Pii: 0045-7825(96)01024-9
نویسنده
چکیده
Mesh partitioning is often the preferred approach for solving unstructured computational mechanics problems on massively parallel processors. Research in this area has focused so far on the automatic generation of subdomains with minimum interface points. In this paper, we address this issue and emphasize other aspects of the partitioning problem including the fast generation of large-scale mesh decompositions on conventional workstations, the optimization of initial decompositions for specific kernels such as parallel frontal solvers and domain decomposition based iterative methods, and parallel adaptive refinement. More specifically, we discuss a two-step partitioning paradigm for tailoring generated mesh partitions to specific applications, and propose a simple mesh contraction procedure for speeding up the optimization of initial mesh decompositions. We discuss what defines a good mesh partition for a given problem, and show that the methodology proposed herein can produce better mesh partitions than the well celebrated multilevel Recursive Spectral Bisection algorithm, and yet be an order of magnitude faster. We illustrate the combined two-step partitioning and contraction methodology with several examples from structural mechanics and fluid dynamics problems, and highlight its impact on the total solution time of realistic applications on current massively parallel processors. In particular, we show that the minimum interface size criterion does not have a significant impact on a reasonably well parallelized application, and highlight other criterion which can have a significant impact.
منابع مشابه
Time discretized operators. Part 1: towards the theoretical design of a new generation of a generalized family of unconditionally stable implicit and explicit representations of arbitrary order for computational dynamics
The objectives and motivation of the exposition presented in Parts 1 and 2 are to fundamentally describe from new perspectives the generic design, development and formal theory towards a new generation of a generalized family of time discretized operators possessing excellent algorithmic attributes as related to the notion of stability and accuracy, and, which also closely mimic the properties ...
متن کاملPii: S0045-7825(98)00387-9
The sweeping process, introduced some time ago by the author with motivation in plasticity theory, today remains an object of mathematical research. It is considered in this paper as the prototype of an evolution conditioned by inequality constraints. Since the governing differential requirements are only of order one with respect to time, this provides a simplified setting for analysing some n...
متن کاملA nonlocal plasticity formulation for the material point method
0045-7825/$ see front matter 2012 Elsevier B.V. A http://dx.doi.org/10.1016/j.cma.2012.03.007 ⇑ Corresponding author. E-mail addresses: [email protected], jeff788@g A new multi-variate fixed-point iteration scheme is devised for solving the coupled dynamic integral equations governing nonlocal plasticity using the material point method (MPM). Novel use of the MPM grid for particle–particle c...
متن کاملFinished Genome Assembly of Yersinia pestis EV76D and KIM 10v
Here, we sequenced the completed genome of Yersinia pestis EV76D and KIM 10v, two genomes used as references in assay development, to improved high-quality draft status.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2003