{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:39:09Z","timestamp":1740123549514,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2017,1,18]],"date-time":"2017-01-18T00:00:00Z","timestamp":1484697600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2017,8]]},"DOI":"10.1007\/s11227-017-1961-6","type":"journal-article","created":{"date-parts":[[2017,1,18]],"date-time":"2017-01-18T15:00:24Z","timestamp":1484751624000},"page":"3603-3634","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["GPU parallelization of the sequential matrix diagonalization algorithm and its application to high-dimensional data"],"prefix":"10.1007","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9456-4565","authenticated-orcid":false,"given":"Manuel","family":"Carcenac","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Soydan","family":"Redif","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Server","family":"Kasap","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,1,18]]},"reference":[{"key":"1961_CR1","volume-title":"Matrix computations","author":"GH Golub","year":"1996","unstructured":"Golub GH, Van Loan CF (1996) Matrix computations, 3rd edn. The Johns Hopkins University Press, Baltimore","edition":"3"},{"key":"1961_CR2","volume-title":"Linear systems","author":"T Kailath","year":"1980","unstructured":"Kailath T (1980) Linear systems. Prentice-Hall, Englewood Cliffs"},{"key":"1961_CR3","volume-title":"Multirate systems and filter banks","author":"PP Vaidyanathan","year":"1993","unstructured":"Vaidyanathan PP (1993) Multirate systems and filter banks. Prentice-Hall, Englewood Cliffs"},{"issue":"5","key":"1961_CR4","doi-asserted-by":"crossref","first-page":"2158","DOI":"10.1109\/TSP.2007.893222","volume":"55","author":"JG McWhirter","year":"2007","unstructured":"McWhirter JG, Baxter PD, Cooper T, Redif S, Foster J (2007) An EVD algorithm for para-Hermitian polynomial matrices. IEEE Trans Signal Proces 55(5):2158\u20132169","journal-title":"IEEE Trans Signal Proces"},{"issue":"1","key":"1961_CR5","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1109\/TSP.2014.2367460","volume":"63","author":"S Redif","year":"2015","unstructured":"Redif S, Weiss S, McWhirter JG (2015) Sequential matrix diagonalisation algorithms for polynomial EVD of parahermitian matrices. IEEE Trans Signal Proces 63(1):81\u201389","journal-title":"IEEE Trans Signal Proces"},{"key":"1961_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/ASP\/2006\/31346","volume":"3","author":"S Weiss","year":"2006","unstructured":"Weiss S, Redif S, Cooper T, Liu C, Baxter P, McWhirter JG (2006) Paraunitary oversampled filter bank design for channel coding. EURASIP J Appl Signal Process 3:1\u201310","journal-title":"EURASIP J Appl Signal Process"},{"doi-asserted-by":"crossref","unstructured":"Moret N, Tonello A, Weiss S (2011) MIMO precoding for filter bank modulation systems based on PSVD. In: Proceedings of the IEEE 73rd Vehicular Technology Conference, pp 1\u201395","key":"1961_CR7","DOI":"10.1109\/VETECS.2011.5956567"},{"issue":"7","key":"1961_CR8","doi-asserted-by":"crossref","first-page":"704","DOI":"10.1049\/iet-spr.2011.0086","volume":"6","author":"J Foster","year":"2012","unstructured":"Foster J, McWhirter JG, Lambotharan S, Proudler I, Davies M, Chambers J (2012) Polynomial matrix QR decomposition and iterative decoding of frequency selective MIMO channels. IET Signal Process 6(7):704\u2013712","journal-title":"IET Signal Process"},{"key":"1961_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.13189\/asp.2013.010101","volume":"1","author":"M Tohidian","year":"2013","unstructured":"Tohidian M, Amindavar H, Reza AM (2013) A DFT-based approximate eigenvalue and singular value decomposition of polynomial matrices. EURASIP J Adv Signal Process 1:1\u201316","journal-title":"EURASIP J Adv Signal Process"},{"doi-asserted-by":"crossref","unstructured":"Brandt R, Bengtsson M (2011) Wideband MIMO channel diagonalization in the time domain. In: Proceedings of the International Symposium on Personal, Indoor and Mobile Radio Communications, pp 1914\u20131918","key":"1961_CR10","DOI":"10.1109\/PIMRC.2011.6139853"},{"unstructured":"Lambert RH, Joho M, Mathis H (2001) Polynomial singular values for number of wideband source estimation and principal components analysis. In: Proceedings of the International Conference on Independent Component Analysis, San Diego, CA, pp 379\u2013383","key":"1961_CR11"},{"doi-asserted-by":"crossref","unstructured":"Redif S, McWhirter JG, Baxter P, Cooper T (2006) Robust broadband adaptive beamforming via polynomial eigenvalues. In: Proceedings of the IEEE Ocean Conference, pp 1\u20136","key":"1961_CR12","DOI":"10.1109\/OCEANS.2006.307113"},{"doi-asserted-by":"crossref","unstructured":"Alrmah MA, Weiss S, Redif S, Lambotharan S, McWhirter JG (2013) Angle of arrival estimation for broadband signals: a comparison. In: Proceedings of the Intelligent Signal Processing Conference. IET, London","key":"1961_CR13","DOI":"10.1049\/cp.2013.2066"},{"key":"1961_CR14","doi-asserted-by":"publisher","DOI":"10.3906\/elk-1401-19","author":"S Redif","year":"2015","unstructured":"Redif S (2015) Fetal electrocardiogram estimation using polynomial eigenvalue decomposition. Turk J Electr Eng Comput Sci. doi: 10.3906\/elk-1401-19","journal-title":"Turk J Electr Eng Comput Sci"},{"doi-asserted-by":"crossref","unstructured":"Tkacenko A (2010) Approximate eigenvalue decomposition of para-Hermitian systems through successive FIR paraunitary transformations. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Dallas, TX, USA, pp 4074\u20134077","key":"1961_CR15","DOI":"10.1109\/ICASSP.2010.5495751"},{"doi-asserted-by":"crossref","unstructured":"Redif S, Weiss S, McWhirter JG (2011) An approximate polynomial matrix eigenvalue decomposition algorithm for para-Hermitian matrices. In: Proceedings of the 11th IEEE International Symposium on Signal Processing and Information Technology, Bilbao, Spain, pp 421\u2013425","key":"1961_CR16","DOI":"10.1109\/ISSPIT.2011.6151599"},{"issue":"11","key":"1961_CR17","doi-asserted-by":"crossref","first-page":"5253","DOI":"10.1109\/TSP.2011.2163065","volume":"59","author":"S Redif","year":"2011","unstructured":"Redif S, McWhirter JG, Weiss S (2011) Design of FIR paraunitary filter banks for subband coding using a polynomial eigenvalue decomposition. IEEE Trans Signal Process 59(11):5253\u20135264","journal-title":"IEEE Trans Signal Process"},{"unstructured":"Redif S (2006) Polynomial matrix decompositions and paraunitary filter banks. Ph.D. Thesis, University of Southampton, ECS, Southampton, UK","key":"1961_CR18"},{"issue":"3","key":"1961_CR19","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1109\/TVLSI.2014.2312997","volume":"23","author":"S Redif","year":"2015","unstructured":"Redif S, Kasap S (2015) Novel reconfigurable hardware architecture for polynomial matrix multiplications. IEEE Trans VLSI Syst 23(3):454\u2013465","journal-title":"IEEE Trans VLSI Syst"},{"issue":"6","key":"1961_CR20","doi-asserted-by":"crossref","first-page":"1528","DOI":"10.1109\/78.678466","volume":"46","author":"PP Vaidyanathan","year":"1998","unstructured":"Vaidyanathan PP (1998) Theory of optimal orthonormal subband coders. IEEE Trans Signal Process 46(6):1528\u20131543","journal-title":"IEEE Trans Signal Process"},{"unstructured":"Nvidia Corporation (2015) CUDA toolkit documentation v7.5. http:\/\/docs.nvidia.com\/cuda","key":"1961_CR21"},{"unstructured":"Nvidia Corporation (2015) CUBLAS library documentation v7.5. http:\/\/docs.nvidia.com\/cuda\/cublas","key":"1961_CR22"},{"issue":"1","key":"1961_CR23","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1016\/j.parco.2008.10.002","volume":"35","author":"A Buttari","year":"2009","unstructured":"Buttari A, Langou J, Kurzak J, Dongarra J (2009) A class of parallel