Some materials-related microstructural problems calculated using the phase-field method are presented. It is well known that the phase field method requires mesh resolution of a diffuse interface. This makes the use of mesh adaptivity essential especially for fast evolving interfaces and other transient problems. Complex problems in 3D are also computationally challenging so that parallel computations are considered necessary. In this paper, a parallel adaptive finite element scheme is proposed. The scheme keeps the level of node and edge for 2D and level of node and face for 3D instead of the complete history of refinements to facilitate derefinement. The information is local and exchange of information is minimized and also less memory is used. The parallel adaptive algorithms that run on distributed memory machines are implemented in the numerical simulation of dendritic growth and capillary-driven flows.

Parallel computers are becoming more available. The natural way to improve computational efficiency of multibody simulations seems to be parallel processing. Within this work we are trying to estimate the efficiency of parallel computations performed using one of the commercial multibody solver. First, the short theoretical outline is presented to give the overview of modeling issues in multibody dynamics. Next, the experimental part is demonstrated. The series of dynamics analyses are carried out. The test mechanisms with variable number of bodies are used to gather the performance results of the solver. The obtained data allow for estimating the number of bodies which are sufficient to gain benefits from parallel computing as well as their level. The parallel processing profits are taken into account in the case of contact forces present in the system. The performance benefits are indicated, when the multilink belt chain is simulated, in which contact forces are included in the model.

In the age of Information and Communication Technology (ICT), Web and the Internet have changed significantly the way applications are developed, deployed and used. One of recent trends is modern design of web-applications based on SOA. This process is based on the composition of existing web services into a single scenario from the point of view of a particular user or client. This allows IT companies to shorten the product-time to market process. On the other hand, it raises questions about the quality of the application, trade-offs between quality factors and attributes and measurements of these. Services are usually hosted and executed in an environment managed by its provider that assures the quality attributes such as availability or throughput. Therefore, in this paper an attempt has been made to perform quality measurements towards the creation of efficient, dependable and user-oriented Web applications. First, the process of designing service-based applications is described. Next, metrics for subsequent measurements of efficiency, dependability and usability of distributed applications are presented. These metrics will assess the efforts and trade-offs in a Web-based application development. As examples, we describe a pair of multimedia applications which we have developed in our department and executed in a cluster-based environment. One of them runs in the BeesyCluster middleware and the second one in the Kaskada platform. For these applications we present results of measurements and conclude about relations between quality attributes in the presented application development model. This knowledge can be used to reason about such relations for new similar applications and be used in rapid and quality development of the latter.

In this paper, a parallel multi-path variant of the well-known TSAB algorithm for the job shop scheduling problem is proposed. Coarse-grained parallelization method is employed, which allows for great scalability of the algorithm with accordance to Gustafon’s law. The resulting P-TSAB algorithm is tested using 162 well-known literature benchmarks. Results indicate that P-TSAB algorithm with a running time of one minute on a modern PC provides solutions comparable to the ones provided by the newest literature approaches to the job shop scheduling problem. Moreover, on average P-TSAB achieves two times smaller percentage relative deviation from the best known solutions than the standard variant of TSAB. The use of parallelization also relieves the user from having to fine-tune the algorithm. The P-TSAB algorithm can thus be used as module in real-life production planning systems or as a local search procedure in other algorithms. It can also provide the upper bound of minimal cycle time for certain problems of cyclic scheduling.

We report on the first application of the graphics processing units (GPUs) accelerated computing technology to improve performance of numerical methods used for the optical characterization of evaporating microdroplets. Single microdroplets of various liquids with different volatility and molecular weight (glycerine, glycols, water, etc.), as well as mixtures of liquids and diverse suspensions evaporate inside the electrodynamic trap under the chosen temperature and composition of atmosphere. The series of scattering patterns recorded from the evaporating microdroplets are processed by fitting complete Mie theory predictions with gradientless lookup table method. We showed that computations on GPUs can be effectively applied to inverse scattering problems. In particular, our technique accelerated calculations of the Mie scattering theory on a single-core processor in a Matlab environment over 800 times and almost 100 times comparing to the corresponding code in C language. Additionally, we overcame problems of the time-consuming data post-processing when some of the parameters (particularly the refractive index) of an investigated liquid are uncertain. Our program allows us to track the parameters characterizing the evaporating droplet nearly simultaneously with the progress of evaporation.