{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:38:54Z","timestamp":1740123534161,"version":"3.37.3"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,3,26]],"date-time":"2020-03-26T00:00:00Z","timestamp":1585180800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,3,26]],"date-time":"2020-03-26T00:00:00Z","timestamp":1585180800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100010198","name":"Ministerio de Econom\u00eda, Industria y Competitividad, Gobierno de Espa\u00f1a","doi-asserted-by":"crossref","award":["TIN2016-76373-P"],"award-info":[{"award-number":["TIN2016-76373-P"]}],"id":[{"id":"10.13039\/501100010198","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100010556","name":"Conseller\u00eda de Econom\u00eda, Emprego e Industria, Xunta de Galicia","doi-asserted-by":"crossref","award":["2016-2019 ED431G2019\/04","2019-2021 ED431C 2018\/19"],"award-info":[{"award-number":["2016-2019 ED431G2019\/04","2019-2021 ED431C 2018\/19"]}],"id":[{"id":"10.13039\/501100010556","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s11227-020-03260-8","type":"journal-article","created":{"date-parts":[[2020,3,26]],"date-time":"2020-03-26T20:02:52Z","timestamp":1585252972000},"page":"95-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["IHP: a dynamic heterogeneous parallel scheme for iterative or time-step methods\u2014image denoising as case study"],"prefix":"10.1007","volume":"77","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2574-4025","authenticated-orcid":false,"given":"Ruben","family":"Laso","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5674-5162","authenticated-orcid":false,"given":"Jos\u00e9 C.","family":"Cabaleiro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6728-9350","authenticated-orcid":false,"given":"Francisco F.","family":"Rivera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8055-063X","authenticated-orcid":false,"given":"M. Carmen","family":"Mu\u00f1iz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9131-4616","authenticated-orcid":false,"given":"Jos\u00e9 A.","family":"\u00c1lvarez-Dios","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,26]]},"reference":[{"issue":"5","key":"3260_CR1","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1002\/nme.2989","volume":"85","author":"C Cecka","year":"2011","unstructured":"Cecka C, Lew AJ, Darve E (2011) Assembly of finite element methods on graphics processors. Int J Numer Methods Eng 85(5):640\u2013669","journal-title":"Int J Numer Methods Eng"},{"issue":"1","key":"3260_CR2","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/99.660313","volume":"5","author":"L Dagum","year":"1998","unstructured":"Dagum L, Menon R (1998) OpenMP: an industry-standard API for shared-memory programming. IEEE Comput Sci Eng 5(1):46\u201355. https:\/\/doi.org\/10.1109\/99.660313","journal-title":"IEEE Comput Sci Eng"},{"key":"3260_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.parco.2014.12.003","volume":"46","author":"C Feichtinger","year":"2015","unstructured":"Feichtinger C, Habich J, K\u00f6stler H, R\u00fcde U, Aoki T (2015) Performance modeling and analysis of heterogeneous lattice Boltzmann simulations on CPU\u2013GPU clusters. Parallel Comput 46:1\u201313. https:\/\/doi.org\/10.1016\/j.parco.2014.12.003","journal-title":"Parallel Comput"},{"key":"3260_CR4","unstructured":"GCC Developer Community (2017) GCC, the GNU compiler collection. https:\/\/gcc.gnu.org\/. Accessed 15 Dec 2018"},{"key":"3260_CR5","doi-asserted-by":"crossref","unstructured":"Hore A, Ziou D (2010) Image quality metrics: PSNR vs. SSIM. In: Proceedings of the 2010 20th International Conference on Pattern Recognition, ICPR \u201910. IEEE Computer Society, IEEE Computer Society, Washington, DC, USA, pp 2366\u20132369. DOIurlhttps:\/\/doi.org\/10.1109\/ICPR.2010.579","DOI":"10.1109\/ICPR.2010.579"},{"key":"3260_CR6","unstructured":"Intel Corporation (2017) Intel core i5-7600 processor. https:\/\/ark.intel.com\/products\/97150\/Intel-Core-i5-7600-Processor-6M-Cache-up-to-4_10-GHz. Accessed 08 Jan 