Parallel Implementation Of Algorithm Research Articles

Embedding of Hypercube into Fractal Cubic Network

The implementation of parallel algorithms and the simulation of interconnection networks can be modeled into a graph embedding problem. Several cost parameters are used to assess the quality of an embedding. The wirelength is one of these factors that is frequently taken into account. A fractal cubic network is a new variant of the hypercube graph. In this study, we compute the wirelength of an embedding of the hypercube [Formula: see text] into the fractal cubic network [Formula: see text] using [Formula: see text]-partition.

Research and Implementation of FPGA Image Compression Parallel Algorithm Based on CCSDS

High-pixel, high-resolution spectral images are an important source of key graphical information obtained from space remote sensing, however, with the dramatically expanding amount of graphical information, the limited transmission bandwidth and hardware resources are difficult to meet the demand for massive data, which makes real-time image lossless compression and transmission technology an important solution. For this reason, this paper is based on the CCSDS image lossless compression algorithm, using FPGA for the construction of image compression system, and proposes a method strategy based on parallel acceleration algorithm to realize the real time processing of large-capacity hyperspectral images. The simulation results show that hyperspectral river and mountain range images can be compressed with greatly improved compression efficiency while maintaining real time performance and accuracy.

Physicist's view on the unbalanced k-cardinality assignment problem.

The k-cardinality unbalanced assignment problem asks for assigning k "agents" to k "tasks" on a one-to-one basis, while minimizing the total cost associated with the assignment, with the total number of agents N and the total number of tasks M possibly different and larger than k. While many exact algorithms have been proposed to find such an optimal assignment, these methods are computationally prohibitive when the problem is large. We propose an approach to solving the k-cardinality assignment problem using techniques adapted from statistical physics. This paper provides a full description of this formalism, including all the proofs of its main claims. We derive a strongly concave free-energy function that captures the constraints of the k-assignment problem at a finite temperature. We prove that this free energy decreases monotonically as a function of β, the inverse of temperature, to the optimal assignment cost, providing a robust framework for temperature annealing. We also prove that for large enough β values the exact solution to the k-assignment problem can be derived using simple round-off to the nearest integer of the elements of the computed assignment matrix. We show that this framework can be adapted to handle degenerate k-assignment problems. We describe a computer implementation of our framework that is optimized for the GPU parallel architecture, using the library CUDA. This implementation is found to be as efficient as state-of-the-art implementations of parallel Hungarian algorithms on generic assignment problems, and orders of magnitude faster than those algorithms for pathological assignment cases.

An approach for low-power heterogeneous parallel implementation of ALC-PSO algorithm using OmpSs and CUDA

PSO (particle swarm optimization), is an intelligent search method for finding the best solution according to population state. Various parallel implementations of this algorithm have been presented for intensive-computing applications. The ALC-PSO algorithm (PSO with an aging leader and challengers) is an improved population-based procedure that increases convergence rapidity, compared to the traditional PSO. In this paper, we propose a low-power heterogeneous parallel implementation of ALC-PSO algorithm using OmpSs and CUDA, for execution on both CPU and GPU cores. This is the first effort to heterogeneous parallel implementing ALC-PSO algorithm with combination of OmpSs and CUDA. This hybrid parallel programming approach increases the performance and efficiency of the intensive-computing applications. The proposed approach of this article is also useful and applicable for heterogeneous parallel execution of the other improved versions of PSO algorithm, on both CPUs and GPUs. The results demonstrate that the proposed approach provides higher performance, in terms of delay and power consumption, than the existence implementations of ALC-PSO algorithm.

