检索结果-内蒙古大学图书馆

Improved conjugate residual algorithm for large symmetric linear systems

Jisuanji Xuebao/Chinese Journal of computers 2006年第3期29卷 495-499页

作者： Liu, Jie Liu, Xing-Ping Chi, Li-Hua Hu, Qing-Feng National Laboratory of Parallel and Distributed Processing School of Computer Science National University of Defense Technology Changsha 410073 China Institute of Applied Physics and Computation Mathematics Beijing 100088 China

The conjugate residual (CR) algorithm is a Krylov subspace algorithm that can be used to obtain fast solutions for symmetric linear systems with very large and very sparse coefficient matrices. By changing the computation sequence in the CR algorithm, this paper proposes an improved Conjugate Residual (ICR) algorithm. The numerical stability of ICR algorithm is same as CR algorithm, but the synchronization overhead that represents the bottleneck of the parallel performance is effectively reduced by a factor of two. And all inner products of a single iteration step are independent and communication time required for inner product can be over lapped efficiently with computation time of vector updates. From the theoretical and experimental analysis it is found that ICR algorithm is faster than CR algorithm as the number of processors in creases. The experiments performed on a 64-processor cluster indicate that ICR is approximately 30% faster than CR.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Scheduling algorithm for long duration transaction based on cost of compensation

引用

Ruan Jian Xue Bao/Journal of Software 2009年第3期20卷 744-753页

作者： Zhu, Rui Guo, Chang-Guo Wang, Huai-Min School of Computer National University of Defense Technology Changsha 410073 China National Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha 410073 China

Transaction of service composition has long-lived feature which a global-transaction is divided into several distributed sub-transactions. Atomicity property is preserved by using compensating transactions, which semantically undo the effects of the completed sub-transactions, in case of global-transaction abort. However, the cost of compensation may be expensive and methods may be complex. To overcome this limitation, a novel scheduling algorithm named STCD (SubTransaction committing delay) is presented based on analysis of compensation. Different from traditional methods, sub-transactions determine the time of committing according to both the cost of compensation and the state of execution dynamically. The correctness of proposed algorithm is proved. Simulations show that STCD algorithm can confine the compensation sphere and reduce the cost of compensation. © by Institute of Software, the Chinese Academy of sciences. All rights reserved.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Maximizing Uniform Multicast Throughput in Multi-Channel Dense Wireless Sensor Networks

Maximizing Uniform Multicast Throughput in Multi-Channel Den...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Xianlong Jiao Guirong Chen Xiaodong Wang Yuli Chen Li Yang College of Information System and Management National University of Defense Technology Changsha Information and Navigation College Air Force Engineering University Xi'an Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha Chongqing Guanyinqiao Elementary School Chongqing Chongqing Liangjiangxinqu Renhe Experimental School Chongqing

ISBN: (纸本)9781509056972

This paper investigates the problem of maximizing uniform multicast throughput (MUMT) for multi-channel dense wireless sensor networks, where all nodes locate within one-hop transmission range and can communicate with each other on multiple orthogonal channels. This kind of networks show wide application in the real world, and maximizing uniform multicast throughput for these networks is worth deep studying. Previous researches have proved MUMT problem is NP-hard. However, previous researches are either hard to implement, or use too many relay nodes to complete the multicast task, and thus incur high overhead or poor performance. To efficiently solve MUMT problem, we adopt the concept of the maximum independent set with the size constraint, and present one novel Single-Broadcast based Multicast algorithm called SBM based on the concept. We prove that SBM algorithm achieves a constant ratio to the theoretical throughput upper bound. Extensive experimental results demonstrate that, SBM performs better than existing work in terms of both the uniform multicast throughput and the total number of transmissions.

