检索结果-内蒙古大学图书馆

International Symposium on parallel Architectures, Algorithms, and Programming

作者： Yi, Wei Tang, Yuhua Wang, Guibin Fang, Xudong National Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha China

ISBN: (纸本)9780769543123

Recently, GPGPU has been adopted well in the High Performance Computing (HPC) field. The limited global memory bandwidth poses a great challenge to many GPGPU programmers trying to exploit parallelism within the CPUGPU heterogeneous platform. In this paper, we choose SWIM, a typical memory intensive application from the SPEC OMP 2001 benchmark suite, for case study. We attempt to optimize the performance and energy consumption of the application utilizing different memory access mechanisms and present optimization methods including matrix transposition and kernel fusion. The experimental results on the Intel CoreTM i920 CPU plus GeForce GTX 295 platform shows that, the proposed optimizing methods achieve a speedup of 8.7X over the original OpenMP program and reduce the energy consumption by 83% for the problem size of 2048*2048. © 2010 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

A novel open source software ecosystem: From a graphic point of view and its application 28

A novel open source software ecosystem: From a graphic point...

引用

28th International Conference on Software Engineering and Knowledge Engineering, SEKE 2016

作者： Song, Chenxi Wang, Tao Yin, Gang Zhang, Xunhui Yang, Cheng National Laboratory for Parallel and Distributed Processing College of Computer National University of Defense Technology Changsha China

ISBN: (纸本)189170639X

With the rapid development of open source software, various elements such as OSS, developers, users and online posts, across different communities and their interactions constitute a novel software ecosystem. Most of the current researches about software ecosystems care the connections between software, and few of them consider the relationship across communities from an overall perspective, and fail to cover the users and their activities which should be an indispensable part of the OSS ecosystem. This paper model the OSS ecosystem as a graph, which combines different types of OSS communities as a whole. Based on this graph model, we analyze the characteristics of ecosystem, like the evolution, competition and symbiosis. In addition, we build a recommendation system as well, and the experiment results suggest the validation of our approach. Copyright © 2016 by KSI Research Inc. and Knowledge Systems Institute Graduate School.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Towards a new methodology for estimating available bandwidth on network paths

引用

7th International Symposium on Advanced parallel processing Technologies, APPT 2007

作者： Lv, Shaohe Wang, Xiaodong Zhou, Xingming Yin, Jianping National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha Hunan 410073 China

ISBN: (纸本)9783540768364

This paper presents a novel methodology, called COPP, to estimate available bandwidth over a given network path. COPP deploys a particular probe scheme, namely chirp of packet pairs, which is composed of several packet pairs with decremental inter-packet spacing. After each pair chirp is received, COPP discovers all turning points, e.g. such packet pair that is interfered more seriously in contrast to its adjacent pairs, and give each point a distinct weight according to the degree to which the pair and its consecutive neighbors are interfered by cross traffic to yield an estimate. The final estimate is the average of the results of all chirps in a measurement episode. Two decision rules are developed to determine whether a packet pair is turning point We test COPP in various simulations and find that COPP can provide accurate results with relatively less overhead while adapt to network variations rapidly. © Springer-Verlag Berlin Heidelberg 2007.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

iRank: Supporting proximity ranking for peer-to-peer applications

iRank: Supporting proximity ranking for peer-to-peer applica...

引用

15th International Conference on parallel and distributed Systems, ICPADS '09

作者： Fu, Yongquan Wang, Yijie National Key Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology China

ISBN: (纸本)9780769539003

Proximity ranking according to end-to-end network distances (e.g., Round-Trip Time, RTT) can reveal detailed proximity information, which is important in network management and performance diagnosis in distributed systems. However, to the best of our knowledge, there has been no similar work on this subject in the P2P computing field. We present a distributed rating method iRank, that enables proximity rankings by providing discrete ratings in a distributed manner. It formulates the proximity ranking as a rating problem that faithfully captures the proximity based on noisy distance measurements scalably and practically. The primary challenge in inferring proximity rankings is enforcing distributed ratings with complex rating policies. Our solution is based on reconstructing ratings by decomposing a centralized rating method Maximum Margin Matrix Factorization (MMMF) into independent sub-problems, that can be efficiently solved in a decentralized manner. By relaxing the dependence on infrastructure nodes that are a single point of failure and limit scalability, iRank can gracefully handle network churns. Through real network latency data sets, we demonstrate that iRank can predict ratings with low distortion, which are smaller than 20 percentage worse than the centralized method, in the context of synthetic complex rating policies. © 2009 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Impact of imprecise programming of memristor on building hardware neural network

Impact of imprecise programming of memristor on building har...

