检索结果-内蒙古大学图书馆

9th International Conference on Advanced computing and Communication Technologies (ICACCT)

作者： Sheokand, Vishal Singh, Vikram Natl Inst Technol Dept Comp Engn Kurukshetra 136119 Haryana India

ISBN: (纸本)9789811010231;9789811010217

With the wide use of information expertise in advanced analytics, basically three characteristics of big data have been identified. These are volume, velocity and variety. The first of these two have enjoyed quite a lot of focus, volume of data and velocity of data, less thought has been focused on variety of available data worldwide. data variety refers to the nature of data in store and under processing, which has three orthogonal natures: structured, semi-structured and unstructured. To handle the variety of data, current universally acceptable solutions are either costlier than customized solutions or less efficient to cater data heterogeneity. Thus, a basic idea is to, first design data processing systems that create abstraction that covers a wide range of data types and support fundamental processing on underlying heterogeneous data. In this paper, we conceptualized data management architecture 'Big dataSpace', for big data processing with the capability to combine heterogeneous data from various data sources. Further, we explain how Big dataSpace architecture can help in processing the heterogeneous and distributed data, a fundamental task in data management.

关键词： Big data Mining dataspace System data intensive computing data Variety data Volume data Integration System

来源：评论

学校读者我要写书评

暂无评论

Design Issues of Big data Parallelisms 3rd

Design Issues of Big Data Parallelisms

引用

3rd International Conference on Information System Design and Intelligent Applications (INDIA)

作者： Mondal, Koushik Indian Inst Technol Indore Madhya Pradesh India

ISBN: (纸本)9788132227526;9788132227502

data intensive computing for Scientific Research needs effective tools for data capture, curate them for designing appropriate algorithms and multidimensional analysis for effective decision making for the society. Different computational environments used for different data intensive problems such as Sentiment Analysis and Opinion Mining of Social media, Massive Open Online Courses (MOOCs), Large Hadron Collider of CERN, Square Kilometer Array (SKA) of radio telescopes project, are usually capable of generating exabytes (EB) of data per day, but present situations limits them to more manageable data collection rates. Different disciplines and data generation rates of different lab experiments, online as well as offline, make the issue of creating effective tools a formidable problem. In this paper we will discuss about different data intensive computing tools, trends of different emerging technologies, how big data processing heavily relying on those effective tools and how it helps in creating different models and decision making.

关键词： data intensive computing High dimensional data Scalable framework data science Machine learning Semi-stochastic X-informatics Big data

来源：评论

学校读者我要写书评

暂无评论

All-Pairs: An Abstraction for data-intensive computing on Campus Grids

引用

IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS 2010年第1期21卷 33-46页

作者： Moretti, Christopher Bui, Hoang Hollingsworth, Karen Rich, Brandon Flynn, Patrick Thain, Douglas Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN 46556 USA

Today, campus grids provide users with easy access to thousands of CPUs. However, it is not always easy for nonexpert users to harness these systems effectively. A large workload composed in what seems to be the obvious way by a naive user may accidentally abuse shared resources and achieve very poor performance. To address this problem, we argue that campus grids should provide end users with high-level abstractions that allow for the easy expression and efficient execution of data-intensive workloads. We present one example of an abstraction-All-Pairs-that fits the needs of several applications in biometrics, bioinformatics, and data mining. We demonstrate that an optimized All-Pairs abstraction is both easier to use than the underlying system, achieve performance orders of magnitude better than the obvious but naive approach, and is both faster and more efficient than a tuned conventional approach. This abstraction has been in production use for one year on a 500 CPU campus grid at the University of Notre Dame and has been used to carry out a groundbreaking analysis of biometric data.

关键词： All-pairs biometrics cloud computing data intensive computing grid computing

来源：评论

学校读者我要写书评

暂无评论

ParSA: High-throughput scientific data analysis framework with distributed file system

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2015年 51卷 111-119页

作者： Zhang, Tao Sun, XiangZheng Xue, Wei Qiao, Nan Huang, Huang Shu, JiWu Zheng, Weimin Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China Intel Corp Beijing Peoples R China

