Efficiency of acoustical parallel computing by bread slicing method

• Autores: Oikawa Yasuhiro, Tokita Yasuhiro, Yoshio Yamasaki
• Localización: Proceedings of the ISRA 2007 Seville, Vol. 3, 2008 (Oral Session Communications), ISBN 9788469082676
• Idioma: español
• Texto completo no disponible (Saber más ...)
• Resumen

  • In order to reduce the amount of communication among each node of the computer cluster on parallel computing, we proposed a method to divide the field of numerical analyses. It was called �bread slicing method�. With this method, the fields must be divided into pieces parallel to the section that has the least area. Generally, on the parallel computing of the distributed memory system, the communicating time occupies most of the total calculating time. Therefore, the reduction to the amount of the communication directly causes the reduction of the calculating time. Numerical analyses by the explicit scheme of the finite difference method greatly reduce the number of known variables that are needed to solve an unknown variable in comparison with the implicit methods. The parallel computing by the explicit scheme of the finite difference method can enable the building up of high-performance algorithms. The results showed that the method enabled the total amount of communication in the computer cluster to be reduced and the geometries of communication to be made simpler. In this study, the efficiency of parallel computing by the method is evaluated. The values of the efficiency are shown the advantage of the method.