I am a Ph.D. student in Networked System Lab at USC, luckily advised by Prof. Ramesh Govindan. I am interested in Cloud/Edge computing and GPU cluster management. I obtained my B.S. degree from SJTU advised by Prof. Xinbing Wang.
[CV] [Google Scholar]
Ongoing Projects
- GPU cluster management
- Scaling for data dependent workload
Selected Publications
Scrooge: A Cost-Effective Deep Learning Inference System
Yitao Hu, Rajrup Ghosh, Ramesh Govindan
ACM SoCC, 2021, to appear.
[Paper] [Slides]
Rim: Offloading Inference to the Edge
Yitao Hu, Weiwu Pang, Xiaochen Liu, Rajrup Ghosh, Bongjun Ko, Wei-Han Lee, Ramesh Govindan
ACM/USENIX IoTDI, 2021.
[Paper] [Slides]
Olympian: Scheduling GPU Usage in a Deep Neural Network Model Serving System
Yitao Hu, Swati Rallapalli, Bongjun Ko, Ramesh Govindan
ACM/USENIX Middleware, 2018.
[Paper] [Slides]
ALPS: Accurate Landmark Positioning at City Scales
Yitao Hu, Xiaochen Liu, Suman Nath, Ramesh Govindan
ACM UbiComp, 2016.
[Paper] [Slides]
Critical Sensing Range for Mobile Heterogeneous Camera Sensor Networks
Yitao Hu, Xinbing Wang, Xiaoying Gan
IEEE INFOCOM, 2014.
[Paper]
Teaching
- Teaching Assistant, CS 353 Introduction to Internetworking, 2016 Fall.
- Mentoring experience: Zheyu Shen (M.S.), Enbang Zhang (Summer Intern), Xiao Ze (B.S.).
Professional Experience
- Research Intern, IBM Research Watson, 2016.
- Research Intern, Samsung Research America, 2016.
Contact
University of Southern California
Department of Computer Science
941 Bloom Walk, SAL 224
Los Angeles, CA 90089
Phone: +1 213-300-1057
Email: yitaoh@usc.edu