Discrete-event simulation and the event horizon

Steinman, Jeff S.

doi:10.1145/195291.182490

Cited by 14 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar transient periods occur in the synthetic experiments before the distribution of events in the event set has stabilized. This phenomenon has been analytically studied in the context of the hold model by Vaucher [1977] and Steinman [1994], respectively. These studies show that the distribution of the events in the queue under the hold model eventually reaches a steady state that is entirely determined by the priority increment distribution.…”

Section: Access Patternsmentioning

confidence: 99%

A comparative study of parallel and sequential priority queue algorithms

Rönngren

Ayani

1997

ACM Trans. Model. Comput. Simul.

View full text Add to dashboard Cite

Priority queues are used in many applications including real-time systems, operating systems, and simulations. Their implementation may have a profound effect on the performance of such applications. In this article, we study the performance of well-known sequential priority queue implementations and the recently proposed parallel access priority queues. To accurately assess the performance of a priority queue, the performance measurement methodology must be appropriate. We use the Classic Hold, the Markov Model, and an Up/Down access pattern to measure performance and look at both the average access time and the worst-case time that are of vital interest to real-time applications. Our results suggest that the best choice for priority queue algorithms depends heavily on the application. For queue sizes smaller than 1,000 elements, the Splay Tree, the Skew Heap, and Henriksen's algorithm show good average access times. For large queue sizes of 5,000 elements or more, the Calendar Queue and the Lazy Queue offer good average access times but have very long worst-case access times. The Skew Heap and the Splay Tree exhibit the best worst-case access times. Among the parallel access priority queues tested, the Parallel Access Skew Heap provides the best performance on small shared memory multiprocessors.

show abstract

Section: Access Patternsmentioning

confidence: 99%

A comparative study of parallel and sequential priority queue algorithms

Rönngren

Ayani

1997

ACM Trans. Model. Comput. Simul.

View full text Add to dashboard Cite

show abstract

“…Thus for m large enough the efficiency is close to 1. For exponential distribution, rn ~ 5x/~ [5,9]. Define D = N/P.…”

Section: /(E[b]-e[a])mentioning

confidence: 99%

“…Approaches based on the event-horizon concept [9] like Breathing Time Buckets [8], advance in simulation time in a synchronous manner by consuming supersteps as in figure 1.a. Note that here we do not consider the additional supersteps required for min-reductions which compute a new global event-horizon on each cycle.…”

mentioning

confidence: 99%

Asynchronous (Time-Warp) versus synchronous (Event-Horizon) simulation time advance in BSP

Marín

1998

Euro-Par’98 Parallel Processing

View full text Add to dashboard Cite

This paper compares the very fundamental concepts behind two approaches to optimistic parallel discrete-event simulation on BSP computers [10]. We refer to (i) asynchronous simulation time advance as it is realised in the BSP implementation of Time Warp [3], and (ii) synchronous time advance as it is realised in the BSP implementation of Breathing Time Buckets [8]. Our results suggest that asynchronous time advance can potentially lead to more efficient and scalable simulations in BSP. IntroductionAs BSP is a (bulk) synchronous model of parallel computing [10], the obvious method of parallel discrete-event simulation [2, 7] on BSP computers seems to be synchronisation protocols based on synchronous time advance, such as Breathing Time Buckets [8]. In this paper we show that using synchronous time advance on a BSP computer might not be a good idea for two reasons. Firstly, synchronous simulation methods force the execution of periodical parallel minreductions during which no interesting advance in simulation time can be made. These operations take some number ofBSP supersteps to complete [10], and the simulation is stopped during their execution. The cumulative cost of these operations is relevant since the total number of min-reductions is equal to the total number of supersteps used to process the simulation events. Secondly and more importantly, synchronous methods impose barriers in simulation time which tend to reduce the rate of time advance per superstep of the simulation. This increases the total number of supersteps dedicated to parallel event-processing. Equivalently, time barriers tend to decrease the number of events that are processed in each superstep.In BSP, supersteps are delimited by the barrier synchronisation of all the processors. In turn this operation takes some amount of reM time to complete and it can become comparatively expensive in simulation models where the amount of computation involved in the processing of events is small (e.g., queuing networks). As many real life simulations can easily demand the execution of hundreds of thousands of event-processing supersteps, a significant reduction of the total number of supersteps can also cause a significant reduction of the total running time of the simulation. In addition, the cost of the remaining barrier

show abstract

“…For each run of our experiment, the number of hold operations (an enqueue followed by a dequeue operation) done is 100 times the queue size. The large number of operations done is used to provide a long enough simulation time for a more accurate average performance 2 measure [9,10]. Measurement for the hold model is only taken when the size is held constant.…”

Section: Benchmarking and Resultsmentioning

confidence: 99%

FELT: A Far Future Event List Structure Optimized for Calendar Queues

Hui

Thng

2002

SIMULATION

View full text Add to dashboard Cite

Calendar queues (CQ) are often employed in discrete event simulators to store pending events. They can achieve O(1) access time as long as the CQ resizes often enough to ensure that events are not skewed but evenly distributed in the queue structure. However, a resize operation would involve creating a new CQ structure and then moving each item from the old CQ to the new CQ before discarding the old CQ. Hence, such resizes can be costly if the size of the queue is very large. This article proposes a new secondary queuing structure that complements the primary CQ structure. Known as FELT (far future event leaf tree), the secondary FELT structure is a lazy queue (i.e., semisorted) structure that manages events that are considered to be too far away to be considered in the primary CQ structure. The FELT structure is shown to be far superior than the dynamic lazy calendar queue. Downloaded from 1. By overhead costs, we mean the queue maintenance costs that are above the basic enqueue and dequeue costs. . His research interests include very high-speed digital communications, array signal processing, provision of quality of service for handoffs in wireless cellular networks, and the development of high speed network simulators.

show abstract

Discrete-event simulation and the event horizon

Cited by 14 publications

References 13 publications

A comparative study of parallel and sequential priority queue algorithms

A comparative study of parallel and sequential priority queue algorithms

Asynchronous (Time-Warp) versus synchronous (Event-Horizon) simulation time advance in BSP

FELT: A Far Future Event List Structure Optimized for Calendar Queues

Contact Info

Product

Resources

About