This paper presents a database containing 'ground truth' segmentations produced by humans for images of a wide variety of natural scenes. We define an error measure which quantifies the consistency between segmentations of differing granularities and find that different human segmentations of the same image are highly consistent. Use of this dataset is demonstrated in two applications: (1) evaluating the performance of segmentation algorithms and (2) measuring probability distributions associated with Gestalt grouping factors as well as statistics of image region properties.

/pdf/a-database-of-human-segmented-natural-images-and-its-2ve1vk356s.pdf

A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics

https://deim.urv.cat/~alexandre.arenas/publicacions/pdf/review.pdf

Synchronization in complex networks

This survey covers rollback-recovery techniques that do not require special language constructs. In the first part of the survey we classify rollback-recovery protocols into checkpoint-based and log-based.Checkpoint-based protocols rely solely on checkpointing for system state restoration. Checkpointing can be coordinated, uncoordinated, or communication-induced. Log-based protocols combine checkpointing with logging of nondeterministic events, encoded in tuples called determinants. Depending on how determinants are logged, log-based protocols can be pessimistic, optimistic, or causal. Throughout the survey, we highlight the research issues that are at the core of rollback-recovery and present the solutions that currently address them. We also compare the performance of different rollback-recovery protocols with respect to a series of desirable properties and discuss the issues that arise in the practical implementations of these protocols.

/pdf/a-survey-of-rollback-recovery-protocols-in-message-passing-bnrpate93a.pdf

A survey of rollback-recovery protocols in message-passing systems

Parallel discrete event simulation (PDES), sometimes called distributed simulation, refers to the execution of a single discrete event simulation program on a parallel computer. PDES has attracted a considerable amount of interest in recent years. From a pragmatic standpoint, this interest arises from the fact that large simulations in engineering, computer science, economics, and military applications, to mention a few, consume enormous amounts of time on sequential machines. From an academic point of view, parallel simulation is interesting because it represents a problem domain that often contains substantial amounts of parallelism (e.g., see [59]), yet paradoxically, is surprisingly difficult to parallelize in practice. A sufficiently general solution to the PDES problem may lead to new insights in parallel computation as a whole. Historically, the irregular, data-dependent nature of PDES programs has identified it as an application where vectorization techniques using supercomputer hardware provide little benefit [14].A discrete event simulation model assumes the system being simulated only changes state at discrete points in simulated time. The simulation model jumps from one state to another upon the occurrence of an event. For example, a simulator of a store-and-forward communication network might include state variables to indicate the length of message queues, the status of communication links (busy or idle), etc. Typical events might include arrival of a message at some node in the network, forwarding a message to another network node, component failures, etc.We are especially concerned with the simulation of asynchronous systems where events are not synchronized by a global clock, but rather, occur at irregular time intervals. For these systems, few simulator events occur at any single point in simulated time; therefore parallelization techniques based on lock-step execution using a global simulation clock perform poorly or require assumptions in the timing model that may compromise the fidelity of the simulation. Concurrent execution of events at different points in simulated time is required, but as we shall soon see, this introduces interesting synchronization problems that are at the heart of the PDES problem.This article deals with the execution of a simulation program on a parallel computer by decomposing the simulation application into a set of concurrently executing processes. For completeness, we conclude this section by mentioning other approaches to exploiting parallelism in simulation problems.Comfort and Shepard et al. have proposed using dedicated functional units to implement specific sequential simulation functions, (e.g., event list manipulation and random number generation [20, 23, 47]). This method can provide only a limited amount of speedup, however. Zhang, Zeigler, and Concepcion use the hierarchical decomposition of the simulation model to allow an event consisting of several subevents to be processed concurrently [21, 98]. A third alternative is to execute independent, sequential simulation programs on different processors [11, 39]. This replicated trials approach is useful if the simulation is largely stochastic and one is performing long simulation runs to reduce variance, or if one is attempting to simulate a specific simulation problem across a large number of different parameter settings. However, one drawback with this approach is that each processor must contain sufficient memory to hold the entire simulation. Furthermore, this approach is less suitable in a design environment where results of one experiment are used to determine the experiment that should be performed next because one must wait for a sequential execution to be completed before results are obtained.

/pdf/parallel-discrete-event-simulation-m759whzicd.pdf

Parallel discrete event simulation

A number of library based parallel and sequential network simulators have been designed. The paper describes a library, called GloMoSim (Global Mobile system Simulator), for parallel simulation of wireless networks. GloMoSim has been designed to be extensible and composable: the communication protocol stack for wireless networks is divided into a set of layers, each with its own API. Models of protocols at one layer interact with those at a lower (or higher) layer only via these APIs. The modular implementation enables consistent comparison of multiple protocols at a given layer. The parallel implementation of GloMoSim can be executed using a variety of conservative synchronization protocols, which include the null message and conditional event algorithms. The paper describes the GloMoSim library, addresses a number of issues relevant to its parallelization, and presents a set of experimental results on the IBM 9076 SP, a distributed memory multicomputer. These experiments use models constructed from the library modules.

