Periodic learning-based region selection for energy-efficient MLC STT-RAM cache

  • Fanfan ShenEmail author
  • Yanxiang He
  • Jun Zhang
  • Chao Xu


The emerging multi-level cell (MLC) spin-transfer torque RAM (STT-RAM) is becoming one of the most promising candidates to replace SRAM as on-chip last-level caches. Compared with single-level cell (SLC) STT-RAM design, MLC cache outperforms SLC cache in terms of storage capacity. However, due to the cell design constrains, MLC STT-RAM suffers from considerably long write latency and high write energy. To explore the potential benefits of MLC STT-RAM cache, this paper proposes a scheme named periodic learning-based region selection (PLRS). We first formulate the region selection problem with greedy algorithm and then profile and collect the cache access behavior through periodic learning. Finally, PLRS will determine region selection based on the behavior information. The experimental results show that PLRS reduces dynamic energy consumption by 22.7% and reduces execution time by 16.2% on average compared to conventional MLC STT-RAM, with negligible overhead.


Periodic learning Region selection Multi-level cell Spin-transfer torque RAM (STT-RAM) 



The authors would like to thank the anonymous referees for their valuable feedback and improvements to this paper. This work is supported by Natural Science Foundation of Jiangsu Province (BK20180821); Natural Science Foundation of the Higher Education Institutions of Jiangsu Province (18KJB520026, 16KJA520002); Key Research Topics of Jiangsu Education Science 13th Five-Year plan (C-a/2018/01/09); Collaborative Innovation Center of Audit Information Engineering and Technology (18CICA11); Talent Introduction Project of Nanjing Audit University; National Natural Science Foundation of China (61662002); Humanity and Social Science Foundation of Ministry of Education (19A11287009).


