Semi-Static and Dynamic Load Balancing for Asynchronous Hurricane Storm Surge Simulations

摘要

The performance of hurricane storm surge simulations is critical to forecast and mitigate the deadly effects of hurricane landfall. Supercomputers play a key role to run these simulations quickly; however, disruptive changes in future computer architectures will require adapting simulators to maintain high performance, such as increasing asynchrony and improving load balance. We introduce two new multi-constraint, fully asynchronous load balancers and a new discrete-event simulator (DGSim) that is able to natively model the execution of task-based hurricane simulations based on efficient one-sided, active message-based communication protocols. We calibrate and validate DGSim, use it to compare the algorithms' load balancing capabilities and task migration costs under many parameterizations, saving of over 5,000x core-hours compared to running the application code directly. Our load balancing algorithms achieve a performance improvement of up to 56 percent over the original static balancer and up to 97 percent of the optimal speed-up.