{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:34:48Z","timestamp":1743150888142,"version":"3.40.3"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319751771"},{"type":"electronic","value":"9783319751788"}],"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\/978-3-319-75178-8_37","type":"book-chapter","created":{"date-parts":[[2018,2,7]],"date-time":"2018-02-07T07:12:27Z","timestamp":1517987547000},"page":"452-464","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Operational Concepts of GPU Systems in HPC Centers: TCO and Productivity"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8069-9728","authenticated-orcid":false,"given":"Fabian P.","family":"Schneider","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5794-3662","authenticated-orcid":false,"given":"Sandra","family":"Wienke","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2545-5258","authenticated-orcid":false,"given":"Matthias S.","family":"M\u00fcller","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,2,8]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Ament, M., Knittel, G., Weiskopf, D., Strasser, W.: A parallel preconditioned conjugate gradient solver for the poisson problem on a multi-GPU platform. In: 2010 18th Euromicro Conference on Parallel, Distributed and Network-Based Processing, pp. 583\u2013592 (2010)","DOI":"10.1109\/PDP.2010.51"},{"issue":"6","key":"37_CR2","doi-asserted-by":"publisher","first-page":"2905","DOI":"10.1137\/07069198X","volume":"30","author":"H B\u00fccker","year":"2008","unstructured":"B\u00fccker, H., Beucker, R., Rupp, A.: Parallel minimum p-norm solution of the neuromagnetic inverse problem for realistic signals using exact Hessian-vector products. SIAM J. Sci. Comput. 30(6), 2905\u20132921 (2008)","journal-title":"SIAM J. Sci. Comput."},{"key":"37_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1007\/978-3-642-01970-8_90","volume-title":"Computational Science \u2013 ICCS 2009","author":"A Cevahir","year":"2009","unstructured":"Cevahir, A., Nukada, A., Matsuoka, S.: Fast conjugate gradients with multiple GPUs. In: Allen, G., Nabrzyski, J., Seidel, E., van Albada, G.D., Dongarra, J., Sloot, P.M.A. (eds.) ICCS 2009 Part I. LNCS, vol. 5544, pp. 893\u2013903. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-01970-8_90"},{"issue":"1\u20132","key":"37_CR4","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s00450-010-0112-6","volume":"25","author":"A Cevahir","year":"2010","unstructured":"Cevahir, A., Nukada, A., Matsuoka, S.: High performance conjugate gradient solver on multi-GPU clusters using hypergraph partitioning. Comput. Sci.- Res. Dev. 25(1\u20132), 83\u201391 (2010)","journal-title":"Comput. Sci.- Res. Dev."},{"key":"37_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/S0065-2458(08)00001-6","volume-title":"Advances in COMPUTERS High Performance Computing","author":"J Dongarra","year":"2008","unstructured":"Dongarra, J., Graybill, R., Harrod, W., Lucas, R., Lusk, E., Luszczek, P., Mcmahon, J., Snavely, A., Vetter, J., Yelick, K., Alam, S., Campbell, R., Carrington, L., Chen, T.Y., Khalili, O., Meredith, J., Tikir, M.: DARPA\u2019s HPCS program: history, models, tools, languages. In: Zelkowitz, M.V. (ed.) Advances in COMPUTERS High Performance Computing, vol. 72, pp. 1\u2013100. Elsevier, Amsterdam (2008)"},{"key":"37_CR6","unstructured":"Dongarra, J.J., De Supinski, B.R. (eds.): International Journal of High Performance Computing Applications, vol. 18, no. 4. Sage Publications (2004)"},{"key":"37_CR7","unstructured":"European Commission - Community Research and Development Information Service (CORDIS): Guide to Financial Issues Relating to FP7 Indirect Actions (2014)"},{"key":"37_CR8","unstructured":"German Science Foundation (DFG): DFG Personnel Rates for 2017"},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, V., Gavrilovska, A., Schwan, K., Kharche, H., Tolia, N., Talwar, V., Ranganathan, P.: GViM: GPU-accelerated virtual machines. In: Proceedings of the 3rd ACM Workshop on System-Level Virtualization for High Performance Computing, pp. 17\u201324. ACM (2009). 1519141","DOI":"10.1145\/1519138.1519141"},{"key":"37_CR10","doi-asserted-by":"publisher","first-page":"409","DOI":"10.6028\/jres.049.044","volume":"49","author":"MR Hestenes","year":"1952","unstructured":"Hestenes, M.R., Stiefel, E.: Methods of conjugate gradients for solving linear systems. Natl. Bur. Stand. 49, 409\u2013436 (1952)","journal-title":"Natl. Bur. Stand."},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Iserte, S., Castello, A., Mayo, R., Quintana-Orti, E.S., Silla, F., Duato, J., Reano, C., Prades, J.: SLURM support for remote GPU virtualization: implementation and performance study. In: 2014 IEEE 26th International Symposium on Computer Architecture and High Performance Computing, pp. 318\u2013325 (2014)","DOI":"10.1109\/SBAC-PAD.2014.49"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Kindratenko, V.V., Enos, J.J., Shi, G., Showerman, M.T., Arnold, G.W., Stone, J.E., Phillips, J., Hwu, W.: GPU clusters for high-performance computing. In: 2009 IEEE International Conference on Cluster Computing and Workshops, pp. 1\u20138 (2009)","DOI":"10.1109\/CLUSTR.2009.5289128"},{"issue":"9","key":"37_CR13","doi-asserted-by":"publisher","first-page":"2884","DOI":"10.1016\/j.jpdc.2014.06.001","volume":"74","author":"J Lang","year":"2014","unstructured":"Lang, J., R\u00fcnger, G.: An execution time and energy model for an energy-aware execution of a conjugate gradient method with CPU\/GPU collaboration. J. Parallel Distrib. Comput. 