{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T11:28:38Z","timestamp":1771068518741,"version":"3.50.1"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,9,8]],"date-time":"2016-09-08T00:00:00Z","timestamp":1473292800000},"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":["J Supercomput"],"published-print":{"date-parts":[[2017,1]]},"DOI":"10.1007\/s11227-016-1864-y","type":"journal-article","created":{"date-parts":[[2016,9,8]],"date-time":"2016-09-08T07:48:38Z","timestamp":1473320918000},"page":"330-342","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Energy efficiency of load balancing for data-parallel applications in heterogeneous systems"],"prefix":"10.1007","volume":"73","author":[{"given":"Borja","family":"P\u00e9rez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9481-8724","authenticated-orcid":false,"given":"Esteban","family":"Stafford","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7718-8449","authenticated-orcid":false,"given":"Jos\u00e9 Luis","family":"Bosque","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ram\u00f3n","family":"Beivide","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,9,8]]},"reference":[{"issue":"2","key":"1864_CR1","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1007\/s11227-014-1322-7","volume":"71","author":"P Benner","year":"2015","unstructured":"Benner P, Rem\u00f3n A, Dufrechou E, Ezzatti P, Quintana-Ort\u00ed Enrique S (2015) Extending lyapack for the solution of band lyapunov equations on hybrid CPU\u2013GPU platforms. J Supercomput 71(2):740\u2013750","journal-title":"J Supercomput"},{"issue":"2","key":"1864_CR2","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1007\/s11227-012-0827-1","volume":"63","author":"X Cai","year":"2013","unstructured":"Cai X, Lai G, Lin X (2013) Forecasting large scale conditional volatility and covariance using neural network on GPU. J Supercomput 63(2):490\u2013507","journal-title":"J Supercomput"},{"issue":"2","key":"1864_CR3","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1007\/s11227-013-1015-7","volume":"67","author":"KE Niemeyer","year":"2014","unstructured":"Niemeyer KE, Sung CJ (2014) Recent progress and challenges in exploiting graphics processors in computational fluid dynamics. J Supercomput 67(2):528\u2013564","journal-title":"J Supercomput"},{"key":"1864_CR4","doi-asserted-by":"crossref","unstructured":"P\u00e9rez B, Bosque JL, Beivide R (2016) Simplifying programming and load balancing of data parallel applications on heterogeneous systems. In: Proc. of the 9th workshop on general purpose processing using GPU, 2016, pp 42\u201351","DOI":"10.1145\/2884045.2884051"},{"issue":"10","key":"1864_CR5","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1109\/12.956091","volume":"50","author":"O Beaumont","year":"2001","unstructured":"Beaumont O, Boudet V, Petitet A, Rastello F, Robert Yves (2001) A proposal for a heterogeneous cluster ScaLAPACK (dense linear solvers). IEEE Trans Comput 50(10):1052\u20131070","journal-title":"IEEE Trans Comput"},{"key":"1864_CR6","unstructured":"Amd accelerated parallel processing software development kit v2.9. Accesed Nov 2015"},{"key":"1864_CR7","doi-asserted-by":"crossref","unstructured":"Rotem E, Naveh A, Rajwan D, Ananthakrishnan A, Weissmann E (2011) Power management architecture of the 2nd generation Intel Core microarchitecture, formerly codenamed Sandy Bridge. In: IEEE Int. HotChips Symp. on High-Perf. Chips (HotChips\u00a0 2011), 2011","DOI":"10.1109\/HOTCHIPS.2011.7477510"},{"key":"1864_CR8","unstructured":"NVIDIA. NVIDIA Management Library (NVML). Accesed April 2016"},{"issue":"2","key":"1864_CR9","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1007\/s11227-014-1316-5","volume":"71","author":"E Castillo","year":"2015","unstructured":"Castillo E, Camarero C, Borrego A, Bosque JL (2015) Financial applications on multi-CPU and multi-GPU architectures. J Supercomput 71(2):729\u2013739","journal-title":"J Supercomput"},{"key":"1864_CR10","doi-asserted-by":"crossref","unstructured":"de la Lama Carlos S, Toharia P, Bosque JL, Robles OD (2012) Static multi-device load balancing for opencl. In: Proc. of ISPA, IEEE Computer Society, 2012, pp 675\u2013682","DOI":"10.1109\/ISPA.2012.100"},{"key":"1864_CR11","unstructured":"Lee J, Samadi M, Park Y, Mahlke S (2013) Transparent CPU\u2013GPU collaboration for data-parallel Kernels on heterogeneous systems. In: Proc. of PACT, Piscataway, NJ, USA, 2013. IEEE Press, pp 245\u2013256"},{"key":"1864_CR12","doi-asserted-by":"crossref","unstructured":"Binotto APD, Pereira CE, Fellner DW (2010) Towards dynamic reconfigurable load-balancing for hybrid desktop platforms. In: Proc. of IPDPS, pp 1\u20134. IEEE