检索结果-内蒙古大学图书馆

2009 Spring Simulation Multiconference, SpringSim 2009

作者： Muzhou, Xiong Cai, Wentong Zhou, Suiping Low, Malcolme Yoke Hean Tian, Feng Chen, Dan Sze, Darrenwee Hamilton, Benjamin D. Parallel and Distributed Computing Centre Nanyang Technological University Singapore639798 Singapore ONG Defence Science and Technology Agency Singapore Technical Support Working Group United States

Crowd simulation has been becoming an efficient tool to study the crowd behavior and its movement. Macroscopic and microscopic approaches take a trade-off between efficiency and accuracy, but neither of them achieves the two goals at the same time. Aiming to achieve both efficiency and accuracy, a multi-resolution model is proposed in this paper for crowd simulation. The paper illustrates how macroscopic and microscopic models co-exist in a single simulator and the interactions between them. The simulation result of a case study shows that the proposed multi-resolution simulation model can obtain a more accurate result than that using a simple macroscopic model alone. The simulation performance is also improved in the meantime.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Unbiased Deep Solvers for Linear Parametric PDEs

引用

Applied Mathematical Finance 2021年第4期28卷 299-329页

作者： Sabate Vidales, Marc Šiška, David Szpruch, Lukasz Edinburgh Parallel Computing Centre University of Edinburgh London United Kingdom School of Mathematics University of Edinburgh Edinburgh United Kingdom Vega Protocol United Kingdom The Alan Turing Institute London United Kingdom

We develop several deep learning algorithms for approximating families of parametric PDE solutions. The proposed algorithms approximate solutions together with their gradients, which in the context of mathematical finance means that the derivative prices and hedging strategies are computed simultaneously. Having approximated the gradient of the solution, one can combine it with a Monte Carlo simulation to remove the bias in the deep network approximation of the PDE solution (derivative price). This is achieved by leveraging the Martingale Representation Theorem and combining the Monte Carlo simulation with the neural network. The resulting algorithm is robust with respect to the quality of the neural network approximation and consequently can be used as a black box in case only limited a-priori information about the underlying problem is available. We believe this is important as neural network-based algorithms often require fair amount of tuning to produce satisfactory results. The methods are empirically shown to work for high-dimensional problems (e.g., 100 dimensions). We provide diagnostics that shed light on appropriate network architectures. © 2022 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： control variates deep neural network Monte Carlo method partial differential equations

来源：评论

学校读者我要写书评

暂无评论

Improving Performance With Serialisation

Improving Performance With Serialisation

引用

Euromicro Workshop on parallel and Distributed Processing

作者： G.R. Ribeiro Justo P.H. Welch Centre for Parallel Computing University of Westminster London UK Computing Laboratory University of Kent Canterbury Kent UK

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Adaptive and Hierarchical Load Sharing Policies for Distributed Systems 13

A Comparative Study of Adaptive and Hierarchical Load Sharin...

引用

13th International Conference on Computers and Their Applications, CATA 1998

作者： Dandamudi, Sivarama P. Lo, Michael Kwok Cheong Centre for Parallel and Distributed Computing School of Computer Science Carleton University OttawaONK1S 5B6 Canada Nortel Technologies OttawaON Canada

ISBN: (纸本)9781618395443

Dynamic load sharing policies take system state into account in making load distribution decisions. The state information can be maintained in one of two basic ways: distributed or centralized. Two principal types of policies that belong to the distributed scheme are the sender-initiated and receiver-initiated policies. In the centralized scheme, a central coordinator node is responsible for collecting system state information. Distributed policies do not perform as well as the centralized policy. Performance of distributed policies is sensitive to variance in job service times and inter-arrival times. Distributed policies, however, are scalable whereas the centralized policy can cause bottleneck and fault-tolerance problems for large systems. An adaptive distributed policy has been proposed that dynamically switches between sender-initiated and receiver-initiated policies depending on the system state. Here we propose a new global hierarchical load sharing policy that minimizes the drawbacks associated with the distributed and centralized policies while retaining their advantages. We provide a performance comparison of these policies and show that the proposed hierarchical policy provides the best performance among the distributed and adaptive policies for all the various system and workload parameters considered. © 13th International Conference on Computers and Their Applications 1998, CATA 1998. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of the hydrogen-saturated self-interstitials in silicon and germanium

