Hardware Features Research Articles

Improving the accuracy of approximate multipliers based on the characteristics of 4:2 compressors

Approximate computing is a new trend applied in many applications such as multimedia processing and pattern recognition, which can tolerate a certain amount of error since they are inherently error-tolerant. In this paper, we use two different methods to modify and improve the accuracy of the previous approximate multipliers. In the first method, we use an error recovery module in the structure of the existing approximate multipliers based on the characteristics of their approximate compressors. In the second method, by considering the accuracy parameters of the previous designs, we combine the previous compressors to improve the efficiency of the existing approximate multipliers. The proposed circuits are simulated using HSPICE with the 7 nm FinFET model. The efficacy of the multipliers in real-life applications such as image processing and neural networks are evaluated using MATLAB. The results show that using the first method increases the accuracy parameters of the previous designs, while it does not lead to considerable power and delay overheads. However, utilizing the second method can improve both the accuracy and hardware characteristics of the previous designs. For example, the PM2 multiplier, using the first proposed method, improves the MED and MRED, as two widely used accuracy metrics, by 36.7% and 21.6%, whereas using this method slightly increases the power-delay product (PDP) by 2.7%. In addition, the PM6 multiplier equipped with the second proposed method improves the MED and MRED values by 26% and 17% and has a 5.2% lower PDP.

SwPHoToNs: Toward trillion‐body‐scale cosmologicalN‐body simulations on SunwayTaihuLightsupercomputer

AbstractCosmologicalN‐body simulations have been essential for astronomers to study the formation of nonlinear structures and hypotheses of dark matter, dark energy, etc. The scale of the problem naturally leads to extreme scenarios with billions or even trillions of particles, thus demanding massive computational power and highly efficient algorithms. In this paper, we present swPHoToNs, a Particle‐Mesh (PM) and Fast Multipole Method‐ (FMM) based code that can perform cosmological simulations with trillions of particles efficiently on the Sunway TaihuLight supercomputer. Our design includes three novel optimizations: (1) a multilevel domain decomposition and dynamic load‐balancing scheme; (2) a pipeline strategy for tree traversal and gravity calculation; (3) optimizations for both computation and MPI kernels with consideration of the hardware features. We manage to conduct cosmological simulations which contain up to 1.6 trillion particles, obtaining a sustained performance of 56.3 PFlops with a weak‐scaling parallel efficiency of 80.9% and a computational efficiency of 44.9%.

Mapping bacterial biofilm on explanted orthopedic hardware: An analysis of 14 consecutive cases.

Hardware implanted during primary total joint arthroplasty carries a serious risk for periprosthetic joint infection (PJI). The formation of bacterial biofilms, which are highly tolerant of antibiotics and host immunity, is recognized as being a major barrier to treatment. It is not known whether some components and their surface features are more prone to biofilm than others. This study attempted to map biofilm on different components and features of orthopedic hardware recovered during revision. Implant surface culture (ISC) was used on 53 components from 14 hip and knee revisions. ISC achieves a thin agar coating over components, followed by incubation and observation for colony outgrowth over 9 days. Recovered organisms were identified by selective culture and 16s rRNA sequencing. Outcomes were compared with clinical culturing and PJI diagnosis based on 2013 Musculoskeletal Infection Society criteria. ISC paralleled clinical culturing with a sensitivity of 100% and a specificity of 57.1%. When compared to Musculoskeletal Infection Society criteria, sensitivity remained at 100% while specificity was 80%. Biofilm accumulation was patchy and heterogeneous throughout different prostheses, though notably the non-articulating surfaces between the tibial tray and polyethylene insert showed consistent growth. On individual components, ridges and edges consistently harbored biofilm, while growth elsewhere was case dependent. ISC successfully identified microbial growth with high sensitivity while also revealing that biofilm growth was commonly localized to particular locations. Understanding where biofilm formation occurs most often on implanted hardware will help guide debridement, retention choices, and implant design.

