Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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
Igenkänning av instanslösningar i OpenCL – En undersökning av en plattformsoberoende parallellprogrammeringsimplementation.
KTH, School of Computer Science and Communication (CSC).
KTH, School of Computer Science and Communication (CSC).
2011 (Swedish)Independent thesis Advanced level (professional degree), 10 credits / 15 HE creditsStudent thesis
Abstract [en]

In recent years parallel computing has become increasingly important. In a regular PC today lies often a FLOPS-capacity surpassing the capacity of a single core in the CPU by far. OpenCL is a standardized framework that allows the programmer to write code able to execute on any computational unit having supporting drivers. This thesis examines the framework by an implementation doing exhaustive searches in order to find solutions to instances of the NP-complete problem of verbal arithmetic. The results imply that this kind of computation is unsuited for processing units without efficient support for random access, but on the other hand showing excellent performance on the ones that do.

Abstract [sv]

På senare år har parallell beräkning blivit allt mer viktigt. En vanlig PC idag har en sammanlagd FLOPS-kapacitet som överstiger kapaciteten en ensam CPU-kärna i PC:n kan erbjuda. OpenCL är ett standardiserat ramverk byggt för portabel parallellberäkning på heterogena system så länge enheterna i systemen har drivrutiner. I denna rapport undersöker vi ramverket genom att göra en implementation som utför uttömmande sökningar för att hitta lösningar till instanser av det NP-fullständiga problemet verbalaritmetik. Resultaten visar att denna typ av beräkning är olämpad för processeringsenheter som inte har stöd för effektiv random access, men är utmärkt för de som har detta stöd.

Place, publisher, year, edition, pages
2011.
Series
Kandidatexjobb CSC, K11007
National Category
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-130808OAI: oai:DiVA.org:kth-130808DiVA: diva2:654255
Educational program
Master of Science in Engineering - Computer Science and Technology
Uppsok
Technology
Supervisors
Examiners
Available from: 2013-10-07 Created: 2013-10-07

Open Access in DiVA

No full text

Other links

http://www.csc.kth.se/utbildning/kandidatexjobb/datateknik/2011/rapport/bjorkman_carl_OCH_cupurdija_michel_K11007.pdf
By organisation
School of Computer Science and Communication (CSC)
Computer Science

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 85 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • 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