Stuck-at Fault Tolerance in RRAM Computing Systems
The DOI matches its Crossref record; 30 of the 31 references it cites were found in a registry or an index.
Abstract
Emerging metal-oxide resistive switching random-access memory (RRAM) devices and RRAM crossbars have demonstrated their potential in boosting the speed and energy-efficiency of analog matrix-vector multiplication. However, due to the immature fabrication technology, commonly occurring Stuck-At-Faults (SAFs) seriously degrade the computational accuracy of an RRAM-based computing system (RCS). In this paper, we present a fault-tolerant framework for RCS. A mapping algorithm with inner fault tolerance is proposed to convert matrix parameters into RRAM conductances in RCS and tolerate SAFs by fully exploring the available mapping space. Two baseline redundancy schemes are proposed to ensure that RCS is effective when the percentage of faulty RRAM cells is high. To reduce the number of redundant RRAM cells when the SAFs follow a non-uniform distribution or an unknown distribution, a distribution-aware redundancy scheme and a re-configurable redundancy scheme are proposed to provide dynamic fault tolerance. Simulation results show that, the baseline redundancy schemes can improve the recognition accuracy of the MNIST data set to almost the same as the RRAM-fault-free case, with an energy overhead of approximately 30%. When SAFs follow a non-uniform and an unknown distribution, the distribution-aware and re-configurable schemes can reduce the number of redundant RRAM cells from more than 200% to less than 40% and 60%, respectively, without reducing the recognition accuracy.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“However, grounding the bitlines through a resistor might alter the potential applied to the bitline, which will no longer be 0 volts, adding variability and thus altering the read over the sensing resistor100,112.”
From Hardware implementation of memristor-based artificial neural networks (2024) · cites this paper as [112]
Citations
Cites
Wong, H.-S. P., Lee, H.-Y., Yu, S., Chen, Y.-S., Wu, Y., Chen, P.-S., Lee, B., Chen, F. T., & Tsai, M.-J. (2012) · Proceedings of the IEEE · doi:10.1109/jproc.2012.2190369 · Cited by 2,757 · cited 1×
“RRAM is an emerging passive two-ports device based on metal oxide materials such as HfOx , TiOx and WOx [17], which has been widely used as non-volatile memory.”
BackgroundISAAC: a convolutional neural network accelerator with in-situ analog arithmetic in crossbars
Shafiee, A., Nag, A., Muralimanohar, N., Balasubramonian, R., Strachan, J. P., Hu, M., Williams, R. S., & Srikumar, V. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001139 · Cited by 1,536 · cited 2×
“, RRAM-based dot-product operator [4], [20], RRAM-based fully-connected Neural Networks (NN) [21], [22], and RRAM-based convolutional neural networks [15], [23].”
MethodChi, P., Li, S., Xu, C., Zhang, T., Zhao, J., Liu, Y., Wang, Y., & Xie, Y. (2016) · ACM SIGARCH Computer Architecture News · doi:10.1145/3007787.3001140 · Cited by 1,231 · cited 2×
“The most attractive feature of RRAM devices is that the crossbar structure of RRAM array can be used to perform matrixvector multiplication, which efficiently merges the memory and computation together [18] and reduces the computation complexity from O(n2) to O(1) [19].”
Self-citationHu, M., Strachan, J. P., Li, Z., Grafals, E. M., Davila, N., Graves, C., Lam, S., Ge, N., Yang, J. J., & Williams, R. S. (2016) · Proceedings of the 53rd Annual Design Automation Conference · doi:10.1145/2897937.2898010 · Cited by 686 · cited 1×
“, RRAM-based dot-product operator [4], [20], RRAM-based fully-connected Neural Networks (NN) [21], [22], and RRAM-based convolutional neural networks [15], [23].”
Memristor Crossbar-Based Neuromorphic Computing System: A Case Study
Hu, M., Li, H., Chen, Y., Wu, Q., Rose, G. S., & Linderman, R. W. (2014) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2296777 · Cited by 414 · cited 3×
“Previously proposed mapping algorithms, which convert matrix parameters into RRAM conductances of the RCS, use simplified assumptions and are targeted at ideal RRAM devices without SAFs [4], [13], [14].”
