Parallel Discrete Event Simulation Research Articles

Behavior-aware Probabilistic Synchronization in Parallel Simulations and the Influence of the Simulation Model

Efficient event scheduling and synchronization constitutes an essential part of high-performance parallel discrete event simulation. Traditional synchronization approaches like conservative and optimistic synchronization focus on a simple scheduling paradigm based on a primitive set of rules. However, we argue that a sophisticated synchronization algorithm considering event interactions can remarkably improve the performance of the simulation. In this article, we discuss three different heuristics which analyze those dependencies online and speed up the simulation by a factor of up to 6.5. Further, we analyze the ability of this paradigm to automatically detect available parallelism by applying it to scenarios featuring different degrees of available parallelism.

Fine-Grained Parallel and Distributed Spatial Stochastic Simulation of Biological Reactions

Fine-Grained Parallel and Distributed Spatial Stochastic Simulation of Biological Reactions

Improving performance of the STochastic Engine for Pathway Simulation (STEPS)

STEPS (http://steps.sourceforge.net) is a GNU-licensed simulation platform that uses an extension of Gillespie's SSA [1] to deal with reactions and diffusion of molecules in 3D reconstructions of neuronal morphology and tissue [2]. In STEPS, the diffusion of molecules is simulated as diffusive fluxes between tetrahedral elements in the mesh, represented by a series of first-order reactions. STEPS has been used in various research projects where its overall performance was considered adequate. However, as more complex models are being developed and investigated, total model simulation times became an issue leading to requests for a faster reaction-diffusion simulator. Here we discuss a number of strategies we have followed to improve STEPS performance at different levels. The previous implementation of STEPS adapted Gibson and Bruck’s enhancement of the Direct method [3] with a k-ary tree structure. The overall complexity of searching and updating of this method is O(logkN), giving N as the total number of kinetic processes in the system and k as the branch width of the tree. Although this is a great improvement comparing to the O(N) complexity of Gillespie’s original method, the logarithmic dependency of N becomes a critical limitation of performance, particularly in simulations with high amount of tetrahedral elements and consequently large N. Recently a constant-time version of the Direct method with a slightly more complex data structure has been introduced [4], providing an attractive searching and updating complexity of O(1), independent of N. This method is implemented in the new version of STEPS. In the poster, I will present the validation of the new simulator by comparing the stochastic simulation results with analytical solutions. I will also present the improvement made by adapting the new method. Several approaches to parallelizing STEPS have been investigated. In a realistic simulation, the state of the system, including molecule distribution, reaction/diffusion rates, may be frequently read and/or modified during the simulation. Some of these operations could be greatly parallelized in shared memory architecture, efficiently reducing the cost of data accessing. Previous studies [5] also suggested that the Direct SSA could be parallelized as a Parallel Discrete-Event Simulation (PDES). However, the performance of such a parallelization significantly depends on the model itself as well as the approach of simulation decomposition. Some examples of above methods will be present and discussed in the poster.

Multicore acceleration of Discrete Event System Specification systems

Parallel discrete-event simulation on heterogeneous multicore platforms requires innovative redesign of existing algorithms in return for better performance. Based on the Discrete Event System Specification (DEVS) methodology, a technique called Multicore Acceleration of DEVS Systems is proposed for efficient parallel discrete-event simulation on the IBM Cell processor. The technique combines multi-grained parallelism and various optimizations to overcome performance bottlenecks, while hiding the technical details of multicore programming from non-expert users. By explicitly exploiting the data- and event-level parallelism inherent in the simulation, the technique significantly accelerates both memory-bound and compute-bound computational kernels in demanding parallel DEVS simulations, as shown in the experimental results. Several key concepts and methods derived from this research can also be applied to other multicore and shared-memory architectures.

Optimal topology for parallel discrete-event simulations

The effect of shortcuts on the task completion landscape in parallel discrete-event simulation (PDES) is investigated. The morphology of the task completion landscape in PDES is known to be described well by the Langevin-type equation for nonequillibrium interface growth phenomena, such as the Kardar-Parisi-Zhang equation. From the numerical simulations, we find that the root-mean-squared fluctuation of task completion landscape, W(t,N), scales as W(t→∞,N)~N when the number of shortcuts, ℓ, is finite. Here N is the number of nodes. This behavior can be understood from the mean-field type argument with effective defects when ℓ is finite. We also study the behavior of W(t,N) when ℓ increases as N increases and provide a criterion to design an optimal topology to achieve a better synchronizability in PDES.

