Performance analysis and introduction to optimization of ParFlow

Abstract

ParFlow is an open-source, object-oriented, parallel watershed flow model. It includes fully-integrated overland flow, the ability to simulate complex topography, geology and heterogeneity and coupled land-surface processes including the land-energy budget, biogeochemistry and snow (via CLM). It is multi-platform and runs with a common I/O structure from laptop to supercomputer. ParFlow is the result of a long, multi-institutional development history and is now a collaborative effort between CSM, LLNL, UniBonn and UCB. This work aims to: get ParFlow to build and compile with instrumentation in order to collect data about the runtime and event timeline of the program; use the collected data to analyze scalability, computation vs. communication and the overall efficiency of the program; and, using this information, pinpoint possible weak points in the code that can be improved and make the necessary changes in an attempt to make the program run faster.