检索结果-内蒙古大学图书馆

18th international conference on parallel and distributed computing systems, pdcs 2005

作者： Blouin, C. Butt, D. Hickey, G. Rau-Chaplin, A. Faculty of Computer Science Dalhousie University HalifaxB3H 5W1 Canada Dept. of Biochemistry and Molecular Biology Faculty of Medicine Dalhousie University HalifaxB3H 5X1 Canada Genome Atlantic Canada

ISBN: (纸本)9781604234565

Inferring phylogenetic relationships between sequences is a difficult and interesting problem. Assuming that there is enough phylogenetic signal in a biological sequence to resolve every tree bifurcation, the resulting tree is a representation of the vertical descent history of a gene. A popular method to evaluate a candidate phylogenetic tree uses the likelihood of the data, given an empirical model of character substitution. the computational cost of search for the maximum-likelihood tree is, however, very large. In this paper, we present a parallel algorithm for protein phylogeny using a maximum likelihood framework. A key design goal, which differentiates our method from others, is that it determines a range (confidence set) of statistically equivalent trees, instead of only a single solution. We also present a number of sequential algorithmic enhancements and both sequential and parallel performance results. © 2005 18th ISCA international conference on parallel and distributed computing systems 2005, pdcs 2005. All rights reserved.

关键词： Maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

An Empirical Analysis of parallel Random Permutation Algorithms on SMPs 18

An Empirical Analysis of Parallel Random Permutation Algorit...

引用

18th international conference on parallel and distributed computing systems, pdcs 2005

作者： Cong, Guojing Bader, David A. T.J. Watson Research Center IBM Yorktown HeightsNY10598 United States College of Computing Georgia Institute of Technology AtlantaGA30332 United States

ISBN: (纸本)9781604234565

We compare parallel algorithms for random permutation generation on symmetric multiprocessors (SMPs). Algorithms considered are the sorting-based algorithm, Anderson’s shuffling algorithm, the dart-throwing algorithm, and Sanders’ algorithm. We investigate the impact of synchronization method, memory access pattern, cost of generating random numbers and other parameters on the performance of the algorithms. Within the range of inputs used and processors employed, Anderson’s algorithm is preferable due to its simplicity when random number generation is relatively costly, while Sanders’ algorithm has superior performance due to good cache performance when a fast random number generator is available. there is no definite winner across all settings. In fact we predict our new dart-throwing algorithm performs best when synchronization among processors becomes costly and memory access is relatively fast. We also compare the performance of our parallel implementations with the sequential implementation. It is unclear without extensive experimental studies whether fast parallel algorithms beat efficient sequential algorithms due to mismatch between model and architecture. Our implementations achieve speedups up to 6 with 12 processors on the Sun E4500. © 2005 18th ISCA international conference on parallel and distributed computing systems 2005, pdcs 2005. All rights reserved.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Operation Liveness and Gossip Management in a Dynamic distributed Atomic Data Service 18

Operation Liveness and Gossip Management in a Dynamic Distri...

引用

18th international conference on parallel and distributed computing systems, pdcs 2005

作者： Gramoli, Vincent C. Musial, Peter M. Shvartsman, Alexander A. IRISA Campus de Beaulieu Rennes Cedex35042 France Dep. of Comp. Sci. and Engi. University of Connecticut StorrsCT06269 United States CSAIL Massachusetts Institute of Technology CambridgeMA02139 United States

ISBN: (纸本)9781604234565

this paper presents performance-oriented refinements and distributed implementation of a reconfigurable linearizable data service for read/write atomic objects. this service is based on the work of Lynch and Shvartsman, and it guarantees consistency under dynamic conditions involving asynchrony, message loss, and node arrivals, departures, and failures. To achieve fault tolerance and availability the service replicates objects at several dynamically, changeable network nodes, to which we refer as owners. All-to-all gossip protocol is used to keep replicas up to date and to maintain the list of the owners. However, when gossip is unconstrained and communication bandwidth is limited, network congestion may degrade system’s performance. Moreover, we identify a problem where under certain scenarios read/write operations may become delayed or blocked. this paper introduces a more practical algorithm that introduces two refinements. First, we reduce communication cost by restricting the all-to-all gossip pattern to replica owners, based on the local decisions of the participating nodes. In this setting we analyze the latency of read/write operations. Second, we present a solution that allows blocked (or delayed) operations to resume processing and complete successfully. We restate the conditional analysis accordingly. Finally, we engineered a complete distributed system implementing this service and we present empirical results that illustrate the advantages of our approach. © 2005 18th ISCA international conference on parallel and distributed computing systems 2005, pdcs 2005. All rights reserved.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

