Parallel dynamic graph-partitioning for unstructured meshes

A parallel method for the dynamic partitioning of unstructured meshes is described. The method introduces a new iterative optimization technique known as relative gain optimization which both balances the workload and attempts to minimize the interprocessor communications overhead. Experiments on a series of adaptively refined meshes indicate that the algorithm provides partitions of an equivalent or higher quality to static partitioners (which do not reuse the existing partition) and much more rapidly. Perhaps more importantly, the algorithm results in only a small fraction of the amount of data migration compared to the static partitioners.

An automatable generic strategy for dynamic load balancing in parallel structured mesh CFD codes

Parallel computing is now widely used in numerical simulation, particularly for application codes based on finite difference and finite element methods. A popular and successful technique employed to parallelize such codes onto large distributed memory systems is to partition the mesh into sub-domains that are then allocated to processors. The code then executes in parallel, using the SPMD methodology, with message passing for inter-processor interactions. In order to improve the parallel efficiency of an imbalanced structured mesh CFD code, a new dynamic load balancing (DLB) strategy has been developed in which the processor partition range limits of just one of the partitioned dimensions uses non-coincidental limits, as opposed to coincidental limits. The ‘local’ partition limit change allows greater flexibility in obtaining a balanced load distribution, as the workload increase, or decrease, on a processor is no longer restricted by the ‘global’ (coincidental) limit change. The automatic implementation of this generic DLB strategy within an existing parallel code is presented in this chapter, along with some preliminary results.

Automatic and effective multi-dimensional parallelisation of structured mesh based codes

The most common parallelisation strategy for many Computational Mechanics (CM) (typified by Computational Fluid Dynamics (CFD) applications) which use structured meshes, involves a 1D partition based upon slabs of cells. However, many CFD codes employ pipeline operations in their solution procedure. For parallelised versions of such codes to scale well they must employ two (or more) dimensional partitions. This paper describes an algorithmic approach to the multi-dimensional mesh partitioning in code parallelisation, its implementation in a toolkit for almost automatically transforming scalar codes to parallel form, and its testing on a range of ‘real-world’ FORTRAN codes. The concept of multi-dimensional partitioning is straightforward, but non-trivial to represent as a sufficiently generic algorithm so that it can be embedded in a code transformation tool. The results of the tests on fine real-world codes demonstrate clear improvements in parallel performance and scalability (over a 1D partition). This is matched by a huge reduction in the time required to develop the parallel versions when hand coded – from weeks/months down to hours/days.

A multilevel algorithm for force-directed graph drawing

We describe a heuristic method for drawing graphs which uses a multilevel technique combined with a force-directed placement algorithm. The multilevel process groups vertices to form clusters, uses the clusters to define a new graph and is repeated until the graph size falls below some threshold. The coarsest graph is then given an initial layout and the layout is successively refined on all the graphs starting with the coarsest and ending with the original. In this way the multilevel algorithm both accelerates and gives a more global quality to the force- directed placement. The algorithm can compute both 2 & 3 dimensional layouts and we demonstrate it on a number of examples ranging from 500 to 225,000 vertices. It is also very fast and can compute a 2D layout of a sparse graph in around 30 seconds for a 10,000 vertex graph to around 10 minutes for the largest graph. This is an order of magnitude faster than recent implementations of force-directed placement algorithms.

A multilevel algorithm for force-directed graph-drawing

We describe a heuristic method for drawing graphs which uses a multilevel framework combined with a force-directed placement algorithm. The multilevel technique matches and coalesces pairs of adjacent vertices to define a new graph and is repeated recursively to create a hierarchy of increasingly coarse graphs, G0, G1, …, GL. The coarsest graph, GL, is then given an initial layout and the layout is refined and extended to all the graphs starting with the coarsest and ending with the original. At each successive change of level, l, the initial layout for Gl is taken from its coarser and smaller child graph, Gl+1, and refined using force-directed placement. In this way the multilevel framework both accelerates and appears to give a more global quality to the drawing. The algorithm can compute both 2 & 3 dimensional layouts and we demonstrate it on examples ranging in size from 10 to 225,000 vertices. It is also very fast and can compute a 2D layout of a sparse graph in around 12 seconds for a 10,000 vertex graph to around 5-7 minutes for the largest graphs. This is an order of magnitude faster than recent implementations of force-directed placement algorithms.

