The National Science Foundation Division of Computer and Network Systems awarded the University of Texas at Dallas $173,068 on October 1, 2025, to develop and evaluate PARSEC (Parallel and Real-Time Multicore Scheduling for an Efficiently-Used Cache), a system design and analysis framework for managing how multiple real-time, safety-critical tasks share memory resources on multicore processors.
The project will deliver new multicore scheduling algorithms that explicitly manage contending task access to memory, formal analysis techniques to verify timing constraint satisfaction, and open-source automated tools enabling system designers to apply the framework on commercial off-the-shelf processing architectures. PARSEC will be implemented and evaluated on the RISC-V architecture to facilitate public dissemination. The research addresses fundamental challenges in autonomous vehicles, robotics, and other time-sensitive safety-critical systems where multiple computational tasks must execute simultaneously on shared hardware under severe size, weight, and power constraints.
The award funds research at the University of Texas at Dallas campus in Richardson, Texas, with a period of performance from October 1, 2025, through August 31, 2026. This is a Computer and Information Science and Engineering project grant under CFDA 47.070, supporting investigator-initiated research in computing and information science and engineering.