期刊文献+

一种高效的混合内存布局机制与编码技术 被引量:4

Efficient Mechanism of Hybrid Memory Placement and Erasure Code
下载PDF
导出
摘要 随着大数据和多核技术的发展,传统内存技术的发展已经远远不能满足大量数据密集型应用涌现所催生的内存计算需求。近年来,新型非易失性存储器(NVM)的兴起与发展为打破传统内存技术瓶颈提供了契机。相变存储器(PCM)作为一种典型的新型非易失性存储器(NVM),与传统内存DRAM各有优势,被认为是最有可能代替传统内存DRAM的存储器,在内存应用中具有很好的发展前景。基于DRAM和PCM的混合内存使得同时发挥DRAM与PCM各自的优势成为可能,故提出一种DRAM与PCM混合内存架构,设计针对混合内存布局的高效读写策略及数据迁移机制,并且在混合内存系统中应用纠删码来提高系统的可靠性。实验表明,此混合内存系统能够大大减少能耗,提高数据吞吐量,同时保证读写的可靠性。 With the rapid development of big data and multi-core technology, the growth of traditional memory technology, as a matter of fact, has been far away from satisfying the memory computing needs along with the emergence of a large number of data intensive applications. In recent years, the emergence and development of non-volatile memory (NVM) obviously provides an opportunity to break the bottleneck of traditional memory technology. As a typical emerging non-volatile memory, phase change memory (PCM) and traditional DRAM memory have their own advantages. What's more, it is widely considered to be most likely to replace traditional DRAM memory and has very good development prospects in the memory applications. Hybrid memory based on DRAM and PCM makes it possible to play the respective advantages of DRAM and PCM simultaneously. Therefore, in this paper, a hybrid memory architecture of DRAM and PCM was proposed, which is designed to evidently improve the system reliability of the hybrid memory system by using erasure code, based on the efficient reading, writing strategy and data migration mechanism. Experiments firmly show that the hybrid memory system can greatly reduce energy consumption, obviously improve the throughput, and ensure the reliability of reading and writing.
出处 《计算机科学》 CSCD 北大核心 2017年第6期57-62,共6页 Computer Science
基金 国家自然科学基金项目(61402518)资助
关键词 混合内存 DRAM PCM 纠删码 读写策略 Hybrid memory, DRAM, PCM, Erasure codes, Reading and writing strategy
  • 相关文献

参考文献3

二级参考文献100

  • 1刘金垒,李琼.新型非易失相变存储器PCM应用研究[J].计算机研究与发展,2012,49(S1):90-93. 被引量:5
  • 2刘波,宋志棠,封松林.我国相变存储器的研究现状与发展前景[J].微纳电子技术,2007,44(2):55-61. 被引量:14
  • 3Layman P, Varian H R. How much information 2003? [EB/OL]. [2010 10-18]. http://www2, sims. berkeley. edu/research/proiects/how-mueh-info-2003.
  • 4Pinheiro E, Weber W D, Barroso L A. Failure trends in a large disk drive population [C] //Proc of the 5th USENIX Conf on File and Storage Technologies. Berkeley, CA: USENIX Association, 2007 : 17-28.
  • 5Schroeder B, Gibson G A. Disk failures in the real world: What does an MTTF of 1,000,000 hours mean to you? [C] //Proc of the 5th USENIX Conf on File and Storage Technologies. Berkeley, CA: USENIX Association, 2007: 1-16.
  • 6Bairavasundaram L N, Goodson G R, Pasupathy S, et al. An analysis of latent sector errors in disk drives [C]//Proc of 2007 ACM SIGMETRICS Int Conf on Measurement and Modeling of Computer Systems. New York: ACM, 200: 289-300.
  • 7Hafner J M, Deenadhayalan V, Rao K, et al. Matrix methods for lost data reconstruction in erasure codes [C] // Proc of the 4th USENIX Conf on File and Storage Technologies. Berkeley, CA: USENIX Association, 2005: 183-196.
  • 8Hafner J M, Deenadhayalan V, Kanungo T, et al. Performance metrics for erasure codes in storage systems, RJ 10321 [R]. San Jose, [A] IBM Research, 2004.
  • 9Li M, Shu J, Zheng W. GRID Codes: Strip based erasure codes with high fault tolerance for storage systems [J].ACM Transon Storage, 2009, 4(4): 1-22.
  • 10Blaum M, Brady J, Bruek J, et al. EVENODD: An efficient scheme for tolerating double disk failures in RAID architectures [J].IEEE Trans on Computer, 1995, 44 (2) 192-202.

共引文献115

同被引文献6

引证文献4

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部