A combined evolutionary search and multilevel optimisation approach to graph-partitioning

The graph-partitioning problem is to divide a graph into several pieces so that the number of vertices in each piece is the same within some defined tolerance and the number of cut edges is minimised. Important applications of the problem arise, for example, in parallel processing where data sets need to be distributed across the memory of a parallel machine. Very effective heuristic algorithms have been developed for this problem which run in real-time, but it is not known how good the partitions are since the problem is, in general, NP-complete. This paper reports an evolutionary search algorithm for finding benchmark partitions. A distinctive feature is the use of a multilevel heuristic algorithm to provide an effective crossover. The technique is tested on several example graphs and it is demonstrated that our method can achieve extremely high quality partitions significantly better than those found by the state-of-the-art graph-partitioning packages.

JOSTLE: multilevel graph partitioning software: an overview

In this chapter we look at JOSTLE, the multilevel graph-partitioning software package, and highlight some of the key research issues that it addresses. We first outline the core algorithms and place it in the context of the multilevel refinement paradigm. We then look at issues relating to its use as a tool for parallel processing and, in particular, partitioning in parallel. Since its first release in 1995, JOSTLE has been used for many mesh-based parallel scientific computing applications and so we also outline some enhancements such as multiphase mesh-partitioning, heterogeneous mapping and partitioning to optimise subdomain shape

A critical examination of node-similarity based graph matching algorithms

In this paper, we shall critically examine a special class of graph matching algorithms that follow the approach of node-similarity measurement. A high-level algorithm framework, namely node-similarity graph matching framework (NSGM framework), is proposed, from which, many existing graph matching algorithms can be subsumed, including the eigen-decomposition method of Umeyama, the polynomial-transformation method of Almohamad, the hubs and authorities method of Kleinberg, and the kronecker product successive projection methods of Wyk, etc. In addition, improved algorithms can be developed from the NSGM framework with respects to the corresponding results in graph theory. As the observation, it is pointed out that, in general, any algorithm which can be subsumed from NSGM framework fails to work well for graphs with non-trivial auto-isomorphism structure.

Measuring similarity of software designs using graph matching for CBR

This paper examines different ways of measuring similarity between software design models for Case Based Reasoning (CBR) to facilitate reuse of software design and code. The paper considers structural and behavioural aspects of similarity between software design models. Similarity metrics for comparing static class structures are defined and discussed. A Graph representation of UML class diagrams and corresponding similarity measures for UML class diagrams are defined. A full search graph matching algorithm for measuring structural similarity diagrams based on the identification of the Maximum Common Sub-graph (MCS) is presented. Finally, a simple evaluation of the approach is presented and discussed.

Scalable and efficient graph colouring in 3 dimensions using emergence engineering principles

This paper describes ways in which emergence engineering principles can be applied to the development of distributed applications. A distributed solution to the graph-colouring problem is used as a vehicle to illustrate some novel techniques. Each node acts autonomously to colour itself based only on its local view of its neighbourhood, and following a simple set of carefully tuned rules. Randomness breaks symmetry and thus enhances stability. The algorithm has been developed to enable self-configuration in wireless sensor networks, and to reflect real-world configurations the algorithm operates with 3 dimensional topologies (reflecting the propagation of radio waves and the placement of sensors in buildings, bridge structures etc.). The algorithm’s performance is evaluated and results presented. It is shown to be simultaneously highly stable and scalable whilst achieving low convergence times. The use of eavesdropping gives rise to low interaction complexity and high efficiency in terms of the communication overheads.

On efficient data integrity and data origin authentication for wireless sensor networks utilising block cipher design techniques

Analysis of the generic attacks and countermeasures for block cipher based message authentication code algorithms (MAC) in sensor applications is undertaken; the conclusions are used in the design of two new MAC constructs Quicker Block Chaining MAC1 (QBC-MAC1) and Quicker Block Chaining MAC2 (QBC-MAC2). Using software simulation we show that our new constructs point to improvements in usage of CPU instruction clock cycle and energy requirement when benchmarked against the de facto Cipher Block Chaining MAC (CBC-MAC) based construct used in the TinySec security protocol for wireless sensor networks.

Zone based systems design framework for the realisation of efficient block cipher based message authentication code algorithms

A zone based systems design framework is described and utilised in the implementation of a message authentication code (MAC) algorithm based on symmetric key block ciphers. The resulting block cipher based MAC algorithm may be used to provide assurance of the authenticity and, hence, the integrity of binary data. Using software simulation to benchmark against the de facto cipher block chaining MAC (CBC-MAC) variant used in the TinySec security protocol for wireless sensor networks and the NIST cipher block chaining MAC standard, CMAC; we show that our zone based systems design framework can lead to block cipher based MAC constructs that point to improvements in message processing efficiency, processing throughput and processing latency.