Search

Ternary content addressable memories (TCAMs) are useful for certain computing tasks since they allow us to compare a search query with a whole dataset stored in the memory array. They can also unlock unique advantages for cryogenic applications like quantum computing, high-performance computing, and space exploration by improving speed and energy efficiency through parallel searching. This paper explores the design and implementation of a cryogenic ternary content addressable memory based on ferroelectric superconducting quantum interference devices (FeSQUIDs). The use of FeSQUID for designing the TCAM provides several unique advantages. First, we can get binary decisions (zero or non-zero voltage) for matching and mismatching conditions without using any peripheral circuitry. Moreover, the proposed TCAM needs ultra-low energy (1.36 aJ and 26.5 aJ average energy consumption for 1-bit binary and ternary search, respectively), thanks to the use of energy-efficient SQUIDs. Finally, we show the efficiency of FeSQUID through the brain-inspired application of Hyperdimensional Computing (HDC). Here, the FeSQUID-based TCAM implements the associative memory to support the highly parallel search needed in the inference step. We estimate an energy consumption of 89.4 fJ per vector comparison using a vector size of 10,000 bits. We also compare the FeSQUID-based TCAM array with the 5nm FinFET-based cryogenic SRAM-based TCAM array and observe that the proposed FeSQUID-based TCAM array consumes over one order of magnitude lower energy while performing the same task., Comment: 6 figures

Compute-in-memory (CiM) is a promising solution for addressing the challenges of artificial intelligence (AI) and the Internet of Things (IoT) hardware such as 'memory wall' issue. Specifically, CiM employing nonvolatile memory (NVM) devices in a crossbar structure can efficiently accelerate multiply-accumulation (MAC) computation, a crucial operator in neural networks among various AI models. Low power CiM designs are thus highly desired for further energy efficiency optimization on AI models. Ferroelectric FET (FeFET), an emerging device, is attractive for building ultra-low power CiM array due to CMOS compatibility, high ION/IOFF ratio, etc. Recent studies have explored FeFET based CiM designs that achieve low power consumption. Nevertheless, subthreshold-operated FeFETs, where the operating voltages are scaled down to the subthreshold region to reduce array power consumption, are particularly vulnerable to temperature drift, leading to accuracy degradation. To address this challenge, we propose a temperature-resilient 2T-1FeFET CiM design that performs MAC operations reliably at subthreahold region from 0 to 85 Celsius, while consuming ultra-low power. Benchmarked against the VGG neural network architecture running the CIFAR-10 dataset, the proposed 2T-1FeFET CiM design achieves 89.45% CIFAR-10 test accuracy. Compared to previous FeFET based CiM designs, it exhibits immunity to temperature drift at an 8-bit wordlength scale, and achieves better energy efficiency with 2866 TOPS/W., Comment: 6 pages, 9 figures, 2 tables. Accepted by Design Automation and Test in Europe (DATE) 2024

One of the major barriers that CMOS devices face at nanometer scale is increasing parameter variation due to manufacturing imperfections. Process variations severely inhibit the reliable operation of circuits, as the operational frequency at the nominal process corner is insufficient to suppress timing violations across the entire variability spectrum. To avoid variability-induced timing errors, previous efforts impose pessimistic and performance-degrading timing guardbands atop the operating frequency. In this work, we employ approximate computing principles and propose a circuit-agnostic automated framework for generating variability-aware approximate circuits that eliminate process-induced timing guardbands. Variability effects are accurately portrayed with the creation of variation-aware standard cell libraries, fully compatible with standard EDA tools. The underlying transistors are fully calibrated against industrial measurements from Intel 14nm FinFET in which both electrical characteristics of transistors and variability effects are accurately captured. In this work, we explore the design space of approximate variability-aware designs to automatically generate circuits of reduced variability and increased performance without the need for timing guardbands. Experimental results show that by introducing negligible functional error of merely $5.3\times 10^{-3}$, our variability-aware approximate circuits can be reliably operated under process variations without sacrificing the application performance., Comment: 13 pages, 14 figures

Using accelerators based on analog computing is an efficient way to process the immensely large workloads in Neural Networks (NNs). One example of an analog computing scheme for NNs is Integrate-and-Fire (IF) Spiking Neural Networks (SNNs). However, to achieve high inference accuracy in IF-SNNs, the analog hardware needs to represent current-based multiply-accumulate (MAC) levels as spike times, for which a large membrane capacitor needs to be charged for a certain amount of time. A large capacitor results in high energy use, considerable area cost, and long latency, constituting one of the major bottlenecks in analog IF-SNN implementations. In this work, we propose a HW/SW Codesign method, called CapMin, for capacitor size minimization in analog computing IF-SNNs. CapMin minimizes the capacitor size by reducing the number of spike times needed for accurate operation of the HW, based on the absolute frequency of MAC level occurrences in the SW. To increase the operation of IF-SNNs to current variation, we propose the method CapMin-V, which trades capacitor size for protection based on the reduced capacitor size found in CapMin. In our experiments, CapMin achieves more than a 14$\times$ reduction in capacitor size over the state of the art, while CapMin-V achieves increased variation tolerance in the IF-SNN operation, requiring only a small increase in capacitor size., Comment: 9 pages, 9 figures

Single-port ferroelectric FET (FeFET) that performs write and read operations on the same electrical gate prevents its wide application in tunable analog electronics and suffers from read disturb, especially to the high-threshold voltage (VTH) state as the retention energy barrier is reduced by the applied read bias. To address both issues, we propose to adopt a read disturb-free dual-port FeFET where write is performed on the gate featuring a ferroelectric layer and the read is done on a separate gate featuring a non-ferroelectric dielectric. Combining the unique structure and the separate read gate, read disturb is eliminated as the applied field is aligned with polarization in the high-VTH state and thus improving its stability, while it is screened by the channel inversion charge and exerts no negative impact on the low-VTH state stability. Comprehensive theoretical and experimental validation have been performed on fully-depleted silicon-on-insulator (FDSOI) FeFETs integrated on 22 nm platform, which intrinsically has dual ports with its buried oxide layer acting as the non-ferroelectric dielectric. Novel applications that can exploit the proposed dual-port FeFET are proposed and experimentally demonstrated for the first time, including FPGA that harnesses its read disturb-free feature and tunable analog electronics (e.g., frequency tunable ring oscillator in this work) leveraging the separated write and read paths., Comment: 32 pages

Ternary content addressable memory (TCAM), widely used in network routers and high-associativity caches, is gaining popularity in machine learning and data-analytic applications. Ferroelectric FETs (FeFETs) are a promising candidate for implementing TCAM owing to their high ON/OFF ratio, non-volatility, and CMOS compatibility. However, conventional single-gate FeFETs (SG-FeFETs) suffer from relatively high write voltage, low endurance, potential read disturbance, and face scaling challenges. Recently, a double-gate FeFET (DG-FeFET) has been proposed and outperforms SG-FeFETs in many aspects. This paper investigates TCAM design challenges specific to DG-FeFETs and introduces a novel 1.5T1Fe TCAM design based on DG-FeFETs. A 2-step search with early termination is employed to reduce the cell area and improve energy efficiency. A shared driver design is proposed to reduce the peripherals area. Detailed analysis and SPICE simulation show that the 1.5T1Fe DG-TCAM leads to superior search speed and energy efficiency. The 1.5T1Fe TCAM design can also be built with SG-FeFETs, which achieve search latency and energy improvement compared with 2FeFET TCAM., Comment: Accepted by Design Automation Conference (DAC) 2023

The globalization of the Integrated Circuit (IC) market is attracting an ever-growing number of partners, while remarkably lengthening the supply chain. Thereby, security concerns, such as those imposed by functional Reverse Engineering (RE), have become quintessential. RE leads to disclosure of confidential information to competitors, potentially enabling the theft of intellectual property. Traditional functional RE methods analyze a given gate-level netlist through employing pattern matching towards reconstructing the underlying basic blocks, and hence, reverse engineer the circuit's function. In this work, we are the first to demonstrate that applying Approximate Computing (AxC) principles to circuits significantly improves the resiliency against RE. This is attributed to the increased complexity in the underlying pattern-matching process. The resiliency remains effective even for Graph Neural Networks (GNNs) that are presently one of the most powerful state-of-the-art techniques in functional RE. Using AxC, we demonstrate a substantial reduction in GNN average classification accuracy-- from 98% to a mere 53%. To surmount the challenges introduced by AxC in RE, we propose the highly promising AppGNN platform, which enables GNNs (still being trained on exact circuits) to: (i) perform accurate classifications, and (ii) reverse engineer the circuit functionality, notwithstanding the applied approximation technique. AppGNN accomplishes this by implementing a novel graph-based node sampling approach that mimics generic approximation methodologies, requiring zero knowledge of the targeted approximation type. We perform an extensive evaluation and show that, using our method, we can improve the classification accuracy from 53% to 81% when classifying approximate adder circuits that have been generated using evolutionary algorithms, which our method is oblivious of., Comment: To appear at the 2022 International Conference On Computer-Aided Design (ICCAD)

Process variations and device aging impose profound challenges for circuit designers. Without a precise understanding of the impact of variations on the delay of circuit paths, guardbands, which keep timing violations at bay, cannot be correctly estimated. This problem is exacerbated for advanced technology nodes, where transistor dimensions reach atomic levels and established margins are severely constrained. Hence, traditional worst-case analysis becomes impractical, resulting in intolerable performance overheads. Contrarily, process-variation/aging-aware static timing analysis (STA) equips designers with accurate statistical delay distributions. Timing guardbands that are small, yet sufficient, can then be effectively estimated. However, such analysis is costly as it requires intensive Monte-Carlo simulations. Further, it necessitates access to confidential physics-based aging models to generate the standard-cell libraries required for STA. In this work, we employ graph neural networks (GNNs) to accurately estimate the impact of process variations and device aging on the delay of any path within a circuit. Our proposed GNN4REL framework empowers designers to perform rapid and accurate reliability estimations without accessing transistor models, standard-cell libraries, or even STA; these components are all incorporated into the GNN model via training by the foundry. Specifically, GNN4REL is trained on a FinFET technology model that is calibrated against industrial 14nm measurement data. Through our extensive experiments on EPFL and ITC-99 benchmarks, as well as RISC-V processors, we successfully estimate delay degradations of all paths -- notably within seconds -- with a mean absolute error down to 0.01 percentage points., Comment: This article will be presented in the International Conference on Compilers, Architectures, and Synthesis for Embedded Systems (CASES) 2022 and will appear as part of the ESWEEK-TCAD special issue

The pivotal issue of reliability is one of colossal concern for circuit designers. The driving force is transistor aging, dependent on operating voltage and workload. At the design time, it is difficult to estimate close-to-the-edge guardbands that keep aging effects during the lifetime at bay. This is because the foundry does not share its calibrated physics-based models, comprised of highly confidential technology and material parameters. However, the unmonitored yet necessary overestimation of degradation amounts to a performance decline, which could be preventable. Furthermore, these physics-based models are exceptionally computationally complex. The costs of modeling millions of individual transistors at design time can be evidently exorbitant. We propose the revolutionizing prospect of a machine learning model trained to replicate the physics-based model, such that no confidential parameters are disclosed. This effectual workaround is fully accessible to circuit designers for the purposes of design optimization. We demonstrate the models' ability to generalize by training on data from one circuit and applying it successfully to a benchmark circuit. The mean relative error is as low as 1.7%, with a speedup of up to 20X. Circuit designers, for the first time ever, will have ease of access to a high-precision aging model, which is paramount for efficient designs. This work is a promising step in the direction of bridging the wide gulf between the foundry and circuit designers.

Brain-inspired hyperdimensional computing (HDC) is an emerging machine learning (ML) methods. It is based on large vectors of binary or bipolar symbols and a few simple mathematical operations. The promise of HDC is a highly efficient implementation for embedded systems like wearables. While fast implementations have been presented, other constraints have not been considered for edge computing. In this work, we aim at answering how thermal-friendly HDC for edge computing is. Devices like smartwatches, smart glasses, or even mobile systems have a restrictive cooling budget due to their limited volume. Although HDC operations are simple, the vectors are large, resulting in a high number of CPU operations and thus a heavy load on the entire system potentially causing temperature violations. In this work, the impact of HDC on the chip's temperature is investigated for the first time. We measure the temperature and power consumption of a commercial embedded system and compare HDC with conventional CNN. We reveal that HDC causes up to 6.8{\deg}C higher temperatures and leads to up to 47% more CPU throttling. Even when both HDC and CNN aim for the same throughput (i.e., perform a similar number of classifications per second), HDC still causes higher on-chip temperatures due to the larger power consumption., Comment: 4 pages, 3 figures

Transistor aging phenomena manifest themselves as degradations in the main electrical characteristics of transistors. Over time, they result in a significant increase of cell propagation delay, leading to errors due to timing violations, since the operating frequency becomes unsustainable as the circuit ages. Conventional techniques employ timing guardbands to mitigate aging-induced delay increase, which leads to considerable performance losses from the beginning of the circuit's lifetime. Leveraging the inherent error resilience of a vast number of application domains, approximate computing was recently introduced as an aging mitigation mechanism. In this work, we present the first automated framework for generating aging-aware approximate circuits. Our framework, by applying directed gate-level netlist approximation, induces a small functional error and recovers the delay degradation due to aging. As a result, our optimized circuits eliminate aging-induced timing errors. Experimental evaluation over a variety of arithmetic circuits and image processing benchmarks demonstrates that for an average error of merely $5\times10^{-3}$, our framework completely eliminates aging-induced timing guardbands. Compared to the respective baseline circuits without timing guardbands (i.e., iso-performance evaluation), the error of the circuits generated by our framework is $1208$x smaller.

Brain-inspired hyperdimensional computing (HDC) is continuously gaining remarkable attention. It is a promising alternative to traditional machine-learning approaches due to its ability to learn from little data, lightweight implementation, and resiliency against errors. However, HDC is overwhelmingly data-centric similar to traditional machine-learning algorithms. In-memory computing is rapidly emerging to overcome the von Neumann bottleneck by eliminating data movements between compute and storage units. In this work, we investigate and model the impact of imprecise in-memory computing hardware on the inference accuracy of HDC. Our modeling is based on 14nm FinFET technology fully calibrated with Intel measurement data. We accurately model, for the first time, the voltage-dependent error probability in SRAM-based and FeFET-based in-memory computing. Thanks to HDC's resiliency against errors, the complexity of the underlying hardware can be reduced, providing large energy savings of up to 6x. Experimental results for SRAM reveal that variability-induced errors have a probability of up to 39 percent. Despite such a high error probability, the inference accuracy is only marginally impacted. This opens doors to explore new tradeoffs. We also demonstrate that the resiliency against errors is application-dependent. In addition, we investigate the robustness of HDC against errors when the underlying in-memory hardware is realized using emerging non-volatile FeFET devices instead of mature CMOS-based SRAMs. We demonstrate that inference accuracy does remain high despite the larger error probability, while large area and power savings can be obtained. All in all, HW/SW co-design is the key for efficient yet reliable in-memory hyperdimensional computing for both conventional CMOS technology and upcoming emerging technologies., Comment: Published in IEEE Transactions on Computers

Recent Deep Neural Networks (DNNs) managed to deliver superhuman accuracy levels on many AI tasks. Several applications rely more and more on DNNs to deliver sophisticated services and DNN accelerators are becoming integral components of modern systems-on-chips. DNNs perform millions of arithmetic operations per inference and DNN accelerators integrate thousands of multiply-accumulate units leading to increased energy requirements. Approximate computing principles are employed to significantly lower the energy consumption of DNN accelerators at the cost of some accuracy loss. Nevertheless, recent research demonstrated that complex DNNs are increasingly sensitive to approximation. Hence, the obtained energy savings are often limited when targeting tight accuracy constraints. In this work, we present a dynamically configurable approximate multiplier that supports three operation modes, i.e., exact, positive error, and negative error. In addition, we propose a filter-oriented approximation method to map the weights to the appropriate modes of the approximate multiplier. Our mapping algorithm balances the positive with the negative errors due to the approximate multiplications, aiming at maximizing the energy reduction while minimizing the overall convolution error. We evaluate our approach on multiple DNNs and datasets against state-of-the-art approaches, where our method achieves 18.33% energy gains on average across 7 NNs on 4 different datasets for a maximum accuracy drop of only 1%., Comment: Accepted for publication at the 40th International Conference On Computer Aided Design (ICCAD 2021)

Transistor aging is one of the major concerns that challenges designers in advanced technologies. It profoundly degrades the reliability of circuits during its lifetime as it slows down transistors resulting in errors due to timing violations unless large guardbands are included, which leads to considerable performance losses. When it comes to Neural Processing Units (NPUs), where increasing the inference speed is the primary goal, such performance losses cannot be tolerated. In this work, we are the first to propose a reliability-aware quantization to eliminate aging effects in NPUs while completely removing guardbands. Our technique delivers a graceful inference accuracy degradation over time while compensating for the aging-induced delay increase of the NPU. Our evaluation, over ten state-of-the-art neural network architectures trained on the ImageNet dataset, demonstrates that for an entire lifetime of 10 years, the average accuracy loss is merely 3%. In the meantime, our technique achieves 23% higher performance due to the elimination of the aging guardband., Comment: Accepted for publication at the 24th Design Automation and Test in Europe Conference (DATE) 2021

In this work, we introduce a control variate approximation technique for low error approximate Deep Neural Network (DNN) accelerators. The control variate technique is used in Monte Carlo methods to achieve variance reduction. Our approach significantly decreases the induced error due to approximate multiplications in DNN inference, without requiring time-exhaustive retraining compared to state-of-the-art. Leveraging our control variate method, we use highly approximated multipliers to generate power-optimized DNN accelerators. Our experimental evaluation on six DNNs, for Cifar-10 and Cifar-100 datasets, demonstrates that, compared to the accurate design, our control variate approximation achieves same performance and 24% power reduction for a merely 0.16% accuracy loss., Comment: Accepted for publication at the 58th Design Automation Conference (DAC'21), December 5-9, 2021, San Francisco, USA

