Addressing non-idealities in Resistive Random Access Memories (RRAMs) is crucial for their successful commercialization. For example, the inherent resistance drift that occurs during consecutive read operations can induce Read Disturb Faults (RDF), leading to functional errors. This paper analyzes and characterizes the resistance drift and the RDF based on data measurements and presents a physics-based RRAM compact model that incorporates these non-idealities. Additionally, an in-field mitigation scheme is proposed, leveraging bidirectional read operations to balance the resistance. The scheme is implemented and validated through circuit simulations, both for RRAM used as memory and for RRAM-based computation-in-memory microarchitectures for deep neural networks. The results demonstrate that RRAM without any mitigation scheme can start failing after 8,000 consecutive reads, while our mitigation scheme ensures that the memory remains functional even after 10⁶ consecutive reads. Furthermore, the results indicate that using the MNIST dataset as a case study, the accuracy can drop significantly from 86% to as low as 12.5% without any mitigation scheme. In contrast, the proposed mitigation scheme improves this accuracy up to 84.2%.

The goal of the NEUROKIT2E project is to create an open-source Deep Learning framework for edge and embedded AI built around an established European value chain. This framework, called AIDGE, supports a wide range of application areas that operate independently and serve a global user community. It provides easy and fast full-stack solutions from Neural Network design and optimization to AI application development all the way down to hardware implementations while enabling code generation for application-specific targets. This platform provides flexibility for academic users in the AI domain to explore and innovate while allowing them the possibility to prototype systems, ensuring their work aligns well with industrial needs. This paper presents the results and achievements of the first part of this three-year project, along with its roadmap and expected outcomes.

In recent years, Spin Waves (SWs) have emerged as a promising avenue for beyond-CMOS computing, offering potential advantages in terms of energy efficiency, scalability, and opening avenues towards novel computation paradigms. Until now, SW interference-based gates, for example, the 3 input majority gate (MAJ3), have been proposed and experimentally demonstrated, and an alternative computing paradigm, which relies on SW phase manipulation instead of SW interference has been proposed. However, state-of-the-art SW-based devices suffer from challenges that hinder the realization of larger-scale SW circuits. In this paper, we explore a different computing avenue that relies on Boolean algebra and introduce a SW Switch that makes use of the Voltage Controlled Magnetic Anisotropy (VCMA) effect to allow/block SW propagation. We introduce the device concept, verify its functionality by means of micromagnetic simulations, and perform a circuit-level analysis on EPFL Combinational Benchmarking Suite circuits. As no SW generation and SW read transducers energy consumption experimental data is available we evaluate their upper bound values for which SW implementations can outperform CMOS counterparts. We implement the circuits by means of state-of-the-art SW technologies and the proposed method, compute the upper bound values, and our results indicate that on average the proposal is increasing the upper bound by about 1.2 ×. Subsequently, we consider SW read transducers energy consumption estimates reported in the literature and argue that while they seem appropriate for evaluating SW Boolean switching gates they have to be multiplied with a factor m>1 to capture the extra complexity of generating the output value for SW interference and Phase manipulation SW gates. Our evaluations indicate that the SW Switch-based approach reduces the energy consumption by 1.2504 × 1.4973 × 1.7443 ×, and 1.9912 ×, when compared to the interference approach, and by 1.2478 ×, 1.4947 ×, 1.7416 ×, and 1.9886 ×, when compared to the phase shifting approach, for m=1.25,1.5,1.75,2, respectively. We finally highlight system level advantages of our proposal and conclude that SW Boolean switching gates are opening the most promising avenue towards energy effective SW computing.

Neuromorphic computing offers a promising solution for realizing energy-efficient and compact Artificial Intelligence (AI) systems. Implemented with Spiking Neural Networks (SNNs), neuromorphic systems can benefit from SNN characteristics, such as event-driven computation, event sparsity, biological plausibility, etc., to achieve high performance and energy efficiency, an aspect vital for the realization of AI at the edge. Although SNNs are biology-inspired structures, their use in mission- and safety-critical applications raises multiple concerns around the trustworthiness of neuromorphic hardware due to various intrinsic and extrinsic reliability and security issues. Hence, adequately studying the dependability of SNNs and neuromorphic hardware accelerators becomes of utmost importance, in order to expose and harden against potential vulnerabilities, so that a reliable and secure operation is ensured. This paper presents an analysis of the dependability and trustworthiness aspects of SNNs and neuromorphic hardware. It outlines potential mitigation and countermeasure strategies to improve the reliability, testability, and security aspects of SNN hardware and ensure its trustworthy deployment in critical application domains.

