This paper analyzes the Detailed policy Assessment tool (DPAT) as an example of a practical real-world aviation simulation that uses optimistic simulation technology. We present a review of analyses that have used DPA...
详细信息
ISBN:
(纸本)0769511058
This paper analyzes the Detailed policy Assessment tool (DPAT) as an example of a practical real-world aviation simulation that uses optimistic simulation technology. We present a review of analyses that have used DPAT results to support their conclusions, and discuss the design and performance of the system in the context of parallelsimulation. The thrust of this paper is to explain how DPAT avoids some of the problems associated with optimistic simulation, while exploiting its strengths. A key conclusion is that parallelsimulation technology, particularly optimistic synchronization, needs to be built into the product from its conceptual design through implementation, as opposed to adding it afterwards.
Optimistic and conservative simulation algorithms have been effective for speeding up the execution of many simulation programs. Event stepped techniques have also been shown to be effective for certain types of probl...
详细信息
ISBN:
(纸本)0769511058
Optimistic and conservative simulation algorithms have been effective for speeding up the execution of many simulation programs. Event stepped techniques have also been shown to be effective for certain types of problems. This paper presents a conjecture that sparse systems are effectively simulated by conservative and optimistic techniques, where sparseness is characterized by the ratio of output generating states to non-output generating states. The speedup results for a representative sparse simulation are shown to support this conjecture.
This paper discusses the problem of risk in optimistic simulation protocols, using as example simulation of a distributed mutual exclusion protocol with strong consistency properties. the simulation model is augmented...
详细信息
ISBN:
(纸本)076951104X;0769511058
This paper discusses the problem of risk in optimistic simulation protocols, using as example simulation of a distributed mutual exclusion protocol with strong consistency properties. the simulation model is augmented to detect model inconsistency errors resulting from risky optimistic simulation. While the model runs sequentially consistency errors, errors occur when the model is executed in parallel optimistically. Some of the errors entirely violate the fundamental mutual exclusion properties of the model itself. To address this problem we extend the optimistic simulation library to eliminate these inconsistencies. We discuss the detail od these extensions and the performance and the performance trade-off for adding them.
When used to stimulate manufacturing systems, most existing parallelsimulation languages cannot easily implement some features of those systems, such as the scheduling rules of a machine or the sharing of operators b...
详细信息
ISBN:
(纸本)076951104X;0769511058
When used to stimulate manufacturing systems, most existing parallelsimulation languages cannot easily implement some features of those systems, such as the scheduling rules of a machine or the sharing of operators by multiple machines. This paper presents the design and implementation of a parallel object-orientated manufacturing simulation Language, called POMSim. A POMSim simulation id developed by using the concept of classes (entity-types) and inheritance to support iterative design of efficient simulation models. POMSim completely hides all the details of parallelsimulation, and provides simple and direct constructs to efficiently model the scheduling rules and in manufacturing simulation. it also provides asynchronous method invocation and synchronous function call. POMSim libraries predefine a set of basic classes for manufacturing simulation, each of which represents a particular component in the physical manufacturing system.
In parallel and distributedsimulations, it is sometimes desirable that the applications time-stamped events and/or the simulator's time-management control messages be exchanged over a combination of reliable and ...
详细信息
ISBN:
(纸本)0769511058
In parallel and distributedsimulations, it is sometimes desirable that the applications time-stamped events and/or the simulator's time-management control messages be exchanged over a combination of reliable and unreliable network channels. A challenge in developing infrastructure for such simulations is to correctly compute simulation time advances despite the loss of some simulation events and/or control messages. Presented here are algorithms for synchronization in distributedsimulations performed directly over best-effort network transport. The algorithms are presented in a sequence of progressive refinement, starting with all reliable transport and finishing with combinations of relable and unreliable transports for both time-stamped events and time management messages. performance results from a preliminary implementation of these algorithms are also presented. To our knowledge, this is the first work to solve asynchronous time synchronization performed directly over unreliable network transport.
This paper describes a parallel proximity detection algorithm and illustrates its application to the problem of conflict detection in an aviation simulation. The algorithm invokes a previously designed sequential func...
