This short panel position paper outlines the vision of modern development methods and supporting technologies for the development of modern and future real-time and embedded software applications. It is argued that th...
详细信息
This short panel position paper outlines the vision of modern development methods and supporting technologies for the development of modern and future real-time and embedded software applications. It is argued that these should be based on so-called model-based softwareengineering techniques and service-oriented principles.
There are document reproduction/distribution systems aimed for the copyright protection in the educational site. But, these systems are not always convenient and it is often hard to manage the systems for network admi...
详细信息
There are document reproduction/distribution systems aimed for the copyright protection in the educational site. But, these systems are not always convenient and it is often hard to manage the systems for network administrator. We apply a DACS Portal to the systems by using the network communication control on the client. On the DACS Scheme, a new distribution system is developed which displays static documents dynamically. The DACS Portal is applied to the copying/distribution system. It is shown that the proposed distribution system is easy to handle for users to get the documents medium. Further, the system is also easy to manage network for network administrator with no change of network configuration.
In our evolving computing environment with heterogenously distributed information systems, products are continuously modified and changed. During this process a change to one part will, in most cases, results in chang...
详细信息
In our evolving computing environment with heterogenously distributed information systems, products are continuously modified and changed. During this process a change to one part will, in most cases, results in changes to other parts. Therefore, in design and redesign for customization, predicting this change presents a significant challenge. Changes are required to fix faults or to improve or update products. This paper reports on the development of a change impact analysis factor adaptation model, a fault and failure assumption model and the implementation of a generic change propagation framework for evaluating and assessing utility service provisioning in a Grid service environment. While implementing the framework, data was collected for a period of 3 years which helped in predicting an immediate year. The obtained results from our pre- diction shows the framework, its associated models and Bayesian statistics as satisfying the criteria for a significant prediction accuracy in evaluating and assessing the effect of a change of service in a grid environment when compared to an unreported regression method.
The existence of redundancy is a serious problem in virtual enterprise in which a number of collaborating enterprises join together to manufacture and sell a class of product for a time-limited period. This paper prop...
详细信息
The existence of redundancy is a serious problem in virtual enterprise in which a number of collaborating enterprises join together to manufacture and sell a class of product for a time-limited period. This paper proposes a new approach for detection and elimination of redundancy in virtual enterprises; the proposed approach is based on workflow and uses Petri net for modeling and simulation of workflows. This paper also presents a working example as a proof of concept.
Most traditional distributed Shared Memory (DSM) systems support data sharing in multi-process applications. This paper proposed a Multi-threaded Multi-home DSM system (MM-DSM) to support both data sharing and computa...
详细信息
Most traditional distributed Shared Memory (DSM) systems support data sharing in multi-process applications. This paper proposed a Multi-threaded Multi-home DSM system (MM-DSM) to support both data sharing and computation synchronization in multi-threaded applications whose threads are grouped into bundles and distributed across multiple computers for parallel execution. Globally shared data are rearranged and assigned to different thread bundles based on their access patterns. As thread bundles move around, their hosting nodes will act as the homes of the associated data blocks to reduce communication cost. Programmers can still stick to the shared memory programming paradigm whereas data consistency, distributed lock, false sharing and multiple writes are taken care of by MM-DSM. Experimental results demonstrate its effectiveness and correctness.
Model-driven engineering (MDE), and its various forms (such as OMG's MDA: model-driven architecture) is a software development methodology focusing on creating models and abstractions for a specific domain. It aim...
详细信息
Model-driven engineering (MDE), and its various forms (such as OMG's MDA: model-driven architecture) is a software development methodology focusing on creating models and abstractions for a specific domain. It aims to increase productivity and avoid traditional SDLC problems by maximizing compatibility between systems, simplifying the process of design, and promoting understanding and communication between stakeholders and developers. Organic computing is a vision for a particular type of system, and considers what is to be delivered (self-management). MDE involves applied research into how to deliver systems. Both have the development of more effective systems as a high level objective, and so can be viewed as complementary.
Stream processing systems have become important, as applications like media broadcasting, sensor network monitoring and on-line data analysis increasingly rely on real-time stream processing. Such systems are often ch...
