Copyrights to these papers may be held by the publishers. The download files are preprints. It is understood that all persons copying this information will adhere to the terms and constraints invoked by each author's copyright. These works may not be reposted without the explicit permission of the copyright holder.
Anuva Kulkarni, Franz Franchetti and Jelena Kovacevic (Proc. High Performance Extreme Computing (HPEC), 2018)
Algorithm Design for Large Scale Parallel FFT-Based Simulations on Heterogeneous Platforms
Preprint (237 KB)
Published paper (link to publisher)
Large scale iterative simulations involving parallel Fast Fourier Transforms (FFTs) have extreme memory requirements and high communication overhead. This prevents scaling to higher grid sizes, which is necessary for high resolution analysis. In this work, we describe an algorithm to overcome these limitations and run stress-strain simulations for larger problem sizes using irregular domain decomposition and local FFTs. Early results show that our method lowers iteration cost without adversely impacting accuracy of the result.Keywords: Parallel processing, Fast Fourier Transform, Simulation, Design, Algorithm, Large Scale