Unpublished manuscript

Abstract As the scale of supercomputers grows, so does the size of the in-terconnect network. Topology-aware task mapping, which maps parallel ap-plication processes onto processors to reduce communication cost, becomes increasingly important. Previous works mainly focus on the task mapping between compute nodes (i.e., inter-node mapping), while ignoring the map-ping within a node (i.e., intra-node mapping). In this paper, we propose a hierarchical task mapping strategy, which performs both inter-node and intra-node mapping. We consider supercomputers with popular fat-tree and torus network topologies, and introduce two mapping algorithms: (1) a generic re-cursive tree mapping algorithm, which can handle both inter-node mapping and intra-node mapping; (2) a recursive bipartitioning mapping algorithm for torus topology, which efficiently partitions the compute nodes according to their coordinates. Moreover, a hierarchical task mapping library is developed. The majority of this work was done when Jingjin and Xuanxing were Ph.D. students a