Abstract:
To cope with the high demand for more accurate forecasts of weather, over the past decades Meteorologists have developed and continued to improve weather simulation software. Their latest attempt has resulted in the Weather Research and Forecasting (WRF) model, which is a complex software application with more than 160,000 lines of legacy Fortran 90 and C. The rationale for choosing Fortran 90 and C was their accuracy and performance, but this choice has led to the use of some old programming techniques, which are rarely used today. Furthermore, WRF is based on its predecessor, the Mesoscale Model 5 (MM5), inheriting its architecture and older stub functions. These old functions provide no use in newer versions of the software and perhaps due to fear of breaking the code, or other unknown reasons, they were never removed! Initially, as part of our effort to enable WRF in a grid environment to provide more accurate forecast in less time, we were obligated to conduct a detailed code inspection in order to discover its actual functionality and flow of execution. During this process, we realized that WRF is a perfect example to show that scientific software written by "professional end-user developers" is in fact hard to understand and improve. To address this problem, we continued the effort started by UCAR (University Corporation for Atmospheric Research, the originator and coordinator of WRF code) to develop a document that is aimed to give in-depth knowledge to those software engineers who need to understand the functionality of WRF. Moreover, once we gained sufficient understanding of this application we initiated the original task of adapting WRF to a Grid computing environment. Using a transparent approach to the code, we have been able to profile WRF processor-power versus number-of-nodes behavior, and as a result we developed a simplified mathematical model that predicts this behavior in a distributed environment. In this presentation, I will explain the process of documentation, profiling of the code, the results of our current research and its future research directions.

Bio:
Javier Figueroa is a senior undergraduate student enrolled at the University of Miami and Florida International University with a Computer Science major and a minor in Mathematics. He is currently working as an undergraduate researcher at Florida International University and his research involves Grid Enablement of Scientific Applications. He is working under the supervision of Dr. Masoud Sadjadi. He has published two papers in modeling and estimating the execution time of the Weather Research and Forecasting code. He has always shared a passion for computers and Mathematics. Future plans include the path of an academic career and hopefully more science contributions to the community.