Computer Society, April 2010","DOI":"10.1109\/IPDPSW.2010.5470804"},{"key":"1864_CR13","doi-asserted-by":"crossref","unstructured":"Boyer M, Skadron K, Che S, Jayasena N (2013) Load balancing in a changing World: dealing with heterogeneity and performance variability. In: Proc. of the ACM international conference on computing frontiers, 2013, pp 21:1\u201321:10","DOI":"10.1145\/2482767.2482794"},{"key":"1864_CR14","doi-asserted-by":"crossref","unstructured":"Kaleem R, Barik R, Shpeisman T, Lewis BT, Hu C, Pingali K (2014) Adaptive heterogeneous scheduling for integrated GPUs. In: Proc. of PACT, New York, NY, USA, 2014. ACM, pp 151\u2013162","DOI":"10.1145\/2628071.2628088"},{"issue":"3","key":"1864_CR15","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1145\/1816038.1815998","volume":"38","author":"S Hong","year":"2010","unstructured":"Hong S, Kim H (2010) An integrated GPU power and performance model. SIGARCH Comput Archit News 38(3):280\u2013289","journal-title":"SIGARCH Comput Archit News"},{"key":"1864_CR16","doi-asserted-by":"crossref","unstructured":"Abe Y, Sasaki H, Kato S, Inoue K, Edahiro M, Peres M (2014) Power and performance characterization and modeling of GPU-accelerated systems. In: Parallel and distributed processing symposium, 2014 IEEE 28th International, 2014, pp 113\u2013122","DOI":"10.1109\/IPDPS.2014.23"},{"key":"1864_CR17","doi-asserted-by":"publisher","unstructured":"Price DC, Clark MA, Barsdell BR, Babich R, Greenhill LJ (2015) Optimizing performance-per-watt on GPUs in high performance computing. Comput Sci Res Dev 1\u20139. doi: 10.1007\/s00450-015-0300-5","DOI":"10.1007\/s00450-015-0300-5"},{"key":"1864_CR18","doi-asserted-by":"crossref","unstructured":"Burtscher M, Zecena I, Zong Z (2014) Measuring GPU power with the k20 built-in sensor. In: Proceedings of workshop on general purpose processing using GPUs, GPGPU-7, New York, NY, USA, 2014. ACM, pp 28:28\u201328:36","DOI":"10.1145\/2588768.2576783"},{"key":"1864_CR19","doi-asserted-by":"crossref","unstructured":"Ge R, Vogt R, Majumder J, Alam A, Burtscher M, Zong Z (2013) Effects of dynamic voltage and frequency scaling on a k20 GPU. In: Proceedings of the 42 Int. conference on parallel processing, ICPP \u201913, 2013, pp 826\u2013833","DOI":"10.1109\/ICPP.2013.98"},{"key":"1864_CR20","doi-asserted-by":"crossref","unstructured":"Ma K, Li X, Chen W, Zhang C, Wang X (2012) GreenGPU: A holistic approach to energy efficiency in GPU\u2013CPU heterogeneous architectures. In: 41st International conference on parallel processing, ICPP 2012, 2012, pp 48\u201357","DOI":"10.1109\/ICPP.2012.31"},{"key":"1864_CR21","doi-asserted-by":"crossref","unstructured":"Wang G, Ren X (2010) Power-efficient work distribution method for CPU\u2013GPU heterogeneous system. In: International symposium on parallel and distributed processing with applications, Sept 2010, pp 122\u2013129","DOI":"10.1109\/ISPA.2010.22"},{"key":"1864_CR22","doi-asserted-by":"publisher","unstructured":"Garz\u00f3n, EM, Moreno JJ, Mart\u00ednez JA (2016) An approach to optimise the energy efficiency of iterative computation on integrated GPU\u2013CPU systems. J Supercomput, 1\u201312. doi: 10.1007\/s11227-016-1643-9","DOI":"10.1007\/s11227-016-1643-9"},{"issue":"1","key":"1864_CR23","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/s11227-011-0720-3","volume":"62","author":"Suleyman Tosun","year":"2012","unstructured":"Tosun Suleyman (2012) Energy- and reliability-aware task scheduling onto heterogeneous mpsoc architectures. J Supercomput 62(1):265\u2013289","journal-title":"J Supercomput"},{"issue":"5","key":"1864_CR24","doi-asserted-by":"crossref","first-page":"1893","DOI":"10.1007\/s11227-014-1372-x","volume":"71","author":"G Le\u00f3n","year":"2015","unstructured":"Le\u00f3n G, Molero JM, Garz\u00f3n EM, Garc\u00eda I, Plaza A, Quintana-Ort\u00ed ES (2015) Exploring the performance\u2013power\u2013energy balance of low-power multicore and manycore architectures for anomaly detection in remote sensing. J Supercomput 71(5):1893\u20131906","journal-title":"J Supercomput"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1864-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-016-1864-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-016-1864-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T18:14:03Z","timestamp":1498328043000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-016-1864-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,9,8]]},"references-count":24,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,1]]}},"alternative-id":["1864"],"URL":"https:\/\/doi.org\/10.1007\/s11227-016-1864-y","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,9,8]]}}}