A Novel Page Replacement Algorithm for the Hybrid Memory Architecture Involving PCM and DRAM

  • Kaimeng Chen
  • Peiquan Jin
  • Lihua Yue
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8707)


Recently, the development of phase change memory (PCM) motivates new hybrid memory architectures that consist of PCM and DRAM. An important issue in such hybrid memory architectures is how to manage the pages resisting in heterogeneous memories. For example, when a requested page is missing in the hybrid memory and the memory has no free spaces, what pages in which type of memory (PCM or DRAM) should be replaced? This problem is much different from traditional buffer replacement management, where they do not consider the special properties of different types of memories. In particular, differing from DRAM, PCM is non-volatile but it has lower access speeds than DRAM. Further, PCM has a limited write endurance which implies that it cannot be written endlessly. Therefore, we have to design a new page replacement algorithm that can not only maintain a high hit ratio as traditional algorithms do but also can avoid frequent writes to PCM. In this paper, aiming to provide a new solution to the page replacement problem in PCM/DRAM-based hybrid memories, we propose a new algorithm called MHR-LRU (Maintain-hit-ratio LRU). The objective of our algorithm is to reduce PCM writes while maintaining a high hit ratio. Specially, it keeps recently updated pages in DRAM and performs page migrations between PCM and DRAM. The migrations take into account both page access patterns and the influences of page faults. We conduct trace-driven experiments and compared our proposal with some existing algorithms including LRU, LRU-WPAM, and CLOCK-DWF. The results show that our proposal is able to efficiently reduce PCM writes without degrading the hit ratio. Thus, our study offers a better solution for the page replacement issue in PCM/DRAM-based hybrid memory systems than previous approaches.


Page replacement Phase change memory Hybrid memory 


  1. 1.
    Burr, G.W., Kurdi, B.N., Campbell Scott, J., et al.: Overview of candidate device technologies for storage-class memory. IBM Journal of Research and Development 52(4-5), 449–464 (2008)CrossRefGoogle Scholar
  2. 2.
    Freitas, R.F., Wilcke, W.W.: Storage-class memory: The next storage system technology. IBM Journal of Research and Development 52(4-5), 439–448 (2008)CrossRefGoogle Scholar
  3. 3.
    Benjamin, C.: Lee, Engin Ipek, Onur Mutlu, et al., Architecting phase change memory as a scalable dram alternative. In: Proc. of ISCA, pp. 2–13 (2009)Google Scholar
  4. 4.
    Qureshi, M.K., Srinivasan, V., Rivers, J.A.: Scalable high performance main memory system using phase-change memory technology. In: Proc. of ISCA, pp. 24–33 (2009)Google Scholar
  5. 5.
    Dhiman, G., Ayoub, R.Z., Rosing, T.: PDRAM: a hybrid PRAM and DRAM main memory system. In: Proc. of DAC, pp. 664–669 (2009)Google Scholar
  6. 6.
    Seok, H., Park, Y., Park, K.W., et al.: Efficient page caching algorithm with prediction and migration for a hybrid main memory. ACM SIGAPP Applied Computing Review 11(4), 38–48 (2011)CrossRefGoogle Scholar
  7. 7.
    Lee, S., Bahn, H., Noh, S.H.: Characterizing Memory Write References for Efficient Management of Hybrid PCM and DRAM Memory. In: Proc. of MASCOTS, pp. 168–175 (2011)Google Scholar
  8. 8.
    Corbato, F.J.: A Paging Experiment with the Multics System. In: Honor of P. M. Morse, pp. 217–228. MIT Press (1969)Google Scholar
  9. 9.
    Bucy, J.S., Schindler, J., Schlosser, S.W., et al.: The disksim simulation environment version 4.0 reference manual (cmu-pdl-08-101). Parallel Data Laboratory 26 (2008)Google Scholar
  10. 10.
    Yang, P., Jin, P., Yue, L.: Hybrid Storage with Disk Based Write Cache. In: Xu, J., Yu, G., Zhou, S., Unland, R. (eds.) DASFAA Workshops 2011. LNCS, vol. 6637, pp. 264–275. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  11. 11.
    Yang, P., Jin, P., Wan, S., Yue, L.: HB-Storage: Optimizing SSDs with a HDD Write Buffer. In: Gao, Y., Shim, K., Ding, Z., Jin, P., Ren, Z., Xiao, Y., Liu, A., Qiao, S. (eds.) WAIM 2013 Workshops 2013. LNCS, vol. 7901, pp. 28–39. Springer, Heidelberg (2013)CrossRefGoogle Scholar
  12. 12.
    Jin, P., Ou, Y., Haerder, T., Li, Z.: ADLRU: An Efficient Buffer Replacement Algorithm for Flash-based Databases. Data and Knowledge Engineering (DKE) 72, 83–102 (2012)CrossRefGoogle Scholar
  13. 13.
    Li, Z., Jin, P., Su, X., Cui, K., Yue, L.: CCF-LRU: A New Buffer Replacement Algorithm for Flash Memory. IEEE Trans. on Consumer Electronics 55(3), 1351–1359 (2009)CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2014

Authors and Affiliations

  • Kaimeng Chen
    • 1
  • Peiquan Jin
    • 1
    • 2
  • Lihua Yue
    • 1
    • 2
  1. 1.School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefeiChina
  2. 2.Key Laboratory of Electromagnetic Space InformationChinese Academy of SciencesHefeiChina

Personalised recommendations