Data-driven execution of fast multipole methods

Handle URI:
http://hdl.handle.net/10754/562978
Title:
Data-driven execution of fast multipole methods
Authors:
Ltaief, Hatem ( 0000-0002-6897-1095 ) ; Yokota, Rio ( 0000-0001-7573-7873 )
Abstract:
Fast multipole methods (FMMs) have O (N) complexity, are compute bound, and require very little synchronization, which makes them a favorable algorithm on next-generation supercomputers. Their most common application is to accelerate N-body problems, but they can also be used to solve boundary integral equations. When the particle distribution is irregular and the tree structure is adaptive, load balancing becomes a non-trivial question. A common strategy for load balancing FMMs is to use the work load from the previous step as weights to statically repartition the next step. The authors discuss in the paper another approach based on data-driven execution to efficiently tackle this challenging load balancing problem. The core idea consists of breaking the most time-consuming stages of the FMMs into smaller tasks. The algorithm can then be represented as a directed acyclic graph where nodes represent tasks and edges represent dependencies among them. The execution of the algorithm is performed by asynchronously scheduling the tasks using the queueing and runtime for kernels runtime environment, in a way such that data dependencies are not violated for numerical correctness purposes. This asynchronous scheduling results in an out-of-order execution. The performance results of the data-driven FMM execution outperform the previous strategy and show linear speedup on a quad-socket quad-core Intel Xeon system.Copyright © 2013 John Wiley & Sons, Ltd. Copyright © 2013 John Wiley & Sons, Ltd.
KAUST Department:
KAUST Supercomputing Laboratory (KSL); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Extreme Computing Research Center
Publisher:
Wiley-Blackwell
Journal:
Concurrency and Computation: Practice and Experience
Issue Date:
17-Sep-2013
DOI:
10.1002/cpe.3132
Type:
Article
ISSN:
15320626
Appears in Collections:
Articles; KAUST Supercomputing Laboratory (KSL); Extreme Computing Research Center; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorLtaief, Hatemen
dc.contributor.authorYokota, Rioen
dc.date.accessioned2015-08-03T11:17:51Zen
dc.date.available2015-08-03T11:17:51Zen
dc.date.issued2013-09-17en
dc.identifier.issn15320626en
dc.identifier.doi10.1002/cpe.3132en
dc.identifier.urihttp://hdl.handle.net/10754/562978en
dc.description.abstractFast multipole methods (FMMs) have O (N) complexity, are compute bound, and require very little synchronization, which makes them a favorable algorithm on next-generation supercomputers. Their most common application is to accelerate N-body problems, but they can also be used to solve boundary integral equations. When the particle distribution is irregular and the tree structure is adaptive, load balancing becomes a non-trivial question. A common strategy for load balancing FMMs is to use the work load from the previous step as weights to statically repartition the next step. The authors discuss in the paper another approach based on data-driven execution to efficiently tackle this challenging load balancing problem. The core idea consists of breaking the most time-consuming stages of the FMMs into smaller tasks. The algorithm can then be represented as a directed acyclic graph where nodes represent tasks and edges represent dependencies among them. The execution of the algorithm is performed by asynchronously scheduling the tasks using the queueing and runtime for kernels runtime environment, in a way such that data dependencies are not violated for numerical correctness purposes. This asynchronous scheduling results in an out-of-order execution. The performance results of the data-driven FMM execution outperform the previous strategy and show linear speedup on a quad-socket quad-core Intel Xeon system.Copyright © 2013 John Wiley & Sons, Ltd. Copyright © 2013 John Wiley & Sons, Ltd.en
dc.publisherWiley-Blackwellen
dc.subjectdynamic schedulingen
dc.subjectfast multipole methodsen
dc.subjectload balancingen
dc.titleData-driven execution of fast multipole methodsen
dc.typeArticleen
dc.contributor.departmentKAUST Supercomputing Laboratory (KSL)en
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentExtreme Computing Research Centeren
dc.identifier.journalConcurrency and Computation: Practice and Experienceen
kaust.authorLtaief, Hatemen
kaust.authorYokota, Rioen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.