We investigate innovative system software techniques that significantly improve the performance, efficiency, security, and reliability of computer systems. We take a vertically integrated research approach to maximize the synergistic effects across the entire computer system hierarchy including computer architecture, system software, runtimes, and applications. Currently, we focus on the following research projects – (1) system software for high-performance and efficient machine learning, (2) machine learning-augmented system software, (3) scalable and efficient parallel and distributed computing, (4) system software for large-scale and emerging memory systems, and (5) computer systems security. We have fully-funded research positions and are actively looking for brilliant graduate students, undergraduate students, and postdocs. Please do not hesitate to contact us, if you are interested in conducting any of the following research projects and/or have your own exciting ideas on system software research. If you want to join our lab as a graduate student, you can apply to either the Department of Computer Science and Engineering or the Graduate School of Artificial Intelligence.
- System Software for High-Performance and Efficient Machine Learning
- Characterizing and optimizing the machine-learning frameworks (e.g., TensorFlow, PyTorch) using high-performance accelerators (e.g., GPGPUs, NPUs) [Euro-Par’18], [PACT’19], [PACT’21], [PACT’24]
- Characterizing and optimizing the programming language runtimes (e.g., garbage collection) and the operating system (e.g., memory management, task scheduling) for high-performance machine learning and Big Data processing [IISWC’16], [TC’20]
- Resource management for large-scale distributed systems for high-performance machine learning and Big Data processing [ICDCS’17p], [TSC’19]
- Machine Learning-Augmented System Software
- Improving the efficiency of parallel and distributed task schedulers and resource managers using machine learning [ICDCS’17p], [TSC’19], [PACT’21]
- Machine learning-augmented dynamic data placement and migration techniques
- Enhancing the security and reliability of computer systems through machine learning
- Machine learning techniques for code analysis, generation, and optimization
- Scalable and Efficient Parallel and Distributed Computing
- OS and runtime scheduling techniques for parallel and heterogeneous systems [DAC’15], [Euro-Par’16], [ICPP’16], [DATE’17], [CCGrid’18a], [PACT’18], [EuroSys’19], [PACT’19p], [TPDS’21], [IPDPS’21]
- High-performance and energy-efficient many-core and GPGPU computing [MES’15], [MICPRO’16], [ICCD’16], [EMSOFT’16], [TPDS’19]
- Performance/power analysis and optimization of real-world and emerging applications on various systems ranging from embedded to large-scale parallel systems [IPDPS’18], [JPDC’19]
- System Software for Large-Scale and Emerging Memory Systems
- System software support for heterogeneous memory systems [NVMSA’16], [ICS’17], [ICCD’18], [Access’23]
- Enhancing the performance, durability, and reliability of conventional and emerging workloads on heterogeneous memory systems [ASPLOS’16], [ASPLOS’17]
- Efficient memory management techniques for emerging computer systems (e.g., GPU, NPU)
- Computer Systems Security
- Design and implementation of secure system software for safe and efficient computing ranging from embedded to cloud computing [CCGrid’18b], [TSC’21]
- Developing security attacks by exploiting the vulnerabilities of the system software and computer architecture [HPCA’22], [ESORICS’23]
- Applying machine-learning techniques to detect security attacks
- Sponsors
In this work, we aim to research and develop system software support for high-performance and efficient machine learning. This research project is funded by National Research Foundation of Korea (NRF) from 2021 to 2025, Institute for Information & Communication Technology Promotion (IITP) from 2021 to 2028, and IITP from 2018 to 2022. Specifically, we investigate the following research topics:
In this work, we aim to investigate machine learning-augmented system software. This research project is funded by NRF from 2021 to 2025, IITP from 2021 to 2028, and IITP from 2018 to 2022. Specifically, we investigate the research topics below. We have just started this project and are actively looking for highly-motivated and passionate graduate and undergraduate students for this project.
In this work, we aim to research and develop system software techniques for highly-scalable and energy-efficient parallel computing on embedded, multi/many-core, and GPGPU systems. This research project is funded by NRF from 2021 to 2025. Specifically, we investigate the following research topics:
In this work, we aim to investigate system software support for large-scale and emerging memory systems. This research project is funded by Samsung Advanced Institute of Technology (SAIT) from 2022 to 2024 and IITP from 2021 to 2028. Specifically, we investigate the following research topics:
In this work, we aim to investigate the design and implementation of secure computer systems. This research project is funded by IITP from 2021 to 2028. Specifically, we investigate the following research topics:
Our research has been supported by grants from Ministry of Science and ICT (MSIT), Ministry of Trade, Industry and Energy (MOTIE), NRF, IITP, UNIST, ETRI, Samsung Advanced Institute of Technology (SAIT), and LG Electronics.
