{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T20:12:41Z","timestamp":1775247161304,"version":"3.50.1"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2018,10,11]],"date-time":"2018-10-11T00:00:00Z","timestamp":1539216000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003176","name":"Ministerio de Educaci\u00f3n, Cultura y Deporte","doi-asserted-by":"publisher","award":["FPU16\/00942"],"award-info":[{"award-number":["FPU16\/00942"]}],"id":[{"id":"10.13039\/501100003176","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010198","name":"Ministerio de Econom\u00eda, Industria y Competitividad, Gobierno de Espa\u00f1a","doi-asserted-by":"publisher","award":["TIN2016-78919-R"],"award-info":[{"award-number":["TIN2016-78919-R"]}],"id":[{"id":"10.13039\/501100010198","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Gobierno de Canarias","award":["ProID2017010130"],"award-info":[{"award-number":["ProID2017010130"]}]},{"name":"CAPAP-H Network"},{"DOI":"10.13039\/501100000921","name":"European Cooperation in Science and Technology","doi-asserted-by":"publisher","award":["cHiPSet COST Action"],"award-info":[{"award-number":["cHiPSet COST Action"]}],"id":[{"id":"10.13039\/501100000921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s11227-018-2638-5","type":"journal-article","created":{"date-parts":[[2018,10,11]],"date-time":"2018-10-11T02:16:13Z","timestamp":1539224173000},"page":"1382-1395","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["High-performance code optimizations for mobile devices"],"prefix":"10.1007","volume":"75","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0838-8057","authenticated-orcid":false,"given":"Sergio","family":"Afonso","sequence":"first","affiliation":[]},{"given":"Alejandro","family":"Acosta","sequence":"additional","affiliation":[]},{"given":"Francisco","family":"Almeida","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,11]]},"reference":[{"key":"2638_CR1","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.simpat.2015.05.006","volume":"58","author":"A Acosta","year":"2015","unstructured":"Acosta A, Almeida F (2015) Towards the optimal execution of renderscript applications in android devices. Simul Model Pract Theory 58:55\u201364. https:\/\/doi.org\/10.1016\/j.simpat.2015.05.006","journal-title":"Simul Model Pract Theory"},{"key":"2638_CR2","doi-asserted-by":"publisher","unstructured":"Afonso S, Acosta A, Almeida F (2017) Automatic acceleration of stencil codes in android devices, pp. 81\u201395. Springer International Publishing, Cham. https:\/\/doi.org\/10.1007\/978-3-319-65482-9_6","DOI":"10.1007\/978-3-319-65482-9_6"},{"key":"2638_CR3","doi-asserted-by":"publisher","unstructured":"Almeida F, Andonov R, Gonz\u00e1lez D, Moreno LM, Poirriez V, Rodr\u00edguez C (2002) Optimal tiling for the RNA base pairing problem. In: SPAA, pp. 173\u2013182. https:\/\/doi.org\/10.1145\/564870.564901","DOI":"10.1145\/564870.564901"},{"issue":"2","key":"2638_CR4","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1006\/jpdc.1997.1371","volume":"45","author":"R Andonov","year":"1997","unstructured":"Andonov R, Rajopadhye S (1997) Optimal orthogonal tiling of 2-d iterations. J Parallel Distrib Comput 45(2):159\u2013165. https:\/\/doi.org\/10.1006\/jpdc.1997.1371","journal-title":"J Parallel Distrib Comput"},{"key":"2638_CR5","unstructured":"ARM: Mali graphics and multimedia processors. https:\/\/developer.arm.com\/products\/graphics-and-multimedia\/mali-gpus"},{"key":"2638_CR6","doi-asserted-by":"publisher","unstructured":"Boratto M, Alonso P, Gim\u00e9nez D, Barreto M (2013) Oliveira K Auto-tuning methodology to represent landform attributes on multicore and multi-gpu systems. In: Proceedings of the 2013 International Workshop on Programming Models and Applications for Multicores and Manycores, PMAM \u201913, pp. 125\u2013132. ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/2442992.2443006","DOI":"10.1145\/2442992.2443006"},{"issue":"1","key":"2638_CR7","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s11227-016-1694-y","volume":"73","author":"M Boratto","year":"2017","unstructured":"Boratto M, Alonso P, Gim\u00e9nez D, Lastovetsky A (2017) Automatic tuning to performance modelling of matrix polynomials on multicore and multi-gpu systems. J Supercomput 73(1):227\u2013239. https:\/\/doi.org\/10.1007\/s11227-016-1694-y","journal-title":"J Supercomput"},{"issue":"6","key":"2638_CR8","doi-asserted-by":"publisher","first-page":"2549","DOI":"10.12785\/amis\/070651","volume":"7","author":"SL Chu","year":"2013","unstructured":"Chu SL, Hsiao CC (2013) Methods for optimizing opencl applications on heterogeneous multicore architectures. Appl Math Inf Sci 7(6):2549","journal-title":"Appl Math Inf Sci"},{"key":"2638_CR9","doi-asserted-by":"crossref","unstructured":"Garc\u00eda LP, Cuenca J, Gim\u00e9nez D (2007) Including improvement of the execution time in a software architecture of libraries with self-optimisation. In: ICSOFT (SE), pp. 156\u2013161. Citeseer","DOI":"10.5220\/0001337501560161"},{"key":"2638_CR10","doi-asserted-by":"crossref","unstructured":"Holewinski J, Pouchet LN, Sadayappan P (2012) High-performance code generation for stencil computations on gpu architectures. In: Proceedings of the 26th ACM International Conference on Supercomputing, pp. 311\u2013320. ACM","DOI":"10.1145\/2304576.2304619"},{"key":"2638_CR11","unstructured":"Imagination: A quick guide to writing OpenCL kernels for PowerVR Rogue GPUs. https:\/\/www.imgtec.com\/blog\/a-quick-guide-to-writing-opencl-kernels-for-rogue\/ . Accessed 9 Oct 2018"},{"key":"2638_CR12","doi-asserted-by":"publisher","unstructured":"Magni A, Dubach C, O\u2019Boyle MFP (2013) A large-scale cross-architecture evaluation of thread-coarsening. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC \u201913, pp. 11:1\u201311:11. ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/2503210.2503268","DOI":"10.1145\/2503210.2503268"},{"key":"2638_CR13","unstructured":"Qualcomm: Adreno GPU SDK. https:\/\/developer.qualcomm.com\/software\/adreno-gpu-sdk . Accessed 9 Oct 2018"},{"issue":"6","key":"2638_CR14","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1145\/2499370.2462176","volume":"48","author":"J Ragan-Kelley","year":"2013","unstructured":"Ragan-Kelley J, Barnes C, Adams A, Paris S, Durand F, Amarasinghe S (2013) Halide: a language and compiler for optimizing parallelism, locality, and recomputation in image processing pipelines. SIGPLAN Not. 48(6):519\u2013530. https:\/\/doi.org\/10.1145\/2499370.2462176","journal-title":"SIGPLAN Not."},{"issue":"8","key":"2638_CR15","doi-asserted-by":"publisher","first-page":"4053","DOI":"10.1002\/cpe.4053","volume":"29","author":"RCO Rocha","year":"2017","unstructured":"Rocha RCO, Pereira AD, Ramos L, G\u00f3es LFW (2017) Toast: automatic tiling for iterative stencil computations on gpus. Concurr Comput Pract Exp 29(8):4053. https:\/\/doi.org\/10.1002\/cpe.4053","journal-title":"Concurr Comput Pract Exp"},{"key":"2638_CR16","doi-asserted-by":"crossref","unstructured":"Shen J, Fang J, Sips H, Varbanescu AL (2013) Performance traps in opencl for cpus. In: 2013 21st Euromicro International Conference on Parallel, Distributed and Network-based Processing (PDP), pp. 38\u201345. IEEE","DOI":"10.1109\/PDP.2013.16"},{"key":"2638_CR17","unstructured":"StatCounter: Mobile operating system market share worldwide. http:\/\/gs.statcounter.com\/os-market-share\/mobile\/worldwide\/2017 . Accessed 9 Oct 2018"},{"key":"2638_CR18","unstructured":"Vivante: Vivante Vega GPGPU technology. http:\/\/www.vivantecorp.com\/index.php\/en\/technology\/gpgpu.html . Accessed 9 Oct 2018"},{"key":"2638_CR19","doi-asserted-by":"publisher","unstructured":"Whaley RC, Petitet A, Dongarra JJ (2001) Automated empirical optimizations of software and the atlas project. Parallel Comput 27(1):3\u201335. https:\/\/doi.org\/10.1016\/S0167-8191(00)00087-9","DOI":"10.1016\/S0167-8191(00)00087-9"},{"key":"2638_CR20","doi-asserted-by":"publisher","unstructured":"Wolfe M (1989) More iteration space tiling. In: Proceedings of the 1989 ACM\/IEEE Conference on Supercomputing, Supercomputing \u201989, pp. 655\u2013664. ACM, New York, NY, USA. https:\/\/doi.org\/10.1145\/76263.76337","DOI":"10.1145\/76263.76337"},{"key":"2638_CR21","doi-asserted-by":"crossref","unstructured":"Zhang Y, Sinclair M, Chien AA (2013) Improving performance portability in opencl programs. In: ISC, pp. 136\u2013150. Springer","DOI":"10.1007\/978-3-642-38750-0_11"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-2638-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11227-018-2638-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-018-2638-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T19:28:31Z","timestamp":1775244511000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11227-018-2638-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10,11]]},"references-count":21,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["2638"],"URL":"https:\/\/doi.org\/10.1007\/s11227-018-2638-5","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,10,11]]},"assertion":[{"value":"11 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}