Load balancing is a crucial factor in achieving good performance for parallel discrete event simulations. In this paper, we present a load balancing scheme that combines both static partitioning and dynamic load balan...
详细信息
Load balancing is a crucial factor in achieving good performance for parallel discrete event simulations. In this paper, we present a load balancing scheme that combines both static partitioning and dynamic load balancing. The static partitioning scheme maps simulation objects to logical processes before simulation starts while the dynamic load balancing scheme attempts to balance the load during runtime. The static scheme involves two steps. First, the simulation objects that contribute to small lookahead are merged together by using a merging algorithm. Then a partitioning algorithm is applied. The merging is needed to ensure a consistent performance for our dynamic scheme. Our dynamic scheme is tailor-made for an asynchronous simulation protocol that does not rely on null messages. The performance study on a supply-chain simulation shows that the partitioning algorithm and dynamic load balancing are important in achieving good performance.
Creation of seasonal scenery images by computer graphics is an attractive theme with many problems to be solved. This paper presents a method of expressing snow to create natural scenery image in winter. We describe a...
ISBN:
(纸本)0769505716
Creation of seasonal scenery images by computer graphics is an attractive theme with many problems to be solved. This paper presents a method of expressing snow to create natural scenery image in winter. We describe a method of automatically creating the behavior of snowflakes in a field of air currents with respect to snow fall, a method of automatically creating shapes of snow accumulation by using virtual temperature as a path-meter with respect to snow cover formed just after snow fall, and a method based on heat propagation simulation taking into account sunlight, ground heat, and radiation heat from objects with respect To snowmelt. This paper furthermore presents an image creation method to express the feel of the material of snow fall and snow cover.
The spread of virtual environments is setting forth a new set of challenges in the management of system resources for guaranteeing Quality of Service (QoS). This paper describes an implementation of end-user QoS contr...
详细信息
ISBN:
(纸本)0769505686
The spread of virtual environments is setting forth a new set of challenges in the management of system resources for guaranteeing Quality of Service (QoS). This paper describes an implementation of end-user QoS control to a distributed Virtual Environment Platform DVECOM [Choukair00]. In particular, we describe how to guarantee mandatory properties such as synchronization and consistency and how to reduce the impact on the application in case of sudden overload in the system and how we master this degradation to guarantee a smooth degradation according to the end user requirements. This representation degradation is driven by the user choices and profile selected through the offered rendering strategy API. We also present our evaluation of the QoS implementation, describing some interesting results we achieved in a simulation of a collaborative work in the system.
In this paper we present the application of an approach for the performance prediction of message passing programs, to a PVM code implementing an iterative solver based on the Successive OverRelaxation method. The app...
详细信息
parallel cluster computing projects use a large number of commodity PCs to provide cost-effective computational power to run parallel applications. Because properly load-balanced distributedparallel applications tend...
详细信息
ISBN:
(纸本)3540678794
parallel cluster computing projects use a large number of commodity PCs to provide cost-effective computational power to run parallel applications. Because properly load-balanced distributedparallel applications tend to send messages synchronously, minimizing blocking is as crucial a requirement for the network fabric as are those of high bandwidth and low latency. We consider the selection of an optimal, commodity-based, interconnect network technology and topology to provide high bandwidth, low latency, and reliable delivery. Since our network design goal is to facilitate the performance of real applications, we evaluated the performance of myrinet and gigabit ethernet technologies in the context of working algorithms using modeling and simulation tools developed for this work.
In this paper, we introduce a new Time Warp system called ROSS: Rensselaer's Optimistic simulation System. ROSS is an extremely modular kernel that is capable of achieving event rates as high as 1,250,000 events p...
详细信息
In this paper, we introduce a new Time Warp system called ROSS: Rensselaer's Optimistic simulation System. ROSS is an extremely modular kernel that is capable of achieving event rates as high as 1,250,000 events per second when simulating a wireless telephone network model (PCS) on a quad processor PC server. In a head-to-head comparison, we observe that ROSS out performs the Georgia Tech Time Warp (GTW) system on the same computing platform by up to 180%. ROSS only requires a small constant amount of memory buffers greater than the amount needed by the sequential simulation for a constant number of processors. The driving force behind these high-performance and low memory utilization results is the coupling of an efficient pointer-based implementation framework, Fujimoto's fast GVT algorithm for shared memory multiprocessors, reverse computation and the introduction of Kernel Processes (KPs). KPs lower fossil collection overheads by aggregating processed event lists. This aspect allows fossil collection to be done with greater frequency, thus lowering the overall memory necessary to sustain stable, efficient parallel execution.
The evaluation of network performance under real application loads is carried out by detailed time-intensive and resource-intensive simulations. Moreover, the use of ILP (instruction-level parallel) processors in cc-N...
详细信息
Testing distributed applications over the Internet is fraught with problems: due to the inability, to control a wide area network consistent, reproduceable performance experiments are not possible. Here a system is de...
详细信息
Testing distributed applications over the Internet is fraught with problems: due to the inability, to control a wide area network consistent, reproduceable performance experiments are not possible. Here a system is described that uses a parallel discrete event simulator that can act as a real-time network emulator. Real Internet Protocol (IP) traffic generated by application programs running on user workstations can interact with modelled traffic in the emulator, thus providing a controlled test environment for distributed applications. parallel execution enables the emulator to simulate large virtual networks and to model traffic interactions that could not be done in real-time sequentially. This paper gives an overview of the emulator and explores the various external data routing methods that the emulator supports. These routing methods allow the emulator to be operated in shared environments with certain constraints, as well as in dedicated test environments. Preliminary performance results are included.
The proceedings contain 12 papers. The topics discussed include: WATIS2: design and application of an environment simulation system for test improvement of control software for automatic logistic systems;preliminary i...
ISBN:
(纸本)0769508375
The proceedings contain 12 papers. The topics discussed include: WATIS2: design and application of an environment simulation system for test improvement of control software for automatic logistic systems;preliminary investigations into distributed computing applications on a beowulf cluster;distributedsimulation over loosely coupled domains;distributed engineering plant simuiatiod stimulation environment accreditation of accuracy;scheduling for very large virtual environments and networked games using visibility and priorities;exploiting temporal uncertainty in time warp simulations;dynamic grid-based multicast group assignment in data distribution management;a hybrid approach to data distribution management;state of the HLN RTI;adapting a supply-chain simulation for HLA;a generic rollback manager for optimistic HLA simulations;HLA-based simulation within an interactive engineering environment;and an approach for stream retrieval over HLA-RTI in distributed virtual environments.
This article describes a method for modeling the propagation of cracks on any 3D surface. Taking a previous cellular automata model as basis [13], this method allows about any type of cracks on any type of triangulate...
详细信息
ISBN:
(纸本)0769505716
This article describes a method for modeling the propagation of cracks on any 3D surface. Taking a previous cellular automata model as basis [13], this method allows about any type of cracks on any type of triangulated 3D object. Our model's main advantage is that it proposes a semi-physical solution, making it at the same time user controllable and easily extensible. After summarizing, works in the literature, we make a brief and simple description of what physically are cracks and how they are generated. Based on this idea, we detail our model of crack propagation. We first introduce the general development of cracks. We then propose our original model of spectrum stress. This is followed by the description of the mutual interaction between cracks and stresses. Finally a set of graphical examples, with their respective parameters, concludes this paper.
暂无评论