Rong Chen: Pioneering Computer Systems Research at Shanghai Jiao Tong University

In the rapidly evolving landscape of computer science, few researchers have made as significant an impact as Rong Chen, a distinguished professor at Shanghai Jiao Tong University (SJTU). Specializing in operating systems, distributed systems, and hardware-software co-design, Chen has turn into a leading figure in shaping the future of high-performance computing, particularly in AI-driven applications. His work bridges the gap between theoretical innovation and practical implementation, earning him accolades from the global research community and positioning SJTU as a hub for cutting-edge systems research.

Academic Journey and Professional Milestones

Rong Chen’s academic career is marked by a deep commitment to advancing computer systems. He earned his Bachelor’s (2000), Master’s (2004), and Ph.D. (2011) degrees in computer science from Fudan University, where he was mentored by Professor Binyu Zang. His doctoral research laid the groundwork for his later contributions to parallel and distributed systems, a field he has since expanded with groundbreaking work in GPU and XPU (accelerator processing unit) architectures.

In January 2012, Chen joined the School of Computer Science at Shanghai Jiao Tong University as a professor, where he also became a core member of the Institute of Parallel and Distributed Systems (IPADS). IPADS, a leading research lab under SJTU’s umbrella, focuses on developing scalable, high-performance computing solutions for modern applications, from cloud infrastructure to edge computing. Chen’s leadership within the institute has been instrumental in fostering collaborations with industry giants like Alibaba, Huawei, and Microsoft, as well as academic partners such as MIT and the University of Minnesota.

Research Focus: Redefining Systems for the AI Era

Chen’s research is characterized by its practical impact on real-world computing challenges. His work spans three primary domains:

1. Operating Systems for Emerging Hardware

As computing hardware evolves—particularly with the rise of GPUs, TPUs, and other specialized accelerators—traditional operating systems struggle to fully utilize their potential. Chen’s research addresses this gap by developing new OS frameworks that optimize performance, energy efficiency, and multitasking capabilities for heterogeneous hardware environments. Key projects in this area include:

• MSched: A proactive memory scheduling system designed to enable fully-fledged GPU multitasking, allowing multiple AI workloads to run concurrently without performance degradation. This work, published on arXiv, has garnered attention for its potential to revolutionize cloud-based AI training.
• XSched: A general preemptive scheduling framework for diverse XPUs (accelerator processing units), presented at OSDI 2025. XSched provides a unified approach to managing tasks across different types of hardware, reducing latency and improving resource utilization in data centers.
• REEF: A real-time, work-conserving GPU scheduling system for concurrent tasks, introduced at OSDI 2022. REEF ensures that GPU resources are allocated efficiently, even when handling multiple high-priority workloads simultaneously.

2. Distributed Systems and Cloud Computing

Chen’s contributions to distributed systems focus on scalability, fault tolerance, and low-latency communication, critical for modern cloud platforms. His work in this area includes:

• XAuto: A heterogeneous scheduling system that leverages fine-grained, multi-XPU abstraction to optimize task distribution across CPUs, GPUs, and other accelerators. This framework is particularly valuable for AI workloads that require seamless coordination between different types of hardware.
• Collaborations with Industry: Chen has partnered with companies like Alibaba to develop systems that improve the efficiency of large-scale data processing, such as those used in e-commerce recommendation engines and real-time analytics.

3. Hardware-Software Co-Design

Recognizing that hardware and software must evolve in tandem, Chen’s research explores co-design methodologies that enable hardware innovations to be fully exploited by software. This approach has led to advancements in:

• Energy-efficient computing: Developing systems that reduce power consumption without sacrificing performance, a critical need for mobile and edge devices.
• Custom accelerators: Designing specialized hardware for AI workloads, such as neural network inference, to achieve faster processing speeds and lower energy usage.

Awards and Recognition

Chen’s contributions to computer science have been widely recognized, both in China, and internationally. His accolades include:

• Best Paper Awards:
  • EuroSys 2024 and 2015: Awarded for groundbreaking work in operating systems and distributed computing.
  • APSys 2017: Recognized for research on scalable systems for emerging applications.
  • ICPP 2007: Honored for early contributions to parallel computing.
• Huawei OlympusMons Pioneer Award (2020): One of the most prestigious awards in China’s tech industry, given to researchers who demonstrate exceptional innovation in computer science.
• ACM Distinguished Member and CCF Distinguished Member: These honors reflect Chen’s standing in the global and Chinese computer science communities, respectively.

Chen’s work has also been featured in the SOSP/OSDI Hall of Fame, a testament to the long-term impact of his research on the field of operating systems.

Teaching and Mentorship

Beyond his research, Chen is deeply committed to education and mentorship. At SJTU, he teaches courses on operating systems, distributed systems, and computer architecture, inspiring the next generation of computer scientists. His lab has produced numerous Ph.D. And Master’s graduates, many of whom have gone on to successful careers in academia and industry, including roles at Alibaba, Microsoft, and Samsung.