Timely identification of cardiac arrhythmia (abnormal heartbeats) is vital for early diagnosis of cardiovascular diseases. Wearable healthcare devices facilitate this process by recording heartbeats through electrocardiogram (ECG) signals and using AI-driven hardware to classify them into arrhythmia classes. Spiking neural networks (SNNs) are well-suited for such hardware as they consume low energy due to event-driven operation. However, their energy-efficiency and accuracy are constrained by encoding methods that translate real-valued ECG data into spikes. In this paper, we present an SNN-based ECG classification architecture featuring a new adaptive multi-threshold spike encoding scheme. This scheme adjusts encoding window and granularity based on the importance of ECG data samples, to capture essential information with fewer spikes. We develop a high-accuracy SNN model for such spike representation, by proposing a technique specifically tailored to our encoding. We design a hardware architecture for this model, which incorporates optimized layer post-processing for energy-efficient data-flow and employs fixed-point quantization for computational efficiency. Moreover, we integrate this architecture with our encoding scheme into a system-on-chip implementation using TSMC 40 nm technology. Our approach provides up to 5.1x energy-efficiency compared to state-of-the-art SNN-based ECG classifiers, with high accuracy.

Structural testing has been very successful in the VLSI manufacturing process to screen out faulty devices and provide high outgoing product quality. However, recent reported data show that existing solutions are not good enough for advanced technology nodes and emerging device technologies. This paper discusses a new manufacturing test approach called DeviceAware Test (DAT), applies it to different flavors of emerging devices, and its potential to be used beyond just manufacturing test.

Advancements in Artificial Intelligence (AI) and Internet-of-Things (IoT) have increased demand for edge AI, but deployment on traditional AI accelerators, like GPUs and TPUs, using von Neumann architecture, suffer from inefficiencies due to separate memory and compute units. Computation-in-Memory (CIM), utilizing non-volatile memristor devices to leverage analog computing principles and perform in-place computations, holds great potential in improving computational efficiency by eliminating frequent data movement. However, standard implementation of CIM faces several challenges, primarily high power consumption and subsequently induced nonlinearity, debating its viability for edge devices. In this paper, we propose C3CIM, a novel memristor-based CIM micro-architecture, featuring a new bit-cell and array design, targeting efficient implementation of Neural Networks (NN). Our architecture uses a constant current source to perform Multiply-and-Accumulate (MAC) operations with a very low computation current (10 to 100 nA), thereby significantly enhancing power efficiency. We adapted C3CIM for Spiking Neural Networks (SNN) and developed a prototype using TSMC 40nm CMOS node for on-silicon validation. Furthermore, our micro-architecture was benchmarked using two SNN models based on N-MNIST and IBM-Gesture datasets, for comparison against current state-of-the-art (SOTA). Results show up to 35x reduction in power along with 6.7x saving in energy compared to SOTA, demonstrating promising potential of this work for edge AI applications.

Computational-neuroscience research is increasingly in need of larger, biophysically realistic brain models. These analog-in-nature models build upon the Hodgkin-Huxley (HH) formalism and are run on digital, high-performance computing systems making simulation very computationally expensive. In circuit form, these models are theoretically suitable for efficient analog implementation. However, the ion-channel components –predominantly, sodium and potassium– are nonlinear, time-varying resistors, lacking an efficient implementation. Chua et al. proved that these ion-channel models are in fact memristors –devices with a conductance as a function of applied-voltage history– claiming that “memristors are the right stuff for building brains”. However, the kind of actual memristor implementation that is the right one for building brains is not defined. In this article, the device class and characteristics of such memristors are defined and existing memristive implementations of HH-like designs are then reviewed. Surprisingly, although often misclassified as such, no physical implementation currently exists that replicates the original HH equations faithfully or efficiently. Having put forward the desired memristor properties, a design guide for screening suitable memristor designs is then proposed. Screening the existing literature reveals that suitable devices likely already exist for potassium ion-channel emulation, while none exists for sodium; this calls for further investigation of higher-order, voltage-controlled and volatile memristors.

