Metall: A Persistent Memory Allocator Enabling Graph Processing
2019 IEEE/ACM 9th Workshop on Irregular Applications: Architectures and Algorithms (IA3)(2019)
摘要
We present Metall, a persistent memory allocator designed to provide developers with an API to allocate custom C++ data structures in both block-storage and byte-addressable persistent memories (e.g., NVMe and Intel Optane DC Persistent Memory). Metall incorporates state-of-the-art allocation algorithms in Supermalloc with the rich C++ interface developed by Boost.Interprocess, and provides persistent memory snapshoting (versioning) capabilities. We demonstrate Metall processing large graphs in a variety of conditions and data-structure configurations, indicating a bright future for data-analytics leveraging emerging persistent memory technologies.
更多查看译文
关键词
Boost.Interprocess,data analytics,persistent memory snapshoting,C++ interface,Supermalloc,byte-addressable persistent memories,block-storage persistent memories,API,data structure configurations,graph processing,allocation algorithms,custom C++ data structures,persistent memory allocator,Metall
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络