首页> 外文会议>International Conference on Identification, Information and Knowledge in the Internet of Things >Hybrid-LRU Caching Scheme for PDRAM Hybrid Memory Architecture in Cloud Computing
【24h】

Hybrid-LRU Caching Scheme for PDRAM Hybrid Memory Architecture in Cloud Computing

机译:云计算中PDRAM混合内存架构的Hybrid-LRU缓存方案

获取原文

摘要

This in recent years, the mixed memory (PDRAM) which is consisted of the phase-change memory (PRAM) and the conventional memory (DRAM) has drawn a lot of attention from both industry and academia. It is a promising alternative to replace the traditional memory architecture. PDRAM has good characteristics as large capacity, good stability and non-volatile, while PRAM has disadvantages of a limited life and large access latency. Traditional policies are not sufficient to be directly applied to the PDRAM memory architecture. They cannot adapt to the new features of the hybrid architecture because of their undifferentiated operation, extensive use of PRAM can cause performance degradation and shorten the life of PDRAM memory. This paper proposed Hybrid-LRU caching scheme to address these problems. Our scheme mainly uses the cache consistency address resolution mode to distinguish between different physical mediums in PDRAM, and then take different actions depending on different physical mediums. We have taken a variety of tradition policies like LRU, FIFO, RANDOM, CFLRU to make experimental comparisons. The experimental results have shown that our scheme can reduce the PRAM utilization rate of 11.8% and improve the performance by 4.6%, energy consumption of write and read operation can be reduced up to 88.2%.
机译:近年来,由相变存储器(PRAM)和常规存储器(DRAM)组成的混合存储器(PDRAM)已经引起了工业界和学术界的广泛关注。它是替代传统内存架构的有前途的替代方法。 PDRAM具有大容量,良好的稳定性和非易失性的良好特性,而PRAM具有寿命有限和访问延迟大的缺点。传统策略不足以直接应用于PDRAM存储器体系结构。由于它们无法区分的操作,它们无法适应混合体系结构的新功能,PRAM的广泛使用会导致性能下降并缩短PDRAM存储器的寿命。本文提出了Hybrid-LRU缓存方案来解决这些问题。我们的方案主要使用缓存一致性地址解析模式来区分PDRAM中的不同物理介质,然后根据不同的物理介质采取不同的操作。我们采用了各种传统策略(例如LRU,FIFO,RANDOM,CFLRU)进行实验比较。实验结果表明,该方案可将PRAM利用率降低11.8%,性能提高4.6%,读写操作的能耗可降低88.2%。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号