Wolfgang Gentzsch

Self-Adaptable Autonomic Computing Systems: An Industry View

This paper reflects different industry views on self-adaptable autonomic computing, as perceived by representatives from Enigmatec, IBM, Intel, MCNC, and Oracle. The statements in this paper serve as starting points for the panel discussion on methodologies, engineering requirements, and technical challenges, during the SAACS Conference

Porting Applications to Grids and Clouds

A Grid enables remote, secure access to a set of distributed, networked computing and data resources. Clouds are a natural next step of Grids towards the provisioning of computing as a service. To “Grid-enable” applications, users have to cope with: complexity of grid architectures; different compute and data nodes; wide spectrum of grid middleware tools and services; the e-science application architectures, algorithms and programs. Therefore, the aim of this chapter is to guide users through the important stages of implementing applications on Grid and Cloud infrastructures, together with a discussion of important challenges and their potential solutions. As a case study, we present the DEISA Distributed European Infrastructure for Supercomputing Applications and describe the DEISA Extreme Computing Initiative DECI for porting and running scientific grand challenge applications on the DEIS� Grid. This chapter concludes with an outlook on Compute Clouds, and the top ten rules of building a sustainable Grid.

Comparison of Supercomputers and Mini- Supercomputers for Computational Fluid Dynamics Calcu Lations

Computational fluid dynamics (CFD) is a powerful tool for the simulation of complex fluid dynamics problems. In the future, the progress in CFD will depend on effi cient algorithms as well as on the power and storage capacity of the computers available. A careful study and comparison of these supercomputers, therefore, is nec essary. The following paper presents a short description of the Engineering and Scientific Model Benchmark, the supercomputers and mini-supercomputers under con sideration, and a discussion of the benchmark results.

High-performance road-vehicle optimised aerodynamic design: Application of parallel computing to car design

Abstract The HIPEROAD project has developed a software system capable of performing a semi-automatic optimisation of the shape of sport cars with respect to their aerodynamical properties. The system utilises an aerodynamic solver implemented on parallel MIMD systems, and features advanced tools for the evolution and meshing of car surfaces. The system allows one to include aerodynamic optimisation in the early stages of car design. It has been tested on a Ferrari auto model and full agreement between computed and measured aerodynamical properties was found. The code has been used for designing an optimised model with improved car safety.

Novel Software Containers for Engineering and Scientific Simulations in the Cloud

The adoption of cloud computing for engineering and scientific applications is still lagging behind, although many cloud providers today offer powerful computing infrastructure as a service, and enterprises are already making routine use of it. Reasons for this slow adoption are many: complex access to clouds, inflexible software licensing, time-consuming big data transfer, loss of control over their assets, service provider lock-in, to name a few. But recently, with the advent of the UberClouds novel high-performance software container technology, many of these roadblocks are currently being removed. In this paper the authors describe the current status and landscape of clouds for engineers and scientists, the benefits and challenges, and how UberCloud is providing an online solution platform and container technology which reduce or even remove many of the current roadblock, and thus offer every engineer and scientist additional compute power on demand, in an easily accessible way.

Grid Economics and Business Models

In Grid Computing systems of heterogeneous networked resources are utilized. Computational resources, storage, memory and bandwidth are complemented with application software and content-oriented input from databases and web services. Hence such systems may operate in predefined and centrally organized ways, or coordination may be conducted in a self-organized, decentralized manner. Although there are plenty of idle computing resources available on the Internet, only a small percentage of these are actually utilized. One of the reasons for this could be a lack of reliability, availability, quality of service and security. Or the resources are simply not in reach of the user. On the other hand, also the absence of appropriate economic incentives to share resources is possibly a reason.

HIgh PErformance ROADvehicle Optimized Aerodynamic Design: Application of Parallel Computing to Car Design

The HIPEROAD project has developed a software system capable of performing a semi-automatic optimisation of the shape of sport cars with respect to their aerodynamical properties. The system utilises an aerodynamic solver implemented on parallel MIMD systems, and features advanced tools for the evolution and meshing of car surfaces. The system allows to include aerodynamic optimisation in the early stages of car design. It has been tested on a Ferrari Auto model and full agreement between computed and measured aerodynamical properties was found. The code has been used for designing an optimised model with improved car safety, reducing the vertical upload significantly without affecting car performance.