Machine Learning-Driven Design Optimization of CNFET-Based SRAM Cells

Authors

https://doi.org/10.48314/apem.v1i1.27

Abstract

The rapid evolution of nanotechnology has positioned Carbon Nanotube Field-Effect Transistors (CNFETs) as a promising alternative to traditional Metal-Oxide-Semiconductor Field-Effect Transistors (MOSFETs) in the design of low-power, high-performance Static Random-Access Memory (SRAM) cells. However, optimizing the design of CNFET-based SRAM cells to meet stringent requirements, such as stability, power efficiency, and scalability, remains a significant challenge. In this paper, we explore the potential of Machine Learning (ML) algorithms to address these challenges by leveraging their capabilities in complex design optimization tasks. This paper comprehensively reviews various ML models, including supervised, unsupervised, reinforcement, and deep learning. It examines their application in optimizing key performance metrics of CNFET-based SRAM cells. Mathematical models and formulas for design optimization are presented alongside case studies demonstrating ML techniques’ effectiveness in improving SRAM stability and reducing power consumption. Finally, we discuss the challenges of integrating ML into circuit design workflows and propose future research directions, highlighting the transformative potential of ML in shaping the future of CNFET-based SRAM design.

Keywords:

Carbon nanotube field-effect transistor-based static random-access memory, Machine learning optimization, Design automation, Low-power circuits, Circuit stability, Deep learning in circuit design, Electronic design automation

