Bogdan Ludwiczak

Dynamic grid scheduling with job migration and rescheduling in the GridLab resource management system

Grid computing has become one of the most important research topics that appeared in the field of computing in the last years. Simultaneously, we have noticed the growing popularity of new Web-based technologies which allow us to create application-oriented Grid middleware services providing capabilities required for dynamic resource and job management, monitoring, security, etc. Consequently, end users are able to get easier access to geographically distributed resources. In this paper we present the results of our experiments with the Grid(Lab) Resource Management System (GRMS), which acts on behalf of end users and controls their computations efficiently using distributed heterogeneous resources. We show how resource matching techniques used within GRMS can be improved by the use of a job migration based rescheduling policy. The main aim of this policy is to shorten job pending times and reduce machine overloads. The influence of this method on application performance and resource utilization is studied in detail and compared with two other simple policies.

Problems Related to Parallelization of CFD Algorithms on GPU, Multi‐GPU and Hybrid Architectures

Computational Fluid Dynamics (CFD) is one of the branches of fluid mechanics, which uses numerical methods and algorithms to solve and analyze fluid flows. CFD is used in various domains, such as oil and gas reservoir uncertainty analysis, aerodynamic body shapes optimization (e.g. planes, cars, ships, sport helmets, skis), natural phenomena analysis, numerical simulation for weather forecasting or realistic visualizations. CFD problem is very complex and needs a lot of computational power to obtain the results in a reasonable time. We have implemented a parallel application for two‐dimensional CFD simulation with a free surface approximation (MAC method) using new hardware architectures, in particular multi‐GPU and hybrid computing environments. For this purpose we decided to use NVIDIA graphic cards with CUDA environment due to its simplicity of programming and good computations performance. We used finite difference discretization of Navier‐Stokes equations, where fluid is propagated over an Eulerian G...

Vitrall: web-based distributed visualization system for creation of collaborative working environments

Advanced parallel computing solutions using GPU for general purpose processing are becoming more and more popular. Applications like CFD or weather modeling take an extensive speed up using GPU-based clusters. Still, original purpose of graphic processing units --- visualization, is not exploited as much as it could be in such powerful processing centres. Main reason of that situation is their fundamental difference from classic desktop configurations: being a structure remote and hidden from the actual viewer. Already existing GPU-based architectures consisting of many processing units may be used for visualization of complex issues from many points of view and in resolutions that are not accessible for single GPUs in real-time. Visualization is a very efficient way of collaboration, especially when collaborators can interact with presented content in a natural way, for example using multi-touch devices. Vitrall embraces these methods by introducing possibility of linkage between modern interfaces and complex visualizations. This paper will begin with summary of several researches that where conducted to establish actual concept of the Vitrall system. Next, proposed architecture of Vitrall will be introduced, following main and secondary usage scenarios. Finally, some of Vitralls specific configurations will be shown, like real-time stereoscopic visualization.

Vine toolkit: grid-enabled portal solution for community driven computing workflows with meta-scheduling capabilities

In large scale production environments, the information sets to perform calculations on come from various sources. In particular, some computations may require the information obtained as a result of previous computations. Workflow description offers an attractive approach to formally deal with such complex processes. Vine Toolkit [1] solution addresses some major challenges here such as the synchronization of distributed workflows, establishing a community driven Grid environment for the seamless results sharing and collaboration. In order to accomplish these goals Vine Toolkit offers integration on different layers starting from rich user interface web components, integration with workflow engine and Grid security and ending up with a built-in meta-scheduling mechanisms, that allow IT administrators to perform load balancing automatically among computing clusters and data centers to meet peak demands. As a result of this particular project a complete solution has been developed and delivered.

PSNC advanced multimedia and visualization infrastructures, services and applications

Poznan Supercomputing and Networking Services (PSNC) offers advanced visualisation and multimedia infrastructures as a set of dedicated laboratories to conduct innovative research and development projects involving both academia and industry. In this short overview we present the existing facilities located at the PSNC campus in Poznan, Poland as well as short descriptions of example applications and networked services which have been recently developed.