Scientific data analysis and visualization have become the key component for nowadays large scale simulations. Due to the rapidly increasing data volume and awkward I/O pattern among high structured files, known serial methods/tools cannot scale well and usually lead to poor performance over traditional architectures. In this paper, we propose a new framework: ParSA (parallel scientific data analysis) for high-throughput and scalable scientific analysis, with distributed file system. ParSA presents the optimization strategies for grouping and splitting logical units to utilize distributed I/O property of distributed file system, scheduling the distribution of block replicas to reduce network reading, as well as to maximize overlapping the data reading, processing, and transferring during computation. Besides, ParSA provides the similar interfaces as the NetCDF Operator (NCO), which is used in most of climate data diagnostic packages, making it easy to use this framework. We utilize ParSA to accelerate well-known analysis methods for climate models on Hadoop Distributed File System (HDFS). Experimental results demonstrate the high efficiency and scalability of ParSA, getting the maximum 1.3 GB/s throughput on a six nodes Hadoop cluster with five disks per node. Yet, it can only get 392 MB/s throughput on a RAID-6 storage node. (C) 2014 Elsevier B.V. All rights reserved.

关键词： data intensive computing Scientific data analysis Distributed file system

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Collective I/O Scheduling for High-Performance computing

引用

BIG data RESEARCH 2015年第3期2卷 117-126页

作者： Liu, Jialin Zhuang, Yu Chen, Yong Texas Tech Univ Dept Comp Sci Lubbock TX 79409 USA

The non-contiguous access pattern of many scientific applications results in a large number of I/O requests, which can seriously limit the data-access performance. Collective I/O has been widely used to address this issue. However, the performance of collective I/O could be dramatically degraded in today's high-performance computing systems due to the increasing shuffle cost caused by highly concurrent data accesses. This situation tends to be even worse as many applications become more and more data intensive. Previous research has primarily focused on optimizing I/O access cost in collective I/O but largely ignored the shuffle cost involved. Previous works assume that the lowest average response time leads to the best QoS and performance, while that is not always true for collective requests when considering the additional shuffle cost. In this study, we propose a new hierarchical I/O scheduling (HIO) algorithm to address the increasing shuffle cost in collective I/O. The fundamental idea is to schedule applications' I/O requests based on a shuffle cost analysis to achieve the optimal overall performance, instead of achieving optimal I/O accesses only. The algorithm is currently evaluated with the MPICH3 and PVFS2. Both theoretical analysis and experimental tests show that the proposed hierarchical I/O scheduling has a potential in addressing the degraded performance issue of collective I/O with highly concurrent accesses. (C) 2015 Elsevier Inc. All rights reserved.

关键词： Collective I/O Scheduling High-performance computing Big data data intensive computing

来源：评论

学校读者我要写书评

暂无评论

A general accelerated R package using GPU

A general accelerated R package using GPU

引用

2015 IEEE International Conference on Smart City/SocialCom/SustainCom (SmartCity)

作者： Huang, Jie Zhuang, Bojin Su, Fei Beijing Univ Posts & Telecommun Sch Informat & Commun Engn Beijing Peoples R China

ISBN: (纸本)9781509018932

In this paper, we present cuLib, a R package that provides an easy-to-access interface for utilizing the computing power of NVIDIA GPU. The cuLib package aims to make GPU-based parallel programming easier, flexible and high-performance. It allows the use of GPU computing in R without further knowledge because the syntax for definition and manipulation of GPU data is similar to formal R language. cuLib is compatible with device and operation system. The data interface is very flexible, enabling the users manipulate data freely. The cuLib package provides an R wrapper for libraries of NVIDIA's CUDA toolkit and numerous operations. More importantly, it is not only a mathematical tool but also practicable for the algorithm in dealing with data intensive computation.

关键词： R GPU CUDA mathematical tool data intensive computing

来源：评论

学校读者我要写书评

暂无评论

Anatomy of Functional Components of Healthcare Information System 8

Anatomy of Functional Components of Healthcare Information S...

引用

2015 Eighth International Conference on Internet computing for Science and Engineering (ICICSE)

作者： Ni, Jun Chen, Ying Sha, Jie Zhang, Minghuan Shanghai Sanda Univ Sch Informat Sci & Technol Big Data & Informat Res Lab Shanghai 201209 Peoples R China

ISBN: (纸本)9781509004546

The healthcare information system (HIS) becomes very important in today medical and healthcare services. Huge healthcare data with various types and structures are generated in a daily base. The processing and mining of the data is in urgent demand. How to design a HIS system that cooperates with cloud computing and big data technology to meet such emergence become critical, technical challenging to today's healthcare services. In this paper we present our preliminary study of computing architecture for such HIS. The architecture design is based on HIS's sub-systems (functional modules) each of which matches with corresponding healthcare service. The architecture is designed based on the features of desired data intensive computing systems with considerations of data volume and growth rate, heterogeneous data structures, and methods of data storages.

关键词： healthcare information systems HIS big data cloud computing healthcare services system architecture system of systems SoSE data intensive computing high performance computing HPC parallel computing

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of task scheduling strategies for massive remote sensing data processing across multiple data centers

引用

SOFTWARE-PRACTICE & EXPERIENCE 2014年第7期44卷 873-886页

作者： Zhang, Wanfeng Wang, Lizhe Ma, Yan Liu, Dingsheng Chinese Acad Sci Inst Remote Sensing & Digital Earth Beijing 100864 Peoples R China China Univ Geosci Sch Comp Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

data intensive applications of remote sensing data processing are more and more widespread resulting from the evolutions in computer and network technologies. Especially, bags-of-tasks (BoTs) applications with a mass of sharing input files and directed acyclic graph (DAG) applications with data dependencies in a widely distributed computing environment bring new challenges. In this article, a strategy of partitioning group based on hypergraph (PGH) is introduced to formulate the model of sharing files. Within the PGH algorithm, BoTs applications would be partitioned into several groups to minimize the time of data transferring. We also adopted another scheduling policy, which is called optimized task tree (OTT) strategy to handle the DAG workflow of massive remote sensing data processing with data dependencies. A scheduling queue of DAG tasks would be updated according to the priorities changing. With the help of GridSim simulation environment, we designed the Gridlets within scheduler to test the performance of PGH and OTT. Copyright (c) 2013 John Wiley & Sons, Ltd.

关键词： multi-datacenter infrastructure data intensive computing task scheduling big data computing

来源：评论

学校读者我要写书评

暂无评论

PARALLEL PROCESSING OF MASSIVE REMOTE SENSING IMAGES IN A GPU ARCHITECTURE

引用

computing AND INFORMATICS 2014年第1期33卷 197-217页

作者： Liu, Peng Yuan, Tao Ma, Yan Wang, Lizhe Liu, Dingsheng Yue, Shasha Kolodziej, Joanna Chinese Acad Sci Inst Remote Sensing & Digital Earth Beijing 100094 Peoples R China Cracow Univ Technol Inst Comp Sci PL-31155 Krakow Poland

Profiting from the development of space remote sensing technology, the amount of remote sensing image data obtained by satellite is increasing dramatically;however, how to deal with these data quickly and efficiently has turned out to be a great computational challenge. With the rapid development of general-purpose CPU computing technology, researchers improved remote sensing applications based on GPU, and obtained good speedup. However, the current CPU parallel processes are not well adapted to the remote sensing image processing;furthermore, they have data loading, storage, and I/O problems. To solve these bottlenecks, this paper proposes three corresponding optimization strategies, and their effectiveness is confirmed by further experiments.

关键词： GPU remote sensing image processing data intensive computing

来源：评论

学校读者我要写书评

暂无评论

Towards unified secure on- and off-line analytics at scale

引用

PARALLEL computing 2014年第10期40卷 738-753页

作者： Coetzee, P. Leeke, M. Jarvis, S. Univ Warwick Dept Comp Sci Coventry CV4 7AL W Midlands England

data scientists have applied various analytic models and techniques to address the oft-cited problems of large volume, high velocity data rates and diversity in semantics. Such approaches have traditionally employed analytic techniques in a streaming or batch processing paradigm. This paper presents CRUCIBLE, a first-in-class framework for the analysis of large-scale datasets that exploits both streaming and batch paradigms in a unified manner. The CRUCIBLE framework includes a domain specific language for describing analyses as a set of communicating sequential processes, a common runtime model for analytic execution in multiple streamed and batch environments, and an approach to automating the management of cell-level security labelling that is applied uniformly across runtimes. This paper shows the applicability of CRUCIBLE to a variety of state-of-the-art analytic environments, and compares a range of runtime models for their scalability and performance against a series of native implementations. The work demonstrates the significant impact of runtime model selection, including improvements of between 2.3 x and 480x between runtime models, with an average performance gap of just 14x between CRUCIBLE and a suite of equivalent native implementations. (C) 2014 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://***/licenses/by/3.0/).

关键词： data science Analytics Streaming analysis Hadoop Domain specific languages data intensive computing

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：