{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:53:07Z","timestamp":1775065987623,"version":"3.50.1"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319936970","type":"print"},{"value":"9783319936987","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-93698-7_45","type":"book-chapter","created":{"date-parts":[[2018,6,11]],"date-time":"2018-06-11T19:30:25Z","timestamp":1528745425000},"page":"586-600","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["The Design of Fast and Energy-Efficient Linear Solvers: On the Potential of Half-Precision Arithmetic and Iterative Refinement Techniques"],"prefix":"10.1007","author":[{"given":"Azzam","family":"Haidar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmad","family":"Abdelfattah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mawussi","family":"Zounon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panruo","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srikara","family":"Pranesh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stanimire","family":"Tomov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,12]]},"reference":[{"issue":"12","key":"45_CR1","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1016\/j.cpc.2008.11.005","volume":"180","author":"M Baboulin","year":"2009","unstructured":"Baboulin, M., Buttari, A., Dongarra, J., Kurzak, J., Langou, J., Langou, J., Luszczek, P., Tomov, S.: Accelerating scientific computations with mixed precision algorithms. Comput. Phys. Commun. 180(12), 2526\u20132533 (2009)","journal-title":"Comput. Phys. Commun."},{"key":"45_CR2","doi-asserted-by":"crossref","unstructured":"Betkaoui, B., Thomas, D.B., Luk, W.: Comparing performance and energy efficiency of FPGAs and GPUs for high productivity computing. In: 2010 International Conference on Field-Programmable Technology, pp. 94\u2013101, December 2010","DOI":"10.1109\/FPT.2010.5681761"},{"key":"45_CR3","unstructured":"Carson, E., Higham, N.J.: Accelerating the solution of linear systems by iterative refinement in three precisions. MIMS EPrint 2017.24, University of Manchester (2017)"},{"issue":"6","key":"45_CR4","doi-asserted-by":"publisher","first-page":"A2834","DOI":"10.1137\/17M1122918","volume":"39","author":"E Carson","year":"2017","unstructured":"Carson, E., Higham, N.J.: A new analysis of iterative refinement and its application to accurate solution of ill-conditioned sparse linear systems. SIAM J. Sci. Comput. 39(6), A2834\u2013A2856 (2017). https:\/\/doi.org\/10.1137\/17M1122918","journal-title":"SIAM J. Sci. Comput."},{"key":"45_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1007\/978-3-319-58667-0_21","volume-title":"High Performance Computing","author":"J Eastep","year":"2017","unstructured":"Eastep, J., Sylvester, S., Cantalupo, C., Geltz, B., Ardanaz, F., Al-Rawi, A., Livingston, K., Keceli, F., Maiterth, M., Jana, S.: Global extensible open power manager: a vehicle for HPC community collaboration on co-designed energy management solutions. In: Kunkel, J.M., Yokota, R., Balaji, P., Keyes, D. (eds.) ISC 2017. LNCS, vol. 10266, pp. 394\u2013412. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-58667-0_21"},{"issue":"4","key":"45_CR6","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1016\/j.jpdc.2012.01.006","volume":"72","author":"M Etinski","year":"2012","unstructured":"Etinski, M., Corbal\u00e1n, J., Labarta, J., Valero, M.: Understanding the future of energy-performance trade-off via DVFS in HPC environments. J. Parallel Distrib. Comput. 72(4), 579\u2013590 (2012)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"5","key":"45_CR7","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1109\/TPDS.2009.76","volume":"21","author":"R Ge","year":"2010","unstructured":"Ge, R., Feng, X., Song, S., Chang, H.C., Li, D., Cameron, K.W.: Powerpack: energy profiling and analysis of high-performance systems and applications. IEEE Trans. Parallel Distrib. Syst. 21(5), 658\u2013671 (2010)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Haidar, A., Jagode, H., YarKhan, A., Vaccaro, P., Tomov, S., Dongarra, J.: Power-aware computing: Measurement, control, and performance analysis for Intel Xeon Phi. In: 2017 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20137, September 2017","DOI":"10.1109\/HPEC.2017.8091085"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Haidar, A., Tomov, S., Luszczek, P., Dongarra, J.: Magma embedded: towards a dense linear algebra library for energy efficient extreme computing. In: 2015 IEEE High Performance Extreme Computing Conference (HPEC 2015), (Best Paper Award). IEEE, Waltham, September 2015","DOI":"10.1109\/HPEC.2015.7322444"},{"key":"45_CR10","doi-asserted-by":"crossref","unstructured":"Haidar, A., Wu, P., Tomov, S., Dongarra, J.: Investigating half precision arithmetic to accelerate dense linear system solvers. In: SC16 Scal A17: 8th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems. ACM, Denver, November 2017","DOI":"10.1145\/3148226.3148237"},{"issue":"3","key":"45_CR11","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/BF01933262","volume":"31","author":"NJ Higham","year":"1991","unstructured":"Higham, N.J.: Iterative refinement enhances the stability of QR factorization methods for solving linear equations. BIT Numer. Math. 31(3), 447\u2013468 (1991). https:\/\/doi.org\/10.1007\/BF01933262","journal-title":"BIT Numer. Math."