Abstract
In this research, we present the first MPI-CUDA implementation of Finite-Difference Time-Domain (FDTD) discretization of Maxwell's equations in dispersive media that uses the MPI API to assign each CPU node its share of the computational domain and GPUs to their corresponding CPU threads. By taking advantage of the CUDA programming model, we present a unique implementation of the FDTD scheme that exploits the memory hierarchy of GPUs, including the global, texture, and shared memory. This enables us to tackle problems that are otherwise computationally prohibitive. Practical results will be presented along with a measure of speedup factors achieved when using multiple GPU processors.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
