DAPPER: a database-inspired approach to persistent memory

Persistent memory collapses the boundaries between the inmemory and secondary storage representations of data structures, and enables the programmer to process data directly from an imperative runtime. We present the early results of the DAPPER project, which takes a database-inspired approach to persistent memory. It supports recoverable data structures in persistent memory at the imperative language level, algorithms optimized for the performance characteristics of the new medium and a runtime to support them, and workload-driven adaptive data placement.