检索结果-内蒙古大学图书馆

2016 2nd international conference on Artificial Intelligence and Industrial engineering (AIIE2016)

作者： Zelong Wang Qiang Lan Dafei Huang Mei Wen Department of Compute National University of Technology Defense National Key Laboratory of Parallel and Distributed Processing National University of Defense Technology

ISBN: (纸本)9781510835368

Convolution operation is the most important and time consuming step in a convolution neural network *** this work,we analyze the computing complexity of direct convolution and fast-Fourier-transform-based(FFT-based) *** creatively propose CS-unit,which is equivalent to a combination of a convolutional layer and a pooling layer but more *** computing complexity of and some other similar operation is demonstrated,revealing an advantage on computation of ***,practical experiments are also performed and the result shows that CS-unit holds a real superiority on run time.

关键词： computing complexity FFT-based convolution CS-unit

来源：评论

学校读者我要写书评

暂无评论

Towards a smart selection of resources for low-energy multimedia processing

Towards a smart selection of resources for low-energy multim...

引用

international conference on cloud Technologies and Applications (cloudTech)

作者： Sidi Ahmed Mahmoudi Faculty of Engineering University of Mons Belgium

ISBN: (纸本)9781467388955

Today, one can find images and videos everywhere, they can come from cameras, mobile phones or from other devices. These images and videos are used to illustrate different objects in a large number of situations (airports, hospitals, public areas, sport events, etc.). This makes the task of processing images and videos a necessary tool that can be used for various domains related to computer vision. The performance of these algorithms have been so reduced due to their high intensive computation and energy consumption. In this work, we propose a new framework that allows users to select in a smart and efficient way the computing units (CPU or/and GPU) in case of processing single image, multiple images, multiple videos or single video in real time. This framework enables to affect the CPU or/and GPU units for calculation depending on the type of media to process and the algorithm complexity. The framework provides several image and video functions on GPU, such as silhouette extraction, points of interest extraction, edges detection, sparse and dense optical flow estimation. These functions are exploited in different applications such as vertebra segmentation in X-ray and MR images, gaze estimation, event detection and localization in real time. Experimental results have been obtained by applying the framework for different use case applications showing a speedup ranging from 5 to 116×, by comparison with sequential CPU implementations. In addition to these performance, the parallel and heterogeneous implementation offered lower power consumption as a result for the fast treatment.

关键词： Biomedical imaging Performance evaluation Estimation Cameras Image edge detection Hardware Graphics processing units

来源：评论

学校读者我要写书评

暂无评论

Optimizing Virtual Machine Live Migration without Shared Storage in Hybrid clouds

Optimizing Virtual Machine Live Migration without Shared Sto...

引用

IEEE international conference on High Performance computing and Communications

作者： Shan He Chunming Hu Bin Shi Tianyu Wo Bo Li State Key Laboratory of Software Development Environment (NLSDE) School of Computer Science and Engineering Beihang University Beijing China 100191

ISBN: (纸本)9781509042982

Virtual machine live migration technology allows a running VM migrates from one physical host to another with no impact on users. As the scale of distributed computing gets larger and larger, hybrid cloud, which is integrated cloud service utilizing both private and public clouds to perform distinct functions within the same organization becomes a hotspot for both academia and industry. Thus, it will be vital to migrate virtual machines in hybrid clouds. The biggest issue which VM migration in hybrid clouds faces today is how to transfer the large amount of storage data. Storage migration of virtual machine with existing mechanisms of memory migration has been studied for a long time. Unfortunately, no one can perform perfectly without modification. It is compelling to consider a new migration model and optimization methods. In this paper, we analyze the advantage and disadvantage of classical methods, and put forward a method which combines the strengths of pre-copy and post-copy migration model and we also use disk working set to optimize virtual machines storage migration. We have developed and implemented our approach to the QEMU/KVM hypervisor and run a series of experiments. The presented technique shows a reduction of up 20.5% on average of the total transfer time for most of the selected scenario. Our approach can also reduce the migration downtime in most cases.

关键词： working set virtual machine live migration storage

来源：评论

学校读者我要写书评

暂无评论

Optimal Task Scheduling in cloud computing Environment: Meta Heuristic Approaches 2

Optimal Task Scheduling in Cloud Computing Environment: Meta...

引用

2nd international conference on Electrical Information and Communication Technology (EICT 2015)

作者： Mandal, Tripti Acharyya, Sriyankar West Bengal Univ Technol Comp Sci & Engn Kolkata W Bengal India

ISBN: (纸本)9781467392570

cloud computing is the latest continuation of parallel computing, distributed computing and grid computing. In this system, user can make use of different services like storage, servers and other applications. cloud resources are not only used by numerous users but are also dynamically redistributed on demand. Requested services are delivered to user's computers and devices through the Internet. The fundamental issue in cloud computing system is related to task scheduling where a scheduler finds an optimal solution in cost-effective manner. Task scheduling issue is mainly focus on to find the best or optimal resources in order to minimize the total processing time of Virtual Machines (VMs). cloud task scheduling is an NP-hard problem. The focus is on increasing the efficient use of the shared resources. A number of meta-heuristic algorithms have been implemented to solve this issue. In this work three meta-heuristic techniques such as Simulated Annealing, Firefly Algorithm and Cuckoo Search Algorithm have been implemented to find an optimal solution. The main goal of these algorithms is to minimize the overall processing time of the VMs which execute a set of tasks. The experimental result shows that Firefly Algorithm (FFA) performs better than Simulated Annealing and Cuckoo Search Algorithm.

关键词： cloud computing Task Scheduling Simulated Annealing Firefly Algorithm Cuckoo Search Algorithm

来源：评论

学校读者我要写书评

暂无评论

Fast Community Detection in Large Weighted Networks Using GraphX in the cloud

Fast Community Detection in Large Weighted Networks Using Gr...

引用

IEEE international conference on High Performance computing and Communications

作者： Xiao Ling Jiahai Yang Dan Wang Jinfeng Chen Liyao Li Tsinghua National Laboratory for Information Science and Technology Institute for Network Sciences and Cyberspace Tsinghua University Department of Computing The Hong Kong Polytechnic University School of Electronic and Information Engineering Fuqing Branch of Fujian Normal University

ISBN: (纸本)9781509042982

Identification of different communities in large weighted networks is of crucial importance since it helps to uncover priori unknown functional modules such as topics in information networks or cyber-communities in social networks. However, the typical size of networks, such as social network services or World Wide Web, now counts in millions of nodes and is computationally complex. This urgently demands feasible methods and available computing platforms to retrieve their structure efficiently. To address this problem, we propose an algorithm Fast Community Detection (FastCD) based on modularity optimization. Furthermore, FastCD easily supports parallel computation. We implement FastCD with GraphX, which is an embedded graph processing framework built on top of Apache Spark. After carrying out comprehensive experiments in a 16-nodes cluster (32 vCPU) on Amazon EC2, the results indicate that FastCD not only outperforms the state-of-the-art algorithms in terms of computation time, but also guarantees the accuracy of the solutions under different real-world networks commonly used for efficiency comparison.

关键词： GraphX Community Detection Modularity Optimization FastCD

来源：评论

学校读者我要写书评

暂无评论

Customized web user interface for hadoop distributed file system

引用

Advances in Intelligent Systems and computing 2016年 380卷 567-576页

作者： Krishna, T. Lakshmi Siva Rama Ragunathan, T. Battula, Sudheer Kumar Hyderabad India Department of CSE ACE Engineering College Hyderabad India

ISBN: (纸本)9788132225225

distributed file system (DFS) is one of the main components of a cloud computing system used to provide scalable storage solutions for Big Data applications. hadoop distributed file system (HDFS) is one of the core components of Apache Hadoop project and many IT companies are using HDFS to store and manage Big Data. HDFS provides both command line and web-based interface to the users for storing and accessing data. The web-based user interface (WBUI) is used only for browsing the file system whereas the command line interface (CLI) is used for creating a file and performing read or write operations on the file. The CLI provides many more facilities and note that CLI is not user friendly as the user has to remember and type the commands to access the HDFS. In this paper, we propose a new customized web user interface (CWBUI) for the HDFS. We have developed CWBUI using servlets and java server pages (JSP) and deployed the same in a Hadoop cluster. The CWBUI is found to be very helpful in using the HDFS in an interactive manner without the need of typing commands in the user interface. © Springer India 2016.

关键词： File organization

来源：评论

学校读者我要写书评

暂无评论

Implementing Molecular Dynamics Simulation on Sunway TaihuLight System

Implementing Molecular Dynamics Simulation on Sunway TaihuLi...

引用

IEEE international conference on High Performance computing and Communications

作者： Wenqian Dong Letian Kang Zhe Quan Kenli Li Keqin Li Ziyu Hao Xiang-Hui Xie College of Information Science and Engineering Hunan University Changsha Hunan 410082 China Department of Computer Science State University of New York New Paltz NY 12561 USA Jiangnan Institute of Computing Technology Wuxi Jiangsu 214000 China

ISBN: (纸本)9781509042982

Molecular dynamics (MD) simulation is a common tool to study the physical movements of atoms and molecules in many research fields. However, it is an extremely time-consuming application which takes researchers weeks or months to run a single simulation when simulation size scales up and computing demands keep growing. In this paper, an improved MD implementation on Sunway TaihuLight supercomputer is developed to solve the above mentioned issues. The new implementation is extended from an existing implementation (i.e., LAMMPS) which widely uses the MD application. Sunway TaihuLight is a heterogeneous supercomputer with a fully customized integration approach and a brand new many-core processor SW26010. The Sunway TaihuLight takes the world's first place with peak performance over 100PFlops. We propose an optimization method of the MD simulation in three steps: paralleled extensions to SW26010, memory-access optimizations, and vectorization. After the optimization process, an 8x speedup is achieved on a single computing node. Superiorly, we also scale up to 95 thousands computing nodes (6 millions cores) with an almost leaner speedup. Besides, the proposed methods can also be applied to many other molecular dynamics codes, or similar applications.

关键词： Sunway TaihuLignt Molecular Dynamics Simulation High performance computing parallel distributed computing

来源：评论

学校读者我要写书评

暂无评论

Independent Task Scheduling in cloud Environment Using Big Bang-Big Crunch Approach 2

Independent Task Scheduling in Cloud Environment Using Big B...

引用

2nd international conference on Recent Advances in engineering

作者： Kumari, Vandna Kalra, Mala Singh, Sarbjeet NITTTR Dept CSE Chandigarh India UIET Dept CSE Chandigarh India

ISBN: (纸本)9781467382533

cloud computing is a well known computing technology that deals with large capacity of information or data using highly available geographically distributed resources that can be accessed by user via internet in terms of pay per use basis. In such a way, tasks should be scheduled efficiently such that user specified QoS constraints are satisfied. Task scheduling, which is NP-complete problem, plays an important role in cloud computing. In this research work, Big Bang-Big Crunch (BBBC) technique is used for scheduling of independent tasks in the cloud environment aiming to reduce makespan. The performance of the proposed approach is evaluated by comparing it against GA using cloudSim tool. Experimental results show that the BBBC approach outperforms GA approach in terms of makespan.

关键词： cloud computing big bang big crunch genetic algorithm task scheduling

来源：评论

学校读者我要写书评

暂无评论

Use of cloud computing for distributed simulation: A way forward 2nd

Use of cloud computing for distributed simulation: A way for...

引用

2nd international conference on Computer, Intelligent computing and Education Technology (CICET)

作者： Fan, Xi Hui Fan, Zhi Xuan, Qian Li, Ming Xi New Star Res Inst Appl Technol Hefei Peoples R China

ISBN: (纸本)9781315685892;9781138028005

Many of the current, in-use simulation systems today are difficult to install, configure, and execute. cloud computing has received a significant amount of attention leading to large information technology (IT) initiatives at the corporate and government levels. It is natural to explore the cloud computing with the modeling and simulation (M&S) community. The paper puts forward a distributed simulation framework use of cloud computing.

关键词： cloud computing Simulation Virtualization SOA OWL

来源：评论

学校读者我要写书评

暂无评论

Managing Heterogeneity in Model-Based Systems engineering of Cyber-Physical Systems 10

Managing Heterogeneity in Model-Based Systems Engineering of...

引用

10th international conference on P2P, parallel, grid, cloud and Internet computing 3PGCIC

作者： Van Acker, Bert Denil, Joachim Vangheluwe, Hans De Meulenaere, Paul Univ Antwerp Constrained Syst Lab CoSys Lab Antwerp Belgium Univ Antwerp Ansymo Antwerp Belgium

ISBN: (纸本)9781467394734

Model-based Systems engineering plays a pivotal role in the design of distributed embedded systems by enabling early virtual integration of the different parts of the system. Traditionally, the system model is composed of subsystem models at the same level of abstraction and with one particular view. However, in some cases the system model may comprise subsystem models at different levels of abstraction. Integration of these different abstraction level models imposes some important drawbacks which hinder the overall system simulations. These drawbacks need to be addressed to facilitate the simulation of systems composed with multi-level subsystem models. In this paper we report on modelling techniques for embedded and distributed systems to deal with this heterogeneity. We describe a methodology to (semi-)automatically generate an executable multi-level system simulation model starting from an abstract system architecture of the system. A platooning system example is used to demonstrate the new modelling techniques.

关键词： Cyber-physical systems distributed Embedded Systems Model-Driven engineering

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：