DOI QR코드

DOI QR Code

Considering Read and Write Characteristics of Page Access Separately for Efficient Memory Management

  • Hyokyung, Bahn (Department of Computer Engineering, Ewha University)
  • Received : 2023.01.05
  • Accepted : 2023.01.11
  • Published : 2023.03.31

Abstract

With the recent proliferation of memory-intensive workloads such as deep learning, analyzing memory access characteristics for efficient memory management is becoming increasingly important. Since read and write operations in memory access have different characteristics, an efficient memory management policy should take into accountthe characteristics of thesetwo operationsseparately. Although some previous studies have considered the different characteristics of reads and writes, they require a modified hardware architecture supporting read bits and write bits. Unlike previous approaches, we propose a software-based management policy under the existing memory architecture for considering read/write characteristics. The proposed policy logically partitions memory space into the read/write area and the write area by making use of reference bits and dirty bits provided in modern paging systems. Simulation experiments with memory access traces show that our approach performs better than the CLOCK algorithm by 23% on average, and the effect is similar to the previous policy with hardware support.

Keywords

Acknowledgement

This work was partly supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2019R1A2C1009275) and the Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No.2021-0-02068, Artificial Intelligence Innovation Hub).

References

  1. S. Dargan, M. Kumar, M.R. Ayyagari and G. Kumar, "A survey of deep learning and its applications: a new paradigm to machine learning," Archives of Computational Methods in Engineering, vol. 27, no. 1, pp. 1071 -1092, 2020. DOI: https://doi.org/10.1109/TC.2013.98
  2. S. Lee, H. Bahn, and S. H. Noh, ''CLOCK-DWF: A write-history-aware page replacement algorithm for hybrid PCM and DRAM memory architectures,'' IEEE Trans. Computers, vol. 63, no. 9, pp. 2187 -2200, 2014. DOI: https://doi.org/10.1109/TC.2013.98
  3. H. Lee and H. Bahn, "Characterizing virtua l memory write references for efficient page replacement in NAND flash memory," Proc. IEEE MASCOTS Conf., pp.1-10, 2009. DOI: https://doi.org/10.1109/MASCOT.2009.5366768
  4. F. J. Corbato, "A paging experiment with the Multics system," In Honor of Philip M. Mo rse, 1st ed., Cambridge, MA, USA, The MIT Press, pp. 217-228, 1969.
  5. S. Lee and H. Bahn, "Characterization of Android memory references and implication to hybrid memory management," IEEE Access, vol. 9, pp. 60997-61009, 2021. DOI: https://doi.org/10.1109/ACCESS.2021.3074179
  6. J. Yue and Y. Zhu, "Accelerating write by exploiting PCM asymmetries," Proc. IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 282-293, 2013. DOI: https://doi.org/10.1109/HPCA.2013.6522326
  7. S. Yoo, Y. Jo, and H. Bahn, "Integrated scheduling of real-time and interactive tasks for configurable industrial systems," IEEE Trans. Industrial Informatics, vol. 18, no. 1, pp. 631-641, 2022. DOI: https://doi.org/10.1109/TII.2021.3067714
  8. S. Yoon, H. Park, K. Cho, and H. Bahn, "Supporting swap in real-time task scheduling for unified power-saving in CPU and memory," IEEE Access, vol. 10, pp. 3559-3570, 2022. DOI: https://doi.org/10.1109/ACCESS.2021.3140166
  9. J. Park, H. Lee, S. Hyun, K. Koh, and H. Bahn, "A cost-aware page replacement algorithm for NAND flash based mobile embedded systems," Proc. ACM EMSOFT Conf., pp. 315-324, 2009. DOI: https://doi.org/10.1145/1629335.1629377
  10. E. Coffman and P. Denning, Operating Systems Theory, Prentice-Hall, pp. 241-283, 1973.
  11. H. Bahn, S. Noh, S. Min, and K. Koh, "Efficient replacement of nonuniform objects in web caches," Computer, vol.35, no.6, pp.65-73, 2002. DOI: https://doi.org/10.1109/MC.2002.1009170
  12. O. Kwon, H. Bahn, and K. Koh, "Popularity and prefix aware interval caching for multimedia streaming servers," Proc. IEEE Conf. on Computer and Information Technology, pp. 555-560, 2008. DOI: https://doi.org/10.1109/CIT.2008.4594735
  13. Memory access traces, https://github.com/oslab-ewha/memtrace