hh.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • 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
The REMAP Reconfigurable Architecture: a Retrospective
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS). Chalmers University of Technology, Gothenburg, Sweden.
Chalmers University of Technology, Gothenburg, Sweden.
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS). Telecommunications Research Center Vienna (FTW), Vienna, Austria.ORCID-id: 0000-0002-0562-2082
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), Centrum för forskning om inbyggda system (CERES).ORCID-id: 0000-0001-6625-6533
Vise andre og tillknytning
2006 (engelsk)Inngår i: FPGA Implementations of Neural Networks, New York: Springer-Verlag New York, 2006, s. 325-360Kapittel i bok, del av antologi (Fagfellevurdert)
Abstract [en]

The goal of the REMAP project was to gain new knowledge about the design and use of massively parallel computer architectures in embedded real-time systems. In order to support adaptive and learning behavior in such systems, the efficient execution of Artificial Neural Network (ANN) algorithms on regular processor arrays was in focus. The REMAP-β parallel computer built in the project was designed with ANN computations as the main target application area. This chapter gives an overview of the computational requirements found in ANN algorithms in general and motivates the use of regular processor arrays for the efficient execution of such algorithms. REMAP-β was implemented using the FPGA circuits that were available around 1990. The architecture, following the SIMD principle (Single Instruction stream, Multiple Data streams), is described, as well as the mapping of some important and representative ANN algorithms. Implemented in FPGA, the system served as an architecture laboratory. Variations of the architecture are discussed, as well as scalability of fully synchronous SIMD architectures. The design principles of a VLSI-implemented successor of REMAP-β are described, and the paper is concluded with a discussion of how the more powerful FPGA circuits of today could be used in a similar architecture. © 2006 Springer.

sted, utgiver, år, opplag, sider
New York: Springer-Verlag New York, 2006. s. 325-360
Emneord [en]
Artificial neural networks, parallel architecture, SIMD, field-programmable gate arrays (FPGA)
HSV kategori
Identifikatorer
URN: urn:nbn:se:hh:diva-377DOI: 10.1007/0-387-28487-7_12Scopus ID: 2-s2.0-84889954052Lokal ID: 2082/701ISBN: 0-387-28485-0 (tryckt)OAI: oai:DiVA.org:hh-377DiVA, id: diva2:237556
Tilgjengelig fra: 2007-01-10 Laget: 2007-01-10 Sist oppdatert: 2018-03-23bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Bengtsson, LarsNordström, TomasSvensson, Bertil

Søk i DiVA

Av forfatter/redaktør
Bengtsson, LarsNordström, TomasSvensson, Bertil
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 458 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • 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