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.

Performance measurement and benchmarking of a major innovation programme

Purpose: The purpose of this paper is to describe the problems encountered and the solutions developed when using benchmarking and key performance indicators (KPIs) to monitor a major UK social house building innovation (change) programme. The innovation programme sought improvements to both the quality of the house product and the procurement process. Design/methodology/approach: Benchmarking and KPIs were used to quantify performance and in-depth case studies to identify underlying cause and effect relationships within the innovation programme. Findings: The inherent competition between consortium members; the complexity of the relationship between the consortium and its strategic partner; the lack of an authoritative management control structure; and the rapidly changing nature of the UK social housing market all proved problematic to the development of a reliable and robust monitoring system. These problems were overcome by the development of multi-dimensional benchmarking model that balanced the needs and aspirations of the individual organisations with the broader objectives of the consortium. Research limitations/implications: Whilst the research methodology provides insight into the factors that affected the performance of a major innovation programme its findings may not be representative of all projects. Practical implications: The lessons learnt should assist those developing benchmarking models for multi-client consortia. Originality/value: The work reported in this paper describes an inclusive approach to benchmarking in which a multiple client group and their strategic partner sought to work together for shared gain. Very few papers have addressed this issue.

A multi-scale atomistic-continuum modelling of crack propagation in a two-dimensional macroscopic plate

A novel multi-scale seamless model of brittle-crack propagation is proposed and applied to the simulation of fracture growth in a two-dimensional Ag plate with macroscopic dimensions. The model represents the crack propagation at the macroscopic scale as the drift-diffusion motion of the crack tip alone. The diffusive motion is associated with the crack-tip coordinates in the position space, and reflects the oscillations observed in the crack velocity following its critical value. The model couples the crack dynamics at the macroscales and nanoscales via an intermediate mesoscale continuum. The finite-element method is employed to make the transition from the macroscale to the nanoscale by computing the continuum-based displacements of the atoms at the boundary of an atomic lattice embedded within the plate and surrounding the tip. Molecular dynamics (MD) simulation then drives the crack tip forward, producing the tip critical velocity and its diffusion constant. These are then used in the Ito stochastic calculus to make the reverse transition from the nanoscale back to the macroscale. The MD-level modelling is based on the use of a many-body potential. The model successfully reproduces the crack-velocity oscillations, roughening transitions of the crack surfaces, as well as the macroscopic crack trajectory. The implications for a 3-D modelling are discussed.

Partition alignment in three dimensional unstructured mesh multi-physics modelling

Unstructured mesh codes for modelling continuum physics phenomena have evolved to provide the facility to model complex interacting systems. Parallelisation of such codes using single Program Multi Data (SPMD) domain decomposition techniques implemented with message passing has been demonstrated to provide high parallel efficiency, scalability to large numbers of processors P and portability across a wide range of parallel platforms. High efficiency, especially for large P requires that load balance is achieved in each parallel loop. For a code in which loops span a variety of mesh entity types, for example, elements, faces and vertices, some compromise is required between load balance for each entity type and the quantity of inter-processor communication required to satisfy data dependence between processors.

CFD analysis of one-dimensional infiltration in vadose zone

This study presents a CFD analysis constructed around PHYSICA, an open framework for multi-physics computational continuum mechanics modelling, to investigate the water movement in unsaturated porous media. The modelling environment is based on a cell-centred finite-volume discretisation technique. A number of test cases are performed in order to validate the correct implementation of Richard's equation for compressible and incompressible fluids. The pressure head form of the equation is used together with the constitutive relationships between pressure, volumetric water content and hydraulic conductivity described by Haverkamp and Van Genuchten models. The flow problems presented are associated with infiltration into initially dry soils with homogeneous or layered geologic settings. Comparison of results with the problems selected from literature shows a good agreement and validates the approach and the implementation.

A three dimensional finite volume approach to the thermo-mechanical modelling of the shape casting of metals

This paper presents a three dimensional, thermos-mechanical modelling approach to the cooling and solidification phases associated with the shape casting of metals ei. Die, sand and investment casting. Novel vortex-based Finite Volume (FV) methods are described and employed with regard to the small strain, non-linear Computational Solid Mechanics (CSM) capabilities required to model shape casting. The CSM capabilities include the non-linear material phenomena of creep and thermo-elasto-visco-plasticity at high temperatures and thermo-elasto-visco-plasticity at low temperatures and also multi body deformable contact with which can occur between the metal casting of the mould. The vortex-based FV methods, which can be readily applied to unstructured meshes, are included within a comprehensive FV modelling framework, PHYSICA. The additional heat transfer, by conduction and convection, filling, porosity and solidification algorithms existing within PHYSICA for the complete modelling of all shape casting process employ cell-centred FV methods. The termo-mechanical coupling is performed in a staggered incremental fashion, which addresses the possible gap formation between the component and the mould, and is ultimately validated against a variety of shape casting benchmarks.

Modelling continuum mechanics phenomena using three dimensional unstructured meshes on massively parallel processors

The difficulties encountered in implementing large scale CM codes on multiprocessor systems are now fairly well understood. Despite the claims of shared memory architecture manufacturers to provide effective parallelizing compilers, these have not proved to be adequate for large or complex programs. Significant programmer effort is usually required to achieve reasonable parallel efficiencies on significant numbers of processors. The paradigm of Single Program Multi Data (SPMD) domain decomposition with message passing, where each processor runs the same code on a subdomain of the problem, communicating through exchange of messages, has for some time been demonstrated to provide the required level of efficiency, scalability, and portability across both shared and distributed memory systems, without the need to re-author the code into a new language or even to support differing message passing implementations. Extension of the methods into three dimensions has been enabled through the engineering of PHYSICA, a framework for supporting 3D, unstructured mesh and continuum mechanics modeling. In PHYSICA, six inspectors are used. Part of the challenge for automation of parallelization is being able to prove the equivalence of inspectors so that they can be merged into as few as possible.

Dynamic load balancing of distributed memory parallel computational mechanics using unstructured meshes for multi-physical modelling

As the complexity of parallel applications increase, the performance limitations resulting from computational load imbalance become dominant. Mapping the problem space to the processors in a parallel machine in a manner that balances the workload of each processors will typically reduce the run-time. In many cases the computation time required for a given calculation cannot be predetermined even at run-time and so static partition of the problem returns poor performance. For problems in which the computational load across the discretisation is dynamic and inhomogeneous, for example multi-physics problems involving fluid and solid mechanics with phase changes, the workload for a static subdomain will change over the course of a computation and cannot be estimated beforehand. For such applications the mapping of loads to process is required to change dynamically, at run-time in order to maintain reasonable efficiency. The issue of dynamic load balancing are examined in the context of PHYSICA, a three dimensional unstructured mesh multi-physics continuum mechanics computational modelling code.