Full-System (FS) simulation is essential for performance evaluation of complete systems that execute complex applications on a complete software stack consisting of an operating system and user applications. Nevertheless, they require careful fine-tuning against real hardware to obtain reliable performance statistics, which can become tedious, error-prone, and time-consuming with typical trial-and-error approaches. We propose a novel, streamlined, component-level calibration methodology to address these shortcomings to validate FS simulation models. Our methodology greatly accelerates the validation process without sacrificing accuracy. It is Instruction Set Architecture (ISA)-agnostic, and can tackle hardware specifications at different levels of detail. We demonstrate its effectiveness by validating FS models against both open-hardware and IP-protected (closed hardware) RISC-V silicon, achieving a mean error of 19%-23% for the SPEC CPU2017 suite in the two cases. We introduce the first open-source RISC-V-based FS-validated simulation models with a complete and replicable methodology.

In recent years, Spin Waves (SWs) have emerged as a promising CMOS alternative technology, and SW interference-based majority gates have been proposed and experimentally realized. In this paper, we pursue a different computation avenue and introduce a SW device able to evaluate 2×2 2D convolution, which is a fundamental element for the implementation of Convolutional Neural Networks (CNNs). Assuming that the window pixels are P = [p₁, p₂; p₃, p₄] and the kernel is K = [k₁, k₂; k₃, k₄] we introduce a device which evaluates the convolution result Σ_{i = 1}⁴ p_i k_i within the SW domain by leveraging SWs inherent mechanisms, i.e., information encoding in SW amplitude and phase, SW amplitude decay due to Gilbert damping, SW interference. After introducing the SW device structure we demonstrate its proper behaviour by means of micromagnetic simulations. We also present power consumption, area, and delay estimates and argue that due to the fact that our proposal does not rely on standard adders and multipliers, it can substantially outperform traditional CMOS-based convolution implementations.

SRAM Physical Unclonable Functions (PUFs) serve as security primitives and can be used to generate random and unique identifiers, which makes their reliability crucial. The reliability is affected by aging and in particular Bias Temperature Instability (BTI), which in turn affects the PUF responses over time typically measured by the Hamming distance (HD). In this work, we model the BTI impact on SRAM PUF reliability for 14 nm FinFET technology and evaluate the reliability of SRAM PUFs using both simulation and silicon measurements. Additionally, we explore the effectiveness of an anti-aging technique on SRAM PUF reliability. Our simulation model and results (which include process variation and circuit noise) are validated with silicon measurements. From them we conclude the following: 1) there exists a direct correlation between BTI and the Hamming distance of an SRAM PUF, where its reliability decreases with 6% over a 6-month period due to aging, and 2) applying anti-aging patterns improves the Hamming distance and hence the reliability with 3% over a 6-month period.

The development of Ferroelectric Field-Effect Transistor (FeFET) manufacturing requires high-quality test solutions, yet research on FeFET testing is still in a nascent stage. To generate a dedicated test method for FeFETs, it is critical to have a deep understanding of manufacturing defects and accurately model them. In this work, we introduce the unique defect, Anomalous Charge Trapping (ACT), in FeFETs. The ACT-defective FeFET is characterized, and the physical mechanism of the defect is explained. Then, we apply the Deviceaware Test (DAT) method to design a specific ACT-defective FeFET model, which includes the physical impact of the defect on the electrical parameters of defect-free models, and calibrate the model with measurement data. Fault modeling is performed based on circuit-level simulations, and dedicated test solutions are proposed.

While Resistive RRAM (RRAM) provides appealing features for artificial neural networks (NN) such as low power operation and high density, its conductance variation can pose significant challenges for synaptic weight storage. This paper reports an experimental evaluation of the conductance variations of manufactured RRAMs memory cells at the memory array level. Variability is evaluated with respect to the RRAM low resistance state (LRS) and high resistance state (HRS) conductance ratio. This ratio is selected as the parameter of interest as it guarantees the proper operation of the RRAM: the larger the ratio, the more reliable and robust the RRAM cell is in storing and retrieving data. The measurement results show that conductance ratio is significantly influenced by variability. Using these findings, the performance of an artificial neural network that uses individual RRAM cells for synaptic weight storage is evaluated in relation to conductance variability. It is shown that RRAM variability can heavily affect the network behavior, resulting in a substantial decrease in the classification accuracy during inference.

