Targeting distributed systems in FastFlow

FastFlow is a structured parallel programming framework targeting shared memory multi-core architectures. In this paper we introduce a FastFlow extension aimed at supporting also a network of multi-core workstations. The extension supports the execution of FastFlow programs by coordinating-in a structured way-the fine grain parallel activities running on a single workstation. We discuss the design and the implementation of this extension presenting preliminary experimental results validating it on state-of-the-art networked multi-core nodes. © 2013 Springer-Verlag.

Dynamical characteristics of solitary waves, shocks and envelope modes in kappa-distributed non-thermal plasmas: an overview

Space plasmas provide abundant evidence of highly energetic particle population, resulting in a long-tailed non-Maxwellian distribution. Furthermore, the first stages in the evolution of plasmas produced during laser-matter interaction are dominated by nonthermal electrons, as confirmed by experimental observation and computer simulations. This phenomenon is efficiently modelled via a kappa-type distribution. We present an overview, from first principles, of the effect of superthermality on the characteristics of electrostatic plasma waves. We rely on a fluid model for ion-acoustic excitations, employing a kappa distribution function to model excess superthermality of the electron distribution. Focusing on nonlinear excitations (solitons), in the form of solitary waves (pulses), shocks and envelope solitons, and employing standard methodological tools of nonlinear plasmadynamical analysis, we discuss the role of excess superthermality in their propagation dynamics (existence laws, stability profile), geometric characteristics and stability. Numerical simulations are employed to confirm theoretical predictions, namely in terms of the stability of electrostatic pulses, as well as the modulational stability profile of bright- and dark-type envelope solitons.

Small aperture evanescent-mode waveguide antenna matched using distributed coupled resonators

Presented is a design methodology which permits the application of distributed coupled resonator bandpass filter principles to form wideband small-aperture evanescent-mode waveguide antenna designs. This approach permits matching of the complex antenna aperture admittance of an evanescent-mode open-ended waveguide to a real impedance generator, and thereby to a coaxial feed probe. A simulated reflection coefficient of < - 10 dB was obtained over a bandwidth of 20%, from 2.0-2.45 GHz, in a 2.58 GHz cutoff waveguide. Dielectric-filled propagating waveguide and air-filled evanescent-mode waveguide sections are used to form the resonators/coupling elements of the antenna's coupled resonator matching sections. Simulated realised gain variation from 3.4-5.0 dBi is observed across the bandwidth. The antenna's maximum aperture dimension is < 0.47 wavelength at the upper operating frequency and so it is suitable for use in a wide angle scanning phased array.

Distributed passive intermodulation generation in coplanar waveguide transmission lines

A phenomenology of distributed passive intermodulation generation in coplanar waveguide transmission line is presented. The theoretical analysis is based upon the generalised nonlinear transmission line model, which accounts for the coupling of two propagating modes. The case of weak substrate nonlinearity is considered and the model is given qualitative verification through the mapping of passive intermodulation products generated in coplanar waveguide fabricated on a commercial laminate. Implications for future research are discussed. © 2012 IEEE.

Swarm scheduling approaches for work-flow applications with security constraints in distributed data-intensive computing environments

The scheduling problem in distributed data-intensive computing environments has become an active research topic due to the tremendous growth in grid and cloud computing environments. As an innovative distributed intelligent paradigm, swarm intelligence provides a novel approach to solving these potentially intractable problems. In this paper, we formulate the scheduling problem for work-flow applications with security constraints in distributed data-intensive computing environments and present a novel security constraint model. Several meta-heuristic adaptations to the particle swarm optimization algorithm are introduced to deal with the formulation of efficient schedules. A variable neighborhood particle swarm optimization algorithm is compared with a multi-start particle swarm optimization and multi-start genetic algorithm. Experimental results illustrate that population based meta-heuristics approaches usually provide a good balance between global exploration and local exploitation and their feasibility and effectiveness for scheduling work-flow applications. © 2010 Elsevier Inc. All rights reserved.