tiled linear algebra algorithms for multicore architectures. Parallel Comput 35(1):38\u201353","journal-title":"Parallel Comput"},{"doi-asserted-by":"crossref","unstructured":"Agullo E, Augonnet C, Dongarra J, Faverge M, Langou J, Ltaief H, Tomov S (2011) LU factorization for accelerator-based systems. In: Proceedings of the AICCSA\u2019 11th Conference, pp 217\u2013224","key":"1961_CR24","DOI":"10.1109\/AICCSA.2011.6126599"},{"issue":"1","key":"1961_CR25","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1007\/s11227-013-1043-3","volume":"68","author":"M Carcenac","year":"2014","unstructured":"Carcenac M (2014) From tile algorithm to stripe algorithm: a CUBLAS-based parallel implementation on GPUs of Gauss method for the resolution of extremely large dense linear systems stored on an array of solid state devices. J Supercomput 68(1):365\u2013413","journal-title":"J Supercomput"},{"unstructured":"TurboSquid, 3D models. http:\/\/www.turbosquid.com","key":"1961_CR26"},{"key":"1961_CR27","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/s10489-015-0715-5","volume":"44","author":"M Carcenac","year":"2016","unstructured":"Carcenac M, Redif S (2016) A highly scalable modular bottleneck neural network for image dimensionality reduction and image transformation. Appl Intell 44:557\u2013610. doi: 10.1007\/s10489-015-0715-5","journal-title":"Appl Intell"},{"unstructured":"Pal D (2010) Image processing through fuzzy logic. InL 2010 IEEE Information Reuse and Integration Conference, August 4\u20136, Las Vegas","key":"1961_CR28"},{"unstructured":"Himanshu T, Srinivas MB, Arabnia HR (2005) A need of quantum computing: reversible logic synthesis of parallel binary adder\u2013subtractor. In: Proceeings of the 2005 International Conference on Embedded Systems and Applications (ESA\u201905), June, Las Vegas, pp 60\u201368","key":"1961_CR29"},{"doi-asserted-by":"crossref","unstructured":"Thapliyal H, Arabnia HR, Vinod AP (2006) Combined integer and floating point multiplication architecture (CIFM) for FPGAs and its reversible logic implementation. In: 49th IEEE International Midwest Symposium on Circuits and Systems (MWSCAS\u201906), San Juan, August 6\u20139, Puerto Rico, pp 148\u2013154","key":"1961_CR30","DOI":"10.1109\/MWSCAS.2006.382306"},{"unstructured":"Gopineedi PD, Thapliyal H, Srinivas MB, Arabnia HR (2006) Novel and efficient 4:2 and 5:2 compressors with minimum number of transistors designed for low-power operations. In: Proceedings of the 2006 International Conference on Embedded Systems and Applications (ESA\u201906), June 26\u201329, Las Vegas, ISBN: 1-60132-017-5 160\u2013166","key":"1961_CR31"},{"unstructured":"Thapliyal H, Arabnia HR (2006) Reversible programmable logic array (RPLA) using Fredkin and Feynman gates for industrial electronics and applications. In: Proceeding of the 2006 International Conference on Computer Design & Conference on Computing in Nanotechnology (CDES\u201906), June 26\u201329, Las Vegas, pp 70\u201374","key":"1961_CR32"},{"unstructured":"Thapliyal H, Arabnia HR, Bajpai R, Sharma KK (2007) Combined integer and variable precision (CIVP) floating point multiplication architecture for FPGAs. In: Proceedings of the 2007 International Conference on Parallel & Distributed Processing Techniques & Applications (PDPTA\u201907), USA, pp 449\u2013450","key":"1961_CR33"},{"doi-asserted-by":"crossref","unstructured":"Thapliyal H, Arabnia HR, Srinivas MB (2009) Efficient reversible logic design of BCD subtractors. In: Transactions on computational science journal, III, LNCS vol 5300. Springer, Berlin, pp 99\u2013121","key":"1961_CR34","DOI":"10.1007\/978-3-642-00212-0_6"},{"unstructured":"Balasubramanian P, Edwards DA, Arabnia HR (2011) Robust asynchronous carry lookahead adders. In: Proceedings of the International Conference on Computer Design (CDES\u201911), July, USA, pp 119\u2013124","key":"1961_CR35"},{"unstructured":"Balasubramanian P, Arisaka R, Arabnia HR (2012) RB_DSOP: a rule based disjoint sum of products synthesis method. In: Proceedings of the 2012 International Conference on Computer Design (CDES\u201912), July, Las Vegas, pp 39\u201343","key":"1961_CR36"},{"doi-asserted-by":"crossref","unstructured":"Thapliyal H, Jayashree HV, Nagamani AN, Arabnia HR (2013) Progress in reversible processor design: a novel methodology for reversible carry look-ahead adder. In: Gavrilova ML, Tan CJK (eds) Transactions in computational science (Springer), XVII, LNCS 7420. Springer, Berlin, pp 73\u201397","key":"1961_CR37","DOI":"10.1007\/978-3-642-35840-1_4"},{"issue":"9","key":"1961_CR38","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1109\/12.954513","volume":"50","author":"S Yu","year":"2001","unstructured":"Yu S, Swartzlander EE Jr (2001) DCT implementation with distributed arithmetic. IEEE Trans Comput 50(9):985\u2013991","journal-title":"IEEE Trans Comput"},{"key":"1961_CR39","first-page":"161","volume-title":"Application specific processors","author":"HS Lim","year":"1996","unstructured":"Lim HS (1996) Multidimensional systolic arrays for computing discrete Fourier transform and discrete cosine transform, Chapter 6. In: Swartzlander EE Jr (ed) Application specific processors. Kluwer, Boston, pp 161\u2013195"},{"unstructured":"Bodda C, Steenbock N (2001) Singular value decomposition on distributed reconfigurable systems. In: Proceedings of the 12th International Workshop Rapid System Prototyping, pp 38\u201343","key":"1961_CR40"},{"key":"1961_CR41","first-page":"369","volume":"3","author":"A Ahmedsaid","year":"2004","unstructured":"Ahmedsaid A, Amira A, Bouridane A (2004) Accelerating MUSIC method on reconfigurable hardware for source localization. Proc Int Symp Circuits Syst 3:369\u2013372","journal-title":"Proc Int Symp Circuits Syst"},{"issue":"12","key":"1961_CR42","doi-asserted-by":"crossref","first-page":"1722","DOI":"10.1109\/TVLSI.2008.2001939","volume":"16","author":"I Bravo","year":"2008","unstructured":"Bravo I, Mazo M, Lazaro JL, Jimenez P, Gardel A, Marron M (2008) Novel HW architecture based on FPGAs oriented to solve the eigen problem. IEEE Trans VLSI Syst 16(12):1722\u20131725","journal-title":"IEEE Trans VLSI Syst"},{"issue":"12","key":"1961_CR43","doi-asserted-by":"crossref","first-page":"1646","DOI":"10.1080\/00207217.2012.751343","volume":"100","author":"S Redif","year":"2013","unstructured":"Redif S, Kasap S (2013) Parallel algorithm for computation of second-order sequential best rotations. Int J Electron 100(12):1646\u20131651 ISSN: 0020-7217","journal-title":"Int J Electron"},{"issue":"3","key":"1961_CR44","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1109\/TVLSI.2013.2248069","volume":"22","author":"S Kasap","year":"2014","unstructured":"Kasap S, Redif S (2014) Novel field-programmable gate array architecture for computing the eigenvalue decomposition of para-Hermitian polynomial matrices. IEEE Trans VLSI Syst 22(3):522\u2013536","journal-title":"IEEE Trans VLSI Syst"},{"key":"1961_CR45","volume-title":"The Fourier transform and its applications","author":"R Bracewell","year":"1999","unstructured":"Bracewell R (1999) The Fourier transform and its applications. McGraw-Hill, New York"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-017-1961-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-017-1961-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-017-1961-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,22]],"date-time":"2022-07-22T00:44:05Z","timestamp":1658450645000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-017-1961-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,18]]},"references-count":45,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2017,8]]}},"alternative-id":["1961"],"URL":"https:\/\/doi.org\/10.1007\/s11227-017-1961-6","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2017,1,18]]}}}