检索结果-内蒙古大学图书馆

A Highly Parallel Reuse Distance Analysis algorithm on GPUs

A Highly Parallel Reuse Distance Analysis Algorithm on GPUs

26th IEEE International Parallel and Distributed Processing Symposium (IPDPS) / Workshop on High Performance Data Intensive Computing

作者： Cui, Huimin Yi, Qing Xue, Jingling Wang, Lei Yang, Yang Feng, Xiaobing Chinese Acad Sci SKL Comp Architecture Inst Comp Technol Beijing Peoples R China Univ Texas CAS Dept Comp Sci San Antonio TX USA Univ New South Wales Sch Comp Sci & Engn Sydney NSW Australia

ISBN: (纸本)9780769546759

Reuse distance analysis is a runtime approach that has been widely used to accurately model the memory system behavior of applications. However, traditional reuse distance analysis algorithms use tree-based data structures and are hard to parallelize, missing the tremendous computing power of modern architectures such as the emerging GPUs. This paper presents a highly-parallel reuse distance analysis algorithm (HP-RDA) to speedup the process using the SPMD execution model of GPUs. In particular, we propose a hybrid data structure of hash table and local arrays to flatten the traditional tree representation of memory access traces. Further, we use a probabilistic model to correct any loss of precision from a straightforward parallelization of the original sequential algorithm. Our experimental results show that using an NVIDIA GPU, our algorithm achieves a factor of 20 speedup over the traditional sequential algorithm with less than 1% loss in precision.

关键词： Reuse reuse modern architectures Data structures sequential algorithm Hash table Precision Probabilistic Model Runtime Speeding algorithms

来源：评论

学校读者我要写书评

暂无评论

An energy-efficient control algorithms for switching fabrics 16

An energy-efficient control algorithms for switching fabrics

引用

16th International Telecommunications Network Strategy and Planning Symposium (Networks)

作者： Zal, Mariusz Wojtysiak, Przemyslaw Poznan Univ Tech Chair Commun & Comp Networks PL-64980 Poznan Poland

ISBN: (纸本)9781479965151

In this paper we present the way of saving electrical energy in high-tech telecommunication and computer networks. To achieve this aim, the work focuses on the description of the current state and the future trends of changes, as well as it analyses the possibility of energy-saving solutions based on the Clos switching network architectures used in switching networks. A simulation program has been implemented to estimate multi-stage switching system energy consumption. This program enabled to check the operating quality (how much energy was saved by the structure during packet forwarding or rejecting), routing algorithms (sequential algorithm, quasi-random algorithm and Benes algorithm) and their modifications that optimize the achieved results.

关键词： energy conservation energy consumption environmental factors multistage interconnection networks telecommunication network routing Benes? algorithm Clos switching network architecture computer network electrical energy energy-efficient control algorithm energy-saving solution high-tech telecommunication network multistage switching system quasirandom algorithm routing algorithm sequential algorithm switching fabrics Energy consumption Power demand Switches Telecommunications Turning energy consumption computer network sequential algorithm electrical energy multistage interconnection networks Routing algorithms Telecommunications Power demand telecommunication network routing Switches Turning Energy conservation Computer algorithms Textile fabrics fabric

来源：评论

学校读者我要写书评

暂无评论

A Simulation-Free Exact Conditional Goodness-of-Fit Test for The Binomial Distribution

引用

Calcutta Statistical Association Bulletin 2015年第3-4期67卷 105-128页

作者： Hazra, Arnab Indian Statistical Institute Kolkata India Department of Statistics North Carolina State University United States

Several exact testing methods for continuous distributions, asymptotic as well as simulation based exact methods for both- discrete and continuous cases have been developed for analyzing goodness-of-fit, a priori. An exact Kolmogorov-Smirnov type goodness-of-fit test is developed for checking whether the data comes from a binomial distribution or not. This is a conditional test;p-value is calculated as the conditional probability given the sample total and hence the success probability need not be specified under the null hypothesis. Instead of using simulation, p-value is calculated using a sequential procedure and hence the inference procedure is simulationfree. Properties of the test, some examples, power comparisons with other existing techniques are also provided. © 2015 SAGE Publications.

