Nikitas A. Alexandridis, Panagiotis Papaioannou, Bhagirath Narahari et al. · 2003
Presents a software environment consisting of a collection of parallel architecture prototypes used to evaluate the performance of parallel vision systems and algorithms. A consistent evaluation of parallel algorithms on various architectures is difficult due to the variety and complexity of parallel architectures and the fact that parallel algorithm-architecture performance is governed by both task characteristics and architecture characteristics. The authors use the prototyping approach for performance evaluation because theoretical analysis as well as simulation of massively parallel computer systems cannot accurately estimate the performance of these systems. The software environment presented offers a uniform basis for the comparison of a variety of parallel system configurations, such as meshes, rings, hypercubes, and pyramids. Performance measurements of algorithms on various configurations can then be derived and used to choose the most efficient algorithm for a particular vision task to run on a particular parallel system configuration. The authors describe the software environment and its operations. Its usefulness was demonstrated by developing a collection of vision tasks, executing them on the software architecture prototypes, and evaluating them by gathering actual performance measurements.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Cited by 0
Neela Madheswari A, Wahida Banu R.S.D · International Journal of Distributed and Parallel systems · 2013
In the area of Computer Science, Parallel job scheduling is an important field of research. Finding a best suitable processor on the high performance or cluster computing for user submitted jobs plays an important role in measuring system performance. A new scheduling technique called communication aware scheduling is devised and is capable of handling serial jobs, parallel jobs, mixed jobs and dynamic jobs. This work focuses the comparison of communication aware scheduling with the available parallel job scheduling techniques and the experimental results show that communication aware scheduling performs better when compared to the available parallel job scheduling techniques.
Cited by 0Open access
Seyed Ehsan Rafiee, M.M. Sadeghiazad · Applied Thermal Engineering · 2017
Cited by 33
Pohuliaiev, Yurii · Zenodo (CERN European Organization for Nuclear Research) · 2025
Implementation of minutiae-based fingerprint comparison algorithm with three computational approaches: parallel processing, full SIMD vectorization (SSE/AVX), and selective hybrid methodology for high-performance biometric identification systems.
Cited by 0Open access
Pohuliaiev, Yurii · Zenodo (CERN European Organization for Nuclear Research) · 2025
Implementation of minutiae-based fingerprint comparison algorithm with three computational approaches: parallel processing, full SIMD vectorization (SSE/AVX), and selective hybrid methodology for high-performance biometric identification systems.
Cited by 0Open access
Lubomír Klimeš, Josef Štětina · 2013
Nowadays, dynamic solidification models of continuously cast steel are commonly used in steelworks over the world to control the casting process and to monitor the steel production. Moreover, these models of transient temperature field can also be utilized for optimization of continuous casting, its on-line regulation, or may help operators to solve non-standard or breakdown situations that can occur when casting. In order to solve these problems in real time, parallel computing of dynamic solidification models can favourably be utilized. One of possible approaches is to use parallel computing on graphics processing units (GPUs) that offer a great computing performance in comparison to ordinary computing on CPUs. The paper describes an implementation of the parallel dynamic solidification model with the use of the CUDA architecture and NVIDIA GPUs. A comparison between the use of parallel and non-parallel models is presented and analysed. Results show that parallel computing on GPUs can considerably enhance the computing performance of solidification models and their use and efficiency in other tasks.
Cited by 1
S.Y.A. Shah, A.J. Al-Khalili, D. Al-Khalili · 2002
Comparison of five different 32-bit integer multipliers is done for various performance measures. Multipliers included in comparison are the array multiplier, modified Booth (radix-4) multiplier, optimized Wallace tree multiplier, combined modified Booth-Wallace tree multiplier and twin pipe serial parallel multiplier. Comparison is based on synthesis results obtained by synthesizing all multiplier architectures towards FPGA.
Cited by 37
Akanksha Dhar, Ishita Chauhan, Hiteshwar Kumar Azad et al. · 2024
The genome is a rapidly evolving topic that constantly offers researchers with new biological and computational application challenges. One of the biggest challenges is biological sequence comparison, which involves identifying similarities or identical segments between a query sequence and a reference sequence. Global and local alignments are two common types of sequence alignments. Global alignment identifies the optimal alignment across entire sequences, while local alignment focuses on matching specific segments rather than the entire length. Local alignment algorithms offer faster performance compared to global alignment since they only align specific portions of sequences. In this study, the Smith-Waterman method would be executed serially and in parallel for comparison and analysis. The results reveal that parallel execution has a significant advantage over serial execution, with a maximum improvement of $78.5 \%$ above serial performance. Furthermore, increasing the matrix size enhances parallel execution performance over serial processing.
Cited by 3
Xiaojun Dong, Laxman Dhulipala, Yan Gu et al. · arXiv (Cornell University) · 2024
Integer sorting is a fundamental problem in computer science. This paper studies parallel integer sort both in theory and in practice. In theory, we show tighter bounds for a class of existing practical integer sort algorithms, which provides a solid theoretical foundation for their widespread usage in practice and strong performance. In practice, we design a new integer sorting algorithm, \textsf{DovetailSort}, that is theoretically-efficient and has good practical performance. In particular, \textsf{DovetailSort} overcomes a common challenge in existing parallel integer sorting algorithms, which is the difficulty of detecting and taking advantage of duplicate keys. The key insight in \textsf{DovetailSort} is to combine algorithmic ideas from both integer- and comparison-sorting algorithms. In our experiments, \textsf{DovetailSort} achieves competitive or better performance than existing state-of-the-art parallel integer and comparison sorting algorithms on various synthetic and real-world datasets.
Cited by 0Open access
N. Cabibbo, N. Cabibbo, A. Mathis et al. · 1994
The Parallel Computing as the basis for High Performance Computing is discussed. An evaluation of Distributed vs. Massively Parallel Computing is outlined, with special reference to the requirements of the so-called Grand Challenge computational problems. A comparison is then carried on the USA&apos;s High Performance Computing and Communications (HPCC) vs. Europe&apos;s High Performance Computing and Networking Programs. The weaknesses, but also the potentialities, of the European scene are discussed. Finally, a proposal is presented for a comprehensive initiative to start an all-European massively parallel supercomputing program, based on the relevant industrial assets presently active in Europe (among them, the Italian Quadrics Massively Parallel Supercomputers, derived from the APE100 Project of the Italian National Institute for Nuclear Physics). Key Words: Parallel computing; Distributed computing; Computer simulation; Massively parallel supercomputing program; Transputer; Quadrics. 1. Hi...
Cited by 0
A.C. Aljundi, J.-L. Dekeyser, Tahar Kechadi et al. · 2004
Interconnection network performance is a key factor when constructing parallel computers. The choice of an interconnection network used in a parallel computer depends on a large number of performance factors which are very often application dependent. We give the outline of a performance evaluation and comparison methodology using what we think of as the most important parameters to be considered when solving such a problem. This methodology is applied on a new interconnection network called MCRB network and on Omega network.
Cited by 6
Shang Xiu-xiang · 2011
The causes of battery capacity unbalance were analyzed,and the effect of charge and discharge of VRLA batteries in series and in parallel respectively on performance were discussed.The comparison tests were performed to the different SOC of lead acid batteries in series and in parallel.The results proves the feasibility of parallel discharging batteries,and confirms that the parallel charging and discharging can improve the balance of batteries.
Cited by 0
D. Bailey, J. Barton, T. Lasinski et al. · 1994
The NAS Parallel Benchmark Kernels in MPL 14of introduced overhead by Mentat as compared to the lower level, hand-coded version of the application, as well as better communications performance 3.4 CG Kernel Performance As in the MG kernel case, our CG implementation was quite similar to the provided NAS version in its exploitation of opportunities for parallel execution. Unfortunately, we observed memory constraints which prevented running the full sized tests, making performance comparison difficult. Given the observed results, however, it seems likely that our performance would compare favorably to that of the PVM implementation.
Cited by 0
Amjad J. Humaidi, Ahmed Ibraheem Abdulkareem · Journal of Control Science and Engineering · 2019
This work presents the design of two control schemes for a Delta/Par4-like parallel robot: augmented PD (APD) controller and augmented nonlinear PD (ANPD) controller. The stability of parallel robot based on nonlinear PD controller has been analyzed and proved based on Lyapunov method. A comparison study between APD and ANPD controllers has been made in terms of performance and accuracy improvement of trajectory tracking. Also, another comparison study has been presented between augmented nonlinear PD (ANPD) controller and nonaugmented nonlinear PD (NANPD) controller in order to show the enhancement of introducing the augmented structure on dynamic performance and trajectory tracking accuracy. The effectiveness of augmented PD controllers (APD and ANPD) and nonaugmented nonlinear PD (NANPD) controller for the considered parallel robot are verified via simulation within the MATLAB environment.
Cited by 44Open access
D.C. Cann, Rich Wolski, John Feo · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · 1992
Sisal (Streams and Iterations in Single Assignment Language) is a functional language for numerical computation on both conventional and novel multiprocessor systems. In this paper, we discuss the Sisal project; illustrate SISAL`s performance in comparison to sequential and parallel FORTRAN; and identify the project`s future directions. We demonstrate that one can raise the level of program abstraction without sacrificing performance. SISAL programs are efficient, portable, determinate, and free of the burden thwarting parallel program is development. Without question, functional programming can resolve today`s parallel programming crisis.
Cited by 1
Rinkle RaniAggarwal · International Journal of Computer Applications · 2012
Parallel processing can be used to design high performance computing systems. In a parallel computer inter-connecting processors and linking them efficiently to the memory modules is not an easy task. Therefore, there is a requirement of an interconnection network that provides the desired connectivity and performance at minimum cost. Multistage interconnection networks (MINs) provide cost-effective, highbandwidth communication between processors and/or memory modules in comparison to bus and crossbar interconnection networks. In this paper a new irregular MIN named IFTN (Improved Four Tree Network) has been proposed. The performance of IFTN has been measured in terms of reliability and cost. It has been proved that the proposed network IFTN provides much better fault-tolerance and reliability at lesser cost In Comparison To Four Trees.
Cited by 3Open access
Jan Broulím · Digital Library (University of West Bohemia) · 2016
In this paper, the utilization of Graphics Processing Units for parallel LDPC decoding is proposed. The proposed algorithm allows decoding of any irregular LDPC code. The principle of the parallel algorithm is briefly presented, and the performance comparison against serial decoding with the use of Central Processing Units is given in this paper.
Cited by 0Open access
Ion Cârstea · 2008
This paper presents an overview of parallel computing as an approach for high-performance scientific computing. We present some aspects in development of the parallel algorithms and parallel programs with emphasis on SIMD and MIMD computers. Some fundamental concepts are presented in the context of development of parallel algorithms and programs with emphasis on the programs efficiency. A comparison of different strategies is analysed.
The fundamental problems of the parallel computing and their solutions are presented. These aspects are treated in the general case related to the portability of algorithms across various parallel architectures.
Cited by 1
Janice E. Huss, James A. Pennline · NASA Technical Reports Server (NASA) · 1987
Five benchmark programs were obtained and run on the NASA Lewis CRAY X-MP/24. A comparison was made between the programs codes and between the methods for calculating performance figures. Several multitasking jobs were run to gain experience in how parallel performance is measured.
Cited by 5Open access
Bill Buzbee · Wuhan University Journal of Natural Sciences · 1996
Using 1995 results from the NASA Parallel Benchmarks, this paper compares the sustained performance (as opposed to peak performance) and cost per unit of sustained performance for state-of-the-art Parallel processing systems that use Micro-Processors (MPP) versus those that use Custom-designed Processors (PVP). This comparison shows that MPPs approach, but seldom surpass, PCPs with respect to either metric.This paper also discusses the merits and demerits of “clusters” of workstation. Ironically, recently introduced low-cost, parallel systems can also be viewed as “virtual workstation clusters” that offer comparable, if not superior, capabilities.Finally, this paper explores the question of whether it will be economically feasible for computer manufacturers to continue building PVPs, or are MPPs the only economically viable option for building parallel systems?
Cited by 0