报告题目：Algorithm and System Co-Optimized Big Data Analytics

报告时间：2021年12月30日 10:00-11:00 (GMT+08:00)

报告方式：ZOOM会议

会议码：956 0022 9256

登陆密码：724608

报告人：刘航

报告人简介：

Dr. Hang LIU is currently an assistant professor in the Department of Electrical and Computer Engineering at Stevens Institute of Technology. He received his Ph.D. degree from George Washington University in 2017, and B.E. from Huazhong University of Science and Technology in 2011. Hang LIU’s research interests include exploiting emerging hardware to build high-performance systems for graph computing, machine learning, data compression, numerical simulation, cloud computing, and software debugging. His publications appear in top-tier conferences, such as SC, VLDB, SIGMOD, ICDE, HPDC, USENIX FAST, USENIX ATC, and DAC. He is the recipient of the prestigious NSF CAREER Award, NSF CRII Award, DOE SRP fellowship, and the Champion of DARPA/MIT/AMAZON Graph Challenge 2018 and 2019. He is also the winner of the Best Dissertation Award from the Department of Electrical and Computer Engineering at George Washington University.

报告内容简介：

Increasingly, people are awash in data, as a growing array of “sensors” that are integrated into our daily life, continues to generate an explosive amount of data. According to a recent study by IBM, we are creating ~2.5 quintillion bytes of data per day. Buried in such a rapidly growing influx of data are the key insights to address critical issues in our society, such as improving productivity, enlisting new economic opportunities, and uncovering novel discoveries in science and engineering. In the High-Performance Data Analytics (HPDA) Lab at Stevens Institute of Technology, we develop novel algorithms and systems to rapidly analyze the gigantic real-world data, understand the contextual and causal relationships within entities and events, and deliver actionable knowledge to stakeholders in real-time. In this talk, I will share our experiences in designing and developing high-performance systems for addressing the computational and I/O challenges faced in structured graph data (featured at SC '20). In addition, I will present our ongoing work on utilizing tensor-core-enabled hardware to accelerate emerging attention-based neural network models for sequence data (featured at SC '21).

主办单位：吉林大学计算机科学与技术学院

吉林大学软件学院

吉林大学计算机科学技术研究所

符号计算与知识工程教育部重点实验室

仿真技术教育部重点实验室

网络技术及应用软件教育部工程研究中心

          吉林大学国家级计算机实验教学示范中心