R.K. Bishnoi
Please Note
54 records found
1
Compute-in-Memory (CiM) architectures based on spin-transfer torque magnetic random-access memory (STTMRAM) are increasingly used to accelerate deep neural networks due to their high density and energy efficiency. However, the security of MRAM-based CiM against side-channel analysis attacks, particularly power analysis attacks, has been little investigated in the literature. To address this gap, we present a systematic vulnerability analysis of MRAM-based CiM accelerators against correlation power analysis (CPA) attacks, focusing on the impact of operating parameters such as temperature and read voltage on attack success. Our results show that CPA attacks are more effective at higher read voltages, while lower temperatures reduce the number of traces required for successful data extraction. Our findings highlight the need to consider these vulnerabilities when selecting design parameters such as read voltage. Moreover, the strong dependence on temperature reveals an attacker-controlled dimension, emphasizing the need for temperature-aware security countermeasures in MRAM-based CiM systems.
Analog Compute-in-Memory (CIM), leveraging non-volatile memristive devices to perform in-place computations in the analog domain, holds great potential to efficiently accelerate vector-matrix multiplications (VMM) and realize AI (Artificial Intelligence) at the edge. However, the data converters in such architectures often trade-off accuracy for high energy and area overheads, practically limiting the benefits of CIM. In this work, we present SABCIM, an array-periphery co-design approach for CIM that enables accurate computation as well as digitization of analog VMM outputs with high energy efficiency and competitive area overhead. By leveraging complementary input activations and data storage, each crossbar column generates differential analog output corresponding to the vector-vector multiplication (VVM) result, while inherently addressing underlying non-idealities. This is digitized using a compact, dual-ramp voltage-to-time converter (VTC)-based analog-to-digital converter (ADC). Benchmark results indicate that our work achieves up to 19.6 × higher energy efficiency compared to state-of-the-art (SOTA), while maintaining comparable accuracies.
Diabetic retinopathy (DR) refers to permanent vision loss resulting from high glucose and blood pressure. As it is a major cause of blindness worldwide, regular screening for DR is crucial to its timely treatment. Neural network-based classifiers offer significant potential to automate this process. Such classifiers must ensure consistent performance throughout development and deployment, provide explanatory feedback for predictions, and support usability for widespread adoption. Energy-efficient deployment on edge devices is also essential for global accessibility. In this chapter, we present a reliable and energy-efficient hardware for DR screening on edge devices. We first develop a DR classification model using custom training data that incorporates diverse image quality and image sources along with improved class balance. This enables effective handling of both on-field variations in retinal images and minority DR classes, enhancing post-deployment reliability. We then present a pseudo-binary classification scheme to further improve the model performance and provide supplementary information about the predictions. Additionally, we introduce an energy-efficient hardware design for our model using memristor-based computation-in-memory for deployment on edge devices.
Multi-Partner Project
Efficient Deep Learning Platforms for Next-Generation Embedded Edge-AI Systems
Resistive random-access memory (RRAM)-based computation-in-memory (CIM) architectures offer a promising solution to meet the stringent energy efficiency demands of executing artificial intelligence (AI) algorithms directly on edge devices. However, these architectures suffer from the read-disturb problem, which can lead to accumulated computational errors over time. To maintain the required level of computational accuracy, conventional approaches rely on a static reprogramming process after a predefined number of read cycles, necessitating large counters and resulting in inefficiencies. This paper presents experimental results using real RRAM devices to analyze the read-disturb effect and builds on these insights to propose a circuit-level detection methodology for real-time monitoring of conductance drifts. The proposed method initiates reprogramming only when the device drift exceeds a defined threshold and reprogramming is actually needed. Additionally, an analytical method is developed to determine the minimum conductance state ratio needed to meet reliable detection criteria. Based on this foundation, the proposed detection technique is further optimized for dynamic identification of read-disturb effects. Experiment-augmented SPICE simulation results, using a calibrated model implemented in TSMC 40 nm CMOS technology, validate the functionality and effectiveness of the proposed detection approach. These results demonstrate its potential to improve both the reliability and efficiency of RRAM-based CIM architectures that provide up to a 4x improvement in energy-efficiency compared to traditional periodic reprogramming methods.
Multi-Partner Project
Scalable, Ferroelectric-based Accelerators for Energy Efficient Edge AI (Ferro4EdgeAI)
The Computing-In-Memory (CIM) paradigm offers a promising solution to the memory-wall bottleneck that limits conventional Von Neumann architectures. By performing data processing at the same physical location where the data are stored, CIM-based architectures minimize costly data movement and drastically improve energy efficiency. When implemented with Ferroelectric Field Effect Transistors (FeFETs), additional advantages from the non-volatility, fast switching, and low operating voltage of FeFETs are added. However, the widespread adoption of FeFETs is limited by their poor endurance, which is overcome by a Back End of the Line (BEoL) integration of FeFET-2, where a ferroelectric capacitor (FeCAP) is wired to the gate of a CMOS transistor providing high endurance compatible with low-power edge applications. These properties enable dense, low-power, and high-speed matrix operations essential for AI workloads. As a result, FeFET-2-based CIM accelerators offer a promising solution for energy-efficient, high-performance AI at the edge. The Ferro4EdgeAI project aims to develop an ultra low-power, scalable edge accelerator for AI, targeting a significant gain in energy efficiency with respect to state-of-the-art AI hardware accelerators. To attain this, our project focuses on innovation all along the value chain from materials, physic concepts, device architecture, integration technologies, and accelerators in a holistic design space exploration approach.
