The semi-automatic parallelisation of scientific application codes using a computer aided parallelisation toolkit

The shared-memory programming model can be an effective way to achieve parallelism on shared memory parallel computers. Historically however, the lack of a programming standard using directives and the limited scalability have affected its take-up. Recent advances in hardware and software technologies have resulted in improvements to both the performance of parallel programs with compiler directives and the issue of portability with the introduction of OpenMP. In this study, the Computer Aided Parallelisation Toolkit has been extended to automatically generate OpenMP-based parallel programs with nominal user assistance. We categorize the different loop types and show how efficient directives can be placed using the toolkit's in-depth interprocedural analysis. Examples are taken from the NAS parallel benchmarks and a number of real-world application codes. This demonstrates the great potential of using the toolkit to quickly parallelise serial programs as well as the good performance achievable on up to 300 processors for hybrid message passing-directive parallelisations.

Extended model of pedestrian escalator behaviour based on data collected within a Chinese underground station

This paper presents data relating to pedestrian escalator behaviour collected in an underground station in Shanghai, China. While data was not collected under emergency or simulated emergency conditions, it is argued that the data collected under rush-hour conditions - where commuters are under time pressures to get to work on time - may be used to approximate emergency evacuation conditions - where commuters are also under time pressures to exit the building as quickly as possible. Data pertaining to escalator/stair choice, proportion of walkers to riders, walker speeds and side usage are presented. The collected data is used to refine the buildingEXODUS escalator model allowing the agents to select whether to use an escalator or neighbouring parallel stair based on congestion conditiions at the base of the stair/escalator and expected travel times. The new model, together with the collected data, is used to simulate a series of hypothetical evacuation scenarios to demonstrate the impact of escalators on evacuation performance.

Shallow water model for aluminium electrolysis cells with variable top and bottom

The MHD wave instability in commercial cells for electrolytic aluminium production is often described using ‘shallow water’ models. The model [1] is extended for a variable height cathode bottom and anode top to account for realistic cell features. The variable depth of the two fluid layers affects the horizontal current density, the wave development and the stability threshold. Instructive examples for the 500 kA cell are presented.