Accelerating Parallel Applications Based on Graph Reordering for Random Network Topologies
Yao Hu · IEEE Access · 2023
The Message Passing Interface (MPI) is a crucial programming tool for enabling communication between processes in parallel applications. The goal of MPI users is to allocate tasks to processors in a way that maximizes both spatial and temporal locality in the network. However, this can be challenging, especially in large-scale networks where maximizing processor locality may not be feasible at runtime. To address this issue, we propose the use ofHamorder, an offline node reassignment approach that takes into account physical processor locations based on graph reordering forRandomnetwork topologies.Hamorderaims to optimize task mapping for improved performance in parallel applications, whether for multiple tasks or within a single task. Additionally, we investigate the potential of improving MPI applications through runtime parameter tuning based onHamorder. Our evaluation results show thatHamorderprovides a 27.3% improvement in performance compared to theGorderalgorithm onRandomtopologies, which is a state-of-the-art solution designed with the aim of enhancing cache locality and achieves this goal by rearranging the vertices of a graph in a way that places the vertices that are typically accessed together in close proximity. Moreover, our autotuning framework usingHamorderresults in an average speedup of 1.38x for targeted MPI applications by searching through various runtime parameter combinations.