Dapper: An Adaptive Manager for Large-Capacity Persistent Memory

Dongliang Xue, Linpeng Huang, Chao Li, Chentao Wu

Abstract: Smart applications are becoming more data centric, and the need for businesses to quickly manage vast amounts of data continues to challenge today’s computing infrastructure. Nevertheless, main memory systems consisting entirely of dynamic random-access memory (DRAM) are already hitting their power and capacity limits. It would be beneficial to unleash significant system performance combined emerging memory modules without being worried about design complexities. Design innovations in highly scalable hybrid memory systems hold great promise to realize this vision.