},{"key":"45_CR12","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/978-3-319-39589-0_4","volume-title":"Tools for High Performance Computing 2015","author":"H Jagode","year":"2016","unstructured":"Jagode, H., YarKhan, A., Danalis, A., Dongarra, J.: Power management and event verification in PAPI. In: Kn\u00fcpfer, A., Hilbrich, T., Niethammer, C., Gracia, J., Nagel, W.E., Resch, M.M. (eds.) Tools for High Performance Computing 2015, pp. 41\u201351. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-39589-0_4"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Kasichayanula, K., Terpstra, D., Luszczek, P., Tomov, S., Moore, S., Peterson, G.: Power aware computing on GPUs. In: SAAHPC 2012 (Best Paper Award), Argonne, IL, July 2012","DOI":"10.1109\/SAAHPC.2012.26"},{"key":"45_CR14","doi-asserted-by":"crossref","unstructured":"Kimura, H., Sato, M., Hotta, Y., Boku, T., Takahashi, D.: Empirical study on reducing energy of parallel programs using slack reclamation by DVFS in a power-scalable high performance cluster. In: 2006 IEEE International Conference on Cluster Computing, pp. 1\u201310, September 2006","DOI":"10.1109\/CLUSTR.2006.311839"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Langou, J., Luszczek, P., Kurzak, J., Buttari, A., Dongarra, J.: Exploiting the performance of 32 bit floating point arithmetic in obtaining 64 bit accuracy (revisiting iterative refinement for linear systems). In: SC 2006 Conference, Proceedings of the ACM\/IEEE, p. 50, November 2006","DOI":"10.1109\/SC.2006.30"},{"key":"45_CR16","unstructured":"NVIDIA Management Library (NVML), NVIDIA (2018). https:\/\/developer.nvidia.com\/nvidia-management-library-nvml"},{"key":"45_CR17","doi-asserted-by":"publisher","unstructured":"Rountree, B., Lownenthal, D.K., de Supinski, B.R., Schulz, M., Freeh, V.W., Bletsch, T.: Adagio: making DVS practical for complex HPC applications. In: Proceedings of the 23rd International Conference on Supercomputing, ICS 2009, pp. 460\u2013469. ACM, New York (2009). https:\/\/doi.org\/10.1145\/1542275.1542340","DOI":"10.1145\/1542275.1542340"},{"issue":"151","key":"45_CR18","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1090\/S0025-5718-1980-0572859-4","volume":"35","author":"RD Skeel","year":"1980","unstructured":"Skeel, R.D.: Iterative refinement implies numerical stability for Gaussian elimination. Math. Comput. 35(151), 817\u2013832 (1980)","journal-title":"Math. Comput."},{"issue":"5\u20136","key":"45_CR19","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.parco.2009.12.005","volume":"36","author":"S Tomov","year":"2010","unstructured":"Tomov, S., Dongarra, J., Baboulin, M.: Towards dense linear algebra for hybrid GPU accelerated manycore systems. Parallel Comput. Syst. Appl. 36(5\u20136), 232\u2013240 (2010). https:\/\/doi.org\/10.1016\/j.parco.2009.12.005","journal-title":"Parallel Comput. Syst. Appl."},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Tomov, S., Nath, R., Ltaief, H., Dongarra, J.: Dense linear algebra solvers for multicore with GPU accelerators. In: Proceedings of the IEEE IPDPS 2010, Atlanta, GA, pp. 1\u20138, 19\u201323 April 2010","DOI":"10.1109\/IPDPSW.2010.5470941"},{"key":"45_CR21","volume-title":"Rounding Errors in Algebraic Processes","author":"JH Wilkinson","year":"1963","unstructured":"Wilkinson, J.H.: Rounding Errors in Algebraic Processes. Prentice-Hall, Upper Saddle River (1963)"}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-93698-7_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,11]],"date-time":"2022-06-11T00:07:42Z","timestamp":1654906062000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-93698-7_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319936970","9783319936987"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-93698-7_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"12 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuxi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2018\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"406","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"148","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"60","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"36% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Acceptance rate in the Main Track is 28%. Acceptance rate in the workshops is 43%.  A high acceptance rate in the workshops is explained by the nature of these thematic sessions, where many experts in a particular field are personally invited by workshop organisers to participate in their sessions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}