检索结果-内蒙古大学图书馆

Deadlock-free buffer configuration for stream computing

INTERNATIONAL JOURNAL OF HIGH PERFORMANCE computing APPLICATIONS 2017年第5期31卷 441-450页

作者： Li, Peng Beard, Jonathan C. Buhler, Jeremy D. Washington Univ Dept Comp Sci & Engn St Louis MO 63130 USA

Stream computing is a popular paradigm for parallel and distributed computing, where compute nodes are connected by first-in first-out data channels. Each channel can be considered as a concatenation of several data buffers, including an output buffer for the sender and an input buffer for the receiver. The configuration of buffer sizes impacts the performance as well as the correctness of the application. In this article, we focus on application deadlocks that are caused by incorrect configuration of buffer sizes. We describe three types of deadlock in streaming applications, categorized by how they can be created. To avoid them, we first prove necessary and sufficient conditions for deadlock-free computations;then based on the theorems, we propose both compile-time and runtime solutions for deadlock avoidance.

关键词： Buffer configuration deadlock avoidance feedback channels parallel and distributed computing streaming computing

来源：评论

学校读者我要写书评

暂无评论

A strong connectivity property of the generalized exchanged hypercube

引用

DISCRETE APPLIED MATHEMATICS 2017年第Part3期216卷 529-536页

作者： Cheng, Eddie Qiu, Ke Shen, Zhizhang Oakland Univ Dept Math & Stat Rochester MI 48309 USA Brock Univ Dept Comp Sci St Catharines ON L2S 3A1 Canada Plymouth State Univ Dept Comp Sci & Technol Plymouth NH 03264 USA

We show that, when a linear number of vertices are removed from a generalized exchanged hypercube, its surviving graph consists of a large connected component and smaller component(s) containing altogether a rather limited number of vertices. This result can be applied to obtain a number of fault tolerant properties of this interesting structure. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Hypercube Generalized exchanged hypercube Connectivity Fault-tolerance properties parallel and distributed computing

来源：评论

学校读者我要写书评

暂无评论

GT-WGS: an efficient and economic tool for large-scale WGS analyses based on the AWS cloud service

引用

BMC GENOMICS 2018年第Sup1期19卷 959-959页

作者： Wang, Yiqi Li, Gen Ma, Mark He, Fazhong Song, Zhuo Zhang, Wei Wu, Chengkun Natl Univ Def Technol Sch Comp Sci Changsha 410000 Hunan Peoples R China Genetalks Biotech Co Ltd Beijing 100000 Peoples R China Cent South Univ Xiangya Hosp Dept Clin Pharmacol Changsha 410000 Hunan Peoples R China

Background: Whole-genome sequencing (WGS) plays an increasingly important role in clinical practice and public health. Due to the big data size, WGS data analysis is usually compute-intensive and IO-intensive. Currently it usually takes 30 to 40 h to finish a 50x WGS analysis task, which is far from the ideal speed required by the industry. Furthermore, the high-end infrastructure required by WGS computing is costly in terms of time and money. In this paper, we aim to improve the time efficiency of WGS analysis and minimize the cost by elastic cloud computing. Results: We developed a distributed system, GT-WGS, for large-scale WGS analyses utilizing the Amazon Web Services (AWS). Our system won the first prize on the Wind and Cloud challenge held by Genomics and Cloud Technology Alliance conference (GCTA) committee. The system makes full use of the dynamic pricing mechanism of AWS. We evaluate the performance of GT-WGS with a 55x WGS dataset (400GB fastq) provided by the GCTA 2017 competition. In the best case, it only took 18.4 min to finish the analysis and the AWS cost of the whole process is only 16.5 US dollars. The accuracy of GT-WGS is 99.9% consistent with that of the Genome Analysis Toolkit (GATK) best practice. We also evaluated the performance of GT-WGS performance on a real-world dataset provided by the XiangYa hospital, which consists of 5x whole-genome dataset with 500 samples, and on average GT-WGS managed to finish one 5x WGS analysis task in 2.4 min at a cost of $3.6. Conclusions: WGS is already playing an important role in guiding therapeutic intervention. However, its application is limited by the time cost and computing cost. GT-WGS excelled as an efficient and affordable WGS analyses tool to address this problem. The demo video and supplementary materials of GT-WGS can be accessed at https://***/Genetalks/wgs_analysis_demo.

关键词： Whole-genome sequencing AWS parallel and distributed computing

来源：评论

学校读者我要写书评

暂无评论

Exploration of de Bruijn graph filtering for de novo assembly using GraphLab 31

Exploration of de Bruijn graph filtering for <i>de novo</i> ...

