Unit Architecture Research Articles

Design and Implementation of a Simulator for Precise WCET Estimation of Multithreaded Program

Significant attention is paid to static analysis methods for Worst Case Execution Time Analysis of programs. However, major effort has been focused on WCET analysis of sequential programs and only a little work is performed on that of multithreaded programs. Shared computer architectural units such as shared instruction cache pose a special challenge in WCET analysis of multithreaded programs. The principle used to improve the precision of shared instruction cache analysis is to shrink the set of interferences, from competing threads to an instruction in a thread that may be accessed from shared instruction cache, using static analysis extended to barriers. An Algorithm that address barrier synchronization and used by the simulator is designed and benchmark programs consisting of both barrier synchronization and computation task synchronization are presented. Improvements in precision upto 20 % are observed while performing the proposed WCET analysis on benchmark programs.

Power unit architecture in a high-power charging system for EVs

The paper proposes a methodology to define the architecture of the power unit of a UFC (Ultra Fast Charging) station for electric vehicles (EVs), capable of reaching a power of 350 kW. The main goal is to improve the efficiency of the system defining the best configuration by a MATLAB software (BEA – Best Efficiency Architecture) developed by the authors. The software allows defining the best architecture taking into account efficiency-power curves of all AC/DC and DC/DC power modules currently available on the market, thus increasing energy savings.Architectures based on different connection of AC/DC and DC/DC converters using DC bus have been taken considered. The best configuration found has been simulated using Simulink software, performing time-domain electrical simulations in order to verify and validate the architecture chosen.

APPROACH FOR CODE ANALYSIS TO ESTIMATE POWER CONSUMPTION OF CUDA CORE

The graphics processing unit is a popular computing device for achieving exascale performance in high-performance computing programs, which is used not only in graphics tasks, but also in computational tasks such as machine learning, scientific computing, and cryptography. With the help of a graphics processor, you can achieve significant speed and performance compared to the central processing unit. CUDA, Compute Unified Device Architecture, a graphics processing unit software development platform, allows developers to use the high-performance computing capabilities of graphics processing units to solve problems traditionally handled by central processing units. Even though the graphics processing unit has a relatively high power to performance ratio, it consumes a significant amount of power during computing. The paper proposes an approach for code analysis to estimate power consumption of CUDA core to improve the power efficiency of applications focused on computing on graphics processing units. The proposed approach makes it possible to estimate the power consumption of such applications without the need to run them on physical devices. The proposed approach is based on static analysis of the CUDA program and machine learning methods. To evaluate the effectiveness of the proposed approach, three graphics processing unit architectures were used: NVIDIA PASCAL, NVIDIA TURING, and NVIDIA AMPERE. The results of the experiments showed that for the NVIDIA AMPERE architecture, the proposed approach using decision trees makes it possible to achieve a determination coefficient of 0.9173. The results obtained confirm the effectiveness of the proposed code analysis method for estimating the power consumption of the CUDA core. This method can be useful for CUDA developers who want to improve the efficiency and power efficiency of their programs.

Vulkan all the way: Transitioning to a modern low-level graphics API in academia

For over two decades, the OpenGL API provided users with the means for implementing versatile, feature-rich, and portable real-time graphics applications. Consequently, it has been widely adopted by practitioners and educators alike and is deeply ingrained in many curricula that teach real-time graphics for higher education. Over the years, the architecture of graphics processing units (GPUs) incrementally diverged from OpenGL’s conceptual design. The more recently introduced Vulkan API provides a more modern, fine-grained approach for interfacing with the GPU, which allows a high level of controllability and, thereby, deep insights into the inner workings of modern GPUs. This property makes the Vulkan API especially well suitable for teaching graphics programming in university education, where fundamental knowledge shall be conveyed. Hence, it stands to reason that educators who have their students’ best interests at heart should provide them with corresponding lecture material. However, Vulkan is notoriously verbose and rather challenging for first-time users, thus transitioning to this new API bears a considerable risk of failing to achieve expected teaching goals. In this paper, we document our experiences after teaching Vulkan in both introductory and advanced graphics courses side-by-side with conventional OpenGL. A collection of surveys enables us to draw conclusions about perceived workload, difficulty, and students’ acceptance of either approach. In doing so, we identify suitable conditions and recommendations for teaching Vulkan to both undergraduate and graduate students.