References

  1. [1] Kavitha, S., Kumar, C., Fayek, H. H., & Rusu, E. (2023). Design and implementation of CNFET SRAM cells by using multi-threshold technique. Electronics, 12(7), 1–23. https://doi.org/10.3390/electronics12071611
  2. [2] Gadgil, S., Sandesh, G. N., & Vudadha, C. (2023). Power efficient designs of CNTFET-based ternary SRAM. Microelectronics journal, 139, 105884. https://doi.org/10.1016/j.mejo.2023.105884
  3. [3] Parvizi, M., & Zanjani, S. M. A. (2020). An efficient, current-mode full-adder based on majority logic in CNFET technology. 2020 10th international conference on computer and knowledge engineering (ICCKE) (pp. 301–305). IEEE. http://dx.doi.org/10.1109/ICCKE50421.2020.9303623
  4. [4] Chen, R., Chen, L., Liang, J., Cheng, Y., Elloumi, S., Lee, J., … & Todri-Sanial, A. (2022). Carbon nanotube SRAM in 5-nm technology node design, optimization, and performance evaluation—Part I: CNFET transistor optimization. IEEE transactions on very large scale integration (VLSI) systems, 30(4), 432–439. https://doi.org/10.1109/TVLSI.2022.3146125
  5. [5] Mohammed, M. U. (2019). Novel high performance ultra low power static random access memories (SRAMs) based on next generation technologies [Thesis].
  6. [6] Patel, P. K., Malik, M. M., & Gupta, T. K. (2020). A novel high-density dual threshold GNRFET SRAM design with improved stability. Microprocessors and microsystems, 73, 102956. https://doi.org/10.1016/j.micpro.2019.102956
  7. [7] Valluria, A., & Musala, S. (2022). Comparative analysis of CNTFET based SRAM cells. ECS transactions, 107(1), 19177. https://doi.org/10.1149/10701.19177ecst
  8. [8] Sajjadi, S. A., Sadrossadat, S. A., Moftakharzadeh, A., Nabavi, M., & Sawan, M. (2024). Yield maximization of flip-flop circuits based on deep neural network and polyhedral estimation of nonlinear constraints. IEEE access, 12, 113944–113959. https://doi.org/10.1109/ACCESS.2024.3443343
  9. [9] Zahoor, F., Jaber, R. A., Isyaku, U. B., Sharma, T., Bashir, F., Abbas, H., … & Hanif, M. (2024). Design implementations of ternary logic systems: A critical review. Results in engineering, 23, 102761. https://doi.org/10.1016/j.rineng.2024.102761
  10. [10] Alekhya, Y., & Nanda, U. (2022). Investigation of CNTFET based energy efficient fast SRAM cells for edge AI devices. Silicon, 14(14), 8815–8830. https://doi.org/10.1007/s12633-021-01589-0
  11. [11] Tabrizchi, S., Angizi, S., & Roohi, A. (2022). Design and evaluation of a robust power-efficient ternary sram cell. 2022 IEEE 65th international midwest symposium on circuits and systems (MWSCAS) (pp. 1–4). IEEE. https://doi.org/10.1109/MWSCAS54063.2022.9859306
  12. [12] Zhang, A. Q., Tosson, A. M. S., Ma, D., Fang, R., & Wei, L. (2023). Stuck-at faults tolerance and recovery in MLP neural networks using imperfect emerging CNFET technology. IEEE journal on exploratory solid-state computational devices and circuits, 9(2), 168–175. https://doi.org/10.1109/JXCDC.2023.3313127
  13. [13] Kim, Y. B. (2023). A Novel CNFET SRAM-based computing-in-memory design and low power techniques for AI accelerator. https://www.proquest.com/openview/ccaa11e388b9d59e7e674e1a7848cd88/1?pq-origsite=gscholar&cbl=18750&diss=y
  14. [14] Birla, S., Dargar, S. K., Singh, N., & Sivakumar, P. (2023). Low power designs in nanodevices and circuits for emerging applications. CRC Press. https://doi.org/10.1201/9781003459231
  15. [15] Zhang, A. Q. (2021). Struck-at fault tolerance with emerging technology RAM in the neurosim MLP neural network system [Thesis]. http://hdl.handle.net/10012/17391
  16. [16] Islam, A., & Hasan, M. (2011). Power optimized variation aware dual-threshold SRAM cell design technique. Nanotechnology, science and applications, 4, 25–33. https://doi.org/10.2147/NSA.S15719
  17. [17] Kenarangi, F., & Partin-Vaisband, I. (2021). A single-MOSFET analog high resolution-targeted (SMART) multiplier for machine learning classification. IEEE journal on emerging and selected topics in circuits and systems, 11(4), 816–828. https://doi.org/10.1109/JETCAS.2021.3124940
  18. [18] Yin, S., Kim, Y., Han, X., Barnaby, H., Yu, S., Luo, Y., … & Seo, J. (2019). Monolithically integrated RRAM-and CMOS-based in-memory computing optimizations for efficient deep learning. IEEE micro, 39(6), 54–63. https://doi.org/10.1109/MM.2019.2943047
