Multilevel mesh partitioning for heterogeneous communication networks

Multilevel algorithms are a successful class of optimisation techniques which address the mesh partitioning problem for distributing unstructured meshes onto parallel computers. They usually combine a graph contraction algorithm together with a local optimisation method which refines the partition at each graph level. To date these algorithms have been used almost exclusively to minimise the cut edge weight in the graph with the aim of minimising the parallel communication overhead, but recently there has been a perceived need to take into account the communications network of the parallel machine. For example the increasing use of SMP clusters (systems of multiprocessor compute nodes with very fast intra-node communications but relatively slow inter-node networks) suggest the use of hierarchical network models. Indeed this requirement is exacerbated in the early experiments with meta-computers (multiple supercomputers combined together, in extreme cases over inter-continental networks). In this paper therefore, we modify a multilevel algorithm in order to minimise a cost function based on a model of the communications network. Several network models and variants of the algorithm are tested and we establish that it is possible to successfully guide the optimisation to reflect the chosen architecture.

The development of parallel implementation for a CFD based fire field model utilising conventional office based PCs

Parallel processing techniques have been used in the past to provide high performance computing resources for activities such as fire-field modelling. This has traditionally been achieved using specialized hardware and software, the expense of which would be difficult to justify for many fire engineering practices. In this article we demonstrate how typical office-based PCs attached to a Local Area Network has the potential to offer the benefits of parallel processing with minimal costs associated with the purchase of additional hardware or software. It was found that good speedups could be achieved on homogeneous networks of PCs, for example a problem composed of ~100,000 cells would run 9.3 times faster on a network of 12 800MHz PCs than on a single 800MHz PC. It was also found that a network of eight 3.2GHz Pentium 4 PCs would run 7.04 times faster than a single 3.2GHz Pentium computer. A dynamic load balancing scheme was also devised to allow the effective use of the software on heterogeneous PC networks. This scheme also ensured that the impact between the parallel processing task and other computer users on the network was minimized.

Trade unions, civil society organisations and health reforms

This article provides an analysis of resistance to neoliberalism and commodification in the public healthcare sector as seen from a trade union perspective. It uses recent research on social-movement unionism and new labour internationalism to structure a series of case studies examining resistance to different dimensions of healthcare commodification in four countries. The range of alliances trade unions are making do not fit tidily into one model, but give insights into the movement elements of trade unionism. This dimension must be strengthened, but can also be in tension with collective bargaining and other institutional processes. How to constantly reconcile these different positions is the future challenge facing trade unions.

Trade credit linkages along the supply chain: evidence for the Italian textile sector

We examine the trade credit linkages among firms within a supply chain to reckon the effect of such linkages on the propagation of liquidity shocks from downstream to upstream firms. We choose a sample appropriate for this task, consisting of a large data set of Italian firms from the textile industry, a well known example of a comprehensive manufacturing cluster featuring a large number of small and specialized firms at each level of the supply chain. The results of the analysis indicate that the level of trade credit that firms provide to their suppliers is positively related to the level of trade credit granted to their clients: when the level of trade credit granted to clients divided by sales goes up by 1, the level of trade credit provided to suppliers divided by cost-of goods-sold goes up by an amount that varies between 0,22 and 0,52. Since all firms along the chain are linked by trade credit relationships, an increase in the level of trade credit granted by wholesalers generates a liquidity cascade throughout the chain. We designate the overall increase in the level of trade credit among all firms in the chain as a result of a unitary impulse in the level of trade credit granted by wholesalers as the multiplier effect of trade credit for the industry chain. We estimate such multiplier to vary between 1.28 and 2.04. We also investigate the effect of final demand on the level of trade credit sourced by firms at various levels of the chain and, in particular, whether such effect is amplified for firms further up in the chain as a result of liquidity propagation via trade credit linkages. We uncover evidence of such amplification when the links of liquidity transmission along the chain are individually modeled and estimated. An unitary increase in wholesalers’ sales is found to produce an effect on trade payables among firms at the top of the chain (i.e., Preparers and Spinners) that is more than twice as big as the corresponding effect among firms at the bottom of the chain (i.e., Wholesalers).