检索结果-内蒙古大学图书馆

15th International Parallel and Distributed Processing Symposium, IPDPS 2001

作者： No, Jaechun Thakur, R. Kaushik, D. Freitag, L. Choudhary, A. Math. and Computer Science Division Argonne National Laboratory ArgonneIL60439 United States Dept. of Elec. and Computer Eng. Northwestern University EvanstonIL60208 United States

ISBN: (纸本)0769509908

Many scientific applications are I/O intensive and generate large data sets, spanning hundreds or thousands of "files." Management, storage, efficient access, and analysis of this data present an extremely challenging task. We have developed a software system, called Scientific Data Manager (SDM), that uses a combination of parallel file I/O and database support for high-performance scientific data management. SDM provides a high-level API to the user and, internally, uses a parallel file system to store real data and a database to store application-related metadata. In this paper, we describe how we designed and implemented SDM to support irregular applications. SDM can efficiently handle the reading and writing of data in an irregular mesh, as well as the distribution of index values. We describe the SDM user interface and how we have implemented it to achieve high performance. SDM makes extensive use of MPI-IO's noncontiguous collective I/O functions. SDM also uses the concept of a history file to optimize the cost of the index distribution using the metadata stored in database. We present performance results with two irregular applications, a CFD code called FUN3D and a Rayleigh-Taylor instability code, on the SGI Origin2000 at Argonne National Laboratory. © 2001 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

A scientific data management system for irregular applications

A scientific data management system for irregular applicatio...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Jaechun No R. Thakur D. Kaushik L. Freitag A. Choudhary Math. and Computer Science Division Argonne National Laboratory Argonne IL USA Department of Elec. and Computer Eng Northwestern University Evanston IL USA

来源：评论

学校读者我要写书评

暂无评论

Implications of Heterogeneous Chemistry of Nitric Acid for Nitrogen Deposition to Marine Ecosystems: Observations and Modeling

引用

Water, Air and Soil Pollution: Focus 2001年第5期1卷 99-107页

作者： Pryor, S. C. Barthelmie, R. J. Schoof, J. T. Sørensen, L. L. Erickson, D. J. Atmospheric Science Program Geography Indiana University Bloomington Dept. of Wind Energy & Atmospheric Physics Risø National Laboratory Roskilde Oak Ridge National Laboratory Computer Science & Math. Division Oak Ridge

Size resolved particle composition and nitric acid (HNO3)measurements from the ASEPS'98 experiment conducted in the BalticSea are used to provide observational evidence of substantialgas-particle transfer of oxidized nitrogen (N) compounds in themarine boundary layer. We then focus on the importance ofHNO3 reactions on sea salt particles in determining spatio-temporal patterns of N dry deposition to marine *** results obtained assuming no kinetic or chemical limiton HNO3 uptake and horizontally homogeneous conditions withnear-neutral stability, indicate that for wind speeds 3.5 – 10 ms-1 transfer of HNO3 to the particle phase to formparticle nitrate (NO3 -) may decrease the N depositionvelocity by 50%. We extend this research using the CHEM-COASTmodel to demonstrate that, in a sulphur poor environment undermoderate wind speeds with HNO3 concentrations representativeof those found in the marine boundary layer, inclusion ofheterogeneous reactions on sea spray significantly reducesmodelled NO3 - deposition in the near coastal zone.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integrating parallel file I/O and database support for high-performance scientific data management

Integrating parallel file I/O and database support for high-...

引用

2000 ACM/IEEE Conference on Supercomputing, SC 2000

作者： No, Jaechun Thakur, Rajeev Choudhary, Alok Math. and Computer Science Division Argonne National Laboratory ArgonneIL60439 United States Dept. of Electrical and Computer Eng Northwestern University EvanstonIL60208 United States

ISBN: (纸本)0780398025

Many scientific applications have large I/O requirements, in terms of both the size of data and the number of files or data sets. Management, storage, efficient access, and analysis of this data present an extremely challenging task. Traditionally, two different solutions are used for this problem: file I/O or databases. File I/O can provide high performance but is tedious to use with large numbers of files and large and complex data sets. Databases can be convenient, flexible, and powerful but do not perform and scale well for parallel supercomputing applications. We have developed a software system, called Scientific Data Manager (SDM), that aims to combine the good features of both file I/O and databases. SDM provides a high-level API to the user and, internally, uses a parallel file system to store real data and a database to store application-related metadata. SDM takes advantage of various I/O optimizations available in MPI-IO, such as collective I/O and noncontiguous requests, in a manner that is transparent to the user. As a result, users can write and retrieve data with the performance of parallel file I/O, without having to bother with the details of actually performing file I/O. In this paper, we describe the design and implementation of SDM. With the help of two parallel application templates, ASTRO3D and an Euler solver, we illustrate how some of the design criteria affect performance. © 2000 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

An evaluation of Java's I/O capabilities for high-performance computing

An evaluation of Java's I/O capabilities for high-performanc...

