vix.ing · top · new · best · stats · spec

Performance evaluation of explicit finite difference algorithms with\n varying amounts of computational and memory intensity

2016/10/28 by Satya P. Jammy, Jammy, Satya P., Christian T. Jacobs +3 · 2 citations
Earth and Planetary Sciences · Engineering · Mathematics · #Computational Fluid Dynamics and Aerodynamics #Computational Physics (physics.comp-ph) #Data Structures and Algorithms (cs.DS) #Distributed #FOS: Computer and information sciences #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn) #Mathematical Software (cs.MS) #Meteorological Phenomena and Simulations #Numerical methods for differential equations #Parallel #and Cluster Computing (cs.DC)

paper · pdf · doi:10.48550/arxiv.1610.09146

openalex publication_date 2016/10/28 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28

Abstract

Future architectures designed to deliver exascale performance motivate the\nneed for novel algorithmic changes in order to fully exploit their\ncapabilities. In this paper, the performance of several numerical algorithms,\ncharacterised by varying degrees of memory and computational intensity, are\nevaluated in the context of finite difference methods for fluid dynamics\nproblems. It is shown that, by storing some of the evaluated derivatives as\nsingle thread- or process-local variables in memory, or recomputing the\nderivatives on-the-fly, a speed-up of ~2 can be obtained compared to\ntraditional algorithms that store all derivatives in global arrays.\n

Cited by

Related