Reinforcement learning based flow and energy management in resource-constrained wireless networks

This paper aims at developing a learning-based framework for MAC sleep–listen–transmit scheduling in wireless networks. The Reinforcement Learning-based paradigm is shown to work in the absence of network time-synchronization and other complex hardware features, such as carrier-sensing, thus making it suitable for low-cost transceivers for IoT and wireless sensor nodes. The framework allows wireless nodes to learn policies that can support throughput-sustainable flows while minimizing node energy expenditure and sleep-induced packet drops and delays. Each node independently learns a scheduling policy without explicit communication with other network nodes. The trade-off between packet drops and energy efficiency is analyzed, and an application-specific solution is proposed for handling the trade-off. It is shown how this model allows users to prioritize between energy efficiency and packet drops depending on specific application requirements. An analytical model is developed for understanding the underlying system dynamics, which is also validated using extensive simulation experiments. Moreover, the developed mechanism is experimented with for heterogeneous network topologies and traffic patterns

Dynamic open set specific emitter identification via multi‐channel reconstructive discriminant network

AbstractSpecific emitter identification (SEI) is an emerging device authentication technology, which depends on the inherent hardware characteristics of wireless devices. By analysing the received signal, the hardware characteristics of a specific emitter can be extracted at the receiver and used for device authentication and association. Most of the existing SEI schemes focus on the identification under closed sets. In view of the explosive growth of the number of IoT devices, based on generative adversarial networks, this study proposes a method that considers the identification of unknown emitters. The reconstruction network to reconstruct the signals of the known class and fully train the feature space of the signals of the known class is designed. In the discriminator, two channels are specifically designed to perform anomaly detection for unknown signals and end‐to‐end closed‐set classification for known signals. In order to better reject unknown signals and accept known signals, Receiver operating characteristic curve and Youden index are used to determine the optimal threshold for anomaly detection. Under the given optimal threshold conditions, the identified threshold points have larger True Positive Rate. In addition, the time‐frequency feature combination vector is designed to reveal the essential characteristics of emitters. The experimental results on the real‐world datasets collected from universal software radio peripherals in short‐range communication scenario show that compared with the existing open‐set recognition methods such as C2AE, Openmax and SoftMax, the average recognition accuracy of the proposed framework improved by 0.08, 0.15, and 0.2 respectively, and the Marco‐F1 score improved by 0.05, 0.1, and 0.16, respectively, which proves the superiority of the proposed framework. In addition to identifying unknown and known Universal software radio peripherals in this article, some potential and widespread applications of the proposed framework include access user security authentication in IoT, such as Hack RF and Blue tooth devices. In addition, as a relatively general signal processing framework, the model can be used for air safety management and maritime ship identity authentication in civil aspects. In the military aspect, it can be used in electronic support and various signal reconnaissance scenarios, such as automatic signal modulation recognition in open set scenarios, individual identity determination of radar emitter and unknown working state identification of transmitters, which proves reference for subsequent research on open‐set signal recognition.

A Review of the Current Task Offloading Algorithms, Strategies and Approach in Edge Computing Systems

Task offloading is an important concept for edge computing and the Internet of Things (IoT) because computationintensive tasks must be offloaded to more resource-powerful remote devices. Task offloading has several advantages, including increased battery life, lower latency, and better application performance. A task offloading method determines whether sections of the full application should be run locally or offloaded for execution remotely. The offloading choice problem is influenced by several factors, including application properties, network conditions, hardware features, and mobility, influencing the offloading system’s operational environment. This study provides a thorough examination of current task offloading and resource allocation in edge computing, covering offloading strategies, algorithms, and factors that influence offloading. Full offloading and partial offloading strategies are the two types of offloading strategies. The algorithms for task offloading and resource allocation are then categorized into two parts: machine learning algorithms and non-machine learning algorithms. We examine and elaborate on algorithms like Supervised Learning, Unsupervised Learning, and Reinforcement Learning (RL) under machine learning. Under the non-machine learning algorithm, we elaborate on algorithms like non(convex) optimization, Lyapunov optimization, Game theory, Heuristic Algorithm, Dynamic Voltage Scaling, Gibbs Sampling, and Generalized Benders Decomposition (GBD). Finally, we highlight and discuss some research challenges and issues in edge computing.