  19. [19] Kenarangi, F., Hu, X., Liu, Y., Incorvia, J. A. C., Friedman, J. S., & Partin-Vaisband, I. (2020). Exploiting dual-gate ambipolar CNFETs for scalable machine learning classification. Scientific reports, 10(1), 5735. https://doi.org/10.1038/s41598-020-62718-0
  20. [20] Pal, S., Bose, S., Ki, W. H., & Islam, A. (2020). A highly stable reliable SRAM cell design for low power applications. Microelectronics reliability, 105, 113503. https://doi.org/10.1016/j.microrel.2019.113503
  21. [21] Prakash, P., Sundaram, K. M., & Bennet, M. A. (2018). A review on carbon nanotube field effect transistors (CNTFETs) for ultra-low power applications. Renewable and sustainable energy reviews, 89, 194–203. https://doi.org/10.1016/j.rser.2018.03.021
  22. [22] Cho, G., Kim, Y. B., Lombardi, F., & Choi, M. (2009). Performance evaluation of CNFET-based logic gates. 2009 IEEE instrumentation and measurement technology conference (pp. 909–912). IEEE. https://doi.org/10.1109/IMTC.2009.5168580
  23. [23] Hailiang, Z., Yue, H., & Minxuan, Z. (2010). Numerical study of the sub-threshold slope in T-CNFETs. Journal of semiconductors, 31(9), 94005. https://doi.org/10.1088/1674-4926/31/9/094005
  24. [24] Sankar, P. A. G., & Udhayakumar, K. (2014). MOSFET-like CNFET based logic gate library for low-power application: A comparative study. Journal of semiconductors, 35(7), 75001. https://doi.org/10.1088/1674-4926/35/7/075001
  25. [25] Su, S. K., Sanchez-Soares, A., Chen, E., Kelly, T., Fagas, G., Greer, J. C., … & Radu, I. P. (2022). Impact of metal hybridization on contact resistance and leakage current of carbon nanotube transistors. IEEE electron device letters, 43(8), 1367–1370. https://doi.org/10.1109/LED.2022.3185991
  26. [26] Dixit, A., & Gupta, N. (2018). Analysis of different gate dielectric materials in carbon nanotube field effect transistor (CNFET) using optimization technique. 2018 IEEE electron devices kolkata conference (EDKCON) (pp. 354–357). IEEE. https://doi.org/10.1109/EDKCON.2018.8770503
  27. [27] Arif, S., & Pal, S. (2015). CNFET based 8-t sram cell to improve stability with reduced power consumption. 2015 international conference on advanced computing and communication systems (pp. 1–5). IEEE. https://doi.org/10.1109/ICACCS.2015.7324112
  28. [28] Madhavi, B. K., & Kishore, K. L. (2012). Low leakage-power sram cell design using CNTFETs at 32nm technology. International conference on advances in communication, network, and computing (pp. 165–171). Springer. https://doi.org/10.1007/978-3-642-35615-5_24
  29. [29] Zanjani, S. M., & Toghian, P. (2024). Design and simulation of a low-power, universal & multi-mode filter for the commercial FM band in 20-nm CNFETs. Analog integrated circuits and signal processing, 120(1), 9–20. https://doi.org/10.1007/s10470-024-02287-8
  30. [30] Srinivasan, V., Varshad Venkatraman, R., & Senthil kumar, K. K. (2013). Schmitt trigger based SRAM cell for ultralow power operation- A CNFET based approach. Procedia engineering, 64, 115–124. https://doi.org/10.1016/j.proeng.2013.09.082
  31. [31] Kureshi, A. K., & Hasan, M. (2009). Performance comparison of CNFET- and CMOS-based 6T SRAM cell in deep submicron. Microelectronics journal, 40(6), 979–982. https://doi.org/10.1016/j.mejo.2008.11.062
  32. [32] Arif, S., & Pal, S. (2015). Variation-resilient cnfet-based 8T sram cell for ultra-low-power application. 2015 international conference on signal processing and communication engineering systems (pp. 147–151). IEEE. https://doi.org/10.1109/SPACES.2015.7058235
  33. [33] Kanhaiya, P. S., Lau, C., Hills, G., Bishop, M. D., & Shulaker, M. M. (2019). Carbon nanotube-based CMOS SRAM: 1 kbit 6T SRAM arrays and 10T SRAM cells. IEEE transactions on electron devices, 66(12), 5375–5380. https://doi.org/10.1109/TED.2019.2945533
  34. [34] Soni, L., & Pandey, N. (2023). A novel CNTFET based schmitt-trigger read decoupled 12T SRAM cell with high speed, low power, and high Ion/Ioff ratio. AEU-international journal of electronics and communications, 167, 154669. https://doi.org/10.1016/j.aeue.2023.154669
