Project Grant 2504591

This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program provides $299,921 to Rutgers, The State University to develop a unified framework for reducing data movement overheads in heterogeneous high-performance computing (HPC) systems. The project integrates three core components: a cross-layer monitoring and learning framework to characterize data transfer patterns and predict contention, a heterogeneity-aware data movement scheduler to coordinate bandwidth usage, and a collaborative caching and prefetching architecture to anticipate future data needs. This research aims to treat data movement as a first-class task parallel to computation, using analytical and machine learning techniques to reduce interference and improve overall throughput for scientific computing workloads such as molecular dynamics, graph neural networks, and particle-in-cell simulations. The project will be validated on petascale and exascale HPC systems, with the goal of providing generalizable strategies for optimizing data movement in next-generation scientific computing environments. This award was deemed worthy of support by the NSF based on its intellectual merit and broader impacts.