Side-channel attacks have empowered bypassing of cryptographic components in circuits. Power side-channel (PSC) attacks have received particular traction, owing to their non-invasiveness and proven effectiveness. Aside from prior art focused on conventional technologies, this is the first work to investigate the emerging Negative Capacitance Transistor (NCFET) technology in the context of PSC attacks. We implement a CAD flow for PSC evaluation at design-time. It leverages industry-standard design tools, while also employing the widely-accepted correlation power analysis (CPA) attack. Using standard-cell libraries based on the 7nm FinFET technology for NCFET and its counterpart CMOS setup, our evaluation reveals that NCFET-based circuits are more resilient to the classical CPA attack, due to the considerable effect of negative capacitance on the switching power. We also demonstrate that the thicker the ferroelectric layer, the higher the resiliency of the NCFET-based circuit, which opens new doors for optimization and trade-offs.

In this paper, we propose a novel accuracy-reconfigurable stochastic computing (ARSC) framework for dynamic reliability and power management. Different than the existing stochastic computing works, where the accuracy versus power/energy trade-off is carried out in the design time, the new ARSC design can change accuracy or bit-width of the data in the run-time so that it can accommodate the long-term aging effects by slowing the system clock frequency at the cost of accuracy while maintaining the throughput of the computing. We validate the ARSC concept on a discrete cosine transformation (DCT) and inverse DCT designs for image compressing/decompressing applications, which are implemented on Xilinx Spartan-6 family XC6SLX45 platform. Experimental results shows that the new design can easily mitigate the long-term aging induced effects by accuracy trade-off while maintaining the throughput of the whole computing process using simple frequency scaling. We further show that one-bit precision loss for input data, which translated to 3.44dB of the accuracy loss in term of Peak Signal to Noise Ratio for images, we can sufficiently compensate the NBTI induced aging effects in 10 years while maintaining the pre-aging computing throughput of 7.19 frames per second. At the same time, we can save 74\% power consumption by 10.67dB of accuracy loss. The proposed ARSC computing framework also allows much aggressive frequency scaling, which can lead to order of magnitude power savings compared to the traditional dynamic voltage and frequency scaling (DVFS) techniques.

Several emerging technologies for byte-addressable non-volatile memory (NVM) have been considered to replace DRAM as the main memory in computer systems during the last years. The disadvantage of a lower write endurance, compared to DRAM, of NVM technologies like Phase-Change Memory (PCM) or Ferroelectric RAM (FeRAM) has been addressed in the literature. As a solution, in-memory wear-leveling techniques have been proposed, which aim to balance the wear-level over all memory cells to achieve an increased memory lifetime. Generally, to apply such advanced aging-aware wear-leveling techniques proposed in the literature, additional special hardware is introduced into the memory system to provide the necessary information about the cell age and thus enable aging-aware wear-leveling decisions. This paper proposes software-only aging-aware wear-leveling based on common CPU features and does not rely on any additional hardware support from the memory subsystem. Specifically, we exploit the memory management unit (MMU), performance counters, and interrupts to approximate the memory write counts as an aging indicator. Although the software-only approach may lead to slightly worse wear-leveling, it is applicable on commonly available hardware. We achieve page-level coarse-grained wear-leveling by approximating the current cell age through statistical sampling and performing physical memory remapping through the MMU. This method results in non-uniform memory usage patterns within a memory page. Hence, we further propose a fine-grained wear-leveling in the stack region of C / C++ compiled software. By applying both wear-leveling techniques, we achieve up to $78.43\%$ of the ideal memory lifetime, which is a lifetime improvement of more than a factor of $900$ compared to the lifetime without any wear-leveling.

This paper reports a novel approach that uses transistor aging in an integrated circuit (IC) to detect hardware Trojans. When a transistor is aged, it results in delays along several paths of the IC. This increase in delay results in timing violations that reveal as timing errors at the output of the IC during its operation. We present experiments using aging-aware standard cell libraries to illustrate the usefulness of the technique in detecting hardware Trojans. Combining IC aging with over-clocking produces a pattern of bit errors at the IC output by the induced timing violations. We use machine learning to learn the bit error distribution at the output of a clean IC. We differentiate the divergence in the pattern of bit errors because of a Trojan in the IC from this baseline distribution. We simulate the golden IC and show robustness to IC-to-IC manufacturing variations. The approach is effective and can detect a Trojan even if we place it far off the critical paths. Results on benchmarks from the Trust-hub show a detection accuracy of $\geq$99%., Comment: 21 pages, 34 figures