Progress towards physics-based space weather forecasting with exascale computing

Particle in cell simulations applied to space weather modelling represent an excellent application for codesign efforts. PIC codes are simple and flexible with many variants addressing different physical conditions (e.g. explicit, implicit, hybrid, gyrokinetic, fluid) and different architectures (e.g. vector, parallel, GPU). It is relatively easy to consider radical changes and test them in a short time. For this reason, the project DEEP funded by the European Commission (www.deep-project.eu) and the Intel Exascience Lab (www.exascience.com) have used PIC as one of their target application for a codesign approach aiming at developing PIC methods for future exascale comupters. The present work focuses on the efforts within DEEP. The starting point is the iPic3D implicit PIC approach. Here we report on the analysis of code performance, on the use of GPUs and the new MICs (Intel Phi processors). We describe how the method can be rethought for hybrid architectures composed of MICs and CPUs (as in the new Deep Supercomputer in Juelich, as well as in others). The focus is on a codesign approach where computer science issues motivate modifications of the algorithms used while physics constraints what should be eventually achieved.