22 May 2024
学术报告：On Optimizing Mobile Memory and Storage
时间：2024年5月22日，星期三
地点：湖北省武汉市，武汉大学，计算机学院B405会议室
联系人：李清安 qingan@whu.edu.cn
| Time | Title & Speaker |
|---|---|
| 14:00 - 15:00 | On Optimizing Mobile Memory and Storage Prof. Chun Jason Xue, MBZUAI (穆罕默德·本·扎耶德人工智能大学) |
| 15:00 - 16:00 | Enabling Efficient and Scalable Parallelization for Data-Intensive Computations Dr. Junqiao QIU, City University of Hong Kong (香港城市大学) |
On Optimizing Mobile Memory and Storage
Current mobile operating systems, such as Android, inherit the Linux kernel. As a result, system software designs that were targeted for servers are now applied in mobile devices. In this series of work, through analyzing mobile application characteristics on files, memory, and storage usage, we found that mobile applications have their own unique characteristics which differ from applications on servers. These differences present new optimization opportunities in mobile memory and storage management. In this talk, I will present several mobile memory and storage management-related works that improve user experience on mobile devices based on mobile application characterization.
Prof. Chun Jason Xue is a professor at the Department of Computer Science, MBZUAI, Abu Dhabi. He received Ph.D. in Computer Science from the University of Texas at Dallas in 2007 and joined the City University of Hong Kong in the same year. He is currently an associate editor of ACM Transactions on Embedded Computing Systems, ACM Transactions on Storage, and ACM Transactions on CPS.
He has served/serves as General Chair, Program Chair, and Program Committee Member on a number of technical conferences and workshops. He is currently the Steering Committee Chair of ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES) since 2020.
His research interest includes system software for memory and storage optimizations, considering mobile and embedded platforms, with a focus on memory technologies such as non-volatile memories and flash memories.
Enabling Efficient and Scalable Parallelization for Data-Intensive Computations
Exploiting parallelism is crucial for achieving high-performance data processing on modern processors. However, many data processing routines still run serially due to the sequential nature of their underlying computation models. In this presentation, I will demonstrate how to effectively break inherent data dependencies and enable scalable and efficient data-parallel processing.
I will begin by introducing our previous work on using speculation to auto-parallelize bitstream processing applications. Following this, I will discuss our ongoing projects that push the boundaries of speculative parallelization. These include leveraging non-SIMD vector instructions to accelerate speculative parallelization, integrating speculation into pattern-aware graph mining applications, and enabling efficient concurrent GPU-based inferences.
Finally, I will conclude the talk by sharing my ideas on parallelizing more general applications, aiming to broaden the applicability of these techniques.
Dr. Junqiao QIU is an Assistant Professor in the Department of Computer Science at City University of Hong Kong. Prior to joining CityU, he was a tenure-track assistant professor at Michigan Technological University and earned his Ph.D. from the University of California Riverside. His research interests span the areas of compilers and systems, with a focus on enabling efficient parallel computing for data-intensive applications and those with irregular data access patterns. He is a recipient of the ACM SIGPLAN PAC Award, the NSF CRII Award, and the Best Paper Award at ASPLOS 2020.