Abstract Next Subvolume Method: A logical process-based approach for spatial stochastic simulation of chemical reactions

AbstractThe spatial stochastic simulation of biochemical systems requires significant calculation efforts. Parallel discrete-event simulation is a promising approach to accelerate the execution of simulation runs. However, achievable speedup depends on the parallelism inherent in the model. One of our goals is to explore this degree of parallelism in the Next Subvolume Method type simulations. Therefore we introduce the Abstract Next Subvolume Method, in which we decouple the model representation from the sequential simulation algorithms, and prove that state trajectories generated by its executions statistically accord with those generated by the Next Subvolume Method. The experimental performance analysis shows that optimistic synchronization algorithms, together with careful controls over the speculative execution, are necessary to achieve considerable speedup and scalability in parallel spatial stochastic simulation of chemical reactions. Our proposed method facilitates a flexible incorporation of different synchronization algorithms, and can be used to select the proper synchronization algorithm to achieve the efficient parallel simulation of chemical reactions.

Java for parallel discrete event simulation: a survey

Since the early 1990s, when it was first released, Java has become one of the most widespread programming languages. Discrete Event Simulation (DES) and also Parallel Discrete Event Simulation (PDES) have attracted more and more projects which are Java–based. This paper presents a brief survey on the tools and facilities that make Java such an attractive option for parallel simulation developers. Nevertheless, several drawbacks and lacks of the language are also exposed.

An efficient optimistic time management algorithm for discrete-event simulation system

Time Wrap algorithm is a well-known mechanism of optimistic synchronization in a parallel discrete-event simulation (PDES) system. It offers a run time recovery mechanism that deals with the causality errors. For an efficient use of rollback, the global virtual time (GVT) computation is performed to reclaim the memory, commit the output, detect the termination, and handle the errors. This paper presents a new unacknowledged message list (UML) scheme for an efficient and accurate GVT computation. The proposed UML scheme is based on the assumption that certain variables are accessible by all processors. In addition to GVT computation, the proposed UML scheme provides an effective solution for both simultaneous reporting and transient message problems in the context of synchronous algorithm. To support the proposed UML approach, two algorithms are presented in details, with a proof of its correctness. Empirical evidence from an experimental study of the proposed UML scheme on PHOLD benchmark fully confirms the theoretical outcomes of this paper. (Received in June 2009, accepted in April 2010. This paper was with the authors 5 months for 3 revisions.)

On the Scalability and Dynamic Load-Balancing of Optimistic Gate Level Simulation

As proscribed by Moore's law, the size of integrated circuits has grown geometrically, resulting in simulation becoming the major bottleneck in the circuit design process. Parallel simulation provides us with a way to cope with this growth. In this paper, we describe an optimistic (time warp) parallel discrete event simulator which can simulate all synthesizeable Verilog circuits. We investigate its scalability and describe a machine learning based dynamic load balancing algorithm for use with the simulator. We initially developed two dynamic load balancing algorithms to balance the load and the communication, respectively, during the course of a simulation. Making use of reinforcement learning (RL), we then created an algorithm which is an amalgam of these two algorithms. To the best of our knowledge, this is the first time that RL has been used for the dynamic load-balancing of time warp. We investigated the scalability and the effectiveness of the dynamic load balancing algorithms on gate level simulations of several realistic very large scale integration (VLSI) circuits. Our experimental results showed that our simulator is indeed scalable. They also reveled a 88.6% improvement in the simulation time through the use of our RL algorithm.

