检索结果-内蒙古大学图书馆

International Conference on Advanced computer Theory and engineering, ICACTE

作者： Bo Peng Xingyu Geng Jun Zhang College of Computer Science Southwest Petroleum University Chengdu China Laboratory of High Performance Scientific Computing and Computer Simulation Department of Computer Science University of Kentucky Lexington KY USA

The problem of privacy-preserving data mining has become more and more important in recent years. Many successful and efficient techniques have been developed. However, in collaborative data analysis, part of the datasets may come from different data owners and may be processed using different data distortion methods. Thus, combinations of datasets processed using different methods are of practical interests. In this paper, a class of novel data distortion strategies is proposed. Four schemes via attribute partition, with different combinations of singular value decomposition (SVD), nonnegative matrix factorization (NMF), discrete wavelet transformation (DWT), are designed to perturb submatrix of the original datasets for privacy protection. We use some metrics to measure the performance of the proposed new strategies. Data utility is examined by using a binary classification based on the support vector machine. Our experimental results indicate that, in comparison with the individual data distortion techniques, the proposed schemes are very efficient in achieving a good trade-off between data privacy and data utility, and provide a feasible solution for collaborative data analysis.

关键词： Discrete wavelet transforms Matrix decomposition Support vector machines Accuracy World Wide Web Conferences

来源：评论

学校读者我要写书评

暂无评论

Application of Lattice Boltzmann Method to Simulation of Compressible Turbulent Flow

引用

Communications in Computational Physics 2010年第10期8卷 1208-1223页

作者： Congshan Zhuo Chengwen Zhong Kai Li Shengwei Xiong Xiaopeng Chen Jun Cao National Key Laboratory of Science and Technology on Aerodynamic Design and Research Northwestern Polytechnical UniversityXi’anShaanxi 710072China Center for High Performance Computing Northwestern Polytechnical UniversityXi’anShaanxi 710072China School of Mechanics Civil Engineering and ArchitectureNorthwestern Polytechnical UniversityXi’anShaanxi 710072China Department of Mechanical and Industrial Engineering Ryerson UniversityTorontoOntarioM5B 2K3Canada

The main goal of this paper is to develop the coupled double-distributionfunction(DDF)lattice Boltzmann method(LBM)for simulation of subsonic and transonic turbulent *** the present study,we adopt the second-order implicit-explicit(IMEX)Runge-Kutta schemes for time discretization and the Non-Oscillatory and NonFree-Parameters Dissipative(NND)finite difference scheme for space *** Sutherland’s law is used for expressing the viscosity of the fluid due to considerable temperature ***,the Spalart-Allmaras(SA)turbulence model is incorporated in order for the turbulent flow effect to be *** experiments are performed on different turbulent compressible flows around a NACA0012 airfoil with body-fitted *** numerical results are found to be in good agreement with experiment data and/or other numerical solutions,demonstrating the applicability of the method presented in this study to simulations of both subsonic and transonic turbulent flows.

关键词： Lattice Boltzmann method compressible turbulent flow airfoil body-fitted grid

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

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Long Chen Oreste Villa Sriram Krishnamoorthy Guang R. Gao Department of Electrical & Computer Engineering University of Delaware Newark DE USA High Performance Computing Pacific Northwest National Laboratory Richland WA USA

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.

关键词： Load management Parallel processing Parallel programming Concurrent computing high performance computing Hardware Power engineering computing Processor scheduling Power engineering and energy Laboratories

来源：评论

学校读者我要写书评

暂无评论

Designing Energy Efficient Communication Runtime Systems for Data Centric Programming Models

Designing Energy Efficient Communication Runtime Systems for...

引用

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social computing (CPSCom) Green computing and Communications (GreenCom)

作者： Abhinav Vishnu Shuaiwen Song Andres Marquez Kevin Barker Darren Kerbyson Kirk Cameron Pavan Balaji High Performance Computing Group Pacific Northwest National Laboratory Richland WA USA Scalable Performance Laboratory Department of Computer Science Virginia Polytechnic Institute Blacksburg VA USA Mathematics and Computer Science Division Argonne National Laboratory Argonne IL USA

The insatiable demand of high performance computing is being driven by the most computationally intensive applications such as computational chemistry, climate modeling, nuclear physics, etc. The last couple of decades have observed a tremendous rise in supercomputers with architectures ranging from traditional clusters to system-on-a-chip in order to achieve the petaflop computing barrier. However, with advent of petaflop-plus computing, we have ushered in an era where power efficient system software stack is imperative for execution on exascale systems and beyond. At the same time, computationally intensive applications are exploring programming models beyond traditional message passing, as a combination of Partitioned Global Address Space (PGAS) languages and libraries, providing one-sided communication paradigm with put, get and accumulate primitives. To support the PGAS models, it is critical to design power efficient and high performance one-sided communication runtime systems. In this paper, we design and implement PASCoL, a high performance power aware one-sided communication library using Aggregate Remote Memory Copy Interface (ARMCI), the communication runtime system of Global Arrays. For various communication primitives provided by ARMCI, we study the impact of Dynamic Voltage/Frequency Scaling (DVFS) and a combination of interrupt (blocking)/polling based mechanisms provided by most modern interconnects. We implement our design and evaluate it with synthetic benchmarks using an Infini Band cluster. Our results indicate that PASCoL can achieve significant reduction in energy consumed per byte transfer without additional penalty for various one-sided communication primitives and various message sizes and data transfer patterns.

关键词： Servers Benchmark testing Protocols Chemistry Computational modeling performance evaluation Data models

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

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： Oreste Villa Long Chen Sriram Krishnamoorthy High Performance Computing Pacific Northwest National Laboratory Richland WA USA Department of Electrical & Computer Engineering University of Delaware Newark DE USA

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.

关键词： Computational modeling high performance computing Load management Hardware Processor scheduling Parallel processing Kernel Laboratories Power engineering computing Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Limitations of the homogenized cardiac Monodomain model for the case of low gap junctional coupling

Limitations of the homogenized cardiac Monodomain model for ...

引用

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

作者： Caroline Mendonca Costa Rodrigo Weber dos Santos FISIOCOMP Laboratory Laboratory of Computational Physiology and High-Performance Computing Department of Computer Science Federal University of Juiz de Fora Juiz de Fora Minas Gerais Brazil

The cardiac Monodomain model is a mathematical model extensively used in studies of propagation of bioelectric wavefronts in the heart. To be able to use the model for complex and large cardiac simulations, such as the case of whole heart and 3D simulations, some parameters of the model that are known to physiologically vary in space, such as the intracellular conductivity, are traditionally kept constant at effective values. These effective values can be obtained via a mathematical procedure called homogenization. In this work we revisit the classical homogenized monodomain formulation to evaluate its ability to reproduce the situation of low gap junctional coupling. This situation arises in many pathological conditions such as during ischemia. Our numerical results suggest some limitations of the homogenized cardiac Monodomain model under these conditions in terms of computed conduction velocity and Action Potential waverforms.

关键词： Mathematical model Biological system modeling Couplings Computational modeling Heart Conductivity Junctions

来源：评论

学校读者我要写书评

暂无评论

Memory access mechanism in embedded real-time Java processor

Memory access mechanism in embedded real-time Java processor

引用

International Conference on computer and Automation engineering, ICCAE

作者： Guang Hu Zhilei Chai Shiliang Tu Department of Computer Science and Engineering Department of Computer Science Shanghai International Studies University Shanghai China Center of Intelligent and High Performance Computing School of Information Technology Jiangnan University Wuxi China Department of Computer Science and Engineering Fudan University Shanghai China

ISBN: (纸本)9781424455690

Currently, Java has been gradually applied in such areas as robotics, industrial control, and other embedded real-time applications owning to its advantages like platform independence, robustness, security, etc. In order to improve the performance of Java's execution engine for embedded real-time applications, an embedded real-time Java processor JPOR-32 (32-bit Java Processor Optimized for RTSJ) is designed. In this paper, the memory access mechanism of JPOR-32 is presented. In JPOR-32, the optimized memory organization structure is designed to implement the runtime data areas of the Java virtual machine (JVM). Based on it, with the preprocessing operation, the memory access instructions optimization is implemented as well. The preprocessing operation enables the JVM's runtime operations involving dynamic loading, verification, preparation, resolution, etc. to be handled in advance. It not only provides an efficient and convenient way to implement memory access, but also makes the contribution to the WCET predictability. As to the memory management, in accordance with the Real-Time Specification for Java (RTSJ), garbage collection (GC) is not allowed in the immortal memory as well as the scoped memory, and in the heap, JPOR-32 adopts improved GC scheme suitable for embedded real-time Java environment. Besides, with the architectural support of the pipelined datapath, JPOR-32 provides effective supports for efficient and predictable memory access.

