeuroIPS、NAS、TPDS、TC、FGCS等多个国际会议和期刊的审稿。


招生信息:欢迎对高性能计算、并行与分布式系统、深度学习系统等研究方向感兴趣的优秀本科生加入,可以通过邮件与我联系:hexin@xidian.edu.cn。

招生专业:计算机科学与技术(学术型)、电子信息(专业型)


参与或主持的科研项目:

[1] 西安电子科技大学博士科研启动项目(主持)

[2] 国家建设高水平大学公派研究生项目(主持)

[3] 广东省基础与应用基础研究基金省市联合基金-青年基金项目(主持)

[4] 国家重点研发计划(参与 )

[5] 国家自然科学基金面上项目(参与) 

[6] 国家自然科学基金面上项目(参与)

[7] 国家自然科学基金面上项目(参与)

[8] 国家重点研发计划(参与 )

[9] 中央高校基本科研业务费专项资金(主持)


论文:

  • Zhen Xie, Murali Emani, Xiaodong Yu, Dingwen Tao, Xin He, Pengfei Su, Keren Zhou, Venkatram Vishwanath. Centimani: Enabling Fast AI Accelerator Selection for DNN Training with a Novel Performance Predictor. The USENIX Annual Technical Conference (USENIX ATC), July 10-12, 2024. (CCF A类会议,计算机系统领域国际顶会,acceptance rate:15.8%,to appear)

  • Xin He, Jianhua Sun, Hao Chen, Dong Li. Campo: Cost-Aware Performance Optimization for Mixed-Precision Neural Network Training. The USENIX Annual Technical Conference (USENIX ATC), July 11-13, 2022. (CCF A类会议,计算机系统领域国际顶会,acceptance rate:16%)

  • Xin He, Jiawen Liu, Zhen Xie, Hao Chen, Guoyang Chen, Weifeng Zhang, Dong Li. Enabling Energy-Efficient DNN Training on Hybrid GPU-FPGA Accelerators. Proc. of the 35th ACM International Conference on Supercomputing (ICS), June 14-17, 2021. (CCF B类会议,高性能计算领域国际顶会,acceptance rate:24%)

  • Xin He, Yapeng Yao, Zhiwen Chen, Jianhua Sun, Hao Chen. Efficient Parallel A* Search on Multi-GPU System. Future Generation Computer Systems (FGCS), 2021. (中科院SCI一区,IF:7.5

  • Xin He, Zhiwen Chen, Jianhua Sun, Hao Chen, Zhe Quan, Dong Li. Exploring Synchronization in Cache Coherent Manycore Systems: A Case Study with Xeon Phi. International Conference on Parallel and Distributed Systems (ICPADS), December 15-17, 2017. (CCF C类会议)

  • Lei Ao, Kaiyuan Feng, Kai Sheng *, Hongyu Zhao, Xin He, Zigang Chen. TPENAS: A Two-phase Evolutionary Neural Architecture Search for Remote Sensing Image Classification. Remote Sensing. (JCR Q1, IF=5.349)

  • Zhiwen Chen, Wenkui Che, Daokun Hu, Xin He, Jianhua Sun, Hao Chen. On the Performance Intricacies of PMem-Aware Database Storage Engines. IEEE Transactions on Knowledge and Data Engineering, 2022.(TKDE), (CCF A类期刊)

  • Zhiwen Chen, Xin He, Jianhua Sun, Hao Chen. Have Your Cake and Eat it (Too): A Concurrent Hash Table with Hardware Transactions[J]. International Journal of Parallel Programming (IJPP), 2017: 1-11. (SCI三区

  • Zhiwen Chen, Xin He, Jianhua Sun, Hao Chen, Ligang He. Concurrent hash tables on multicore machines: Comparison, evaluation and implications[J]. Future Generation Computer Systems (FGCS), 2018. (中科院SCI一区,IF:7.5

  • Wentao Li, Zhiwen Chen, Xin He, Guoyun Duan, Jianhua Sun, Hao Chen. CVFuzz: Detecting Complexity Vulnerabilities in OpenCL Kernels via Automated Pathological Input Generation. Future Generation Computer Systems (FGCS), 2021. (中科院SCI一区,IF:7.5


专利:

  1. 一种面向混合精度人工智能模型训练的高效优化器(申请号:202210836727.8)。发明专利(已受理)2022

  2. 一种基于人车路协同的行人意图预警系统及方法(申请号:202211650143.8)。发明专利(已受理)2022


授课信息:

研究生课程:《并行计算导论》

本科生课程:《知识工程》