Heterogeneous cluster for acceleration of linear algebra computations

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21240%2F12%3A00189743" target="_blank" >RIV/68407700:21240/12:00189743 - isvavai.cz</a>
Result on the web
<a href="http://journal.aplimat.com/volume_5_2012/Journal_volume_5/Number_2/Simecek_Langr.pdf" target="_blank" >http://journal.aplimat.com/volume_5_2012/Journal_volume_5/Number_2/Simecek_Langr.pdf</a>
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Heterogeneous cluster for acceleration of linear algebra computations
Original language description
Plenty of numerical algebra libraries have been developed in recent years. These libraries are tuned for the given CPU and its memory architecture, fully utilize its memory hierarchy and inner pipelines and achieve impressive computation power. There isalso a new trend in the high-performance computing: GPU computing. This paper deals with a new concept of the heterogeneous grid for acceleration of the numerical linear algebra computing. We design this grid with respect to maximal ratio between cost and computational power. It allows a parallelization of scientific codes with minimal programming effort. We also optimize grid concept to be less sensitive to network parameters.
Czech name
—
Czech description
—

Type
J<sub>x</sub> - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)
CEP classification
IN - Informatics
OECD FORD branch
—

Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)