Materials Nanoarchitectonics for Advanced Physics Research

AbstractNanoarchitectonics combines nanotechnology with existing fields such as organic chemistry, supramolecular chemistry, materials science, microfabrication, and bio‐chemistry. It is a concept to create the architecture of atoms, molecules, nanomaterials, and other units for use in functional material systems through various processes. Structural control through nanoarchitectonics can contribute to a variety of fields for advanced physical research. New physical properties can be controlled by forming atomic arrangements, molecular designs, polymer syntheses, crystal structures, self‐assembled structures, and superstructures. Construction of nanospace structures can also elucidate the specific physical properties of molecules trapped in them. Thus, nanoarchitectonics has great potential to contribute to advanced physical research. This paper will discuss some perspectives, categorizing the examples into those that focus on structure formation, those related to optical and photonic functions, those that exploit electronic and electrical properties, and those oriented toward device applications. The presented examples ensure significant contribution of nanoarchitectonics to advanced physical research.

Classifying animal behavior from accelerometry data via recurrent neural networks

We study the classification of animal behavior from accelerometry data using various recurrent neural network (RNN) models. RNNs have extensively been employed to classify time-series data in various applications. However, their utilization for classifying animal behavior from wearable sensor data, particularly accelerometry data, as well as the underlying accuracy-complexity trade-offs is rather under-explored. We use four triaxial accelerometry datasets acquired from grazing cattle via collar tags or ear tags to evaluate the classification performance and complexity of the considered RNN models, which feature long short-time memory (LSTM) or gated recurrent unit (GRU) architectures with varying depths and widths. In the evaluations, we also include two state-of-the-art convolutional neural network (CNN)-based time-series classification models. The results show that the considered RNN-based models can achieve similar or higher animal behavior classification accuracy compared to the CNN-based models while having smaller computational and memory requirements. We also observe that the GRU-based models generally outperform the LSTM-based ones in terms of classification accuracy despite being less complex. A single-layer uni-directional GRU model with 64 hidden units appears to offer a good balance between accuracy and complexity making it suitable for implementation on edge/embedded devices.

Towards Highly Efficient Nitrogen Dioxide Gas Sensors in Humid and Wet Environments Using Triggerable-Polymer Metasurfaces.

We report simulations on a highly-sensitive class of metasurface-based nitrogen dioxide (NO2) gas sensors, operating in the telecom C band around the 1550 nm line and exhibiting strong variations in terms of the reflection coefficient after assimilation of NO2 molecules. The unit architecture employs a polymer-based (polyvinylidene fluoride-PVDF or polyimide-PI) motif of either half-rings, rods, or disks having selected sizes and orientations, deposited on a gold substrate. On top of this, we add a layer of hydrophyllic polymer (POEGMA) functionalized with a NO2-responsive monomer (PAPUEMA), which is able to adsorb water molecules only in the presence of NO2 molecules. In this process, the POEGMA raises its hidrophyllicity, while not triggering a phase change in the bulk material, which, in turn, modifies its electrical properties. Contrary to absorption-based gas detection and electrical signal-based sensors, which experience considerable limitations in humid or wet environments, our method stands out by simple exploitation of the basic material properties of the functionalized polymer. The results show that NO2-triggered water molecule adsorption from humid and wet environments can be used in conjunction with our metasurface architecture in order to provide a highly-sensitive response in the desired spectral window. Additionally, instead of measuring the absorption spectrum of the NO2 gas, in which humidity counts as a parasitic effect due to spectral overlap, this method allows tuning to a desired wavelength at which the water molecules are transparent, by scaling the geometry and thicknesses of the layers to respond to a desired wavelength. All these advantages make our proposed sensor architecture an extremely-viable candidate for both biological and atmospheric NO2 gas-sensing applications.