Chen actively seeks self-motivated students with strong backgrounds in systems-related areas. Prospective students interested in working with him are encouraged to reach out via email at rongchen@sjtu.edu.cn.

Collaborations and Industry Impact

Chen’s research has had a tangible impact on the tech industry, particularly in China. His collaborations with leading companies have helped shape the development of:

• Cloud Computing: His work on GPU scheduling and distributed systems has been integrated into cloud platforms, improving the efficiency of AI training and inference workloads.
• Edge Computing: Chen’s research on hardware-software co-design has influenced the development of edge devices, enabling faster and more energy-efficient processing for applications like autonomous vehicles and IoT.
• AI Infrastructure: His frameworks for heterogeneous scheduling are being used to optimize AI workloads in data centers, reducing costs and improving performance for companies like Alibaba and Huawei.

Key Takeaways: Why Rong Chen’s Work Matters

Chen’s research addresses some of the most pressing challenges in modern computing:

• Bridging the Gap Between Hardware and Software: His work ensures that emerging hardware—such as GPUs and XPUs—can be fully utilized by operating systems, unlocking new levels of performance for AI and other compute-intensive applications.
• Enabling Scalable AI: By developing systems that efficiently manage resources across heterogeneous hardware, Chen is helping to make AI more accessible and cost-effective for businesses and researchers.
• Driving Industry Innovation: His collaborations with tech giants have led to real-world implementations of his research, demonstrating the practical value of academic work.
• Educating the Next Generation: Through his teaching and mentorship, Chen is shaping the future of computer science in China and beyond.

Looking Ahead: The Future of Systems Research

As AI continues to transform industries, the demand for high-performance, scalable, and energy-efficient computing systems will only grow. Rong Chen’s work is at the forefront of this evolution, with ongoing projects exploring:

• Next-Generation Operating Systems: Developing OS frameworks that can seamlessly integrate with future hardware innovations, such as quantum accelerators and neuromorphic chips.
• Sustainable Computing: Reducing the energy footprint of data centers and edge devices, a critical challenge as global computing demands rise.
• Real-Time AI: Enabling AI systems to process data and make decisions in real-time, with applications in autonomous vehicles, robotics, and healthcare.

Chen’s vision for the future of computer systems is one where hardware and software evolve in harmony, unlocking new possibilities for AI, cloud computing, and beyond. His leadership at SJTU and IPADS ensures that China remains a global leader in this dynamic field.

FAQ: Understanding Rong Chen’s Research

What is the Institute of Parallel and Distributed Systems (IPADS)?

IPADS is a research lab within Shanghai Jiao Tong University dedicated to advancing the field of parallel and distributed computing. It focuses on developing scalable, high-performance systems for modern applications, including AI, cloud computing, and edge computing. IPADS is known for its collaborations with industry and academia, as well as its contributions to open-source software.

What are XPUs, and why are they vital?

XPUs refer to accelerator processing units, a category of specialized hardware designed to handle specific types of computations more efficiently than traditional CPUs. Examples include GPUs (graphics processing units), TPUs (tensor processing units), and FPGAs (field-programmable gate arrays). XPUs are critical for AI workloads, as they can process large amounts of data in parallel, significantly speeding up tasks like machine learning training and inference.

How does Rong Chen’s work impact everyday technology?

Chen’s research has a direct impact on the technology we use daily, even if we don’t realize it. For example:

• Cloud Services: His work on GPU scheduling improves the performance of cloud-based AI services, such as voice assistants and recommendation engines.
• Smartphones and IoT Devices: His research on energy-efficient computing helps extend battery life and improve performance in mobile and edge devices.
• Data Centers: His frameworks for heterogeneous scheduling reduce costs and energy consumption in data centers, making cloud computing more sustainable.

What is the Huawei OlympusMons Pioneer Award?

The Huawei OlympusMons Pioneer Award is one of the most prestigious honors in China’s tech industry. It recognizes researchers and engineers who have made outstanding contributions to computer science and technology. The award is named after Olympus Mons, the tallest volcano in the solar system, symbolizing the towering impact of the recipients’ work.

How can students receive involved in Rong Chen’s research?

Chen is actively seeking self-motivated students with strong backgrounds in computer systems, operating systems, or distributed computing. Interested students can reach out to him via email at rongchen@sjtu.edu.cn. His lab offers opportunities to work on cutting-edge research projects with real-world applications, as well as collaborations with industry partners.

Conclusion

Rong Chen’s career is a testament to the power of innovation in computer science. Through his research, teaching, and industry collaborations, he has not only advanced the field of systems research but also inspired a new generation of computer scientists. As AI and computing continue to evolve, Chen’s work will play a pivotal role in shaping the technologies that define our future. For those interested in the intersection of hardware and software, his contributions offer a roadmap for the next era of computing.

For more information about Rong Chen’s research, visit his official page at IPADS or explore his publications on Google Scholar.