检索结果-内蒙古大学图书馆

12th Mediterranean Conference on Medical and Biological engineering and computing, MEDICON 2010

作者： Campos, R.S. Xavier, M.P. Lobosco, M. Dos Santos, R.W. FISIOCOMP: Laboratory of Computational Physiology and High Performance Computing Computer Science Department Federal University of Juiz de Fora Juiz de Fora Minas Gerais Brazil

ISBN: (纸本)9783642130380

Over the last few years, computer models have become valuable tools for the understanding of complex biological phenomena, such as the electric propagation on cardiac tissue. We have developed a Heart Simulator that models this electric propagation as a set of non-linear system of partial differential equations. Solving this problem is computationally expensive even when a parallel approach is used. Depending on how accurate is the simulation, it can take many hours or even some days to compute a single heart beat. In addition, the simulation of some cardiac diseases as well as the quantification of the cardiac response to drugs demand thousands of single-beat simulations. This would only be feasible today in a Grid, an environment that provides computational resources that are remotely available through the Internet. In this work, we evaluate our Heart Simulator on a Grid environment. The preliminary performance tests suggest that the Heart Simulator is a promising tool and the computational resources of the Grid may promote the use of new and more complex cardiac simulations. © 2010 International Federation for Medical and Biological engineering.

关键词： Grid computing

来源：评论

学校读者我要写书评

暂无评论

A network management system based on DPI

A network management system based on DPI

引用

International Conference on Network-Based Information Systems

作者： Yang, Chu-Sing Liao, Ming-Yi Luo, Mon-Yen Wang, Shin-Min Yeh, C. Eugene Department of Electrical Engineering Institute of Computer and Communication Engineering National Cheng Kung University Taiwan Department of Computer Science and Information Engineering National Kaohsiung University of Applied Sciences Kaohsiung Taiwan National Center for High-Performance Computing Taiwan

ISBN: (纸本)9780769541679

More and more network applications have appeared in recent years. Government, university, industry and individual Internet users and network services need more bandwidth and various network applications. Many new network protocols are proposed so that it is now becoming harder to manage the network. In the conditional network, every network protocol uses the fixed port, the so-called well-known port number. In the past, it was easy to classify and manage the network traffic because we could identify the network service by the port number. However, new types of network applications do not use fixed port number. The method of traffic classification with fixed port number is inadequate. In recent years, the DPI (Deep Packet Inspection) is used to classify the traffic. This study deploys a NMS (network management system) based on DPI and SNMP. The NMS controls the network devices and services according to the traffic classification of DPIS (DPI server). The platform of DPIS is implemented on the Netfilter framework in Linux kernel. © 2010 IEEE.

关键词： Network management

来源：评论

学校读者我要写书评

暂无评论

Submesh allocation in heterogeneous chip multiprocessors

Submesh allocation in heterogeneous chip multiprocessors

引用

International Conference on Machine Learning and Cybernetics

作者： Zuo, Qi Qiu, Jing High Performance Embedded Computing Library School of Computer Science and Technology Beijing Institute of Technology Beijing 100081 China Department of information science and engineering Hebei University of Science and Technology Shijiazhuang 050018 China

ISBN: (纸本)9781424465262

Lots of submesh allocation strategies are devised in mesh connected computers. In chip multiprocessors connected by network on chip, submesh allocation is also used to allocate processors. Existing research mainly focuses on fragmentation, system performance and algorithmic complexity. The processors are assumed to be homogeneous, and the representation of them only reflects the state of processors usage, free or allocated. However, heterogeneous cores have been widely adopted in modern chip multiprocessors to better support the different computation needs. Therefore, the submesh allocation should be re-designed to reflect the difference between cores in heterogeneous chip multiprocessors. In this paper, a simple submesh allocation strategy based on processor array is presented. The strategy represents the heterogeneous processors by computing power array and usage bitmap. The jobs are represented by needed computing power array. A constrained first fit algorithm is devised to map jobs to the chip multiprocessors. © 2010 IEEE.

关键词： computing power

来源：评论

学校读者我要写书评

暂无评论

Location-aware routing for delay tolerant networks

Location-aware routing for delay tolerant networks

引用

作者： Tian, Ye Li, Jiang Anhui Province Key Laboratory on High Performance Computing School of Computer Science and Technology University of Science and Technology of China Hefei Anhui 230027 China Department of Systems and Computer Science Howard University Washington DC 20059 United States

ISBN: (纸本)9780984589333

In this paper, we sought to understand the reasons causing failures and delays of message delivery in Delay Tolerant Networks (DTN), and to use this understanding for improving the network. By studying two real-world datasets, we found that node isolation is prevalent, which largely accounts for the inefficiencies in DTN's message delivery. In addition, by analyzing nodes' contact-location relationship, we found that individual and system-wide key locations exist and their existence suggests potential improvements. Motivated by our observations, we designed a location aware routing scheme for DTN networks. With simulation-based experiments, we compared our proposal with other representative DTN routing schemes, and showed that with the awareness of the location information, our solution can deliver more messages within shorter delays, therefore improves the network intensively.

关键词： Delay tolerant networks

来源：评论

学校读者我要写书评

暂无评论

high performance molecular dynamic simulation on single and multi-GPU systems

High performance molecular dynamic simulation on single and ...

引用

2010 IEEE International Symposium on Circuits and Systems: Nano-Bio Circuit Fabrics and Systems, ISCAS 2010

作者： Villa, Oreste Chen, Long Krishnamoorthy, Sriram High Performance Computing Pacific Northwest National Laboratory Richland WA 99352 United States Department of Electrical and Computer Engineering University of Delaware Newark DE 19716 United States

ISBN: (纸本)9781424453085

The computational power provided by many-core graphics processing units (GPUs) has been exploited in many applications. The programming techniques supported and employed on these GPUs and Multi-GPUs systems are not sufficient to address problems exhibiting irregular, and unbalanced workload such as Molecular Dynamic (MD) simulations of systems with non-uniform densities. In this paper, we propose a task-based dynamic load-balancing solution to employ on MD simulations for single- and multi-GPU systems. The solution allows load balancing at a finer granularity than what is supported in existing APIs such as NVIDIA's CUDA. Experimental results with a single-GPU configuration show that our fine-grained task solution can utilize the hardware more efficiently than the CUDA scheduler. On multi-GPU systems, our solution achieves near-linear speedup, load balance, and significant performance improvement over techniques based on standard CUDA APIs. ©2010 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Dynamic load balancing on single- and multi-GPU systems

Dynamic load balancing on single- and multi-GPU systems

引用

24th IEEE International Parallel and Distributed Processing Symposium, IPDPS 2010

作者： Chen, Long Villa, Oreste Krishnamoorthy, Sriram Gao, Guang R. Department of Electrical and Computer Engineering University of Delaware Newark DE 19716 United States High Performance Computing Pacific Northwest National Laboratory Richland WA 99352 United States

ISBN: (纸本)9781424464432

The computational power provided by many-core graphics processing units (GPUs) has been exploited in many applications. The programming techniques currently employed on these GPUs are not sufficient to address problems exhibiting irregular, and unbalanced workload. The problem is exacerbated when trying to effectively exploit multiple GPUs concurrently, which are commonly available in many modern systems. In this paper, we propose a task-based dynamic load-balancing solution for single- and multi-GPU systems. The solution allows load balancing at a finer granularity than what is supported in current GPU programming APIs, such as NVIDIA's CUDA. We evaluate our approach using both micro-benchmarks and a molecular dynamics application that exhibits significant load imbalance. Experimental results with a single- GPU configuration show that our fine-grained task solution can utilize the hardware more efficiently than the CUDA scheduler for unbalanced workload. On multi- GPU systems, our solution achieves near-linear speedup, load balance, and significant performance improvement over techniques based on standard CUDA APIs. ©2010 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Bayesian cognitive trust model based self-clustering algorithm for MANETs

引用

science China(Information sciences) 2010年第3期53卷 494-505页

作者： WANG Wei1,2,3 & ZENG GuoSun1,2,31department of computer science & Technology, Tongji University, Shanghai 200092, China 2Tongji Branch, National engineering & Technology Center of high performance computer, Shanghai 200092, China 3Key Loboratory of Embedded System and Service computing, Ministry of Education, Shanghai 200092, China 1. Department of Computer Science & Technology Tongji University Shanghai 200092 China2. Tongji Branch National Engineering & Technology Center of High Performance Computer Shanghai 200092 China3. Key Loboratory of Embedded System and Service Computing Ministry of Education Shanghai 200092 China

With the introduction of mobile Ad hoc networks (MANETs), nodes are able to participate in a dynamic network which lacks an underlying infrastructure. Before two nodes agree to interact, they must trust that each will satisfy the security and privacy requirements of the other. In this paper, using the cognition inspired method from the brain informatics (BI), we present a novel approach to improving the search efficiency and scalability of MANETs by clustering nodes based on cognitive trust mechanism. The trust relationship is formed by evaluating the level of trust using Bayesian statistic analysis, and clusters can be formed and maintained autonomously by nodes with only partial knowledge. Simulation experiments show that each node can form and join proper clusters, which improve the interaction performance of the entire network. The essence of the underlying reason is analyzed through the theory of complex networks, revealing great scalability of this method.

关键词： trust model MANET self-clustering Bayesian method cognitive mobile

来源：评论

学校读者我要写书评

暂无评论

An EM method based on entropy LD block partition for haplotype inference

An EM method based on entropy LD block partition for haploty...

引用

2010 IEEE 5th International Conference on Bio-Inspired computing: Theories and Applications, BIC-TA 2010

作者： Xu, Yun Wang, Ying Yao, Xiaohui Zhao, Yuzhong Department of Computer Science University of Science and Technology of China Hefei Anhui 230026 China Anhui Province-MOST Co-Key Laboratory of High Performance Computing and Its Application Hefei Anhui 230027 China

ISBN: (纸本)9781424464388

Genetic diseases have attracted much attention to the genetic research which depends on the data named haplotypes. Because of most haplotypes are generated from genotypes, haplotype inference (HI) problem becomes very popular. To solve this problem, we propose a new method based on EM and partition-ligation (PL) strategy. Compared to the previous methods, our algorithm uses the PL strategy based on multilocus linkage disequilibrium (LD), which has an advantage over the uniform block partition and pairwise LD. Considering the scale of data and the missing alleles, we also change the ligation strategy to control the complexity of time and space. The experimental results on the real data and the simulated data show that the algorithm in this paper has better performance than previous ones. © 2010 IEEE.

关键词： Maximum principle

来源：评论

学校读者我要写书评

暂无评论

A framework of user-driven data analytics in the cloud for course management

A framework of user-driven data analytics in the cloud for c...

引用

18th International Conference on computers in Education: Enhancing and Sustaining New Knowledge Through the Use of Digital Technology in Education, ICCE 2010

作者： Zhang, Jie Tjhi, William Chandra Lee, Bu Sung Lee, Kee Khoon Vassileva, Julita Looi, Chee Kit School of Computer Engineering Nanyang Technological University Singapore A Star Institute of High Performance Computing Singapore Department of Computer Science University of Saskatchewan Canada Centre of Excellence for Learning Innovation National Institute of Education Singapore

ISBN: (纸本)9789834251253

In this paper, we describe our goal of an effective course management system for assisting course managers to make informed decisions about what materials should be most appropriate to be presented to students (learners) and what learning strategies or methods should be used for the students. The system is supported by our design of a novel framework for user-driven data analytics in the cloud. Different modules of the framework will be illustrated in detail in the context of course management.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

An efficient parallel algorithm for longest common subsequence problem on GPUs

An efficient parallel algorithm for longest common subsequen...

引用

作者： Yang, Jiaoyun Xu, Yun Shang, Yi Key Laboratory on High Performance Computing Anhui Province China College of Computer Science and Technology University of Science and Technology of China Heifei Anhui China Department of Computer Science University of Missouri Columbia MO United States

ISBN: (纸本)9789881701299

Sequence alignment is an important problem in computational biology and finding the longest common subsequence (LCS) of multiple biological sequences is an essential and effective technique in sequence alignment. A major computational approach for solving the LCS problem is dynamic programming. Several dynamic programming methods have been proposed to have reduced time and space complexity. As databases of biological sequences become larger, parallel algorithms become increasingly important to tackle large size problems. In the meantime, general-purpose computing on graphics processing units (GPGPU) has emerged as a promising technology for cost-effective high performance computing. In this paper, we develop an efficient parallel algorithm on GPUs for the LCS problem. We propose a new technique that changes the data dependency in the score table used by dynamic programming algorithms to enable higher degrees of parallelism. The algorithm takes advantage of the large number of processing units and the unique memory-accessing properties of GPUs to achieve high performance. The algorithm was implemented on Nvidia 9800GT GPUs and tested on randomly generated sequences of different lengths. The experiment results show that the new algorithm is about 6 times faster on GPUs than on typical CPUs and is 3 times faster than an existing efficient parallel algorithm, the diagonal parallel algorithm.

关键词： Parallel algorithms

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：