000155246 001__ 155246
000155246 005__ 20210129214040.0
000155246 020__ $$a978-3-540-63138-5 (print)
000155246 020__ $$a978-3-540-69157-0 (electronic)
000155246 0247_ $$2doi$$a10.1007/3-540-63138-0_7
000155246 0247_ $$2ISSN$$a1611-3349
000155246 0247_ $$2ISSN$$a0302-9743
000155246 037__ $$aFZJ-2014-04420
000155246 082__ $$a004
000155246 1001_ $$0P:(DE-HGF)0$$aBücker, H. Martin$$b0$$eCorresponding Author
000155246 1112_ $$aFourth International Symposium on Solving Irregularly Structured Problems in Parallel$$cPaderborn$$d1997-06-11 - 1997-06-13$$gIRREGULAR '97$$wGermany
000155246 245__ $$aA variant of the biconjugate gradient method suitable for massively parallel computing
000155246 260__ $$aBerlin, Heidelberg$$bSpringer Berlin Heidelberg$$c1997
000155246 29510 $$aSolving Irregularly Structured Problems in Parallel
000155246 300__ $$a72 - 79
000155246 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1408542542_5994
000155246 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000155246 3367_ $$033$$2EndNote$$aConference Paper
000155246 3367_ $$2ORCID$$aCONFERENCE_PAPER
000155246 3367_ $$2DataCite$$aOutput Types/Conference Paper
000155246 3367_ $$2DRIVER$$aconferenceObject
000155246 3367_ $$2BibTeX$$aINPROCEEDINGS
000155246 4900_ $$aLecture Notes in Computer Science$$v1253
000155246 520__ $$aStarting from a specific implementation of the Lanczos biorthogonalization algorithm, an iterative process for the solution of systems of linear equations with general non-Hermitian coefficient matrix is derived. Due to the orthogonalization of the underlying Lanczos process the resulting iterative scheme involves inner products leading to global communication and synchronization on parallel processors. For massively parallel computers, these effects cause considerable delays often preventing the scalability of the implementation. In the process proposed, all inner product-like operations of an iteration step are independent such that the implementation consists of only a single global synchronization point per iteration. In exact arithmetic, the process is shown to be mathematically equivalent to the biconjugate gradient method. The efficiency of this new variant is demonstrated by numerical experiments on a PARAGON system using up to 121 processors.
000155246 536__ $$0G:(DE-HGF)POF2-899$$a899 - ohne Topic (POF2-899)$$cPOF2-899$$fPOF I$$x0
000155246 588__ $$aDataset connected to CrossRef Book, juser.fz-juelich.de
000155246 7001_ $$0P:(DE-HGF)0$$aSauren, Manfred$$b1
000155246 773__ $$a10.1007/3-540-63138-0_7
000155246 8564_ $$uhttps://juser.fz-juelich.de/record/155246/files/FZJ-2014-04420.pdf$$yRestricted
000155246 909CO $$ooai:juser.fz-juelich.de:155246$$pVDB
000155246 9132_ $$0G:(DE-HGF)POF3-899$$1G:(DE-HGF)POF3-890$$2G:(DE-HGF)POF3-800$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vohne Topic$$x0
000155246 9131_ $$0G:(DE-HGF)POF2-899$$1G:(DE-HGF)POF2-890$$2G:(DE-HGF)POF2-800$$3G:(DE-HGF)POF2$$4G:(DE-HGF)POF$$aDE-HGF$$bProgrammungebundene Forschung$$lohne Programm$$vohne Topic$$x0
000155246 915__ $$0StatID:(DE-HGF)0020$$2StatID$$aNo Peer review
000155246 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR
000155246 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection
000155246 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bThomson Reuters Master Journal List
000155246 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000155246 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz
000155246 920__ $$lyes
000155246 9201_ $$0I:(DE-Juel1)VDB62$$kZAM$$lZentralinstitut für Angewandte Mathematik$$x0
000155246 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x1
000155246 980__ $$acontrib
000155246 980__ $$aVDB
000155246 980__ $$acontb
000155246 980__ $$aI:(DE-Juel1)VDB62
000155246 980__ $$aI:(DE-Juel1)JSC-20090406
000155246 980__ $$aUNRESTRICTED
000155246 981__ $$aI:(DE-Juel1)JSC-20090406