引用

2nd Annual Conference on Electrical and Control Engineering, ICECE 2011

作者： Zhu, Xuan National Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology ChangSha China

ISBN: (纸本)9781424481637

The application of memristor in building hardware neural network has accepted widespread interests, and may bring novel opportunities to neural computing. However, due to the limitation of programming precision, the conductance of memristor which represents stored information may deviate from theoretical value, and thus bring error to the neural computing results. In this paper, we analyze the impact of imprecise programming on building hardeware neural network through Monte Carlo simulation on feedback layer model. The results show that the fault-tolerance ability of neural network could well adapt to these errors, which further proves the potential of building neural networks using memristors. © 2011 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Improving performance portability for GPU-specific Open CL kernels on multi-core/many-core CPUs by analysis-based transformations

引用

Frontiers of Information Technology & Electronic Engineering 2015年第11期16卷 899-916页

作者： Mei WEN Da-fei HUANG Chang-qing XUN Dong CHEN School of Computer National University of Defense Technology National Key Laboratory of Parallel and Distributed Processing

OpenCL is an open heterogeneous programming framework. Although OpenCL programs are func- tionally portable, they do not provide performance portability, so code transformation often plays an irreplaceable role. When adapting GPU-specific OpenCL kernels to run on multi-core/many-core CPUs, coarsening the thread granularity is necessary and thus has been extensively used. However, locality concerns exposed in GPU-specific OpenCL code are usually inherited without analysis, which may give side-effects on the CPU performance. Typi- cally, the use of OpenCL＇s local memory on multi-core/many-core CPUs may lead to an opposite performance effect, because local-memory arrays no longer match well with the hardware and the associated synchronizations are costly. To solve this dilemma, we actively analyze the memory access patterns using array-access descriptors derived from GPU-specific kernels, which can thus be adapted for CPUs by （1） removing all the unwanted local-memory arrays together with the obsolete barrier statements and （2） optimizing the coalesced kernel code with vectorization and locality re-exploitation. Moreover, we have developed an automated tool chain that makes this transformation of GPU-specific OpenCL kernels into a CPU-friendly form, which is accompanied with a scheduler that forms a new OpenCL runtime. Experiments show that the automated transformation can improve OpenCL kernel performance on a multi-core CPU by an average factor of 3.24. Satisfactory performance improvements axe also achieved on Intel＇s many-integrated-core coprocessor. The resultant performance on both architectures is better than or comparable with the corresponding OpenMP performance.

关键词： OpenCL Performance portability Multi-core/many-core CPU Analysis-based transformation

来源：评论

学校读者我要写书评

暂无评论

Optimizing adaptive synchronization in parallel simulators for large-scale parallel systems and applications

Optimizing adaptive synchronization in parallel simulators f...

引用

10th IEEE International Conference on Computer and Information Technology, CIT-2010, 7th IEEE International Conference on Embedded Software and Systems, ICESS-2010, 10th IEEE Int. Conf. Scalable Computing and Communications, ScalCom-2010

作者： Xu, Chuanfu Che, Yonggang Fang, Jianbin Wang, Zhenghua National Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha China

ISBN: (纸本)9780769541082

This paper addresses the optimization of parallel simulators for large-scale parallel systems and applications. Such simulators are often based on parallel discrete event simulation with conservative or optimistic protocols to synchronize the simulating processes. The paper considers how available future information about events and application behaviors can be efficiently extracted and further exploited to improve the performance of adaptive optimistic protocols. First, we extract information about future events and their dependencies in application traces to guide adaptive adjustments of time window in trace-driven parallel simulation. Second, we use information about application behaviors, specifically the iterative behavior found in many applications, to avoid the unnecessary adjustments of time window. These techniques are implemented in the BigSim simulator and tested by real-world and standard benchmark applications including Jacobi3D and HPL. The results show that our optimization approaches can reduce the execution times of simulation ranging from 11% up to 32%. Moreover, our methods are easy to implement and don't need to augment compilers or even modify the core codes of parallel simulators. © 2010 IEEE.

