{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T20:24:04Z","timestamp":1768076644605,"version":"3.49.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T00:00:00Z","timestamp":1571616000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T00:00:00Z","timestamp":1571616000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1007\/s11227-019-03034-x","type":"journal-article","created":{"date-parts":[[2019,10,21]],"date-time":"2019-10-21T12:38:31Z","timestamp":1571661511000},"page":"255-274","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["An study of the effect of process malleability in the energy efficiency on GPU-based clusters"],"prefix":"10.1007","volume":"76","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3654-7924","authenticated-orcid":false,"given":"Sergio","family":"Iserte","sequence":"first","affiliation":[]},{"given":"Krzysztof","family":"Rojek","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,10,21]]},"reference":[{"key":"3034_CR1","unstructured":"Nvidia web page. \nhttp:\/\/www.nvidia.com\n\n (2018). Accessed: 2018-12-17"},{"key":"3034_CR2","volume-title":"Multicore and GPU programming: an integrated approach","author":"G Barlas","year":"2014","unstructured":"Barlas G (2014) Multicore and GPU programming: an integrated approach. Elsevier, Amsterdam"},{"key":"3034_CR3","first-page":"28:28","volume-title":"Measuring GPU power with the K20 built-in sensor","author":"M Burtscher","year":"2014","unstructured":"Burtscher M, Zecena I, Zong Z (2014) Measuring GPU power with the K20 built-in sensor. ACM, New York, pp 28:28\u201328:36"},{"key":"3034_CR4","doi-asserted-by":"crossref","unstructured":"Compr\u00e9s I, Mo-Hellenbrand A, Gerndt M, Bungartz HJ (2016) Infrastructure and API extensions for elastic execution of MPI applications. In: Proceedings of the 23rd European MPI Users\u2019 Group Meeting on\u2014EuroMPI 2016. ACM Press, New York, pp 82\u201397","DOI":"10.1145\/2966884.2966917"},{"issue":"3","key":"3034_CR5","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1002\/cpe.1362","volume":"21","author":"K El Maghraoui","year":"2009","unstructured":"El Maghraoui K, Desell TJ, Szymanski BK, Varela CA (2009) Malleable iterative MPI applications. Concurr Comput Practice Exp 21(3):393\u2013413","journal-title":"Concurr Comput Practice Exp"},{"key":"3034_CR6","doi-asserted-by":"crossref","unstructured":"El Maghraoui K, Szymanski BK, Varela C (2006) An architecture for reconfigurable iterative MPI applications in dynamic environments. In: International Conference on Parallel Processing and Applied Mathematics, pp 258\u201327","DOI":"10.1007\/11752578_32"},{"key":"3034_CR7","first-page":"89","volume-title":"Lecture notes in computer science book series (LNCS)","author":"DG Feitelson","year":"1996","unstructured":"Feitelson DG (1996) Packing schemes for gang scheduling. In: Feitelson DG, Rudolph L (eds) Lecture notes in computer science book series (LNCS), vol 1162. Springer, Berlin, pp 89\u2013110"},{"key":"3034_CR8","doi-asserted-by":"crossref","unstructured":"Gupta A, Acun B, Sarood O, Kal\u00e9 LV (2014) Towards realizing the potential of malleable jobs. In: 21st International Conference on High Performance Computing (HiPC)","DOI":"10.1109\/HiPC.2014.7116905"},{"key":"3034_CR9","unstructured":"Iserte S (2018) High-throughput computation through efficient resource management. Ph.D. thesis, Universitat Jaume I, Castell\u00f3 de la Plana"},{"key":"3034_CR10","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1177\/1094342018802347","volume":"33","author":"S Iserte","year":"2018","unstructured":"Iserte S, Mart\u00ednez H, Barrachina S, Castillo M, Mayo R, Pe\u00f1a AJ (2018) Dynamic reconfiguration of noniterative scientific applications. Int J High Perform Comput Appl 33:804\u2013816","journal-title":"Int J High Perform Comput Appl"},{"key":"3034_CR11","doi-asserted-by":"crossref","unstructured":"Iserte S, Mayo R, Quintana-Ort\u00ed ES, Beltran V, Pe\u00f1a AJ (2017) Efficient scalable computing through flexible applications and adaptive workloads. In: 10th International Workshop on Parallel Programming Models and Systems Software for High-End Computing (P2S2). Bristol","DOI":"10.1109\/ICPPW.2017.36"},{"key":"3034_CR12","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.parco.2018.07.006","volume":"78","author":"S Iserte","year":"2018","unstructured":"Iserte S, Mayo R, Quintana-Ort\u00ed ES, Beltran V, Pe\u00f1a AJ (2018) DMR API: improving cluster productivity by turning applications into malleable. Parallel Comput 78:54\u201366","journal-title":"Parallel Comput"},{"key":"3034_CR13","unstructured":"Kungand HT, Leiserson CE (1979) Algorithms for VLSI processor arrays. In: Introduction to VLSI Systems. Addison-Wesley"},{"key":"3034_CR14","doi-asserted-by":"crossref","unstructured":"Lemarinier P, Hasanov K, Venugopal S, Katrinis K (2016) Architecting malleable MPI applications for priority-driven adaptive scheduling. In: Proceedings of the 23rd European MPI Users\u2019 Group Meeting (EuroMPI), pp 74\u201381","DOI":"10.1145\/2966884.2966907"},{"issue":"11","key":"3034_CR15","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1016\/S0743-7315(03)00108-4","volume":"63","author":"U Lublin","year":"2003","unstructured":"Lublin U, Feitelson DG (2003) The workload on parallel