Abstract
Nonvolatile memory is a promising candidate to replace CMOS devices with the two most common magnetoresistive RAM (MRAM) cell types being spin-transfer torque (STT-)MRAM and spin-orbit torque (SOT-)MRAM. Recently introduced combinations of these two mechanisms allow the amelioration of MRAM performance.
To optimize the switching, we implemented an approach based on reinforcement learning. In particular, we train an agent to switch an SOT-assisted STT-MRAM cell by applying STT or SOT current pulses independently. During this process, by means of rewards based on its actions, the agent is encouraged to either reverse the magnetization in the memory cell fast or by using little energy. After successfully training RL agents under the given constraints, the results of the two rewarding schemes applied to SOT-assisted STT-MRAM are discussed.
The financial support by the Federal Ministry of Labour and Economy, the National Foundation for Research, Technology and Development and the Christian Doppler Research Association is gratefully acknowledged.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Ender, J., de Orio, R.L., Fiorentini, S., Selberherr, S., Goes, W., Sverdlov, V.: Reinforcement learning approach for deterministic SOT-MRAM switching. In: Spintronics XIV, vol. 11805, pp. 56–63. SPIE (2021)
Ender, J., de Orio, R.L., Fiorentini, S., Selberherr, S., Goes, W., Sverdlov, V.: Reinforcement learning to reduce failures in SOT-MRAM switching. Microelectron. Reliab. 135, 114570 (2022)
Fösel, T., Tighineanu, P., Weiss, T., Marquardt, F.: Reinforcement learning with neural networks for quantum feedback. Phys. Rev. X 8(3), 031084 (2018)
Makarov, A.: Modeling of Emerging Resistive Switching Based Memory Cells. Ph.D. thesis, Institut für Mikroelektronik (2014). https://doi.org/10.34726/hss.2014.23875, http://www.iue.tuwien.ac.at/phd/makarov/
Meo, A., Chureemart, J., Chantrell, R.W., Chureemart, P.: Magnetisation switching dynamics induced by combination of spin transfer torque and spin orbit torque. Sci. Rep. 12(1), 3380 (2022)
Mnih, V., et al.: Playing atari with deep reinforcement learning. CoRR abs/1312.5602 (2013). http://arxiv.org/abs/1312.5602
Orio, R., Ender, J., Fiorentini, S., Goes, W., Selberherr, S., Sverdlov, V.: Optimization of a spin-orbit torque switching scheme based on micromagnetic simulations and reinforcement learning. Micromachines 12(4), 443 (2021). https://doi.org/10.3390/mi12040443, https://www.iue.tuwien.ac.at/pdf/ib_2021/JB2021_Orio_2.pdf
Orio, R., Ender, J., Goes, W., Fiorentini, S., Selberherr, S., Sverdlov, V.: About the switching energy of a magnetic tunnel junction determined by spin-orbit torque and voltage-controlled magnetic anisotropy. In: 2022 IEEE Latin American Electron Devices Conference (LAEDC), pp. 1–4 (2022). https://doi.org/10.1109/LAEDC54796.2022.9908222, talk: 2022 IEEE Latin American Electron Devices Conference (LAEDC), Puebla, Mexico; 2022-06-04 – 2022-06-06, 978-1-6654-9768-8
Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1–8 (2021). http://jmlr.org/papers/v22/20-1364.html
Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362(6419), 1140–1144 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ender, J., de Orio, R.L., Gös, W., Sverdlov, V. (2024). Towards Efficient SOT-Assisted STT-MRAM Cell Switching Using Reinforcement Learning. In: Lirkov, I., Margenov, S. (eds) Large-Scale Scientific Computations. LSSC 2023. Lecture Notes in Computer Science, vol 13952. Springer, Cham. https://doi.org/10.1007/978-3-031-56208-2_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-56208-2_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-56207-5
Online ISBN: 978-3-031-56208-2
eBook Packages: Computer ScienceComputer Science (R0)