At Kennesaw State University, Associate Professor Xuechen Zhang is working on new ways to improve how supercomputers process large amounts of data. His research focuses on a method called computational storage, which allows some data processing to happen directly on storage devices before the information is sent to the main processor.
“When we train scientific machine-learning models, we need a lot of data,” Zhang said. “Moving that data from storage to processors takes time, and preprocessing can become a major hurdle.”
This approach could help reduce delays in artificial intelligence training and scientific simulations, especially as datasets grow larger. The faster processing may allow scientists in areas such as climate modeling and medical research to reach conclusions more quickly by running simulations in less time.
“In the future, supercomputers will be more heterogeneous and specialized,” Zhang said. “Different components will handle different tasks, and that flexibility will open the door to faster and more scalable scientific applications.”
Zhang’s project has received a $479,358 grant from the National Science Foundation for three years. The funding supports doctoral students at KSU, provides access to high-performance computing resources, enables presentations at national conferences, and helps strengthen student curriculum.
“This funding allows us to build a pipeline for our students and give them hands-on experience with state-of-the-art systems,” Zhang said. “It is not only about research results, but also about preparing students for careers in high-performance computing and artificial intelligence.”
The research is being conducted with Xiaokun Yang from the University of Houston–Clear Lake. This partnership combines hardware and software expertise.
Yiming Ji, Interim Dean of the College of Computing and Software Engineering at KSU, commented on the impact of this work: “Dr. Zhang’s work reflects the type of forward-thinking research we strive to cultivate in the College of Computing and Software Engineering. His efforts advance scientific discovery while creating meaningful learning opportunities for our students.”
After joining KSU, Zhang established the AI Systems and Storage Lab on the Marietta Campus where he is assembling servers and recruiting doctoral students. Early tests suggest that data preprocessing can be a significant challenge in large-scale computing projects. The lab is expected to grow as more graduate researchers join.