Developing A Contextual Combinational Approach for Predictive Analysis of Users Mobile Phone Trajectory Data in LBSNs

Today, smartphones, due to their ubiquity, have become indispensable in human daily life. Progress in the technology of mobile phones has recently resulted in the emergence of several popular services such as location-based social networks (LBSNs) and predicting the next Point of Interest (POI), which is an important task in these services. The gathered trajectory data in LBSNs include various contextual information such as geographical and temporal contextual information (GTCI) that play a crucial role in the next POI recommendations. Various methods, including collaborating filtering (CF) and recurrent neural networks, incorporated the contextual information of the user’ trajectory data to predict the next POIs. CF methods do not consider the effect of sequential data on modeling, while the next POI prediction problem is inherently a time sequence problem. Although recurrent models have been proposed for sequential data modeling, they have limitations such as similarly considering the effect of contextual information. Nonetheless, they have a separate impact as well. In the current study, a geographical temporal contextual information-extended attention gated recurrent unit (GTCI-EAGRU) architecture was proposed to separately consider the influence of geographical and temporal contextual information on the next POI recommendations. In this research, the GRU model was developed using three separate attention gates to consider the contextual information of the user trajectory data in the recurrent layer GTCI-EAGRU architecture, including timestamp, geographical, and temporal contextual attention gates. Inspired by the assumption of the matrix factorization method in CF approaches, a ranked list of POI recommendations was provided for each user. Moreover, a comprehensive evaluation was conducted by utilizing large-scale real-world datasets based on three LBSNs, including Gowalla, Brightkite, and Foursquare. The results revealed that the performance of GTCI-EAGRU was higher than that of competitive baseline methods in terms of Acc@10, on average, by 42.11% in three datasets.

GPU-Based Cellular Automata Model for Multi-Orient Dendrite Growth and the Application on Binary Alloy

To simulate dendrite growth with different orientations more efficiently, a high-performance cellular automata (CA) model based on heterogenous central processing unit (CPU)+ graphics processing unit (GPU) architecture has been proposed in this paper. Firstly, the decentered square algorithm (DCSA) is used to simulate the morphology of dendrite with different orientations. Secondly, parallel algorithms are proposed to take full advantage of many cores by maximizing computational parallelism. Thirdly, in order to further improve the calculation efficiency, the task scheduling scheme using multi-stream is designed to solve the waiting problem among independent tasks, improving task parallelism. Then, the present model was validated by comparing its steady dendrite tip velocity with the Lipton–Glicksman–Kurz (LGK) analytical model, which shows great agreement. Finally, it is applied to simulate the dendrite growth of the binary alloy, which proves that the present model can not only simulate the clear dendrite morphology with different orientations and secondary arms, but also show a good agreement with the in situ experiment. In addition, compared with the traditional CPU model, the speedup of this model is up to 158×, which provides a great acceleration.

Physical simulation of remaining oil distribution in the 3rd-order architecture unit in beach sand reservoir

Introduction:Oilfield development’s primary objective has changed in recent years as a result of a deeper focus on oilfield exploration and possible reservoir oil extraction. These days, the distribution and characteristics of residual oil are hot topics.Methodology:This research study provides a physical simulation of the remaining oil distribution in the third-order architectural unit in the beach reservoir. Based on the reservoir geometry and compositional sequence, the third-order architecture unit in a beach sand reservoir can be divided into three types: layered, plate-like, and trough-like architecture units.Results and Discussion:A water-flooding simulation experiment is performed to find the distribution pattern of remaining oil (shortened as RO and used hereafter) and the controlling effect of the mudstone interlayer. The simulation results revealed that in the layered architecture unit with reverse-graded bedding, RO is mainly distributed between interlayers and accumulates at the bottom in fine-grain sands. The horizontal distribution of the mudstone interlayer has a profound effect on blocking the longitudinal migration of fluid. Second, in the plate-like architecture unit with uniform grain size, RO is mainly found in the middle portion of the model, separated by clay interlayers, with irregular presence of RO in the upper and lower part of the model. The oblique distribution of the clay interlayer has a significant effect on blocking the lateral migration of the fluid. Thirdly, in the trough-like architectural unit with normal-graded bedding, the RO is mainly distributed on top of the model in fine-grain sands and on the ridge-like parts formed by the interlayer’s intersection.Conclusion:A trough-like clay interlayer can promote fluid movement. RO distribution patterns from the current experiment can be used to explore the remaining oil in beach sand reservoirs of similar oilfields.

