Dynamic Data Migration for Structured AMR Solvers.
Saved in:
| Title: | Dynamic Data Migration for Structured AMR Solvers. |
|---|---|
| Authors: | Nordén, Markus1 markusn@it.uu.se, Löf, Henrik1 henlof@it.uu.se, Rantakokko, Jarmo1 jarmo@it.uu.se, Holmgren, Sverker1 sverker@it.uu.se |
| Source: | International Journal of Parallel Programming. Oct2007, Vol. 35 Issue 5, p477-491. 15p. 1 Diagram, 5 Charts, 1 Graph. |
| Subjects: | Parallel programming, Dynamic data exchange, Numerical grid generation (Numerical analysis), Virtual storage (Computer science), Computer software, Microprocessors, Programming language semantics, Data transmission systems, Computer programming |
| Abstract: | On cc-NUMA multi-processors, the non-uniformity of main memory latencies motivates the need for co-location of threads and data. We call this special form of data locality, geographical locality. In this article, we study the performance of a parallel PDE solver with adaptive mesh refinement (AMR). The solver is parallelized using OpenMP and the adaptive mesh refinement makes dynamic load balancing necessary. Due to the dynamically changing memory access pattern caused by the runtime adaption, it is a challenging task to achieve a high degree of geographical locality. The main conclusions of the study are: (1) that geographical locality is very important for the performance of the solver, (2) that the performance can be improved significantly using dynamic page migration of misplaced data, (3) that a migrate-on-next-touch directive works well whereas the first-touch strategy is less advantageous for programs exhibiting a dynamically changing memory access patterns, and (4) that the overhead for such migration is low compared to the total execution time. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Parallel Programming is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 26515244 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Dynamic Data Migration for Structured AMR Solvers. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Nordén%2C+Markus%22">Nordén, Markus</searchLink><relatesTo>1</relatesTo><i> markusn@it.uu.se</i><br /><searchLink fieldCode="AR" term="%22Löf%2C+Henrik%22">Löf, Henrik</searchLink><relatesTo>1</relatesTo><i> henlof@it.uu.se</i><br /><searchLink fieldCode="AR" term="%22Rantakokko%2C+Jarmo%22">Rantakokko, Jarmo</searchLink><relatesTo>1</relatesTo><i> jarmo@it.uu.se</i><br /><searchLink fieldCode="AR" term="%22Holmgren%2C+Sverker%22">Holmgren, Sverker</searchLink><relatesTo>1</relatesTo><i> sverker@it.uu.se</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Parallel+Programming%22">International Journal of Parallel Programming</searchLink>. Oct2007, Vol. 35 Issue 5, p477-491. 15p. 1 Diagram, 5 Charts, 1 Graph. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Parallel+programming%22">Parallel programming</searchLink><br /><searchLink fieldCode="DE" term="%22Dynamic+data+exchange%22">Dynamic data exchange</searchLink><br /><searchLink fieldCode="DE" term="%22Numerical+grid+generation+%28Numerical+analysis%29%22">Numerical grid generation (Numerical analysis)</searchLink><br /><searchLink fieldCode="DE" term="%22Virtual+storage+%28Computer+science%29%22">Virtual storage (Computer science)</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+software%22">Computer software</searchLink><br /><searchLink fieldCode="DE" term="%22Microprocessors%22">Microprocessors</searchLink><br /><searchLink fieldCode="DE" term="%22Programming+language+semantics%22">Programming language semantics</searchLink><br /><searchLink fieldCode="DE" term="%22Data+transmission+systems%22">Data transmission systems</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+programming%22">Computer programming</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: On cc-NUMA multi-processors, the non-uniformity of main memory latencies motivates the need for co-location of threads and data. We call this special form of data locality, geographical locality. In this article, we study the performance of a parallel PDE solver with adaptive mesh refinement (AMR). The solver is parallelized using OpenMP and the adaptive mesh refinement makes dynamic load balancing necessary. Due to the dynamically changing memory access pattern caused by the runtime adaption, it is a challenging task to achieve a high degree of geographical locality. The main conclusions of the study are: (1) that geographical locality is very important for the performance of the solver, (2) that the performance can be improved significantly using dynamic page migration of misplaced data, (3) that a migrate-on-next-touch directive works well whereas the first-touch strategy is less advantageous for programs exhibiting a dynamically changing memory access patterns, and (4) that the overhead for such migration is low compared to the total execution time. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of Parallel Programming is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=26515244 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s10766-007-0056-z Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 15 StartPage: 477 Subjects: – SubjectFull: Parallel programming Type: general – SubjectFull: Dynamic data exchange Type: general – SubjectFull: Numerical grid generation (Numerical analysis) Type: general – SubjectFull: Virtual storage (Computer science) Type: general – SubjectFull: Computer software Type: general – SubjectFull: Microprocessors Type: general – SubjectFull: Programming language semantics Type: general – SubjectFull: Data transmission systems Type: general – SubjectFull: Computer programming Type: general Titles: – TitleFull: Dynamic Data Migration for Structured AMR Solvers. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Nordén, Markus – PersonEntity: Name: NameFull: Löf, Henrik – PersonEntity: Name: NameFull: Rantakokko, Jarmo – PersonEntity: Name: NameFull: Holmgren, Sverker IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 10 Text: Oct2007 Type: published Y: 2007 Identifiers: – Type: issn-print Value: 08857458 Numbering: – Type: volume Value: 35 – Type: issue Value: 5 Titles: – TitleFull: International Journal of Parallel Programming Type: main |
| ResultId | 1 |