详细信息
ISBN:
(纸本)9781424437511
Stream processing systems have become important, as applications like media broadcasting, sensor network monitoring and on-line data analysis increasingly rely on real-time stream processing. Such systems are often challenged by the bursty nature of the applications. In this paper, we present BARRE (Burst Accommodation through Rate REconfiguration), a system to address the problem of bursty data streams in distributed stream processing systems. Upon the emergence of a burst, BARRE dynamically reserves resources dispersed across the nodes of a distributed stream processing system, based on the requirements of each application as well as the resources available on the nodes. Our experimental results over our Synergy distributed stream processing system demonstrate the efficiency of our approach.
High-end machines at modern HPC centers are constantly undergoing hardware and system software upgrades - necessitating frequent rebuilds of application codes. The number of possible combinations of compilers, librari...
详细信息
High-end machines at modern HPC centers are constantly undergoing hardware and system software upgrades - necessitating frequent rebuilds of application codes. The number of possible combinations of compilers, libraries, application build configurations, differing hardware architectures, etc, makes the process of building applications very onerous, requiring expert build knowledge from different domains. Our ongoing Harness Workbench Toolkit (HWT) project aims to foster and streamline the entire build process on heterogeneous computational platforms. This paper focuses on a key research issue of the HWT that regards facilitating and enhancement portability of build systems across multifarious machines, with particular respect to scientific software commonly used in the HPC community. The article presents a novel HWT approach based on the concept of generic build systems and profiles which encapsulate build knowledge provided independently by relevant experts. The paper describes profiles, the logistics of storing and retrieving build information, and interfacing to user-guided builds. We also report on experiences with applying the HWT approach to two scientific production codes (CPMD, GAMESS) on Cray XT4.
This extended abstract describes the keynote presentation "stochastically robust resource management in heterogeneous parallel computing systems," to be given by H. J. Siegel. What does it mean for a compute...
详细信息
This extended abstract describes the keynote presentation "stochastically robust resource management in heterogeneous parallel computing systems," to be given by H. J. Siegel. What does it mean for a computer system to be "robust"? How can robustness be described? How does one determine if a claim of robustness is true? How can one decide which of two systems is more robust? Often people state that their system software component, piece of hardware, application code, or technique is "robust," but never define what they mean by "robust." How does one determine if a claim of robustness is true when it is not defined? Furthermore, without a definition, robustness cannot be quantified, so if two people claim to have robust computing systems, for example, how can one decide which is the more robust? These are the types of issues we address in this keynote presentation. We study robustness in the context of resource allocation in heterogeneous parallel and distributed computing systems, but the robustness concepts presented have broad applicability. In heterogeneous parallel and distributed computing environments, a collection of different machines is interconnected and provides a variety of computational capabilities. These capabilities can be used to execute a workload composed of different types of applications, each of which may consist of multiple tasks, where the tasks have diverse computational requirements. The execution times of a task may vary from one machine to the next, and just because some machine A is faster than some machine B for task 1 does not mean it will be faster for task 2. Furthermore, there can be inter-task data dependencies. Tasks must share the computing and communication resources of the system. A critical research problem is how to allocate resources to tasks to optimize some performance objective. However, systems frequently have degraded performance due to uncertainties, such as unexpected machine failures, changes in system workload, or i
This paper describes how to improve separation between domain-specific code and parallel code in skeletal systems. Traditionally, the code used to exploit parallelism is tangled among domain-specific code, which leads...
详细信息
ISBN:
(纸本)9781424444106
This paper describes how to improve separation between domain-specific code and parallel code in skeletal systems. Traditionally, the code used to exploit parallelism is tangled among domain-specific code, which leads to problems such as: poor maintainability, lower flexibility, and weak scalability. In this paper we introduce the design of the YaSkel framework, which is a support tool to write parallel programs. We argue that the design of YaSkel framework allows more freedom to change the parallelization strategy when compared with traditional skeleton frameworks. To change the parallelization strategy we rely on DI - Dependency Injection - to inject a reference of a specific skeleton in latter development stages. We also show that AOP - Aspect Oriented Programming - could be used to minimize the impact of applying skeleton based approaches to legacy code.
暂无评论