检索结果-内蒙古大学图书馆

21st International Conference on Complex Systems - Control and Modeling Problems (CSCMP)

作者： Barabanova, Polina Zasov, Valery Samara State Transport Univ Samara Russia

ISBN: (纸本)9781728167008

The paper presents the results of the comparative analysis of various methods for detecting and localizing race conditions in multithread systems with shared memory. The paper highlights the advantages of the static method, one of the effective implementations of which is an algorithm based on the analysis of a program presented as a control flow graph or one of its varieties-a joint flow execution graph. To solve applied problems, we carried out a software implementation of this algorithm, which served as the basis for developing a test program package for automated detection of race conditions in multithread systems. The reliability and efficiency of the program package is confirmed by the results of computer simulation illustrated using the Peterson algorithm.

关键词： multithread programming flow synchronization race conditions program reliability testing static analysis algorithm control flow graph program package

来源：评论

学校读者我要写书评

暂无评论

Multi-rate electromagnetic transient simulation of large-scale power system based on multi-core

引用

The Journal of Engineering 2018年第13期2017卷 1106-1112页

作者： Zhan Peng Yao Shu-jun Zhang Hai-lin Zhang Shuo North China Electric Power University Beijing 102206 People's Republic of China

The traditional electromagnetic transient simulation has a short-step size and a large computation, which results in small-scale simulation. Multi-rate simulation method and parallel computing are combined to carry out multi-rate simulation on the basis of parallel processing of power network, which can further improve the computational efficiency and expand the simulation scale. At the same time, a multi-rate simulation method of rotational frequency reduction is proposed. In which short step is used for the parts that want detailed simulation, for the AC network part, large step is adopted to the simulation and the frequency is reduced by the rotation of the signal for each phase. The wide application of multi-core central processing unit (CPU) computer is a great change that is being carried out. This paper develops the multi-thread programming based on open multi-processing (MP), makes full use of the convenience of multi-core CPU computer and simulates the method proposed.

关键词： EMTP power system analysis computing multiprocessing systems microprocessor chips multi-threading open MP multithread programming CPU multicore central processing unit computer AC network rotational frequency reduction simulation scale computational efhciency power network parallel computing large-scale power system multirate electromagnetic transient simulation

来源：评论

学校读者我要写书评

暂无评论

Platform Simulation Based Unmanned Aircraft Systems Design 2

Platform Simulation Based Unmanned Aircraft Systems Design

引用

2014 Second World Conference on Complex Systems (WCCS)

作者： Louali, Rabah Bouaziz, Samir Elouardi, Abdelhafid Abouzahir, Mohamed Ecole Mil Polytech BP 17 Algiers Algeria Univ Paris 11 IEF Orsay France

ISBN: (纸本)9781479946471

Unmanned Aircraft Systems (UAS) know a tremendous interest in many fields thanks to their wide range of applications. UAS are complex "system of systems" because, in addition to stringent safety and embedded constraints, they incorporate heterogeneous interacting sub-systems. Adequate development approaches and tools have to be provided to deal with this complexity. A literature review concerning this perspective shows a lack because current UAS simulation tools focus on limited or isolated development application. We propose a system-level simulation platform for the development of UAS. The proposed platform supports a component-based design for the UAS where each component is developed using a based-model methodology. A network-oriented architecture and object-oriented conception was adopted to design the platform. This allows the latter to be modular, flexible and integrate many UAS components simultaneously. A Controller Area Network (CAN) data bus is integrated to the platform. It will permit a "smooth" transition from the simulation phase to experimentation phase. To accelerate the platform design, a COTS flight simulator is integrated. This latter implements the dynamic, graphic and environmental model of the aircraft.

关键词： Unmanned Aircraft System System of Systems Simulation Platform System-Level Design Component-Based Conception Based-Model Methodology Network-Oriented Architecture Object-Oriented Design multithread programming Controller Area Network (CAN) COTS Flight Simulator

来源：评论

学校读者我要写书评

暂无评论

Improving Performance of a Mobile Personalized Recommendation Engine using multithreading

Improving Performance of a Mobile Personalized Recommendatio...