关键词： Throughput Wireless sensor networks Approximation algorithms Schedules Data communication Algorithm design and analysis Relays

来源：评论

学校读者我要写书评

暂无评论

Optimization approaches of organizing streams on imagine processor

引用

Jisuanji Xuebao/Chinese Journal of computers 2008年第7期31卷 1092-1100页

作者： Yang, Xue-Jun Zeng, Li-Fang Deng, Yu Tang, Yu-Hua National Key Laboratory of Parallel and Distributed Processing School of Computer Science National University of Defense Technology Changsha 410073 China Jiangnan Remote Sensing Institute Shanghai 200072 China

Due to the characteristics of stream applications and the insufficiency of conventional processors when running stream programs, stream processors which support data-level parallelism become the research hotspot. This paper presents two means, stream partition (SP) and stream compression (SC), to optimize streams on Imagine. The results of simulation show that SP and SC can make stream applications take full advantage of the parallel clusters, pipelines and three-level memory hierarchy of the Imagine processor, and then reduce the execution time of stream programs.

关键词： parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Multi-replica clustering management method based on limited-coding

引用

Ruan Jian Xue Bao/Journal of Software 2007年第6期18卷 1456-1467页

作者： Zhou, Jing Wang, Yi-Jie Li, Si-Kun School of Computer National University of Defense Technology Changsha 410073 China National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha 410073 China

In this paper, according to the resource management problems brought by a large number of replicas, a multi-replica clustering management method based on limited-coding is proposed. In this method, according to the process of creating new replicas from existent single replica, replicas are partitioned into different hierarchies and clusters. Then replicas are coded and managed based on the user-defined limited-coding rule consisting of replica hierarchy and replica sequence, which can also dispose the alteration of clusters caused by dynamic adjustments on replicas (replica addition or replica removal) effectively. After that, a management model of centralization in local and peer to peer in wide area is adopted to organize replicas, and the cost of reconciling consistency can be greatly depressed combining with defined minimal-time of update propagation. The relevance between the coding rule and the number of replicas, and the solutions to replica failure and replica recover are discussed. The results of the performance evaluation show that the clustering method is an efficient way to manage a large number of replicas, achieving good scalability, not sensitive to moderate node failure, and adapting well to applications with frequent updates.

关键词： Data processing

来源：评论

学校读者我要写书评

暂无评论

Research on self-similar network traffic prediction

Hunan Daxue Xuebao/Journal of Hunan University Natural Scien...

引用

Hunan Daxue Xuebao/Journal of Hunan University Natural sciences 2008年第6期35卷 82-86页

作者： Zhang, Guang-Sheng Li, Jing-Bo Dou, Wen-Hua Shao, Li-Song National Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha 410073 China Journal of Hunan University Changsha 410082 China

Recent studies on network traffic have shown that self-similar is very popular, and the character will not be changed during buffering, switching and transmitting. The character self-similar must be considered in network traffic prediction. This paper analyzed and summarized the research results of self-similar network traffic prediction from the fields of self-similar modeling, parameter computing and performance prediction. An equivalent bandwidth algorithm of self-similar traffic prediction based on measurement was put forward. Our analysis has shown that the algorithm can effectively reduce computing and realizing complexities.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Two layered P2P model for semantic service discovery

引用

Ruan Jian Xue Bao/Journal of Software 2007年第8期18卷 1922-1932页

作者： Liu, Zhi-Zhong Wang, Huai-Min Zhou, Bin Institute of Network and Information Security School of Computer National University of Defense Technology Changsha 410073 China National Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha 410073 China

In open Internet environment, it is inevitable that multiple ontologies coexist. Centralized service discovery mechanism becomes the bottleneck of SOC (service oriented computing), which results in poor scalability of system. Aiming at solving these problems, a two layered P2P based model for semantic service discovery is proposed in this paper. The model is based on ontology community and integrates iVCE (Internet-based virtual computing environment) core concepts into a P2P model. Based on this model, a service discovery algorithm composed of two stages and three steps is proposed. It matches services across communities as well as within community. Within a community, algorithm locates registers holding service information with a high probability of satisfying a request firstly. Then it captures semantic matching between service advertisements and service requests by logical reasoning. Service discovery across communities occurs according to some policies. The model is suitable for opening environment with coexistent multiple ontologies. Experimental results show that given an appropriate setting, the model can make a tradeoff between recall and responding time. In addition, the model will release the mean load of registers efficiently while holding recall.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

FCloudless: A Performance-Aware Collaborative Mechanism for JointCloud Serverless

FCloudless: A Performance-Aware Collaborative Mechanism for ...

引用

IEEE International Conference on Joint Cloud Computing (JCC)

作者： Jianfei Liu Huaimin Wang Peichang Shi Yaojie Li Penghui Ma Guodong Yi National Key Laboratory of Parallel and Distributed Computing College of Computer Science National University of Defense Technology Changsha 410073 China Key Laboratory of Software Engineering for Complex Systems College of Computer Science National University of Defense Technology Changsha 410073 China Xiangjiang Lab Changsha 410073 China School of Advanced Interdisciplinary Studies Hunan University Of Technology and Business Changsha 410073 China

As a new stage in the development of the cloud computing paradigm, serverless computing has the high-level abstraction characteristic of shielding underlying details. This makes it extremely challenging for users to choose a suitable serverless platform. To address this, targeting the jointcloud computing scenario of heterogeneous serverless platforms across multiple clouds, this paper presents a jointcloud collaborative mechanism called FCloudless with cross-cloud detection of the full lifecycle performance of serverless platforms. Based on the benchmark metrics set that probe performance critical stages of the full lifecycle, this paper proposes a performance optimization algorithm based on detected performance data that takes into account all key stages that affect the performance during the lifecycle of a function and predicts the overall performance by combining the scores of local stages and dynamic weights. We evaluate FCloudless on AWS, AliYun, and Azure. The experimental results show that FCloudless can detect the underlying performance of serverless platforms hidden in the black box and its optimization algorithm can select the optimal scheduling strategy for various applications in a jointcloud environment. FCloudless reduces the runtime by 23.3% and 24.7% for cold and warm invocations respectively under cost constraints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scalable unbiased sampling method based on multi-peer adaptive random walk

引用

Ruan Jian Xue Bao/Journal of Software 2009年第3期20卷 630-643页

作者： Fu, Yong-Quan Wang, Yi-Jie Zhou, Jing National Key Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha 410073 China Staff Room of Computer Command Academy of the Corps of Engineers Xuzhou 221000 China

To deal with the scalable and fast unbiased sampling problems in unstructured P2P systems, a sampling method based on multi-peer adaptive random walk (SMARW) is proposed. In the method, based on the multi-peer random walk process, a set of provisional peers are selected as agents which start the sampling processes, by which the sampling process is speeded up with receiving a set of tunable number samples each time;Meanwhile, after receiving new samples earlier agents are replaced with these new samples which repeat the sampling process. With this simple replacement, it can be guaranteed with high probability that the system can reach the optimal load balance;furthermore, SMARW adopts an adaptive distributed random walk adjustment process to increase the convergence rate of the sampling process. A detailed theorical analysis and performance evaluation confirm that SMARW has a high level of unbiased sampling and near-optimal load balancing capability. © by Institute of Software, the Chinese Academy of sciences. All rights reserved.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning for combinatorial optimization: Covering salesman problems

arXiv

引用

arXiv 2021年

作者： Li, Kaiwen Zhang, Tao Wang, Rui Wang, Yuheng Han, Yi College of Systems Engineering National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Multi-Energy System Intelligent Interconnection Technology HKL-MSI2T Changsha410073 China Graduate College National University of Defense Technology Changsha410073 China Science and Technology on Parallel and Distributed Processing Laboratory College of Computer National University of Defense Technology Changsha410073 China

This paper introduces a new deep learning approach to approximately solve the Covering Salesman Problem (CSP). In this approach, given the city locations of a CSP as input, a deep neural network model is designed to directly output the solution. It is trained using the deep reinforcement learning without supervision. Specifically, in the model, we apply the Multi-head Attention to capture the structural patterns, and design a dynamic embedding to handle the dynamic patterns of the problem. Once the model is trained, it can generalize to various types of CSP tasks (different sizes and topologies) with no need of re-training. Through controlled experiments, the proposed approach shows desirable time complexity: it runs more than 20 times faster than the traditional heuristic solvers with a tiny gap of optimality. Moreover, it significantly outperforms the current state-of-the-art deep learning approaches for combinatorial optimization in the aspect of both training and inference. In comparison with traditional solvers, this approach is highly desirable for most of the challenging tasks in practice that are usually large-scale and require quick decisions. Copyright © 2021, The Authors. All rights reserved.

关键词： Combinatorial optimization

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：