Narrow Results

This paper investigates the influence of the interconnection network topology of a parallel system on the delivery time of an ensemble of messages, called the communication scheme. More specifically, we focus on the impact on the performance of structure in network topology and communication scheme. We introduce causal structure learning algorithms for the modeling of the communication time. The experimental data, from which the models are learned automatically, is retrieved from simulations. The qualitative models provide insight about which and how variables influence the communication performance. Next, a generic property is defined which characterizes the performance of individual communication schemes and network topologies. The property allows the accurate quantitative prediction of the runtime of random communication on random topologies. However, when either communication scheme or network topology exhibit regularities the prediction can become very inaccurate. The causal models can also differ qualitatively and quantitatively. Each combination of communication scheme regularity type, e.g. a one-to-all broadcast, and network topology regularity type, e.g. torus, possibly results in a different model which is based on different characteristics.

Structural and parametric identification of nonlinear continuous dynamic systems with a closed cycle on a set of continuous block-oriented models with feedback is considered. The method of structural identification in the steady state based on the observation of the system's input and output variables at the input periodic influences is proposed. The solution of the parameter identification problems, which can be immediately connected with the structural identification problem, is carried out in the steady and transient states by the method of least squares. The structural and parametric identification algorithms are investigated by means of both theoretical analysis and computer modeling.