检索结果-内蒙古大学图书馆

proceedings of the 5th IEEE workshop on Challenges of Large Applications in distributed Environments, CLADE'07 2007年 1-10页

作者： Gardner, Jeffrey P. Connolly, Andrew McBride, Cameron Pittsburgh Supercomputing Center 300 S. Craig St. Pittsburgh PA 15213 University of Washington Department of Astronomy Seattle WA 98195 University of Pittsburgh Department of Physics and Astronomy 3941 O'Hara St. Pittsburgh PA 15260

ISBN: (纸本)1595937145

Virtual observatories will give astronomers easy access to anunprecedented amount of data. Extracting scientific knowledge from these data will increasingly demand both efficient algorithms as well as the power of parallel computers. Nearly all efficient analyses of large astronomical datasets use trees as their fundamental data structure. Writing efficient tree-based techniques, a task that is time-consuming even on single-processor computers, is exceedingly cumbersome on massively parallel platforms (MPPs). Most applications that run on MPPs are simulation codes, since the expense of developing them is offset by the fact that they will be used for many years by many researchers. In contrast, data analysis codes change far more rapidly, are often unique to individual researchers, and therefore accommodate little reuse. Consequently, the economics of the current high-performance computing development paradigm for MPPs does not favor data analysis applications. We have therefore built a library, called Ntropy, that provides a flexible, extensible, and easy-to-use way of developing tree-based data analysis algorithms for both serial and parallel platforms. Our experience has shown that not only does our library save development time, it can also deliver excellent serial performance and parallel scalability. Furthermore, Ntropy makes it easy for an astronomer with little or noparallel programming experience to quickly scale their application to a distributed multiprocessor environment. By minimizing development time for efficient and scalable data analysis, we enable wide-scale knowledge discovery on massive datasets. Copyright 2007 ACM.

关键词： Data reduction

来源：评论

学校读者我要写书评

暂无评论

On extending more parallelism to serial simulators 96

On extending more parallelism to serial simulators

引用

proceedings of the tenth workshop on parallel and distributed simulation

作者： David Nicol Philip Heidelberger Department of Computer Science The College of William and Mary Williamsburg VA IBM T.J. Watson Research Center P.O. Box 704 Yorktown Heights NY

ISBN: (纸本)9780818675393

The Utilitarian parallel Simulator (U.P.S.) extends parallelism to the CSIM sequential simulation tool by providing several new modeling constructs. Using conservative synchronization techniques, these constructs automatically support time-synchronized communications between CSIM submodels running on different processors. This paper describes extensions to U.P.S. that allow the user to assist U.P.S. by providing additional "process lookahead," thereby reducing the frequency of synchronizations. The use and effect on performance of process lookahead is described for several models. In a mobile cellular communications model, the use of process lookahead results in up to a 60% improvement in speedup on 32 nodes of the IBM SP2. A factor of 3 improvement is obtained on a closed queueing network simulation running on 32 nodes of the Intel Paragon.

关键词： queueing system communications network parallel simulation

来源：评论

学校读者我要写书评

暂无评论

Colored Petri net methods for performance analysis of scalable high-speed interconnects

Colored Petri net methods for performance analysis of scalab...

引用

International Symposium on Modeling, Analysis and simulation of Computer and Telecommunication Systems (MASCOTS)

作者： L. Cherkasova A. Davis V. Kotov T. Rokicki Hewlett Packard Laboratories Palo Alto CA USA Comptuer Science Department University of Stanford Stanford CA USA

Large concurrent or distributed systems have proven notoriously difficult to comprehend due to their combinatoric complexity. There is a clear need for thorough formal system modeling at all design stages. Ease of use and validation capability are important criteria in method selection. It is important that the selection permit evaluation of design details with respect to performance and behavioral goals. Net models are a likely candidate to achieve the requisite needs of such a modeling environment. They provide both graphical and mathematical system modeling views which inherently enable both quantitative and qualitative analysis of the design. To demonstrate this claim, a colored Petri Net model and performance analysis of a particular scalable multiprocessor interconnect fabric is presented. The fundamental component of this fabric is an adaptive routing device, R2. The R2 fabric is based on the interconnection scheme used in the Mayfly parallel processing system.< >

关键词： Performance analysis Fabrics Routing Petri nets Modeling Topology Milling machines parallel processing Computer science Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

The SPEEDES Persistence Framework and the Standard simulation Architecture 03

The SPEEDES Persistence Framework and the Standard Simulatio...

