Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 7,601 papers for “parallel performance comparison”

A performance comparison between parallel and lazy fetching in vertically distributed cloud databases

Jens Köhler, Thomas Specht · 2015

The following work focuses on the severe performance issues that come along with the vertical data distribution approach of the SeDiCo framework. SeDiCo (A Secure and Distributed Cloud Data Store) is a framework that vertically distributes database data across several clouds in order to maintain data security, protection and privacy. However, this vertical data distribution requires joining data together before any client access. This join is extremely time-consuming and thus, this approach is currently not feasible in practical usage scenarios. In order to overcome those performance issues, this work proposes the introduction of a data cache architecture and two corresponding fetch procedures, i.e. lazy and parallel fetching. We further implemented both strategies, measured their performance and compared them to each other. Our results show that the parallel fetch strategy by far outperforms the lazy fetch strategy. Above that, this work outlines the entire caching architecture of our approach and discusses the two strategies in detail. Finally, this work concludes the measured results and discusses further challenges in the context of the SeDiCo framework as future work tasks.

Cited by 6

Performance Comparison of Mismatch Power Loss Minimization Techniques in Series-Parallel PV Array Configurations

Ahmed Al Mansur, Md. Ruhul Amin, Кази Хайрул Ислам · Energies · 2019

The mismatch in current-voltage (I-V) characteristics of photovoltaic (PV) modules causes significant power loss in a large PV array, which is known as mismatch power loss (MML). The PV array output power generation can be improved by minimizing MML using different techniques. This paper investigates the performance of different module arrangement techniques to minimize MML both for long series string (LSS) and long parallel branch (LPB) in series-parallel (SP) array configurations at uniform irradiance condition. To investigate the significance of MML LSS-SP configuration with dimensions: 1 × 40, 2 × 20, 4 × 10, 5 × 8 and LPB-SP configuration with dimensions: 40 × 1, 20 × 2, 10 × 4, 8 × 5 were used. A comparative analysis is made to find the effectiveness of MML reduction techniques on PV arrays with three different power ratings. Simulation results show that the PV modules arrangement obtained by the genetic algorithm (GA) and current based arrangement (Im) performed better than the arrangements obtained by all other techniques in terms of PV array output power and MML minimization. The performance of the proposed technique was analyzed for both LSS-SP and LPB-SP array configurations in 400 W, 3400 W, and 9880 W arrays. To substantiate the simulation results experiment was performed using a 400 W PV array in outdoor weather condition and obtained similar results. It was also observed that the percentage of recoverable energy (%RE) obtained by arranging the modules using the GA method was higher than Im based method for both LSS-SP and LPB-SP array configurations. A maximum %RE of 4.159 % was recorded for a 5 × 8 LSS-SP array configuration by applying the GA based MML reduction method.

Cited by 50Open access

Parallel performance comparison of different CFD solvers and overset libraries for store separation analyses

Saleh Abuhanieh, Buğra Batan, Onur Mert Aksoy et al. · The International Journal of High Performance Computing Applications · 2025

The present work attempts to provide, for the first time to the best of the authors’ knowledge, a comprehensive comparison study about the parallel performance of different Computational Fluid Dynamics (CFD) codes which utilize the overset method to account for the relative motion in the computational domain which is required by the store separation simulations. Two commercial codes (Ansys Fluent and Simcenter STAR-CCM) and two open-source implementations were compared using a generic test case from the open literature utilizing the same mesh, the same hardware, and as much as possible, the same settings. The first open-source implementation was taken from a previous work of the first author, and the second implementation is presented in this work. The scalability and efficiency for the four codes were evaluated up to 2,048 processor cores. The results show that, the open-source implementations performance is satisfactory and even outperform the commercial codes (specially the second implementation) for the tested case.

