Abstract
We propose a NOR flash-based computing-in-memory (CIM) to implement high-precision (32-bit) Poisson image editing, including the gradient operations and Laplace operation. To meet the requirements of image processing, CIM operation schemes and reliabilities are carefully studied and optimized, showing that the power consumption at the near-threshold-voltage (NTV) region can be as low as 40 fJ/bit, which is two orders lower than working at the saturation region. High-temperature retention, as well as various disturbs, are also analyzed. The proposed CIM scheme can be applied as an energy-efficient approach to construct the high-precision image processing accelerator.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Li C, Hu M, Li Y N, et al. Analogue signal and image processing with large memristor crossbars. Nat Electron, 2018, 1: 52–59
Ma W, Zidan M A, Lu W D. Neuromorphic computing with memristive devices. Sci China Inf Sci, 2018, 61: 060422
Hao Y X, Zhang Y, Wu Z H, et al. Uniform, fast, and reliable CMOS compatible resistive switching memory. J Semicond, 2022, 43: 054102
Raoux S, Wełnic W, Ielmini D. Phase change materials and their application to nonvolatile memories. Chem Rev, 2009, 110: 240–267
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
Mikolajick T, Dehm C, Hartner W, et al. FeRAM technology for high density applications. MicroElectron Reliab, 2001, 41: 947–950
Jiang Y N, Huang P, Zhou Z, et al. Circuit design of RRAM-based neuromorphic hardware systems for classification and modified Hebbian learning. Sci China Inf Sci, 2019, 62: 062408
Guo X, Bayat F M, Prezioso M, et al. Temperature-insensitive analog vector-by-matrix multiplier based on 55 nm NOR flash memory cells. In: Proceedings of Custom Integrated Circuits Conference (CICC), Austin, 2017. 1–4
Bavandpour M, Mahmoodi M R, Strukov D B. Energy-efficient time-domain vector-by-matrix multiplier for neurocomputing and beyond. IEEE Trans Circ Syst II, 2019, 66: 1512–1516
Han R Z, Huang P, Xiang Y C, et al. A novel convolution computing paradigm based on NOR flash array with high computing speed and energy efficiency. IEEE Trans Circ Syst I, 2019, 66: 1692–1703
Xiang Y C, Huang P, Zhou Z, et al. Analog deep neural network based on nor flash computing array for high speed/energy efficiency computation. In: Proceedings IEEE International Symposium on Circuits and Systems (ISCAS), Sapporo, 2019. 1–4
Xiang Y C, Huang P, Han R Z, et al. Efficient and robust spike-driven deep convolutional neural networks based on NOR flash computing array. IEEE Trans Electron Dev, 2020, 67: 2329–2335
Lee S T, Yeom G, Hwang J, et al. Utilization of unsigned inputs for NAND flash-based parallel and high-density synaptic architecture in binary neural networks. IEEE J Electron Dev Soc, 2021, 9: 1049–1054
Joshi V, Le Gallo M, Haefeli S, et al. Accurate deep neural network inference using computational phase-change memory. Nat Commun, 2020, 11: 1
Pérez P, Gangnet M, Blake A. Poisson image editing. In: Proceedings of ACM SIGGRAPH, San Diego, 2003. 313–318
Feng Y, Chen B, Liu J, et al. Design-technology co-optimizations for general-purpose computing in-memory based on 55nm NOR flash technology. In: Proceedings of IEEE International Electron Devices Meeting (IEDM), San Francisco, 2021
Feng Y, Wang F, Zhan X P, et al. Flash memory based computing-in-memory system to solve partial differential equations. Sci China Inf Sci, 2021, 64: 169401
Zhang D, Wang H, Feng Y, et al. Implementation of image compression by using high-precision in-memory computing scheme based on NOR flash memory. IEEE Electron Dev Lett, 2021, 42: 1603–1606
Jiang X B, Guo S F, Wang R S, et al. New insights into the near-threshold design in nanoscale FinFET technology for sub-0.2V applications. In: Proceedings of IEEE International Electron Devices Meeting (IEDM), San Francisco, 2016
Lue H T, Hsu P K, Wei M L, et al. Optimal design methods to transform 3D NAND flash into a high-density, high-bandwidth and low-power nonvolatile computing in memory (nvCIM) accelerator for deep-learning neural networks (DNN). In: Proceedings of IEEE International Electron Devices Meeting (IEDM), San Francisco, 2019
Acknowledgements This work was supported by National Natural Science Foundation of China (Grant Nos. 62034006, 92264201, 91964105), Natural Science Foundation of Shandong Province (Grant Nos. ZR2020JQ28, ZR2020KF016), and Program of Qilu Young Scholars of Shandong University.
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Feng, Y., Chen, B., Tang, M. et al. Near-threshold-voltage operation in flash-based high-precision computing-in-memory to implement Poisson image editing. Sci. China Inf. Sci. 66, 222402 (2023). https://doi.org/10.1007/s11432-022-3743-x
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-022-3743-x