RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Advances in Task-Based Parallel Programming for Distributed Memory Architectures
Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Avdelningen för beräkningsvetenskap. Uppsala universitet, Teknisk-naturvetenskapliga vetenskapsområdet, Matematisk-datavetenskapliga sektionen, Institutionen för informationsteknologi, Tillämpad beräkningsvetenskap.
2018 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

It has become common knowledge that parallel programming is needed for scientific applications, particularly for running large scale simulations. Different programming models are introduced for simplifying parallel programming, while enabling an application to use the full computational capacity of the hardware. In task-based programming, all the variables in the program are abstractly viewed as data. Parallelism is provided by partitioning the data. A task is a collection of operations performed on input data to generate output data. In distributed memory environments, the data is distributed over the computational nodes (or processes), and is communicated when a task needs remote data.

This thesis discusses advanced techniques in distributed task-based parallel programming, implemented in the DuctTeip software library. DuctTeip uses MPI (Message Passing Interface) for asynchronous inter-process communication and Pthreads for shared memory parallelization within the processes. The data dependencies that determine which subsets of tasks can be executed in parallel are extracted from information about the data accesses (input or output) of the tasks. A versioning system is used internally to represent the task-data dependencies efficiently. A hierarchical partitioning of tasks and data allows for independent optimization of the size of computational tasks and the size of communicated data. A data listener technique is used to manage communication efficiently.

DuctTeip provides an algorithm independent dynamic load balancing functionality. Redistributing tasks from busy processes to idle processes dynamically can provide an overall shorter execution time. A random search method with high probability of success is employed for locating idle/busy nodes.

The advantage of the abstract view of tasks and data is exploited in a unified programming interface, which provides a standard for task-based frameworks to decouple framework development from application development. The interface can be used for collaboration between different frameworks in running an application program efficiently on different hardware.

To evaluate the DuctTeip programming model, applications such as Cholesky factorization, a time-dependent PDE solver for the shallow water equations, and the fast multipole method have been implemented using DuctTeip. Experiments show that DuctTeip provides both scalability and performance. Comparisons with similar frameworks such as StarPU, OmpSs, and PaRSEC show competitive results.

sted, utgiver, år, opplag, sider
Uppsala: Acta Universitatis Upsaliensis, 2018. , s. 42
Serie
Digital Comprehensive Summaries of Uppsala Dissertations from the Faculty of Science and Technology, ISSN 1651-6214 ; 1621
Emneord [en]
parallel programming, task-based programming, distributed memory system, scientific computing, hierarchical data, hierarchical tasks
HSV kategori
Identifikatorer
URN: urn:nbn:se:uu:diva-338838ISBN: 978-91-513-0209-6 (tryckt)OAI: oai:DiVA.org:uu-338838DiVA, id: diva2:1173783
Disputas
2018-03-02, ITC/2446, ITC, Lägerhyddsvägen 2, Uppsala, 10:00 (engelsk)
Opponent
Veileder
Tilgjengelig fra: 2018-02-09 Laget: 2018-01-14 Sist oppdatert: 2018-03-08
Delarbeid
1. Programming models based on data versioning for dependency-aware task-based parallelisation
Åpne denne publikasjonen i ny fane eller vindu >>Programming models based on data versioning for dependency-aware task-based parallelisation
2012 (engelsk)Inngår i: Proc. 15th International Conference on Computational Science and Engineering, Los Alamitos, CA: IEEE Computer Society, 2012, s. 275-280Konferansepaper, Publicerat paper (Fagfellevurdert)
sted, utgiver, år, opplag, sider
Los Alamitos, CA: IEEE Computer Society, 2012
HSV kategori
Identifikatorer
urn:nbn:se:uu:diva-187446 (URN)10.1109/ICCSE.2012.45 (DOI)000317475000038 ()978-1-4673-5165-2 (ISBN)
Konferanse
CSE 2012
Prosjekter
eSSENCEUPMARC
Tilgjengelig fra: 2013-01-24 Laget: 2012-12-06 Sist oppdatert: 2018-01-16bibliografisk kontrollert
2. DuctTeip: An efficient programming model for distributed task based parallel computing
Åpne denne publikasjonen i ny fane eller vindu >>DuctTeip: An efficient programming model for distributed task based parallel computing
2018 (engelsk)Inngår i: Computing Research Repository, nr 1801.03578Artikkel i tidsskrift (Annet vitenskapelig) Submitted
HSV kategori
Identifikatorer
urn:nbn:se:uu:diva-338832 (URN)
Prosjekter
UPMARCeSSENCE
Tilgjengelig fra: 2018-01-10 Laget: 2018-01-14 Sist oppdatert: 2018-04-18bibliografisk kontrollert
3. TaskUniVerse: A Task-Based Unified Interface for Versatile Parallel Execution
Åpne denne publikasjonen i ny fane eller vindu >>TaskUniVerse: A Task-Based Unified Interface for Versatile Parallel Execution
2018 (engelsk)Inngår i: Parallel Processing and Applied Mathematics: Part I, Springer, 2018, s. 169-184Konferansepaper, Publicerat paper (Fagfellevurdert)
sted, utgiver, år, opplag, sider
Springer, 2018
Serie
Lecture Notes in Computer Science ; 10777
HSV kategori
Identifikatorer
urn:nbn:se:uu:diva-338836 (URN)10.1007/978-3-319-78024-5_16 (DOI)978-3-319-78023-8 (ISBN)
Konferanse
PPAM 2017
Prosjekter
eSSENCE
Tilgjengelig fra: 2018-03-23 Laget: 2018-01-14 Sist oppdatert: 2018-03-26bibliografisk kontrollert
4. Task parallel implementation of a solver for electromagnetic scattering problems
Åpne denne publikasjonen i ny fane eller vindu >>Task parallel implementation of a solver for electromagnetic scattering problems
Vise andre…
2018 (engelsk)Inngår i: Computing Research Repository, nr 1801.03589Artikkel i tidsskrift (Annet vitenskapelig) Submitted
HSV kategori
Identifikatorer
urn:nbn:se:uu:diva-338833 (URN)
Prosjekter
eSSENCE
Tilgjengelig fra: 2018-01-11 Laget: 2018-01-14 Sist oppdatert: 2018-04-18bibliografisk kontrollert
5. Distributed dynamic load balancing for task parallel programming
Åpne denne publikasjonen i ny fane eller vindu >>Distributed dynamic load balancing for task parallel programming
2018 (engelsk)Inngår i: Computing Research Repository, nr 1801.04582Artikkel i tidsskrift (Annet vitenskapelig) Submitted
HSV kategori
Identifikatorer
urn:nbn:se:uu:diva-338835 (URN)
Prosjekter
UPMARCeSSENCE
Tilgjengelig fra: 2018-01-14 Laget: 2018-01-14 Sist oppdatert: 2018-04-18bibliografisk kontrollert

Open Access i DiVA

fulltext(795 kB)120 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 795 kBChecksum SHA-512
ff83de16d1f6cd1e08f2e5e45476d07986401fd6a62cf15014e0a47c96defa43941d3d4c96f69d1205f16a0cde18859033dd8df95081bb064f7243bdd9ac25b0
Type fulltextMimetype application/pdf
Kjøp publikasjonen >>

Søk i DiVA

Av forfatter/redaktør
Zafari, Afshin
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 120 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

isbn
urn-nbn

Altmetric

isbn
urn-nbn
Totalt: 932 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf