Han Zhao 赵涵

Assistant Professor

Shanghai Jiao Tong University (SJTU)

Biography

I am an assistant professor at Computer Science and Engineering Department in Shanghai Jiao Tong University (SJTU). I received the Master and Ph.D. degrees from Shanghai Jiao Tong University under the supervision of Prof. Quan Chen and Prof. Minyi Guo. For now, I still work closely with Prof. Quan Chen and Assist Prof. Weihao Cui.

My past research focused on High performance computing on CPU architecture, Task scheduling on GPU architecture, Resource management in Datacenter, and DNN inference system design. My future research will cover more cloud computing topics such as GPU serverless and GPU virtualization. Specically, my future research could be divided into four aspects: Fine-grained GPU resource division, Multi-worker scheduling for DNN tasks, GPU serverless and Resource management in Datacenter.

I am now looking for perspective Ph.D students and Master Students. If you are interested in above areas, we should talk.

Interests

Cloud computing
Serverless computing
Task scheduling
DNN inference system
Resource management in Datacenter

Education

PhD in Computer Science, 2019-2022

Shanghai Jiao Tong University
MSc in Computer Science, 2016-2019

Shanghai Jiao Tong University
BSc in Computer Science, 2012-2016

Huazhong University of Science and Technology

Recent Publications

Chuhao Xu, Yiyu Liu, Zijun Li, Quan Chen, Han Zhao, Deze Zeng, Qian Peng, Xueqi Wu, Haifeng Zhao, Senbo Fu, Minyi Guo (2024). Improving the Multi-Tenancy GPU Performance through Adaptive Bubbleless Spatial-Temporal Sharing. In ASPLOS2024 (CCF-A) (Accepted).

Shulai Zhang, Quan Chen, Weihao Cui, Han Zhao, Chunyu Xue, Zhen Zheng, Wei Lin, Minyi Guo (2024). Improving the Multi-Tenancy GPU Performance through Adaptive Bubbleless Spatial-Temporal Sharing. In Eurosys2024 (CCF-A) (Revision).

Binghao Chen, Han Zhao, Weihao Cui, Yifu He, Shulai Zhang, Quan Chen, Zijun Li, Minyi Guo (2023). Maximizing the Utilization of GPUs Used by Cloud Gaming through Adaptive Co-location with Combo. In SoCC2023 (CCF-B) (Corresponding author).

PDF Cite

Han Zhao, Weihao Cui, Quan Chen, Jingwen Leng, Deze Zeng, Minyi Guo (2023). Improving Cluster Utilization Through Adaptive Resource Management for Deep Neural Network and CPU Jobs Colocation. In TC2023 (CCF-A).

PDF Cite

Han Zhao, Weihao Cui, Quan Chen, Minyi Guo (2022). ISPA: Exploiting Intra-SM Parallelism in GPUs via Fine-grained Resource Management. In TC2022 (CCF-A).

PDF Cite

Weihao Cui, Han Zhao, Quan Chen, Hao Wei, Zirui Li, Deze Zeng, Chao Li, Minyi Guo (2022). DVABatch: Diversity-aware Multi-Entry Multi-Exit Batching for Efficient Processing of DNN Services on GPUs. In ATC2022 (CCF-A).

PDF Cite

Han Zhao, Weihao Cui, Quan Chen, Youtao Zhang, Yanchao Lu, Chao Li, Jingwen Leng, Minyi Guo (2022). Tacker:Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS. In HPCA2022 (CCF-A).

PDF Cite

Weihao Cui, Han Zhao, Quan Chen, Ningxin Zheng, Jingwen Leng, Jieru Zhao, Zhuo Song, Tao Ma, Yong Yang, Chao Li, Minyi Guo (2021). Enable Simultaneous DNN Services Based on Deterministic Operator Overlap and Precise Latency Prediction. In SC2021 (CCF-A).

PDF Cite

Han Zhao, Weihao Cui, Quan Chen, Jieru Zhao, Jingwen Leng, Minyi Guo (2021). Exploiting Intra-SM Parallelism in GPUs via Persistent and Elastic Blocks. In ICCD2021 (CCF-B).

PDF Cite

Weihao Cui, Quan Chen, Han Zhao, Mengze Wei, Xiaoxin Tang, Minyi Guo (2020). E2bird: Enhanced Elastic Batch for Improving Responsiveness and Throughput of Deep Learning Services. In TPDS2020 (CCF-A).

PDF Cite

Han Zhao, Weihao Cui, Quan Chen, Jingwen Leng, Kai Yu, Deze Zeng, Chao Li, Minyi Guo (2020). CODA: Improving Resource Utilization by Slimming and Co-locating DNN and CPU Jobs. In ICDCS2020 (CCF-B).

PDF Cite

Han Zhao, Quan Chen, Yuxian Qiu, Ming Wu, Yao Shen, Jingwen Leng, Chao Li, Minyi Guo (2019). Bandwidth and Locality Aware Task-stealing for Manycore Architectures with Bandwidth-Asymmetric Memory. In TACO2019 (CCF-A).

PDF Cite