Modern Hardware Research Articles

Edge Container for Speech Recognition

Containerization has been mainly used in pure software solutions, but it is gradually finding its way into the industrial systems. This paper introduces the edge container with artificial intelligence for speech recognition, which performs the voice control function of the actuator as a part of the Human Machine Interface (HMI). This work proposes a procedure for creating voice-controlled applications with modern hardware and software resources. The created architecture integrates well-known digital technologies such as containerization, cloud, edge computing and a commercial voice processing tool. This methodology and architecture enable the actual speech recognition and the voice control on the edge device in the local network, rather than in the cloud, like the majority of recent solutions. The Linux containers are designed to run without any additional configuration and setup by the end user. A simple adaptation of voice commands via configuration file may be considered as an additional contribution of the work. The architecture was verified by experiments with running containers on different devices, such as PC, Tinker Board 2, Raspberry Pi 3 and 4. The proposed solution and the practical experiment show how a voice-controlled system can be created, easily managed and distributed to many devices around the world in a few seconds. All this can be achieved by simple downloading and running two types of ready-made containers without any complex installations. The result of this work is a proven stable (network-independent) solution with data protection and low latency.

Methods to find digital footprints on a personal computer

Digital footprints remain on a personal computer no matter how hard PC users try to wipe them. This paper can be useful both as an instruction to find such footprints and as an instruction for their destruction. The paper is devoted to the overview of specific examples of the use of modern hardware and hardware-software systems to find digital footprints of activity directly on a personal computer. The options to obtain information from random access memory (RAM), hard drives and SSD devices are described in detail. For example, the following information can be obtained from a dump of the RAM of a PC: running processes, network connections, passwords, various encryption keys, clipboard, etc.

BioDynaMo: a modular platform for high-performance agent-based simulation.

MotivationAgent-based modeling is an indispensable tool for studying complex biological systems. However, existing simulation platforms do not always take full advantage of modern hardware and often have a field-specific software design.ResultsWe present a novel simulation platform called BioDynaMo that alleviates both of these problems. BioDynaMo features a modular and high-performance simulation engine. We demonstrate that BioDynaMo can be used to simulate use cases in: neuroscience, oncology and epidemiology. For each use case, we validate our findings with experimental data or an analytical solution. Our performance results show that BioDynaMo performs up to three orders of magnitude faster than the state-of-the-art baselines. This improvement makes it feasible to simulate each use case with one billion agents on a single server, showcasing the potential BioDynaMo has for computational biology research.Availability and implementationBioDynaMo is an open-source project under the Apache 2.0 license and is available at www.biodynamo.org. Instructions to reproduce the results are available in the supplementary information.Supplementary informationAvailable at https://doi.org/10.5281/zenodo.5121618.

MATLAB BASED HIL FRAMEWORK: A GUIDE TO BUILD A HARDWARE IN THE LOOP DAQ PERIPHERAL

Testing and validating modern hardware such as some subsystems in modern vehicles is a little challenging especially before assembling them into the final product. To achieve a valid real-time test, the tested hardware or unit must be placed into its real-time environment which is not possible in some cases. Recently, and with the presence of advanced simulation software applications, the hardware environment could be simulated easily to fulfill the real-time test properly. Simulating an environment in one loop with real physical hardware knowing as Hardware-in-the-loop is used nowadays in various development fields, medical, industrial, research, and education. Amongst the aforementioned, HIL is widely used in control systems applications. In the paper, building a framework to enable hardware in the loop (HIL) simulation with the aid of MATLAB/Simulink is discussed. Over serial communication, and inexpensive data acquisition (DAQ) peripheral has been developed using a microcontroller unit. the development of the framework is discussed to be used as a guide for building it by using any microcontroller. The resultant performance appeal to excellent real-time response with quite a small delay of about 70ms in the worst case.

Multichannel Analysis of Surface Waves Accelerated (MASWAccelerated): Software for efficient surface wave inversion using MPI and GPUs