BackgroundMethodReal-time EEG analysis with subject-specific spatial patterns for a brain-computer interface (BCI)
Guger, C., Ramoser, H., & Pfurtscheller, G. (2000) · IEEE Transactions on Rehabilitation Engineering · doi:10.1109/86.895947 · Cited by 383 · cited 1×
“2776980 GPU, and FPGA, cannot meet the requirements of processing data in real-time with high energy efficiency [1].”
BackgroundRRAM Defect Modeling and Failure Analysis Based on March Test and a Novel Squeeze-Search Scheme
Chen, C.-Y., Shih, H.-C., Wu, C.-W., Lin, C.-H., Chiu, P.-F., Sheu, S.-S., & Chen, F. T. (2015) · IEEE Transactions on Computers · doi:10.1109/tc.2014.12 · Cited by 261 · cited 9×
“For example, researchers reported that only 63% of the RRAM cells are fault-free for a fabricated 4-Mb HfO2-based RRAM test chip, and SAFs appear rather frequently - about 10% of the RRAM cells in the chip contain SAFs [5].”
BackgroundMethodInfluentialRescuing Memristor-based Neuromorphic Design with High Defects
Liu, C., Hu, M., Strachan, J. P., & Li, H. (. (2017) · Proceedings of the 54th Annual Design Automation Conference 2017 · doi:10.1145/3061639.3062310 · Cited by 257 · cited 3×
“In future work, we will combine the proposed hardwarelevel schemes with algorithm-level methods [8], [9], [27] to further improve the fault tolerance of RCS.”
MethodAccelerator-friendly neural-network training: Learning variations and defects in RRAM crossbar
Chen, L., Li, J., Chen, Y., Deng, Q., Shen, J., Liang, X., & Jiang, L. (2017) · Design, Automation & Test in Europe Conference & Exhibition (DATE), 2017 · doi:10.23919/date.2017.7926952 · Cited by 245 · cited 4×
“In future work, we will combine the proposed hardwarelevel schemes with algorithm-level methods [8], [9], [27] to further improve the fault tolerance of RCS.”
BackgroundMethodInfluentialTechnological Exploration of RRAM Crossbar Array for Matrix-Vector Multiplication
Xia, L., Gu, P., Li, B., Tang, T., Yin, X., Huangfu, W., Yu, S., Cao, Y., Wang, Y., & Yang, H. (2016) · Journal of Computer Science and Technology · doi:10.1007/s11390-016-1608-8 · Cited by 183 · cited 6×
“In prior work, after an RCS is fabricated, the parameters in the computed matrices are first mapped to the conductances of RRAM cells [4], [14].”
BackgroundMethodSelf-citation
Research works printed but not linked: 2
- lecun, 0, The MNIST Database of Handwritten Digits
- prakash, 2013, Improved resistance memory characteristics and switching mechanism using TiN electrode on TaOx/W structure, Proc Winter Simulation Conf, 136
Cited by
Items 101–177 of 177
Liu, G., Hu, M., Zhang, Y., Du, E., & Liu, D. (2020) · IEICE Electronics Express · doi:10.1587/elex.17.20200273 · Cited by 3
“1 Device defects There are two kinds of Stuck-at-Fault (SAF) defects in ReRAM devices, which are Stuck-at-Zero (SA0) and Stuckat-One (SA1), respectively [13, 14, 15].”
BackgroundZhou, H., Wu, B., Huan, C., Liu, J., Lei, T., Feng, D., & Tong, W. (2024) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro61859.2024.00028 · Cited by 5
“Existing error mitigation techniques [22], [50]–[52] enable CIM systems to tolerate a certain degree of error.”
Area-Efficient and Reliable Hybrid CMOS/Memristor ECC Circuit for ReRAM Storage
Ishizaka, M., Shintani, M., & Inoue, M. (2018) · Proceedings - Asian Test Symposium/Proceedings · doi:10.1109/ats.2018.00040 · Cited by 3
STAT: Mean and Variance Characterization for Robust Inference of DNNs on Memristor-based Platforms
Zhang, B., Uysal, N., & Ewetz, R. (2019) · ACM Great Lakes Symposium on VLSI (GLSVLSI) · doi:10.1145/3299874.3318032 · Cited by 3
“Substantial robustness improvements at the expense of power and hardware overhead were demonstrated [14].”
