Sabine Richling

Learn More
This paper considers an InfiniBand connection between two bwGRiD clusters over a distance of 28 km in day-to-day production use. We discuss the hardware setup of InfiniBand messages converted and transported over a fiber optic connection. The two clusters can be operated as single system image, the batch system will enforce that all nodes for a job are(More)
By means of numerical simulations we investigate the photoevaporation of protostellar disks. Here we concentrate on the evolution of disks under the influence of an external Ly-man continuum radiation field. The morphological evolution is illustrated in detail for the case of a relatively massive disk exposed to a modest ionizing flux. Cometary tails(More)
We present a new performance model based on the roofline concept for the analysis and performance prediction of distributed computing clusters. The background for our performance modeling is the 28 km InfiniBand interconnection between two bwGRiD clusters each consisting of 140 compute nodes in day-to-day production use. The model is used to analyze the MPI(More)
We discuss operational and organizational issues of an InfiniBand interconnection between two clusters over a distance of 28 km in day-to-day production use. We describe the setup of hardware and networking components, and the solution of technical integration problems. Then we present solutions for a federated authorization system for the cluster within(More)
Context. A significant fraction of the high-redshift galaxies show strong Lyα emission lines. For redshifts z > 5, most known galaxies belong to this class. However, so far not much is known about the physical structure and nature of these objects. Aims. Our aim is to analyse the Lyα emission in a sample of high-redshift UV-continuum selected galaxies and(More)
We present theoretical continuum emission spectra (SED's), isophotal maps and line profiles for several models of photoevaporating disks at different orientations with respect to the observer. The hydrodynamic evolution of these models has been the topic of the two previous papers of this series. We discuss in detail the numerical scheme used for these(More)
We develop a simple hierarchical model for the performance analysis of compute clusters assembled from multi-core compute nodes connected by a (high-speed) network. The performance is described by the dimensionless speed-up and efficiency in dependence on important hardware and application parameters. The hardware parameters are the number of compute nodes(More)