Skip to main content
SpringerLink
Log in
Book cover

IFIP International Conference on Network and Parallel Computing

NPC 2022: Network and Parallel Computing pp 180–191Cite as

TransMigrator: A Transformer-Based Predictive Page Migration Mechanism for Heterogeneous Memory

  • Conference paper
  • First Online:

  • 851 Accesses

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13615))

Abstract

Page migration strategies are crucial to the performance of a hybrid main memory system which consists of DRAM and Non-Volatile RAM. Previous locality-based migration strategies have limitations on deciding which pages should be placed in limited DRAM. In this paper, we propose TransMigrator, a transformer-based predictive page migration mechanism. TransMigrator uses an end-to-end neural network to directly predict the page that will be accessed most in the near future, by learning patterns from long memory access history. The network achieved 0.7245 average accuracy of prediction with 0.804 MB model parameter size. Besides, a threshold-based method is used at the same time to make the system robust. TransMigrator reduces access time by 23.59% on average compared with AC-CLOCK, THMigrator and VC-HMM.

This is a preview of subscription content, log in via an institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

References

  1. Adavally, S., Islam, M., Kavi, K.: Dynamically adapting page migration policies based on applications’ memory access behaviors. ACM J. Emerg. Technol. Comput. Syst. 17(2), 1–24 (2021)

    Article  Google Scholar 

  2. Burr, G.W., et al.: Recent progress in phase-change memory technology. IEEE J. Emerg. Sel. Top. Circuits Syst. 6(2), 146–162 (2016)

    Article  Google Scholar 

  3. Cappelletti, P.: Non volatile memory evolution and revolution. In: 2015 IEEE International Electron Devices Meeting (IEDM), pp. 10.1.1–10.1.4 (2015)

    Google Scholar 

  4. Chen, A.: A review of emerging non-volatile memory (NVM) technologies and applications. Solid-State Electron. 125, 25–38 (2016)

    Article  Google Scholar 

  5. Dayarathna, M., Wen, Y., Fan, R.: Data center energy consumption modeling: a survey. IEEE Commun. Surv. Tutor. 18(1), 732–794 (2016)

    Article  Google Scholar 

  6. Doudali, T.D., Blagodurov, S., Vishnu, A., Gurumurthi, S., Gavrilovska, A.: Kleio: a hybrid memory page scheduler with machine intelligence. In: Proceedings of the 28th International Symposium on High-Performance Parallel and Distributed Computing, pp. 37–48. HPDC 2019, Association for Computing Machinery, New York, June 2019

    Google Scholar 

  7. Doudali, T.D., Gavrilovska, A.: Toward Computer Vision-based Machine Intelligent Hybrid Memory Management. In: The International Symposium on Memory Systems, pp. 1–6. ACM, Washington, DC, USA, September 2021

    Google Scholar 

  8. Henning, J.L.: SPEC CPU2006 benchmark descriptions. ACM SIGARCH Comput. Architect. News 34(4), 1–17 (2006)

    Article  Google Scholar 

  9. John Pimo, E.S., Ashok, V., Logeswaran, T., Sri Sai Satyanarayana, D.: A comparative performance analysis of phase change memory as main memory and DRAM. In: Proceedings of Materials Today, February 2021

    Google Scholar 

  10. Kim, S., Hwang, S.H., Kwak, J.W.: Adaptive-classification CLOCK: page replacement policy based on read/write access pattern for hybrid DRAM and PCM main memory. Microprocess. Microsyst. 57, 65–75 (2018)

    Article  Google Scholar 

  11. Lee, S., Bahn, H., Noh, S.H.: CLOCK-DWF: a write-history-aware page replacement algorithm for hybrid PCM and DRAM memory architectures. IEEE Trans. Comput. 63(9), 2187–2200 (2014)

    Article  MathSciNet  MATH  Google Scholar 

  12. Liu, H., Liu, R., Liao, X., Jin, H., He, B., Zhang, Y.: Object-level memory allocation and migration in hybrid memory systems. IEEE Trans. Comput. 69(9), 1401–1413 (2020)

    Article  MATH  Google Scholar 

  13. Long, X., Gong, X., Zhou, H.: Deep Learning based Data Prefetching in CPU-GPU Unified Virtual Memory, March 2022

    Google Scholar 

  14. Lowe-Power, J., et al.: The gem5 Simulator: Version 20.0+. arXiv:2007.03152, September 2020

  15. Mittal, S., Vetter, J.S.: A survey of software techniques for using non-volatile memories for storage and main memory systems. IEEE Trans. Parallel Distrib. Syst. 27(5), 1537–1550 (2016)

