Many systems rely on the ability to rollback (or restore) parts of the system state to undo or recover from undesired or erroneous computations. Examples of such systems include fault tolerant systems with checkpointing, editors with undo capabilities, transaction and data base systems and optimistically synchronized parallel and distributed simulations. An essential part of such systems is the state saving mechanism. It should not only allow efficient state saving, but also support efficient state restoration in case of roll back. Furthermore, it is often a requirement that this mechanism is transparent to the user. In this paper we present a method to implement a transparent incremental state saving mechanism in an optimistically synchronized parallel discrete event simulation system based on the Time Warp mechanism. The usefulness of this approach is demonstrated by simulations of large, detailed, realistic FCA and a DCA-like cellular phone systems. 1. Introduction Many systems rel...

Abstract not found

In the past decade, parallel processing has gained very significant advances in all fronts of the theory, systems, and applications. However, despite years of research and its apparent significance, parallel simulation remains a major outstanding challenge. In particular, there has been no simulation system which facilitates an early prediction of the program performance. In this report, we document a survey of the major existing approaches for parallel simulation as well as a comparative study of two leading computational models, namely, Valiant's BSP and Leiserson's Cilk, which are useful formal models for performance prediction of simulation programs. 1 Introduction Simulation has been heavily relied upon by computer scientists, physicists, circuit designers, mathematicians, military force, and even video game designers [LK91, Fis95, Chi92]. For decades, simulationists have been devising simulation models for large and complex systems to facilitate performance analysis, stud...

In the last three decades a considerable amount of research has been pursued in the efficient implementation of the pending event set (PES) associated with discrete-event simulation. The reason is simple: a fast event management has a very crucial impact in the total running time of both sequential and parallel simulations. This report focuses on this problem by studying the empirical performance of a number of solutions to the PES implementation in which we include a complete binary tree described in [26], 1 Introduction The PES is defined as the set of all the events generated during a discrete-event simulation and whose occurrence have not been simulated yet. In order to determine the next event to take place, it is necessary to extract the event with the least time from the PES. We call this operation extract-min. On the other hand, the occurrence of any event during the simulation can produce the insertion of new pending or future events in the PES; insert operation. These two b...

this paper we study the performance of the very first tournament based complete binary tree. We focus on discrete-event simulation and our results show that this unknown predecessor of heaps can be a more efficient alternative to the fastest pending event set implementations reported in the literature. We also extend the idea of binary tournaments to a (2; L)-tournament structure which exhibits the property of delaying the processing of events with larger timestamps whilst it keeps similar theoretical performance bounds to the native (2; 1)-structure or CBT. This property can be certainly useful in systems where many pending events are expected to be deleted or rescheduled during the simulation. 2 Tournament trees

This paper proposes a novel Lightweight Time Warp (LTW) protocol for high-performance parallel optimistic simulation of large-scale DEVS and Cell-DEVS models. By exploiting the characteristics of the simulation process, the protocol is able to set free most logical processes (LPs) from the Time Warp mechanism, while the overall simulation still executes optimistically, driven by only a few full-fledged Time Warp LPs. The LTW protocol includes a rule-based event-scheduling mechanism using two types of event queues, an aggregated state-saving technique for optimal risk-free state management, and a new rollback algorithm that recovers lightweight LPs from causality errors without sending anti-messages. The impact on global control mechanisms such as GVT computation, fossil collection, and load migration is also discussed. The basic concepts of the protocol could also apply to a broad range of Time Warp systems under certain conditions and with appropriate control over the LPs. 1.

The bulk-synchronous parallel (BSP) model of computing has been proposed to enable the development of portable software which achieves scalable performance across diverse parallel architectures. A number of applications of computing science have been demonstrated to be efficiently supported by the BSP model in practice.

Efficient management of events lists is important in optimizing discrete event simulation performance. This is especially true in distributed simulation systems. The performance of simulators is directly dependent on the event list management operations such as insertion, deletion, and search. Several factors such as scheduling, checkpointing, and state management influence the organization of data structures to manage events efficiently in a distributed simulator. In this paper, we present a new organization for input event queues, called append-queues, for an optimistically synchronized parallel discrete-event simulator. Append-queues exploits the fact that events exchanged between the distributed simulators are generated in sequences with monotonically increasing time orders. A comparison of append-queues with an existing multi-list organization is developed that uses both analytical and experimental analysis to show the event management cost of different configurations. The comparison shows performance improvements ranging from 3% to 47% for the applications studied.

Parallel discrete event simulation (PDES) is efficient in simulating a large digital circuit. In this dissertation, two techniques are proposed to improve the performance of PDES in logic simulation. One is a partitioning algorithm and the other is a hybrid parallel simulation protocol. Experiments were performed to demonstrate that the two proposed techniques together provide significant reduction in parallel simulation time. Unlike most other partitioning algorithms, the proposed partitioning algorithm preserves circuit concurrency by assigning circuit gates that can be evaluated at about the same time to different processors. As a result, the concurrency preserving partitioning (CPP) algorithm can provide instantaneous load balancing, instead of only aggregated load balancing, throughout the period of a parallel simulation. This is especially important when the algorithm is used together with a Time Warp simulation where a high degree of concurrency can lead to fewer rollbacks and better performance. In addition, a new concurrency metric is proposed to evaluate partitioning algorithms before the execution of parallel simulations. Even though PDES can reduce the logic simulation time for large circuits considerably, it generates more events than necessary for certain high activity circuits and produces inconsistent speedup over different circuits. The proposed Event Lookahead Time Warp (ETW) algorithm can look ahead and combine and execute multiple events at each gate optimistically so that the probability of unnecessary events can be reduced. As a result, it can reduce rollback cost, obtain better load balance, and achieve more consistent execution times and reasonable speedups.

ii CONTENTS