Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Enabling Normally-off In-Situ Computing with a Magneto-Electric FET-based SRAM Design (2312.05212v1)

Published 8 Dec 2023 in cs.AR

Abstract: As an emerging post-CMOS Field Effect Transistor, Magneto-Electric FETs (MEFETs) offer compelling design characteristics for logic and memory applications, such as high-speed switching, low power consumption, and non-volatility. In this paper, for the first time, a non-volatile MEFET-based SRAM design named ME-SRAM is proposed for edge applications which can remarkably save the SRAM static power consumption in the idle state through a fast backup-restore process. To enable normally-off in-situ computing, the ME-SRAM cell is integrated into a novel processing-in-SRAM architecture that exploits a hardware-optimized bit-line computing approach for the execution of Boolean logic operations between operands housed in a memory sub-array within a single clock cycle. Our device-to-architecture evaluation results on Binary convolutional neural network acceleration show the robust performance of ME- SRAM while reducing energy consumption on average by a factor of 5.3 times compared to the best in-SRAM designs.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (28)
  1. M. K. Q. Jooq, M. H. Moaiyeri, and K. Tamersit, “A new design paradigm for auto-nonvolatile ternary srams using ferroelectric cntfets: From device to array architecture,” IEEE TED, vol. 69, pp. 6113–6120, 2022, doi: 10.1109/TED.2022.3207703.
  2. M. Morsali, S. Tabrizchi, A. Marshall, A. Roohi, D. Misra, and S. Angizi, “Design and evaluation of a near-sensor magneto-electric fet-based event detector,” IEEE TED, 2023, doi: 10.1109/TED.2023.3296389.
  3. S. Angizi, S. Tabrizchi, D. Z. Pan, and A. Roohi, “Pisa: A non-volatile processing-in-sensor accelerator for imaging systems,” IEEE Transactions on Emerging Topics in Computing, 2023.
  4. P. Dowben, D. Nikonov, A. Marshall, and C. Binek, “Magneto-electric antiferromagnetic spin–orbit logic devices,” Applied Physics Letters, vol. 116, no. 8, p. 080502, 2020, doi: 10.1063/1.5141371.
  5. C. Ma, Y. Wang, Z. Shen, R. Chen, Z. Wang, and Z. Shao, “Mnftl: An efficient flash translation layer for mlc nand flash memory,” ACM TODAES, vol. 25, pp. 1–19, 2020, doi: 10.1145/3398037.
  6. P. A. Dowben, C. Binek, K. Zhang, L. Wang, W.-N. Mei, J. P. Bird, U. Singisetti, X. Hong, K. L. Wang, and D. Nikonov, “Towards a strong spin–orbit coupling magnetoelectric transistor,” IEEE JxCDC, vol. 4, no. 1, pp. 1–9, 2018, doi: 10.1109/JXCDC.2018.2809640.
  7. Y. Pan, P. Ouyang, Y. Zhao, W. Kang, S. Yin, Y. Zhang, W. Zhao, and S. Wei, “A multilevel cell stt-mram-based computing in-memory accelerator for binary convolutional neural network,” IEEE TMAG, no. 99, pp. 1–5, 2018, doi: 10.1109/TMAG.2018.2848625.
  8. X. Fong, Y. Kim, K. Yogendra, D. Fan, A. Sengupta, A. Raghunathan, and K. Roy, “Spin-transfer torque devices for logic and memory: Prospects and perspectives,” IEEE TCAD, vol. 35, no. 1, pp. 1–22, 2015, doi: 10.1109/TCAD.2015.2481793.
  9. D. E. Nikonov and I. A. Young, “Benchmarking of beyond-cmos exploratory devices for logic integrated circuits,” IEEE JxCDC, vol. 1, pp. 3–11, 2015, doi: 10.1109/JXCDC.2015.2418033.
  10. S. Angizi, Z. He, F. Parveen, and D. Fan, “Imce: Energy-efficient bit-wise in-memory convolution engine for deep neural network,” in 2018 23rd Asia and South Pacific Design Automation Conference (ASP-DAC).   IEEE, 2018, pp. 111–116.
  11. S. Angizi, Z. He, A. S. Rakin, and D. Fan, “Cmp-pim: an energy-efficient comparator-based processing-in-memory neural network accelerator,” in Proceedings of the 55th Annual Design Automation Conference, 2018, pp. 1–6.
  12. M. Abedin, A. Roohi, M. Liehr, N. Cady, and S. Angizi, “Mr-pipa: An integrated multilevel rram (hfo x)-based processing-in-pixel accelerator,” IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, vol. 8, no. 2, pp. 59–67, 2022.
  13. N. Sharma, C. Binek, A. Marshall, J. Bird, P. Dowben, and D. Nikonov, “Compact modeling and design of magneto-electric transistor devices and circuits,” in IEEE SOCC.   IEEE, 2018, pp. 146–151, doi: 10.1109/SOCC.2018.8618494.