详细信息
ISBN:
(纸本)0769511058
This paper describes a parallel proximity detection algorithm and illustrates its application to the problem of conflict detection in an aviation simulation. The algorithm invokes a previously designed sequential function in parallel, using spatial information acquired during the traversal of a quad tree, to keep the separate invocations of the function as independent as possible. The method is generally applicable to any function (not just conflict detection) whose arguments are spatially organized. Empirical results shoe that a single-threaded version of the algorithm sped up the simulation by 57%, while a four-threaded parallel version extracted 30% of the remaining additional speedup. These results are even more noteworthy given that the architecture of the simulation remains intact: we only replace the invocation mechanism for one function.
A new parallel algorithm for simulating Ising spin systems is presented. The sequential prototype is the n-fold way algorithm [2], which is efficient but is hard to parallelize using conservative methods. Our parallel...
详细信息
ISBN:
(纸本)076951104X;0769511058
A new parallel algorithm for simulating Ising spin systems is presented. The sequential prototype is the n-fold way algorithm [2], which is efficient but is hard to parallelize using conservative methods. Our parallel algorithm is optimistic. Unlike other optimistic algorithms, e.g., Time Warp, our algorithm is synchronous. It also belongs to the class of simulations known as "relaxation" [3];hence it is named "synchronous relaxation." We derive performance guarantees for this algorithm. If N is the number of PEs, then under weak assumptions we show that the number of correct events processed per unit of time is, on average, at least of order N/logN. All communication delays, processing time, and busy waits are taken into account.
In this paper we study the influence of spatio-temporal correlations on the dynamic runtime behaviour of the optimistic parallel Time Warp simulation method. By using the Ising spin model, we show experimentally that ...
详细信息
ISBN:
(纸本)0769511058
In this paper we study the influence of spatio-temporal correlations on the dynamic runtime behaviour of the optimistic parallel Time Warp simulation method. By using the Ising spin model, we show experimentally that the distribution of the number of rolled back events behaves as a power-law distribution over a large range of sub-critical Ising temperatures and decays exponentially for super-critical Ising temperatures. For critical Ising temperatures, where long-range correlations occur, the computational complexity of Time Warp and physical complexity of the Ising spin model are entangled and contribute both to the runtine behavior in a nonlinear way.
Networks of workstations have become a popular architecture for distributedsimulation due to their high availability as opposed to specialized multiprocessor computers. Networks of workstations are also a well-suited...
详细信息
ISBN:
(纸本)076951104X;0769511058
Networks of workstations have become a popular architecture for distributedsimulation due to their high availability as opposed to specialized multiprocessor computers. Networks of workstations are also a well-suited framework for distributedsimulation systems based on the High Level Architecture (HLA). However, using workstations in a distributedsimulation system may eventually effect the availability of computing resources for the users who need their computers as working tools. Thus, for coarse grained distributedsimulation it may be desirable to let the users control to what extent their workstations should participate in a distributedsimulation. In this paper, we present a resource sharing system (RSS) that provides a client user interface on each potentially participating workstation. With the RSS clients, users of workstations can control the availability of their computer for the HLA simulation federation. An RSS manager keeps track of available computing resources and balances the participating HLA federates among the available workstations.
Optimistic techniques can improve the performance of discrete-event simulations, but one area where optimistic simulators have been unable to show performance improvement is in the simulation of parallel programs. Unf...
详细信息
ISBN:
(纸本)0769511058
Optimistic techniques can improve the performance of discrete-event simulations, but one area where optimistic simulators have been unable to show performance improvement is in the simulation of parallel programs. Unfortunately, parallel program simulation using direct execution is difficult;the use of direct execution implies that the memory and computation requirements of the simulator are at least as large as that of the target application, which restricts the target systems and application problem sizes that can be studied. Memory usage is especially important for optimistic simulators due to the need for periodic state-saving and rollback. In our research we addressed this problem and have implemented a simulation library running a Time-Warp-based optimistic engine that uses direct execution to simulate and predict the performance of parallel MPI programs while attaining good simulation speedup. For programs with data sets too large to be directly executed with our optimistic simulator, we reduced the memory and computational needs of these programs by utilizing a static task graph and code-slicing methodology, an approach which also exhibited good performance speedup.
暂无评论