抄録
This paper concerns development of large-scale high-performance (LSHP) CFD coding method for PC-Cluster Parallel Computing Environment. Main objective of the present study is enhancement of capability of Reynolds-averaged Navier-Stokes (RaNS) equation solver and its advanced applications for LSHP computing in ship hull form design. One of the finial goals is to achieve the scalable coding of RaNS equation solver in the level of 10^7 computational grids using 64 CPUs. In the present 1st report, focus of discussion is placed on setup and initial evaluation of the present coding environment. The Message Passing Interface (MPI) protocol and the Score-D job scheduling method are implemented in the present system. In the following, details of the present parallel coding environment are described. Then results of the performance evaluation are discussed based on benchmark data for high-performance parallel coding of CFD-based nonlinear programming and a domain-decomposition-based commercial RaNS equation solver.