Active Materiality as The Basis of Architectural Design in Dealing with Pollution

This paper describes the architectural design process based on an understanding of living materials’ properties and their growth process in response to pollution. The development of the design method was based on the existence of living materials and their potential to be the active unit of architecture. Living materials could actively grow and adapt through their reactions to external factors, in this case, pollution, allowing the material to be in a passive phase temporarily due to the forces. This paper focuses on the development of design methods based on the understanding of algae, fungi, and lichen as the living materials that will detect and detoxify air and soil pollution around Daan Mogot, West Jakarta. By conducting research through design, this paper then proposes architectural design by injecting the active-passive growth process of living materials (algae, fungi, and lichen) into the context using split and absorb mechanisms. In response to pollution, the active and passive schemes of living materials become the foundation of architectural design. This paper then proposes the term "active materiality," considering the existence and capability of the living materials as the active unit. The development of an architectural design method in this study demonstrates the possibility of design ideas to enhance dialogue between humans, other living things, and the environment and to develop programming to respond to environmental issues.

Domestic Space in France and Belgium: Art, Literature and Design, 1850–1920 ed. by Claire Moran

Reviewed by: Domestic Space in France and Belgium: Art, Literature and Design, 1850–1920ed. by Claire Moran Camilla Murgia Domestic Space in France and Belgium: Art, Literature and Design, 1850–1920. Ed. by C laireM oran. ( Material Culture of Art and Design) New York: Bloomsbury Visual Arts. 2022. xxi+ 343 pp. £81. ISBN 978-1-5013-4169-4. Recent scholarship has increasingly paid attention to the role of interiors and their multiple impacts on arts, literature, design, and visual culture across the long nineteenth century. Claire Moran points out this growing and multidisciplinary research interest in the Introduction to Domestic Space in France and Belgium(p. 1). The book aims to study the interior through different methodological approaches, considering the relation between inside and outside, and to deal with various topics, from literary texts to pictorial representations and architectural units. However, Moran, together with the other scholars in this volume, does much more than that. The collection as a whole combines a discussion of the agency of space with analysis of the ways in which the notions of interior and domesticity intervene in artistic, literary, and cultural practices. Moran highlights the book's purpose of studying the domestic interior as a 'modernist phenomenon' (p. 4), thus significantly widening the discussion of spatiality and domesticity to include literary, architectural, and art-historical contexts. The book consists of thirteen chapters organized in three parts, exploring different aspects of the relationship between space and domesticity. The first part, 'Representing [End Page 139]the Domestic Interior', consists of six chapters discussing the representation of interiors through visual and literary documents and sources. Matteo Piccioni deals with a particular chronological frame—the July Monarchy—examining a rich range of satirical images and 'panoramic literature' (pp. 23–28). Ulrike Müller and Marjan Sterckx focus on private collectors' spaces in Belgium, while Moran deals with visual and literary material, including Fernand Khnopff's and James Ensor's artworks and the writings of Maurice Maeterlinck and Georges Rodenbach, to name but a few. Moran considers the relationship between internal and external spaces (p. 80) and addresses issues regarding 'in-betweenness' (p. 81), discussing the characteristics of Belgian art and literature with depth and flair. Anne Green's chapter focuses on a vast corpus of French texts, including novels and writings by Gustave Flaubert, Émile Zola, and Maxime Du Camp, while Nathalie Aubert focuses on texts by Georges Rodenbach and Marcel Proust. Dominique Bauer provides an outstanding examination of spatial images of the domestic interior, analysing Jules Romains's Cromedeyre-le-Vieiland providing a thought-provoking investigation of notions such as unanimism (pp. 122–25). The second part of the book, entitled 'Gender and Domestic Space', consists of three chapters considering the representations of domestic interiors from a gender-related perspective. For instance, Sinéad Furlong-Clancy studies the domestic space as depicted by Berthe Morisot and Mary Cassatt. Attention is paid in this part of the volume to the bourgeois dimension of the material studied. Caroline Ardrey explores the notion of bricolage, considering three journals as diverse as La Ménagère, La Mode illustréeand Stéphane Mallarmé's La Dernière Mode. Through the prism of Claude Lévi-Strauss's discussion of the notion of bricolage, Ardrey aims to study how the feminine press employed and relied on this activity, which was thought to be the preserve of masculine spheres. Aina Marti analyses the relation between bourgeois homes and sexualities in Colette's Claudineseries, showing how sexuality allows us to investigate domesticity through the description of characters' living spaces, such as Rézi's room (pp. 193–96) or Renaud's apartment (pp. 196–200). Finally, the third part, entitled 'Aesthetics and the Domestic Interior', reviews some aspects of art and architecture, following comparative and specific angles. Aniel Guxholli compares Art Nouveau and Belgian Symbolism, while Jill Owen relies on Balzac and Impressionism to interrogate the notion of ekphrasis. Maria Golovteeva deals more specifically with the interior of Villa Khnopff in Brussels, which survives only in photographs, studying the impact that Symbolism and Symbolist theories had on the domestic space. Finally, Anna Jozefacka studies the values of private space...

Scalable solutions for the Control Unit of the KM3NeT DAQ system

The neutrino telescopes of KM3NeT are being incrementally expanded, and will reach their final size in the coming years. New versions of optical modules running new versions of firmware and new instrumentation for calibration are being introduced in the originally repetitive lattice. The inner architecture and data flow of the Control Unit of the KM3NeT telescopes is described, with information about computational and architectural complexity. The current goal is to control two full blocks of the KM3NeT/ARCA detector, i.e. 4370 CLBs and 128340 photomultipliers for 230 detection units, with a single mid-range commercial server machine. The system is designed with software protections and fault tolerance for hardware failure.

Shared Memory Semi-Implicit Solver for Hydrodynamical Instability Processes

The Advection-Diffusion Reaction (ADR) equation appears in many problems in nature. This constitutes a general model that is useful in various scenarios, from porous media to atmospheric processes. Particularly, it is used at the interface between two fluids where different types of instabilities due to surface mobility may appear. Together with the ADR equation, the Darcy-Brinkman model describes the phenomena known as fingering that appear in different contexts. The study of this type of system gains in complexity when the number of chemical species dissolved in both fluids increases. With more solutes, the increasing complexity of this phenomenon generally requires much computational power. To face the need for more computational resources, we build a solver tool based on an Alternating Direction Implicit (ADI) scheme that can be run in Central Processing Unit (CPU) and Graphic Processing Unit (GPU) architectures on any notebook. The implementation is done using the MATLAB platform to compare both versions. It is shown that using the GPU version strongly saves both resources and calculation times.

Anomaly Detection in IoT Networks: Machine Learning Approaches for Intrusion Detection

The proliferation of Internet of Things (IoT) devices has ushered in an era of unprecedented connectivity and innovation. However, this interconnected landscape also presents unique security challenges, necessitating robust intrusion detection mechanisms. In this research, we present a comprehensive study of anomaly detection in IoT networks, leveraging advanced machine learning techniques. Specifically, we employ the Gated Recurrent Unit (GRU) architecture as the backbone network to capture temporal dependencies within IoT traffic. Furthermore, our approach embraces hierarchical federated training to ensure scalability and privacy preservation across distributed IoT devices. Our experimental design encompasses public IoT datasets, facilitating rigorous evaluation of the model's performance and adaptability. Results indicate that our GRU-based model excels in identifying a spectrum of attacks, from Distributed Denial of Service (DDoS) incursions to SQL injection attempts. Visualizations of learning curves, Receiver Operating Characteristic (ROC) curves, and confusion matrices offer insights into the model's learning process, discriminatory power, and classification performance. Our findings contribute to the evolving landscape of IoT security, offering a roadmap for enhancing the resilience of interconnected systems in an era of increasing connectivity.

A Class of Inertial Measurement Units for Low-Noise Angular Velocity Estimation

An Inertial Measurement Unit (IMU) architecture estimating angular velocity is introduced. It expands the concept of multi-accelerometers gyroscope-free IMUs (GF-IMUs), taking advantage of their excellent noise performance and resolving their inability to compensate for accelerometers’ bias and their requirement for specific accelerometers placement, which makes GF-IMUs inappropriate for real world applications. It does so by embedding the accelerometers in a low-bandwidth closed-loop configuration with a three-axis gyroscope and by addressing the complete non-linear dynamics. Extensive theoretical analysis provides a complete framework for designing low-noise IMUs including sufficient stability criteria for the non-linear system’s dynamics. Simulation and experimental results support the theoretical analysis and indicate that even a minimal system using the proposed architecture can outperform the gyroscope in noise performance by at most 15dB in some frequency range.

The Tomb of Petophois: Tomb 5 in the Necropolis of Bir el‑Shaghalaمقبرة بتوفويس: المقبرة ٥ في جبانة بير الشغالة

This article presents the results of the excavation of a newly discovered tomb (no. 5) in Bir elShaghala, a necropolis located in the Dakhla Oasis. It belongs to Petophois, Padiwepwaut, who was one of the most important members of the elite society of Mothis (Mut). The superstructure of the tomb has two chambers and a rectangular hall leads to the pyramid chamber, which is the most prominent element of the superstructure of the tomb complex. These three architectural units functioned as a funerary floor for the tomb’s visitors. The subterranean structure consists of a rectangular antechamber with a vaulted ceiling and the burial chamber. The tomb has a small shaft in the vaulted ceiling of the burial chamber connected with a long tube passing through the southern subterranean structure and terminating in another shaft in the outside face of the south wall. Most decorations and texts cast light on the 24th, 25th and 26th days of the Osirian Khoiak Festival, with the tomb owner and his family standing in the attitude of adoration in front of Sokar-Osiris and Osiris. The approximate dating is to the Roman period, possibly to the reign of Trajan.

On Temples, Palaces and the Case of Hazor’s Building 7050: Classifying Ancient Architecture Based on Archaeological Methods

This paper addresses a major methodological issue faced by archaeologists when seeking to apply clear definitions to architectural units. Temples and palaces dominate the Bronze Age landscape of the southern Levant. But what are the parameters for distinguishing between these two types of spaces? Architectural analysis on its own can lead to misguided conclusions. A structure must be further contextualized on the local and regional levels, and the use of its interior space must be understood. This paper focuses specifically on the classification of Hazor’s Building 7050, a monumental Late Bronze Age building that sits atop the site’s acropolis. A detailed study of Building 7050’s architecture, space syntax, activity types, metrology, and the site’s urban planning demonstrates that the complex was modeled on cultic, not palatial, space.

Arhitektonski triptih u Bigovu - stambeni objekat Bigovo 3, Bigovo, Crna Gora, autori projekta: Verica Krstić, Vasilije Milunović, Jelena Ivanović Vojvodić

The Bigovo complex is an architectural unit consisting of three buildings in the village of Bigovo on the Montenegrin coast. The buildings were designed by architects Vasilije Milunović, Jelena Ivanović Vojvodić and Verica Krstić. The architecture of the complex is an example of contextual functionalism. The buildings are organically unified with the terrain and vegetation, and their form and composition naturally develop from the environment. The authors have created a discreet modern interpretation of the traditional architecture of the area. The complex is open towards the sea, and the internal organization enables each room to have maximum openness.

Electrical Insulator Surface Condition Analysis Based on Joint Fully Convolutional and Multiscale Spatial Pooling Attention Network

Health condition monitoring of insulators is one of the key factors to ensure a stable power supply. This article proposes an automated insulator surface condition analysis approach based on vision measurement and the convolutional neural network (CNN). Specifically, we consider the condition analysis of insulators as an image multiclassification problem. An insulator image is first fed into a feature extractor, implemented by leveraging CNN, to extract features automatically. Then, a softmax classifier is utilized to map the feature representation into a probability vector to obtain the analysis results. Considering that neither each layer nor each location of features has the same impact on classification performance, we further focus on feature relationships and present a novel attention architectural unit, called the joint fully convolutional and multiscale spatial pooling attention (JFCMSPA) module. This new attention module not only considers the friendly fusion of different pooled information but also introduces the local similarity property of images into visual attention for the first time. These new insights allow it to efficiently learn feature importance. Finally, experimental results demonstrate the effectiveness of the proposed method and the value of its application in the inspection of power equipment.