Multichannel Analysis of Surface Waves (MASW) is a technique frequently used in geotechnical engineering and engineering geophysics to infer 1D layered models of seismic shear wave velocities in the top tens to hundreds of meters of the subsurface. We aim to accelerate MASW calculations by capitalizing on modern computer hardware available in the workstations of most engineers: multiple cores and graphics processing units (GPUs). We propose new parallel and GPU accelerated algorithms for computing 1D MASW inversion, and provide software implementations in C using Message Passing Interface (MPI) and CUDA. These algorithms take advantage of sparsity that arises in the problem, and the work balance between processes considers typical data trends. We compare our methods to an existing open source Matlab MASW tool. Our serial C implementation achieves a 2x speedup over the Matlab software, and we continue to see improvements by parallelizing the problem with MPI. We see nearly perfect strong and weak scaling for uniform data, and improve strong scaling for realistic data by repartitioning the problem to process mapping. By utilizing GPUs available on most modern workstations, we observe an additional 1.3x speedup over the serial C implementation on the first use of the method. We typically repeatedly evaluate theoretical dispersion curves as part of an optimization procedure, and on the GPU the kernel can be cached for faster reuse on later runs. We observe a 3.2x speedup on the cached GPU runs compared to the serial C runs. This work is the first open-source parallel or GPU-accelerated software tool for MASW imaging, and should enable geotechnical engineers to fully utilize all computer hardware at their disposal.

An exponential integrator/WENO discretization for sonic-boom simulation on modern computer hardware

Recently a splitting approach has been presented for the simulation of sonic-boom propagation. Splitting methods allow one to divide complicated partial differential equations into simpler parts that are solved by specifically tailored numerical schemes. The present work proposes a second order exponential integrator for the numerical solution of sonic-boom propagation modelled through a dispersive equation with Burgers' nonlinearity. The linear terms are efficiently solved in frequency space through FFT, while the nonlinear terms are efficiently solved by a WENO scheme. The numerical method is designed to be highly parallelisable and therefore takes full advantage of modern computer hardware. The new approach also improves the accuracy compared to the splitting method and it reduces oscillations. The enclosed numerical results illustrate that parallelisation on a CPU results in a speedup of 22 times faster than the straightforward sequential version. The GPU implementation further accelerates the runtime by a factor 3, which improves to 5 when single precision is used instead of double precision.

СТЕНД СИСТЕМ И СРЕДСТВ АВТОМАТИЗАЦИИ ОБОРУДОВАНИЯ РЕЗЕРВУАРНЫХ ПАРКОВ НЕФТЕПРОДУКТОВ

The aim of the work is to develop a general structure of the stand that simulates the operation of systems and means of automation of equipment for tank farms of oil products using modern hardware and software, for researching the operation of algorithms for protection and interlocks, alarms and automatic control in accordance with the current regulatory documentation based on modern micro- processor systems. The method of system analysis, the theory of automatic control, structural solutions of human-machine systems intended for the automation of production and intelligent support of control processes and the necessary data processing in organizational, technological and distributed control systems were used. The concept of the stand, the block diagram of the control system and the hydraulic diagram of the stand have been developed. The novelty of the work lies in the creation of a compact model of a tank farm with a complex distributed control system for researching its operation.

Improved Lorenz-Mie Look-Up Table for Lidar and Polarimeter Retrievals

Lidar and polarimeter aerosol microphysical retrievals require calculating single-scattering properties that are computationally expensive. One of the easiest ways to speed up these calculations is to use a look-up table. Two important currently available look-up tables were created about 15 years ago. Advancements in modern computational hardware allows us to create a new look-up table with improved precision over a larger range of aerosol properties. In this new and improved Lorenz-Mie look-up table we tabulate the light scattering by an ensemble of homogeneous isotropic spheres at arbitrary wavelengths starting from 0.355 μm. The improved look-up table covers spherical atmospheric aerosols with radii in the range of 0.001–100 μm, with real parts of the complex refractive index in the range of 1.29–1.65, and with imaginary parts of the complex refractive index in the range of 0–0.05. We test twelve wavelengths from 0.355 to 2.264 μm and find that the elements of the normalized scattering matrix as well as the asymmetry parameter, the aerosol absorption, backscatter, extinction, and scattering coefficients are precise to within 1% for 99.99% of cases. The look-up table together with C++, Fortran, Matlab, and Python codes are freely available online.

Justification of the N eed for Locomotive Diagnostic Systems

In the world and domestic practices of technical maintenance and repair (TMR) of locomotives there exists a tendency for the expanded use of technical diagnostics systems, the transition to predictive repair to reduce the costs of their life cycle. Modern hardware and software tools make it possible to create automated technical diagnostics systems (ATDS) for all types of locomotive equipment but equipping service repair locomotive depots with them requires significant capital costs with an unacceptably long payback period. The objective of the work is to develop a method and a corresponding simulation modelling software program to determine technical and economic feasibility of using certain means of technical diagnostics.Diagnostic systems reduce waiting time for repairs, the volume and cost of scheduled and unscheduled TMR, which makes it possible to reduce the operating fleet of locomotives.In modern economic calculations, to assess the success of an investment project, the indicator «Net present value (NPV)» of the project is used. Based on this principle, in relation to ATDS, a method for determining feasibility of introducing various types of ATDS and the corresponding methodology and software made with the algorithmic language VBA (Visual BASIC for Applications) in the MS Excel environment has been developed.The work carried out simulation modelling for Russian conditions of the payback of main types of diagnostic systems comprising on-board based microprocessor control systems, rheostat testing stations for diesel locomotives, diagnostics of traction motors, etc. The economic feasibility of introducing these systems has been proved. Also, economically inexpedient diagnostic systems have been identified, f o r example, automatic measurement of the profile of a wheel set tire.

