EECS Professor Receives National Science Foundation Award for Collaborative Research

Heechul Yun, Associate Professor in KU Engineering's Department of Electrical Engineering and Computer Science (EECS) and researcher at the Institute for Information Sciences (I2S), was recently awarded a grant from the National Science Foundation for a project titled "Effortless Data Locality Through Near-memory On-the-fly Data Transformation."

The ability of computing systems to efficiently and timely process large amounts of data is a key enabler in the modern landscape of data-driven applications. To bridge the widening gap between memory technology and processors, computing systems continue to rely heavily on complex multi-level cache hierarchies. While caches can prevent costly accesses to downstream memory if the processed data items exhibit good spatiotemporal locality, locality does not always emerge naturally in complex data processing pipelines.

"This project proposes a novel software/hardware collaborative approach to improve data locality with specialized programmable hardware units, which we call data transformation units (DTUs), that can reorganize data on-the-fly so that the computing units (CPUs or GPUs) can process them much more efficiently," says Yun. "Essentially, what we hope to achieve is to enable spatiotemporal locality to be achieved effortlessly, without the need for heavy algorithmic re-engineering."

Yun notes that it is a collaborative research project with two other investigators at Boston University. Yun is the KU-side principal investigator of the project while BU is the leading institution. This award of $396,000 to KU's Office of Research, which includes I2S, is part of the NSF's Software & Hardware Foundation and is co-funded by NSF's Established Program to Stimulate Competitive Research (EPSCoR). The award was announced in July and is estimated to run through July 2028.