Dataflow dot product on networks of heterogeneous digit-serial arithmetic units

DSpace/Manakin Repository

Show simple item record

dc.contributor.author Laboratoire de l'informatique du parallélisme en_US
dc.contributor.author Duprat, Jean en_US
dc.contributor.author Fiallos-Aguilar, Mario en_US
dc.date.accessioned 2007-05-24T11:53:08Z
dc.date.available 2007-05-24T11:53:08Z
dc.date.issued 1992-03-30 en_US
dc.identifier.other LIP-RR - 1993-10 en_US
dc.identifier.uri http://hdl.handle.net/2332/1182
dc.description.abstract (eng) In this paper we deal with a new high precision computation of the dot product. The key idea is to use hundreds of digit-serial arithmetic units that allow a massive digit-level pipelining. Parallel discrete-event simulations performed on a memory-distributed massively parallel computer show that with a limited number of arithmetic units, the computation of dot product when performed using a ``classical'' algorithmic technique (i.e. serial cumulative multiplications) is almost as fast as the case where an ``optimal'' divide-and-conquer algorithmic technique is used. Interconnection networks for both algorithmic techniques are considered. en_US
dc.format.extent 2+17p en_US
dc.format.extent 454773 bytes
dc.format.extent 23 bytes
dc.format.mimetype application/pdf
dc.format.mimetype application/octet-stream
dc.language.iso eng en_US
dc.rights http://lara.inist.fr/utilisation.jsp en_US
dc.source.uri ftp://ftp.ens-lyon.fr/pub/LIP/Rapports/RR/RR1993/RR1993-10.ps.Z en_US
dc.subject Dataflow en_US
dc.subject Dot Product en
dc.subject Massive Pipelining en
dc.subject Digit On-Line Computation en
dc.title Dataflow dot product on networks of heterogeneous digit-serial arithmetic units en_US
dc.type Research report en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account

Bookmark and Share