Abstract
The slowing down of transistor scaling and explosive growth for intelligence computing power emerge as the two driving factors for the study of novel devices and materials to pursue highly-efficient computing systems. Memristors, incorporating rich intrinsic dynamics, are a promising candidate for constructing efficient and scalable bio-inspired computing systems. In this progress report, we review the latest advances in novel types of memristors as well as their applications in implementing neuromorphic computing systems. This paper not only covers the memristive dynamics-enabled bionic computing systems but also discusses the memristive sensory systems that integrate sensing and computing. Eventually, device-circuit co-optimization methods are given to emphasize the trend of cross-layer co-design in this fast-evolving field. The innovation in memristor devices mainly focuses on specialized computing hardware and yields superior computing and sensing efficiency. At last, we offer our insight into the trend of state-of-the-art research in memristive materials, devices, circuits, and systems.
Similar content being viewed by others
References
Kumar S, Wang X, Strachan J P, et al. Dynamical memristors for higher-complexity neuromorphic computing. Nat Rev Mater, 2022, 7: 575–591
Yan B, Li B, Qiao X, et al. Resistive memory-based in-memory computing: from device and large-scale integration system perspectives. Adv Intell Syst, 2019, 1: 1900068
Cheng C D, Tiw P J, Cai Y M, et al. In-memory computing with emerging nonvolatile memory devices. Sci China Inf Sci, 2021, 64: 221402
Wang Y, Yang Y, Hao Y, et al. Embracing the era of neuromorphic computing. J Semicond, 2021, 42: 010301
Yao P, Wu H, Gao B, et al. Fully hardware-implemented memristor convolutional neural network. Nature, 2020, 577: 641–646
Tang J, Yuan F, Shen X, et al. Bridging biological and artificial neural networks with emerging neuromorphic devices: fundamentals, progress, and challenges. Adv Mater, 2019, 31: 1902761
Yao P, Wu H, Gao B, et al. Face classification using electronic synapses. Nat Commun, 2017, 8: 15199
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of Advances in Neural Information Processing Systems, Long Beach, 2017. 5998–6008
Ramachandran P, Parmar N, Vaswani A, et al. Stand-alone self-attention in vision models. In: Proceedings of Advances in Neural Information Processing Systems, Vancouver, 2019
Von Neumann J, Kurzweil R. The Computer and the Brain. New Haven: Yale University Press, 2012
Zhang B, Zhu J, Su H. Toward the third generation artificial intelligence. Sci China Inf Sci, 2023, 66: 121101
Chen S T, Jian Z Q, Huang Y H, et al. Autonomous driving: cognitive construction and situation understanding. Sci China Inf Sci, 2019, 62: 081101
Chen P Y, Peng X, Yu S. NeuroSim+: an integrated device-to-algorithm framework for benchmarking synaptic devices and array architectures. In: Proceedings of IEEE International Electron Devices Meeting (IEDM), San Francisco, 2017. 1–6
Radford A, Wu J, Child R, et al. Language models are unsupervised multitask learners. OpenAI blog, 2019, 1: 9
Partzsch J, Höppner S, Eberlein M, et al. A fixed point exponential function accelerator for a neuromorphic many-core system. In: Proceedings of IEEE International Symposium on Circuits and Systems (ISCAS), Toronto, 2017. 1–4
Guo Q, Guo X C, Bai Y X, et al. A resistive TCAM accelerator for data-intensive computing. In: Proceedings of the 44th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), Porto Alegre, 2011. 339–350
Mei L, Dandekar M, Rodopoulos D, et al. Sub-word parallel precision-scalable MAC engines for efficient embedded DNN inference. In: Proceedings of IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), Hsinchu, 2019. 6–10
Chen W H, Li K X, Lin W Y, et al. A 65 nm 1 Mb nonvolatile computing-in-memory ReRAM macro with sub-16 ns multiply-and-accumulate for binary DNN AI edge processors. In: Proceedings of IEEE International Solid-State Circuits Conference (ISSCC), San Francisco, 2018. 494–496