Predicting the behavior of large scale P2P systems by parallel discrete event simulation

P2P systems are becoming the dominator of Internet. Such systems are typically composed of thousands to millions of physical computers, which make it difficult to predict their behaviors without a large scale distributed system simulator. This paper is an attempt to predict the behavior of large scale P2P systems by building a novel parallel simulator: AegeanSim, which provides parallel discrete event simulation of such systems on high performance server clusters. We abstract the execution of P2P applications with a specific event model, and parallel the simulation of events in a cluster, thus expanding the simulation scale and boosting the simulation process dramatically. A 1-stage synchronization method is proposed to improve the performance. An event callback interface is designed to implement their application logic easily while keeping the simulator application-independent. We use AegeanSim to predict the behavior of a typical P2P system: BitTorrent. By comparing the simulation behavior of BT with that of related BT studies and verifying its efficiency, scalability and accuracy, we make predictions about the behavior of BT system assuming they are assaulted by different man-made system attacks. Some reasonable results are found: (1) Tracker isolation can hardly work because of its short attacking time window. (2) Limiting the bandwidth of BT may be an efficient way to control it.

A Dynamic Partitioning Algorithm Based on Approximate Local Search for Optimistic Parallel Discrete Event Simulation

With the rise of simulation platforms which support efficiently migration,the dynamic partitioning mechanism can significantly improve performance of the PDES.How to estimate and optimize the communication structure becomes an essential research topic for dynamic partitioning.Currently,there are several dynamic partitioning algorithms.Since they consider computation and communication load balancing isolated,these algorithms may suffer under complex application background.This paper formalizes the dynamic partitioning problem statement which combine both computation and communication load balancing,and proposes an algorithm based on approximate local search,which obtains a solution with value no smaller than(1-1/|N|)(1-e)of the optimal solution value in polynomial time complexity.The experiments show that the algorithm has high performance and low overhead.

Parallel and Distributed Simulation of Ad Hoc Networks

Modeling and simulation are traditional methods used to evaluate wireless network design. This paper addresses issues associated with the application of parallel discrete event simulation to mobile ad hoc networks design and analysis. The basic characteristics and major issues pertaining to ad hoc networks modeling and simulation are introduced. The focus is on wireless transmission and mobility models. Particular attention is paid to the MobASim system, a Javabased software environment for parallel and distributed simulation of mobile ad hoc networks. We describe the design, performance and possible applications of presented simulation software.

The Triangular Pyramid Scheduling Model and algorithm for PDES in Grid

Grid is a perfect environment for the large scale Parallel Discrete Event Simulation (PDES), because its distribution and collaboration features match the PDES applications well. The PDES tasks or applications are modeled as a Directed Acyclic Graph (DAG), in which the simulation resources consist of three critical factors, simulation hosting machine (SHM), simulation service (SS) and simulation data (SD) in Grid environment. By solving the model we attempt to obtain an optimized triangular matching of the simulation resources on Grid, so that it can support the PDES activities better. We name the algorithm of solving the model Triangular Pyramid Scheduling (TPS). The PDES DAG is divided into three basic graph structures: Sequential structure, Fork structure, and Join structure. The TPS algorithm is developed based on these graph structures. The simulation results show that TPS algorithm can reduce the makespan and congestion, improve the simulation efficiency, and increase the resource utilization efficiency, compared to the existing algorithms.

An Efficient Statistical Synchronization Method For Parallel Simulation

In this paper, we propose the improved Statistical Synchronization Method (SSM-T) for parallel discrete event simulation. Criteria are given for the time-driven approach (SSM-T). It is proven that the level of the output error can be guaranteed. SSM-T is implemented in the OMNeT++ discrete event simulation tool, which is a useful and widespread framework for creating various simulation models to evaluate the performance of telecommunication networks. Case studies have been performed, which shows that SSM-T is a very efficient synchronization method for the parallel simulation of communication networks.

Analysing probabilistically constrained optimism

AbstractIn previous work we presented the DTRD algorithm, an optimistic synchronization algorithm for parallel discrete event simulation of multi‐agent systems, and showed that it outperforms Time Warp and time windows on a range of test cases. DTRD uses a decision‐theoretic model of rollback to derive an optimal time to delay read event so as to maximize the rate of LVT progression. The algorithm assumes that the inter‐arrival times (both virtual and real) of events are normally distributed. In this paper we present a more detailed evaluation of the DTRD algorithm, and specifically how the performance of the algorithm is affected when the inter‐arrival times do not follow the assumed distributions. Our analysis suggests that the performance of the algorithm is relatively insensitive to events whose inter‐arrival times are not normally distributed. However, as the variance of event inter‐arrival times increases, its performance degrades to that of Time Warp. The evaluation approach we present is generally applicable, and we sketch how a similar analysis may be performed for two other decision‐theoretic optimistic synchronization algorithms. Copyright © 2009 John Wiley & Sons, Ltd.