Cited by 0

Performance comparison of parallel out-of-core MoM using SSD and SAS hard drives

Yu Zhang, Sheng Zuo, Xunwang Zhao et al. · 2015

The performance of the parallel out-of-core method of higher-order moments (HOMoM) is analysed. The I/O to hard disk significantly affects the performance of the out-of-core algorithm. In order to reduce the I/O time, solid state drives (SSD) with high read and write speeds are utilized. The size of the in-core buffer allocated to each process, IASIZE, is tuned to achieve the best performance of the out-of-core algorithm. Numerical results show that out-of-core algorithm using SSD exhibits better performance than that using SAS hard drives.

Cited by 0

Performance Comparison between Color and Spatial Segmentation for Image Retrieval and Its Parallel System Implementation

Pengdong Gao, Yongquan Lu, Chu Qiu et al. · 2008

In this paper segmentation on both color and spatial space is implemented to compare their influence to the performance of content-based image retrieval (CBIR) system. Firstly, images are converted from RGB color space to HSV space. And then cumulative histograms on H component are extracted from four segmented blocks as one color feature of the image. At the same time, the HSV color space is further divided into H2SV space. Local accumulative histograms on H1 and H2 components are sequentially extracted as the other color feature of the image. Finally, both color features combined with the texture feature are taken to evaluate their performance of retrieving images. In addition, some parallel techniques are applied to construct an image retrieval system based on the cluster architecture. Experimental results have demonstrated that spatial segmentation has done more influence on the performance of CBIR system. And the parallel techniques can improve the retrieval efficiency significantly.

Cited by 3

Comparison of High Performance Parallel Implementations of TLBO and Jaya Optimization Methods on Manycore GPU

Rico, Héctor, Sanchez-Romero, Jose-Luis, Jimeno-Morenilla, Antonio et al. · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · 2019

The utilization of optimization algorithms within engineering problems has had a major rise in recent years, which has led to the proliferation of a large number of new algorithms to solve optimization problems. In addition, the emergence of new parallelization techniques applicable to these algorithms to improve their convergence time has made it a subject of study by many authors. Recently, two optimization algorithms have been developed: Teaching-Learning Based Optimization and Jaya. One of the main advantages of both algorithms over other optimization methods is that the former do not need to adjust specific parameters for the particular problem to which they are applied. In this paper, the parallel implementations of Teaching-Learning Based Optimization and Jaya are compared. The parallelization of both algorithms is performed using manycore GPU techniques. Different scenarios will be created involving functions frequently applied to the evaluation of optimization algorithms. Results will make it possible to compare both parallel algorithms with regard to the number of iterations and the time needed to perform them so as to obtain a predefined error level. The GPU resources occupation in each case will also be analyzed.

Cited by 0

A Practical Performance Comparison of Two Parallel Fast Fourier Transform Algorithms on Cluster of PCs

Kalim Qureshi, Haroon Rashid · IEEJ Transactions on Electronics Information and Systems · 2004

In this paper, we present the performance analysis of two parallel Fast Fourier Transform algorithms, binary-exchange and transpose algorithms. These two algorithms were implemented and tested on a cluster of PCs using Message Passing Interface (MPI). The binary-exchange algorithm implementation was showing less processing and communication time than transpose algorithm.

Cited by 2Open access

Comparison of the Performance of Mini Generator Water Turbines in Series and Parallel Flow Systems

Mikael Adi Kriswidijatmoko, Rudi Hariyanto, Fransiskus A. Widiharsa · Transmisi · 2023

