{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:16:23Z","timestamp":1760141783748,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031304446"},{"type":"electronic","value":"9783031304453"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-30445-3_6","type":"book-chapter","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T09:02:52Z","timestamp":1682499772000},"page":"63-74","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Parallel Vectorized Implementations of\u00a0Compensated Summation Algorithms"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9823-2595","authenticated-orcid":false,"given":"Beata","family":"Dmitruk","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8661-414X","authenticated-orcid":false,"given":"Przemys\u0142aw","family":"Stpiczy\u0144ski","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,27]]},"reference":[{"key":"6_CR1","doi-asserted-by":"publisher","unstructured":"Ahrens, P., Demmel, J., Nguyen, H.D.: Algorithms for efficient reproducible floating point summation. ACM Trans. Math. Softw. 46, 22:1\u201322:49 (2020). https:\/\/doi.org\/10.1145\/3389360","DOI":"10.1145\/3389360"},{"key":"6_CR2","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.jpdc.2019.09.012","volume":"135","author":"H Amiri","year":"2020","unstructured":"Amiri, H., Shahbahrami, A.: SIMD programming using intel vector extensions. J. Parallel Distrib. Comput. 135, 83\u2013100 (2020). https:\/\/doi.org\/10.1016\/j.jpdc.2019.09.012","journal-title":"J. Parallel Distrib. Comput."},{"key":"6_CR3","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.parco.2015.09.001","volume":"49","author":"S Collange","year":"2015","unstructured":"Collange, S., Defour, D., Graillat, S., Iakymchuk, R.: Numerical reproducibility for the parallel reduction on multi- and many-core architectures. Parallel Comput. 49, 83\u201397 (2015). https:\/\/doi.org\/10.1016\/j.parco.2015.09.001","journal-title":"Parallel Comput."},{"key":"6_CR4","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1145\/103162.103163","volume":"23","author":"D Goldberg","year":"1991","unstructured":"Goldberg, D.: What every computer scientist should know about floating-point arithmetic. ACM Comput. Surv. 23, 5\u201348 (1991). https:\/\/doi.org\/10.1145\/103162.103163","journal-title":"ACM Comput. Surv."},{"key":"6_CR5","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1023\/A:1008153532043","volume":"18","author":"Y He","year":"2001","unstructured":"He, Y., Ding, C.H.Q.: Using accurate arithmetics to improve numerical reproducibility and stability in parallel applications. J. Supercomput. 18, 259\u2013277 (2001). https:\/\/doi.org\/10.1023\/A:1008153532043","journal-title":"J. Supercomput."},{"key":"6_CR6","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1137\/0914050","volume":"14","author":"NJ Higham","year":"1993","unstructured":"Higham, N.J.: The accuracy of floating point summation. SIAM J. Sci. Comput. 14, 783\u2013799 (1993). https:\/\/doi.org\/10.1137\/0914050","journal-title":"SIAM J. Sci. Comput."},{"key":"6_CR7","volume-title":"Accuracy and Stability of Numerical Algorithms","author":"N Higham","year":"1996","unstructured":"Higham, N.: Accuracy and Stability of Numerical Algorithms. SIAM, Philadelphia (1996)"},{"key":"6_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/978-3-319-32149-3_7","volume-title":"Parallel Processing and Applied Mathematics","author":"J Hofmann","year":"2016","unstructured":"Hofmann, J., Fey, D., Riedmann, M., Eitzinger, J., Hager, G., Wellein, G.: Performance analysis of the Kahan-enhanced scalar product on current multicore processors. In: Wyrzykowski, R., Deelman, E., Dongarra, J., Karczewski, K., Kitowski, J., Wiatr, K. (eds.) PPAM 2015. LNCS, vol. 9573, pp. 63\u201373. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-32149-3_7"},{"key":"6_CR9","doi-asserted-by":"publisher","unstructured":"Hofmann, J., Fey, D., Riedmann, M., Eitzinger, J., Hager, G., Wellein, G.: Performance analysis of the Kahan-enhanced scalar product on current multi-core and many-core processors. Concurr. Comput. Pract. Exp. 29(9) (2017). https:\/\/doi.org\/10.1002\/cpe.3921","DOI":"10.1002\/cpe.3921"},{"key":"6_CR10","first-page":"435","volume":"19","author":"M Jankowski","year":"1983","unstructured":"Jankowski, M., Smoktunowicz, A., Wo\u017aniakowski, H.: A note on floating-point summation of very many terms. Elektronische Informationsverarbeitung und Kybernetik 19, 435\u2013440 (1983)","journal-title":"Elektronische Informationsverarbeitung und Kybernetik"},{"key":"6_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/BF01936142","author":"M Jankowski","year":"1985","unstructured":"Jankowski, M., Wo\u017aniakowski, H.: The accurate solution of certain continuous problems using only single precision arithmetic. BIT Num.l Math. (1985). https:\/\/doi.org\/10.1007\/BF01936142","journal-title":"BIT Num.l Math."},{"key":"6_CR12","volume-title":"Intel Xeon Phi Processor High-Performance Programming","author":"J Jeffers","year":"2016","unstructured":"Jeffers, J., Reinders, J., Sodani, A.: Intel Xeon Phi Processor High-Performance Programming. Knights Landing Edition. Morgan Kaufman, Cambridge (2016)"},{"key":"6_CR13","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/363707.363723","volume":"8","author":"W Kahan","year":"1965","unstructured":"Kahan, W.: Pracniques: further remarks on reducing truncation errors. Commun. ACM 8, 40 (1965). https:\/\/doi.org\/10.1145\/363707.363723","journal-title":"Commun. ACM"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Kie\u0142basi\u0144ski, A.: The summation algorithm with correction and their applications. Math. Appl. (Matematyka Stosowana) (1973). 10.14708\/ma.v1i1.295","DOI":"10.14708\/ma.v1i1.295"},{"key":"6_CR15","doi-asserted-by":"publisher","first-page":"2111","DOI":"10.1109\/TC.2017.2690632","volume":"66","author":"V Lef\u00e8vre","year":"2017","unstructured":"Lef\u00e8vre, V.: Correctly rounded arbitrary-precision floating-point summation. IEEE Trans. Comput. 66, 2111\u20132124 (2017). https:\/\/doi.org\/10.1109\/TC.2017.2690632","journal-title":"IEEE Trans. Comput."},{"key":"6_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2021.113827","volume":"406","author":"X Lei","year":"2022","unstructured":"Lei, X., Gu, T., Graillat, S., Jiang, H., Qi, J.: A fast parallel high-precision summation algorithm based on AccSumK. J. Computut. Appl. Math. 406, 113827 (2022). https:\/\/doi.org\/10.1016\/j.cam.2021.113827","journal-title":"J. Computut. Appl. Math."},{"key":"6_CR17","doi-asserted-by":"publisher","unstructured":"Lutz, D.R., Hinds, C.N.: High-precision anchored accumulators for reproducible floating-point summation. In: Burgess, N., Bruguera, J.D., de Dinechin, F. (eds.) 24th IEEE Symposium on Computer Arithmetic, ARITH 2017, London, UK, 24\u201326 July 2017, pp. 98\u2013105. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/ARITH.2017.20","DOI":"10.1109\/ARITH.2017.20"},{"key":"6_CR18","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1007\/BF01975722","volume":"5","author":"O M\u00f8ller","year":"1965","unstructured":"M\u00f8ller, O.: Quasi double-precision in floating point addition. BIT Num.l Math. 5, 37\u201350 (1965). https:\/\/doi.org\/10.1007\/BF01975722","journal-title":"BIT Num.l Math."},{"key":"6_CR19","doi-asserted-by":"publisher","unstructured":"Neuman, B., Dubois, A., Monroe, L., Robey, R.W.: Fast, good, and repeatable: Summations, vectorization, and reproducibility. Int. J. High Perform. Comput. Appl. 34 (2020). https:\/\/doi.org\/10.1177\/1094342020938425","DOI":"10.1177\/1094342020938425"},{"key":"6_CR20","unstructured":"van der Pas, R., Stotzer, E., Terboven, C.: Using OpenMP - The Next Step. Affinity, Accelerators, Tasking, and SIMD. MIT Press, Cambridge (2017)"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Stojanov, A., Toskov, I., Rompf, T., P\u00fcschel, M.: SIMD intrinsics on managed language runtimes. In: Proceedings of the 2018 International Symposium on Code Generation and Optimization, pp. 2\u201315. ACM, New York, NY (2018). https:\/\/doi.org\/10.1145\/3168810","DOI":"10.1145\/3168810"},{"issue":"4","key":"6_CR22","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1007\/s11227-017-2231-3","volume":"74","author":"P Stpiczy\u0144ski","year":"2018","unstructured":"Stpiczy\u0144ski, P.: Language-based vectorization and parallelization using intrinsics, OpenMP, TBB and Cilk Plus. J. Supercomput. 74(4), 1461\u20131472 (2018). https:\/\/doi.org\/10.1007\/s11227-017-2231-3","journal-title":"J. Supercomput."},{"key":"6_CR23","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.jpdc.2019.12.004","volume":"137","author":"P Stpiczy\u0144ski","year":"2020","unstructured":"Stpiczy\u0144ski, P.: Algorithmic and language-based optimization of Marsa-LFIB4 pseudorandom number generator using OpenMP, OpenACC and CUDA. J. Parallel Distrib. Comput. 137, 238\u2013245 (2020). https:\/\/doi.org\/10.1016\/j.jpdc.2019.12.004","journal-title":"J. Parallel Distrib. Comput."},{"key":"6_CR24","doi-asserted-by":"publisher","unstructured":"Uguen, Y., de Dinechin, F., Derrien, S.: Bridging high-level synthesis and application-specific arithmetic: the case study of floating-point summations. In: Santambrogio, M.D., G\u00f6hringer, D., Stroobandt, D., Mentens, N., Nurmi, J. (eds.) 27th International Conference on Field Programmable Logic and Applications, FPL 2017, Ghent, Belgium, 4\u20138 September 2017, pp. 1\u20138. IEEE (2017). https:\/\/doi.org\/10.23919\/FPL.2017.8056792","DOI":"10.23919\/FPL.2017.8056792"},{"key":"6_CR25","doi-asserted-by":"publisher","unstructured":"Wang, H., Wu, P., Tanase, I.G., Serrano, M.J., Moreira, J.E.: Simple, portable and fast SIMD intrinsic programming: generic SIMD library. In: Proceedings of the 2014 Workshop on Programming Models for SIMD\/Vector Processing, pp. 9\u201316. ACM, New York, NY (2014). https:\/\/doi.org\/10.1145\/2568058.2568059","DOI":"10.1145\/2568058.2568059"},{"key":"6_CR26","volume-title":"Rounding Errors in Algebraic Processes","author":"J Wilkinson","year":"1963","unstructured":"Wilkinson, J.: Rounding Errors in Algebraic Processes. Prentice-Hall, Englewood Cliffs (1963)"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-30445-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T04:45:17Z","timestamp":1760071517000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-30445-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031304446","9783031304453"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-30445-3_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PPAM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Processing and Applied Mathematics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gdansk","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ppam2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ppam.edu.pl\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}