  35. [35] Kim, Y., Patel, S., Kim, H., Yadav, N., & Choi, K. K. (2021). Ultra-low power and high-throughput SRAM design to enhance AI computing ability in autonomous vehicles. Electronics, 10(3), 1–22. https://doi.org/10.3390/electronics10030256
  36. [36] Aslam, M. F. (2024). An inverter based OTA with novel tunable pseudoresistor and its application in arrhythmia detection using machine learning algorithms. https://doi.org/10.21203/rs.3.rs-4957694/v1
  37. [37] Gupta, S. K. (2024). Special topic on physics-based modeling and simulation of materials, devices, and circuits of beyond-CMOS logic and memory technologies for energy-efficient computing. IEEE journal on exploratory solid-state computational devices and circuits, 9(2),1-3. https://doi.org/10.1109/JXCDC.2023.3340557
  38. [38] Singh, J., & Singh, D. (2024). Applications of AI/ML algorithms in VLSI design and technology. In Integrated devices for artificial intelligence and VLSI (pp. 157–191). Wiley Online Library. https://doi.org/10.1002/9781394205158.ch7
  39. [39] Maqbool, M., Sharma, V. K., & Kaushik, N. (2024). CNTFET-based SRAM cell design using INDEP technique. E-prime-advances in electrical engineering, electronics and energy, 7, 100477. https://doi.org/10.1016/j.prime.2024.100477
  40. [40] Elangovan, M., Sharma, K., Sachdeva, A., & Gupta, L. (2024). Read improved and low leakage power CNTFET based hybrid 10t SRAM cell for low power applications. Circuits, systems, and signal processing, 43(3), 1627–1660. https://doi.org/10.1007/s00034-023-02529-6
  41. [41] Marani, R., & Perri, A. G. (2024). A procedure to compare CNTFET and CMOS technologies through the design of a SRAM cell: A review. International journal of nanoscience and nanotechnology, 20(2), 113–127. https://doi.org/10.22034/ijnn.2024.2021428.2472
  42. [42] Chu, C., Xu, D., Wang, Y., & Chen, F. (2022). Canopy: A cnfet-based process variation aware systolic DNN accelerator. Proceedings of the acm/IEEE international symposium on low power electronics and design (pp. 1–6). IEEE. https://doi.org/10.1145/3531437.3539703
  43. [43] Sachdeva, A., Sharma, K., Bhargava, A., & Abbasian, E. (2024). A CNTFET based stable, single-ended 7T SRAM cell with improved write operation. Physica scripta, 99(3), 35011. https://doi.org/10.1088/1402-4896/ad24a8
  44. [44] Darabi, A., Salehi, M. R., & Abiri, E. (2023). Single-sided gate-wrap-around CNTFET SRAM cell for utilization in reliable IoT-based platforms. AEU-international journal of electronics and communications, 163, 154605. https://doi.org/10.1016/j.aeue.2023.154605
  45. [45] Sadeghi, A., Ghasemi, R., Ghasemian, H., & Shiri, N. (2023). Efficient and optimized approximate GDI full adders based on dynamic threshold CNTFETs for specific least significant bits. Frontiers of information technology & electronic engineering, 24(4), 599–616. https://doi.org/10.1631/FITEE.2200077
  46. [46] Darabi, A., Salehi, M. R., & Abiri, E. (2021). Newly energy-efficient SRAM bit-cell using GAA CNT-GDI method with asymmetrical write and built-in read-assist schemes for QR code-based multimedia applications. Microelectronics journal, 114, 105117. https://doi.org/10.1016/j.mejo.2021.105117
  47. [47] Sajjadi, S. A., Sadrossadat, S. A., Moftakharzadeh, A., Nabavi, M., & Sawan, M. (2024). DNN-Based optimization to significantly speed up and increase the accuracy of electronic circuit design. IEEE transactions on circuits and systems I: Regular papers, 71(3), 1273–1284. https://doi.org/10.1109/TCSI.2023.3347688
  48. [48] Raja, G. B., & Madheswaran, M. (2013). Design and analysis of 5-T SRAM cell in 32nm CMOS and CNTFET technologies. International journal of electronics and electrical engineering, 1(4), 256–261. https://doi.org/10.12720/ijeee.1.4.256-261
  49. [49] Yadav, A., & Wairya, S. (2021). Performance and area optimization of SRAM Cell in nanocomputing application. International journal of computing and digital system, 11(1), 1009–1026. http://dx.doi.org/10.12785/ijcds/110182
  50. [50] Gopinath, A., Cochran, Z., Ytterdal, T., & Rizkalla, M. (2022). SRAM design leveraging material properties of exploratory transistors. Materials today: Proceedings, 57, 368–374. https://doi.org/10.1016/j.matpr.2021.10.327
  51. [51] Arora, S., & Tripathi, S. L. (2024). A comprehensive analysis of ultra low power GNRFET based 20T hybrid full adder for computing applications. Physica scripta, 99(8), 85008. https://doi.org/10.1088/1402-4896/ad5c0b
