Building High-Performance Smartphones via Non-Volatile Memory: The Swap Approach

被引:42
作者
Zhong, Kan [1 ]
Wang, Tianzheng [2 ]
Zhu, Xiao [1 ]
Long, Linbo [1 ]
Liu, Duo [3 ]
Liu, Weichen [1 ]
Shao, Zili [2 ]
Sha, Edwin H-M [1 ]
机构
[1] Chongqing Univ, Coll Comp Sci, Key Lab Dependable Serv Comp Cyber Phys Soc, Minist Educ, Chongqing, Peoples R China
[2] Univ Toronto, Dept Comp Sci, Toronto, ON, Canada
[3] Hong Kong Polytech Univ, Dept Comp, Hong Kong, Peoples R China
来源
2014 INTERNATIONAL CONFERENCE ON EMBEDDED SOFTWARE (EMSOFT) | 2014年
基金
中国国家自然科学基金; 高等学校博士学科点专项科研基金;
关键词
PHASE-CHANGE MEMORY;
D O I
10.1145/2656045.2656049
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Smartphones are getting increasingly high-performance with advances in mobile processors and larger main memories to support feature-rich applications. However, the storage subsystem has always been a prohibitive factor that slows down the pace of reaching even higher performance while maintaining good user experience. Despite today's smartphones are equipped with larger-than-ever main memories, they consume more energy and still run out of memory. But the slow NAND flash based storage vetoes the possibility of swapping-an important technique to extend main memory-and leaves a system that constantly terminates user applications under memory pressure. In this paper, we revisit swapping for smartphones with fast, byte-addressable, non-volatile memory (NVM) technologies. Instead of using flash, we build the swap area with NVM, to allow high performance without sacrificing user experience. Based on NVM's high performance and byte-addressability, we show that a copy-on-write swap-in scheme can achieve even better performance by avoiding unnecessary memory copy operations. To avoid fast worn-out of certain NVMs, we also propose Heap-Wear, a wear leveling algorithm that more evenly distributes writes in NVM. Evaluation results based on the Google Nexus 5 smartphone show that our solution can effectively enhance smartphone performance and give better wear-leveling of NVM.
引用
收藏
页数:10
相关论文
共 30 条
[1]  
[Anonymous], 2008, Professional Linux Kernel Architecture
[2]  
[Anonymous], 2012, 2012 INT JT C NEUR N, DOI DOI 10.1109/HPCA.2012.6169027
[3]  
Chen CH, 2012, DES AUT CON, P453
[4]  
Condit J, 2009, SOSP'09: PROCEEDINGS OF THE TWENTY-SECOND ACM SIGOPS SYMPOSIUM ON OPERATING SYSTEMS PRINCIPLES, P133
[5]  
Duo Liu, 2011, Proceedings of the 2011 IEEE 32nd Real-Time Systems Symposium (RTSS 2011), P357, DOI 10.1109/RTSS.2011.40
[6]  
Eilert S, 2009, 2009 IEEE INTERNATIONAL MEMORY WORKSHOP, P72
[7]   Sleep-Aware Variable Partitioning for Energy-Efficient Hybrid PRAM and DRAM Main Memory [J].
Fu, Chenchen ;
Zhao, Mengying ;
Xue, Chun Jason ;
Orailoglu, Alex .
PROCEEDINGS OF THE 2014 IEEE/ACM INTERNATIONAL SYMPOSIUM ON LOW POWER ELECTRONICS AND DESIGN (ISLPED), 2014, :75-80
[8]  
Google, 2014, ANDR DEV DOC
[9]  
Hosomi M, 2005, INT EL DEVICES MEET, P473
[10]  
Hynix, 2009, HYNIX NEWSLETTER