74(9), 2884\u20132897 (2014)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"6","key":"37_CR14","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1016\/j.cpc.2012.01.019","volume":"183","author":"F Lu","year":"2012","unstructured":"Lu, F., Song, J., Yin, F., Zhu, X.: Performance evaluation of hybrid programming patterns for large CPU\/GPU heterogeneous clusters. Comput. Phys. Commun. 183(6), 1172\u20131181 (2012)","journal-title":"Comput. Phys. Commun."},{"key":"37_CR15","unstructured":"Oak Ridge National Laboratory: Job Resource Accounting. https:\/\/www.olcf.ornl.gov\/support\/system-user-guides\/titan-user-guide\/. Accessed 4 2017"},{"key":"37_CR16","unstructured":"Oak Ridge National Laboratory: XK7 (Titan) Node Description. https:\/\/www.olcf.ornl.gov\/support\/system-user-guides\/accelerated-computing-guide. Accessed 4 2017"},{"issue":"10","key":"37_CR17","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1016\/j.parco.2014.09.011","volume":"40","author":"AJ Pena","year":"2014","unstructured":"Pena, A.J., Reano, C., Silla, F., Mayo, R., Quintana-Orti, E.S., Duato, J.: A complete and efficient CUDA-sharing solution for HPC clusters. Parallel Comput. 40(10), 574\u2013588 (2014)","journal-title":"Parallel Comput."},{"key":"37_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1007\/978-3-642-40047-6_56","volume-title":"Euro-Par 2013 Parallel Processing","author":"D Schmidl","year":"2013","unstructured":"Schmidl, D., Cramer, T., Wienke, S., Terboven, C., M\u00fcller, M.S.: Assessing the performance of OpenMP programs on the Intel Xeon Phi. In: Wolf, F., Mohr, B., an Mey, D. (eds.) Euro-Par 2013. LNCS, vol. 8097, pp. 547\u2013558. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-40047-6_56"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Silla, F., Prades, J., Iserte, S., Reano, C.: Remote GPU virtualization: is it useful? In: 2016 2nd IEEE International Workshop on High-Performance Interconnection Networks in the Exascale and Big-Data Era (HiPINEB), pp. 41\u201348 (2016)","DOI":"10.1109\/HIPINEB.2016.8"},{"key":"37_CR20","unstructured":"The Global Scientific Information and Computing Center (GSIC): TSUBAME 2.5 User\u2019s Guide: User Environment. http:\/\/tsubame.gsic.titech.ac.jp\/docs\/guides\/tsubame2\/html_en\/resources.html. Accessed 4 2017"},{"key":"37_CR21","unstructured":"Top500-The List. https:\/\/www.top500.org\/lists\/2016\/11\/, November 2016"},{"issue":"10\u201311","key":"37_CR22","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1016\/j.parco.2012.07.002","volume":"38","author":"M Verschoor","year":"2012","unstructured":"Verschoor, M., Jalba, A.C.: Analysis and performance estimation of the Conjugate Gradient method on multiple GPUs. Parallel Comput. 38(10\u201311), 552\u2013575 (2012)","journal-title":"Parallel Comput."},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"V\u00e1zquez, F., Ortega, G., Fern\u00e1ndez, J.J., Garz\u00f3n, E.M.: Improving the performance of the sparse matrix vector product with GPUs. In: 10th IEEE International Conference on Computer and Information Technology, pp. 1146\u20131151 (2010)","DOI":"10.1109\/CIT.2010.208"},{"key":"37_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1007\/978-3-642-38750-0_25","volume-title":"Supercomputing","author":"S Wienke","year":"2013","unstructured":"Wienke, S., an Mey, D., M\u00fcller, M.S.: Accelerators for technical computing: is it worth the pain? A TCO perspective. In: Kunkel, J.M., Ludwig, T., Meuer, H.W. (eds.) ISC 2013. LNCS, vol. 7905, pp. 330\u2013342. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-38750-0_25"},{"key":"37_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1007\/978-3-319-20119-1_26","volume-title":"High Performance Computing","author":"S Wienke","year":"2015","unstructured":"Wienke, S., Iliev, H., an Mey, D., M\u00fcller, M.S.: Modeling the productivity of HPC systems on a computing center scale. In: Kunkel, J.M., Ludwig, T. (eds.) ISC High Performance 2015. LNCS, vol. 9137, pp. 358\u2013375. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-20119-1_26"},{"key":"37_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1007\/978-3-642-32820-6_85","volume-title":"Euro-Par 2012 Parallel Processing","author":"S Wienke","year":"2012","unstructured":"Wienke, S., Springer, P., Terboven, C., an Mey, D.: OpenACC\u2014first experiences with real-world applications. In: Kaklamanis, C., Papatheodorou, T., Spirakis, P.G. (eds.) Euro-Par 2012. LNCS, vol. 7484, pp. 859\u2013870. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-32820-6_85"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2017: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-75178-8_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,8]],"date-time":"2022-02-08T01:06:44Z","timestamp":1644282404000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-75178-8_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319751771","9783319751788"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-75178-8_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"8 February 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Santiago de Compostela","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/europar2017.usc.es","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}