BackgroundMethodInfluentialNeuron Deactivation Scheme for Defect-Tolerant Memristor Neural Networks
Oh, S., An, J., & Min, K. (2022) · International Conference on Modern Circuits and Systems Technologies · doi:10.1109/mocast54814.2022.9837695 · Cited by 3
Mitigating Imperfections in Mixed-Signal Neuromorphic CircuitsPreprint
Fahimi, Z., Mahmoodi, M. R., Klachko, M., Nili, H., Kim, H., & Strukov, D. B. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.04236 · Cited by 6
“A tremendous body of research predicts analog implementations of neuromorphic networks [1,4,5,6] could bridge the gap between artificial and biological prototypes [7,8,9] and offer comparable areal density to biological prototypes at a better processing time.”
BackgroundReal-Time Compensation Framework for Large-Scale ReRAM-Based Sparse LU Factorization
Chen, W., Chen, Z., Yu, B., Chen, S., Kang, Y., & Xu, Q. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3576332 · Cited by 3
“SAF: SAF is another reliability issue in ReRAM [21], where memory cells become “stuck” in a particular resistive state (either Stuck-At-One or Stuck-At-Zero), regardless of the applied programming voltage.”
MoF-LoRA: Mixture of Low-Rank Fault-Tolerant Experts for RRAM-Based In-Memory Computing
Ahmed, S. T., Ortega, E., Xiao, P., Feinberg, B., Bennett, C. H., Marinella, M. J., & Chakrabarty, K. (2026) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2026.3655242 · Cited by 3
“This degradation can cause hard faults, where a cell becomes permanently unresponsive to programming operations, a phenomenon known as a stuck-at fault (SAF) [35], [36].”
Self-citationReSAFT: An efficient stuck-at fault-tolerant scheme for ReRAM-based process-in-memory accelerators
Dorostkar, A., Farbeh, H., & Zarandi, H. R. (2026) · Future Generation Computer Systems · doi:10.1016/j.future.2026.108685 · Cited by 3
Addressing Resiliency of In-Memory Floating Point Computation
Ensan, S. S., Ghosh, S., Motaman, S., & Weast, D. (2022) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2022.3170542 · Cited by 2
“, by assigning inputs of faulty RRAMs to the redundant rows or columns) [18], [21], [22].”
BackgroundTolerating Stuck-at Fault and Variation in Resistive Edge Inference Engine via Weight Mapping
Ma, Y., Zheng, L., & Zhou, P. (2021) · ACM Great Lakes Symposium on VLSI (GLSVLSI) · doi:10.1145/3453688.3461487 · Cited by 3
Effect of ReRAM Neuromorphic Circuit Array Variation and Fault on Inference Accuracy
Quibuyen, P., Jiao, T., & Wong, H. Y. (2022) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas54282.2022.9869936 · Cited by 2
“Finally, it is inevitable to have stuck-at faults in ReRAM after fabrications [17][18].”
BackgroundFault-Tolerant Deep Learning Processors
Li, X., Yan, G., & Liu, C. (2023) · Springer eBooks · doi:10.1007/978-981-19-8551-5_5 · Cited by 2
UpTime: Towards Flow-based In-Memory Computing with High Fault-Tolerance
Thijssen, S., Rashed, M. R. H., Jha, S. K., & Ewetz, R. (2023) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1109/dac56929.2023.10247692 · Cited by 2
“The runtime defects occur from the continuous on/off switching of the memristors [24].”
BackgroundYang, J., & Kwak, S. W. (2023) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2023.3310004 · Cited by 2
“Example 1: A typical example of permanent faults charging state components of the controller is stuck-at faults [41], which occur to the memory bits representing the state of a digital system.”
BackgroundWen, J., Vargas, F. L., Zhu, F., Reiser, D., Baroni, A., Fritscher, M., Pérez, E., Reichenbach, M., Wenger, C., & Krstic, M. D. (2024) · IEEE Latin American Test Symposium (LATS) · doi:10.1109/lats62223.2024.10534601 · Cited by 2
“Additionally, the immature fabrication process may introduce manufacturing defects, such as stuck-at faults [10], further deteriorating the reliability.”
BackgroundZhong, Z., You, Z., & Liu, P. (2024) · IEEE International Test Conference in Asia (ITC-Asia) · doi:10.1109/itc-asia62534.2024.10661325 · Cited by 3
“The closest value 0 is programmed into the memristors to reduce its weight difference [15].”
BackgroundFault Tolerant Design for Memristor-based AI Accelerators
Spyrou, T., Zografou, A., Hamdioui, S., & Gebregiorgis, A. (2024) · doi:10.1109/dttis62212.2024.10779989 · Cited by 2
“In [8], a re-configurable crossbar array is proposed Fig.”
Improving Self-Fault-Tolerance Capability of Memristor Crossbar Using a Weight-Sharing Approach
Yadav, D. N., Thangkhiew, P. L., Lalchhandama, F., Datta, K., Drechsler, R., & Sengupta, I. (2024) · Proceedings - Asian Test Symposium/Proceedings · doi:10.1109/ats64447.2024.10915508 · Cited by 2
“The fault-tolerance approaches for memristive cross-bars [13]–[16] can be broadly classified into three approaches. i) Fault Aware Training : The authors in [13] proposed a training approach by considering faults that can occur in the crossbar.”
Reliability Enhancement of Memristor-Based Neural Networks with Fault-Injected Training
Islam, M. S., Eguchi, R., & Inoue, M. B. (2024) · Proceedings - Asian Test Symposium/Proceedings · doi:10.1109/ats64447.2024.10915534 · Cited by 3
“[12] presented a fault-tolerance mapping algorithm (MAO).”
Vourkas, I. (2025) · Parallel Processing Letters · doi:10.1142/s0129626425500112 · Cited by 2
Mapping Large-Scale Spiking Neural Network on Arbitrary Meshed Neuromorphic Hardware
Jin, O., Xing, Q., Chen, Z., Zhang, M., Ma, D., Li, Y., Du, X., He, S., Deng, S., & Pan, G. (2025) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2025.3601993 · Cited by 4
“Otherworksfocus onencoding-basedapproaches,whereworkloadsareallocated andtunedtocounteracthardwaredefects,asdiscussedbyXiaet al.[27].”
Fast Resilient-Aware Data Layout Organization for Resistive Computing Systems
Zhang, B., Murshed, M. G. S., Hussain, F., & Ewetz, R. (2020) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi49217.2020.00023 · Cited by 2
“…the negative impact of defects are based on Research was supported in part by NSF awards CCF-1755825 and CNS-1908471. hardware-aware training [2], [11], [12], [15], [4], digital compensation [4], utilizing redundant hardware [2], [5], [16], [18], and data layout organization [2], [11], [15], [18].”
BackgroundMethodInfluentialRobust Fault-Tolerant Design Based on Checksum and On-Line Testing for Memristor Neural Network
Shintani, M., Ishizaka, M., & Inoue, M. (2021) · Proceedings - Asian Test Symposium/Proceedings · doi:10.1109/ats52891.2021.00017 · Cited by 1
Exploring a Hybrid SRAM-RRAM Computing-In-Memory Architecture for DNNs Model Inference
Chen, Y., Liu, Z., & Tsai, Y.-J. (2024) · IEEE Computer Society Annual Symposium on VLSI · doi:10.1109/isvlsi61997.2024.00031 · Cited by 1
“Here we apply RRAM unit failure model proposed in [16] and perform soft-hardware co-simulation for accuracy comparison.”
BackgroundMethodInfluentialRobust In-Memory Computation With Bayesian Analog Error Mitigating Codes
Jha, N. K., Guo, H., & Lau, V. K. N. (2025) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2025.3530149 · Cited by 1
“The precision of the input DAC and the crossbar are set to 8 bits and utilises element-wise clipped uniform quantisation with values clipped in the range [ − 4 , 4] following [8], [9], [10] and hence, we set the scale for the modified tanh activation function as υ = 4 .”
FairXbar: Improving the Fairness of Deep Neural Networks with Non-Ideal in-Memory Computing Hardware
Mugdho, S. S., Guo, Y., Rogers, E. G., Zhao, W., Shi, Y., & Wang, C. (2025) · Design, Automation, and Test in Europe · doi:10.23919/date64628.2025.10993038 · Cited by 2
“Stuck-at faults (SAF) occur when an NVM cell (such as a resistive random access memory ReRAM) becomes permanently locked in a specific resistance state, rendering it unable to alter its resistance in Write Operations [23].”
WOLF: Weight-Level OutLier and Fault Integration for Reliable LLM Deployment
Wang, C., Fu, W., Zhang, J., Li, S., Hou, R., Yang, J., & Wang, Y. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3587957 · Cited by 1
“A variety of countermeasures have been explored for DNN accelerators, including redundant substitution [43], fault-tolerant training [44] or pruning [45], error-correction encodings [10], [31], and checksum methods [5], [6].”
Self-citationERGo: Energy-Efficient Hybrid Graph Neural Network Training on Processing-in-Memory Architectures
Dhingra, P., Ugwu, C., Doppa, J. R., & Pande, P. P. (2025) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3760402 · Cited by 1
“Hardware approaches do not reduce the number of writes but add redundancy to the computing system, such as redundant columns or a fault map to compensate for the output [ 28 ].”
Toward Variation-Tolerant Ferroelectric Neural Computing: Special Session Paper
Saha, A., Mia, M. Z. A., Duan, J., Ni, K., & Sengupta, A. (2025) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas53549.2025.11244385 · Cited by 1
“Such faults can originate from various device-level defects, including trapped charges, defects within the ferroelectric layer, or imperfections introduced during the fabrication process [27].”
Dynamic Error Correction for Memristive Devices via Passive Resistance-to-Time Encoding
Tompris, I., Chatzipaschalis, I. K., Fyrigos, I.-A., & Sirakoulis, G. C. (2025) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs66544.2025.11270708 · Cited by 1
“To mitigate these limitations, error correction circuits are routinely employed in memristive systems [7].”
Mask-based Meta-Learning for Stuck-at Faults Tolerance in ReRAM Computing Systems
Shen, Z. L., Zhou, Y., Xu, T., Shen, S., Mei, Z. X., Sun, D., & Zhang, Z. (2026) · Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.1109/asp-dac66049.2026.11420339 · Cited by 1
“Exist experiments demonstrated that with just 10% of crossbar cells exhibiting SAFs, the inference accuracy reduces over 50% [4], highlighting the need for fault-tolerant methodologies in ReRAM-based CIM systems.”
Fault-free analogue computing with imperfect hardware
Xu, Z., Liu, J., Huang, S., Li, Z., Wang, S., Wen, B., Mao, R., Jiang, M., Pedretti, G., Ignowski, J., et al. (2026) · Nature Electronics · doi:10.1038/s41928-026-01638-9 · Cited by 4
“Redundancy uses additional devices to average out errors 30,32 , compensate for inaccuracies 8,31 or encode information to detect computing outliers 38,39 .”
HAT-FI: Hardware-Aware Training for Fault-Tolerant LLM Inference on RRAM-Based Compute-in-Memory
Sharma, P., Ahmed, S. T., Firouzi, F., & Chakrabarty, K. (2026) · IEEE VLSI Test Symposium (VTS) · doi:10.1109/vts69484.2026.11563304 · Cited by 1
“…filament formation at write time [8], (2) conductance drift from post-programming relaxation [9], (3) stuck-at faults from endurance degradation [10], (4) stochastic read noise per inference from electron conduction variability [11], and (5) temperature-dependent variability in conductance…”
Self-citationEfficient training of neuromorphic electronics
Yang, S., Tang, J., Zhou, T., Linares-Barranco, B., Indiveri, G., Zheng, X., Azghadi, M. R., & Chen, B. (2026) · Nature Electronics · doi:10.1038/s41928-026-01631-2 · Cited by 2
Fault-Aware Adversary Attack Analyses and Enhancement for RRAM-Based Neuromorphic Accelerator
Shang, L., Jung, S., Li, F., & Pan, C. (2022) · Frontiers in Sensors · doi:10.3389/fsens.2022.896299 · Cited by 1
Neuromorphic System Design Fundamentals
Abdallah, A. B., & Dang, K. N. (2022) · Springer eBooks · doi:10.1007/978-3-030-92525-3_2 · Cited by 1
Yield Evaluation of Faulty Memristive Crossbar Array-based Neural Networks with Repairability
Bala, A., Khandelwal, S., Jabir, A. M., & Ottavi, M. L. (2022) · IEEE International On-Line Testing Symposium (IOLTS) · doi:10.1109/iolts56730.2022.9897183 · Cited by 1
“Therefore, these faults can limit the recognition accuracy of memristor-based neural circuits [3], [4].”
BackgroundCircuit and Training Techniques Compensating for Non-Ideal Effects in Memristor Neural Networks
Oh, S., An, J., & Min, K. (2022) · IEEE International Conference on Solid-State and Integrated Circuit Technology · doi:10.1109/icsict55466.2022.9963389 · Cited by 1
“Neuron-deactivation scheme of compensating for stuck-at-fault defects In addition to the parasitic resistance mentioned in the section 2, stuck-at-fault defects can also be found in nonideal memristor crossbars [11], [12].”
BackgroundBang, S., Kim, S., Hong, K., Mohanan, K. U., Cho, S., & Choi, W. Y. (2022) · AIP Advances · doi:10.1063/5.0117486 · Cited by 1
Enabling Neuromorphic Computing for Artificial Intelligence with Hardware-Software Co-Design
Li, B., Zhong, D., Chen, X., & Liu, C. (2023) · Artificial intelligence · doi:10.5772/intechopen.111963 · Cited by 1
Aguirre, F. L., Piros, E., Kaiser, N., Vogel, T., Petzold, S., Gehrunger, J., Oster, T., Hofmann, K., Hochberger, C., Suñé, J., et al. (2023) · APL Machine Learning · doi:10.1063/5.0143926 · Cited by 3
Yang, C., Jin, S. C., Shen, J., & Wang, Z. (2023) · Proceedings - Asian Test Symposium/Proceedings · doi:10.1109/ats59501.2023.10317978 · Cited by 1
“Hardware level solutions include involving additional logic circuits and memory or using memristor redundancy columns to increase the weights mapping selection [9]-[10].”
BackgroundTokarev, A. A. (2025) · ELECTRONICS Science Technology Business · doi:10.22184/1992-4178.2025.247.6.106.112 · Cited by 1
SEC-CiM+: Selective and Reconfigurable Error Compensation for ReRAM-based Compute-in-Memory
Bommana, A. R., Firouzi, F., Ogbogu, C., Joardar, B. K., Doppa, J. R., Pande, P. P., & Chakrabarty, K. (2026) · ACM Transactions on Design Automation of Electronic Systems · doi:10.1145/3812655 · Cited by 1
Self-citationKim, Y., Kim, S., Yeh, C.-C., Narayanan, V., & Choi, J. (2020) · ACM Journal on Emerging Technologies in Computing Systems · doi:10.1145/3393669 · Cited by 4
“assumption is consistent with the other works such as a dead device modeled as g= 0 in PCM array [26], or a stuck-at-1 fail cell modeled as a minimum conductance (or g’0) of the system in ReRAM array [33]. In contrast, the resistance of the overformed 4 (OF) devices can be as low as few hundreds of Ω to few kΩ whereas…”
BackgroundResultArea-Efficient and Reliable Error Correcting Code Circuit Based on Hybrid CMOS/Memristor Circuit
Ishizaka, M., Shintani, M., & Inoue, M. (2020) · Journal of Electronic Testing · doi:10.1007/s10836-020-05892-3 · Cited by 1
“A hard fault is a fault where the resistance of a memristor is stuck at a high-resistance or low-resistance state, i.e., stuck-at fault , caused by fabrication defects (static fault) [4] and or limited endurance (dynamic fault) [28].”
BackgroundBio-inspired learning and hardware acceleration with emerging memories
Kulkarni, S. (2019)
Robust Acceleration of Data-Centric Applications using Resistive Computing Systems
Zhang, B. (2021) · Journal of International Crisis and Risk Communication Research
2018 IndexIEEE Journal on Emerging and Selected Topics in Circuits and SystemsVol. 8
(2018) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2018.2887151
Digital Twin Based Fault-Tolerance Framework for RRAM Based Neural Computing Systems
Vatti, C. S., Sai Dinesh, Y., V, Nimbekar, A., & Acharyya, A. (2023) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas57524.2023.10405988
Fault Tolerance Framework for Memristor based Binarized Neural Networks
Qian, J., Yang, Y. S., & Huang, C. (2023) · IEEE International Conference on Memristive Computing and Applications (ICMCA) · doi:10.1109/icmca59770.2023.10480978
“The redundancy scheme utilizes additional memristor crossbars, and when a fault occurs in the computing memristor crossbar, the redundant array is activated to replace the faulty crossbar [12].”
MethodAnalysis of Memristor Neural Networks for fault Tolerant Computing
Bhagya, Hiremath, S. G., & Vijayakumar, C. N. (2024) · International Conference on Knowledge Engineering and Communication Systems (ICKECS) · doi:10.1109/ickecs61492.2024.10617381
Fault Tolerance in Triplet Network Training: Analysis, Evaluation and Protection Methods
Wang, Z.-H., Niknia, F., Liu, S.-S., Reviriego, P., Louri, A., & Lombardi, F. (2025) · IEEE Transactions on Emerging Topics in Computing · doi:10.1109/tetc.2024.3481962
An Automated Design Platform for ReRAM-based DNN Accelerators with Hardware-Software Co-exploration
Lai, Y.-C. “., & Nien, C.-F. (2024) · IEEE Asia Pacific Conference on Circuits and Systems (APCCAS) · doi:10.1109/apccas62602.2024.10808244
Brief Review of Neuron Typology and Analysis of the Use of Memristor Crossbars
Tokarev, A. A., & Khorin, I. A. (2024) · Russian Microelectronics · doi:10.1134/s1063739724600766
“This problem is solved by both software and hardware methods [84–87].”
Malhotra, A., & Gupta, S. K. (2024) · doi:10.1145/3676536.3697134
“SAFs are randomly and uniformly injected throughout the TNNs/BNNs, consistent with methods in related research [26].”
Double Column Error Correction in RRAM Matrix Multiplication Using Weighted Checksums
Kodali, K., Pinto, K. X., Das, A., & Touba, N. A. (2025) · IEEE Latin American Test Symposium (LATS) · doi:10.1109/lats65346.2025.10963967
“However, these improvements come with its own set of challenges, the primary being the low yield and high error rate in RRAM fabrication compared to conventional memory technologies [5] [6].”
Neuromorphic System Design Fundamentals
Abdallah, A. B., & Dang, K. N. (2024) · Springer eBooks · doi:10.1007/978-3-031-83089-1_2 · Cited by 1
A Novel Full Adder Design Using Hybrid Memristor Ratioed Logic
Fadlallah, H., Kanj, R. N., & Hajri, B. (2025) · International Symposium on Quality Electronic Design (ISQED) · doi:10.1109/isqed65160.2025.11014320
“The memristor can suffer from permanent stuck-at-faults during the fabrication process [31].”
FR 2 eRAM: A Fault-Resilient Graph Processing Paradigm in Realistic ReRAMs
Wang, X., Yue, H., Jiang, N., Li, Z., Deng, J., Huang, Y., Qiu, M., & Wei, X. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3581138
“Several solutions have been proposed to enhance the reliability of ReRAM-based processing [11], [12], [13], [14], [18], [19], [23], [27], [28].”
InfluentialMalhotra, A., & Gupta, S. K. (2025) · IEEE Transactions on Very Large Scale Integration (VLSI) Systems · doi:10.1109/tvlsi.2025.3585043 · Cited by 1
“However, such techniques may need sizeable overheads, with energy overheads ranging from 24% to 112% in [25].”
InfluentialYet another reliability assessment method for RRAM-based dot-product engine
Mahmoudi, A., Veronesi, A., Grothe, P., Wen, J., Meyer, R., Ulbricht, M., Buchty, R., Bereković, M., & Mulhem, S. (2025) · Microelectronics Reliability · doi:10.1016/j.microrel.2025.115938
Guo, L., Zhu, Z., Lin, Q., Xie, Y., Yang, H., Fu, W., & Wang, Y. (2025) · doi:10.1109/iccad66269.2025.11240851
“The non-ideal effects of NVM devices mainly include conductance reading variation [21], programming error [18], Stuck-At-Fault (SAF) [28], and thermal noise [29].”
Self-citationStaudigl, F., & Leupers, R. (2026) · Synthesis lectures on engineering, science, and technology · doi:10.1007/978-3-032-09586-2_3
IR-Aware Weight Remapping Considering Thermal Effect and Stuck-at Faults in RRAM Crossbar Array
Chang, S.-H., He, Y.-L., & Liu, C. J. (2025) · IEEE Asia Pacific Conference on Circuits and Systems (APCCAS) · doi:10.1109/apccas67402.2025.11377170
“[10] proposes different redundancy schemes and a mapping algorithm to convert matrix parameters into RRAM conductance and tolerate SAFs by fully exploring the mapping space.”
Vourkas, I. (2026) · International Journal of Parallel Emergent and Distributed Systems · doi:10.1080/17445760.2026.2636490
Hybrid Memristor-CMOS System: Circuit Design Solutions for Control and Data Processing
Tokarev, A. A., & Khorin, I. A. (2025) · Russian Microelectronics · doi:10.1134/s1063739725601183
S, S. K., Shashidhara, H. R., & S, D. M. (2026) · BioNanoScience · doi:10.1007/s12668-026-02516-6
Fault Tolerance in Hardware Spiking Neural Networks
El-Sayed, S. A. (2021) · theses.fr (ABES) · doi:10.70675/51158377zc7caz47e3zbb49z616c633eebf5 · Cited by 2
Functional safety and reliability of neuromorphic computing systems
Spyrou, T. (2023) · theses.fr (ABES) · doi:10.70675/76481b77z6471z475cz9788z94892a1c1779
Kazerooni-Zand, R., Afzali‐Kusha, A., & Kamal, M. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133773
Fault-tolerance Mapping of Spiking Neural Networks to RRAM-based Neuromorphic Hardware
Xiong, Y., Xiao, C., Yang, Z., (6656), L. W., & Zhao, M. (2026) · Design, Automation, and Test in Europe · doi:10.23919/date69613.2026.11539562
“In the context of RRAM crossbars, to mitigate the impact of SAFs, a hardware approach introduces redundant rows to recover computation results, at the cost of higher area and power consumption [18]–[20].”
Lin, J., Wu, W., Wang, M., Kang, W., & Han, G. (2026) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2026.3700723
“In [19] In [21], Xia et al. leveraged tunability between positive and negative arrays to mutually compensate for faults without extra hardware.”
Li, R., Li, J., Xu, C., Yao, P., Wu, D., Jie, L., He, Y., Qin, Q., Pan, S., Zhang, Q., et al. (2026) · IEEE Electron Device Letters · doi:10.1109/led.2026.3707870
“On the other hand, stuck-at-low-resistance (SALR) faults induce excessive read currents that overwhelm the column-ADC dynamic range, rendering a ff ected channels unusable and degrading matrix-vector multiplication (MVM) accuracy [7].”
Fault Resilience in Memristor Crossbar: Sensitivity-Driven Mapping for Neural Accelerators
Sahil, Rathor, K. K., Raj, U., Sethi, B., Thangkhiew, P. L., & Yadav, D. N. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-27120-4_3
PVTVAD: PVT-Variation-Aware Fault Diagnosis in ReRAM-Based CAM Arrays
Hezayyin, H. G., Mayahinia, M., & Tahoori, M. B. (2026) · IEEE Transactions on Device and Materials Reliability · doi:10.1109/tdmr.2026.3732979
“Identifying the exact location of defective cells can significantly benefit fault tolerance and reliability [37], [38], Fig.”
Metadata
- Authors
- Xia, L., Huangfu, W., Tang, T., Yin, X., Chakrabarty, K., Xie, Y., Wang, Y., & Yang, H.
- Affiliations
- Tsinghua University (CN)
- University of California, Santa Barbara (US)
- Duke University (US)
- Venue
- IEEE Journal on Emerging and Selected Topics in Circuits and Systems
- Published
- 2018-03
- Volume
- 8
- Issue
- 1
- Pages
- 102-115
- ISSN
- 2156-3357 (ISSN-L)
- 2156-3365
- OpenAlex
- W2768104155
- Cited by
- 177
- References
- 31
- Citations by year
- 2026: 17 · 2025: 23 · 2024: 25 · 2023: 18 · 2022: 33 · 2021: 20 · 2020: 23 · 2019: 13 · 2018: 5
- FWCI
- 4.66
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Journal on Emerging and Selected Topics in Circuits and Systems (publishedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- Funders
- National Key Research and Development Program of China (2017YFA0207600)
- National Natural Science Foundation of China (61373026, 61622403, 61621091)
- Joint Fund of Equipment Pre-Research and Ministry of Education (6141A02022608)
- U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research (DE-SC0013553)
- NSF (1461698, 1500848)
- Qualcomm
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Computer Science › Hardware and Architecture › VLSI and Analog Circuit Testing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Ferroelectric and Negative Capacitance Devices
- Keywords
- stuck-at faults, fault tolerance, resistive random access memory, redundancy schemes, in-memory computing, energy overhead, MNIST recognition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.