Image Reconstruction of Synthetic Aperture Radiometer by Transformer

In passive microwave remote sensing of the earth, compared with real aperture radiometer, synthetic aperture radiometer is a very powerful instrument with many advantages. However, the system design is more complex than the real aperture radiometer, and the hardware ideality is often not guaranteed. The non-ideal characteristics of the system hardware will bring a variety of errors to the system, which will cause the Fourier transform relationship between the visibility function and the brightness temperature image to no longer be established, thus reducing the quality of microwave brightness temperature image reconstruction by traditional methods. In this paper, a new microwave brightness temperature image reconstruction method for synthetic aperture radiometer by Transformer is proposed. This method uses a specially designed Transformer structure to extract the spectrum features in the visibility function. This method learns the mapping relationship between the visibility function and the original scene brightness temperature image through the supervised learning method, and learns as much as possible the spectrum information contained in the original scene brightness temperature image. Moreover, when there are missing baselines, this method will supplement the missing observation frequency information, so as to obtain better reconstructed image quality. With the above advantages, this method can suppress the Gibbs oscillation, and greatly reduce the side lobe. Compared with the existing reconstruction methods, whether missing baselines or not, the proposed image reconstruction method by Transformer has advantages in image quality. We verify the performance of this brightness temperature image reconstruction method through simulation and experiment.

Direct-Conversion Spectrum Sensor Impaired by Symmetric α-Stable and α-Sub-Gaussian Noises

Spectrum sensing in underwater cognitive acoustic networks or in underwater acoustic sensor networks can be impaired by impulsive noise generated by snapping shrimps. In mathematical analysis or simulations, the amplitude variations of this noise are commonly modeled by the symmetric alpha-stable (SαS) distribution. As an alternative, the alpha-sub-Gaussian (αSG) distribution can model both temporal correlation and amplitude variations. This article assesses the performance of underwater spectrum sensing with a direct-conversion receiver (DCR) under impulsive noise modeled by the SαS and αSG distributions. Several recent test statistics are compared, demonstrating that they have different degrees of robustness against impulsive noise and that the DCR is significantly less sensitive to this noise, compared to the conventional receiver model that does not take into account the influences of hardware characteristics into the performance of spectrum sensing.

Evaluating RF Hardware Characteristics for Automotive JCRS Systems Based on PMCW-CDMA at 77GHz

Joint communications and radar sensing (JCRS) applications are currently being hailed as the innovation of the next generation of mobile communications. The combination of communications and sensor technology on one hardware platform offers various advantages, such as significant savings in space and costs. The two technologies are no longer being optimized and developed side by side, as has been the case in the past, but jointly. The physical channel is used by both simultaneously, including the transmitter and receiver structures, which must be optimized for the combined application. This inevitably leads to an influence on the performance of both systems. In this work, this influence is considered and analyzed with respect to the effects of the radio frequency components. For this purpose, our previously published code-division multiple access (CDMA)-based and vehicle-to-vehicle-focused model is extended to a JCRS model and evaluated according to the achieved bit error rate as well as the mean deviation of the detected distance and velocity in Simulink. The influence of the non-ideal hardware components (mixers, power amplifier, low noise amplifier, filter, antenna) and characteristics (S-parameters, non-linearity of the amplifiers and the noise) on the sensing and communications are analyzed and compared in this automotive context. The results reveal that the noise of the low noise amplifier at the receiver side has the most decisive influence. In contrast, the noise generated by the power amplifier at the transmitter has no effect due to the relatively high signal power. The non-linearity of amplifiers at the transmitter also significantly impacts the available sensing range by limiting and compressing signal power. Besides, the phase noise with a frequency offset higher than 10MHz can increase the communications and sensing error rate. In contrast, the influence of S-parameters is negligible, as the performance of communications and sensing is almost unchanged with different S-parameters. In the future, the proposed single-target scene will be further extended to a multi-target one.

오픈 플랫폼 호환 지능형 IoT 컴포넌트 자동 생성 도구

As IoT applications that provide AI services increase, various hardware and software that support autonomous learning and inference are being developed. However, as the characteristics and constraints of each hardware increase difficulties in developing IoT applications, the development of an integrated platform is required. In this paper, we propose a tool for automatically generating components based on artificial neural networks and spiking neural networks as well as IoT technologies to be compatible with open platforms. The proposed component automatic generation tool supports the creation of components considering the characteristics of various hardware devices through the virtual component layer of IoT and AI and enables automatic application to open platforms.

PI PUF: A Processor-Intrinsic PUF for IoT

Most IoT devices cannot offer sufficient resources for traditional cryptography technologies, posing a severe security challenge. Physical unclonable function (PUF) is a new lightweight hardware security primitive that extracts the entropy from process variations of circuits. However, the existing PUFs commonly are ASICs that require extra overhead on the area and extended instruction. To address such issues, this paper proposes a novel Processor-Intrinsic PUF (PI PUF). It exploits the pipeline design of processors and the timing dependence of data paths to generate abnormal information which carries the unclonable hardware characteristics. Moreover, a multi-round instruction obfuscation (MRIO) mechanism and the Gray code encoding method are conducted in the abnormal information to improve the uniqueness and randomness of our PUF. Finally, we design a lightweight authentication protocol based on the proposed PUF, whose security is further enhanced by shared key encryption and XOR random number encryption. Meanwhile, we also provide detailed security analysis under various attack scenarios. The Monte Carlo simulation results show that the proposed PUF achieves 50.93% of uniqueness, 50.62% of randomness, and 5.02% of the worst bit error rate, which outperforms the same type of state-of-the-art works. It also passes the NIST test.

AnaBHEL (Analog Black Hole Evaporation via Lasers) Experiment: Concept, Design, and Status

Accelerating relativistic mirrors have long been recognized as viable settings where the physics mimic those of the black hole Hawking radiation. In 2017, Chen and Mourou proposed a novel method to realize such a system by traversing an ultra-intense laser through a plasma target with a decreasing density. An international AnaBHEL (Analog Black Hole Evaporation via Lasers) collaboration was formed with the objectives of observing the analog Hawking radiation, shedding light on the information loss paradox. To reach these goals, we plan to first verify the dynamics of the flying plasma mirror and characterize the correspondence between the plasma density gradient and the trajectory of the accelerating plasma mirror. We will then attempt to detect the analog Hawking radiation photons and measure the entanglement between the Hawking photons and their “partner particles”. In this paper, we describe our vision and strategy of AnaBHEL using the Apollon laser as a reference, and we report on the progress of our R&D concerning the key components in this experiment, including the supersonic gas jet with a graded density profile, and the superconducting nanowire single-photon Hawking detector. In parallel to these hardware efforts, we performed computer simulations to estimate the potential backgrounds, and derived analytic expressions for modifications to the blackbody spectrum of the Hawking radiation for a perfectly reflecting point mirror, due to the semi-transparency and finite-size effects specific to flying plasma mirrors. Based on this more realistic radiation spectrum, we estimate the Hawking photon yield to guide the design of the AnaBHEL experiment, which appears to be achievable.

A proposed ontology to support the hardware design of building inspection robot systems

Due to the growing number of architecturally complex buildings built in recent decades, mobile building inspection robot systems are required to operate in increasingly complex environments. This leads to higher requirements for their hardware design. The existing literature on the design of building inspection robots has implicitly mentioned the impact of building environments and building defects on defining robot hardware design requirements. However, the explicit representation of what information is required to define a specific hardware requirement is stimissing. To fill this gap, this paper presents an ontology that provides an overview of the building and inspection domain objects that affect the determination of robot hardware design requirements (RoboDesign). It also explores the relationship between specific robot hardware requirements and features of complex buildings and their defects. The RoboDesign ontology integrates two main domain ontology models including a Robot System Model and a Building and Defect Model. A content evaluation and an automated consistency checking are conducted for the internal evaluation of the ontology. Additionally, the proposed ontology is implemented in two wall-climbing inspection robot design cases to check if the investigation of the robot’s application environment is comprehensive. The validation results also demonstrate that the use of the proposed ontological model allows to efficiently retrieve information required to determine a particular hardware requirement.