引用

31st IEEE International parallel and distributed Processing Symposium Workshops (IPDPS)

作者： Collet, Julien Sassolas, Tanguy Lhuillier, Yves Sirdey, Renaud Carlier, Jacques CEA LIST F-91191 Gif Sur Yvette France Univ Technol Compiegne Heudiasyc F-60203 Compiegne France

ISBN: (纸本)9780769561493

The emergence of next generation DNA sequencers has raised interest in short read de novo assembly of whole genomes. Though numerous frameworks were developed in the field, the presence of errors in reads as well as the increasing size of datasets call for scalable preprocessing methods for noise filtering. In this paper we present a filtering algorithm that targets determination of valid k-mers in a de Bruijn graph built from short reads. Such preprocessing will help increase accuracy and reduce memory footprint in further assembly procedures by removing erroneous k-mers from the datasets at an early stage. The algorithm leverages GraphLab, a scalable graph processing framework not previously used in traditional assembly toolchains. The accuracy of the algorithm was evaluated with synthetic datasets exhibiting various error rates and proven to be able to determine large parts of de Bruijn graphs on datasets with error level greater than real-life datasets. The implementation is executed on a distributed cluster and a study of its scalability and operating performances is conducted and exhibits interesting scaling properties, hence demonstrating the relevance of GraphLab in such a context.

关键词： De novo assembly De Bruijn Graphs Libraries and Programming Environments parallel and distributed computing Big Data and Data Analytics GraphLab

来源：评论

学校读者我要写书评

暂无评论

Early Classification of Multivariate Time Series on distributed and In-Memory Platforms 1

引用

21st Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)

作者： Tseng, Vincent S. Huang, Huai-Shuo Huang, Chia-Wei Wang, Ping-Feng Li, Chu-Feng Natl Chiao Tung Univ Hsinchu Taiwan Inst Informat Ind Taipei Taiwan

ISBN: (数字)9783319672748

ISBN: (纸本)9783319672748;9783319672731

With the popularity of Internet of Things (IOT) applications, various kinds of active sensors are deployed and multivariate time series datasets are generated rapidly. Early classification of multivariate time series is an emerging topic in data mining due to the wide applications in many domains. The unique part of early classification lies in that it uses only earlier part of time series data to reach classification results with the same accuracy as by methods using complete time series information. Although a number of relevant studies have been presented recently, most of them didn't consider the issues of data scale and execution efficiency simultaneously. The main research issue of this paper falls in how to mine interpretable patterns from multivariate time series data, with which effective classification models can be constructed to ensure the accuracy as well as earliness. To take into account the issues of data scale and execution efficiency simultaneously, we explore distributed in-memory computing techniques and multivariate shapelets-based approaches to construct a Spark-based inmemory mining framework to parallelize the feature extraction process. We implement a framework with Multivariate Shapelets Detection (MSD) method as a based example. Through empirical evaluation on various kinds of sensory datasets, the scalability of the framework is evaluated in terms of efficiency while ensuring the same accuracy and reliability in early classification of multivariate time series. This work is the first one to realize multivariate time series early classification on Spark distributed in-memory computing platform, which can serve as a good base for an extension to other time series classification methods based on shapelet feature extraction.

关键词： Early classification Multivariate time series parallel and distributed computing Shapelets

来源：评论

学校读者我要写书评

暂无评论

Understanding Customers' Behaviour of Telecommunication Companies Increasing the Efficiency of Clustering Techniques 25

Understanding Customers' Behaviour of Telecommunication Comp...

引用

25th Telecommunication Forum (TELFOR)

作者： Savvas, I. K. Chaikalis, C. Messina, F. Tselios, D. TEI Thessaly Dept Comp Sci & Engn Larisa Greece Univ Catania Dept Math & Informat Catania Italy TEI Thessaly Dept Business Adm Larisa Greece

ISBN: (纸本)9781538630730

The customers' data of Telecommunication Companies represent a powerful tool to explore their behaviour and then to increase their satisfaction. The data produced is too large to extract on time useful information, which could be beneficial for both sides, companies and customers. One of the solutions to explore this data is representing it by the adoption of clustering techniques. In this work, two distributed / multi-core versions of clustering algorithms were used, namely DBSCAN and k-means, which both of them cluster data according to its characteristics. While DBSCAN is a density-based spatial clustering algorithm and groups data based on the minimum size of participating objects per cluster and the minimum required distance between them, k-means clusters the data objects according the pre-desired number of groups. Thus, since the two methods use different roads to group the data objects, they form different clusters but each one has its importance depending on the characteristics of the applied method. The experiment results of both proposed distributed / multi-core techniques proved their efficiency.

关键词： DBSCAN k-means parallel and distributed computing OpenMP MPI

来源：评论

学校读者我要写书评

暂无评论

OUTRIDER: Optimizing the mutation Testing pRocess In distributed EnviRonments

OUTRIDER: Optimizing the mutation Testing pRocess In Distrib...

引用

International Conference on Computational Science (ICCS)

作者： Canizares, Pablo C. Nunez, Alberto de Tiara, Juan Univ Complutense Madrid Madrid Spain Univ Autonoma Madrid Madrid Spain

The adoption of commodity clusters has been widely extended due to its cost-effectiveness and the evolution of networks. These systems can be used to reduce the long execution time of applications that require a vast amount of computational resources, and especially of those techniques that are usually deployed in centralized environments, like testing. Currently, one of the main challenges in testing is to obtain an appropriate test suite. Mutation testing is a widely used technique aimed at generating high quality test suites. However, the execution of this technique requires a high computational cost. In this work we propose OUTRIDER, an HPC-based optimization that contributes to bridging the gap between the high computational cost of mutation testing and the parallel infrastructures of HPC systems aimed to speed-up the execution of computational applications. This optimization is based on our previous work called EMINENT, an algorithm focused on parallelizing the mutation testing process using MPI. However, since EMINENT does not efficiently exploit the computational resources in HPC systems, we propose 4 strategies to alleviate this issue. A thorough experimental study using different applications shows an increase of up to 70% performance improvement using these optimizations. (C) 2017 The Authors. Published by Elsevier B. V.