Eshraghian J K, Kang S-M, Baek S, et al. Analog weights in ReRAM DNN accelerators. In: Proceedings of IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), Hsinchu, 2019. 267–271
Lee E, Han T, Seo D, et al. A charge-domain scalable-weight in-memory computing macro with dual-SRAM architecture for precision-scalable DNN accelerators. IEEE Trans Circ Syst I, 2021, 68: 3305–3316
Belluomini W, Jamsek D, Martin A, et al. An 8 GHz floating-point multiply. In: Proceedings of IEEE International Solid-State Circuits Conference (ISSCC), San Francisco, 2005. 374–604
Krizhevsky A. Learning multiple layers of features from tiny images. 2009. https://www.cs.toronto.edu/~kriz/learning-features-2009-TR.pdf
Kumar A, Kharadi A, Singh D, et al. Automatic question-answer pair generation using deep learning. In: Proceedings of International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, 2021
Greff K, Srivastava R K, Koutnik J, et al. LSTM: a search space odyssey. IEEE Trans Neural Netw Learn Syst, 2016, 28: 2222–2232
Sze V, Chen Y H, Yang T J, et al. Efficient processing of deep neural networks: a tutorial and survey. Proc IEEE, 2017, 105: 2295–2329
Bankman D, Yang L, Moons B, et al. An always-on 3.8 J/86% CIFAR-10 mixed-signal binary CNN processor with all memory on chip in 28-nm CMOS. IEEE J Solid-State Circ, 2019, 54: 158–172
Biswas A, Chandrakasan A P. CONV-SRAM: an energy-efficient SRAM with in-memory dot-product computation for low-power convolutional neural networks. IEEE J Solid-State Circ, 2019, 54: 217–230
Sebastian A, Le Gallo M, Khaddam-Aljameh R, et al. Memory devices and applications for in-memory computing. Nat Nanotechnol, 2020, 15: 529–544
Verma N, Jia H, Valavi H, et al. In-memory computing: advances and prospects. IEEE Solid-State Circ Mag, 2019, 11: 43–55
Ielmini D, Wong H S P. In-memory computing with resistive switching devices. Nat Electron, 2018, 1: 333–343
Zhao Y, Ouyang P, Kang W, et al. An STT-MRAM based in memory architecture for low power integral computing. IEEE Trans Comput, 2018, 68: 617–623
Zhu D, Lu S, Wang M, et al. Efficient precision-adjustable architecture for softmax function in deep learning. IEEE Trans Circ Syst II, 2020, 67: 3382–3386
Stevens J R, Venkatesan R, Dai S, et al. Softermax: hardware/software co-design of an efficient softmax for transformers. 2021. ArXiv:210309301
Kvatinsky S, Belousov D, Liman S, et al. MAGIC-memristor-aided logic. IEEE Trans Circ Syst II, 2014, 61: 895–899
Shafiee A, Nag A, Muralimanohar N, et al. ISAAC: a convolutional neural network accelerator with in-situ analog arithmetic in crossbars. In: Proceedings of International Symposium on Computer Architecture (ISCA), Seoul, 2016. 14–26
Devlin J, Chang M-W, Lee K, et al. BERT: pre-training of deep bidirectional transformers for language understanding. 2018. ArXiv:181004805
Zhou H J, Li Y, Miao X S. Low-time-complexity document clustering using memristive dot product engine. Sci China Inf Sci, 2022, 65: 122410
Wan T Q, Ma S J, Liao F Y, et al. Neuromorphic sensory computing. Sci China Inf Sci, 2022, 65: 141401
Bao H, Chen Z G, Cai J M, et al. Memristive cyclic three-neuron-based neural network with chaos and global coexisting attractors. Sci China Technol Sci, 2022, 65: 2582–2592
Wei J S, Zhang J L, Zhang X M, et al. A neuromorphic core based on threshold switching memristor with asynchronous address event representation circuits. Sci China Inf Sci, 2022, 65: 122408
Thakur C S, Molin J L, Cauwenberghs G, et al. Large-scale neuromorphic spiking array processors: a quest to mimic the brain. Front Neurosci, 2018, 12: 891
Reis D, Niemier M, Hu X S. Computing in memory with FeFETs. In: Proceedings of ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED), Bellevue, 2018. 1–6
Lee J, Park B G, Kim Y. Implementation of Boolean logic functions in charge trap flash for in-memory computing. IEEE Electron Dev Lett, 2019, 40: 1358–1361