2019"},{"key":"3260_CR7","doi-asserted-by":"publisher","unstructured":"Kaleem R, Barik R, Shpeisman T, Hu C, Lewis BT, Pingali K (2014) Adaptive heterogeneous scheduling for integrated GPUs. In: 2014 23rd International Conference on Parallel Architecture and Compilation Techniques (PACT), pp 151\u2013162. https:\/\/doi.org\/10.1145\/2628071.2628088","DOI":"10.1145\/2628071.2628088"},{"issue":"4","key":"3260_CR8","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/s12273-015-0232-9","volume":"8","author":"MAI Khan","year":"2015","unstructured":"Khan MAI, Delbosc N, Noakes CJ, Summers J (2015) Real-time flow simulation of indoor environments using lattice Boltzmann method. Build Simul 8(4):405\u2013414. https:\/\/doi.org\/10.1007\/s12273-015-0232-9","journal-title":"Build Simul"},{"issue":"5","key":"3260_CR9","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/j.jpdc.2009.01.006","volume":"69","author":"D Komatitsch","year":"2009","unstructured":"Komatitsch D, Mich\u00e9a D, Erlebacher G (2009) Porting a high-order finite-element earthquake modeling application to NVIDIA graphics cards using CUDA. J Parallel Distrib Comput 69(5):451\u2013460. https:\/\/doi.org\/10.1016\/j.jpdc.2009.01.006","journal-title":"J Parallel Distrib Comput"},{"key":"3260_CR10","unstructured":"Laso R, Cabaleiro JC, Rivera FF, Mu\u00f1iz MC, \u00c1lvarez-Dios JA (2019) Diffusion methods for image denoising using IHP. https:\/\/gitlab.citius.usc.es\/ruben.laso\/diffusion-methods-ihp-opencl. Accessed 24 Mar 2020"},{"key":"3260_CR11","unstructured":"Laso R, Cabaleiro JC, Rivera FF, Mu\u00f1iz MC, \u00c1lvarez-Dios JA (2019) IHP: iterative heterogeneous parallelism. https:\/\/gitlab.citius.usc.es\/ruben.laso\/ihp. Accessed 24 Mar 2020"},{"issue":"1","key":"3260_CR12","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1002\/fld.3648","volume":"71","author":"G Markall","year":"2013","unstructured":"Markall G, Slemmer A, Ham D, Kelly P, Cantwell C, Sherwin S (2013) Finite element assembly strategies on multi-core and many-core architectures. Int J Numer Methods Fluids 71(1):80\u201397","journal-title":"Int J Numer Methods Fluids"},{"key":"3260_CR13","doi-asserted-by":"publisher","unstructured":"Micikevicius P (2009) 3D finite difference computation on GPUs using CUDA. In: Proceedings of 2nd Workshop on General Purpose Processing on Graphics Processing Units, GPGPU-2. ACM, New York, pp 79\u201384. https:\/\/doi.org\/10.1145\/1513895.1513905","DOI":"10.1145\/1513895.1513905"},{"issue":"4","key":"3260_CR14","doi-asserted-by":"publisher","first-page":"69:1","DOI":"10.1145\/2788396","volume":"47","author":"S Mittal","year":"2015","unstructured":"Mittal S, Vetter JS (2015) A survey of CPU\u2013GPU heterogeneous computing techniques. ACM Comput Surv 47(4):69:1\u201369:35. https:\/\/doi.org\/10.1145\/2788396","journal-title":"ACM Comput Surv"},{"issue":"2","key":"3260_CR15","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s10766-018-0555-0","volume":"47","author":"A Navarro","year":"2019","unstructured":"Navarro A, Corbera F, Rodriguez A, Vilches A, Asenjo R (2019) Heterogeneous parallel\\_for template for CPU\u2013GPU chips. Int J Parallel Program 47(2):213\u2013233. https:\/\/doi.org\/10.1007\/s10766-018-0555-0","journal-title":"Int J Parallel Program"},{"issue":"2","key":"3260_CR16","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1145\/1365490.1365500","volume":"6","author":"J Nickolls","year":"2008","unstructured":"Nickolls J, Buck I, Garland M, Skadron K (2008) Scalable parallel programming with CUDA. Queue 6(2):40\u201353. https:\/\/doi.org\/10.1145\/1365490.1365500","journal-title":"Queue"},{"key":"3260_CR17","unstructured":"NVIDIA Corporation (2018) CUDA compiler driver NVCC, reference guide. https:\/\/docs.nvidia.com\/pdf\/CUDA_Compiler_Driver_NVCC.pdf. Accessed 7 May 2019"},{"key":"3260_CR18","unstructured":"NVIDIA Corporation (2018) Geforce GTX 1050 Ti. https:\/\/www.geforce.com\/hardware\/desktop-gpus\/geforce-gtx-1050-ti\/specifications. Accessed 8 Jan 2019"},{"issue":"13","key":"3260_CR19","doi-asserted-by":"publisher","first-page":"1490","DOI":"10.1016\/j.cma.2011.01.013","volume":"200","author":"M