Scalable rank-mapping algorithm for an icosahedral grid system on the massive parallel computer with a 3-D torus network

• Published in: Parallel computing 2014-08, Vol.40 (8), p.362-373
• Main Authors: Kodama, Chihiro, Terai, Masaaki, Noda, Akira T., Yamada, Yohei, Satoh, Masaki, Seiki, Tatsuya, Iga, Shin-ichi, Yashiro, Hisashi, Tomita, Hirofumi, Minami, Kazuo
• Format: Article
• Language: English
• Subjects: HPC; Icosahedral grid system; MPI; Rank-mapping algorithm; Torus network topology
• ISSN: 0167-8191; 1872-7336
• DOI: 10.1016/j.parco.2014.06.002

•Rank-mapping algorithm for an icosahedral grid system is developed.•The new algorithm is applicable to the computer with a 3-D torus network topology.•Using the new algorithm, number of hops does not increase with the number of nodes.•The new algorithm achieves almost perfect weak scaling on the K computer.•The new algorithm seems to reduce the communication congestion on the K computer. In this paper, we develop a rank-mapping algorithm for an icosahedral grid system on a massive parallel computer with the 3-D torus network topology, specifically on the K computer. Our aim is to improve the weak scaling performance of the point-to-point communications for exchanging grid-point values between adjacent grid regions on a sphere. We formulate a new rank-mapping algorithm to reduce the maximum number of hops for the point-to-point communications. We evaluate both the new algorithm and the standard ones on the K computer, using the communication kernel of the Nonhydrostatic Icosahedral Atmospheric Model (NICAM), a global atmospheric model with an icosahedral grid system. We confirm that, unlike the standard algorithms, the new one achieves almost perfect performance in the weak scaling on the K computer, even for 10,240 nodes. Results of additional experiments imply that the high scalability of the new rank-mapping algorithm on the K computer is achieved by reducing network congestion in the links between adjacent nodes.