Liu K, Dang B, Zhang T, et al. Multilayer reservoir computing based on ferroelectric a-In2Se3 for hierarchical information processing. Adv Mater, 2022, 34: 2108826
Jing Z, Yang Y. Artificial intelligence goes physical. Small Sci, 2021, 1: 2000065
Wright L G, Onodera T, Stein M M, et al. Deep physical neural networks trained with backpropagation. Nature, 2022, 601: 549–555
Kan S, Nakajima K, Asai T, et al. Physical implementation of reservoir computing through electrochemical reaction. Adv Sci, 2022, 9: 2104076
Yang K, Joshua Yang J, Huang R, et al. Nonlinearity in memristors for neuromorphic dynamic systems. Small Sci, 2022, 2: 2100049
Xu L, Zhu J, Chen B, et al. A distributed nanocluster based multi-agent evolutionary network. Nat Commun, 2022, 13: 4698
Tang J, Duan H, Lao S. Swarm intelligence algorithms for multiple unmanned aerial vehicles collaboration: a comprehensive review. Artif Intell Rev, 2023, 56: 4295–4327
Attiya I, Elaziz M A, Abualigah L, et al. An improved hybrid swarm intelligence for scheduling IoT application tasks in the cloud. IEEE Trans Ind Inf, 2022, 18: 6264–6272
Saeed R A, Omri M, Abdel-Khalek S, et al. Optimal path planning for drones based on swarm intelligence algorithm. Neural Comput Applic, 2022, 34: 10133–10155
Xiao Z, Yan B, Zhang T, et al. Memristive devices based hardware for unlabeled data processing. Neuromorph Comput Eng, 2022, 2: 022003
Duan Q, Zhang T, Liu C, et al. Artificial multisensory neurons with fused haptic and temperature perception for multimodal in-sensor computing. Adv Intell Syst, 2022, 4: 2200039
Wang T, Meng J, Zhou X, et al. Reconfigurable neuromorphic memristor network for ultralow-power smart textile electronics. Nat Commun, 2022, 13: 7432
Zhou G, Wang Z, Sun B, et al. Volatile and nonvolatile memristive devices for neuromorphic computing. Adv Elect Mater, 2022, 8: 2101127
Jiang H, Li C, Lin P, et al. Ta/HfO2-based memristor and crossbar arrays for in-memory computing. In: Memristor Computing Systems. Berlin: Springer, 2022. 167–188
Zhuo Y, Midya R, Song W, et al. A dynamical compact model of diffusive and drift memristors for neuromorphic computing. Adv Elect Mater, 2022, 8: 2270040
Yang X, Taylor B, Wu A, et al. Research progress on memristor: from synapses to computing systems. IEEE Trans Circ Syst I, 2022, 69: 1845–1857
Wu X, Dang B, Wang H, et al. Spike-enabled audio learning in multilevel synaptic memristor array-based spiking neural network. Adv Intell Syst, 2022, 4: 2100151
Yan B, Hsu J L, Yu P C, et al. A 1.041-Mb/MM2 27.38-TOPS/W signed-INT8 dynamic-logic-based ADC-less SRAM compute-in-memory macro in 28 nm with reconfigurable bitwise operation for AI and embedded applications. In: Proceedings of International Solid-State Circuits Conference (ISSCC), San Francisco, 2022. 188–190
Chaudhuri A, Yan B, Chen Y, et al. Hardware fault tolerance for binary RRAM crossbars. In: Proceedings of IEEE International Test Conference (ITC), Washington, 2019. 1–10
Liu Z, Tang J, Gao B, et al. Multichannel parallel processing of neural signals in memristor arrays. Sci Adv, 2020, 6: eabc4797
Duan S, Hu X, Dong Z, et al. Memristor-based cellular nonlinear/neural network: design, analysis, and applications. IEEE Trans Neural Netw Learn Syst, 2014, 26: 1202–1213
Hu X F, Shi W Q, Zhou Y, et al. Quantized and adaptive memristor based CNN (QA-mCNN) for image processing. Sci China Inf Sci, 2022, 65: 119104
Jacob B, Kligys S, Chen B, et al. Quantization and training of neural networks for efficient integer-arithmetic-only inference. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, 2018. 2704–2713
Wang M, Rasoulinezhad S, Leong P H W, et al. NITI: training integer neural networks using integer-only arithmetic. IEEE Trans Parallel Distrib Syst, 2022, 33: 3249–3261
Banner R, Hubara I, Hoffer E, et al. Scalable methods for 8-bit training of neural networks. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, Montréal, 2018
