Jan Kwiatkowski

Evaluation of Parallel Programs by Measurement of Its Granularity

In the past years computing has been moving from the sequential world to the parallel one, from centralised organisation to a decentralised. In parallel programming the goal of the design process cannot be reduced to optimise a single metrics like for example speed. While evaluating a parallel program a problem specific function of execution time, memory requirements, communication cost, implementation cost, and others have to be taken into consideration. The paper deals with the use of an idea of program granularity in the evaluation of parallel programs. The obtained results suggest that the presented method can be used for performance evaluation of parallel programs.

Smart work workbench; integrated tool for IT services planning, management, execution and evaluation

Smart Service Workbench (SSW) is an integrated tool devoted to support business processes in distributed IT environment based on Service Oriented Architecture (SOA) paradigm. The tools scope of functionalities is divided into modules that cover the whole process starting from the arrival of service request and ending with a return results of request. The latter is assumed to be a service composed of well-defined components available in predefined and staging repository. The tools modules are responsible for requirements analysis, services choice or service composition, communication and computational resources allocation in distributed environment as well as for resources utilization monitoring to services quality and security evaluation purposes.

Performance Evaluation of Different Kohenen Network Parallelization Techniques

The Kohonen feature maps are commonly employed to process large input data but their effective working abilities can be achieved only after a time-consuming process of learning. Performed tests have shown that the sequential program, solving a typical problem, uses more than 95 percent of its time to localize the winners. The aim of the paper is to present and compare different ways of the algorithm parallelization. We compare two different classes of parallel implementations - the network parallelization and the learning set parallelization. During performed experiments two different ways of experimental evaluation are used: standard evaluation based on such metrics as speedup and efficiency and the approximation method based on the granularity concept

Request distribution in hybrid processing environments

In recent years the evolution of software architectures led to the rising prominence of the Service Oriented Architecture (SOA) concept. This architecture paradigm facilitates building flexible service systems. The services can be deployed in distributed environments, executed on different hardware and software platforms, reused and composed into complex services. In the paper a SOA request analysis and distribution architecture for hybrid environments is proposed. The requests are examined in accordance to the SOA request description model. The functional and non-functional request requirements in conjunction with monitoring of execution and communication links performance data are used to distribute requests and allocate the services and resources.

Specifications and Deployment of SOA Business Applications Within a Configurable Framework Provided as a Service

This chapter presents the concept of development and management of SOA applications within the configurable service platform which supports all phases starting from business process definition. The unique features of the platform include: business process compatibility, easy reconfiguration of composition schemes, visual support for requirements and service definition, QoS assessment (including communication services) and service execution control. Moreover, it illustrates how effective tools for SOA management may be developed within the SOA paradigm itself, and how this paradigm may be used to achieve their interoperability and flexibility.

An environment for service composition, execution and resource allocation

In recent years the evolution of software architectures led to the rising prominence of the Service Oriented Architecture (SOA) concept. The services can be deployed in distributed environments and executed on different hardware and software platforms. In the paper a configurable and flexible environment, allowing composition, deployment and execution of composite services, which can be applied in the wide range of SOA-based systems is presented. It supports service semantic description, composition and the distribution of service requests guaranteeing services quality, especially efficient allocating communication and computational resources to services. We present an unified approach, which assumes the semantic description of Web service functionalities with an XML-based language - Smart Service Description Language which provides similar features to that of OWL-S or WSDL, however, it was designed to support services execution and monitoring. These unique features allow to design a service execution engine, compatible with the underlying execution environment and providing support for service QoS guarantees.

Using Fractal Coding in Medical Image Magnification

In the last few years a quick development of non-invasive medical diagnostic methods has been observed. One of these has been high-resolution ultrasonic imaging. It can demonstrate the layers of the arterial wall with a high degree of clarity. The paper briefly describes utilising fractal magnification for measurement of the intima-media thickness during evaluation of the vascular wall. The short description of algorithm used and the methods of its parallelisation are presented.

Context-sensitive text mining with fitness leveling Genetic Algorithm

Contextual processing is a great challenge for information retrieval study - the most approved techniques include scanning content of HTML web pages, user supported metadata analysis, automatic inference grounded on knowledge base, or content-oriented digital documents analysis. We propose a meta-heuristic by making use of Genetic Algorithms for Contextual Search (GACS) built on genetic programming (GP) and custom fitness leveling function to optimize contextual queries in exact search that represents unstructured phrases generated by the user. Our findings show that the queries built with GACS can significantly optimize the retrieval process.

Virtual Networks with the IPv6 Addressing in the Xen Virtualization Environment

There is a common agreement that virtualization allows more efficient use of the computational and communication resources. In most cases virtualization is used on the operating systems level. Occasionally virtualization is considered on the computer network level. The paper is devoted to the virtualization of the network connections at the Layer 2 and 3 within virtualizers and real devices. For this aim the Xen 4.0 virtualizer is used. VLANs and VLAN in VLAN tunnelling (802.1ad, QinQ) are considered at Layer 2. The static as well as the dynamic routing for the IPv6-in-IPv6 tunnelling are examined at Layer 3. The aim of the paper is to present the implementation of various technologies supporting the network virtualization in the real and virtual environments.

Request distribution toolkit for virtual resources allocation

The Service Oriented Architecture (SOA) concept facilitates building flexible services that can be deployed in distributed environment, and executed on different hardware and software platforms. On the other hand SOA paradigm rises many challenges in the area of Quality of Service and resources utilization. In the paper Resources Distribution Manager (RDM) that manages resources and service delivery in order to satisfy user requirements and service providers needs is presented. Requests for services are distributed to selected virtualized instances of services or optionally new instances are created for handling the requests. The allocation decisions are based on the knowledge about the communication resources and the current load of computational resources which are dynamically monitored by special RDM module. The decision on the resources allocation is then compared with its utilization during service execution and causes changes in allocation strategy.