SOD2D code: towards the exascale in CFD

Abstract: In the path towards the exascale computing paradigm, the current trend in new High-Performance Computing (HPC) platforms is to achieve more computing performance by installing increasingly more modules based on General-Purpose Graphical Processing Units (GPGPUs). Hence, new scientific computing codes must be programmed in such a way that they can benefit from the fine-grained parallelism and large data throughput of these devices. With this in mind, we have developed the SOD2D code (Spectral high-Order coDe 2 solve partial Differential equations), a Continuous Galerkin High-Order Spectral Element Method (CG-SEM) code designed to solve simulations of both turbulent compressible and incompressible flows, intending to efficiently exploit all the potential that brand new and future HPC architectures can offer, and aiming to perform CFD simulations that few years ago were just a fantasy.

Bio: Dr. Jordi Muela Castro holds a PhD in Thermal Engineering (UPC, 2018), a MEng in Energy Engineering (UPC) and a BS in Mechanical Engineering (UPC) awarded with the Best Academic Expedient. He is currently working as a Recognised Researcher at Barcelona Supercomputing Center (BSC). His research is mainly focused on developing numerical algorithms to solve fluid dynamics problems and heat and mass transfer problems in High Performance Computing (HPC) platforms, and it covered a wide range of topics like the physics of particle-laden flows and combustion phenomena, the development of highly scalable algorithms for sliding mesh problems and efficient numerical integration for CFD software. He has experience with different numerical methods and programming languages, as well as programming for heterogeneous computing platforms. During his research career, he has participated in different research projects and authored several papers in international journals and conferences.