Angizi S, He Z, Awad A, et al. MRIMA: an MRAM-based in-memory accelerator. IEEE Trans Comput-Aided Des Integr Circ Syst, 2019, 39: 1123–1136
Liu K, Zhang T, Dang B, et al. An optoelectronic synapse based on α-In2Se3 with controllable temporal dynamics for multimode and multiscale reservoir computing. Nat Electron, 2022, 5: 761–773
Zhang D, Schoenherr P, Sharma P, et al. Ferroelectric order in van der Waals layered materials. Nat Rev Mater, 2023, 8: 25–40
Wan S, Peng Q, Wu Z, et al. Nonvolatile ferroelectric memory with lateral β/α/β In2Se3 heterojunctions. ACS Appl Mater Interfaces, 2022, 14: 25693–25700
Yuan R, Duan Q, Tiw P J, et al. A calibratable sensory neuron based on epitaxial VO2 for spike-based neuromorphic multisensory system. Nat Commun, 2022, 13: 3973
Zhou F, Zhou Z, Chen J, et al. Optoelectronic resistive random access memory for neuromorphic vision sensors. Nat Nanotechnol, 2019, 14: 776–782
Dang B J, Liu K Q, Wu X L, et al. One-phototransistor-one-memristor array with high-linearity light-tunable weight for optic neuromorphic computing. Adv Mater, 2022. doi: https://doi.org/10.1002/adma.202204844
Li Y J. Accelerated value iteration via Anderson mixing. Sci China Inf Sci, 2021, 64: 222105
Laskin M, Lee K, Stooke A, et al. Reinforcement learning with augmented data. In: Proceedings of Advances in Neural Information Processing Systems, Vancouver, 2020. 19884–19895
Moerland T M, Broekens J, Plaat A, et al. Model-based reinforcement learning: a survey. FNT Mach Learn, 2023, 16: 1–118
Kiran B R, Sobh I, Talpaert V, et al. Deep reinforcement learning for autonomous driving: a survey. IEEE Trans Intell Transp Syst, 2021, 23: 4909–4926
Lu Y, Li X, Yan B, et al. In-memory realization of eligibility traces based on conductance drift of phase change memory for energy-efficient reinforcement learning. Adv Mater, 2022, 34: 2107811
Ding F, Jiao Y, Peng B, et al. Modeling the gradual RESET of phase change memory with confined geometry. IEEE Trans Electron Dev, 2022, 69: 6662–6668
Yan B, Yang J, Wu Q, et al. A closed-loop design to enhance weight stability of memristor based neural network chips. In: Proceedings of International Conference on Computer-Aided Design (ICCAD), Irvine, 2017. 541–548
Yan L, Li X, Zhu Y, et al. Uncertainty quantification based on multilevel conductance and stochasticity of heater size dependent C-doped Ge2Sb2Te5 PCM chip. In: Proceedings of IEEE International Electron Devices Meeting (IEDM), San Francisco, 2021. 22–28
Khaddam-Aljameh R, Stanisavljevic M, Mas J F, et al. HERMES core-A 14 nm CMOS and PCM-based in-memory compute core using an array of 300ps/LSB linearized CCO-based ADCs and local digital processing. In: Proceedings of IEEE Symposium on VLSI Circuits, Kyoto, 2021. 1–2
Joshi V, Le Gallo M, Haefeli S, et al. Accurate deep neural network inference using computational phase-change memory. Nat Commun, 2020, 11: 1–3
Lu Y, Li X, Yan L, et al. Accelerated local training of CNNs by optimized direct feedback alignment based on stochasticity of 4 Mb C-doped Ge2Sb2Te5 PCM chip in 40 nm node. In: Proceedings of IEEE International Electron Devices Meeting (IEDM), San Francisco, 2020. 33–36
Wong H S P, Lee H Y, Yu S, et al. Metal-oxide RRAM. Proc IEEE, 2012, 100: 1951–1970
Qiu K, Zhang Y, Yan B, et al. Heterogeneous memory architecture accommodating processing-in-memory on SoC for AIoT applications. In: Proceedings of Asia and South Pacific Design Automation Conference (ASP-DAC), Hsinchu, 2022. 383–388
Li Z, Zheng Q, Yan B, et al. ASTERS: adaptable threshold spike-timing neuromorphic design with twin-column ReRAM synapses. In: Proceedings of Design Automation Conference (DAC), San Francisco, 2022. 1099–1104
Chi P, Li S, Xu C, et al. PRIME: a novel processing-in-memory architecture for neural network computation in ReRAM-based main memory. In: Proceedings of the 43rd Annual International Symposium on Computer Architecture (ISCA), Seoul, 2016. 27–39
