Modern artificial intelligence (AI) systems are increasingly limited not by arithmetic, but by memory. As frontier AI models become more capable, they require far more data to be moved, stored, and accessed efficiently. These workloads systematically generate large volumes of short-lived data that are written in memory, consumed, and quickly discarded, as well as long-lived data that must be retained reliably across much longer time scales. Conventional memory systems are poorly optimized to this behavior, as they are typically designed as one-size-fits-all storage, resulting in excessive energy consumption and increasingly limited density scaling. This project addresses that mismatch by developing a computing infrastructure that treats data persistence as a central design consideration by statically and dynamically matching short-lived and long-lived data to differentiated memory architectures and technologies, each optimized for the appropriate retention window. The result is a more efficient and sustainable foundation for accelerating large-scale AI systems in both datacenter and edge settings. The project also supports education and workforce development through new course materials, industry engagement, and open-source resources that expand participation in next-generation AI hardware accelerator design and computer engineering. The project develops a retention-aware computing stack that aligns AI application data lifetimes with heterogeneous memory architectures and technologies offering different retention times and densities. The research is organized around four integrated activities: (1) building a profiling framework to characterize how long different data values remain useful and to map those lifetimes onto suitable memory tiers; (2) developing algorithmic techniques that restructure computation and data movement to better satisfy retention constraints; (3) designing compilation and scheduling methods for retention-aware data placement across differen