The Case for Optimizing the Frequency of Periodic Data Movements over Hybrid Memory Systems

The Case for Optimizing the Frequency of Periodic Data Movements over Hybrid Memory Systems
复制标题

优化混合内存系统周期性数据移动频率的案例

DOI:
10.1145/3422575.3422788
复制
发表时间:
2020
期刊:
MEMSYS 2020
影响因子:
--
通讯作者:
Gavrilovska, Ada
Gavrilovska, Ada
中科院分区:
--
文献类型:
--
作者:
Doudali, Thaleia Dimitra;Zahka, Daniel;Gavrilovska, Ada

文献摘要

参考文献

被引文献

相似文献

在具有混合存储器组件(例如DRAM和Intel的Optane DC持久性存储器)的新兴系统中,可以通过周期性数据移动来提高应用性能,从而最大限度地提高DRAM使用率和系统资源效率。同样,主要使用的仅NUMA DRAM系统也受益于数据平衡解决方案,如AutoNUMA,它会定期将应用程序及其数据重新映射到同一NUMA节点上。虽然已经有大量的研究集中在要定期移动的数据的巧妙选择上,但是对于如何选择数据移动的频率,即,监测期的持续时间。我们的实验分析表明,微调周期频率可以提高应用程序的性能平均70%的系统与本地连接的内存单元和5倍时,通过互联网络访问远程内存。因此,除了选择数据本身之外,只要巧妙地选择数据移动的频率,就有可能显著提高性能。虽然现有的解决方案凭经验设置的持续时间的期间,我们的工作提供了深入的应用程序级的属性,影响选择的期间。更具体地说,我们表明,有一个应用程序级的数据重用距离和迁移频率之间的相关性。未来的工作旨在巩固这种相关性,并构建一个分析解决方案,为用户提供动态数据管理解决方案可以使用的数据移动频率,以提高性能。
Application performance improvements in emerging systems with hybrid memory components, such as DRAM and Intel’s Optane DC persistent memory, are possible via periodic data movements, that maximize the DRAM use and system resource efficiency. Similarly, predominantly used NUMA DRAM-only systems benefit from data balancing solutions, such as AutoNUMA, which periodically remap an application and its data on the same NUMA node. Although there has been a significant body of research focused on the clever selection of the data to be moved periodically, there is little insight as to how to select the frequency of the data movements, i.e., the duration of the monitoring period. Our experimental analysis shows that fine-tuning the period frequency can boost application performance on average by 70% for systems with locally attached memory units and 5x when accessing remote memory via interconnection networks. Thus, there is potential for significant performance improvements just by cleverly selecting the frequency of the data movements apart from choosing the data itself. While existing solutions empirically set the duration of the period, our work provides insights into the application-level properties that influence the choice of the period. More specifically, we show that there is a correlation between the application-level data reuse distance and migration frequency. Future work aims to solidify this correlation and build a profiling solution that provides users with the data movement frequency which dynamic data management solutions can then use to enhance performance.
DOI: 10.1145/3307681.3325398
发表时间: 2019-06
期刊: Proceedings of the 28th International Symposium on High-Performance Parallel and Distributed Computing
影响因子: --
作者:
Thaleia Dimitra Doudali;S. Blagodurov;Abhinav Vishnu;S. Gurumurthi;Ada Gavrilovska
通讯作者: Thaleia Dimitra Doudali;S. Blagodurov;Abhinav Vishnu;S. Gurumurthi;Ada Gavrilovska
DOI: 10.1145/2926697.2926702
发表时间: 2016-06
期刊: Proceedings of the 2016 ACM SIGPLAN International Symposium on Memory Management
影响因子: --
作者:
Du Shen;Xu Liu;F. Lin
通讯作者: Du Shen;Xu Liu;F. Lin
Mnemo:提高混合内存系统的内存成本效率
DOI: 10.1109/ipdpsw.2019.00080
发表时间: 2019
期刊: Workshop on High-Performance Big Data and Cloud Computing (HPBDC
影响因子: --
作者:
Doudali, Thaleia Dimitra;Gavrilovska, Ada
通讯作者: Gavrilovska, Ada
DOI: --
发表时间: 2019-03
期刊: ArXiv
影响因子: --
作者:
Joseph Izraelevitz;Jian Yang;Lu Zhang;Juno Kim;Xiao Liu;Amirsaman Memaripour;Yun Joon Soh;
通讯作者: Joseph Izraelevitz;Jian Yang;Lu Zhang;Juno Kim;Xiao Liu;Amirsaman Memaripour;Yun Joon Soh;