Song L, Qian X, Li H, et al. Pipelayer: a pipelined ReRAM-based accelerator for deep learning. In: Proceedings of IEEE International Symposium on High Performance Computer Architecture (HPCA), Austin, 2017. 541–552
Hu M, Li H, Chen Y, et al. Memristor crossbar-based neuromorphic computing system: a case study. IEEE Trans Neural Netw Learn Syst, 2014, 25: 1864–1878
Golonzka O, Arslan U, Bai P, et al. Non-volatile RRAM embedded into 22FFL FinFET technology. In: Proceedings of IEEE Symposium on VLSI Technology, Kyoto, 2019. 230–231
Doevenspeck J, Garello K, Verhoef B, et al. SOT-MRAM based analog in-memory computing for DNN inference. In: Proceedings of IEEE Symposium on VLSI Technology, San Francisco, 2020. 1–2
Xi Y, Gao B, Tang J, et al. In-memory learning with analog resistive switching memory: a review and perspective. Proc IEEE, 2020, 109: 14–42
Chen W H, Dou C, Li K X, et al. CMOS-integrated memristive non-volatile computing-in-memory for AI edge processors. Nat Electron, 2019, 2: 420–428
Jing Z, Yan B, Yang Y, et al. VSDCA: a voltage sensing differential column architecture based on 1T2R RRAM array for computing-in-memory accelerators. IEEE Trans Circ Syst I, 2022, 69: 4028–4041
Piazza F, Uncini A, Zenobi M. Neural networks with digital LUT activation functions. In: Proceedings of International Conference on Neural Networks (IJCNN), Nagoya, 1993. 1401–1404
Micikevicius P, Narang S, Alben J, et al. Mixed precision training. 2017. ArXiv:171003740
Zheng Q, Wang Z, Feng Z, et al. Lattice: an ADC/DAC-less ReRAM-based processing-in-memory architecture for accelerating deep convolution neural networks. In: Proceedings of Design Automation Conference (DAC), San Francisco, 2020. 1–6
Roy K, Jaiswal A, Panda P. Towards spike-based machine intelligence with neuromorphic computing. Nature, 2019, 575: 607–617
Courbariaux M, Bengio Y, David J-P. Training deep neural networks with low precision multiplications. 2014. ArXiv:14127024
Khwa W S, Chen J J, Li J F, et al. A 65 nm 4 Kb algorithm-dependent computing-in-memory SRAM unit-macro with 2.3 ns and 55.8 TOPS/W fully parallel product-sum operation for binary DNN edge processors. In: Proceedings of International Solid State Circuits Conference (ISSCC), San Francisco, 2018. 496–498
Dang B, Lv L, Wang H, et al. 1-HEMT-1-memristor with hardware encryptor for privacy-preserving image processing. IEEE Electron Device Lett, 2022, 43: 1223–1226
Su J W, Chou Y C, Liu R, et al. A 28 nm 384 Kb 6T-SRAM computation-in-memory macro with 8b precision for AI edge chips. In: Proceedings of International Solid State Circuits Conference (ISSCC), San Francisco, 2021. 250–252
Lee J, Kim J, Jo W, et al. ECIM: exponent computing in memory for an energy-efficient heterogeneous floating-point DNN training processor. IEEE Micro, 2021, 42: 99–107
Yang X, Yan B, Li H, et al. ReTransformer: ReRAM-based processing-in-memory architecture for transformer acceleration. In: Proceedings of International Conference on Computer-Aided Design (ICCAD), Virtual Event, 2020. 1–9
Xu N, Fang L, Kim K M, et al. Time-efficient stateful dual-bit-memristor logic. Phys Status Solidi RRL, 2019, 13: 1900033
Yuan R, Ma M Y, Xu L Y, et al. Efficient 16 Boolean logic and arithmetic based on bipolar oxide memristors. Sci China Inf Sci, 2020, 63: 202401
Cai W L, Wang M X, Cao K H, et al. Stateful implication logic based on perpendicular magnetic tunnel junctions. Sci China Inf Sci, 2022, 65: 122406
Acknowledgements
This work was supported by National Natural Science Foundation of China (Grant Nos. 61925401, 92064004, 61927901, 92164302) and 111 Project (Grant No. B18001). Yuchao YANG acknowledges support from Fok Ying-Tong Education Foundation and Tencent Foundation through the XPLORER PRIZE.
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Yan, B., Yang, Y. & Huang, R. Memristive dynamics enabled neuromorphic computing systems. Sci. China Inf. Sci. 66, 200401 (2023). https://doi.org/10.1007/s11432-023-3739-0
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-023-3739-0