GloMoSim: a library for parallel simulation of large-scale wireless networks

Challenges such as understanding sustainable urban development require modeling interdependencies and interactions among systems. The High Level Architecture (HLA) provides an approach to studying these aspects by integrating separately developed simulations in a distributed computing environment. These applications require coupling interdependent simulations and sequencing their execution to ensure certain data dependence requirements are met. An approach to specifying the proper sequence of execution of interdependent simulations using SysML sequence diagrams is proposed. A means to implement these specifications by automatically generating code using HLA's time management services is described. This approach is demonstrated through the creation of a federated simulation to model interactions among land use, transportation, and transit in the San Diego area by integrating widely used simulators such as UrbanSim and MATSim.

An approach to integrate inter-dependent simulations using HLA with applications to sustainable urban development

Network emulation has been widely used to aid in the development and evaluation of real-time applications. Traditional emulation tools based on a single node machine or a cluster of machines cannot satisfy today's requirements for testing real-time applications distributed over wide area networks. ROSENET (RemOte SErver-based Network EmulaTion) is a network emulation approach that exploits a remote high-fidelity simulation to provide scale and accuracy for a low-fidelity emulator serving a locally executing real-time application. This paper evaluates the performance of an implementation of ROSENET using the NIST Net emulator and GTNetS simulator. Experimental results examining end-to-end delay and loss show that ROSENET provides a promising approach to network emulation supporting accuracy and scale while meeting real-time constraints.

Performance Evaluation of the ROSENET Network Emulation System

The question of the energy consumed by synchronization algorithms for distributed simulation programs is addressed. The concept of zero energy synchronization is introduced wherein a distributed simulation program incurs no additional energy cost for synchronization. A theoretical approach to achieving zero energy synchronization using an oracle is described. An energy efficient implementation of the YAWNS algorithm, termed Low Energy YAWNS (LEY) is presented. It is shown that LEY can yield, in principle, zero energy synchronization for many classes of applications. Preliminary experimental results are presented showing that LEY achieves significantly less energy consumption compared to a conventional implementation of YAWNS that does not consider energy use as a design goal. Further, these experimental results indicate that LEY achieves energy consumption only modestly greater than that of an execution of the same application using an oracle for the test cases that were examined. These results suggest that it may be feasible to develop practical distributed simulation synchronization algorithms that approach zero energy synchronization.

https://dl.acm.org/doi/pdf/10.1145/3200921.3200938

Zero Energy Synchronization of Distributed Simulations

It has been observed that many networks arising in practice have skewed node degree distributions. Scale-free networks are one well-known class of such networks. Achieving efficient parallel simulation of scale-free networks is challenging because large-degree nodes can create bottlenecks that limit performance. To help address this problem we describe an approach called link partitioning where each network link is mapped to a logical process (LP) in contrast to the conventional approach of mapping each network node to an LP. Link partitioning is discussed in the context of packet-level simulations of telecommunication networks. The parallelism of link partitioning relative to node partitioning is examined in terms of an idealized execution using the well-known YAWNS synchronization algorithm. Further, a critical path analysis suggests that there is much more parallelism available in these simulations than can be exploited using the YAWNS algorithm.

Link Partitioning in Parallel Simulation of Scale-Free Networks

Ad hoc distributed simulations are constructed by embedding online simulations into a network of sensors. Recent work examining the effectiveness of ad hoc distributed simulations in modeling open queueing networks has been limited to a specific network configuration. This paper examines the accuracy of the ad hoc approach more broadly for open queueing networks. First, we identify conditions where the ad hoc approach will yield accuracy comparable to traditional replicated simulations. For cases where these conditions do not apply, we propose a "buffered-area" mechanism to improve the accuracy of system performance estimates. Empirical evidence is presented showing that this mechanism helps achieve a substantial bias reduction with a moderate increase in execution time.

Richard M. Fujimoto

Papers

An approach to integrate inter-dependent simulations using HLA with applications to sustainable urban development

Performance Evaluation of the ROSENET Network Emulation System

Zero Energy Synchronization of Distributed Simulations

Link Partitioning in Parallel Simulation of Scale-Free Networks

On the Accuracy of Ad Hoc Distributed Simulations for Open Queueing Network