Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • 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
Finite Element Computations on Multicore and Graphics Processors
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, Computational Science.
2017 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

In this thesis, techniques for efficient utilization of modern computer hardwarefor numerical simulation are considered. In particular, we study techniques for improving the performance of computations using the finite element method.

One of the main difficulties in finite-element computations is how to perform the assembly of the system matrix efficiently in parallel, due to its complicated memory access pattern. The challenge lies in the fact that many entries of the matrix are being updated concurrently by several parallel threads. We consider transactional memory, an exotic hardware feature for concurrent update of shared variables, and conduct benchmarks on a prototype multicore processor supporting it. Our experiments show that transactions can both simplify programming and provide good performance for concurrent updates of floating point data.

Secondly, we study a matrix-free approach to finite-element computation which avoids the matrix assembly. In addition to removing the need to store the system matrix, matrix-free methods are attractive due to their low memory footprint and therefore better match the architecture of modern processors where memory bandwidth is scarce and compute power is abundant. Motivated by this, we consider matrix-free implementations of high-order finite-element methods for execution on graphics processors, which have seen a revolutionary increase in usage for numerical computations during recent years due to their more efficient architecture. In the implementation, we exploit sum-factorization techniques for efficient evaluation of matrix-vector products, mesh coloring and atomic updates for concurrent updates, and a geometric multigrid algorithm for efficient preconditioning of iterative solvers. Our performance studies show that on the GPU, a matrix-free approach is the method of choice for elements of order two and higher, yielding both a significantly faster execution, and allowing for solution of considerably larger problems. Compared to corresponding CPU implementations executed on comparable multicore processors, the GPU implementation is about twice as fast, suggesting that graphics processors are about twice as power efficient as multicores for computations of this kind.

Place, publisher, year, edition, pages
Uppsala: Acta Universitatis Upsaliensis, 2017. , p. 64
Series
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 1512
Keywords [en]
Finite Element Methods, GPU, Matrix-Free, Multigrid, Transactional Memory
National Category
Computer Sciences Computational Mathematics
Research subject
Scientific Computing
Identifiers
URN: urn:nbn:se:uu:diva-320147ISBN: 978-91-554-9907-5 (print)OAI: oai:DiVA.org:uu-320147DiVA, id: diva2:1088894
Public defence
2017-06-09, ITC 2446, Lägerhyddsvägen 2, Uppsala, 10:15 (English)
Opponent
Supervisors
Available from: 2017-05-16 Created: 2017-04-17 Last updated: 2018-01-13
List of papers
1. Using hardware transactional memory for high-performance computing
Open this publication in new window or tab >>Using hardware transactional memory for high-performance computing
Show others...
2011 (English)In: Proc. 25th International Symposium on Parallel and Distributed Processing Workshops and PhD Forum, Piscataway, NJ: IEEE , 2011, p. 1660-1667Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Piscataway, NJ: IEEE, 2011
National Category
Computer Sciences
Identifiers
urn:nbn:se:uu:diva-158551 (URN)10.1109/IPDPS.2011.322 (DOI)978-1-61284-425-1 (ISBN)
Conference
IPDPS Workshop on Multi-Threaded Architectures and Applications
Projects
eSSENCEUPMARC
Available from: 2011-09-01 Created: 2011-09-10 Last updated: 2018-01-12Bibliographically approved
2. Matrix-free finite-element operator application on graphics processing units
Open this publication in new window or tab >>Matrix-free finite-element operator application on graphics processing units
2014 (English)In: Euro-Par 2014: Parallel Processing Workshops, Part II, Springer, 2014, p. 450-461Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
Springer, 2014
Series
Lecture Notes in Computer Science ; 8806
National Category
Computer Sciences Computational Mathematics
Identifiers
urn:nbn:se:uu:diva-238380 (URN)10.1007/978-3-319-14313-2_38 (DOI)000354785000038 ()978-3-319-14312-5 (ISBN)
Conference
7th Workshop on Unconventional High-Performance Computing
Projects
UPMARCeSSENCE
Available from: 2014-12-11 Created: 2014-12-11 Last updated: 2018-01-11Bibliographically approved
3. Matrix-free finite-element computations on graphics processors with adaptively refined unstructured meshes
Open this publication in new window or tab >>Matrix-free finite-element computations on graphics processors with adaptively refined unstructured meshes
2017 (English)In: Proc. 25th High Performance Computing Symposium, San Diego, CA: The Society for Modeling and Simulation International, 2017, p. 1-12Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
San Diego, CA: The Society for Modeling and Simulation International, 2017
National Category
Computer Sciences Computational Mathematics
Identifiers
urn:nbn:se:uu:diva-320146 (URN)978-1-5108-3822-2 (ISBN)
Conference
HPC 2017, April 23–26, Virginia Beach, VA
Projects
UPMARC
Available from: 2017-04-23 Created: 2017-04-16 Last updated: 2018-01-13Bibliographically approved
4. Multigrid for matrix-free finite element computations on graphics processors
Open this publication in new window or tab >>Multigrid for matrix-free finite element computations on graphics processors
2017 (English)Report (Other academic)
Series
Technical report / Department of Information Technology, Uppsala University, ISSN 1404-3203 ; 2017-006
National Category
Computer Sciences Computational Mathematics
Identifiers
urn:nbn:se:uu:diva-320073 (URN)
Projects
UPMARCeSSENCE
Available from: 2017-04-20 Created: 2017-04-13 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

fulltext(1002 kB)161 downloads
File information
File name FULLTEXT01.pdfFile size 1002 kBChecksum SHA-512
3966b6481c78ea0a6147a18c160b2f1051f0c3b481e26c2c7e482bece68b393e040970ae29f77ad3fafaf92c61a046f833ed9aa73727e0a848299c75ff789302
Type fulltextMimetype application/pdf
Buy this publication >>

Search in DiVA

By author/editor
Ljungkvist, Karl
By organisation
Division of Scientific ComputingComputational Science
Computer SciencesComputational Mathematics

Search outside of DiVA

GoogleGoogle Scholar
Total: 161 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: 1006 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • 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