关键词： Java Memory management Design optimization Runtime Service robots Industrial control Robust control Security Engines Virtual machining

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

Single pattern search implementations in a cluster computing environment

Single pattern search implementations in a cluster computing...

引用

Inaugural IEEE-IES Digital EcoSystems and Technologies Conference, DEST

作者： J C Prasad K.S.M. Panicker Department of Computer Science and Engineering Federal Institute of Science and Technology MGR University Chennai Angamaly India Centre of High Performance Computing Federal Institute of Science and Technology Angamaly India

This paper provides an overview of different string matching algorithms in parallel environments. In this work, we have evaluated several algorithms, such as Knuth-Morris-Pratt, Boyer-Moore algorithm, Boyer Moore Horspool Algorithm, Zhu Takaoka algorithm, Quick Search Algorithm, BR Algorithm, Fast Searching algorithm, SSABS algorithm, TVSBS algorithm, ZTMBH algorithm and BRBMH algorithm. Static pattern of string matching algorithms are widely used for searching. For comparisons of speed different algorithms are implemented with parallel programming technique of MPI Standard, for a large text file with a pattern of small length. A Beowulf based homogenous cluster architecture was developed which has a performance of 81 Gigabits floating point operations per second in searching environment. The result of pattern searching showed the variation of performance with this customized cluster architecture for variable number of compute nodes with different pattern lengths. Nearly 80% of the searching code part works in parallel. The performance of string search algorithm is based on the network bandwidth and the selection of algorithms used. Depending on certain applications, different algorithm can be used. It is observed that the cluster searching architecture provides better speed with different algorithms. In general, from the experiments, BRBMH Algorithm is found to be efficient for a general string searching applications.

关键词： Clustering algorithms Signal processing algorithms Algorithm design and analysis computer architecture Complexity theory Program processors Software algorithms

来源：评论

学校读者我要写书评

暂无评论

A Smart-NIC-Based Power-Proxy Solution for Reduced Power Consumption during Instant Messaging

A Smart-NIC-Based Power-Proxy Solution for Reduced Power Con...

引用

IEEE Green Technologies Conference (IEEE-Green)

作者： Dexiang Wang Janise McNair Alan George Wireless and Mobile Systems Laboratory Department of Electrical and Computer Engineering University of Florida Gainesville USA NSF Center for High-Performance Reconfigurable Computing (CHREC) Department of Electrical and Computer Engineering University of Florida Gainesville USA

ISBN: (纸本)9781424452743

The major challenge to achieving efficient power management for local computers that serve as edge devices of the Internet is to achieve long sleeping times while at the same time maintaining network connectivity. By modifying the network interface card (NIC) with a low-weight proxy module that can handle a certain amount of network protocol semantics and hence still keep the local computer alive on the Internet, a longer host sleeping time can be achieved, while keeping many of the components, including CPU, memory, motherboard, hard drive, etc, remain in a very-low-energy mode. In this paper, we pursue a power-proxy solution to the widely-used Instant Messenger (IM) applications. Yahoo! ® Messenger is selected for a case study to investigate its communication protocol YMSG. Furthermore, the decision on inactivity time-out values is a crucial factor for energy savings, but the random nature of idle periods makes the decision another challenge. We formulate the decision problem into a stochastic program and propose an adaptive algorithm to set up appropriate inactivity time-out values. Simulations show that the proposed power-proxy solution combined with the inactivity time-out setup algorithm can efficiently reduce the power consumption of an edge computer.

关键词： Energy consumption computer networks IP networks Protocols computer network management Energy management Network interfaces computer interfaces Central Processing Unit Drives

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：