关键词： parallel and distributed computing High Performance computing Mutation testing

来源：评论

学校读者我要写书评

暂无评论

Dependable parallel Multi-population Different Evolutionary Particle Swarm Optimization for Voltage and Reactive Power Control in Electric Power Systems 10

Dependable Parallel Multi-population Different Evolutionary ...

引用

10th IEEE International Workshop on Computational Intelligence and Applications (IWCIA)

作者： Yoshida, Hotaka Fukuyama, Yoshikazu Meiji Univ Sch Interdisciplinary Math Sci Tokyo Japan

ISBN: (纸本)9781538604694

This paper presents dependable parallel multipopulation differential evolutionary particle swam optimization (DEEPSO) for voltage and reactive power control (VRPC) in electric power systems. Considering large penetration of renewable energies and deregulated environment of power systems, VRPC requires fast computation even for larger-scale problems. One solutions to increase the computation speed is to use parallel and distributed computing. Since power system is one of the infrastructures of social community, not only fast computation, but also sustainable control (dependability) is strongly required for VRPC. A multi-population model is known to be one of the techniques to improve solution quality. The simulation results with IEEE 118 bus systems indicate that dependable parallel multi-population DEEPSO is superior to parallel DEEPSO using a master-slave model especially for dependability on VRPC.

关键词： Voltage and reactive power control parallel and distributed computing Multi-population Dependability Different Evolutionary Particle Swarm Optimization

来源：评论

学校读者我要写书评

暂无评论

MRA*: parallel and distributed Path in Large-Scale Graph Using MapReduce-A* Based Approach 3rd

MRA*: Parallel and Distributed Path in Large-Scale Graph Usi...

引用

3rd International Symposium on Ubiquitous Networking (UNet)

作者： Hamilton Adoni, Wilfried Yves Nahhal, Tarik Aghezzaf, Brahim Elbyed, Abdeltif Hassan II Univ Fac Sci Casablanca LIMSAD Km 8 Route EI JadidaBP 5366 Casablanca 20100 Morocco

ISBN: (纸本)9783319681795;9783319681788

In this paper, we present a contribution for the Single Source Shortest Path Problem (SSSPP) in large-scale graph with A* algorithm. A* is one of the most efficient graph traversal algorithm because it is driven by a heuristic which determines the optimal path. A* approach is not efficient when the graph is too large to be processed due to exponential time complexity. We propose a MapReduce-based approach called MRA*: MapReduce-A* which consists to combine the A* algorithm with MapReduce paradigm to compute the shortest path in parallel and distributed environment. We perform experiments in a Hadoop multi-node cluster and our results prove that the proposed approach outperforms A* algorithm and reduces significantly the computational time.

关键词： A* algorithm Large-scale graph Shortest path problem Hadoop MapReduce parallel and distributed computing

来源：评论

学校读者我要写书评

暂无评论

parallel and distributed Statistical-based Extraction of Relevant Multiwords from Large Corpora

Parallel and Distributed Statistical-based Extraction of Rel...

引用

作者： Carlos Jorge de Sousa Goncalves NOVA University of Lisbon

学位级别：博士

The amount of information available through the Internet has been showing a significant growth in the last decade. The information can result from various sources such as scientific experiments resulting from particle acceleration, recording the ﬂight data of a commercial aircraft, or sets of documents from a given domain such as medical articles, news headlines from a newspaper, or social networks contents. Due to the volume of data that must be analyzed, it is necessary to endow the search engines with new tools that allow the user to obtain the desired information in a timely and accurate manner. One approach is the annotation of documents with their relevant expressions. The extraction of relevant expressions from natural language text documents can be accomplished by the use of semantic, syntactic, or statistical techniques. Although the latter tend to be not so accurate, they have the advantage of being independent of the language. This investigation was performed in the context of LocalMaxs, which is a statistical method, thus language-independent, capable of extracting relevant expressions from natural language corpora. However, due to the large volume of data involved, the sequential implementations of the above techniques have severe limitations both in terms of execution time and memory space. In this thesis we propose a distributed architecture and strategies for parallel implementations of statistical-based extraction of relevant expressions from large corpora. A methodology was developed for modeling and evaluating those strategies based on empirical and theoretical approaches to estimate the statistical distribution of n-grams in natural language corpora. These approaches were applied to guide the design and evalu- ation of the behavior of LocalMaxs parallel and distributed implementations on cluster and cloud computing platforms. The implementation alternatives were compared regar- ding their precision and recall, and their performance metrics, namel

关键词： parallel and distributed computing Extraction of Relevant Expressions Sta-tistical n-gram Methods Caching Strategies

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：