Discrete event simulation is widely used within the networking community for purposes such as demonstrating the validity of network protocols and architectures. Depending on the level of detail modeled within the simu...
详细信息
Discrete event simulation is widely used within the networking community for purposes such as demonstrating the validity of network protocols and architectures. Depending on the level of detail modeled within the simulation, the running time and memory requirements can be excessive. the goal of our research is to develop and demonstrate a practical, scalable approach to parallel and distributedsimulationthat will enable widespread reuse of sequential network simulation models and software. We focus on an approach to parallelization where an existing network simulator is used to build models of subnetworks that are composed to create simulations of larger networks. Changes to the original simulator are minimized, enabling the parallel simulator to easily track enhancements to the sequential version. In this paper we describe our lessons learned in applying this approach to the publicly available ns software package, and converting it to run in a parallel fashion on a network of workstations. this activity highlights a number of important problems, from the standpoint of how to parallelize an existing serial simulation model and achieving acceptable parallel performance.
the GRISSLi coupling interface is a runtime library designed for the coupled computation of grid-based multidisciplinary applications. Established simulation programs, which are deleted to a single discipline, can be ...
详细信息
ISBN:
(纸本)0769500595
the GRISSLi coupling interface is a runtime library designed for the coupled computation of grid-based multidisciplinary applications. Established simulation programs, which are deleted to a single discipline, can be interconnected to a complex simulation system via the GRISSLi coupling interface without recoding the participating programs. We introduce a data model to establish the links between the (dynamic) grids and the attached coupling values in a single application program and to establish the mappings between grids and coupling values among different application programs. the user-specified consistency model is realized ruing asynchronous communication based on the MPI message passing standard Efficient communication is achieved by pre-computing an optimized communication schedule and overlapping communication with computation. Flexible coupling algorithms with adaptive grids and branches are supported in GRISSLi. We have developed a prototype implementation, which provides language bindings in ANSI C and Fortran, and runs currently on IBM RS/6000 SP Gray T3E, SGI Origin/Octane and HP-V Class. We verify the functionality and evaluate the performance of our library rising an industry relevant pilot application, the steel strip production process.
In a journalistic scenario new dimensions of cooperative feature writing are described. In order to compose a highly up-re-date article on economic events with global causes and consequences under the tight time const...
详细信息
ISBN:
(纸本)0769500595
In a journalistic scenario new dimensions of cooperative feature writing are described. In order to compose a highly up-re-date article on economic events with global causes and consequences under the tight time constraints of a daily newspaper by utilizing the geographic competence of correspondents and economic or political experts, their latest observations and views (in contrast to heavily using archived material, even for weekly magazines), novel forms of cooperative work, including distributed on-line writing of feature sections, would have to be supported by innovative distributed operating system services, in particular complex group-based authorization and authentication procedures. the related aspects of our distributed operating system DRAGON SLAYER III are presented, the utilization of services is explained in the scenario context and the authentication of all users and sites participating in the scenario is described. Outlines of ongoing and future work are also discussed.
the proceedings contain 24 papers. the topics discussed include: comprehension with[in] virtual environment visualizations;improving the visibility of graphical program displays: an experimental study;reconstructing o...
ISBN:
(纸本)0769501796
the proceedings contain 24 papers. the topics discussed include: comprehension with[in] virtual environment visualizations;improving the visibility of graphical program displays: an experimental study;reconstructing ownership architectures to help understand software systems;an architecture for automated software maintenance;extending software quality assessment techniques to java systems;improving software comprehension through an automated dependency tracer;an application of fuzzy reasoning to support automated program comprehension;restructuring parallel programs by transformation of point-to-point interactions into collective communication;and comprehending a complex, distributed, object-oriented software system: a report from the field.
this paper describes how the VHDL hardware description language can be used to aid the analysis, design and implementation of adaptive array beamformers for use in teleconferencing environments using parallel architec...
详细信息
ISBN:
(纸本)0769500595
this paper describes how the VHDL hardware description language can be used to aid the analysis, design and implementation of adaptive array beamformers for use in teleconferencing environments using parallel architectures. Beamformer models are often implemented in traditional programming languages such as C, Pascal and FORTRAN. this paper argues that VHDL provides a number of benefits to designers of such systems including improved vision of algorithm architecture, a faster design cycle and a more parallel and implementation-orientated design. the level of abstraction that VHDL gives is an important aid to overcoming the implementation problems associated with designing microphone array beamformers. the traditional view of VHDL as a tool for making implementations in silicon can thus be extended to view VHDL as a tool for thinking with, in some circumstances better than with conventional algorithmic computer languages.
Branch and Bound is a standard method for searching an optimal solution in the scope of continuous and discrete Global Optimization. It iteratively creates a search tree where each node represents a problem which is d...
详细信息
ISBN:
(纸本)0769500595
Branch and Bound is a standard method for searching an optimal solution in the scope of continuous and discrete Global Optimization. It iteratively creates a search tree where each node represents a problem which is decomposed in several subproblems provided that a feasible solution can be found by solving this set of subproblems. the computational power needed to solved most of the Branch and Bound Global Optimization problems and their high degree of potential parallelism make them suitable candidates to be solved in a multiprocessing environment. With palallel processing in mind Branch and Bound techniques can be considered as irregular and dynamic problems. So, their parallel implementations are not straightforward and require the use of dynamic load balance methods where the workload of a subproblem is a crucial parameter. In this pn per. an efficient parallel approach to the Branch and Bound continuous Global Optimization problem is described. It is based on a centralized asynchronous parallel model and on the prediction of the work load of the set of subproblems containing a feasible solution. the proposed dynamic load balancing model obtains ar? almost perfect work load balance with lon communication overhead.
High performance clusters (HPCs) based on commodity hardware are becoming more and more popular in the parallel computing community. these new platforms offer a hardware capable of a very low latency and a very high t...
详细信息
High performance clusters (HPCs) based on commodity hardware are becoming more and more popular in the parallel computing community. these new platforms offer a hardware capable of a very low latency and a very high throughput at an unbeatable cost, making them attractive for a large variety of parallel and distributed applications. With adequate communication software, HPCs have the potential to achieve a level of performance similar to massively parallel computers. However, for parallel applications that present a high communication/computation ratio, it is still essential to provide the lowest latency in order to minimize the communication overhead. In this paper, we are investigating message aggregation techniques to improve parallelsimulations of fine-grain ATM communication network models. Even if message aggregation is a well-known solution for improving the communication performance of high latency interconnection networks, the complex interaction between message aggregation and the underlying communication software is often ignored. We show that message aggregation must carefully take into account the characteristics of the communication software to be efficient on an HPC. this methodology can be applied as a preliminary step to tune a message aggregation algorithm for a given combination of hardware architecture and communication software layer.
A set of computers connected by the Internet can be seen as a MIMD virtual parallel computer withdistributed memory. We call such a computer a Massively parallel Virtual Computer (MPVC). the implementation of an MPVC...
详细信息
ISBN:
(纸本)0769500595
A set of computers connected by the Internet can be seen as a MIMD virtual parallel computer withdistributed memory. We call such a computer a Massively parallel Virtual Computer (MPVC). the implementation of an MPVC will be feasible in rite next few years, as new technologies bring to Internet communication speeds undreamed of nowadays. Problems such as Monte Carlo simulations and image processing and generation are good candidates to take advantage of MPVCs, since they can use practically: all rite computing power they can get. Massively parallel Processing on the I,Internet introduces the problem of scalability that is, how to administrate efficiently a large number of computers and an even larger number of tasks running in them. Previous approaches either do not scale well or let the programmer solve the problem by himself this paper explains the Dynamic Virtual Hypercubes, a structure created to logically organize an MPVC. Dynamic Virtual Hypercubes provide a scalable and efficient way to handle a large number of computers and tasks, since they can adapt to changes it? workload and number of available machines.
In this work we present two different algorithms implemented through neural networks on a multiprocessor device: the parallel single-chip TI TMS32C80 Multimedia VideoProcessor (MVP). the goal of this experimentation i...
详细信息
ISBN:
(纸本)0769500595
In this work we present two different algorithms implemented through neural networks on a multiprocessor device: the parallel single-chip TI TMS32C80 Multimedia VideoProcessor (MVP). the goal of this experimentation is to test, on real problems. the performance of this powerful unit made lip by one Master Rise Processor and by four Slave Digital Signal Processors (DSPs) and to evaluate its suitability to neural network applications. the first problem implemented is a typical classification algorithm, in which the network recognises which points belong to different regions inside a 2D space. the second problem is more computationally heavy and consists of a network able to recognise 'hand-written' digits. the parallel version of the first algorithm, was also tested on a commercially available supercomputer.
In this paper pal allel modelling of linear inhomogeneous 1D distributed parameter systems is considered. Two modelling methods in relation to parallelsimulation are discussed: a two-point series expansion method and...
详细信息
ISBN:
(纸本)3540658211
In this paper pal allel modelling of linear inhomogeneous 1D distributed parameter systems is considered. Two modelling methods in relation to parallelsimulation are discussed: a two-point series expansion method and an eigenfunction expansion method. Both methods are validated with two different source terms for which the analytical solutions are known. A comparison of both approaches with respect to convergence aspects, accuracy, work load, and explicit parallelism is presented.
暂无评论