A fine-grained parallelization of the immersed boundary method. (July 2022)

• Record Type: Journal Article
• Authors: Kassen, Andrew; Shankar, Varun; Fogelson, Aaron L
• Is Part Of: International journal of high performance computing applications. Volume 36:Number 4(2022)
• Page Start: 443
• Page End: 458
• Publication Date: 2022-07
• Subjects: Compute Unified Device Architecture -- computational fluid dynamics -- immersed boundary method -- geometric modeling -- red blood cell; High performance computing -- Periodicals; Supercomputers -- Periodicals; 004.1105
• DOI: 10.1177/10943420221083572
• Languages: English
• ISSNs: 1094-3420

Abstract

We present new algorithms for the parallelization of Eulerian–Lagrangian interaction operations in the immersed boundary method. Our algorithms rely on two well-studied parallel primitives: key-value sort and segmented reduce. The use of these parallel primitives allows us to implement our algorithms on both graphics processing units (GPUs) and on other shared-memory architectures. We present strong and weak scaling tests on problems involving scattered points and elastic structures. Our tests show that our algorithms exhibit near-ideal scaling on both multicore CPUs and GPUs.