引用

ACM 2000 Java Grande Conference

作者： Dickens, Phillip M. Thakur, Rajeev Illinois Institute of Technology 10 West 31st Street Chicago IL 60616 United States Math. and Computer Science Division Argonne National Laboratory Argonne IL 60439 United States

ISBN: (纸本)1581132883

Java is quickly becoming the preferred language for writing distributed applications because of its inherent support for programming on distributed platforms. In particular, Java provides compile-time and run-time security, automatic garbage collection, inherent support for multithreading, support for persistent objects and object migration, and portability. Given these significant advantages of Java, there is a growing interest in using Java for high-performance computing applications. To be successful in the high-performance computing domain, however, Java must have the capability to efficiently handle the significant I/O requirements commonly found in high-performance computing applications. While there has been significant research in high-performance I/O using languages such as C, C++, and Fortran, there has been relatively little research into the I/O capabilities of Java. In this paper, we evaluate the I/O capabilities of Java for high-performance computing. We examine several approaches that attempt to provide high-performance I/O - many of which are not obvious at first glance - and investigate their performance in both parallel and multithreaded environments. We also provide suggestions for expanding the I/O capabilities of Java to better support the needs of high-performance computing applications.

关键词： Java programming language

来源：评论

学校读者我要写书评

暂无评论

Coloring powers of planar graphs 00

Coloring powers of planar graphs

引用

Proceedings of the eleventh annual ACM-SIAM symposium on Discrete algorithms

作者： Geir Agnarsson Magnús M. Halldórsson Division of Math. Science Institute University of Iceland Graduate School of Informatics Kyoto University and Division of Applied Math and Computer Sci. Science Institute University of Iceland

来源：评论

学校读者我要写书评

暂无评论

Integrating parallel file I/O and database support for high-performance scientific data management 00

Integrating parallel file I/O and database support for high-...

引用

Proceedings of the 2000 ACM/IEEE conference on Supercomputing

作者： Jaechun No Rajeev Thakur Alok Choudhary Math. and Computer Science Division Argonne National Laboratory Argonne IL Dept. of Electrical and Computer Eng. Northwestern University Evanston IL

ISBN: (纸本)9780780398023

Many scientific applications have large I/O requirements, in terms of both the size of data and the number of files or data sets. Management, storage, efficient access, and analysis of these data present an extremely challenging task. Traditionally, two different solutions are used for this problem: file I/O or databases. File I/O can provide high performance but is tedious to use with large numbers of files and large and complex data sets. Databases can be convenient, flexible, and powerful but do not perform and scale well for parallel supercomputing applications. We have developed a software system, called Scientific Data Manager (SDM), which aims to combine the good features of both file I/O and databases. SDM provides a high-level API to the user and, internally, uses a parallel file system to store real data and a database to store appreciation-related metadata. SDM takes advantage of various I/O optimizations available in MPI-IO, such as collective I/O and noncontiguous requests, in a manner that is transparent to the user. As a result, users can write and retrieve data with the performance of parallel file I/O, without having to bother with the details of actually performing file I/*** this paper, we describe the design and implementation of SDM. With the help of two parallel application templates, ASTRO3D and an Euler solver, we illustrate how some of the design criteria affect performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two dimensional simulations of enhanced heat transfer in an intermittently grooved channel

American Society of Mechanical Engineers, Heat Transfer Divi...

引用

American Society of Mechanical Engineers, Heat Transfer division, (Publication) HTD 2000年 366卷 23-31页

作者： Greiner, M. Fischer, P.F. Tufo, H.M. Mechanical Engineering Department University of Nevada Reno NV 89557 United States Math. and Computer Science Division Argonne National Laboratory Argonne IL 60439 United States Department of Computer Science University of Chicago Chicago IL 60637 United States

Two-dimensional Navier-Stokes simulations of heat and momentum transport in an intermittently grooved passage are performed using the spectral element technique for the Reynolds number range 600 [less-than or equal to] Re [less-than or equal to] 1800. The computational domain has seven contiguous transverse grooves cut symmetrically into opposite walls, followed by a flat section with the same length. Periodic inflow/outflow boundary conditions are employed. The development and decay of unsteady flow is observed in the grooved and flat sections, respectively. The axial variation of the unsteady component of velocity is compared to the local heat transfer, shear stress and pressure gradient. The results suggest that intermittently grooved passages may offer even higher heat transfer for a given pumping power than the levels observed in fully grooved passages.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Full abstractness of a metric semantics for action refinement

引用

Fundamenta Informaticae 1999年第4期40卷 335-382页

作者： Den, Hartog, J.I. De, Vink, E.P. De, Bakker, J.W. Math. and Computer Science Division Vrije Universiteit Amsterdam Netherlands KPN Research Leidschendam Netherlands Department of Software Engineering CWI Amsterdam Netherlands KPN Research P.O. Box 421 2260 AK Leidschendam Netherlands

For a process language with action refinement and synchronization both an operational and a denotational semantics are given. The operational semantics is based on an SOS-style transition system specification involving syntactical refinement sequences. The denotational semantics is an interleaving model which uses semantical refinement 'environments'. It identifies those statements which are equal under all refinements. The denotational model is shown to be fully abstract with respect to the operational one. The underlying metric machinery is exploited to obtain this full abstractness result. Usually, action refinement is treated either in a model with some form of true concurrency, or, when an interleaving model is applied, by assuming that the refining statements are atomized. We argue that an interleaving model without such atomization is attractive as well.

关键词： operational semantics denotational semantics metric topology action refinement full abstractness semantical refinement

来源：评论

学校读者我要写书评

暂无评论

Playing twenty questions with a procrastinator 99

Playing twenty questions with a procrastinator

引用

Proceedings of the tenth annual ACM-SIAM symposium on Discrete algorithms

作者： Andris Ambainis Stephen A. Bloch David L. Schweizer Computer Science Division University of California Berkeley CA Department of Math. & Computer Science Adelphi University Garden City NY Barclays Global Investors 45 Fremont Street San Francisco CA

No abstract available.

ISBN: (纸本)9780898714340

No abstract available.

关键词：

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：