Edge AI accelerators have revolutionized intelligent information processing, enabling applications, such as self-driving cars and low-power IoT devices. Design efforts prioritize computational power and energy efficiency. Nevertheless, testability is also critical for in-field, reliable operation, especially for novel architectures such as memristive, analog Computation-in-Memory (CIM) cores. These structures combine emerging Resistive Random Access Memory (RRAM) with CMOS peripherals to efficiently implement vector-matrix-multiplication (VMM) operations for inference. Current research on AI Accelerator testing relies on functional test patterns, derived from abstract and unrealistic fault models. This paper presents a novel structural testing methodology for CIM VMM circuits. The methodology utilizes device-level defect models and defines new fault models for CIM VMM. The resulting test patterns are optimized to maximize defect coverage and minimize test time, since they require only a single write operation per victim cell.

The IEEE European Test Symposium (ETS) has been facilitating progress in electronic systems testing since its launch in 1996. On the occasion of its 30th anniversary, this collaborative paper gathers sections by 21 ETS teams to outline their influential ideas and milestones. Each team's section highlights historical perspective, current research, frameworks and projects as well as forward-looking research agendas in the area of electronic-based circuits and systems testing, reliability, safety, security and validation. This anniversary summary documents how research of various ETS teams, exemplifying the test community, has been evolving and transitioning from concepts to practical standards and Electronic Design Automation (EDA) tools and flows. This legacy is a strong base to drive the next generation of advances in electronic systems testing.

Due to the immature manufacturing process, Resistive Random Access Memories (RRAMs) are prone to exhibit new failure mechanisms and faults, which should be efficiently detected for high-volume production. Those unique faults are hard to detect but require specific Design-for-Test (DfT) circuit design. This paper proposes a DfT based on a parallel-reference write circuit that can detect all RRAM array faults during diagnosis, production testing, and its application in the field.

Computation-in-memory (CIM) using memristors can facilitate data processing within the memory itself, leading to superior energy efficiency than conventional von-Neumann architecture. This makes CIM well-suited for data-intensive applications like neural networks. However, a large number of read operations can induce an undesired resistance change in the memristor, known as read-disturb. As memristor resistances represent the neural network weights in CIM hardware, read-disturb causes an unintended change in the network’s weights that leads to poor accuracy. In this paper, we propose a methodology for read-disturb detection and mitigation in CIM-based neural networks. We first analyze the key insights regarding the read-disturb phenomenon. We then introduce a mechanism to dynamically detect the occurrence of read-disturb in CIM-based neural networks. In response to such detections, we develop a method that adapts the sensing conditions of CIM hardware to provide error-free operation even in the presence of read-disturb. Simulation results show that our proposed methodology achieves up to 2× accuracy and up to 2× correct operations per unit energy compared to conventional CIM architectures.

Computation-In-Memory (CIM) using emerging memristive devices offers a promising solution to implementing energy efficient Artificial Intelligence (AI) hardware accelerators. Though, the non-idealities characterizing memristive devices cause a negative impact on the performance of CIM-based micro-architectures. We propose a two-step fault tolerance strategy to address the impact of Stack-at Faults (SAFs) and conductance variation of RRAM crossbar arrays, composed of a fault tolerant activation function and a retraining method. Evaluation results on Binary Neural Network (BNNs) architectures trained with MNIST, Fashion-MNIST, and CIFAR-10 datasets demonstrate that the proposed techniques can restore the classification accuracy by up to 20%, 40% and 80%, respectively.

Binary Neural Networks (BNNs) have demonstrated significant advantages in reducing computation and memory costs, all while maintaining acceptable accuracy on various image detection tasks. Thus, BNNs have the potential to support practical cognitive tasks on resource-constrained platforms, such as edge computing devices. To realize this, SRAM-based digital Computation-in-Memory (CIM) has gained growing attention as it overcomes the analog CIM architecture bottlenecks such as limited computing accuracy due to process variation, non-linearity, power and area-hungry Analog-to-Digital Converters (ADCs), etc. However, digital CIM architectures are highly dominated by power-hungry adder-trees, which can nullify the benefits of SRAM-based digital CIM. To address this issue, this paper proposes an adder free SRAM-based digital CIM, AFSRAM-CIM, for BNN acceleration. The proposed CIM architecture utilizes a multi-functional 10-T SRAM cell-based crossbar array and a new energy-efficient approach to perform the popcount operation. Simulation results using the MNIST dataset show that the proposed architecture maintains the state-of-the-art inference accuracy of 99.21% with only 11.86 fJ energy per operation. Moreover, AFSRAM-CIM achieves over 3× energy and ≈17× area savings when compared to the conventional digital CIM approaches.