parallel Monte Carlo simulation requires reliable RNGs. For sequential machines, good generators exist. A is not at all trivial to find high-quality RNGs for parallel machines. In this paper we present a short review ...
详细信息
ISBN:
(纸本)0818684577
parallel Monte Carlo simulation requires reliable RNGs. For sequential machines, good generators exist. A is not at all trivial to find high-quality RNGs for parallel machines. In this paper we present a short review of the main concepts to produce random numbers on parallel processors and, further, we illustrate some phenomena that occur with parallelization.
In this paper, the relationship between the computational models of Object-Oriented Rewriting and parallel Discrete-Event simulation models is explored. A discrete-event simulation program in which several objects int...
详细信息
ISBN:
(纸本)0818683325
In this paper, the relationship between the computational models of Object-Oriented Rewriting and parallel Discrete-Event simulation models is explored. A discrete-event simulation program in which several objects interact with each other by exchanging messages may have a high degree of concurrency (which can be exploited using optimistic or conservative parallelsimulation methods). We report on some observations on using Rewriting Logic in the field of parallel Discrete Event simulations, and investigate how parallelsimulation applications can be expressed using Object-Oriented Rewriting.
parallel and distributed discrete-event simulation (PDES) is a critical technology for an important class of very large complicated simulation models. However, with few exceptions, the bulk of empirical work in PDES h...
详细信息
parallel and distributed discrete-event simulation (PDES) is a critical technology for an important class of very large complicated simulation models. However, with few exceptions, the bulk of empirical work in PDES has been on small models. Furthermore, synchronization behavior is frequently complicated, which makes it very difficult to analytically prove anything about the performance executing large models on large machines. Scalability analysis asks how the performance of a certain application behaves as the application problem size increases and the parallel architecture executing it increases.
One of the key factors for efficiency in distributedsimulation is the detection of model-inherent concurrency, which is related on the prediction of the future behavior of each logical simulation process. In this pap...
详细信息
One of the key factors for efficiency in distributedsimulation is the detection of model-inherent concurrency, which is related on the prediction of the future behavior of each logical simulation process. In this paper we present a generalization of traditional approaches to behavioral prediction which provides more accurate predictions in general and a high degree of scalability in terms of computational and communication overhead. We give a sequential implementation, prove its correctness using concepts from the analysis of real-time process networks and then show how these results can be used in distributedsimulation.
This paper describes Nops, a conservatively synchronized process-oriented parallelsimulation system. Nops is designed to support the programming model of the Telecommunications Description Language (TeD), with specia...
详细信息
This paper describes Nops, a conservatively synchronized process-oriented parallelsimulation system. Nops is designed to support the programming model of the Telecommunications Description Language (TeD), with special emphasis on scaling up to very large network models. We chronicle the decisions beyond Nops' design, describe that design, assess its raw performance relative to CSIM, Maisie, and GTW, and study its ability to scale to large models.
In this work we discuss the use and possible abuse of linear and inversive pseudorandom numbers (PRNs) in parallel and distributed environments. After an investigation of properties of PRNs which determine hour these ...
详细信息
ISBN:
(纸本)0818684577
In this work we discuss the use and possible abuse of linear and inversive pseudorandom numbers (PRNs) in parallel and distributed environments. After an investigation of properties of PRNs which determine hour these may be applied in such environments we introduce a software package which provides an unified and easy-to-use approach to the generating and handling of parallel streams of such PRNs. Experimental results are conducted which describe the features of the software package and compare the performance of two selected types of pseudorandom number *** this work we discuss the use and possible abuse of linear and inversive pseudorandom numbers (PRNs) in parallel and distributed environments. After an investigation of properties of PRNs which determine hour these may be applied in such environments we introduce a software package which provides an unified and easy-to-use approach to the generating and handling of parallel streams of such PRNs. Experimental results are conducted which describe the features of the software package and compare the performance of two selected types of pseudorandom number generators.
Data distribution management (DDM) is concerned with the problem of efficiently distributing state information among the entities in a distributedsimulation. While heavily studied in the DIS community for training ap...
详细信息
Data distribution management (DDM) is concerned with the problem of efficiently distributing state information among the entities in a distributedsimulation. While heavily studied in the DIS community for training applications using real-time synchronization, this problem has received considerably less attention for logical time simulations, and little performance data has appeared in this regard. This paper is concerned with evaluating the performance of a logical time synchronized.
A probabilistic scheduling policy for selecting the next event to be processed by a processor during optimistic parallel discrete event simulation is presented. This policy exploits the knowledge about statistical dis...
详细信息
A probabilistic scheduling policy for selecting the next event to be processed by a processor during optimistic parallel discrete event simulation is presented. This policy exploits the knowledge about statistical distributions of the difference between the timestamps of successively committed events of a logical process. simulation results are presented to demonstrate that under appropriate conditions probabilistic scheduling generates substantially fewer number of rollbacks compared to the lowest timestamp first scheduling policy.
A number of library-based parallel and sequential network simulators have been designed. This paper describes a library, called GloMoSim (for Global Mobile system Simulator), for parallelsimulation of wireless networ...
详细信息
ISBN:
(纸本)0818684577
A number of library-based parallel and sequential network simulators have been designed. This paper describes a library, called GloMoSim (for Global Mobile system Simulator), for parallelsimulation of wireless networks. GloMoSim has been designed to be extensible and composable: the communication protocol stack for wireless networks is divided into a set of layers, each with its own API. Models of protocols at one layer interact with those at a lower (or higher) layer only via these APIs. The modular implementation enables consistent comparison of multiple protocols at a given layer. The parallel implementation of GloMoSim can be executed using a variety of conservative synchronization protocols, which include the null message and conditional event algorithms This paper describes the GloMoSim library, addresses a number of issues relevant to its parallelization, and presents a set of experimental results on the IBM 9076 SP, a distributed memory multi-computer. These experiments use models constructed from the library modules.
暂无评论