Parallel Performance Studies for a Three-Species Application Problem on the Cluster tara

Abstract

High performance parallel computing depends on the interaction of a number of factors including the processors, the architecture of the compute nodes, their interconnect network, and the numerical code. In this note, we present performance and scalability studies on the cluster tara using a well established parallelized code for a three-species application problem. This application problem requires long-time simulations on a fine mesh, thus posing a very computationally intensive problem. The speedup of run times afforded by parallel computing makes the difference between simply unacceptably long runs to obtain the results (e.g., several days or weeks) and practically feasible studies (e.g., overnight runs). The results also support the scheduling policy implemented, since they confirm that it is beneficial to use all eight cores of the two quad-core processors on each node simultaneously, giving us in-effect a computer that can run jobs efficiently with up to 656 parallel processes when using all 82 compute nodes. The cluster tara is an IBM server x iDataPlex purchased in 2009 by the UMBC High Performance Computing Facility (www.umbc.edu/hpcf). It is an 86-node distributed-memory cluster comprised of 82 compute, 2 develop, 1 user and 1 management nodes. Each node features two quad-core Intel Nehalem X5550 processors (2.66 GHz, 8 MB cache), 24 GB memory, and a 120 GB local hard drive. All nodes and the 160 TB central storage are connected by an InfiniBand (QDR) interconnect network.