Game Effect Based on Particle System in Unity 3D

The gaming industry has been one of the main driving forces behind the development of advanced modern hardware such as multi-core, hyperthreaded processors, high-performance graphics processing units (GPUs), advanced sound processing devices, and extraordinary human-computer interface devices such as virtual reality helmets and brain sensor caps . The computer gaming industry has grown by leaps and bounds, becoming a mainstream software development sector, and earning billions of dollars in revenue each year. Computer games are like a book, a movie, or a museum .

Real-time neural radiance caching for path tracing

We present a real-time neural radiance caching method for path-traced global illumination. Our system is designed to handle fully dynamic scenes, and makes no assumptions about the lighting, geometry, and materials. The data-driven nature of our approach sidesteps many difficulties of caching algorithms, such as locating, interpolating, and updating cache points. Since pretraining neural networks to handle novel, dynamic scenes is a formidable generalization challenge, we do away with pretraining and instead achieve generalization via adaptation , i.e. we opt for training the radiance cache while rendering. We employ self-training to provide low-noise training targets and simulate infinite-bounce transport by merely iterating few-bounce training updates. The updates and cache queries incur a mild overhead---about 2.6ms on full HD resolution---thanks to a streaming implementation of the neural network that fully exploits modern hardware. We demonstrate significant noise reduction at the cost of little induced bias, and report state-of-the-art, real-time performance on a number of challenging scenarios.

Multi-Temperate Logical Data Warehouse Design for Large-Scale Healthcare Data

Modern hardware architectures and advances in database technology are driving increased adoption of logical data warehouses (LDWs) that complement traditional physical data warehousing (PDW) approaches. In contrast to PDW design methodologies that emphasize physical consolidation of all data of interest on a single (perhaps distributed) computing platform, along with early-binding approaches that pre-materialize transformations and changes to the source data, LDW techniques allow for the integration and transformation of data at run-time and typically physically move or modify much less data in advance. In an environment with premium hardware such as multi-temperate storage, the successful design of LDWs depends on replication of high value data to their physical core to maximize spatial locality. Identifying and collocating high value data is a non-trivial task that has not been adequately explored in the context of LDWs in multi-temperate storage systems. In this paper, we gather queries to construct an OLAP workload for use in supporting and evaluating LDW design algorithms for a large healthcare organization. We introduce new algorithms to address the preprocessing of the workload, identification of data clusters to support OLAP queries, and assignment of clusters to appropriate (hot, warm, and cold) storage tiers, allowing the LDW to deliver results more efficiently by covering a higher percentage of its query workload using the fastest storage devices. Any use case involving copying data from sources to tiered storage targets for analytic querying could benefit from the techniques and solutions presented here.

Chopping off the Tail: Bounded Non-Determinism for Real-Time Accelerators

Modern data centers run web-scale applications on tens of thousands of servers, generating tens of thousands of Remote Procedure Calls (RPCs) to backend services for each incoming user request. Tail latency, due to a small fraction of randomly slow RPCs, decreases the performance of these incoming requests, degrades users' quality of experience, and limits disaggregation (applications' ability to scale across a data center). We argue that current approaches to improve tail latency (especially, those bounding computation time) are insufficient, even with (reconfigurable-) hardware accelerators. Instead, to chop off the tail, datacenter services should dynamically trade correctness (or result quality) for timeliness, providing bounded latency with near-ideal accuracy. In this paper, we discuss how the increasing prevalence of machine learning (including search techniques like approximate nearest neighbor and PageRank), perceptual algorithms (like computational photography and image/video caching), and natural language processing lets modern hardware accelerators make these dynamic correctness tradeoffs while improving users' quality of experience.

Mansard Roofline Model: Reinforcing the Accuracy of the Roofs

Continuous enhancements and diversity in modern multi-core hardware, such as wider and deeper core pipelines and memory subsystems, bring to practice a set of hard-to-solve challenges when modeling their upper-bound capabilities and identifying the main application bottlenecks. Insightful roofline models are widely used for this purpose, but the existing approaches overly abstract the micro-architecture complexity, thus providing unrealistic performance bounds that lead to a misleading characterization of real-world applications. To address this problem, the Mansard Roofline Model (MaRM), proposed in this work, uncovers a minimum set of architectural features that must be considered to provide insightful, but yet accurate and realistic, modeling of performance upper bounds for modern processors. By encapsulating the retirement constraints due to the amount of retirement slots, Reorder-Buffer and Physical Register File sizes, the proposed model accurately models the capabilities of a real platform (average rRMSE of 5.4%) and characterizes 12 application kernels from standard benchmark suites. By following a herein proposed MaRM interpretation methodology and guidelines, speed-ups of up to 5× are obtained when optimizing real-world bioinformatic application, as well as a super-linear speedup of 18.5× when parallelized.

Fast data series indexing for in-memory data

Data series similarity search is a core operation for several data series analysis applications across many different domains. However, the state-of-the-art techniques fail to deliver the time performance required for interactive exploration, or analysis of large data series collections. In this work, we propose MESSI, the first data series index designed for in-memory operation on modern hardware. Our index takes advantage of the modern hardware parallelization opportunities (i.e., SIMD instructions, multi-socket and multi-core architectures), in order to accelerate both index construction and similarity search processing times. Moreover, it benefits from a careful design in the setup and coordination of the parallel workers and data structures, so that it maximizes its performance for in-memory operations. MESSI supports similarity search using both the Euclidean and dynamic time warping (DTW) distances. Our experiments with synthetic and real datasets demonstrate that overall MESSI is up to 4x faster at index construction and up to 11x faster at query answering than the state-of-the-art parallel approach. MESSI is the first to answer exact similarity search queries on 100GB datasets in \(\sim \)50 ms (30–75 ms across diverse datasets), which enables real-time, interactive data exploration on very large data series collections.

Present-day vehicular traffic tunnels in designing stage and under construction

The characteristics are given for the tunnels of the principal countries where vehicular traffic tunnels are being designed, constructed and used. The analysis of the data has shown that the existing ventilation systems that operate in a stable economic regime call for the use of natural draught along with the modern hardware. Using Rikoti and Rocki vehicular traffic tunnels as an example, it has been shown that the longitudinal and transverse ventilation scheme employed in Rikoti and Rocki vehicular traffic tunnels is inconsistent with the internationally accepted schemes for the tunnels of similar length. A comparison has been made between the ventilation system of 6560 m long tunnel in Norway (Fodnes) and that of Rikoti tunnel. The analysis of tunnel cross-section configurations, geometric parameters and the schematic diagrams of ventilator arrangement has shown the advantage of the replacement of the semi-longitudinal ventilation scheme existing in Rikoti tunnel by the longitudinal scheme. Table 1 provides a list of vehicular traffic tunnels, both in-service and under construction. A separate table 1 includes the parameters of tunnels under construction in Germany and Norway. 111.2, tabl. 2, bibl.2.

Practical comparisons of EIT excitation protocols with applications in high-contrast imaging

In the field of electrical impedance tomography (EIT), numerous studies have aimed at the optimal excitation/measurement strategies for improving conductivity distribution imaging, particularly in the applications involving highly contrasted materials. These studies focus on the conditions to be imposed on the currents fed into the electrodes and on their measurement counterparts, while making use of various quantitative optimal criteria. While most EIT systems rely on a sequential excitation at neighboring electrodes with measurements at the remaining ones, some alternative excitation strategies, or protocols, have also proven to be effective and easy to implement using modern hardware. In this context, the present study aims at confronting some of the predominant EIT excitation protocols on a practical system that is dedicated to the imaging of media with highly contrasted material components, i.e. with large variations of the conductivity field. More specifically, the so-called adjacent, opposite, full-scan and trigonometric excitation strategies are considered here and assessed on a number of criteria, which are: complexity of a practical implementation, number of independent measurements, amplitude of the measured responses, sensitivity distribution and quality of the final reconstructed images. For each of these excitation protocols, numerical simulations and static experiments with test objects placed in the EIT sensor considered are carried out using various conductivity profiles, while reconstructed images are evaluated both qualitatively and qualitatively. Our results highlight the preeminence of the full-scan and trigonometric strategies, which are characterized by high response signals and satisfying overall sensitivities. Moreover, for the studied configurations in both numerical simulations and static experiments, the full scan and trigonometric strategies lead to improved contrasts in the reconstructed images of the phases distribution.