Segmentation of Tree-Like Data Structures and Their Parallel Processing in Authentication Methods Based on Block Coupling Encoding

Purpose of reseach. In the tasks of authenticating groups of messages encoded in the mode of chaining blocks, there is a need for the formation and processing of specific tree-like structures. The contents of such structures, in addition to information about the placement of data in the internal memory of the calculators, describes the relative location of messages in the data stream between subscribers of a peer-to-peer network. This information is necessary to isolate a structured set from the entire message stream to the receiver, for which its source is uniquely determined. Using approaches to segmentation of tree structures allows you to parallelize the processes of adding elements to it and searching for areas corresponding to an authentication error.Methods. The division of the tree structure into areas subject to modification and areas for analysis is based on a metric dynamically formed from message authentication codes – the position of a specific message in a structured set of messages transmitted from the source to the receiver. The value of this metric determines the distance from the root of the tree, which defines the boundary between the two named areasResults. By isolating the modified and analyzed sections of the tree structure, races of processes implementing independent algorithms for working with it are excluded. The possibility of detecting authentication errors before receiving the last message in a structured set of messages is shown. As a result, there is no need to transmit those group messages that were supposed to be sent after the error was detected. Formulas for estimating the average transmission time of multiple messages with sequential and parallel implementation of procedures for the formation and processing of a tree structure containing descriptors of incoming messages to the receiver are given.Conclusion. The paper shows that the parallel implementation of algorithms for adding elements to the tree structure and the algorithm for searching for areas corresponding to an error reduces the average transmission time of a group of messages by 5-12% compared with the sequential implementation of these algorithms. This reduces the load on the communication channel for the target class of systems using block coupling encoding for authentication.

Multiarmed Bandit Algorithms on Zynq System-on-Chip: Go Frequentist or Bayesian?

Multiarmed Bandit (MAB) algorithms identify the best arm among multiple arms via exploration-exploitation trade-off without prior knowledge of arm statistics. Their usefulness in wireless radio, Internet of Things (IoT), and robotics demand deployment on edge devices, and hence, a mapping on system-on-chip (SoC) is desired. Theoretically, the Bayesian-approach-based Thompson sampling (TS) algorithm offers better performance than the frequentist-approach-based upper confidence bound (UCB) algorithm. However, TS is not synthesizable due to Beta function. We address this problem by approximating it via a pseudorandom number generator (PRNG)-based architecture and efficiently realize the TS algorithm on Zynq SoC. In practice, the type of arms distribution (e.g., Bernoulli, Gaussian) is unknown, and hence, a single algorithm may not be optimal. We propose a reconfigurable and intelligent MAB (RI-MAB) framework. Here, intelligence enables the identification of appropriate MAB algorithms in an unknown environment, and reconfigurability allows on-the-fly switching between algorithms on the SoC. This eliminates the need for parallel implementation of algorithms resulting in huge savings in resources and power consumption. We analyze the functional correctness, area, power, and execution time of the proposed and existing architectures for various arm distributions, word length, and hardware-software codesign approaches. We demonstrate the superiority of the RI-MAB algorithm and its architecture over the TS and UCB algorithms.

THB-Diff: a GPU-accelerated differentiable programming framework for THB-splines

AbstractWe have developed a differentiable programming framework for truncated hierarchical B-splines (THB-splines), which can be used for several applications in geometry modeling, such as surface fitting and deformable image registration, and can be easily integrated with geometric deep learning frameworks. Differentiable programming is a novel paradigm that enables an algorithm to be differentiated via automatic differentiation, i.e., using automatic differentiation to compute the derivatives of its outputs with respect to its inputs or parameters. Differentiable programming has been used extensively in machine learning for obtaining gradients required in optimization algorithms such as stochastic gradient descent (SGD). While incorporating differentiable programming with traditional functions is straightforward, it is challenging when the functions are complex, such as splines. In this work, we extend the differentiable programming paradigm to THB-splines. THB-splines offer an efficient approach for complex surface fitting by utilizing a hierarchical tensor structure of B-splines, enabling local adaptive refinement. However, this approach brings challenges, such as a larger computational overhead and the non-trivial implementation of automatic differentiation and parallel evaluation algorithms. We use custom kernel functions for GPU acceleration in forward and backward evaluation that are necessary for differentiable programming of THB-splines. Our approach not only improves computational efficiency but also significantly enhances the speed of surface evaluation compared to previous methods. Our differentiable THB-splines framework facilitates faster and more accurate surface modeling with local refinement, with several applications in CAD and isogeometric analysis.

Parallel Implementation of Gaussian Filter Image Processing on a Cluster of Single Board Computer

Gaussian filters are widely used in image processing applications, such as edge detection, segmentation, and feature extraction. However, computationally intensive computations can take a long time to process large images. Therefore, a parallel algorithm implementation is necessary to accelerate the process. The authors proposed the use of Orange Pi SBCs for parallel image processing tasks involving a Gaussian filter. This paper outlines the steps for implementing a parallel Gaussian filter on a cluster of SBCs. The performance of the parallel implementation was evaluated in terms of speedup and efficiency, which are essential parameters for measuring the effectiveness of the approach. The parallel implementation speedup is described as the ratio of the time required by the serial implementation to that required by the parallel implementation. The parallel implementation efficiency is described as the speedup ratio of the number of SBCs in a cluster. The results of the performance evaluation show that the parallel implementation of the Gaussian filter on a cluster of Orange Pi SBCs can achieve significant speedup and efficiency compared to the serial implementation. The speedup increases with the number of SBCs used in the cluster. Using four SBCs can result in a speedup of up to 2.1 times faster than serial implementation. The efficiency also increases with the number of SBCs used in the cluster. Using four SBCs could achieve an efficiency of up to 53.4%.

Two different parallel approaches for a hybrid fractional order Coronavirus model

In this paper, two different parallel approaches for a hybrid fractional order Coronavirus (2019-nCov) mathematical model are presented. Both parallel approaches are implemented using Julia high level language. Parallel algorithm implementations are developed for the HPC cluster using Message Passing Interface (MPI) technology and general-purpose computing on GPUs (GPGPU) using Compute Unified Device Architecture (CUDA) based on hardware environments. The algorithm implementation are used to solve the real-world problem of the hybrid fractional order Coronavirus (2019-nCov) mathematical model and to study the parallel efficiency. The introduced hybrid fractional order derivative is defined as a linear combination of the integral of Riemann-Liouville and the fractional order Caputo derivative. A parallel algorithm is designed based on the predictor-corrector method with the discretization of the Caputo proportional constant fractional hybrid operator for solving the model problem numerically. Simulation results show that, both the new parallel approaches achieve significant efficiency.

Artificial intelligence implementation in ukrainian banks: perspectives and limitations

Methods. During the research, the method of scientific abstraction was applied – to define the concept of «artificial intelligence»; analysis and synthesis – when identifying the functional capabilities of artificial intelligence; comparison – to determine the level of use of artificial intelligence systems in Ukrainian banks. Results. The article examines the genesis of algorithms of generative artificial intelligence (AI) from the point of view of the prerequisites for its appearance, development and impact on economic and financial agents. It was determined that artificial intelligence is the main factor in revitalizing economic growth and a strategic advantage in the long term. The current state of implementation of AI tools in the activities of Ukrainian banks in comparison with foreign banks is analyzed. For further development, commercial banks are suggested to create joint projects with scientific institutions, technological companies regarding training and adaptation of models for clients of financial institutions and parallel implementation of algorithms in internal bank processes, including search, adaptation and development of personnel, marketing, internal information technologies and processes or in the event of sufficient financial resources, the creation of intra-bank divisions for the development of AI. The transition to innovative types of services will also require financial institutions to communicate properly with clients. Novelty. The level of use of artificial intelligence systems in Ukrainian banks was determined. According to the results of the study, it was determined that the key factor that negatively affects the introduction of new technologies is the high cost of investments in the preparation of models and the selection of teams. Other challenges relate to the regulation of relations with consumers of financial services and insufficient attention from the regulator. Practical value. Applied research results are focused on taking into account the specific positions and opportunities of the enterprise's competitive potential when evaluating the effectiveness of its innovative activities.

