S4352 - ASUCA on GPU: Uncompromising Hybrid Port for Physical Core of Japanese Weather Model
( MSc ETH in Electrical Engineering and Information Technology, RIKEN Advanced Institute for Computational Science )
￼Graduated from ETH Zurich in 2012 as Master of Science in Electrical Engineering and Information Technology, Michel's Master thesis was written as guest at the Gordon Bell price winning Aoki Laboratory at the Tokyo Institute of Technology. He successfully migrated Japan's next generation weather prediction model (ASUCA) to Hybrid Fortran in a three month project at the renowned RIKEN Advanced Institute for Computational Science, home of one of the world's fastest super computers. Mr. Müller
presented at the GPU Technology Conference 2013 hosted by NVIDIA in San Jose, California and has four years of experience as a Software Engineer at ATEGRA AG Switzerland.
ASUCA is the next generation non-hydrostatic Japanese mesoscale weather prediction model, currently developed at the Japan Meteorological Agency. In order to join the successful GPU port of its Dynamical Core by Shimokawabe et al., the Physical Core has now been fully ported as well. In order to achieve a unified codebase with high usability as well as high performance on both GPU and CPU, a new directive based Open Source language extension called 'Hybrid Fortran' has been used (as introduced at GTC 2013). Using a python-based preprocessor it automatically creates CUDA Fortran code for GPU and OpenMP Fortran code for CPU - with two separate horizontal loop orders in order to keep performance. Attendees of this session will learn how to create a hybrid codebase with high usability as well as high performance on both CPU and GPU, how we used a preprocessor to achieve our goals and, how to use Macros for Memory optimizations while following the DRY principle.
Session Level: Intermediate
Session Type: Talk
Tags: Climate, Weather, Ocean Modeling