  52. [52] Ghorbani, A., Dolatshahi, M., Zanjani, S. M., & Barekatain, B. (2022). A new low-power dynamic-GDI full adder in CNFET technology. Integration, 83, 46–59. https://doi.org/10.1016/j.vlsi.2021.12.001
  53. [53] Valdés, R. C., García, F., García, R. Z., López, A., & Hernández, N. (2023). Parameter extraction in thin film transistors using artificial neural networks. Journal of materials science: Materials in electronics, 34(6), 555. https://doi.org/10.1007/s10854-023-09953-z
  54. [54] Bhuvaneswari, T., & Kathirvelu, M. (2024). A comprehensive analysis on the intelligent VLSI systems design and applications. Indian journal of natural sciences, 15(83). 71174-71180. https://www.researchgate.net/publication/382335425
  55. [55] Ghorbani, A., Dolatshahi, M., Zanjani, S. M., & Barekatain, B. (2022). A new low power, area efficient 4-bit carry look ahead adder in CNFET technology. Majlesi journal of electrical engineering, 16(1), 1-9. https://oiccpress.com/mjee/article/view/4943
  56. [56] Chen, F., Song, L., Li, H., & Chen, Y. (2021). Marvel: A vertical resistive accelerator for low-power deep learning inference in monolithic 3D. 2021 design, automation & test in europe conference & exhibition (DATE) (pp. 1240–1245). IEEE. https://doi.org/10.23919/DATE51398.2021.9474208
  57. [57] Mahida, N., Parikh, K. A., Darji, K., Gupta, R., Tanwar, S., Shahinzadeh, H., & Mohammad-Hosseini, M. (2024). PneuTeleCNN: Deep learning-assisted framework for pneumonia identification in web-enabled telemedicine systems. 2024 10th international conference on web research (ICWR). IEEE. http://dx.doi.org/10.1109/ICWR61162.2024.10533369
  58. [58] Shahinzadeh, H., Mahmoudi, A., Asilian, A., Sadrarhami, H., Hemmati, M., & Saberi, Y. (2024). Deep learning: A overview of theory and architectures. 2024 20th csi international symposium on artificial intelligence and signal processing (AISP) (pp. 1–11). IEEE. https://doi.org/10.1109/AISP61396.2024.10475265
  59. [59] Bhavsar, A., Patel, V., Patel, Y., Geddam, R., Gupta, R., Tanwar, S., … & Shahinzadeh, H. (2024). Transfer learning based breast cancer detection for telemedicine systems in healthare environment. 2024 8th international conference on smart cities, internet of things and applications (SCIOT) (pp. 156–161). IEEE. https://doi.org/10.1109/SCIoT62588.2024.10570101
  60. [60] Vijay, M. M., Kumar, O. P., Francis, S. A. J., Stalin, A. D., & Vincent, S. (2024). Enhancing high-speed digital systems: MVL circuit design with CNTFET and RRAM. Journal of king saud university - computer and information sciences, 36(4), 102033. https://doi.org/10.1016/j.jksuci.2024.102033
  61. [61] Dutt, A. (2023). Modelling, exploration and optimization of hardware accelerators for deep learning applications. https://dr.ntu.edu.sg/entities/publication/ddc4a592-3921-4c45-8a40-e44232913d94
  62. [62] Das, R. R., Rajalekshmi, T. R., & James, A. (2024). FinFET to GAA MBCFET: A review and insights. IEEE access, 12, 50556–50577. https://doi.org/10.1109/ACCESS.2024.3384428
  63. [63] Ghasemi Nejad Raeini, A., Kordrostami, Z., & Hamedi, S. (2021). Coupled NEGF-PSO method for maximizing the current ratio of CNTFETs based on oxide thickness optimization. Journal of computational electronics, 20(5), 1657–1665. https://doi.org/10.1007/s10825-021-01743-2
  64. [64] Sandhya Rani, S., Pasha Mohammad, H., & Masthan, S. (2024). Remora optimized dynamic neural network to design low-power CNTFET logic gate realization with multiple-valued circuits. Electric power components and systems, 1–14. https://doi.org/10.1080/15325008.2024.2326854
  65. [65] Mohammaden, A., Fouda, M. E., Alouani, I., Said, L. A., & Radwan, A. G. (2022). CNTFET-based ternary multiply-and-accumulate unit. Electronics, 11(9), 1–10. https://doi.org/10.3390/electronics11091455

Downloads

Published

2024-02-25

Issue

Vol. 1 No. 1 (2024): Annals of Process Engineering and Management

Section

Articles

How to Cite

Machine Learning-Driven Design Optimization of CNFET-Based SRAM Cells. (2024). Annals of Process Engineering and Management, 1(1), 86-105. https://doi.org/10.48314/apem.v1i1.27

Similar Articles

You may also start an advanced similarity search for this article.