引用

Physical Review B 1998年第8期57卷 4397-4397页

作者： M. Budde B. Bech Nielsen P. Leary J. Goss R. Jones P. R. Briddon S. Öberg S. J. Breuer Edinburgh Parallel Computing Centre University of Edinburgh Edinburgh EH9 3JZ United Kingdom

Silicon and germanium single crystals are implanted with protons. The infrared-absorption spectra of the samples contain sharp absorption lines due to the excitation of hydrogen-related local vibrational modes. The lines at 743.1, 748.0, 1986.5, and 1989.4cm−1 in silicon and at 700.3, 705.5, 1881.8, and 1883.5cm−1 in germanium originate from the same defect in the two materials. Measurements on samples coimplanted with protons and deuterons show that the defect contains two equivalent hydrogen atoms. Uniaxial stress measurements are carried out and a detailed analysis of the results is presented. It is shown that the defect has monoclinic-II symmetry, and the orientations of the Si-H and Ge-H bonds of the defect are determined. Ab initio local-density-functional theory is used to calculate the structure and local vibrational modes of the self-interstitial binding one and two hydrogen atoms in silicon and germanium together with the structure of the self-interstitial itself. The observed properties of the defect are in excellent agreement with those calculated for the self-interstitial binding two hydrogen atoms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HIPERTRANS: High performance transport network modelling and simulation 6

引用

6th International European Conference on parallel computing, Euro-Par 2000

作者： Ijaha, Stephen E. Winter, Stephen C. Kalantery, Nasser Centre for Parallel Computing Cavendish School of Computer Science University of Westminster 115 New Cavendish Street LondonW1M 8JS United Kingdom

ISBN: (纸本)9783540679561

HIPERTRANS (High Performance Transport network modelling and Simulation) is a fast and visually representative simulator that can predict traffic on a given urban road network. It was designed using object-oriented techniques and by re-engineering established road traffic models. It has the capability of interfacing to a range of UTC (urban traffic control) systems. Its high performance version was implemented by using a novel parallel programming platform called SPIDER;it has the capability of executing faster than real time and runs on distributed processors. The simulator provides a powerful GUI (graphical user interface) for entering road network models, configuring simulation runs, and visualising simulation results. The system provides helpful traffic diagnostic tools enabling local transport authorities, policy makers, researchers, and UTC manufacturers to gainfully exploit its functionality. The HIPERTRANS project was funded by the European Commission under the 4th Framework programme. © Springer-Verlag Berlin Heidelberg 2000.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

HPF and numerical libraries 4th

引用

4th International ACPC Conference on parallel Computation, ACPC 1999

作者： Ehold, Harald J. Gansterer, Wilfried N. Kvasnicka, Dieter F. Ueberhuber, Christoph W. VCPC European Centre for Parallel Computing at Vienna Australia Institute for Applied and Numerical Mathematics Vienna University of Technology Austria Institute for Physical and Theoretical Chemistry Vienna University of Technology Austria

ISBN: (纸本)3540656413

Portable and effcient ways for calling numerical high performance software libraries from HPF programs are investigated. The methods suggested utilize HPF’s EXTRINSIC mechanism and are independent of implementation details of HPF compilers. Two prototypical examples are used to illustrate these techniques. Highly optimized Blas routines are utilized for local computations: (i) in parallel multiplication of matrices, and (ii) in parallel Cholesky factorization. Both implementations turn out to be very efficient and show significant improvements over standard HPF implementations. © Springer-Verlag Berlin Heidelberg 1999.

关键词： Libraries

来源：评论

学校读者我要写书评

暂无评论

Cloud apps to-go: Cloud portability with TOSCA and MiCADO

Cloud apps to-go: Cloud portability with TOSCA and MiCADO

引用

作者： DesLauriers, James Kiss, Tamas Ariyattu, Resmi C. Dang, Hai-Van Ullah, Amjad Bowden, James Krefting, Dagmar Pierantoni, Gabriele Terstyanszky, Gabor Research Centre for Parallel Computing University of Westminster London United Kingdom Hochschule für Technik und Wirtschaft Berlin Germany University Medical Center Göttingen Germany

As cloud adoption increases, so do the number of available cloud service providers. Moving complex applications between clouds can be beneficial—or other times necessary—but achieving this so-called cloud portability is rarely straightforward. This article presents the adoption of OASIS TOSCA, a standard in the declarative description of cloud applications, to encourage and facilitate cloud portability in MiCADO, an application-level multi-cloud orchestration and auto-scaling framework. The interface to MiCADO is an Application Description Template, which draws from the TOSCA specification to describe an application in MiCADO. The generic design of these templates is presented and their applicability for achieving portability between different container and cloud environments is analysed and evaluated. A proof-of-concept where MiCADO serves as the deployment and execution engine for a Science Gateway in Sleep Healthcare is then described. In this proof-of-concept, MiCADO facilitates the deployment of a complex healthcare application, which is then moved from one cloud service provider to another with only minimal changes to the template which originally described it. This TOSCA-based approach to templates in MiCADO encourages movement between clouds by making cloud portability more approachable. © 2020 The Authors. Concurrency and Computation: Practice and Experience published by John Wiley & Sons Ltd.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

Static, dynamic, and electronic properties of liquid gallium studied by first-principles simulation

引用

Physical Review B 1995年第2期52卷 967-967页

作者： J. M. Holender M. J. Gillan M. C. Payne A. D. Simpson Edinburgh Parallel Computing Centre Edinburgh University Edinburgh EH9 3JZ United Kingdom

First-principles molecular-dynamics simulations having a duration of 8 ps have been used to study the static, dynamic, and electronic properties of Ga at the temperatures 702 and 982 K. The simulations use the density-functional pseudopotential method and the system is maintained on the Born-Oppenheimer surface by conjugate gradients relaxation. The static structure factor and radial distribution function of the simulated system agree very closely with experimental data, but the diffusion coefficient is noticeably lower than measured values. The long simulations allow us to calculate the dynamical structure factor S(q,ω). A sound-wave peak is clearly visible in S(q,ω) at small wave vectors, and we present results for the dispersion curve and hence the sound velocity, which is close to the experimental value. The electronic density of states is very close to the free-electron form. Values of the electrical conductivity calculated from the Kubo-Greenwood formula are in satisfactory accord with measured data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance of hybrid message-passing and shared-memory parallelism for discrete element modeling

Performance of hybrid message-passing and shared-memory para...

引用

2000 ACM/IEEE Conference on Supercomputing, SC 2000

作者： Henty, D.S. Edinburgh Parallel Computing Centre The University of Edinburgh James Clerk Maxwell Building The King's Buildings Mayfield Road EdinburghEH9 3JZ United Kingdom

ISBN: (纸本)0780398025

The current trend in HPC hardware is towards clusters of shared-memory (SMP) compute nodes. For applications developers the major question is how best to program these SMP clusters. To address this we study an algorithm from Discrete Element Modeling, parallelised using both the message-passing and shared-memory models simultaneously ("hybrid" parallelisation). The natural load-balancing methods are different in the two parallel models, the shared-memory method being in principle more efficient for very load-imbalanced problems. It is therefore possible that hybrid parallelism will be beneficial on SMP clusters. We benchmark MPI and OpenMP implementations of the algorithm on MPP, SMP and cluster architectures, and evaluate the effectiveness of hybrid parallelism. Although we observe cases where OpenMP is more efficient than MPI on a single SMP node, we conclude that our current OpenMP implementation is not yet efficient enough for hybrid parallelism to outperform pure message-passing on an SMP cluster. © 2000 IEEE.

关键词： Message passing

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：