uu.seUppsala University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Multithreaded PDE Solvers on Non-Uniform Memory Architectures
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Scientific Computing. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Numerical Analysis. (Software Aspects of High-Performance Computing)
2006 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

A trend in parallel computer architecture is that systems with a large shared memory are becoming more and more popular. A shared memory system can be either a uniform memory architecture (UMA) or a cache coherent non-uniform memory architecture (cc-NUMA).

In the present thesis, the performance of parallel PDE solvers on cc-NUMA computers is studied. In particular, we consider the shared namespace programming model, represented by OpenMP. Since the main memory is physically, or geographically distributed over several multi-processor nodes, the latency for local memory accesses is smaller than for remote accesses. Therefore, the geographical locality of the data becomes important.

The focus of the present thesis is to study multithreaded PDE solvers on cc-NUMA systems, in particular their memory access pattern with respect to geographical locality. The questions posed are: (1) How large is the influence on performance of the non-uniformity of the memory system? (2) How should a program be written in order to reduce this influence? (3) Is it possible to introduce optimizations in the computer system for this purpose?

The main conclusion is that geographical locality is important for performance on cc-NUMA systems. This is shown experimentally for a broad range of PDE solvers as well as theoretically using a model involving characteristics of computer systems and applications.

Geographical locality can be achieved through migration directives that are inserted by the programmer or — possibly in the future — automatically by the compiler. On some systems, it can also be accomplished by means of transparent, hardware initiated migration and replication. However, a necessary condition that must be fulfilled if migration is to be effective is that the memory access pattern must not be "speckled", i.e. as few threads as possible shall make accesses to each memory page.

We also conclude that OpenMP is competitive with MPI on cc-NUMA systems if care is taken to get a favourable data distribution.

Place, publisher, year, edition, pages
Uppsala: Acta Universitatis Upsaliensis , 2006. , p. 33
Series
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 224
Keywords [en]
PDE solver, high-performance, NUMA, UMA, OpenMP, MPI, data migration, data replication, thread scheduling, data affinity
National Category
Software Engineering
Research subject
Scientific Computing
Identifiers
URN: urn:nbn:se:uu:diva-7149ISBN: 91-554-6656-7 (print)OAI: oai:DiVA.org:uu-7149DiVA, id: diva2:168886
Public defence
2006-10-20, Room 2446, Polacksbacken, Lägerhyddsvägen 2D, Uppsala, 10:15 (English)
Opponent
Supervisors
Available from: 2006-09-28 Created: 2006-09-28 Last updated: 2018-01-13Bibliographically approved
List of papers
1. OpenMP versus MPI for PDE solvers based on regular sparse numerical operators
Open this publication in new window or tab >>OpenMP versus MPI for PDE solvers based on regular sparse numerical operators
2006 (English)In: Future generations computer systems, ISSN 0167-739X, E-ISSN 1872-7115, Vol. 22, p. 194-203Article in journal (Refereed) Published
National Category
Software Engineering Computational Mathematics
Identifiers
urn:nbn:se:uu:diva-47210 (URN)10.1016/j.future.2003.09.004 (DOI)000234408800016 ()
Available from: 2006-05-23 Created: 2006-05-23 Last updated: 2018-01-11Bibliographically approved
2. Performance of PDE solvers on a self-optimizing NUMA architecture
Open this publication in new window or tab >>Performance of PDE solvers on a self-optimizing NUMA architecture
2002 (English)In: Parallel Algorithms and Applications, ISSN 1063-7192, E-ISSN 1029-032X, Vol. 17, p. 285-299Article in journal (Refereed) Published
National Category
Computer Sciences Computational Mathematics
Identifiers
urn:nbn:se:uu:diva-66909 (URN)10.1080/01495730208941445 (DOI)
Available from: 2006-05-22 Created: 2006-05-22 Last updated: 2018-01-10Bibliographically approved
3. Improving Geographical Locality of Data for Shared Memory Implementations of PDE Solvers
Open this publication in new window or tab >>Improving Geographical Locality of Data for Shared Memory Implementations of PDE Solvers
2004 (English)In: Computational Science – ICCS 2004, Berlin: Springer-Verlag , 2004, p. 9-16Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Berlin: Springer-Verlag, 2004
Series
Lecture Notes in Computer Science ; 3037
National Category
Computer Sciences Computational Mathematics
Identifiers
urn:nbn:se:uu:diva-71098 (URN)10.1007/b97988 (DOI)
Available from: 2007-03-11 Created: 2007-03-11 Last updated: 2018-01-10Bibliographically approved
4. Geographical locality and dynamic data migration for OpenMP implementations of adaptive PDE solvers
Open this publication in new window or tab >>Geographical locality and dynamic data migration for OpenMP implementations of adaptive PDE solvers
2008 (English)In: OpenMP Shared Memory Parallel Programming, Berlin: Springer-Verlag , 2008, p. 382-393Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Berlin: Springer-Verlag, 2008
Series
Lecture Notes in Computer Science ; 4315
National Category
Computer Sciences Computational Mathematics
Identifiers
urn:nbn:se:uu:diva-17844 (URN)10.1007/978-3-540-68555-5_31 (DOI)000256573200031 ()978-3-540-68554-8 (ISBN)
Projects
UPMARC
Available from: 2008-09-05 Created: 2008-09-05 Last updated: 2018-01-12Bibliographically approved
5. Performance modelling for parallel PDE solvers on NUMA-systems
Open this publication in new window or tab >>Performance modelling for parallel PDE solvers on NUMA-systems
2006 (English)Report (Other academic)
Series
Technical report / Department of Information Technology, Uppsala University, ISSN 1404-3203 ; 2006-041
National Category
Computer Sciences Computational Mathematics
Identifiers
urn:nbn:se:uu:diva-81930 (URN)
Available from: 2008-02-19 Created: 2008-02-19 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

fulltext(390 kB)789 downloads
File information
File name FULLTEXT01.pdfFile size 390 kBChecksum MD5
5a847e95df87a45ee0a4263cfb4afa7770446f29a59db477c220107732143c200029eb34
Type fulltextMimetype application/pdf
Buy this publication >>

Authority records BETA

Nordén, Markus

Search in DiVA

By author/editor
Nordén, Markus
By organisation
Division of Scientific ComputingNumerical Analysis
Software Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 789 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 1439 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf