检索结果-内蒙古大学图书馆

15th International Parallel and Distributed Processing Symposium, IPDPS 2001

作者： DeRose, L. Hoover, T. Hollingsworth, J.K. Advanced Computing Technology Center IBM Research Yorktown HeightsNY10598 United States Tools Development Dept. IBM PoughkeepsieNY12601 United States Computer Science Department University of Maryland College ParkMD20742 United States

ISBN: (纸本)0769509908

The complexity of both parallel architectures and parallel applications poses several problems for the development of performance analysis and optimization tools. In this paper, we describe the motivations and the main aspects of the design of the Dynamic Probe Class Library (DPCL), an object based C++ class library that provides an infrastructure to reduce the cost of writing instrumentation for performance tools. Additionally, we present some of the performance tools built on top of DPCL, which demonstrate the power and flexibility of the library. © 2001 IEEE.

关键词： Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

An image segmentation and tracking method by segment scanning wave propagation network

An image segmentation and tracking method by segment scannin...

引用

IEEE International Conference on Image Processing

作者： T. Ishii K. Kyuma Multi-Modul Function Mitsubishi Laboratory Real World Computing Partnership c/o Advanced Technology Research & Development Center Mitsubishi Electric Corporation Limited Japan

Image segmentation is a mixture of complex sub-problems. Following the concept of perceptual organization, we first discuss categorization of these problems. Then we propose a method to bind most of all pixels in each image regions. It is based on image region scanning dynamic wave propagation and region label information represented in the probability distribution. This wave propagation method realizes boundary noise robustness as well as its interpolation. The segment representation in probability distribution enhances the stability of the segmentation result.

关键词： Image segmentation Pixel Computer networks Interpolation Humans Assembly Laboratories Research and development Noise robustness Probability distribution

来源：评论

学校读者我要写书评

暂无评论

The dynamic probe class library-an infrastructure for developing instrumentation for performance tools

The dynamic probe class library-an infrastructure for develo...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： L. DeRose T. Hoover J.K. Hollingsworth Advanced Computing Technology Center IBM Research Yorktown Heights NY USA Tools Development Department IBM Poughkeepsie NY USA Computing Technology Center IBM Research Israel Computer Science Department University of Maryland College Park MD USA

ISBN: (纸本)0769509908

关键词： Probes Libraries Instruments Costs Application software Writing Performance analysis Computer science Educational institutions Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

The influence of electrostatic truncation on simulations of polarizable systems

引用

AIP Conference Proceedings 1999年第1期492卷 114-126页

作者： Steven W. Rick Advanced Biomedical Computing Center SAIC-Frederick NCI-Frederick Cancer Research and Development Center Frederick Maryland 27102

Different schemes for the treatment of long-ranged electrostatic interactions will be examined for water simulations using the polarizable fluctuating charge potential. Several different methods are compared, including Ewald sums, potential shifting, spherical truncation and reaction field corrections. For liquid water, properties such as the energy, pressure, dynamics and structure are more sensitive to the treatment of the long-ranged interactions with polarizable than with non-polarizable potentials.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the hydration of monoatomic ions

引用

AIP Conference Proceedings 1999年第1期492卷 382-410页

作者： G. J. Tawa I. A. Topol S. K. Burt A. A. Rashin Advanced Biomedical Computing Center SAIC Frederick NCI Frederick Cancer Research and Development Center P.O. Box B Frederick Maryland 21702-1201 BioChemComp Inc 543 Sagamore Ave Teaneck New Jersey 07666

It is shown that an understanding of some key biological processes such as the thermodynamics of enzyme-ligand binding or the selectivity of ion-channels is ultimately dependent on an understanding of the details of ion hydration. Therefore, a model for calculating the hydration free energy of ions in aqueous solvent is presented. The model is used to first calculate the proton hydration free energy, ΔGhyd(H+), in an effort to resolve the uncertainty concerning its exact value. In the model we define ΔGhyd(H+) as the free energy change associated with the following process: ΔG{H+(gas)+[H2O]n(aq)→H+[H2O]n)(aq)}, where the solvent is represented by a neutral n-water cluster embedded in a dielectric continuum and the solvated proton is represented by a protonated n-water cluster also in the continuum. All solvated species are treated as quantum mechanical solutes (B3LYP, MP2, MP4, CCSD(T)) coupled to a dielectric continuum using a self consistent reaction field (SCRF) cycle. An investigation of the behavior of ΔGhyd(H+) as the number of explicit waters of hydration is increased reveals convergence by n=4. The converged value is −262.23 kcal/mol and is independent of the ab initio method used. These results indicate that the first hydration shell of the proton is composed of at least 4 water molecules. The result strongly suggests that the proton hydration free energy is at the far lower end of the range of values obtained from the literature. The methodology is then used to calculate the hydration free energies of other ions relative to that of the proton. These include cationic forms of the alkali earth elements Li, Na, and K, and anionic forms of the halogens F, Cl, and Br. The relative ion hydration free energy is defined as Δ[ΔGhyd(Z±)]=G(Z±[H2O]n(aq))−G(H+[H2O]n(aq))−G(Z±(gas))−G(H+(gas))), where the solvated ions are represented by ion-water clusters coupled to a dielectric continuum using a self-consistent reaction field (SCRF) cycle. An investigation of the beh

关键词：

来源：评论

学校读者我要写书评

暂无评论

Finite state machines: a deeper look into synthesis optimization for VHDL

Finite state machines: a deeper look into synthesis optimiza...

引用

International Conference on VLSI Design

作者： V.A. Nebhrajani N. Suthar Center for Development of Advanced Computing Pune University Campus Pune India

This paper provides a deeper insight into the synthesis mechanism of VHDL tools. It examines three methods of writing VHDL code, and each of the three models finite state machines in a different way. There can be significant reductions in the VLSI area and improvements in performance by adopting a certain modeling style, but this is at the cost of writing low level VHDL code, thereby undermining the purpose of VHDL as the design, entry medium. However, there is a simpler approach, which is demonstrated by a software tool called vtvt which allows writing VHDL code at high level and optimizes for area and performance without the burden of writing and maintaining low level code.

关键词： Automata Very large scale integration Writing Software tools History Design optimization Circuits Decoding Hardware Costs

来源：评论

学校读者我要写书评

暂无评论

Parallelization of finite volume computations for heat transfer application using unstructured mesh partitioning algorithms

Parallelization of finite volume computations for heat trans...

引用

International Conference on High Performance computing

作者： C. Singh Verma V.C.V. Rao Center for Development of Advanced Computing Pune University Campus Pune India Department of Computer Science University of Minnesota Minneapolis MN USA

An effective parallelization of finite volume computations for heat transfer application using unstructured triangular meshes and mesh partitioning algorithms are presented. The mesh partitioning software (METIS) is employed to create nearly load balanced subdomains and to minimize the interprocessor communications. Efficient data structures are developed to handle the neighboring element information at the interfaces of all subdomains and a simple strategy to overlap the computations to communications has been implemented for improving the performance of the program. The explicit time integration method is used and the results for the rectangular domain and L-shaped domain have been presented. The code (PHEAT2D) is written in Fortran90 and MPI for message passing is used. The algorithm is tested on distributed memory MIMD machine, PARAM OPENFRAME.

关键词： Concurrent computing Heat transfer Application software Temperature control Partitioning algorithms Data structures Computer interfaces Algorithm design and analysis Parallel processing Equations

来源：评论

学校读者我要写书评

暂无评论

Virtual control channel and its application to the massively parallel computer RWC-1

Virtual control channel and its application to the massively...

引用

International Conference on High Performance computing

作者： T. Yokota H. Matsuoka K. Okamoto H. Hirono S. Sakai Advanced Technology Research & Development Center Mitsubishi Electric Corporation Limited Japan Real World Computing Partnership Japan University of Tsukuba Japan

Global operation and system control are important issues in massively parallel systems. The paper discusses virtual control networks (VCNs), which are substitutes for the current dedicated control networks. First we introduce a new mechanism called Virtual Control Channel (VCC) used to conduct control information over data network links. The network nodes have control finite state machines (CFSMs) and a VCN is composed of CFSMs. The VCC performs the role of a connection wire between CFSMs. The mechanisms are applied to the RWC-1 machine. The simulation results reveal that reduction and broadcasting operations are efficiently executed on VCNs by exploiting the tree structure.

关键词： Application software Concurrent computing Control systems Virtual colonoscopy Broadcasting Delay Costs Automata Wire Tree data structures

来源：评论

学校读者我要写书评

暂无评论

PARALLEL ALGORITHMS FOR SPARSE TRIANGULAR SYSTEM SOLUTION

引用

PARALLEL computing 1993年第2期19卷 187-196页

作者： KUMAR, PS KUMAR, MK BASU, A Center for Development of Advanced Computing 2/1 Brunton Road Bangalore 560 025 India

We present new local-memory multiprocessor algorithms for solving sparse triangular systems of equations that arise in the context of Cholesky factorization. Unlike in the existing algorithms, we use the notion of the elimination tree and achieve significant improvement in the performance of both the forward and backward substitution phases. Our algorithms also incorporate the generalization of an important technique of Li and Coleman that gave rise to the best performance for dense triangular system solution.

关键词： LOCAL-MEMORY MULTIPROCESSOR SYSTEMS PARALLEL ALGORITHMS SPARSE CHOLESKY FACTORIZATION SPARSE TRIANGULAR SYSTEMS ELIMINATION TREE

来源：评论

学校读者我要写书评

暂无评论

CHALLENGES TO THE USE OF SUPERCOMPUTERS AND SCIENTIFIC VISUALIZATION FOR AUTOMOTIVE APPLICATIONS

引用

COMPUTERS & GRAPHICS 1993年第5期17卷 507-515页

作者： GINSBERG, M High-End Computing Section EDS Advanced Computing Center General Motors Research and Development Center 30500 Mound Road P.O. Box 9055 Warren MI 48090-9055 USA

Supercomputing and visualization facilities are used in the automotive industry to produce large-scale computer simulations of physical phenomena related to the efficient design, analysis, and manufacture of cars and trucks. Such tools are an economic necessity for creating very high-quality vehicles that can be rapidly brought from concept to production in an increasingly competitive worldwide automotive market. This paper focuses attention on current and future directions for supercomputing and scientific visualization in an automotive applications environment. Extensive references to automotive simulation work on vector/parallel computers at General Motors are given in the Appendix. The interactions of supercomputers and visualization tools are discussed along with potential bottlenecks which must be overcome.

关键词： Computer graphics

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：