Parallel discrete event simulation on desktop grid computing infrastructures

In contrast to traditional Parallel Discrete Event Simulation (PDES) systems using dedicated machines, an alternative master/worker approach for high throughput execution on shared computing platforms is proposed. Master/worker systems offer potential advantages over traditional PDES systems such as better support for heterogeneous machines, client-driven load balancing, fault tolerance, and execution on non-dedicated machines. We examine feasibility of executing PDES codes on master/worker systems. We characterise application properties that are important for efficient execution and define suitable performance metrics. The Aurora Parallel and Distributed Simulation System utilising the master/worker approach is described along with performance measurements in executing conservative PDES codes.

Object-oriented Design Patterns for Parallel Discrete Event Simulation of Distributed Control Systems

Distributed control systems (DCS) consist of many sensors/actuators and a network interconnecting them, and are being introduced in various automation areas. For assuring the control performance of a DCS under heavy communication traffic, the precise simulation of the DCS is strongly needed. For this purpose, we propose a uniform, efficient and systematic method based on object-oriented design patterns for modeling and simulating DCSs. In this paper, two design patterns are newly proposed; Time-Warp pattern and Protocol pattern. Time-Warp pattern describes classes and interaction for executing the DCS simulation by communicating events having send/receive times, using Time Warp mechanism. Protocol pattern describes classes and interaction for uniformly structuring various communication protocol models used in DCSs, which are composed of the interactions among several layers and the state transition of each layer in a communication protocol. Finally, the effectiveness of the DCS simulator which is developed using these patterns was proved by comparing simulation results with the experiment results using the real DCS consisting of four CAN-based control nodes.

Multiprogrammed non-blocking checkpoints in support of optimistic simulation on myrinet clusters

CCL (checkpointing and communication library) is a software layer in support of optimistic parallel discrete event simulation (PDES) on myrinet-based COTS clusters. Beyond classical low latency message delivery functionalities, this library implements CPU offloaded, non-blocking (asynchronous) checkpointing functionalities based on data transfer capabilities provided by a programmable DMA engine on board of myrinet network cards. These functionalities are unique since optimistic simulation systems conventionally rely on checkpointing implemented as a synchronous, CPU-based data copy. Releases of CCL up to v2.4 only support monoprogrammed non-blocking checkpoints. This forces re-synchronization between CPU and DMA activities, which is a potential source of overhead, each time a new checkpoint request must be issued at the simulation application level while the last issued one is still being carried out by the DMA engine. In this paper we present a redesigned release of CCL (v3.0) that, exploiting hardware capabilities of more advanced myrinet clusters, supports multiprogrammed non-blocking checkpoints. The multiprogrammed approach allows higher degree of concurrency between checkpointing and other simulation specific operations carried out by the CPU, with benefits on performance. We also report the results of the experimental evaluation of those benefits for the case of a Personal Communication System (PCS) simulation application, selected as a real world test-bed.

Optimistic Simulations of Physical Systems Using Reverse Computation

Efficient computer simulation of complex physical phenomena has long been challenging due to their multiphysics and multiscale nature. In contrast to traditional time-stepped execution methods, the authors describe an approach using optimistic parallel discrete event simulation (PDES) and reverse computation techniques to execute plasma physics codes. They show that reverse computation-based optimistic parallel execution can significantly reduce the execution time of an example plasma simulation without requiring a significant amount of additional memory compared to conservative execution techniques. The authors describe an application-level reverse computation technique that is efficient and suitable for complex scientific simulations.

Cancellation strategy in rollback mechanism

Rollback is a synchronization mechanism in optimistic parallel discrete event simulation (PDES). A basic and popular realization of rollback is based on cancellation of error executed messages. In this paper, several cancellation strategies are introduced, and a new method proposed. Performance comparison is made based on experimental results.