2.50
Hdl Handle:
http://hdl.handle.net/10547/272038
Title:
Parallel MLEM on multicore architectures
Authors:
Kustner, Tilman; Weidendorfer, Josef; Schirmer, Jasmine; Klug, Tobias; Trinitis, Carsten; Ziegler, Sybille
Abstract:
The efficient use of multicore architectures for sparse matrix-vector multiplication (SpMV) is currently an open challenge. One algorithm which makes use of SpMV is the maximum likelihood expectation maximization (MLEM) algorithm. When using MLEM for positron emission tomography (PET) image reconstruction, one requires a particularly large matrix. We present a new storage scheme for this type of matrix which cuts the memory requirements by half, compared to the widely-used compressed sparse row format. For parallelization we combine the two partitioning techniques recursive bisection and striping. Our results show good load balancing and cache behavior. We also give speedup measurements on various modern multicore systems.
Affiliation:
Technische Universität München
Citation:
Küstner, T., Weidendorfer, J., Schirmer, J., Klug, T., Trinitis, C., Ziegler, S. (2009) 'Parallel MLEM on Multicore Architectures' in ICCS '09 Proceedings of the 9th International Conference on Computational Science: Part I: 491-500
Publisher:
Springer
Issue Date:
2009
URI:
http://hdl.handle.net/10547/272038
DOI:
10.1007/978-3-642-01970-8_48
Additional Links:
http://dl.acm.org/citation.cfm?id=1561015.1560813
Type:
Conference papers, meetings and proceedings
Language:
en
ISBN:
978-3-642-01969-2
Appears in Collections:
Centre for Research in Distributed Technologies (CREDIT)

Full metadata record

DC FieldValue Language
dc.contributor.authorKustner, Tilmanen_GB
dc.contributor.authorWeidendorfer, Josefen_GB
dc.contributor.authorSchirmer, Jasmineen_GB
dc.contributor.authorKlug, Tobiasen_GB
dc.contributor.authorTrinitis, Carstenen_GB
dc.contributor.authorZiegler, Sybilleen_GB
dc.date.accessioned2013-03-13T12:52:05Z-
dc.date.available2013-03-13T12:52:05Z-
dc.date.issued2009-
dc.identifier.citationKüstner, T., Weidendorfer, J., Schirmer, J., Klug, T., Trinitis, C., Ziegler, S. (2009) 'Parallel MLEM on Multicore Architectures' in ICCS '09 Proceedings of the 9th International Conference on Computational Science: Part I: 491-500en_GB
dc.identifier.isbn978-3-642-01969-2-
dc.identifier.doi10.1007/978-3-642-01970-8_48-
dc.identifier.urihttp://hdl.handle.net/10547/272038-
dc.description.abstractThe efficient use of multicore architectures for sparse matrix-vector multiplication (SpMV) is currently an open challenge. One algorithm which makes use of SpMV is the maximum likelihood expectation maximization (MLEM) algorithm. When using MLEM for positron emission tomography (PET) image reconstruction, one requires a particularly large matrix. We present a new storage scheme for this type of matrix which cuts the memory requirements by half, compared to the widely-used compressed sparse row format. For parallelization we combine the two partitioning techniques recursive bisection and striping. Our results show good load balancing and cache behavior. We also give speedup measurements on various modern multicore systems.en_GB
dc.language.isoenen
dc.publisherSpringeren_GB
dc.relation.urlhttp://dl.acm.org/citation.cfm?id=1561015.1560813en_GB
dc.subjectsparse matrix-vector multiplicationen_GB
dc.subjectmaximum likelihood expectation maximizationen_GB
dc.titleParallel MLEM on multicore architecturesen
dc.typeConference papers, meetings and proceedingsen
dc.contributor.departmentTechnische Universität Münchenen_GB
All Items in UOBREP are protected by copyright, with all rights reserved, unless otherwise indicated.