{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:38:54Z","timestamp":1740123534175,"version":"3.37.3"},"reference-count":18,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,4,5]],"date-time":"2019-04-05T00:00:00Z","timestamp":1554422400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Bundesministerium f\u00fcr Bildung und Forschung","doi-asserted-by":"publisher","award":["01IH16012B"],"award-info":[{"award-number":["01IH16012B"]}],"id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1007\/s11227-019-02839-0","type":"journal-article","created":{"date-parts":[[2019,4,6]],"date-time":"2019-04-06T21:13:53Z","timestamp":1554585233000},"page":"1999-2021","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Performance and energy consumption of the SIMD Gram\u2013Schmidt process for vector orthogonalization"],"prefix":"10.1007","volume":"76","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0149-5992","authenticated-orcid":false,"given":"Thomas","family":"Jakobs","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4850-5430","authenticated-orcid":false,"given":"Billy","family":"Naumann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5364-2088","authenticated-orcid":false,"given":"Gudula","family":"R\u00fcnger","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,4,5]]},"reference":[{"key":"2839_CR1","doi-asserted-by":"publisher","unstructured":"Bj\u00f6rck \u00c5 (1967) Solving linear least squares problems by Gram\u2013Schmidt orthogonalization. BIT Numer Math 7(1). https:\/\/doi.org\/10.1007\/BF01934122","DOI":"10.1007\/BF01934122"},{"key":"2839_CR2","doi-asserted-by":"publisher","unstructured":"Businger P, Golub GH (1965) Linear least squares solutions by householder transformations. Numer Math 7(3). https:\/\/doi.org\/10.1007\/BF01436084","DOI":"10.1007\/BF01436084"},{"key":"2839_CR3","doi-asserted-by":"publisher","unstructured":"Carretero J, Distefano S, Petcu D, Pop D, Rauber T, R\u00fcnger G, Singh DE (2015) Energy-efficient Algorithms for ultrascale systems. Supercomput Front Innov 2(2). https:\/\/doi.org\/10.14529\/jsfi150205","DOI":"10.14529\/jsfi150205"},{"key":"2839_CR4","doi-asserted-by":"publisher","unstructured":"Cebri\u00e1n JM, Jahre M, Natvig L (2014) Optimized hardware for suboptimal software: the case for SIMD-aware benchmarks. In: 2014 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS). https:\/\/doi.org\/10.1109\/ISPASS.2014.6844462","DOI":"10.1109\/ISPASS.2014.6844462"},{"key":"2839_CR5","doi-asserted-by":"publisher","unstructured":"Cebrian JM, Jahre M, Natvig L (2015) ParVec: vectorizing the PARSEC benchmark suite. Computing 97(11). https:\/\/doi.org\/10.1007\/s00607-015-0444-y","DOI":"10.1007\/s00607-015-0444-y"},{"key":"2839_CR6","doi-asserted-by":"publisher","unstructured":"Cebri\u00e1n JM, Natvig L, Meyer JC (2014) Performance and energy impact of parallelization and vectorization techniques in modern microprocessors. Computing 96(12). https:\/\/doi.org\/10.1007\/s00607-013-0366-5","DOI":"10.1007\/s00607-013-0366-5"},{"key":"2839_CR7","doi-asserted-by":"publisher","unstructured":"Cr\u00e2\u015fmariu V, Arvinte M, Enescu A, Ciochin\u0103 S (2017) Optimized block-diagonalization precoding technique using givens rotations QR decomposition. In: 2017 25th European Signal Processing Conference (EUSIPCO). https:\/\/doi.org\/10.23919\/EUSIPCO.2017.8081328","DOI":"10.23919\/EUSIPCO.2017.8081328"},{"key":"2839_CR8","doi-asserted-by":"crossref","DOI":"10.56021\/9781421407944","volume-title":"Matrix computations","author":"GH Golub","year":"2013","unstructured":"Golub GH, Van Loan CF (2013) Matrix computations, 4th edn. Johns Hopkins University Press, Baltimore","edition":"4"},{"key":"2839_CR9","doi-asserted-by":"publisher","unstructured":"Haidar A, Jagode H, YarKhan A, Vaccaro P, Tomov S, Dongarra J (2017) Power-aware computing: measurement, control, and performance analysis for Intel Xeon Phi. In: 2017 IEEE High Performance Extreme Computing Conference (HPEC). https:\/\/doi.org\/10.1109\/HPEC.2017.8091085","DOI":"10.1109\/HPEC.2017.8091085"},{"key":"2839_CR10","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/BF02241222","volume":"41","author":"W Hoffmann","year":"1989","unstructured":"Hoffmann W (1989) Iterative algorithms for Gram\u2013Schmidt orthogonalization. Computing 41:4. https:\/\/doi.org\/10.1007\/BF02241222","journal-title":"Computing"},{"key":"2839_CR11","doi-asserted-by":"publisher","unstructured":"Ibrahim MEA, Rupp M, Fahmy HAH (2009) Code transformations and SIMD impact on embedded software energy\/power consumption. In: 2009 International Conference on Computer Engineering Systems. https:\/\/doi.org\/10.1109\/ICCES.2009.5383317","DOI":"10.1109\/ICCES.2009.5383317"},{"key":"2839_CR12","unstructured":"Intel Corporation (2018) Intel 64 and IA-32 Architectures Software Developer\u2019s Manual Combined Volumes: 1, 2a, 2b, 2c,2d, 3a, 3b, 3c, 3d and 4. Technical report, Intel Corporation. URL https:\/\/software.intel.com\/en-us\/articles\/intel-sdm"},{"key":"2839_CR13","doi-asserted-by":"publisher","unstructured":"Jakobs T, Hofmann M, R\u00fcnger G (2016) Reducing the power consumption of matrix multiplications by vectorization. In: 2016 IEEE International Conference on Computational Science and Engineering (CSE). https:\/\/doi.org\/10.1109\/CSE-EUC-DCABES.2016.187","DOI":"10.1109\/CSE-EUC-DCABES.2016.187"},{"key":"2839_CR14","doi-asserted-by":"publisher","unstructured":"Jakobs T, R\u00fcnger G (2018) Examining energy efficiency of vectorization techniques using a Gaussian elimination. In: International Conference on High Performance Computing & Simulation (HPCS 2018). IEEE. https:\/\/doi.org\/10.1109\/HPCS.2018.00054","DOI":"10.1109\/HPCS.2018.00054"},{"key":"2839_CR15","doi-asserted-by":"publisher","unstructured":"Jakobs T, R\u00fcnger G (2018) On the energy consumption of Load\/Store AVX instructions. In: Federated Conference on Computer Science and Information Systems (FedCSIS). https:\/\/doi.org\/10.15439\/2018F28","DOI":"10.15439\/2018F28"},{"key":"2839_CR16","unstructured":"Kim C, Satish N, Chhugani J, Saito H, Krishnaiyer R, Smelyanskiy M, Girkar M, Dubey P (2013) Closing the ninja performance gap through traditional programming and compiler technology. Technical report, Intel Corporation. https:\/\/software.intel.com\/sites\/default\/files\/article\/478267\/intel-labs-closing-ninja-gap-paper.pdf"},{"key":"2839_CR17","doi-asserted-by":"publisher","unstructured":"R\u00fcnger G, Schwind M (2005) Comparison of different parallel modified Gram\u2013Schmidt algorithms. In: Euro-Par 2005 Parallel Process. https:\/\/doi.org\/10.1109\/IPDPS.2008.4536474","DOI":"10.1109\/IPDPS.2008.4536474"},{"key":"2839_CR18","doi-asserted-by":"publisher","unstructured":"Stock K, Pouchet LN, Sadayappan P (2012) Using machine learning to improve automatic vectorization. ACM Trans Archit Code Optim 8(4). https:\/\/doi.org\/10.1145\/2086696.2086729","DOI":"10.1145\/2086696.2086729"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-02839-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-019-02839-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-02839-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,15]],"date-time":"2023-09-15T13:20:14Z","timestamp":1694784014000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-019-02839-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,5]]},"references-count":18,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2020,3]]}},"alternative-id":["2839"],"URL":"https:\/\/doi.org\/10.1007\/s11227-019-02839-0","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2019,4,5]]},"assertion":[{"value":"5 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}