  1. 1.
    Hameed F, Khan AA, Castrillon J (2018) Performance and energy-efficient design of STT-RAM last-level cache. IEEE Trans Very Large Scale Integr Syst PP(99):1–14Google Scholar
  2. 2.
    Park J, Yim YU (2018) Two-phase read strategy for low energy variation-tolerant STT-RAM. IEEE Trans Very Large Scale Integr Syst 26(12):2584–2590CrossRefGoogle Scholar
  3. 3.
    Kuan K, Adegbija T (2018) LARS: logically adaptable retention time STT-RAM cache for embedded systems. In: 2018 Design, Automation Test in Europe Conference Exhibition (DATE), pp 461–466Google Scholar
  4. 4.
    Nasri A, Fathy M, Broumandnia A (2018) An energy-efficient 3D-stacked STT-RAM cache architecture for cloud processors: the effect on emerging scale-out workloads. J Supercomput 74(4):1547–1561CrossRefGoogle Scholar
  5. 5.
    Sayed N, Bishnoi R, Oboril F, Tahoori MB (2018) A cross-layer adaptive approach for performance and power optimization in STT-MRAM. In: 2018 Design, Automation Test in Europe Conference Exhibition (DATE), pp 791–796Google Scholar
  6. 6.
    Luo H, Hu J, Shi L, Xue CJ, Zhuge Q (2016) Two-step state transition minimization for lifetime and performance improvement on MLC STT-RAM. In: Proceedings of the 53rd Annual Design Automation Conference, pp 171:1–171:6Google Scholar
  7. 7.
    Wen W, Zhang Y, Mao M, Chen Y (2014) State-restrict MLC STT-RAM designs for high-reliable high-performance memory system. In: Proceedings of the 51st Annual Design Automation Conference, pp 35:1–35:6Google Scholar
  8. 8.
    Zhang Y, Zhang L, Wen W, Sun G, Chen Y (2012) Multi-level cell STT-RAM: is it realistic or just a dream? In: Proceedings of the International Conference on Computer-Aided Design, pp 526–532Google Scholar
  9. 9.
    Bi X, Mao M, Wang D, Li H (2013) Unleashing the potential of MLC STT-RAM caches. In: Proceedings of the International Conference on Computer-Aided Design, pp 429–436Google Scholar
  10. 10.
    Hong S, Lee J, Kim S (2014) Ternary cache: three-valued MLC STT-RAM caches. In: 2014 IEEE 32nd International Conference on Computer Design (ICCD), pp 83–89Google Scholar
  11. 11.
    Chen X, Khoshavi N, Zhou J, Huang D, DeMara R et al (2016) AOS: adaptive overwrite scheme for energy-efficient MLC STT-RAM cache. In: Proceedings of the 53rd Annual Design Automation Conference, pp 170:1–170:6Google Scholar
  12. 12.
    Chen Y, Wong W, Li H, Koh C, Zhang Y, Wen W (2013) On-chip caches built on multilevel spin-transfer torque ram cells and its optimizations. ACM J Emerg Technol Comput Syst (JETC) 9(2):16:1–16:22Google Scholar
  13. 13.
    Chen Y, Wang X, Zhu W, Li H, Sun Z, Sun G, Xie Y (2010) Access scheme of multi-level cell spin-transfer torque random access memory and its optimization. In: 2010 53rd IEEE International Midwest Symposium on Circuits and Systems, pp 1109–1112Google Scholar
  14. 14.
    Wang J, Roy P, Wong WF, Bi X, Li H (2014) Optimizing MLC-based STT-RAM caches by dynamic block size reconfiguration. In: 2014 IEEE 32nd International Conference on Computer Design (ICCD), pp 133–138Google Scholar
  15. 15.
    Jiang L, Zhao B, Zhang Y, Yang J (2012) Constructing large and fast multi-level cell STT-MRAM based cache for embedded processors. In: Proceedings of the 49th Annual Design Automation Conference, pp 907–912Google Scholar
  16. 16.
    Sampaio F, Shafique M, Zatt B, Bampi S, Henkel J (2015) Approximation-aware multi-level cells STT-RAM cache architecture. In: Proceedings of the 2015 International Conference on Compilers, Architecture and Synthesis for Embedded Systems, pp 79–88Google Scholar
  17. 17.
    Chen Y, Wong WF, Li H, Koh CK (2011) Processor caches built using multi-level spin-transfer torque ram cells. In: IEEE/ACM International Symposium on Low Power Electronics and Design, pp 73–78Google Scholar
  18. 18.
    Khan SM, Tian Y, Jimenez DA (2010) Sampling dead block prediction for last-level caches. In: 2010 43rd Annual IEEE/ACM International Symposium on Microarchitecture, pp 175–186Google Scholar
  19. 19.
    Binkert N, Beckmann B, Black G, Reinhardt SK, Saidi A et al (2011) The gem5 simulator. SIGARCH Comput Archit News 39(2):1–7CrossRefGoogle Scholar
  20. 20.
    Muralimanohar N, Balasubramonian R, Jouppi N (2007) Optimizing NUCA organizations and wiring alternatives for large caches with CACTI 6.0. In: Proceedings of the 40th Annual IEEE/ACM International Symposium on Microarchitecture, pp 3–14Google Scholar
  21. 21.
    Dong X, Xu C, Jouppi N, Xie Y (2014) Nvsim: a circuit-level performance, energy, and area model for emerging non-volatile memory. In: Emerging memory technologies, pp 15–50Google Scholar
  22. 22.
    Bienia C, Kumar S, Singh JP, Li K (2008) The parsec benchmark suite: characterization and architectural implications. In: Proceedings of the International Conference on Parallel Architecture and Compilation Techniques, pp 72–81Google Scholar
  23. 23.
    Yin S, Lu T, Xie Z, Liu L, Wei S (2018) Bit-level disturbance-aware memory partitioning for parallel data access for MLC STT-RAM. IEEE Trans Very Large Scale Integr Syst 26(11):2345–2357CrossRefGoogle Scholar
  24. 24.
    Liu Z, Mao M, Liu T, Wang X, Wen W, Chen Y, Li H, Wang D, Pei Y, Ge N (2018) Trizone: a design of MLC STT-RAM cache for combined performance, energy, and reliability optimizations. IEEE Trans Comput Aided Des Integr Circuits Syst 37(10):1985–1998CrossRefGoogle Scholar
  25. 25.
    Jadidi A, Arjomand M, Kandemir M, Das C (2018) Performance and power-efficient design of dense non-volatile cache in CMPS. IEEE Trans Comput 67(7):1054–1061MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Information EngineeringNanjing Audit UniversityNanjingChina
  2. 2.Computer SchoolWuhan UniversityWuhanChina
  3. 3.School of SoftwareEast China University of TechnologyNanchangChina

Personalised recommendations