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%.
Approximately one-third of individuals with chronic epilepsy, a condition resulting from uncontrolled brain activity, do not respond to medication. Animal models are widely used to investigate the mechanism underlying epilepsy, so better drug treatments can be developed for this disease. In such studies, epileptiform activity, assessed by EEG recordings, can be used as a marker for the development of the disease. However, the analysis of EEG recordings is typically done manually, which is time-consuming, subject to observer bias, error-prone, and lacks consistency and efficiency. In this paper, we develop a novel automated methodology for detecting and classifying epileptiform activity, which is tested using the intrahippocampal kainic acid (IHKA) mouse model, a representation of human temporal lobe epilepsy. For that, EEG/LFP recordings are obtained from biological experiments using the IHKA mouse model for data acquisition. We use a spike detection method that combines an improved version of the nonlinear energy operator (NEO) with the automatic NEO thresholding (ANT) algorithm. The proposed method is implemented in Python as an automated and time-efficient algorithm, given its adaptability to different spike and epileptiform event criteria, making it suitable for use in preclinical and potentially future clinical studies. Using our proposed methodology, we achieve a 93.1% accuracy in detecting epileptiform events and a 95.8% accuracy in classification. Moreover, the time for analysis of EEG recordings was reduced by 98.8% compared to manual analysis. Additionally, to demonstrate the potential of the algorithm for brain–machine interfaces (BMI) applications, we develop a hardware architecture and implement it using both an application-specific integrated circuit (ASIC) and a field programmable gate array (FPGA). The FPGA shows the feasibility of near real-time implementation, and for our ASIC implementation, we achieve a post-layout area of 9114 µm2 with a dynamic power consumption of 16.09 μW using TSMC 40 nm technology.
C3CIM
Constant Column Current Memristor-Based Computation-in-Memory Micro-Architecture
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.
Real-time edge artificial intelligence (AI) demands memory elements that are not only energy-efficient and multifunctional, but also compact, tunable, and integrable with flexible substrates. Planar memory architecture offers distinct advantages for neuromorphic computing, including surface accessibility, facile fabrication, and seamless integration with flexible substrates, making it ideal for next-generation synaptic hardware. Traditional metal oxide-based memristors often fail to meet all these requirements simultaneously due to their rigid architecture and limited material versatility. Herein, we present a planar Ti3C2Tx-MXene-based memristor (PMX-memristor) fabricated on a flexible cyclic olefin copolymer (COC) substrate, constituting the first fully planar MXene-based resistive device reported to date. The planar architecture exposes the active MXene channel, which enables direct surface inspection and functionalization while delivering robust analog switching. By tuning the voltage amplitude, the device operates in two modes: (i) a volatile regime based on valence change dynamics with transient conductance states, and (ii) a non-volatile regime driven by voltage-induced Ti→TiOx transformation, supporting eight distinct resistance levels. Detailed EDX and XPS analyses, performed before and after electrical stress, confirm the voltage-induced oxidation pathway that underpins this dual-mode behavior. The memristor’s eight-level precision enables compact 9-bit weight encoding using 3×3-bit multi-level cells in crossbar arrays, reducing area and energy compared to binary implementations. We demonstrate end-to-end deployment of these devices in spiking neural networks for real-time classification of neuromorphic vision datasets, showcasing high-performance, task-relevant learning capabilities on benchmarks such as N-MNIST and DVS-Gesture. These results underscore the potential of the designed PMX-memristor for voltage-controlled, neuromorphic edge computing and provide direct surface accessibility for functionalization and potential bio-interfacing for next-generation smart wearables.
Recent advances in Resistive RAM (RRAM) based Computation-In-Memory (CIM) architectures highlight significant potential for accelerating data-intensive computing tasks. However, non-idealities in RRAM devices, such as variability, result in small sensing margins that can significantly affect the computational efficiency. This issue becomes even more pronounced when dealing with complex multi-operand logic operations. This paper introduces a circuit-level scheme for CIM-based multi-operand XOR logic operations, leveraging a Voltage-To-Time converter (VTC) to perform multi-phased XORs in a single clock cycle. In this approach, we exploit bitline capacitances for voltage-based sensing during computation, generating an output voltage that is linearly proportional to the operand values. This voltage is then converted into the desired logic output using the VTC design. Furthermore, low-power techniques are employed in the deployment of sense amplifiers, such as regulating power consumption during operation and disabling the amplifiers once the decision is made. Simulation results for a post-layout extracted 512x512 (256Kb) RRAM-based CIM array show that up to 16-operand XOR operation can be accurately and reliably performed as opposed to a maximum of three operands supported by state-of-the-art solutions, while offering up to 49× better figure-of-merit combining energy-efficiency and throughput.
European Test Symposium Teams
An Anniversary Snapshot
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.