关键词： Simulators

来源：评论

学校读者我要写书评

暂无评论

Applying active measurement in the rate adaptation for 802.11 wireless networks 4

Applying active measurement in the rate adaptation for 802.1...

引用

4th Annual International Conference on Wireless Internet, WICON 2008

作者： Lv, Shaohe Wang, Xiaodong Zhou, Xingming National Laboratory of Parallel and Distributed Processing National University of Defense Technology ChangSha Hunan410073 China

Rate Adaptation (RA) is a mechanism to choose transmission rate based on the dynamic channel quality in wireless networks. The adaptation algorithm run solely at the sender side in 802.11 networks is studied. The key insight is the inference discrepancy in inferring the relative order of the expected performance of candidate rate, which argues that one can not always reach the correct order based on the channel state information collected exclusively by the sender itself. The consequence is wrong rate decision and significant performance loss. Therefore, a new RA structure is proposed to mitigate such effect by a novel component, rate testing. By embracing the active measurement, a lightweight and effective testing mechanism SFB, short frame burst, is proposed to detect and filter out the unsuitable transmission rate. Finally, an active measurement-based rate adaptation mechanism (AMRA) is designed and implemented. The experiments show that AMRA outperforms many other well-known RA solutions in most scenarios. Copyright © 2008 ICST.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Property-oriented testing of real-time systems

Property-oriented testing of real-time systems

引用

Proceedings - 11th Asia-Pacific Software Engineering Conference, APSEC 2004

作者： Li, Shuhao Wang, Ji Dong, Wei Qi, Zhi-Chang National Laboratory for Parallel and Distributed Processing Changsha China State Key Laboratory for Software Engineering Wuhan University China

ISBN: (纸本)0769522459

Although Statecharts has gained widespread use as a formalism for modeling reactive real-time systems, testing these systems still confronts some difficulties, of which a major one is the existence of numerous and complex system behaviors. It is extremely difficult to conduct comprehensive and in-depth testing of such real-time systems. This paper presents an approach to property-oriented real-time testing. Necessary real-time extensions are proposed such that the time-enriched Statecharts can describe non-trivial timing constraints. The properties to be tested are characterized by a restricted real-time logic. Then the targeted test sequences are derived from the real-time models according to the user-specified properties. Using this approach, testing efforts can be focused on particular properties of the real-time systems and usually only a small portion of the total behaviors needs to be tested. © 2004 IEEE.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Automatic generation of run-time test oracles for distributed real-time systems

引用

24th IFIP WG 6.1 International Conference on Formal Techniques for Networked and distributed Systems, FORTE 2004

作者： Wang, Xin Wang, Ji Qi, Zhi-Chang National Laboratory for Parallel and Distributed Processing 300 Lichen Rd Changsha410073 China

ISBN: (纸本)3540232524

distributed real-time systems are of one important type of real-time systems. They are usually characterized by both reactive and real-time factors and it has long been recognized that how to automatically check such systems’ correctness at run time is still an unaddressed problem. As one of the main solutions, test oracle is a method usually used to check whether the system under test has behaved correctly on a particular execution. Test oracle is not only the indispensable stage of software testing, but also the weak link of the software testing research. In this paper, real-time specifications are adopted to describe the properties of distributed real-time systems and a real-time specification-based method for automatic run-time test oracles generating is proposed. The method proposed here is based on tableau construction theory of real-time model checking, automatically generates timed automata as test oracles, which can automatically check system behaviors’ correctness from real-time specifications written in MITL[0,d]. © IFIP International Federation for Information processing 2004.

关键词： Software testing

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：