000860344 001__ 860344
000860344 005__ 20200914095805.0
000860344 020__ $$a978-3-540-64443-9 (print)
000860344 020__ $$a978-3-540-69783-1 (electronic)
000860344 0247_ $$2doi$$a10.1007/BFb0037171
000860344 0247_ $$2ISSN$$a0302-9743
000860344 0247_ $$2ISSN$$a1611-3349
000860344 037__ $$aFZJ-2019-01119
000860344 1001_ $$0P:(DE-Juel1)132179$$aLippert, Th.$$b0$$ufzj
000860344 1112_ $$aInternational Conference on High-Performance Computing and Networking$$cAmsterdam$$d1998-04-21 - 1998-04-23$$wThe Netherlands
000860344 245__ $$aTranspose algorithm for FFT on APE/Quadrics
000860344 260__ $$aBerlin, Heidelberg$$bSpringer Berlin Heidelberg$$c1998
000860344 29510 $$aHigh-Performance Computing and Networking / Sloot, Peter (Editor)   ; Berlin, Heidelberg : Springer Berlin Heidelberg, 1998, Chapter 46 ; ISSN: 0302-9743=1611-3349 ; ISBN: 978-3-540-64443-9=978-3-540-69783-1 ; doi:10.1007/BFb0037125
000860344 300__ $$a439 - 448
000860344 3367_ $$2ORCID$$aCONFERENCE_PAPER
000860344 3367_ $$033$$2EndNote$$aConference Paper
000860344 3367_ $$2BibTeX$$aINPROCEEDINGS
000860344 3367_ $$2DRIVER$$aconferenceObject
000860344 3367_ $$2DataCite$$aOutput Types/Conference Paper
000860344 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1600070267_27411
000860344 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000860344 4900_ $$aLecture Notes in Computer Science$$v1401
000860344 520__ $$aWe describe a novel practical parallel FFT scheme designed for SIMD systems and/or data parallel programming. A bit-exchange of elements between the processors is avoided by means of the ‘Transpose Algorithm’. Our transposition is based on the assignment of the data field onto a 1-dimensional ring of systolic cells which subsequently is mapped onto a ring of processors, realized as a subset of the system's connectivity. We have implemented and benchmarked a 2-dimensional parallel FFT code on the APE100/Quadrics parallel computer, where–due to a rigid next-neighbour connectivity and lack of local addressing–efficient FFT implementations could not be realized so far.
000860344 588__ $$aDataset connected to CrossRef Book Series
000860344 7001_ $$0P:(DE-HGF)0$$aSchilling, K.$$b1
000860344 7001_ $$0P:(DE-HGF)0$$aToschi, F.$$b2
000860344 7001_ $$0P:(DE-HGF)0$$aTrentmann, S.$$b3
000860344 7001_ $$0P:(DE-HGF)0$$aTripiccione, R.$$b4
000860344 773__ $$a10.1007/BFb0037171
000860344 909CO $$ooai:juser.fz-juelich.de:860344$$pextern4vita
000860344 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132179$$aForschungszentrum Jülich$$b0$$kFZJ
000860344 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$aExternal Institute$$b1$$kExtern
000860344 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz
000860344 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS
000860344 980__ $$acontrib
000860344 980__ $$aEDITORS
000860344 980__ $$acontb
000860344 980__ $$aI:(DE-Juel1)JSC-20090406
000860344 980__ $$aI:(DE-Juel1)NIC-20090406
000860344 9801_ $$aEXTERN4VITA