{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T21:10:05Z","timestamp":1740258605199,"version":"3.37.3"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2010,7,1]],"date-time":"2010-07-01T00:00:00Z","timestamp":1277942400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Comput. Sci. Technol."],"published-print":{"date-parts":[[2010,7]]},"DOI":"10.1007\/s11390-010-9372-7","type":"journal-article","created":{"date-parts":[[2010,7,11]],"date-time":"2010-07-11T22:35:33Z","timestamp":1278887733000},"page":"874-885","source":"Crossref","is-referenced-by-count":4,"title":["A Unified Co-Processor Architecture for Matrix Decomposition"],"prefix":"10.1007","volume":"25","author":[{"given":"Yong","family":"Dou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gui-Ming","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing-Fei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan-Wu","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shi-Ce","family":"Ni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,7,11]]},"reference":[{"key":"9372_CR1","doi-asserted-by":"crossref","unstructured":"Farina A, Timmoneri L. Parallel algorithms and processing architectures for space-time adaptive processing. In Proc. Radar CIE International Conference, Beijing, China, October 8-10, 1996, pp.770-774.","DOI":"10.1109\/ICR.1996.574610"},{"key":"9372_CR2","doi-asserted-by":"crossref","unstructured":"Rabideau D J, Kogon S M. A signal processing architecture for space-based GMTI radar. In Proc. the Record of the IEEE Radar Conference, Waltham, Massachusetts, April 20-22, 1999, pp.96-101.","DOI":"10.1109\/NRC.1999.767282"},{"issue":"1","key":"9372_CR3","first-page":"1","volume":"22","author":"B Fischer","year":"1999","unstructured":"Fischer B, Modersitzki J. Fast inversion of matrices arising in image processing. Computer Science, 1999, 22(1): 1-11.","journal-title":"Computer Science"},{"key":"9372_CR4","doi-asserted-by":"crossref","unstructured":"Batchelor G H. Introduction to Fluid Dynamics. 2nd Edition, Cambridge University Press, 2000.","DOI":"10.1017\/CBO9780511800955"},{"issue":"1\u20133","key":"9372_CR5","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/0045-7949(85)90060-4","volume":"20","author":"IU Ojalvo","year":"1985","unstructured":"Ojalvo I U. Proper use of Lanczos vectors for large eigenvalue problems. Computers & Structures, 1985, 20(1-3): 115-120.","journal-title":"Computers & Structures"},{"issue":"13","key":"9372_CR6","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1002\/cpe.1301","volume":"20","author":"A Buttari","year":"2008","unstructured":"Buttari A, Langou J, Kurzak J, Dongarra J. Parallel tiled QR factorization for multicore architecture. Concurrency and Computation: Practice and Experience, 2008, 20(13): 1573-1590.","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"9372_CR7","unstructured":"The LINPACK Benchmark. http:\/\/www.netlib.org\/linpack\/ , December, 2008."},{"key":"9372_CR8","unstructured":"Xu H, Alexander W E. Parallel QR factorization on a block data flow architecture. In Proc. the 24th Southeastern Symposium and the 3rd Annual Symposium on Communications, Signal Processing Expert Systems, and ASIC VLSI Design, March 1-3, 1992, pp.332-336."},{"key":"9372_CR9","unstructured":"Fernandez L, Garcia J M. The performance of fast Givens Rotation problem implemented with MPI extensions in multicomputer. In Proc. International Conference on Applications of High-Performance Computers in Engineering, Santiago de Compostela, Espagne, July 1997, pp.83-92."},{"key":"9372_CR10","doi-asserted-by":"crossref","unstructured":"Ian N Dunn, Gerard G L Meyer. Parallel QR factorization for hybrid message passing\/shared memory operation. Journal of the Franklin Institute, 338(5): 601-613.","DOI":"10.1016\/S0016-0032(01)00023-0"},{"key":"9372_CR11","unstructured":"Hernandez V, Roman J E, Tomas A. A parallel variant of the gram-Schmidt process with reorthogonalization. In Proc. International Conference on Parallel Computing: Current & Future Issues of High-End Computing, Malaga, Spain, Sept. 13-16, 2005, pp.221-228."},{"issue":"1","key":"9372_CR12","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1137\/0912002","volume":"12","author":"CH Bischof","year":"1991","unstructured":"Bischof C H. A parallel QR factorization algorithm using local pivoting. SIAM Journal on Scientific and Statistical Computing, 1991, 12(1): 36-57.","journal-title":"SIAM Journal on Scientific and Statistical Computing"},{"key":"9372_CR13","unstructured":"Peng S, Sedukhin S, Sedukhin I. Householder bidiagonalization on parallel computers with dynamic ring architecture. In Proc. the 2nd Aizu International Symposium on Parallel Algorithms\/Architecture Synthesis, Aizu-Wakamatsu, Japan, March 17-21, 1997, pp.182-191."},{"key":"9372_CR14","doi-asserted-by":"crossref","unstructured":"R\u00fcger G, Schwind M. Comparison of different parallel modified Gram-Schmidt algorithms. In Proc. Euro-Par Parallel Processing, Lisbon, Portugal, Aug. 30-September 2, 2005, pp.826-836.","DOI":"10.1007\/11549468_90"},{"issue":"13","key":"9372_CR15","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1002\/cpe.1301","volume":"20","author":"A Buttari","year":"2008","unstructured":"Buttari A, Langou J, Kurzak J, Dongarra J. Parallel tiled QR factorization for multicore architectures. Concurrency and Computation: Practice and Experience, 2008, 20(13): 1573-1590.","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"9372_CR16","doi-asserted-by":"crossref","unstructured":"Oliveria S, Soma T. New partitioning schemes for parallel modified Gram-Schmidt orthogonalization. In Proc. the 3rd International Symposium on Parallel Architectures, Algorithms and Networks, Las Vegas, Nevada, USA, Dec. 7-9, 1997, pp.233-239.","DOI":"10.1109\/ISPAN.1997.645102"},{"key":"9372_CR17","doi-asserted-by":"crossref","unstructured":"Wilburn C Wilburn, Hak-Lim Ko, Winser E Alexander. An algorithm and architecture for the parallel solution of systems of linear equations. In Proc. IEEE Fifteenth Annual International Phoenix Conference on Computers and Communications, Arizona, USA, 1996, pp.392-398.","DOI":"10.1109\/PCCC.1996.493662"},{"key":"9372_CR18","doi-asserted-by":"crossref","unstructured":"Singh C K, Prasad S H, Balsara P T. VLSI architecture for matrix inversion using modified Gram-Schmidt based QR decomposition. In Proc. the 20th International Conference on VLSI Design, Bangalore, India, Jan. 6-10, 2007, pp.836-841.","DOI":"10.1109\/VLSID.2007.177"},{"issue":"12","key":"9372_CR19","doi-asserted-by":"crossref","first-page":"3014","DOI":"10.1109\/78.476445","volume":"43","author":"F Lorenzelli","year":"1995","unstructured":"Lorenzelli F, Yao K. A linear systolic array for recursive least squares. IEEE Transactions on Signal Processing, 1995, 43(12): 3014-3021.","journal-title":"IEEE Transactions on Signal Processing"},{"key":"9372_CR20","doi-asserted-by":"crossref","unstructured":"Liu K J R, Heieh S F , Yao K. Recursive LS filtering using block Householder transformation. In Proc. IEEE ICASSP, Albuquerque, USA, April 3-6, 1990, pp.1631-1634.","DOI":"10.1109\/ICASSP.1990.115739"},{"key":"9372_CR21","doi-asserted-by":"crossref","unstructured":"Tang C F T, Liu K J R, Tretter S A. On systolic arrays for recursive complex Householder transformations with applications to array processing. In Proc. International Conference on Acoustics, Speech, and Signal Processing, Toronto, Canada, May 14-17, 1991, pp.1033-1036.","DOI":"10.1109\/ICASSP.1991.150519"},{"key":"9372_CR22","doi-asserted-by":"crossref","unstructured":"Sergyienko A, Maslennikov O. Implementation of givens QR decomposition in FPGA. In Proc. Int. Conf. Parallel Processing and Applied Mathematics, Na Lecz\u00f3w, Porland, Sept. 9-12, 2000, pp.458-465.","DOI":"10.1007\/3-540-48086-2_50"},{"key":"9372_CR23","doi-asserted-by":"crossref","unstructured":"Yokoyama Y, Kim M, Arai H. Implementation of Systolic RLS adaptive array using FPGA and its performance evaluation. In Proc. the 64th Vehicular Technology Conference, Montreal, Canada, Sept. 25-28, 2006, pp.1-5.","DOI":"10.1109\/VTCF.2006.87"},{"key":"9372_CR24","doi-asserted-by":"crossref","unstructured":"Karkooti M, Cavallaro J R, Dick C. FPGA implementation of matrix inversion using QRD-RLS algorithm. In Conference Record of the 39th Asilomar Conference on Signals, Systems and Computers, Pacific Grove, CA, Oct. 30-Nov. 2, 2005, pp.1625-1629.","DOI":"10.1109\/ACSSC.2005.1600043"},{"key":"9372_CR25","unstructured":"Echman F, Owall V. A scalable pipelined complex valued matrix inversion architecture. In Proc. IEEE International Symposium on Circuits and Systems, Kobe, Japan, May 23-26, 2005, pp.4489-4492."},{"key":"9372_CR26","doi-asserted-by":"crossref","unstructured":"Kim D, Rajopadhye S. An improved systolic architecture for LU decomposition. In Proc. ASAP 2006, Steamboat Springs, USA, Sept. 11-13, 2006, pp.231-238.","DOI":"10.1109\/ASAP.2006.12"},{"key":"9372_CR27","doi-asserted-by":"crossref","unstructured":"Choi S, Prasanna V. Time and energy efficient matrix factorization using FPGAs. In Proc. FPL 2003, Lisbon, Portugal, Sept. 1-3, 2003, pp.507-519.","DOI":"10.1007\/978-3-540-45234-8_50"},{"issue":"1\/2","key":"9372_CR28","first-page":"15","volume":"53","author":"K Yao","year":"2007","unstructured":"Yao K, Lorenzelli F. Systolic algorithm and architecture for high-throughput processing applications. Journal of VLSI Signal Processing, 2007, 53(1\/2): 15-34.","journal-title":"Journal of VLSI Signal Processing"}],"container-title":["Journal of Computer Science and Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-010-9372-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11390-010-9372-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11390-010-9372-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,22]],"date-time":"2025-02-22T20:31:10Z","timestamp":1740256270000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11390-010-9372-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,7]]},"references-count":28,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2010,7]]}},"alternative-id":["9372"],"URL":"https:\/\/doi.org\/10.1007\/s11390-010-9372-7","relation":{},"ISSN":["1000-9000","1860-4749"],"issn-type":[{"type":"print","value":"1000-9000"},{"type":"electronic","value":"1860-4749"}],"subject":[],"published":{"date-parts":[[2010,7]]}}}