SMSG: Profiling-Free Parallelism Modeling for Distributed Training of DNN

The increasing size of deep neural networks (DNNs) raises a high demand for distributed training. An expert could find good hybrid parallelism strategies, but designing suitable strategies is time and labor-consuming. Therefore, automating parallelism strategy generation is crucial and desirable for DNN designers. Some automatic searching approaches have recently been studied to free the experts from the heavy parallel strategy conception. However, these approaches all rely on a numerical cost model, which requires heavy profiling results that lack portability. These profiling-based approaches cannot lighten the strategy generation work due to the non-reusable profiling value. Our intuition is that there is no need to estimate the actual execution time of the distributed training but to compare the relative cost of different strategies. We propose SMSG (Symbolic Modeling for Strategy Generation), which analyses the cost based on the communication and computation semantics. With SMSG, the parallel cost analyses are decoupled from hardware characteristics. SMSG defines cost functions for each kind of operator to quantitatively evaluate the amount of data for computation and communication, which eliminates the heavy profiling tasks. Besides, SMSG introduces how to apply functional transformation by using the Third Homomorphism theorem to control the high searching complexity. Our experiments show that SMSG can find good hybrid parallelism strategies to generate an efficient training performance similar to the state of the art. Moreover, SMSG covers a wide variety of DNN models with good scalability. SMSG provides good portability when changing training configurations that a profiling-based approach cannot.

Adversarial attacks and active defense on deep learning based identification of GaN power amplifiers under physical perturbation

Deep learning (DL)-based radiofrequency (RF) fingerprinting identification has shown significantly growing importance in the wireless industry including 5G, IoT and Wireless Sensor Networks (WSN). However, there is little investigation on the robustness of the corresponding DL models against adversarial attacks and adversarial defense. This paper discusses the effects of four cutting-edge adversarial attacks on DL-based RF fingerprinting identification and provides a graphical analysis of RF feature perturbations following adversarial attacks. For the first time we also demonstrate the results of combined physical attack (i.e. tuning the drain currents of the power amplifiers) by tuning the physical features of the device hardware (i.e. drain current), and adversarial attacks on DL-based classifiers. Experimental results from 16 Gallium nitride (GaN) power amplifiers (PA) reveal that adversarial attacks can seriously deteriorate the accuracy of RF identification from about 100.00% to below 10.00% even with only 0.50% adversarial perturbation. In order to deal with the problem of decreased accuracy caused by attacks, we proposed an adversarial defense method based on feature-level interpretability (FIAT), which improved the accuracy of RF identification with interpretability analysis. The results compared with several common defense methods validate that the proposed FIAT can maintain an accuracy of 96.00% even when the adversarial attack perturbation is 5.00% and with physical attack. Moreover, the changes of data features in the process of adversarial attacks and defense are given, providing a new way for the interpretability of adversarial attacks and defense on RF identification tasks.

Co-Concurrency Mechanism for Multi-GPUs in Distributed Heterogeneous Environments

The high concurrency and high throughput characteristics of graphics processing units (GPUs) have made researchers continue to use it to optimize distributed parallel computing architectures. With the upgrading of processor architecture, GPUs allow multiple kernels to execute concurrently through stream queues. However, due to the different hardware characteristics and kernel properties in distributed architectures, existing research lacks careful consideration of optimization schemes for concurrent streams and kernel block sizes. Unreasonable stream concurrency and kernel block size configuration will lead to prolonged execution time and waste of computing resources during application execution. Therefore, we propose a multi-GPU multi-stream co-concurrency mechanism (MGSC) in a distributed heterogeneous environment, dynamically adjusting the number of concurrent streams and exploring the optimal block size in task scheduling. According to the memory resources and startup overhead occupied in concurrent stream scheduling, a resource-aware concurrent stream adaptive adjustment mechanism is proposed, which can dynamically adjust the number of streams. To explore the optimal block size, we abstract it as a multi-armed bandit problem (MAB) and propose a block size adjustment algorithm based on the upper confidence bound (UCB). We implement MGSC in Spark 3.1.1 and NVIDIA CUDA 11.2. We conduct comparative experiments with multiple typical benchmarks to evaluate the performance of MGSC. The experimental results show that the algorithm can make full use of the computing power of the GPU and significantly reduce the execution time of tasks.

Excalibur

In recent years, hardware has become increasingly diverse, in terms of features as well as performance. This poses a problem for complex software in general and database systems in particular. To achieve top-notch performance, we need to exploit hardware features, but do not fully know which behave best on the current, and more-so future, machines. Specializing query execution methods for many diverse hardware platforms will significantly increase database software complexity and also poses a physical query optimization problem that cannot be solved robustly with static cost models. In this paper, we propose a new query execution architecture addressing these problems. Based on the flexible domain-specific language VOILA, it can generate thousands of different flavors from a single code-base. As an abstraction, a virtual machine (VM) allows hiding physical execution details, such that the VM can transparently switch between different execution tactics within each query, applied at a fine granularity. We show rules to describe a search space for good tactics, and describe efficient search strategies, that limit the overhead of adaptive JIT code generation and compilation. The VM starts executing each query in full vectorized code style, but adaptively replaces (parts of) query pipelines by code fragments compiled using different execution flavors, exploring this search space and exploiting the best tactics found, casting adaptive query execution into a Multi-Armed Bandit (MAB) problem. Excalibur, our prototype, outperforms open-source systems by up to 28X and the state-of-the-art system Umbra by up to 1.8X. In specific queries Excalibur performs up to 2X faster than static flavors.