POFCM: A Parallel Fuzzy Clustering Algorithm for Large Datasets

Clustering algorithms have proven to be a useful tool to extract knowledge and support decision making by processing large volumes of data. Hard and fuzzy clustering algorithms have been used successfully to identify patterns and trends in many areas, such as finance, healthcare, and marketing. However, these algorithms significantly increase their solution time as the size of the datasets to be solved increase, making their use unfeasible. In this sense, the parallel processing of algorithms has proven to be an efficient alternative to reduce their solution time. It has been established that the parallel implementation of algorithms requires its redesign to optimise the hardware resources of the platform that will be used. In this article, we propose a new parallel implementation of the Hybrid OK-Means Fuzzy C-Means (HOFCM) algorithm, which is an efficient variant of Fuzzy C-Means, in OpenMP. An advantage of using OpenMP is its scalability. The efficiency of the implementation is compared against the HOFCM algorithm. The experimental results of processing large real and synthetic datasets show that our implementation tends to more efficiently solve instances with a large number of clusters and dimensions. Additionally, the implementation shows excellent results concerning speedup and parallel efficiency metrics. Our main contribution is a Fuzzy clustering algorithm for large datasets that is scalable and not limited to a specific domain.

Параллельная реализация алгоритма восстановления сейсмического источника по серии статистически идентичных моделей среды с применением Fortran Coarray

Рассматривается задача параллельной реализации алгоритма определения сейсмического источника внутри случайно-неоднородной среды. Алгоритм определения исходной позиции источника использует данные записанных сейсмограмм на свободной поверхности и информацию о статистических свойствах случайной среды. Предложенный подход требует решения большого количества задач динамической теории упругости для различных статистически эквивалентных скоростных моделей, идентифицированных по статистическим параметрам исходной среды. Это наиболее трудоемкая часть алгоритма решения. Чтобы ускорить расчеты, используется двухуровневая стратегия распараллеливания с помощью создания групп, каждая из которых решает свою задачу динамической теории упругости с декомпозицией расчетной области внутри группы. Реализация программы выполнена с использованием Fortran Coarray. Также приводится сравнение используемых конструкций расширения Fortran Coarray с функциями MPI. The research considers the problem of parallel implementation of an algorithm for determining a seismic source inside a randomly heterogeneous medium. The algorithm for determining the initial position of the source uses the data of recorded seismograms on the free surface and information about the statistical properties of the random environment. The proposed approach requires solving a large number of problems in the dynamic theory of elasticity for various statistically equivalent velocity models identified by the statistical parameters of the initial medium. This is the most time-consuming part of the solution algorithm. To speed up calculations, a twolevel parallelization strategy is used by creating groups, each of which solves its problem of dynamic elasticity theory with a decomposition of the computational domain within the group. Program implementation uses Fortran Coarray. It also compares the used Fortran Coarray extension constructs with MPI functions.

Acceleration of Particle Swarm Optimization with AVX Instructions

Parallel implementations of algorithms are usually compared with single-core CPU performance. The advantage of multicore vector processors decreases the performance gap between GPU and CPU computation, as shown in many recent pieces of research. With the AVX-512 instruction set, there will be another performance boost for CPU computations. The availability of parallel code running on CPUs made them much easier and more accessible than GPUs. This article compares the performances of parallel implementations of the particle swarm optimization algorithm. The code was written in C++, and we used various techniques to obtain parallel execution through Advanced Vector Extensions. We present the performance on various benchmark functions and different problem configurations. The article describes and compares the performance boost gained from parallel execution on CPU, along with advantages and disadvantages of parallelization techniques.

Comparative analysis of the implementation of parallel algorithms on the central processors of automation systems in agriculture

The article presents a comparative analysis of the implementation of parallel algorithms on the central processors of automation systems in agriculture. Modern automation systems impose increased requirements on the reliability of the implementation of parallel algorithms in real time. It is proposed to use models for the development, analysis and comparison of parallel algorithms on GPUs. The proposed model of parallel computing on GPUs is designed to simplify the development of parallel algorithms for a heterogeneous CPU-GPU environment. Those, with this model, you can: develop parallel algorithms that use data parallelism, while applying the existing experience in creating parallel algorithms for the PRAM machine; evaluate the running time of the parallel algorithm and analyze which part of it is the most resource-intensive and requires optimization; compare parallel algorithms according to some parameters of the model, and, if required, select the best one according to these parameters in real time for automation in agriculture.

QUANTUM DIGITAL-ANALOGUE COMPUTING

Context. Nature is the relation among processes and phenomena. Nothing exists in the universe without relations. Computer is transactions of relations between data with the help of control and execution mechanisms. Quantum relations are a superposition of particles and their states. Superposition and entanglement are equivalent concepts. Entanglement is a non-local superposition of deterministic states. A quantum computer is unconditional transactions of relations between qubit data. Quantum computer is an analog device for parallel solution of combinatorial problems. Practically oriented definitions of the quantum computer concepts are the path to development of scalable quantum parallel algorithms for combinatorial problems solving. Any algorithm can be reduced to a sequence of operations without conditions, because any truth table is a collection of a complete system of conditions-states. Any sequence of actions can always be reduced to one parallel operation. Conditions and sequences arise only when the developer wants to use previously created primitive constructs to build an always non-optimal computing unit. The paradigm of quantum computer creation is determined through the use of photonic transactions on the electrons of an atom may exclude the use of quantum logic. The evolutionary path of a quantum computer from the classical one: “memory-address-transaction” (MAT) → “electron-addresstransaction” → “electron-address-quantaction” (EAQ) → state-superposition-logic. The meeting point of classical and quantum computers is photon transactions on the structure of electrons. Everything that is calculated on a quantum computer can be calculated in parallel on a classical one on account of memory redundancy. The given example is a memory-driven algorithm for modeling digital products based on qubit-vector forms of functionality description for significant performance boost of computing processes by parallel execution of logical operations.
 Objective. Simulation of the correct SoC-component behavior based on vector representation of the logic. Formation of the triggering development of a computing based on the superposition of the classical, quantum and analog computing process, which in its development should be based on technological qubit, tabular and vector data structures for the parallel solution of combinatorial problems.
 Method. MAT-computing implements any algorithms on account of transactions (read-write) in memory. Qubit-vector models for describing functionalities, which differ from known truth tables in compactness of description and manufacturability for the implementation of parallel algorithms of the synthesis and analysis of digital devices and SoC-components.
 Results. 1) The metric of the technological data structures, focused on parallel troubleshooting in digital systems based on the usage of two logical vector operations, was proposed for the first time. 2) The metric of relations between the individual components of QC, allowing organizing a quantum deterministic computer, has been further developed. 3) Quantum architectural solutions, that allow solving coverage problems in a quasi-parallel mode, were proposed for the first time. 4) Architectural solutions based on an analog-to-digital computing, which can be used to solve the problems of the digital systems parallel analysis, have been further developed. 5) Vector-qubit structures of the logic data, that allow a quasi-parallel simulation of digital circuits, were proposed.
 Conclusions. Qubit models, quantum methods and combinatorial algorithms for technical diagnostics of digital devices have been implemented, which can significantly (up to 25%) reduce the time of test synthesis, deductive modeling of faulty and correct behavior, search for defective states by introducing an innovative idea of using qubit-vector data structures for describing logical components. Comparative assessments of qubit models and methods usage show an increase in the efficiency of algorithms for modeling digital devices compared to tabular ones. The superposition of a classical, quantum and analog computer is integrally represented, which allows to find the best solutions for recognition and decision making.

First AI for Deep Super-resolution Wide-field Imaging in Radio Astronomy: Unveiling Structure in ESO 137-006

We introduce the first AI-based framework for deep, super-resolution, wide-field radio interferometric imaging and demonstrate it on observations of the ESO 137-006 radio galaxy. The algorithmic framework to solve the inverse problem for image reconstruction builds on a recent “plug-and-play” scheme whereby a denoising operator is injected as an image regularizer in an optimization algorithm, which alternates until convergence between denoising steps and gradient-descent data fidelity steps. We investigate handcrafted and learned variants of high-resolution, high dynamic range denoisers. We propose a parallel algorithm implementation relying on automated decompositions of the image into facets and the measurement operator into sparse low-dimensional blocks, enabling scalability to large data and image dimensions. We validate our framework for image formation at a wide field of view containing ESO 137-006 from 19 GB of MeerKAT data at 1053 and 1399 MHz. The recovered maps exhibit significantly more resolution and dynamic range than CLEAN, revealing collimated synchrotron threads close to the galactic core.

About Selecting the Number of Processors for Parallel Multipopulation Genetic Algorithm

Introduction. The paper considers some features of the parallel implementation of a multipopulation genetic algorithm, as well as approaches to its optimization. The results of experiments with the use of a different number of processors and different methods of generating initial populations are presented in order to optimize the algorithm according to several criteria (assessment of the use of computational and time resources). On the example of a specific test problem, estimates are given for choosing the optimal number of processors to obtain the desired result. The purpose of this work is to conduct experiments with a given test problem with a different number of processors and alternative methods for generating the initial population to evaluate the effectiveness of the algorithm. Results. For the test problem, to obtain a result of 90–94 % of the optimum, the most efficient in terms of computing resources is the use of 4 processors with an algorithm for uniform scanning of the space of factor values. To achieve a result exceeding 94 % and optimize by K1 (computational resources), 8 processors and an algorithm for uniform scanning of the space of factor values showed the best result. If we also take into account the criterion of time resources K2, then to achieve 90–98 % of the optimum, it is necessary to use 8 processors, for 99–100 % 12 or 16 processes, depending on C1 and C2 (cost of computational and time resources respectively). Conclusions. Performed experiments show that the algorithm of uniform scanning of the space of factor values is more efficient than the random method of generating the initial population. Experiments also showed that in order to achieve the maximum efficiency of PMGA, the number of processors must be chosen depending on the desired result precision. Keywords: parallel genetic algorithm, initial population generation, choice of the number of processors (populations), algorithm optimization.

Herbal Compound Screening with GPU Computation on ZINC Database through Similarity Comparison Approach

Covid-19 is a global pandemic that drives many researchers to strive to look for its solution, especially in the field of health, medicine, and total countermeasures. Early screening with in-silico processes is crucial to minimize the search space of the potential drugs to cure a disease. This research aims to find potential drugs of covid-19 disease in the ZINC database to be further investigated through the in-vitro method. About 997.402.117 chemical compounds are searched about their similarity to some of the confirmed drugs to combat coronavirus. Sequential computation would take months to accomplish this task. The general programming graphic processing unit approach is used to implement a similarity comparison algorithm in parallel, in order to speed up the process. The result of this study shows the parallel algorithm implementation can speed up the computation process up to 55 times faster, and also that some of the chemical compounds have high similarity scores and can be found in nature

GWMA: the parallel implementation of woodpecker mating algorithm on the GPU

ABSTRACT The Woodpecker Mating Algorithm (WMA) is a new metaheuristic algorithm (MA) with high efficiency in solving optimization problems. Nevertheless, WMA needs many search agents to explore the problem space when handling complex problems, resulting in a long computational time. This paper focuses on the acceleration of WMA for solving optimization problems with parallelization in the graphics processing unit (GPU) to improve the speedup and decrease the execution time of the WMA, thereby retaining the quality of the optimal outcomes. The proposed algorithm provides various mechanisms for generating random factors on the host system, bulk transfer of these factors to the GPU, parallel initialization and evaluation of the initial population on GPU, updating and evaluating the search agents’ position. It also uses a decreasing mechanism to determine the best agent. The comparative evaluations of the parallel and serial WMA are based on a classical benchmark and CEC2017 test functions. In addition, the execution time of the GWMA is measured by other parallel MAs to represent the speed of the GWMA. The ultimate outcomes prove that the GWMA is run about 10–82 times quicker than the sequential WMA. Also, the GWMA is faster than other parallel algorithms in solving optimization problems.

Parallel design and implementation of Jacobi iterative algorithm based on ternary optical computer

Parallel design and implementation of Jacobi iterative algorithm based on ternary optical computer