    Article  Google Scholar 

  16. Pei, S., Ji, Y., Shen, T., Liu, H.: Migration mechanism of heterogeneous memory pages using a two-way Hash chain list. SCIENTIA SINICA Inform. 49(9), 1138–1158 (2019)

    Article  Google Scholar 

  17. Pei, S., Qian, Y., Ye, X., Liu, H., Kong, L.: DRAM-based victim cache for page migration mechanism on heterogeneous main memory. J. Comput. Res. Develop. 3, 568–581 (2022)

    Google Scholar 

  18. Raoux, S., Xiong, F., Wuttig, M., Pop, E.: Phase change materials and phase change memory. MRS Bull. 39(8), 703–710 (2014)

    Article  Google Scholar 

  19. Tan, Y., Wang, B., Yan, Z., Srisa-an, W., Chen, X., Liu, D.: APMigration: improving performance of hybrid memory performance via an adaptive page migration method. IEEE Trans. Parallel Distrib. Syst. 31(2), 266–278 (2020)

    Article  Google Scholar 

  20. Valad Beigi, M., Pourshirazi, B., Memik, G., Zhu, Z.: DeepSwapper: a deep learning based page swap management scheme for hybrid memory systems. In: Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques, pp. 353–354. PACT 2020, Association for Computing Machinery, New York, NY, USA, September 2020

    Google Scholar 

  21. Vaswani, A., et al.: Attention Is All You Need, December 2017

    Google Scholar 

  22. Vetter, J.S., Mittal, S.: Opportunities for nonvolatile memory systems in extreme-scale high-performance computing. Comput. Sci. Eng. 17(2), 73–82 (2015)

    Article  Google Scholar 

  23. Wang, I.J., et al.: Enabling write-reduction multiversion scheme with efficient dual-range query over NVRAM. IEEE Trans. Very Large Scale Integr. (VLSI) Syst. 29(6), 1244–1256 (2021)

    Google Scholar 

  24. Zhang, P., Srivastava, A., Nori, A.V., Kannan, R., Prasanna, V.K.: Fine-grained address segmentation for attention-based variable-degree prefetching. In: Proceedings of the 19th ACM International Conference on Computing Frontiers, pp. 103–112. CF 2022, Association for Computing Machinery, New York, NY, USA, May 2022

    Google Scholar 

Download references

Acknowledgments

We would like to thank the anonymous reviewers for their invaluable comments. This work was partially funded by the National Natural Science Foundation of China under Grant 61975124, Shanghai Natural Science Foundation (20ZR1438500), State Key Laboratory of Computer Architecture (ICT, CAS) under Grant No. CARCHA202111, and Engineering Research Center of Software/Hardware Co-design Technology and Application, Ministry of Education East China Normal University under Grant No.OP202202. Any opinions, findings and conclusions expressed in this paper are those of the authors and do not necessarily reflect the views of the sponsors.

Author information

Authors and Affiliations

  1. University of Shanghai for Science and Technology, Shanghai, 200093, China

    Songwen Pei, Jianan Li & Yihuan Qian

  2. State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, 100190, China

    Songwen Pei

  3. South China University of Technology, Guangzhou, 510641, China

    Jie Tang

  4. University of California, Irvine, CA, 92617, USA

    Jean-Luc Gaudiot

Authors
  1. Songwen Pei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yihuan Qian
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jie Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jean-Luc Gaudiot
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Songwen Pei .

Editor information

Editors and Affiliations

  1. PerceptIn, Inc., Fremont, CA, USA

    Shaoshan Liu

  2. Jilin University, Changchun, China

    Xiaohui Wei

Rights and permissions

Reprints and permissions

Copyright information

© 2022 IFIP International Federation for Information Processing

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Pei, S., Li, J., Qian, Y., Tang, J., Gaudiot, JL. (2022). TransMigrator: A Transformer-Based Predictive Page Migration Mechanism for Heterogeneous Memory. In: Liu, S., Wei, X. (eds) Network and Parallel Computing. NPC 2022. Lecture Notes in Computer Science, vol 13615. Springer, Cham. https://doi.org/10.1007/978-3-031-21395-3_17

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-21395-3_17

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-21394-6

  • Online ISBN: 978-3-031-21395-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation