检索结果-内蒙古大学图书馆

I/O performance evaluation with Parabench — programmable I/O benchmark

Procedia computer science 2010年第1期1卷 2125-2134页

作者： Olga Mordvinova Dennis Runz Julian M. Kunkel Thomas Ludwig Ruprecht-Karls-Universität Heidelberg Department of Computer Science Im Neuenheimer Feld 348 69120 Heidelberg Germany German Climate Computing Center Bundesstraße 45a 20146 Hamburg Germany Universität Hamburg and German Climate Computing Center Department of Informatics a Bundesstraße 45a 20146 Hamburg Germany

Choosing an appropriate cluster file system for a specific high performance computing application is challenging and depends mainly on the specific application I/O needs. There is a wide variety of I/O requirements: Some implementations require reading and writing large datasets, others out-of-core data access, or they have database access requirements. Application access patterns reflect different I/O behavior and can be used for performance testing. This paper presents the programmable I/O benchmarking tool Parabench . It has access patterns as input, which can be adapted to mimic behavior for a rich set of applications. Using this benchmarking tool, composed patterns can be automatically tested and easily compared on different local and cluster file systems. Here we introduce the design of the proposed benchmark, focusing on the Parabench programming language, which was developed for flexible pattern creation. We also demonstrate here an exemplary usage of Parabench and its capabilities to handle the POSIX and MPI-IO interfaces.

关键词： I/O performance evaluation Access pattern modeling MPI-IO POSIX

来源：评论

学校读者我要写书评

暂无评论

Automatic artifact removal from EEG - a mixed approach based on double blind source separation and support vector machine

Automatic artifact removal from EEG - a mixed approach based...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Georg Bartels Li-Chen Shi Bao-Liang Lu Shanghai Jiao Tong University Shanghai CN Center of Brain Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiaotong University China

Electroencephalography (EEG) recordings are often obscured by physiological artifacts that can render huge amounts of data useless and thus constitute a key challenge in current brain-computer interface research. This paper presents a new algorithm that automatically and reliably removes artifacts from EEG based on blind source separation and support vector machine. Performance on a motor imagery task is compared for artifact-contaminated and preprocessed signals to verify the accuracy of the proposed approach. The results showed improved results over all datasets. Furthermore, the online applicability of the algorithm is investigated.

关键词： Electroencephalography Electrooculography Electromyography Support vector machines Algorithm design and analysis Brain modeling Muscles

来源：评论

学校读者我要写书评

暂无评论

Synchronizing the timestamps of concurrent events in traces of hybrid MPI/OpenMP applications

Synchronizing the timestamps of concurrent events in traces ...

引用

作者： Becker, Daniel Geimer, Markus Rabenseifner, Rolf Wolf, Felix German Research School for Simulation Sciences Laboratory for Parallel Programming 52062 Aachen Germany RWTH Aachen University Department of Computer Science 52056 Aachen Germany Forschungszentrum Jülich Jülich Supercomputing Centre 52428 Jülich Germany University of Stuttgart High Performance Computing-Center 70550 Stuttgart Germany

ISBN: (纸本)9780769542201

Event traces are helpful in understanding the performance behavior of parallel applications since they allow the indepth analysis of communication and synchronization patterns. However, the absence of synchronized clocks on most cluster systems may render the analysis ineffective because inaccurate relative event timings may misrepresent the logical event order and lead to errors when quantifying the impact of certain behaviors or confuse the users of time-line visualization tools by showing messages flowing backward in time. In our earlier work, we have developed a scalable algorithm that eliminates inconsistent inter-process timings postmortem in traces of pure MPI applications. Since hybrid programming, the combination of MPI and OpenMP in a single application, is becoming more popular on clusters in response to rising numbers of cores per chip and widening shared-memory nodes, we present an extended version of the algorithm that in addition to message-passing event semantics also preserves and restores shared-memory event semantics. © 2010 IEEE.

关键词： Message passing

来源：评论

学校读者我要写书评

暂无评论

Computational Complexity of Decoding Orthogonal Space-Time Block Codes

Computational Complexity of Decoding Orthogonal Space-Time B...

引用

IEEE International Conference on Communications (ICC)

作者： E. Ayanoglu E. G. Larsson E. Karipidis Center of Pervasive Communications and Computing Department of Electrical Engineering and Computer Science University of California Irvine Irvine CA USA Department of Electrical Engineering Linköping University Linkoping Sweden

The computational complexity of optimum decoding for an orthogonal space-time block code is quantified. Four equivalent techniques of optimum decoding which have the same computational complexity are specified. Modifi... 详细信息

关键词： Computational complexity Block codes Maximum likelihood decoding Receiving antennas Symmetric matrices Transmitting antennas Matrix decomposition Communications Society Peer to peer computing Pervasive computing

来源：评论

学校读者我要写书评

暂无评论

On 2-Site Voronoi Diagrams under Arithmetic Combinations of Point-to-Point Distances

On 2-Site Voronoi Diagrams under Arithmetic Combinations of ...

引用

International Symposium on Voronoi Diagrams in science and Engineering (ISVD)

作者： Kira Vyatkina Gill Barequet Department of Mathematics and Mechanics Saint Petersburg State University Saint Petersburg Russia Center of Graphics and Geometric Computing Department of Computer Science Technion-Israel Institute of Technology Haifa Israel

ISBN: (纸本)9781424476060;9780769541129

We consider a generalization of Voronoi diagrams, recently introduced by Barequet et al., in which the distance is measured from a pair of sites to a point. An easy way to define such distance was proposed together with the concept: it can be the sum-of, the product-of, or (the absolute value of) the difference-between Euclidean distances from either site to the respective point. We explore further the last definition, and analyze the complexity of the nearest- and the furthest-neighbor 2-site Voronoi diagrams for points in the plane with Manhattan or Chebyshev underlying metrics, providing extensions to general Minkowsky metrics and, for the nearest-neighbor case, to higher dimensions. In addition, we point out that the observation made earlier in the literature that 2-point site Voronoi diagrams under the sum-of and the product-of Euclidean distances are identical and almost identical to the second order Voronoi diagrams, respectively, holds in a much more general statement.

关键词： computer science Digital arithmetic Mathematics computer graphics Mechanical variables measurement Chebyshev approximation Application software History Information resources Books

来源：评论

学校读者我要写书评

暂无评论

Differentiable Spectrum Partition for Fractional Frequency Reuse in Multi-Cell OFDMA Networks

Differentiable Spectrum Partition for Fractional Frequency R...

引用

IEEE Conference on Wireless Communications and Networking

作者： Weihuang Fu Zhifeng Tao Jinyun Zhang Dharma P. Agrawal Center for Distributed and Mobile Computing Department of Computer Science University of Cincinnati Cincinnati OH USA Mitsubishi Electric Research Laboratories Inc. Cambridge MA USA

To mitigate inter-cell interference (ICI) and achieve higher spectrum efficiency, fractional frequency reuse (FFR) has been widely adopted by the next generation wireless systems, wherein different frequency reuse factors are applied to cell center and cell edge zones. In such conventional FFR, a contiguous radio spectrum is partitioned in a fixed fashion across all cells for edge and cell center zones. This approach evidently lacks the flexibility of inter-cell and/or intra-cell resource allocation adjustment and the capability of dealing with traffic load fluctuation and quality of service (QoS) requirements variations. This paper models the implementation of FFR in a multi-cell network environment and proposes a scheme called D-FFR that can adaptively partition radio spectrum in a distributed manner to achieve different FFR configuration among different cells. Resource demands and various inter-cell/intracell allocation constraints are accounted in D-FFR to enable differentiable inter-cell and/or intra-cell throughput and deliver higher spectrum efficiency. Analytical and extensive simulation results are provided in the paper to validate the effectiveness of our proposed scheme.

关键词： Resource management Telecommunication traffic Quality of service Frequency conversion USA Councils Interference Throughput Communications Society Mobile computing computer networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Probabilistic Decision-Based Energy Saving Strategy for the Next Generation Cellular Wireless Systems

Adaptive Probabilistic Decision-Based Energy Saving Strategy...

引用

IEEE International Conference on Communications (ICC)

作者： W. Fu Z. Tao J. Zhang D. P. Agrawal Center of Distributed and Mobile Computing Department of Computer Science University of Cincinnati Cincinnati OH USA Mitsubishi Electric Research Laboratories Inc. Cambridge MA USA

As mobile stations (MSs) in the next generation cellular wireless systems will more frequently operate on multiple applications, such as web browsing, VoIP, online video etc., energy saving becomes more critical and face new challenges from the quality of service (QoS) requirements. A special operation state, called sleep mode, is designed for energy saving of MS, in which MS operates on continuous sleep cycles, where every sleep cycle is the sum of a listening window and a sleep window. This paper proposes an energy saving method that adaptively determines sleep cycles and shifts listening window. When MS is in sleep mode, the sleep cycles are extended by probabilistic decisions related to the traffic statistic attributes. Different from conventional methods, our method is also able to deal with mixed traffic pattern by shifting listening window. Extensive simulation results validate the advantages of our method both in terms of energy saving and shorter response time.

关键词： Quality of service Mobile computing USA Councils Telecommunication traffic Traffic control Handheld computers Communications Society Distributed computing Peer to peer computing computer science

来源：评论

学校读者我要写书评

暂无评论

Clustering Based Fractional Frequency Reuse and Fair Resource Allocation in Multi-Cell Networks

Clustering Based Fractional Frequency Reuse and Fair Resourc...

引用

IEEE International Conference on Communications (ICC)

Fractional frequency reuse (FFR), using different frequency reuse factors for cell center and edge regions, is able to effectively improve spectrum efficiency in multi-cell OFDMA networks. However, optimal performance is hard to achieve in practice as the efficiency of resource allocation could drop drastically due to the constraint from the frequency partitions formed by FFR. Since the radio resource is pre-partitioned for cell edge and center, fair resource allocation in a cell is also difficult to implement. Conventional frequency partition adjustment either has high complexity due to global optimization or suffers from heavy performance degradation due to absence of effective control on inter-cell interference (ICI). To solve this issue, we create models for analyzing geographical distribution of interference in multi-cell networks. Based on the observed non-uniform distributed ICI, we redefine the zones for fractional reuse and propose clustering based FFR, which offers resource allocation higher flexibility and better fairness with additional spatial dimension. Extensive simulation has been performed to validate practicality and effectiveness of our proposed scheme.

关键词： Radio spectrum management Resource management Interference USA Councils Degradation Space technology Communications Society Mobile computing computer networks Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Feature selection for semi-supervised multi-label learning with application to gene function analysis 10

Feature selection for semi-supervised multi-label learning w...

引用

Proceedings of the First ACM International Conference on Bioinformatics and Computational Biology

作者： Li, Guo-Zheng You, Mingyu Ge, Lei Yang, Jack Y. Yang, Mary Qu MOE Key Laboratory of Embedded System and Service Computing Tongji University Shanghai 201804 China Department of Control Science and Engineering Tongji University Shanghai 201804 China School of Computer Science and Engineering Shanghai University Shanghai 200072 China Purdue Univ. ECE West Lafayette IN 47907 United States Indiana Univ. Bioinformatics Center Indianapolis IN 46202 United States

ISBN: (纸本)9781450304382

This paper investigates gene function annotation of Yeast by using semi-supervised multi-label learning. Multi-label learning has been a hot topic in the bioinformatics field, but there are many samples unlabeled. Semi-supervised learning may be employed to utilize the unlabeled data. This paper proposes a novel semi-supervised multi-label learning algorithm COMN by combining Co-Training with ML-kNN to utilize the unlabeled yeast gene data to improve modeling accuracy of function annotation. Furthermore, an embedded feature selection algorithm PRECOMN is proposed to perform feature selection for COMN to remove the irrelevant and redundant features. Experimental results on one benchmark data set of Yeast show COMN and PRECOMN perform better than the original multi-label learning algorithm ML-kNN. Furthermore PRECOMN improves generalization performance of COMN. Copyright © 2010 ACM.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Secure coprocessor-based private information retrieval without periodical preprocessing

Conferences in Research and Practice in Information Technolo...

引用

Conferences in Research and Practice in Information Technology Series 2010年 105卷 5-11页

作者： Wang, Peishun Wang, Huaxiong Pieprzyk, Josef School of Computer Science and Software Engineering University of Wollongong NSW 2522 Australia Center for Advanced Computing Algorithms and Cryptography Department of Computing Macquarie University NSW 2109 Australia Division of Mathematical Sciences School of Physical and Mathematical Sciences Nanyang Technological University Singapore

ISBN: (纸本)9781920682866

Early works on Private Information Retrieval (PIR) focused on minimizing the necessary communication overhead. Theyseemed to achieve this goal but at the expense of query response time. To mitigate this weakness, protocols with secure coprocessors were introduced. They achieve optimal communication complexity and better online processing complexity. Unfortunately, all secure coprocessor-based PIR protocols require heavy periodical preprocessing. In this paper, we propose a new protocol, which is free from the periodical preprocessing while offering the opti-mal communication complexity and almost optimal online processing complexity. The proposed protocol is proven to be secure. © 2010, Australian computer Society, Inc.

关键词： Coprocessor

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：