引用

10th International Joint Conference on Computer Science and Software Engineering (JCSSE)

作者： Chatcharaporn, Komkid Angskun, Jitimon Angskun, Thara Suranaree Univ Technol Sch Informat Technol Nakhon Ratchasima Thailand

ISBN: (纸本)9781479908066;9781479908059

Popularity of social networking services (SNS) and location-based SNS (LBSNS) have an influence on lifestyles of many people. Furthermore, the advancement of mobile technology enables people to share their interests and lifestyles to their friends conveniently. These factors cause the Internet to become massive personal information resource. A mobile personalized recommendation (MPR) engine plays an important role in offering solely essential information to prevent information overload for the users. Unfortunately, processing time of traditional MPR engine is high. This paper proposes an approach to improve performance of MPR using multithread programming (MP). The experimental results indicate that the multithread programming (MP) could deliver higher performance than sequential programming (SP), especially speedup between 5 and 7 times approximately.

关键词： multithread programming mobile application personalized recommendation engine social networking service

来源：评论

学校读者我要写书评

暂无评论

Implementation of Selected Numerical Algorithms for Solving Sparse Matrixes Using CUDA Technology

Implementation of Selected Numerical Algorithms for Solving ...

引用

International Symposium on Electrodynamic and Mechatronic System (SELM)

作者： Zimon, J. Zoworka, M. Opole Univ Technol Fac Elect Engn Automat & Informat Dept Ind Elect Engn PL-45758 Opole Poland

ISBN: (纸本)9781467355902;9781467355889

This thesis presents an implementation of Finite Element Method (FEM), with focus on sparse matrix solving methods using NVIDIA CUDA devices. Development of an application GPU_FEM that implements Finite Element Method has been presented. The calculation results and calculation times have been compared for different hardware configuration as well as for different algorithms. Presented tests show up to 70 times faster sparse matrix solving in comparison to FEMM application.

关键词： Finite Element Method Numerical calculations sparse matrixes NVIDIA CUDA technology multithread programming

来源：评论

学校读者我要写书评

暂无评论

Determination of the Magnetic Field Parameters Using a New Fast Computational Tool

Determination of the Magnetic Field Parameters Using a New F...

引用

International Symposium on Electrodynamic and Mechatronic System (SELM)

作者： Zimon, J. Pikula, D. Opole Univ Technol Dept Ind Elect Engn Fac Elect Engn Automat & Informat PL-45758 Opole Poland

ISBN: (纸本)9781467355902;9781467355889

The aim of this work was to design and create a multi-threaded computer application for field integral parameters calculation named PikSolver. Scope of the work included project of the system, implementation of mathematical algorithms and developing a computer application running on Windows operating system which performs multi-threaded calculations of integral parameters of the electromagnetic field. The multi-threaded application allows user to conduct multi-variant electromagnetic field distribution calculations, determine differential and integral parameters of the electromagnetic field for both the static and the quasi-static field including sinusoidal alternating current excitation. Results of the calculations allow user to compare them to the parameters set by the Finite Element Analysis programs.

关键词： Numerical calculations multithread programming advanced object-oriented programming techniques

来源：评论

学校读者我要写书评

暂无评论

A Study of Parallelization and Performance Optimizations Based on OpenMP

A Study of Parallelization and Performance Optimizations Bas...

引用

International Conference on Mechatronics and Industrial Informatics (ICMII 2013)

作者： Shen, Hua Zhou, Guoshun Yan, HuiQi Univ Neusoft Informat Dalian Dept Elect Engn Liaoning 116023 Peoples R China

ISBN: (纸本)9783037856949

The primary consequence of the transition to multicore processors is that applications will increasingly need to be parallelized to improve application's throughput, responsiveness and latency. multithreading is becoming increasingly important for modern programming. Unfortunately, parallel programming is no doubt much more tedious and error-prone than serial programming. Although modern compilers can manage threads well, but in practice, synchronization errors (such as: data race errors, deadlocks) required careful management and good optimization method. This paper presents a preliminary study of the usability of the Intel threading tools for multicore programming. This work compare performance of a single threaded application with multithreaded applications, use tools called Intel (R) VTune Performance Analyzer, Intel (R) Thread Checker and OpenMP to efficiently optimize multithreaded applications.

关键词： Parallelization Performance analysis Multicore multithread programming Threading Tools

来源：评论

学校读者我要写书评

暂无评论

Speed Up the Image Registration with PDE Model and Parallel AOS Scheme

Speed Up the Image Registration with PDE Model and Parallel ...

引用

The Second International Conference on Theoretical and Mathematical Foundations of Computer Science（ICTMF 2011）

作者： Murong Jiang Jian Li Zexian Zhang Jie Zhang Ruilin Guo School of Information Science and Engineering Yunnan University Yunnan Jiaotong College Yunnan Bureau of Meteorolgy

Image registration is to find a suitable space transformation that aligns two or more images of the same scene taken at different times. As the image size is increasing, the numerical approaches based on the pixel matrix may stepup the computation complexity, and it is difficult to perform the large size registration on a single computer in the limited time. PDE-based registration is employing the partial differential equation driven by a similarity measure to minimize the distance between the corresponding pixel points. During the minimization process, Additive operator splitting(AOS) scheme is usually be used. In this paper, we discuss a multithreading method to perform AOS scheme and apply it to the parallel image registration computing with Open MP and MPI on a dual core cluster. Some experimental results show that this method can produce the large size parallel image registration and save the time consume efficiently.

关键词： image registration parallel computing AOS scheme multithread programming

来源：评论

学校读者我要写书评

暂无评论

Speedup and Performance Improvement of ICA-based Robot Audition by Parallel and Resampling-based Block-wise Processing

Speedup and Performance Improvement of ICA-based Robot Audit...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Takeda, Ryu Nakadai, Kazuhiro Takahashi, Toru Komatani, Kazunori Ogata, Tetsuya Okuno, Hiroshi G. Kyoto Univ Dept Intelligence Sci & Technol Grad Sch Informat Kyoto 6068501 Japan Honda Res Inst Japan Co Ltd Wako Saitama 3510114 Japan

ISBN: (纸本)9781424466757

This paper describes a speedup and performance improvement of multi-channel semi-blind ICA (MCSB-ICA) with parallel and resampling-based block-wise processing. MCSB-ICA is an integrated method of sound source separation that accomplishes blind source separation, blind dereverberation, and echo cancellation. This method enables robots to separate user's speech signals from observed signals including the robot's own speech, other speech and their reverberations without a priori information. The main problem when MCSB-ICA is applied to robot audition is its high computational cost. We tackle this by multi-threading programming, and the two main issues are 1) the design of parallel processing and 2) incremental implementation. These are solved by a) multiple-stack-based parallel implementation, and b) resampling-based overlaps and block-wise separation. The experimental results proved that our method reduced the real-time factor to less than 0.5 with an eight-core CPU, and it improves the performance of automatic speech recognition by 2-10 points compared with the single-stack-based parallel implementation without the resampling technique.

关键词： ICA based robot audition MCSB ICA automatic speech recognition blind dereverberation blind source separation block wise processing echo cancellation echo suppression eight core CPU hearing humanoid robots multi-threading multichannel semiblind ICA multithread programming parallel processing resampling reverberation robot programming sound source separation speech recognition

来源：评论

学校读者我要写书评

暂无评论

Periodic steady-state analysis of large-scale electric systems using Poincare map and parallel processing

引用

IEEE TRANSACTIONS ON POWER SYSTEMS 2004年第4期19卷 1784-1793页

作者： Garcia, N Acha, E Univ Glasgow Dept Elect & Elect Engn Glasgow G12 8LT Lanark Scotland

An advanced time-domain representation suitable for accelerated periodic, steady-state solutions of large-scale electric power systems is introduced in this paper. The power system, which is three-phase in nature, is modeled by a set of ordinary differential equations. In addition to the all-important transmission lines' geometric imbalances, frequency-dependency and long-line effects, the transformers' saturation characteristics are also incorporated. In order to provide realistic initial conditions, the data needed for the modeling of the electric system is obtained from power-flow studies. The time domain solution of the overall set of differential equations is computed very reliably using a powerful blend of Newton methods and parallel processing techniques. Whereas the computation of the periodic steady-state solution is obtained with an acceleration procedure based on Newton methods and the Poincare map, the application of parallel processing techniques using multithread programming speeds up further the time taken by the acceleration process to get to the periodic, steady-state solution. To show the effectiveness and versatility of the newly developed environment, transient and steady-state analysis are carried-out for a three-phase version of the IEEE 118-node system, where nonlinearities are incorporated in the form of the transformers' saturation characteristics and a static var compensator.

关键词： harmonics limit cycle multithread programming Newton methods parallel processing periodic steady-state Poincare map

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：