The need for electricity is crucial in modern life, but the depletion of fossil fuel resources and their negative impact on the environment has led to the need for alternative, sustainable, and renewable energy sources. One of the most widely used renewable energy sources is hydro energy, which can be harnessed through the use of water turbine generators. This research aims to design, prototype, and test the performance of a mini-series and parallel water turbine generator system with a 24-volt system. Furthermore, this research will evaluate the difference in performance between the series and parallel systems and analyze the efficiency of the mini-series and parallel water turbine generator system. The focus of this research is on the efficiency of the water turbine generator system with variations in water flow, but it does not cover large-scale industrial applications. This research aims to provide sustainable and environmentally friendly energy sources as an alternative to conventional energy sources. The results of this research can serve as a reference for researchers and practitioners interested in the development of renewable energy sources, particularly water turbine generators. In the testing, the Series Turbine Series Generator system with a water flow rate of 6.38 L/min produced a maximum power of 2.43 watts, while the Parallel Turbine Series Generator system with a water flow rate of 13.01 L/min produced a maximum power of 2.142 watts. The efficiency ratio between the Series Generator and Parallel Generator is 1.5, with the Series Generator achieving a maximum efficiency of 38.6% in the Series Turbine Series Generator system, and the Parallel Generator achieving a maximum efficiency of 25.3% in the Series Turbine Parallel Generator system.

Cited by 0Open access

Performance Comparison of Various Weight and Combination Function on Heterogeneous Parallel Ensemble Machine Learning Model

Huzain Azis, Munaisyah Abdullah, Suriana Ismail · Journal of Advanced Research in Applied Sciences and Engineering Technology · 2025

This research study evaluates the performance of different weight and combination functions - Majority Voting, Accuracy Weighting, Entropy Weighting, and Dempster Shafer Weighting - in heterogeneous parallel ensemble machine learning models. Utilizing five health datasets - Breast Cancer, Diabetes, Heart Failure, Heart Disease, and Cervical Cancer - we conduct an in-depth analysis. Following data pre-processing and exploratory analysis, we implement these datasets into five classifiers. The comparative evaluation of the ensemble models, based on their error rates, demonstrates that Accuracy Weighting function consistently outperforms the others across most datasets, although effectiveness varies depending on the specific dataset. These findings not only provide vital insights into the behaviour of weight and combination functions in ensemble models but also propose future research directions. Future work will delve into understanding the characteristics of datasets that influence the performance of these functions and exploring the use of adaptive ensemble systems that can dynamically choose the most suitable function based on the dataset.

Cited by 0Open access

Implementation of High Speed FIR Filter: Performance Comparison with Different Parallel Prefix Adders in FPGAs

S. Uma, P. Dhavachelvan · Research Journal of Applied Sciences Engineering and Technology · 2014

This study describes the design of high speed FIR filter using parallel prefix adders and factorized multiplier. The fundamental component in constructing any high speed FIR filter consists of adders, multipliers and delay elements. To meet the constraint of high speed performance and low power consumption parallel prefix adders are more suitable. This study focus the design of new Parallel Prefix Adder (PPA) and new multiplier cell called factorized multiplier with minimal depth algorithm and its functional characteristics is compared with the existing architecture in terms of delay and area. The performance evaluation of the proposed PPA and multiplier are examined for the bit sizes of 8, 16, 32 and 64. The coefficient of the filter is obtained through hamming window using MATLAB program. The proposed FIR filter using new PPA and factorized multiplier has been prototyped on XC3S1600EFG320 in Spartan-3E Platform using Integrated Synthesis Environment (ISE) for 90 nm process. Nearly 14% of slice utilization and 34% of speed improvement has been obtained for FIR using new PPA and factorized multiplier.

Cited by 0Open access

Comparison of PEMFC performance with parallel serpentine and parallel serpentine-baffled flow fields under various operating and geometrical conditions; a parametric study

A. Hamrang, M. Abdollahzadeh, Abbas Moradi Bilondi et al. · International Journal of Hydrogen Energy · 2022

Optimal flow channel design of a fuel cell is crucial to further improve the performance of polymer electrolyte membrane fuel cell (PEMFC). In this work, a comprehensive parametric study was conducted to analyze the performance of a PEMFC with conventional parallel serpentine flow fields (PSFF) and parallel serpentine-baffled flow fields (PSBFF). A three-dimensional two-phase computational fluid dynamics model was used to numerically simulate the fuel cell performance. The effects of operating parameters such as pressure, temperature, and stoichiometric ratio, as well as the geometric parameters of channel height to channel width ratio and rib width to channel width ratio for both flow fields on fuel cell performance were investigated. The results show that as pressure, temperature, and stoichiometric ratio increase, cell performance increases for both flow fields, with a more substantial rate of improvement for the PSBFF design. A 16.1% improvement in cell performance at an operating pressure of 1 atm, a 19.9% improvement at a cell temperature of 70 °C, and a 16.1% improvement at a stoichiometric ratio of 2 were obtained when PSBFF was used instead of PSFF. By increasing the channel height and rib width, the cell performance for PSBFF remains almost constant due to the improved forced convection of the gas mixture and the reduction in concentration loss, while the cell performance for PSFF decreases significantly. At the largest channel height to channel width ratio of 1.5 and rib width to channel width ratio of 1.315 studied in this work, an improvement in cell performance of 53.3% and 58.5%, respectively, was achieved when PSBFF was used instead of PSFF. In addition, PSBFF was more effective in removing water from the porous zones than PSFF under all conditions.

Cited by 46Open access

Performance Comparison of Massively Parallel Sequencing (MPS) Instruments Using Single-Nucleotide Polymorphism (SNP) Panels for Ancestry

Ashley M. Cooley, Kelly A. Meiklejohn, Natalie Damaso et al. · SLAS TECHNOLOGY · 2020

Thermo Fisher Scientific released the Precision ID Ancestry Panel, a 165-single-nucleotide polymorphism (SNP) panel for ancestry prediction that was initially compatible with the manufacturer’s massively parallel sequencer, the Ion Torrent Personal Genome Machine (PGM). The semiautomated workflow using the panel with the PGM involved several time-consuming manual steps across three instruments, including making templating solutions and loading sequencing chips. In 2014, the manufacturer released the Ion Chef robot, followed by the Ion S5 massively parallel sequencer in late 2015. The robot performs the templating with reagent cartridges and loads the chips, thus creating a fully automated workflow across two instruments. The objective of the work reported here is to compare the performance of two massively parallel sequencing systems and ascertain if the change in the workflow produces different ancestry predictions. For performance comparison of the two systems, forensic-type samples (n = 16) were used to make libraries. Libraries were templated either with the Ion OneTouch 2 system (for the PGM) or on the Ion Chef robot (for the S5). Sequencing results indicated that the ion sphere particle performance metrics were similar for the two systems. The total coverages per SNP and SNP quality were both higher for the S5 system. Ancestry predictions were concordant for the mock forensic-type samples sequenced on both massively parallel sequencing systems. The results indicated that automating the workflow with the Ion Chef system reduced the labor involved and increased the sequencing quality.

Cited by 6Open access

Kinematically Identical Manipulators for an Asymmetric 3-PRS Parallel Manipulator and Their Constraint Performance Comparison Study

Bo Hu, Dongsheng Shi, Shi Yan-guo et al. · Journal of Mechanical Engineering · 2020

摘要： 少自由度并联机构存在运动等效机构，表现为多种结构不同的机构运动学完全相同而性能各异，从具有运动等效特性的一组机构中遴选出性能优异的机型具有重要意义。基于运动等效机构的演化机理导出了一种非对称3-PRS机构的三种无过约束和三种含过约束的运动等效机构。基于运动/力传递指标对非对称3-PRS机构及其运动等效机构进行了优化设计，得到了优化尺寸区域。针对非对称3-PRS机构及其运动等效机构运动学相同而约束不同导致机构约束性能各异的特点，建立了此类机构的约束性能指标，在运动/力传递性能优化尺寸下，绘制了各机构的约束性能图谱，求解了各机构的全局约束指标，完成了此类机构的约束性能对比研究，实现了非对称3-PRS机构及其运动等效机构兼顾传递和约束性能的机构优选。

Cited by 2Open access