Towards Green Multi-frontal Solver for Adaptive Finite Element Method

Handle URI:
http://hdl.handle.net/10754/556613
Title:
Towards Green Multi-frontal Solver for Adaptive Finite Element Method
Authors:
AbbouEisha, H.; Moshkov, Mikhail ( 0000-0003-0085-9483 ) ; Jopek, K.; Gepner, P.; Kitowski, J.; Paszyn'ski, M.
Abstract:
In this paper we present the optimization of the energy consumption for the multi-frontal solver algorithm executed over two dimensional grids with point singularities. The multi-frontal solver algorithm is controlled by so-called elimination tree, defining the order of elimination of rows from particular frontal matrices, as well as order of memory transfers for Schur complement matrices. For a given mesh there are many possible elimination trees resulting in different number of floating point operations (FLOPs) of the solver or different amount of data trans- ferred via memory transfers. In this paper we utilize the dynamic programming optimization procedure and we compare elimination trees optimized with respect to FLOPs with elimination trees optimized with respect to energy consumption.
KAUST Department:
Computer Science Program
Citation:
Towards Green Multi-frontal Solver for Adaptive Finite Element Method 2015, 51:984 Procedia Computer Science
Publisher:
Elsevier BV
Journal:
Procedia Computer Science
Conference/Event name:
International Conference on Computational Science, ICCS 2002
Issue Date:
1-Jun-2015
DOI:
10.1016/j.procs.2015.05.240
Type:
Conference Paper
ISSN:
18770509
Additional Links:
http://linkinghub.elsevier.com/retrieve/pii/S1877050915010480
Appears in Collections:
Conference Papers; Computer Science Program

Full metadata record

DC FieldValue Language
dc.contributor.authorAbbouEisha, H.en
dc.contributor.authorMoshkov, Mikhailen
dc.contributor.authorJopek, K.en
dc.contributor.authorGepner, P.en
dc.contributor.authorKitowski, J.en
dc.contributor.authorPaszyn'ski, M.en
dc.date.accessioned2015-06-10T11:26:36Zen
dc.date.available2015-06-10T11:26:36Zen
dc.date.issued2015-06-01en
dc.identifier.citationTowards Green Multi-frontal Solver for Adaptive Finite Element Method 2015, 51:984 Procedia Computer Scienceen
dc.identifier.issn18770509en
dc.identifier.doi10.1016/j.procs.2015.05.240en
dc.identifier.urihttp://hdl.handle.net/10754/556613en
dc.description.abstractIn this paper we present the optimization of the energy consumption for the multi-frontal solver algorithm executed over two dimensional grids with point singularities. The multi-frontal solver algorithm is controlled by so-called elimination tree, defining the order of elimination of rows from particular frontal matrices, as well as order of memory transfers for Schur complement matrices. For a given mesh there are many possible elimination trees resulting in different number of floating point operations (FLOPs) of the solver or different amount of data trans- ferred via memory transfers. In this paper we utilize the dynamic programming optimization procedure and we compare elimination trees optimized with respect to FLOPs with elimination trees optimized with respect to energy consumption.en
dc.publisherElsevier BVen
dc.relation.urlhttp://linkinghub.elsevier.com/retrieve/pii/S1877050915010480en
dc.rightsArchived with thanks to Procedia Computer Science, Under a Creative Commons license http://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectGreen computingen
dc.subjectAdaptive finite element methoden
dc.subjectMulti-frontal direct solveren
dc.titleTowards Green Multi-frontal Solver for Adaptive Finite Element Methoden
dc.typeConference Paperen
dc.contributor.departmentComputer Science Programen
dc.identifier.journalProcedia Computer Scienceen
dc.conference.date2002-04-21 to 2002-04-24en
dc.conference.nameInternational Conference on Computational Science, ICCS 2002en
dc.conference.locationAmsterdam, NLDen
dc.eprint.versionPublisher's Version/PDFen
dc.contributor.institutionAGH University of Science and Technology, Krakow, Polanden
dc.contributor.institutionIntel Corporation, Swindon, United Kingdomen
kaust.authorMoshkov, Mikhailen
kaust.authorAbboueisha, H.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.