Papadrakakis","year":"2011","unstructured":"Papadrakakis M, Stavroulakis G, Karatarakis A (2011) A new era in scientific computing: domain decomposition methods in hybrid CPU\u2013GPU architectures. Comput Methods Appl Mech Eng 200(13):1490\u20131508. https:\/\/doi.org\/10.1016\/j.cma.2011.01.013","journal-title":"Comput Methods Appl Mech Eng"},{"key":"3260_CR20","doi-asserted-by":"publisher","unstructured":"P\u00e9rez B, Bosque JL, Beivide R (2016) Simplifying programming and load balancing of data parallel applications on heterogeneous systems. In: Proceedings of the 9th Annual Workshop on General Purpose Processing Using Graphics Processing Unit, GPGPU \u201916. ACM, New York, pp 42\u201351. https:\/\/doi.org\/10.1145\/2884045.2884051","DOI":"10.1145\/2884045.2884051"},{"issue":"4","key":"3260_CR21","first-page":"298","volume":"23","author":"C Pheatt","year":"2008","unstructured":"Pheatt C (2008) Intel threading building blocks. J Comput Sci Coll 23(4):298\u2013298","journal-title":"J Comput Sci Coll"},{"issue":"4","key":"3260_CR22","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1016\/j.jpdc.2010.10.011","volume":"71","author":"R Shams","year":"2011","unstructured":"Shams R, Sadeghi P (2011) On optimization of finite-difference time-domain (FDTD) computation on heterogeneous and GPU clusters. J Parallel Distrib Comput 71(4):584\u2013593. https:\/\/doi.org\/10.1016\/j.jpdc.2010.10.011","journal-title":"J Parallel Distrib Comput"},{"issue":"3","key":"3260_CR23","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/MCSE.2010.69","volume":"12","author":"JE Stone","year":"2010","unstructured":"Stone JE, Gohara D, Shi G (2010) OpenCL: a parallel programming standard for heterogeneous computing systems. Comput Sci Eng 12(3):66\u201373. https:\/\/doi.org\/10.1109\/MCSE.2010.69","journal-title":"Comput Sci Eng"},{"issue":"5","key":"3260_CR24","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1109\/83.918563","volume":"10","author":"B Tang","year":"2001","unstructured":"Tang B, Sapiro G, Caselles V (2001) Color image enhancement via chromaticity diffusion. IEEE Trans Image Process 10(5):701\u2013707. https:\/\/doi.org\/10.1109\/83.918563","journal-title":"IEEE Trans Image Process"},{"key":"3260_CR25","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.procs.2015.05.213","volume":"51","author":"A Vilches","year":"2015","unstructured":"Vilches A, Asenjo R, Navarro A, Corbera F, Gran R, Garzar\u00e1n M (2015) Adaptive partitioning for irregular applications on heterogeneous CPU\u2013GPU chips. Proc Comput Sci 51:140\u2013149. https:\/\/doi.org\/10.1016\/j.procs.2015.05.213","journal-title":"Proc Comput Sci"},{"issue":"12","key":"3260_CR26","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1016\/j.jpdc.2013.07.013","volume":"73","author":"M Vi\u00f1as","year":"2013","unstructured":"Vi\u00f1as M, Bozkus Z, Fraguela BB (2013) Exploiting heterogeneous parallelism with the heterogeneous programming library. J Parallel Distrib Comput 73(12):1627\u20131638. https:\/\/doi.org\/10.1016\/j.jpdc.2013.07.013","journal-title":"J Parallel Distrib Comput"},{"issue":"4","key":"3260_CR27","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP et al (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600\u2013612. https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans Image Process"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03260-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-020-03260-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03260-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,26]],"date-time":"2021-03-26T01:03:34Z","timestamp":1616720614000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-020-03260-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3,26]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["3260"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03260-8","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2020,3,26]]},"assertion":[{"value":"26 March 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}