Using approximation with time-parallel simulation

引用

SIMULATION-TRANSACTIONS OF thE SOCIETY FOR MODELING AND SIMULATION international 2005年第4期81卷 255-266页

作者： Kiesling, T Univ Bundeswehr Munchen Fak Informat D-85577 Neubiberg Germany

Temporal decomposition of simulation models, which is used in time-parallel simulation, is a promising alternative to classical spatial decomposition. It has been successfully applied to a small number of different models, most prominently for the simulation of computer caches and queuing systems. Unfortunately, widespread use is prevented by the state-match problem, which restricts the application of time-parallel simulation. Instead of a correct solution to the state-match problem, this work proposes the use of approximate solutions to facilitate the temporal decomposition of simulation models and to extend the class of models suitable for time-parallel simulation. However, this introduces an error in the simulation results, which might seriously distort or even invalidate results. therefore, the error must be closely analyzed, and a method of error control must be provided. In addition to the basic properties of approximate techniques in time-parallel simulation, this work presents two use cases that illustrate the introduced concepts.

关键词： simulation parallel computing time-parallel simulation approximate method

来源：评论

学校读者我要写书评

暂无评论

Electron beam processors over fast processing the information received from matrix multiplexers

Electron beam processors over fast processing the informatio...

引用

18th international conference on Photoelectronics and Night Vision Devices

作者： Vasichev, BN Fatjanova, GI State Unitary Enterprise ORION RD&P Ctr Moscow Russia

ISBN: (纸本)0819458287

Work is devoted to the decision of extremely actual problem - to development of physicotechnical bases and a design of microprocessors over fast processing the information and an identification of the image, received with matrix multiplexers. Processing of spatially distributed information acting from matrix multiplexers, is made in a parallel mode with the help vacuum over tiny electron beam cells, commensurable with elements of a photo of a matrix. Use of such processors will allow to refuse bulky computers on semiconductors, and considerably to reduce expenses of energy. For example operation of an identification of an image is carried out 1000 times faster, than with the help of modern computers.

关键词： Electron beams Diffraction Ions Multiplexers computing systems Integrated circuits Chemical species Data processing Magnetism Metals

来源：评论

学校读者我要写书评

暂无评论

A framework for distributed and hierarchical design-for-test

A framework for distributed and hierarchical design-for-test

引用

18th international conference on VLSI Design/4th international conference on Embedded systems Design

作者： Ravikumar, CP Dandamudi, R Devanathan, VR Haldar, N Kiran, K Kumar, PSV Texas Instruments India Pvt Ltd Bangalore 560093 Karnataka India

ISBN: (纸本)0769522645

As we move into the system-on-chip era, test cost is becoming a significant portion of the total cost. Similarly, test synthesis, test pattern generation, pattern compression and pattern validation are consuming significant portion of the design cycle time. the volume of test generation and validation is high due to the size of the designs as well as the types of tests that are required to be run - scan test patterns for stuck-at and delay tests, logic and memory BIST patterns, IDDQ tests, burn-in tests, and several miscellaneous tests. Designs cannot be taped out without validated test patterns. At the same time, since design timing closure takes up a significant portion of the project time and the timing information is not available until late in the schedule, there is immense pressure on the DFT team to generate and validated patterns in a small time frame. this paper describes a framework for design-for-test which exploits both hierarchy and the inherent parallelism in the DFT jobs to run the jobs in a distributed computing environment so as to minimize the runtime impact.

