Please use this identifier to cite or link to this item: http://hdl.handle.net/1822/26070

TitleclOpenCL : supporting distributed heterogeneous computing in HPC clusters
Author(s)Alves, Albano Agostinho Gomes
Rufino, José
Pina, António Manuel Silva
Santos, Luís Paulo
KeywordsHeterogeneous Systems
Cluster
OpenCL
GPGPU
Heterogeneous/Cluster/GPGPU Computing
Issue date2013
PublisherSpringer
JournalLecture Notes in Computer Science
Abstract(s)Clusters that combine heterogeneous compute device architectures, coupled with novel programming models, have created a true alternative to traditional (homogeneous) cluster computing, allowing to leverage the performance of parallel applications. In this paper we introduce clOpenCL, a platform that supports the simple deployment and efficient running of OpenCL-based parallel applications that may span several cluster nodes, expanding the original single-node OpenCL model. clOpenCL is deployed through user level services, thus allowing OpenCL applications from different users to share the same cluster nodes and their compute devices. Data exchanges between distributed clOpenCL components rely on Open-MX, a high-performance communication library. We also present extensive experimental data and key conditions that must be addressed when exploiting clOpenCL with real applications.
TypeConference paper
URIhttp://hdl.handle.net/1822/26070
ISBN9783642369483
DOI10.1007/978-3-642-36949-0_14
ISSN0302-9743
Peer-Reviewedyes
AccessOpen access
Appears in Collections:DI/CCTC - Artigos (papers)

Files in This Item:
File Description SizeFormat 
HeteroPar2012-clOpenCL.pdfDocumento Principal702,76 kBAdobe PDFView/Open

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu ORCID