{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T07:06:08Z","timestamp":1760079968237,"version":"3.40.3"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319321486"},{"type":"electronic","value":"9783319321493"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-32149-3_7","type":"book-chapter","created":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T02:24:42Z","timestamp":1459477482000},"page":"63-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Performance Analysis of the Kahan-Enhanced Scalar Product on Current Multicore Processors"],"prefix":"10.1007","author":[{"given":"Johannes","family":"Hofmann","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dietmar","family":"Fey","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Riedmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jan","family":"Eitzinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Hager","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Wellein","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,4,2]]},"reference":[{"issue":"1","key":"7_CR1","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(1), 5\u201348 (1991)","journal-title":"ACM Comput. Surv."},{"issue":"6","key":"7_CR2","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1145\/362384.362498","volume":"13","author":"P Linz","year":"1970","unstructured":"Linz, P.: Accurate floating-point summation. Commun. ACM 13(6), 361\u2013362 (1970)","journal-title":"Commun. ACM"},{"issue":"9","key":"7_CR3","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1145\/361573.361584","volume":"15","author":"J Gregory","year":"1972","unstructured":"Gregory, J.: A comparison of floating point summation methods. Commun. ACM 15(9), 838 (1972)","journal-title":"Commun. ACM"},{"issue":"1","key":"7_CR4","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(1), 40 (1965)","journal-title":"Commun. ACM"},{"issue":"1","key":"7_CR5","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1137\/050645671","volume":"31","author":"SM Rump","year":"2008","unstructured":"Rump, S.M., Ogita, T., Oishi, S.: Accurate floating-point summation Part I: faithful rounding. SIAM J. Sci. Comput. 31(1), 189\u2013224 (2008)","journal-title":"SIAM J. Sci. Comput."},{"issue":"3","key":"7_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1824801.1824815","volume":"37","author":"YK Zhu","year":"2010","unstructured":"Zhu, Y.K., Hayes, W.B.: Algorithm 908: online exact summation of floating-point streams. ACM Trans. Math. Softw. 37(3), 1\u201313 (2010)","journal-title":"ACM Trans. Math. Softw."},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Demmel, J., Nguyen, H.D.: Fast reproducible floating-point summation. In: 21st IEEE Symposium on Computer Arithmetic, pp. 163\u2013172, April 2013","DOI":"10.1109\/ARITH.2013.9"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Dalton, B., Wang, A., Blainey, B.: SIMDizing pairwise sums: a summation algorithm balancing accuracy with throughput. In: Proceedings of the 2014 Workshop on Programming Models for SIMD\/Vector Processing, WPMVP 2014, pp. 65\u201370. ACM, New York (2014)","DOI":"10.1145\/2568058.2568070"},{"key":"7_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1007\/978-3-642-14390-8_64","volume-title":"Parallel Processing and Applied Mathematics","author":"J Treibig","year":"2010","unstructured":"Treibig, J., Hager, G.: Introducing a performance model for bandwidth-limited loop kernels. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wasniewski, J. (eds.) PPAM 2009, Part I. LNCS, vol. 6067, pp. 615\u2013624. Springer, Heidelberg (2010)"},{"issue":"2","key":"7_CR10","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1002\/cpe.3180","volume":"28","author":"Georg Hager","year":"2013","unstructured":"Hager, G., Treibig, J., Habich, J., Wellein, G.: Exploring performance and power properties of modern multicore chips via simple machine models. Concurrency Comput.: Pract. Exper. (2013). doi:10.1002\/cpe.3180","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"7_CR11","doi-asserted-by":"crossref","unstructured":"Stengel, H., Treibig, J., Hager, G., Wellein, G.: Quantifying performance bottlenecks of stencil computations using the execution-cache-memory model. In: Proceedings of the 29th ACM International Conference on Supercomputing, ICS 2015. ACM, New York (2015)","DOI":"10.1145\/2751205.2751240"},{"issue":"4","key":"7_CR12","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009)","journal-title":"Commun. ACM"},{"key":"7_CR13","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/978-3-642-31476-6_3","volume-title":"Tools for High Performance Computing 2011","author":"J Treibig","year":"2012","unstructured":"Treibig, J., Hager, G., Wellein, G.: likwid-bench: An extensible microbenchmarking platform for x86 multicore compute nodes. In: Brunst, H., et al. (eds.) Tools for High Performance Computing 2011, pp. 27\u201336. Springer, Heidelberg (2012)"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-32149-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,15]],"date-time":"2020-12-15T01:06:49Z","timestamp":1607994409000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-32149-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319321486","9783319321493"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-32149-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"2 April 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}