supercomputers: modeling the characteristics of rigid jobs. J Parallel Distrib Comput 63(11):1105\u20131122","journal-title":"J Parallel Distrib Comput"},{"key":"3034_CR16","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.parco.2015.04.003","volume":"46","author":"G Mart\u00edn","year":"2015","unstructured":"Mart\u00edn G, Singh DE, Marinescu MC, Carretero J (2015) Enhancing the performance of malleable MPI applications by using performance-aware dynamic reconfiguration. Parallel Comput 46:60\u201377","journal-title":"Parallel Comput"},{"key":"3034_CR17","doi-asserted-by":"crossref","unstructured":"Prabhakaran S, Neumann M, Rinke S, Wolf F, Gupta A, Kale LV (2015) A batch system with efficient adaptive scheduling for malleable and evolving applications. In: 2015 IEEE International Parallel and Distributed Processing Symposium, pp 429\u2013438","DOI":"10.1109\/IPDPS.2015.34"},{"key":"3034_CR18","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1016\/j.compfluid.2007.12.001","volume":"37","author":"J Prusa","year":"2008","unstructured":"Prusa J, Smolarkiewicz P, Wyszogrodzki A (2008) EULAG, a computational model for multiscale flows. Comput Fluids 37:1193\u20131207","journal-title":"Comput Fluids"},{"key":"3034_CR19","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4644","author":"K Rojek","year":"2018","unstructured":"Rojek K (2018) Machine learning method for energy reduction by utilizing dynamic mixed precision on GPU-based supercomputers. Concurr Comput Practice Exp. \nhttps:\/\/doi.org\/10.1002\/cpe.4644","journal-title":"Concurr Comput Practice Exp"},{"issue":"10","key":"3034_CR20","doi-asserted-by":"publisher","first-page":"4373","DOI":"10.1007\/s11227-017-2020-z","volume":"73","author":"K Rojek","year":"2017","unstructured":"Rojek K, Quintana-Ort\u00ed ES, Wyrzykowski R (2017) Modeling power consumption of 3D MPDATA and the CG method on ARM and intel multicore architectures. J Supercomput 73(10):4373\u20134389","journal-title":"J Supercomput"},{"issue":"2","key":"3034_CR21","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/s11227-016-1774-z","volume":"73","author":"K Rojek","year":"2017","unstructured":"Rojek K, Wyrzykowski R (2017) Performance modeling of 3D MPDATA simulations on GPU cluster. J Supercomput 73(2):664\u2013675","journal-title":"J Supercomput"},{"issue":"9","key":"3034_CR22","doi-asserted-by":"publisher","first-page":"e3970","DOI":"10.1002\/cpe.3970","volume":"29","author":"K Rojek","year":"2017","unstructured":"Rojek K, Wyrzykowski R, Kuczynski L (2017) Systematic adaptation of stencil-based 3D MPDATA to GPU architectures. Concurr Comput Practice Exp 29(9):e3970","journal-title":"Concurr Comput Practice Exp"},{"key":"3034_CR23","doi-asserted-by":"crossref","unstructured":"Sainz F, Bellon J, Beltran V, Labarta J (2015) Collective offload for heterogeneous clusters. In: 22nd International Conference on High Performance Computing (HiPC)","DOI":"10.1109\/HiPC.2015.20"},{"key":"3034_CR24","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1002\/fld.1071","volume":"50","author":"P Smolarkiewicz","year":"2006","unstructured":"Smolarkiewicz P (2006) Multidimensional positive definite advection transport algorithm: an overview. Int J Numer Methods Fluids 50:1123\u20131144","journal-title":"Int J Numer Methods Fluids"},{"key":"3034_CR25","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1016\/j.comptc.2019.02.002","volume":"1151","author":"F Spenke","year":"2019","unstructured":"Spenke F, Balzer K, Frick S, Hartke B, Dieterich JM (2019) Malleable parallelism with minimal effort for maximal throughput and maximal hardware load. Comput Theor Chem 1151:72\u201377","journal-title":"Comput Theor Chem"},{"key":"3034_CR26","doi-asserted-by":"crossref","unstructured":"Sudarsan R, Ribbens C (2009) Scheduling resizable parallel applications. In: International Symposium on Parallel and Distributed Processing","DOI":"10.1109\/IPDPS.2009.5161077"},{"issue":"4","key":"3034_CR27","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.1007\/s11227-018-2239-3","volume":"74","author":"L Szustak","year":"2018","unstructured":"Szustak L (2018) Strategy for data-flow synchronizations in stencil parallel computations on multi-\/manycore systems. J Supercomput 74(4):1534\u20131546","journal-title":"J Supercomput"},{"key":"3034_CR28","doi-asserted-by":"crossref","unstructured":"Yoo AB, Jette MA, Grondona M (2003) SLURM: simple linux utility for resource management. In: 9th International Workshop on Job Scheduling Strategies for Parallel Processing (JSSPP), pp 44\u201360","DOI":"10.1007\/10968987_3"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-03034-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-019-03034-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-019-03034-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,19]],"date-time":"2020-10-19T23:24:23Z","timestamp":1603149863000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-019-03034-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,21]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2020,1]]}},"alternative-id":["3034"],"URL":"https:\/\/doi.org\/10.1007\/s11227-019-03034-x","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,21]]},"assertion":[{"value":"21 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}