关键词： conditional test Goodness-of-fit hypergeometric distribution Kolmogorov-Smirnov test sequential algorithm

来源：评论

学校读者我要写书评

暂无评论

High Performance Online Key Performance Indicator's Calculations in Oil Refineries 23

High Performance Online Key Performance Indicator's Calculat...

引用

23nd Signal Processing and Communications Applications Conference (SIU)

作者： Bakir, Mustafa Sevilgen, Fatih Erdogan TUPRAS Genel Mudurluk Surec Gelistirme & Yazilim Mudurlugu Batman Merkez Batman Turkey Gebze Tekn Univ Bilgisayar Muhendisligi Gebze Turkey

ISBN: (纸本)9781467373869

It is critical in Oil Refineries to monitor the process online by several departments with respect to various perspectives. Key performance indicators generated by conversion of sensor - based measurements into meaningful data fulfill this requirement. However, the performance indicators must be provided to the users online. In this article, we discuss code optimization and parallelization of key performance indicator's calculation. By using these methods we obtained %696 improvement against the initial algorithm and %55 improvement against the optimal sequential algorithm in the performance of the system.

关键词： petroleum refinery performance indicators code optimization sequential algorithm parallelization Departments

来源：评论

学校读者我要写书评

暂无评论

sequential LOCAL FRI SAMPLING OF INFINITE STREAMS OF DIRACS

SEQUENTIAL LOCAL FRI SAMPLING OF INFINITE STREAMS OF DIRACS

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Jon Onativia Jose Antonio Uriguen Pier Luigi Dragotti Department of Electrical and Electronic Engineering Imperial College London

ISBN: (纸本)9781479903573

The theory of sampling signals with finite rate of innovation (FRI) has shown that it is possible to perfectly recover classes of non-bandlimited signals such as streams of Diracs from uniform samples. Most of previous papers, however, have to some extent only focused on the sampling of periodic or finite duration signals. In this paper we propose a novel method that is able to reconstruct infinite streams of Diracs, even in high noise scenarios. We sequentially process the discrete samples and output locations and amplitudes of the Diracs in real-time. We first establish conditions for perfect reconstruction in the noiseless case and then present the sequential algorithm for the noisy scenario. We also show that we can achieve a high reconstruction accuracy of 1000 Diracs for SNRs as low as 5dB.

关键词： Analog-to-digital conversion Finite rate of innovation Sampling theory Annihilating filter Analog-digital conversion streams Sampling sequential algorithm perfect reconstruction Paul Adrien Maurice Dirac rivers signals Noise

来源：评论

学校读者我要写书评

暂无评论

Parallel algorithms for Gröbner-basis construction

引用

Journal of Mathematical Sciences 2007年第4期142卷 2248-2266页

作者： Mityunin, V.A. Pankratiev, E.V. Moscow State University Russian Federation

The problem of the Gröbner-basis construction is important both from the theoretical and applied points of view. As examples of applications of Gröbner bases, one can mention the consistency problem for systems of nonlinear algebraic equations and the determination of the number of solutions to a system of nonlinear algebraic equations. The Gröbner bases are actively used in the constructive theory of polynomial ideals and at the preliminary stage of numerical solution of systems of nonlinear algebraic equations. Unfortunately, many real examples cannot be processed due to the high computational complexity of known algorithms for computing the Gröbner bases. However, the efficiency of the standard basis construction can be significantly increased in practice. In this paper, we analyze the known algorithms for constructing the standard bases and consider some methods for increasing their efficiency. We describe a technique for estimating the efficiency of paralleling the algorithms and present some estimates. © Springer Science+Business Media, Inc. 2007.

关键词： Computer Algebra System Polynomial Ideal Polynomial System sequential algorithm Nonlinear Algebraic Equation

来源：评论

学校读者我要写书评

暂无评论

Restructuring and Implementations of 2D Matrix Transpose algorithm Using SSE4 Vector Instructions 1

Restructuring and Implementations of 2D Matrix Transpose Alg...

