A massively parallel and memory-efficient FEM toolbox with a hybrid total FETI solver with accelerator support

Show simple item record
dc.contributor.advisor
dc.contributor.authorŘíha, Lubomír
dc.contributor.authorMerta, Michal
dc.contributor.authorVavřík, Radim
dc.contributor.authorBrzobohatý, Tomáš
dc.contributor.authorMarkopoulos, Alexandros
dc.contributor.authorMeca, Ondřej
dc.contributor.authorVysocký, Ondřej
dc.contributor.authorKozubek, Tomáš
dc.contributor.authorVondrák, Vít
dc.date.accessioned2018-09-21T06:02:33Z
dc.date.available2018-09-21T06:02:33Z
dc.date.issued2018
dc.description.abstract-enIn this article, we present the ExaScale PaRallel finite element tearing and interconnecting SOlver (ESPRESO) finite element method (FEM) library, which includes an FEM toolbox with interfaces to professional and open-source simulation tools, and a massively parallel hybrid total finite element tearing and interconnecting (HTFETI) solver which can fully utilize the Oak Ridge Leadership Computing Facility Titan supercomputer and achieve superlinear scaling. This article presents several new techniques for finite element tearing and interconnecting (FETI) solvers designed for efficient utilization of supercomputers with a focus on (i) performance—we present a fivefold reduction of solver runtime for the Laplace equation by redesigning the FETI solver and offloading the key workload to the accelerator. We compare Intel Xeon Phi 7120p and Tesla K80 and P100 accelerators to Intel Xeon E5-2680v3 and Xeon Phi 7210 central processing units; and (ii) memory efficiency—we present two techniques which increase the efficiency of the HTFETI solver 1.8 times and push the limits of the largest possible problem ESPRESO that can solve from 124 to 223 billion unknowns for problems with unstructured meshes. Finally, we show that by dynamically tuning hardware parameters, we can reduce energy consumption by up to 33%.
dc.format.extent2126959 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.citationInternational Journal of High Performance Computing Applications. 2018.cs
dc.identifier.doi10.1177/1094342018798452
dc.identifier.issn1094-3420
dc.identifier.issn1741-2846
dc.identifier.urihttp://hdl.handle.net/10084/132038
dc.languageNeuvedenocs
dc.language.isoencs
dc.publisherSAGE Publishing
dc.relation.urihttps://doi.org/10.1177/1094342018798452
dc.titleA massively parallel and memory-efficient FEM toolbox with a hybrid total FETI solver with accelerator supportcs
dc.typearticlecs

Files

Original bundle

Now showing 1 - 1 out of 1 results
Thumbnail Image
Name:
ijhpca-massively-parallel-8.pdf
Size:
2.03 MB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download

License bundle

Now showing 1 - 1 out of 1 results
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Publikační činnost IT4Innovations / Publications of IT4Innovations (9600)