A Station Terminal Management System Based on Scheduling Small Site in Power Dispatching

In the process of power dispatching and control, dispatching small network is an effective means to realize the remote number allocation in power dispatching and switching network. However, due to the scattered site, a wide range, and some unmanned site remote locations, there is a need for a small site terminal equipment to find the fault. To solve these problems, a terminal graphics management system is established. First, the real-time status monitoring mechanism of terminal is established based on IPoE technology to realize the status awareness of remote terminal. The heartbeat mechanism is segmented in link layer to meet the real-time performance of terminal state presentation. Then, the message class method with special characters is used to replace the original dial method to test the detection mode of manual answering. Automatic monitoring using telemetry technology can effectively monitor in unattended situations. Finally, considering the performance of different devices and various fault scenarios, according to the inherent hardware characteristics of segmented devices, the unified packet detection technology is used to realize the fault diagnosis of network sub-nodes, and finally realize the fault diagnosis of the terminal. After experimental verification and testing, the platform can realize remote fault detection and management of each plant terminal through topological graphical management system. The system can improve the scale and management ability of intelligent power dispatching of small stations.

Classification of random number generator applications in IoT: A comprehensive taxonomy

Randomness is an important issue for Internet of Things (IoT). The need to generate suitable random numbers for IoT devices with resource and size limitations has emerged due to the cryptographic protocols. Although random number generation approaches have been proposed considering IoT device constraints, commonly used software and hardware-based solutions have not been discussed in detail. The main contribution of this paper is the detailed examination of the problems encountered in random number generation in the IoT ecosystem and the proposed solution approaches. In this context, a classification has been proposed for hardware containing random number generator (RNG), which has different usage areas in IoT environments. Based on the presented classification, the characteristics of the devices in terms of resource constraints are examined. This classification serves as a guide for selecting suitable hardware in applications with or without random number needs. Also, basic RNGs and test suites are discussed. Some challenges are summarized by explaining the random numbers usage in the IoT environment. In addition, proposed random number generation scenarios for IoT devices are determined. Success rate analysis is carried out based on these techniques in terms of randomness tests. Software and hardware-based solution methods are detailed to meet the need for random numbers in real-world IoT applications. RNG algorithms actively used in IoT applications, basic working principles, usage areas, and hardware features are summarized. Finally, the problem that arises in generating random numbers in system-on-chip (SoC) systems, one of the proposed classification components, are summarized, and some precautions that can be taken are expressed.

Distance and camera features measurements affect the detection of temperature asymmetries using infrared thermography

ABSTRACT Small skin temperature asymmetries are claimed to indicate injuries, but the influence of measurement conditions and technical aspects of image acquisition are concerns for determining temperature asymmetries. This research determines whether distance and camera specifications affect thermal asymmetries detection. We simulated thermal asymmetries filling two glasses with water at different temperatures measured at two distances (0.7 and 1.5 m) using four different infrared cameras (T1020, E60BX, C2 and FLIR ONE). Linear regression verified the similarity between each camera and the T1020 camera (gold standard). The intraclass correlation coefficient assessed the inter-camera reproducibility. Linear regression reported increasing adjustment using mean temperature, with lower values at 1.5 m between the T1020 and FLIR ONE (0.7 m, r = 0.58; 1.5 m, r = 0.34), C2 (0.7 m, r = 0.90; 1.5 m, r = 0.62) and E60BX (0.7 m, r = 0.96; 1.5 m, r = 0.68). Higher inter-camera reproducibility was observed at 0.7 m than 1.5 m. It is preferable to take thermal images with shorter distances and to prioritise cameras with superior hardware characteristics. The portability of FLIR ONE and C2 may be an advantage in studies investigating expected differences greater than 0.05ºC and larger regions of interest.