Ibis' is a programming environment for the development of grid applications in Java. We aim to support a wide range of applications and parallel platforms, so our example programs should also go beyond small bench...
详细信息
ISBN:
(纸本)3540287000
Ibis' is a programming environment for the development of grid applications in Java. We aim to support a wide range of applications and parallel platforms, so our example programs should also go beyond small benchmarks, In this paper we describe a number of larger applications we have developed to evaluate Ibis' suitability for writing grid applications: a cellular automata simulator, a solver for the Satisfiability problem, and grammar-based text analysis. We give an overview of the applications, we describe their implementation, and we show performance results on a number of parallel platforms, ranging from a large supercomputer cluster to a real global grid testbed. Since all of these applications require communication between the processors during execution, it is not surprising that a supercomputer cluster proved to be the most effective platform. However, all of our applications were also efficient on a wide-area cluster system, and some of them even on a grid testbed. Since grid systems are usually only used for trivially parallel systems, we consider these results an encouraging sign that Ibis is indeed an effective environment for grid computing. In particular because for two of the three of the applicationsthe parallelisation required very little additional program code.
Network security technology has become crucial in protecting government and industry computing infrastructure. Modern intrusion detection applications face complex requirements - they need to be reliable, extensible, ...
详细信息
Scientists are increasingly using large distributed systems built from commodity off-the-shelf components to perform scientific computation. Grid computing has expanded the scale of such systems by spanning them acros...
详细信息
ISBN:
(纸本)3540287000
Scientists are increasingly using large distributed systems built from commodity off-the-shelf components to perform scientific computation. Grid computing has expanded the scale of such systems by spanning them across organizations. While such systems are cost-effective, the usage of large number of commodity components causes high fault and failure rates. Some of these faults result in silent data corruption leaving users with possibly incorrect results. In this work, we analyzed the faults and failures that occurred in Condor pools at UW-Madison having a few thousand CPUs and in two large distributedapplications: US-CMS and BMRB BLAST, each of which used hundreds of thousands of CPU hours. We propose 'silent-fail-stutter' fault-model to correctly model the silent failures and detail how to handle them. Based on the model, we have designed mechanisms that automatically detect and handle silent failures and ensure that users get correct results. Our mechanisms perform automated fault location and can transparently adapt applications to avoid faulty machines. We also designed a data provenance mechanism that tracks the origin of the results, enabling scientists to selectively purge results from faulty components.
the contribution of this paper is to present a novel and well-experimented middleware service platform and its architecture for service gateway based distributed systems. this is called the MidGate platform. the resea...
详细信息
the contribution of this paper is to present a novel and well-experimented middleware service platform and its architecture for service gateway based distributed systems. this is called the MidGate platform. the research problem that the MidGate platform addresses is how to facilitate the development of interoperable applications into heterogeneous and distributed service gateway based environments. the paper is based on the constructive method of analyzing the related research results, technologies, and trial systems. the MidGate platform is a middleware platform that provides communication middleware, a set of generic service elements, and a dynamically reconfigurable service framework to be applied in the development and deployment of distributedapplications. the MidGate architecture is defined on the basis of the requirements of real applications, and it is evaluated in a series of laboratory prototypes reviewed in the paper.
Internet computing and grid technologies promise to change the way we tackle complex problems. they will enable large-scale aggregation and sharing of computational, data and other resources across institutional bound...
详细信息
ISBN:
(纸本)0769522491
Internet computing and grid technologies promise to change the way we tackle complex problems. they will enable large-scale aggregation and sharing of computational, data and other resources across institutional boundaries. As grid computing is becoming a reality, there is a need for managing and monitoring the available resources worldwide, as well as the need for conveying these resources to the everyday user. this paper describes a resource broker with its main function as to match the available resources to the user's needs. the use of the resource broker provides a uniform interface to access any of the available and appropriate resources using user's credentials. the resource broker runs on top of the Globus toolkit. therefore, it provides security and current information about the available resources and serves as a link to the diverse systems available in the grid.
the main objective of this paper is to propose a homogeneous approach to represent and process in silico models for predictive toxicology and also to improve the computational representation of developed models by har...
详细信息
the main objective of this paper is to propose a homogeneous approach to represent and process in silico models for predictive toxicology and also to improve the computational representation of developed models by harmonizing new trends in predictive data mining. We propose to combine local and global models as ensemble experts by mixing technologies in hybrid systems in order to improve the prediction accuracy, and also to provide reasonable training response time by using parallel processing. More investigations have still to be done to develop an optimized strategy, but our approach demonstrates encouraging results.
Popular network simulation tools, such as ns-2, are useful for undertaking experiments with emerging networking technologies. As networked applications become distributed at scales comparable to the Internet, such as ...
详细信息
Popular network simulation tools, such as ns-2, are useful for undertaking experiments with emerging networking technologies. As networked applications become distributed at scales comparable to the Internet, such as peer-to-peer applications, testing and experimentation becomes increasingly difficult and important. Withthis paper, we are introducing an elaborate extension to existing simulation capabilities by allowing realistic highly distributed application prototypes to be attached to a simulator for transparent testing and experimentation. We enable developers to focus on building their applications rather than detailing simulation scripts. Testing can then be performed in a natural setting. PDNS is a parallel and distributed version of the commonly used ns-2 simulation package. We describe our extensions to the PDNS simulator which allow real application prototypes to be run across a simulated network. We describe our use of virtualisation as a means for sending an application's network traffic through the simulator. Our implementation allows for large scale simulations withthousands of real peers and hundreds of thousands of simulated nodes in a network, thus we can test real peer-to-peer software at large scales.
In this paper we study two important problems - coverage-boundary detection and implementing distributed hash tables in ad-hoc wireless networks. these problems frequently arise in service location and relocation in w...
详细信息
ISBN:
(纸本)0769521525
In this paper we study two important problems - coverage-boundary detection and implementing distributed hash tables in ad-hoc wireless networks. these problems frequently arise in service location and relocation in wireless networks. For the centralized coverage-boundary problem we prove a Omega(n log n) lower bound for n devices. We show that both problems can be effectively reduced to the problem of computing Voronoi overlays, and maintaining these overlays dynamically. Since the computation of Voronoi diagrams requires O(n log n) time, our solution is optimal for the computation of the coverage-boundary. We present efficient distributed algorithms for computing and dynamically maintaining Voronoi overlays, and prove the stability properties for the latter - i.e., if the nodes stop moving, the overlay stabilizes to the correct Voronoi overlay. Finally, we present experimental results in the context of the two selected applications, which validate the performance of our distributed and dynamic algorithms.
this paper presents an efficient and scalable approach to solve global optimization problem by distributedparallel tunneling using mobile agents. To use the parallel and concurrent characteristic of the tunneling alg...
详细信息
ISBN:
(纸本)3540240136
this paper presents an efficient and scalable approach to solve global optimization problem by distributedparallel tunneling using mobile agents. To use the parallel and concurrent characteristic of the tunneling algorithms and increase the speed of the computing, we use mobile agents as a tool for parallel implementation in a distributed environment. the experimental results demonstrate the feasibility and the potential of the proposed method.
暂无评论