引用

International Conference on Applied Research in Computer Science and Engineering (ICAR)

作者： Zekri, Ahmed S. Beirut Arab Univ Fac Sci Dept Math & Comp Sci Beirut Lebanon

ISBN: (纸本)9781467385435

Current general-purpose processors are augmented with vector instructions that can process many elements of matrices and vectors in parallel. Transposing a matrix in-place is a main kernel operation required by many scientific and engineering applications to shuttle data before, during, or after processing. This operation increases the traffic on the memory bus and hence clever techniques such as blocking are required to enhance the performance. In this paper, we present an enhanced version of a previously published algorithm for transposing a matrix on a two-dimensional processor arrays. We restructured this algorithm to fit the one-dimensional vector register architecture augmented to general-purpose CPUs. We implemented the new vector algorithm using Intel SSE4 vector instruction set and compare its performance with the standard sequential algorithm in addition to an already employed implementation of Ekhlundh's algorithm. We also studied the automatic compiler optimizations and their effect on the vectorization of the algorithm. The best of our implementations showed a maximum speedup of 1.6 compared with the sequential algorithm, and an almost equal performance compared with Eklundh's algorithm implementation.

关键词： instruction sets mathematics computing matrix algebra optimising compilers parallel processing 2D matrix transpose algorithm Ekhlundh algorithm Intel SSE4 vector instruction set automatic compiler optimization general-purpose CPU general-purpose processor memory bus one-dimensional vector register architecture standard sequential algorithm two-dimensional processor arrays Kernel Multicore processing Parallel processing Program processors Registers Signal processing algorithms Yttrium PARALLEL PROCESSING (COMPUTERS) instruction sets mathematics computing Program processors Signal processing algorithms Registers matrix algebra Rare earths yttrium sequential algorithm Kernel general processor

来源：评论

学校读者我要写书评

暂无评论

Policy-based access control framework for large networks

Policy-based access control framework for large networks

引用

8th IEEE International Conference on Networks (ICON 2000)

作者： Duan, HX Wu, JP Li, X Tsing Hua Univ Network Res Ctr Beijing Peoples R China

ISBN: (纸本)0769507778

Efforts of this paper focus on the issues about management and throughput of firewalls (or screening routers) applied in transit networks. On the one hand, manual configuration of large amount of firewalls distributed in many access points can not meet the global security requirements in the open and dynamic environment. On the other hand, the ordinal lookup of filtering rules in each individual firewall results in great decrease of throughput. Aimed at a typical transit network and its security policy requirements, a policy-based access control framework (PACF) is proposed in this paper. This framework is based on three levels of abstract access control policy: organizational access control policy (OACP), global access control policy (GACP) and local access control policy (LACP). The GACP, which comes from the results of IDSes and search engines according to OACP, is automatically and dynamically distributed to firewalls as LACPs. Each LACP is then enforced by an individual firewall. Some key algorithms for distribution of GACP and enforcement of LACP are described. A hash-based algorithm is proposed, for lookup of filtering rules in LACP. Under the environment with policy requirements described in this paper the new algorithm reduces the time complexity of lookup from O (N) of traditional sequential algorithm to O (1), which therefore increases largely the throughput of firewalls.

关键词： access control telecommunication network management telecommunication network routing authorisation cryptography table lookup computational complexity search engines telecommunication security policy based access control large networks firewalls management firewalls throughput screening routers transit networks global security requirements open environment dynamic environment ordinal lookup filtering rules security policy requirements policy-based access control framework organizational access control policy global access control policy local access control policy IDSes search engines key algorithms hash-based algorithm time complexity reduction sequential algorithm

来源：评论

学校读者我要写书评

暂无评论

sequential Localization with Inaccurate Measurements

Sequential Localization with Inaccurate Measurements

引用

2009 American Control Conference (ACC 2009)

作者： J. Fang D. Duncan A. S. Morse Department of Electrical Engineering at Yale University

ISBN: (纸本)9781424445233

The sensor network localization problem with distance information is to determine the positions of all sensors in a network given the positions of some sensors and the distances between some pairs of sensors. We present a sequential algorithm for estimating sensor positions when only inaccurate distance measurements are available, and evaluate the performance of the algorithm on simulations of randomly deployed networks of 100 sensors.

关键词： Sensors Inaccurate sequential algorithm position sensor sequential

来源：评论

学校读者我要写书评

暂无评论

Mit :: Ai :: Aim :: Aitr-995

引用

2016年

Mit :: Ai :: Aim :: Aitr-995 by published by

关键词： aitr-995 algorithm chapter computation connection machine cube expansion expansions local expansion multipole multipole expansion node numerical verifications parallel parallel algorithm pythagorean configuration running time sequential algorithm sequential implementation three bodies tree

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：