WRF Goddard Microphysics Scheme Optimization
Jarno Mielikainen; Bormin Huang; Allen H.-L. Huang University of Wisconsin-Madison, USA
Abstract
This chapter examines the optimization of numerical weather prediction through optimizations that include reducing the memory bound nature of the code. Code restructuring for better vectorization is also shown to be essential for such a legacy code. The code that is optimized is the weather research and forecasting model, an open source numerical weather prediction model.
Keywords
Weather forecasting
Weather Research and Forecasting (WRF) model
Microphysics
Vectorization
VTune
Software Development Emulator
Xeon Phi
Knights Landing
Acknowledgments
This work is supported by Intel Corporation, ...
Get High Performance Parallelism Pearls Volume Two now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