引用

proceedings of the seventeenth workshop on parallel and distributed simulation

作者： Dr. Jeffrey S. Steinman Jennifer W. Wong RAM Laboratories 10525 Vista Sorrento Parkway Suite 220 San Diego CA

ISBN: (纸本)9780769519708

This paper provides an overview of the SPEEDESpersistence framework that is currently used to automatecheckpoint/restart for the Joint simulation System. Thepersistence framework interfaces are documented in thispaper and are proposed standards for the Standardsimulation *** persistence framework fundamentally keeps trackof memory allocations and pointer references within ahigh-speed internal database linked with *** persistence, an object, and the collection of objectsit recursively references through pointers, can beautomatically packed into a buffer that is written to diskor sent as a message to another machine. Later, thatbuffer can be used to reconstruct the object and all of itsrecursively referenced objects. The reconstructed objectswill likely be instantiated at different memory *** persistence framework automatically updates allaffected pointer references to account for this *** persistence framework is fully integrated with theSPEEDES rollback infrastructure and built-in containerclass libraries that include an implementation of theStandard Template Library. These utilities automatesupport for optimistic event processing required by manyhigh-performance parallel and distributed timemanagement algorithms. In the future, persistence willenable dynamic load balancing algorithms to migratecomplex objects to different processors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving lookahead in parallel discrete event simulations of large-scale applications using compiler analysis 01

Improving lookahead in parallel discrete event simulations o...

引用

proceedings of the fifteenth workshop on parallel and distributed simulation

作者： Ewa Deelman Rajive Bagrodia Rizos Sakellariou Vikram Adve ISI/USC UCLA Manchester University UIUC

ISBN: (纸本)9780769511047

This paper addresses the issue of efficient and accurate performance prediction of large-scale message-passing applications on high performance architectures using simulation. Such simulators are often based on parallel discrete event simulation, typically using the conservative protocol to synchronize the simulation threads. The paper considers how a compiler can be used to automatically extract information about the lookahead present in the application, and how this can be used to improve the performance of the null protocol used for synchronization. These techniques are implemented in the MPI-Sim simulator and dHPF compiler, which had previously been extended to work together for optimizing the simulation of local computational components of an application. The results shows that the availability of lookahead information improves the runtime of the simulator by factors ranging from 9% up to two orders of magnitude, with 30-60% improvements being typical for the real-world codes. The experiments also show that these improvements are directly correlated with reductions in the number of null messages required by the simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic load balancing strategies for conservative parallel simulations 97

Dynamic load balancing strategies for conservative parallel ...

引用

proceedings of the eleventh workshop on parallel and distributed simulation

作者： Azzedine Boukerche Sajal K. Das Center for Research in Parallel and Distributed Computing Department of Computer Sciences University of North of Texas Denton TX

ISBN: (纸本)9780818679650

This paper studies the problem of load balancing for conservative parallel simulations for execution on a multicomputer. The synchronization protocol makes use of Chandy-Misra null-messages. We propose a dynamic load balancing algorithm which assumes no compile time knowledge about the workload parameters. It is based upon a process migration mechanism, and the notion of CPU-queue length, which indicates the workload at each *** examine two variations for the algorithm which we refer to as centralized and multi-level hierarchical methods, in the context of queueing network simulation of a torus. The torus was chosen because it of its many cycles aid in the formation of deadlock making it a stress test for any conservative synchronization protocols. Our experiments indicate that our dynamic load balancing schemes significantly reduce the run time of an optimized version of Chandy-Misra null message approach, and decreases by 30-40\% the synchronization overhead when compared to the use of a static partitioning algorithm. Significantly, the results obtained also indicate that the multi-level scheme always outperforms both the centralized load balancing approach and the static partitioning algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

parallel Discrete-Event simulation (PDES): a case study in design, development, and performance using SPEEDES 95

Parallel Discrete-Event Simulation (PDES): a case study in d...

引用

proceedings of the ninth workshop on parallel and distributed simulation

作者： Frederick Wieland Eric Blair Tony Zukas The MITRE Corporation 7525 Colshire Dr. McLean VA

ISBN: (纸本)9780818671203

Can parallel simulations efficiently exploit a network of workstations? Why haven't PDES models followed standard modeling methodologies? Will the field of PDES survive, and if so, in what form? Researchers in the PDES field have addressed these questions and others in a series of papers published in the last few years [1,2,3,4]. The purpose of this paper is to shed light on these questions, by documenting an actual case study of the development of an optimistically synchronized PDES application on a network of workstations. This paper is unique in that its focus is not necessarily on performance, but on the whole process of developing a model, from the physical system being simulated, through its conceptual design, validation, implementation, and, of course, its performance. This paper also presents the first reported performance results indicating the impact of risk on performance. The results suggest that the optimal value of risk is sensitive to the latency parameters of the communications network.

关键词： performance network of workstations implementation aerospace simulation validation flight simulation aerospace computing communications network SPEEDES discrete event simulation conceptual design parallel discrete-event simulation optimistically synchronized PDES operations research

来源：评论

学校读者我要写书评

暂无评论

Performance prediction tools for parallel discrete-event simulation 99

Performance prediction tools for parallel discrete-event sim...

