liu.seSök publikationer i DiVA
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Customizing Instruction Set Extensible Reconfigurable Processors using GPUs
Linköpings universitet, Institutionen för datavetenskap, ESLAB - Laboratoriet för inbyggda system. Linköpings universitet, Tekniska högskolan.
Linköpings universitet, Institutionen för datavetenskap, ESLAB - Laboratoriet för inbyggda system. Linköpings universitet, Tekniska högskolan.
Technical University of Munich, Germany.
Technical University of Munich, Germany.
Visa övriga samt affilieringar
2012 (Engelska)Ingår i: 25th International Conferennce on VLSI Design, Hyderabad, India, January 07-11, 2012., IEEE , 2012, s. 418-423Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Many reconfigurable processors allow their instruction sets to be tailored according to the performance requirements of target applications. They have gained immense popularity in recent years because of this flexibility of adding custom instructions. However, most design automation algorithms for instruction set customization (like enumerating and selecting the optimal set of custom instructions) are computationally intractable. As such, existing tools to customize instruction sets of extensible processors rely on approximation methods or heuristics. In contrast to such traditional approaches, we propose to use GPUs (Graphics Processing Units) to efficiently solve computationally expensive algorithms in the design automation tools for extensible processors. To demonstrate our idea, we choose a custom instruction selection problem and accelerate it using CUDA (CUDA is a GPU computing engine). Our CUDA implementation is devised to maximize the achievable speedups by various optimizations like exploiting on-chip shared memory and register usage. Experiments conducted on well known benchmarks show significant speedups over sequential CPU implementations as well as over multi-core implementations.

Ort, förlag, år, upplaga, sidor
IEEE , 2012. s. 418-423
Serie
VLSI Design : Proceedings / the ... International Conference on VLSI Design, ISSN 1063-9667
Nationell ämneskategori
Teknik och teknologier
Identifikatorer
URN: urn:nbn:se:liu:diva-72205ISBN: 978-0-7695-4638-4 (tryckt)ISBN: 978-1-4673-0438-2 (tryckt)OAI: oai:DiVA.org:liu-72205DiVA, id: diva2:458264
Konferens
25th International Conferennce on VLSI Design, Hyderabad, India, January 07-11, 2012.
Tillgänglig från: 2011-11-22 Skapad: 2011-11-22 Senast uppdaterad: 2013-09-10

Open Access i DiVA

Fulltext saknas i DiVA

Personposter BETA

Bordoloi, Unmesh D.Suri, BharathEles, PetruPeng, Zebo

Sök vidare i DiVA

Av författaren/redaktören
Bordoloi, Unmesh D.Suri, BharathEles, PetruPeng, Zebo
Av organisationen
ESLAB - Laboratoriet för inbyggda systemTekniska högskolan
Teknik och teknologier

Sök vidare utanför DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetricpoäng

isbn
urn-nbn
Totalt: 268 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf