Domain decomposition method for unstructured meshes in an OpenMP computing environment

✍ Scribed by Masashi Yamakawa; Yusuke Kita; Kenichi Matsuno

• Publisher: Elsevier Science
• Year: 2011
• Tongue: English
• Weight: 671 KB
• Volume: 45
• Category: Article
• ISSN: 0045-7930
• DOI: 10.1016/j.compfluid.2011.02.008

✦ Synopsis

a b s t r a c t

In this paper, an efficient unstructured mesh calculation method in an OpenMP parallel computation using multi-core processor is proposed. This is a new domain decomposition method with two characteristics. The first characteristic is to define the size of the sub-block in the computation domain by the size of the cache memory in each core. The second one is to reduce idle time by distributing a defined subblock for each core appropriately. Using the proposed method, a computation on compressible flow around a plane was able to achieve speed-up more than about 20% in comparison with a conventional method.