引用

proceedings of the thirteenth workshop on parallel and distributed simulation

作者： Chu-Cheow Lim Yoke-Hean Low Boon-Ping Gan Sanjay Jain Wentong Cai Wen Jing Hsu Shell Ying Huang Gintic Institute of Manufacturing Technology 71 Nanyang Drive Singapore 638075 Singapore Centre for Advanced Information Systems School of Applied Science Nanyang Technological University Singapore 639798 Singapore

ISBN: (纸本)9780769501550

We have developed a set of performance prediction tools which help to estimate the achievable speedups from parallelizing a sequential simulation. The tools focus on two important factors in the actual speedup of a parallel simulation program : (a) the simulation protocol used, and (b) the inherent parallelism in the simulation model. The first two tools are a performance/parallelism analyzer for a conservative, asynchronous simulation protocol, and a similar analyzer for a conservative, synchronous ("super-step") protocol. Each analyzer allows us to study how the speedup of a model changes with increasing number of processors, when a specific protocol is used. The third tool -- a critical path analyzer -- gives an ideal upper bound to the model's speedup. This paper gives an overview of the prediction tools, and reports the predictions from applying the tools to a discrete-event wafer fabrication simulation model. The predictions are close to speedups from actual parallel implementations. These tools help us to set realistic expectations of the speedup from a parallel simulation program, and to focus our work on issues which are more likely to yield performance improvement.

关键词： parallel processing discrete event simulation software performance evaluation integrated circuit manufacture performance prediction tools parallel discrete-event simulation sequential simulation parallelization simulation protocol conservative asynchronous simulation conservative synchronous simulation critical path analyzer upper bound wafer fabrication simulation performance improvement

来源：评论

学校读者我要写书评

暂无评论

Dag consistent parallel simulation: a predictable and robust conservative algorithm 97

Dag consistent parallel simulation: a predictable and robust...

引用

proceedings of the eleventh workshop on parallel and distributed simulation

作者： Wentong Cai Emmanuelle Letertre Stephen J. Turner School of Applied Science Nanyang Technological University Singapore 639798 IFSIC Universié de Rennes I Campus de Beaulieu 35042 Rennes Cedex France and Dept. of Computer Science University of Exeter Exeter EX4 4PT U.K. Dept. of Computer Science University of Exeter Exeter EX4 4PT U.K.

ISBN: (纸本)9780818679650

We present a novel approach to parallel discrete event simulation based on the Cilk model of multithreaded computation. Cilk's runtime system not only manages the low-level aspects of program execution, but also provides the user with an algorithmic model of performance which can be used to predict the execution time of a parallel simulation. Moreover, a Cilk application can ``scale down'' to run on a single processor with nearly the same performance as that of serial code.A conservative parallel discrete event simulation algorithm has been developed in which communication between logical processes is achieved using Cilk's virtual memory model, dag consistent shared memory. The simulation executes in cycles, where each cycle involves a divide and conquer computation. Although local lookahead information can be exploited, the algorithm is robust in that it also calculates a global simulation time for each cycle. It can therefore be used for applications where zero lookahead may occur.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimistic simulation of parallel architectures using program executables 96

Optimistic simulation of parallel architectures using progra...

引用

proceedings of the tenth workshop on parallel and distributed simulation

作者： Sashikanth Chandrasekaran Mark D. Hill Computer Sciences Department University of Wisconsin-Madison 1210 West Dayton Street Madison WI

ISBN: (纸本)9780818675393

A key tool of computer architects is computer simulation at the level of detail that can execute program executables. The time and memory requirements of such simulations can be enormous, especially when the machine under design-the target-is a parallel machine. Thus, it is attractive to use parallel simulation, as successfully demonstrated by the Wisconsin Wind Tunnel (WWT). WWT uses a conservative simulation algorithm and eschews network simulation to make lookahead adequate. Nevertheless, we find most of WWT's slowdown to be due to the synchronization overhead in the conservative simulation algorithm. This paper examines the use of optimistic algorithms to perform parallel simulations of parallel machines. We first show that we can make optimistic algorithms work correctly even with WWT's direct execution of program executables. We checkpoint processor registers (integer, floating-point, and condition codes) and use executable editing to log the value of memory words just before they are overwritten by stores. Second, we consider the performance of two optimistic algorithms. The first executes programs optimistically, but performs protocol events (e.g., sending messages) conservatively. The second executes everything optimistically and is similar to Time Warp with lazy message cancellation. Unfortunately, both approaches make parallel simulation performance worse for the default WWT assumptions. We conclude by speculating on the performance of optimistic simulation when simulating (1) target network details, and (2) on hosts with high message latencies and no synchronization hardware.

关键词： Optimistic simulation State Saving parallel Machines Direct Execution

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：