Cybersecurity Considerations for Grid-Connected Batteries with Hardware Demonstrations

The share of renewable and distributed energy resources (DERs), like wind turbines, solar photovoltaics and grid-connected batteries, interconnected to the electric grid is rapidly increasing due to reduced costs, rising efficiency, and regulatory requirements aimed at incentivizing a lower-carbon electricity system. These distributed energy resources differ from traditional generation in many ways including the use of many smaller devices connected primarily (but not exclusively) to the distribution network, rather than few larger devices connected to the transmission network. DERs being installed today often include modern communication hardware like cellular modems and WiFi connectivity and, in addition, the inverters used to connect these resources to the grid are gaining increasingly complex capabilities, like providing voltage and frequency support or supporting microgrids. To perform these new functions safely, communications to the device and more complex controls are required. The distributed nature of DER devices combined with their network connectivity and complex controls interfaces present a larger potential attack surface for adversaries looking to create instability in power systems. To address this area of concern, the steps of a cyberattack on DERs have been studied, including the security of industrial protocols, the misuse of the DER interface, and the physical impacts. These different steps have not previously been tied together in practice and not specifically studied for grid-connected storage devices. In this work, we focus on grid-connected batteries. We explore the potential impacts of a cyberattack on a battery to power system stability, to the battery hardware, and on economics for various stakeholders. We then use real hardware to demonstrate end-to-end attack paths exist when security features are disabled or misconfigured. Our experimental focus is on control interface security and protocol security, with the initial assumption that an adversary has gained access to the network to which the device is connected. We provide real examples of the effectiveness of certain defenses. This work can be used to help utilities and other grid-connected battery owners and operators evaluate the severity of different threats and the effectiveness of defense strategies so they can effectively deploy and protect grid-connected storage devices.

A scalable parallel preconditioned conjugate gradient method for bundle adjustment

Bundle adjustment is a fundamental problem in computer vision, with important applications such as 3D structure reconstruction from 2D images. This paper focuses on large-scale bundle adjustment tasks, e.g., city-wide 3D reconstruction, which require highly efficient solutions. For this purpose, it is common to apply the Levenberg-Marquardt algorithm, whose bottleneck lies in solving normal equations. The majority of recent methods focus on achieving scalability through modern hardware such as GPUs and distributed systems. On the other hand, the core of the solution, i.e., the math underlying the optimizer for the normal equations, remains largely unimproved since the proposal of the classic parallel bundle adjustment (PBA) algorithm, which increasingly becomes a major limiting factor for the scalability of bundle adjustment. This paper proposes parallel preconditioned conjugate gradient (PPCG) method, a novel parallel method for bundle adjustment based on preconditioned conjugate gradient, which achieves significantly higher efficiency and scalability than existing methods on the algorithmic level. The main idea is to exploit the sparsity of the Hessian matrix and reduce its structure parameters through an effective parallel Schur complement method; the result of this step is then fed into our carefully designed PPCG method which reduces matrix operations that are either expensive (e.g., large matrix reverse or multiplications) or scales poorly to multi-processors (e.g., parallel Reduce operators). Extensive experiments demonstrate that PPCG outperforms existing optimizers by large margins, on a wide range of datasets.

РЕАЛІЗАЦІЯ МЕТОДУ КОВЗНОЇ МЕДІАНИ НА ПЛІС ДЛЯ ПОПЕРЕДНЬОГО ОПРАЦЮВАННЯ СИГНАЛІВ СЕНСОРІВ

The use of modern hardware platforms in the development of computer system components, including digital signal processing, allows to describe circuit solutions using specialized languages such as AlteraHDL, VHDL, Verilog, etc. One of the options for using the resources of programmable logic integrated circuits is to create digital components of signal pre-processing, in particular in information and measurement channels. The application of this approach is due to the presence of various distortions that lead to information and accuracy loss. Another problem is the need to preserve the information performance of such information and measurement channels. It is common to use analog implementations of signal pre-processing methods, in particular different types filters. In this case, the implementation of pre-processing methods at the hardware level will provide the appropriate processing speed at insignificant hardware costs. The paper proposes the implementation of the algorithm for processing information and measurement signals using the sliding median method, implemented on a programmable logic integrated circuit. Based on the simulation in a numerical experiment, the efficiency of using such a method is shown in a relatively simple implementation scheme on the FPGA platform. In fact, the pyramidal scheme of conditional constructions provides a simple description of the logical scheme by means of the Altera HDL language, and also allows to reduce the number of comparison operations. The proposed algorithm does not require complex hardware resources, which allows you to effectively involve typical circuit solutions.