  14. A. Mahmood, W. Echtenkamp, M. Street, J.-L. Wang, S. Cao, T. Komesu, P. A. Dowben, P. Buragohain, H. Lu, A. Gruverman, A. Parthasarathy, S. Rakheja, and C. Binek, “Voltage controlled néel vector rotation in zero magnetic field,” Nature communications, vol. 12, no. 1, pp. 1–8, 2021, doi: 10.1038/s41467-021-21872-3.
  15. H.-J. Chuang, B. Chamlagain, M. Koehler, M. M. Perera, J. Yan, D. Mandrus, D. Tomanek, and Z. Zhou, “Low-resistance 2d/2d ohmic contacts: a universal approach to high-performance wse2, mos2, and mose2 transistors,” Nano letters, vol. 16, no. 3, pp. 1896–1902, 2016, doi: 10.1021/acs.nanolett.5b05066.
  16. M. Anantram, M. S. Lundstrom, and D. E. Nikonov, “Modeling of nanoscale devices,” Proceedings of the IEEE, vol. 96, no. 9, pp. 1511–1550, 2008, doi: 10.1109/JPROC.2008.927355.
  17. A. Iyama and T. Kimura, “Magnetoelectric hysteresis loops in cr 2 o 3 at room temperature,” Physical Review B, vol. 87, no. 18, p. 180408, 2013, doi: 10.1103/PhysRevB.87.180408.
  18. N. Sharma, A. Marshall, J. Bird, and P. Dowben, “Verilog-a based compact modeling of the magneto-electric fet device,” in E3S.   IEEE, 2017, pp. 1–3, doi: 10.1109/E3S.2017.8246186.
  19. X. Fong, S. K. Gupta, N. N. Mojumder, S. H. Choday, C. Augustine, and K. Roy, “Knack: A hybrid spin-charge mixed-mode simulator for evaluating different genres of spin-transfer torque mram bit-cells,” in IEEE SISPAD.   IEEE, 2011, pp. 51–54, doi: 10.1109/SISPAD.2011.6035047.
  20. X. Dong, C. Xu, Y. Xie, and N. P. Jouppi, “Nvsim: A circuit-level performance, energy, and area model for emerging nonvolatile memory,” IEEE TCAD, vol. 31, pp. 994–1007, 2012, doi: 10.1109/TCAD.2012.2185930.
  21. K. Ali, F. Li, S. Y. Lua, and C.-H. Heng, “Energy efficient reduced area overhead spin-orbit torque non-volatile srams,” pp. 2275–2280, 2020, doi: 10.1109/IECON43393.2020.9254623.
  22. C. Wang, D. Zhang, K. Zhang, L. Zeng, Y. Wang, Z. Hou, Y. Zhang, and W. Zhao, “Magnetic nonvolatile sram based on voltage-gated spin-orbit-torque magnetic tunnel junctions,” IEEE TED, vol. 67, no. 5, pp. 1965–1971, 2020, doi: 10.1109/TED.2020.2982683.
  23. S. Tripathi, S. Choudhary, and P. K. Misra, “A novel stt–sot mtj-based nonvolatile sram for power gating applications,” IEEE TED, vol. 69, no. 3, pp. 1058–1064, 2022, doi: 10.1109/TED.2022.3140407.
  24. A. Agrawal, A. Jaiswal, C. Lee, and K. Roy, “X-sram: Enabling in-memory boolean computations in cmos static random access memories,” IEEE TCASI, vol. 65, no. 12, pp. 4219–4232, 2018, doi: 10.1109/TCSI.2018.2848999.
  25. S. Aga, S. Jeloka, A. Subramaniyan, S. Narayanasamy, D. Blaauw, and R. Das, “Compute caches,” in HPCA.   IEEE, 2017, pp. 481–492, doi: 10.1109/HPCA.2017.21.
  26. J. Wang, X. Wang, C. Eckert, A. Subramaniyan, R. Das, D. Blaauw, and D. Sylvester, “A 28-nm compute sram with bit-serial logic/arithmetic operations for programmable in-memory vector computing,” IEEE JSSC, vol. 55, no. 1, pp. 76–86, 2019, doi: 10.1109/JSSC.2019.2939682.
  27. Q. Dong, S. Jeloka, M. Saligane, Y. Kim, M. Kawaminami, A. Harada, S. Miyoshi, M. Yasuda, D. Blaauw, and D. Sylvester, “A 4 + 2t sram for searching and in-memory computing with 0.3-v vddminsubscript𝑣ddminv_{\mathrm{ddmin}}italic_v start_POSTSUBSCRIPT roman_ddmin end_POSTSUBSCRIPT,” IEEE JSSC, vol. 53, no. 4, pp. 1006–1015, 2017, doi: 10.1109/JSSC.2017.2776309.
  28. S. Angizi, M. Morsali, S. Tabrizchi, and A. Roohi, “A near-sensor processing accelerator for approximate local binary pattern networks,” IEEE TETC, 2023, doi: 10.1109/TED.2023.3296389.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now