关键词： Logic design

来源：评论

学校读者我要写书评

暂无评论

DGMonitor: A performance monitoring tool for sandbox-based desktop grid platforms

引用

JOURNAL OF SUPERcomputing 2005年第2期34卷 113-133页

作者： Cicotti, P Taufer, M Chien, AA Univ Calif San Diego Dept Comp Sci & Engn La Jolla CA 92093 USA Scripps Res Inst Dept Mol Biol La Jolla CA 92037 USA Univ Texas Dept Comp Sci El Paso TX 79968 USA

Accurate, continuous resource monitoring and profiling are critical for enabling performance tuning and scheduling optimization. In desktop grid systems that employ sandboxing, these issues are challenging because (1) subjobs inside sandboxes are executed in a virtual computing environment and (2) the state of this virtual environment within the sandboxes is reset to an initial empty state after a subjob completion. DGMonitor is a monitoring tool which builds a global, accurate, and continuous view of real resource utilization for desktop grids with sandboxing. Our monitoring tool measures performance unobtrusively and reliably, uses a simple performance data model, and is easy to use. Our measurements demonstrate that DGMonitor can scale to large desktop grids (up to 12000 PCs) with low monitoring overhead in terms of resource consumption (less than 0.1% per machine). though we originally developed DGMonitor with the Entropia DCGrid platform, our tool is easily portable and integrated into other desktop grid systems. In all of these systems, DGMonitor data can support existing and novel information services, particularly for performance tuning and scheduling. In this paper, the high scalability and monitoring power of DGMonitor are demonstrated with the Entropia DCGrid platform and the BOINC platform respectively.

关键词： performance monitoring and profiling sandboxing techniques distributed computing

来源：评论

学校读者我要写书评

暂无评论

Communication benchmarking and performance modelling of MPI programs on cluster computers

引用

JOURNAL OF SUPERcomputing 2005年第2期34卷 201-217页

作者： Grove, DA Coddington, PD Univ Adelaide Sch Comp Sci Adelaide SA 5005 Australia

this paper gives an overview of two related tools that we have developed to provide more accurate measurement and modelling of the performance of message-passing communication and application programs on distributed memory parallel computers. MPIBench uses a very precise, globally synchronised clock to measure the performance of MPI communication routines. It can generate probability distributions of communication times, not just the average values produced by other MPI benchmarks. this allows useful insights to be made into the MPI communication performance of parallel computers, and in particular how performance is affected by network contention. the Performance Evaluating Virtual parallel Machine (PEVPM) provides a simple, fast and accurate technique for modelling and predicting the performance of message-passing parallel programs. It uses a virtual parallel machine to simulate the execution of the parallel program. the effects of network contention can be accurately modelled by sampling from the probability distributions generated by MPIBench. these tools are particularly useful on clusters with commodity Ethernet networks, where relatively high latencies, network congestion and TCP problems can significantly affect communication performance, which is difficult to model accurately using other tools. Experiments with example parallel programs demonstrate that PEVPM gives accurate performance predictions on commodity clusters. We also show that modelling communication performance using average times rather than sampling from probability distributions can give misleading results, particularly for programs running on a large number of processors.

关键词： parallel computing cluster computing performance modelling

来源：评论

学校读者我要写书评

暂无评论

A general performance model of structured and unstructured mesh particle transport computations

引用

JOURNAL OF SUPERcomputing 2005年第2期34卷 181-199页

作者： Mathis, MM Kerbyson, DJ Los Alamos Natl Lab PAL Los Alamos NM 87545 USA

the performance of unstructured mesh applications presents a number of complexities and subtleties that do not arise for dense structured meshes. From a programming point of view, the handling of unstructured meshes has an increased complexity in order to manage the necessary data structures and interactions between mesh-cells. From a performance point of view, there are added difficulties in understanding both the processing time on a single processor and the scaling characteristics when using large-scale parallel systems. In this work we present a general performance model for the calculation of deterministic S-N transport on unstructured meshes that is also applicable to structured meshes. the model captures the key processing characteristics of the calculation and is parametric using both system performance data (latency, bandwidth, processing rate etc.) and application data (mesh size etc.) as input. A single formulation of the model is used to predict the performance of two quite different implementations of the same calculation. It is validated on two clusters (an HP AlphaServer and an Itanium-2 system) showing high prediction accuracy.

关键词： performance modeling performance analysis high performance computing SN transport unstructured meshes parallel processing large-scale systems

来源：评论

学校读者我要写书评

暂无评论

Communication benchmarking and performance modelling of MPI programs on cluster computers

Communication benchmarking and performance modelling of MPI ...

引用

3rd international Workshop on Performance Modelling, Evaluation, and Optimization of parallel and distributed systems held in Conjunction with the 18th international parallel and distributed Processing Symposium

作者： Grove, DA Coddington, PD Univ Adelaide Sch Comp Sci Adelaide SA 5005 Australia

ISBN: (纸本)0769521320

关键词： parallel computing cluster computing performance modelling

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：