Three parallel programming paradigms: Comparisons on an archetypal PDE computation

Three paradigms for distributed-memory parallel computation that free the application programmer from the details of message passing are compared for an archetypal structured scientific computation -- a nonlinear, structured-grid partial differential equation boundary value problem -- using the same algorithm on the same hardware. All of the paradigms -- parallel languages represented by the Portland Group's HPF, (semi-)automated serial-to-parallel source-to-source translation represented by CAP-Tools from the University of Greenwich, and parallel libraries represented by Argonne's PETSc -- are found to be easy to use for this problem class, and all are reasonably effective in exploiting concurrency after a short learning curve. The level of involvement required by the application programmer under any paradigm includes specification of the data partitioning, corresponding to a geometrically simple decomposition of the domain of the PDE. Programming in SPMD style for the PETSc library requires writing only the routines that discretize the PDE and its Jacobian, managing subdomain-to-processor mappings (affine global-to-local index mappings), and interfacing to library solver routines. Programming for HPF requires a complete sequential implementation of the same algorithm as a starting point, introduction of concurrency through subdomain blocking (a task similar to the index mapping), and modest experimentation with rewriting loops to elucidate to the compiler the latent concurrency. Programming with CAPTools involves feeding the same sequential implementation to the CAPTools interactive parallelization system, and guiding the source-to-source code transformation by responding to various queries about quantities knowable only at runtime. Results representative of "the state of the practice" for a scaled sequence of structured grid problems are given on three of the most important contemporary high-performance platforms: the IBM SP, the SGI Origin 2000, and the CRAYY T3E.

Phase-accuracy comparisons and improved far-field estimates for 3-D edge elements on tetrahedral meshes

Edge-element methods have proved very effective for 3-D electromagnetic computations and are widely used on unstructured meshes. However, the accuracy of standard edge elements can be criticised because of their low order. This paper analyses discrete dispersion relations together with numerical propagation accuracy to determine the effect of tetrahedral shape on the phase accuracy of standard 3-D edgeelement approximations in comparison to other methods. Scattering computations for the sphere obtained with edge elements are compared with results obtained with vertex elements, and a new formulation of the far-field integral approximations for use with edge elements is shown to give improved cross sections over conventional formulations.

Likelihood, entropy and species diversity; some comparisons in a Sumatran forest

In attempts to conserve the species diversity of trees in tropical forests, monitoring of diversity in inventories is essential. For effective monitoring it is crucial to be able to make meaningful comparisons between different regions, or comparisons of the diversity of a region at different times. Many species diversity measures have been defined, including the well-known abundance and entropy measures. All such measures share a number of problems in their effective practical use. However, probably the most problematic is that they cannot be used to meaningfully assess changes, since thay are only concerned with the number of species or the proportions of the population/sample which they constitute. A natural (though simplistic) model of a species frequency distribution is the multinomial distribution. It is shown that the likelihood analysis of samples from such a distribution are closely related to a number of entropy-type measures of diversity. Hence a comparison of the species distribution on two plots, using the multinomial model and likelihood methods, leads to generalised cross-entropy as the LRT test statistic of the null that the species distributions are the same. Data from 30 contiguous plots in a forest in Sumatra are analysed using these methods. Significance tests between all pairs of plots yield extremely low p-values, indicating strongly that it ought to been "Obvious" that the observed species distributions are different on different plots. In terms of how different the plots are, and how these differences vary over the whole study site, a display of the degrees of freedom of the test, (equivalent to the number of shared species) seems to be the most revealing indicator, as well as the simplest.

Analysing the evacuation procedures employed on a Thames passenger boat using the maritimeEXODUS evacuation model

On the 19 June 2001, a Thames passenger/tour boat underwent several evacuation trials. This work was conducted in order to collect data for the validation of marine-based computer models. The trials involved 111 participants who were distributed throughout the vessel. The boat had two decks and two points of exit from the lower deck placed on either side of the craft, forward and aft. The boat had a twin set of staircases towards the rear of the craft, just forward of the rear exits. maritimeEXODUS was used to simulate the full-scale evacuation trials conducted. The simulation times generated were compared against the original results and categorised according to the exit point availability. The predictions closely approximate the original results, differing by an average of 6.6% across the comparisons, with numerous qualitative similarities between the predictions and experimental results. The maritimeEXODUS evacuation model was then used to examine the evacuation procedure currently employed on the vessel. This was found to have potential to produce long evacuation times. maritimeEXODUS was used to suggest modifications to the mustering procedures. These theoretical results suggest that it is possible to significantly reduce evacuation times.

The Fraud Act 2006: some early observations and comparisons with the former law

Provides a detailed analysis of the Fraud Act 2006 provisions on the offence of fraud by false representation (s.2) and the offence of obtaining services dishonestly (s.11) and assesses the extent to which they address problems arising in connection with the former deception offences under the Theft Acts 1968 and 1978. [From Legal Journals Index]

Comparisons between “sand blast” and “centripetal effect accelerator” type erosion testers

There are two major types of erosion testing devices that are used throughout the world for quantifying particle impact erosion against a solid surface. The first of these uses pressurised air to accelerate abrasive particles through a nozzle so that they impinge upon a target specimen. The second adopts a rotating disc to accelerate abrasive particles using the centripetal effect so that they impinge upon a series of targets arranged around the periphery of the disc. This paper reports the findings of a collaborative project that was designed to compare the performance and results obtained from a rig of each of the two types mentioned above. The sand blast type rig was provided by The Department of Powder Science Technology (POSTEC) at The Telemark Technological Research and Development Centre (TEL-TEK), Porsgrunn, Norway while the centripetal effect accelerator was provided by The Wolfson Centre for Bulk Solids Handling Technology, University of Greenwich, London, UK. The test programme included tests against a wide range of materials that are commonly used in pneumatic handling facilities. (Pneumatic handling is a means of conveying and transporting powders and granular solid materials in bulk in industrial process plant, through pipelines using a gas as the carrier medium.) Olivine sand was used as the abrasive and it was projected against the test specimens at velocities and concentrations commensurate with those seen in pneumatic conveyors. In all instances the materials used in the test programme were taken from the same batch so that scatter of experimental results due to specimen variation was minimised. The paper contains a series of recommendations for erosion testing equipment. A discussion based on the results and their applicability to the prediction of wear in pneumatic conveyors concludes the paper.