{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T03:10:01Z","timestamp":1747710601391,"version":"3.40.5"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2015,2,27]],"date-time":"2015-02-27T00:00:00Z","timestamp":1424995200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2015,10]]},"DOI":"10.1007\/s10766-015-0349-6","type":"journal-article","created":{"date-parts":[[2015,2,26]],"date-time":"2015-02-26T13:26:45Z","timestamp":1424957205000},"page":"939-960","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["TuCCompi: A Multi-layer Model for Distributed Heterogeneous Computing with Tuning Capabilities"],"prefix":"10.1007","volume":"43","author":[{"given":"Hector","family":"Ortega-Arranz","sequence":"first","affiliation":[]},{"given":"Yuri","family":"Torres","sequence":"additional","affiliation":[]},{"given":"Arturo","family":"Gonzalez-Escribano","sequence":"additional","affiliation":[]},{"given":"Diego R.","family":"Llanos","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,2,27]]},"reference":[{"key":"349_CR1","volume-title":"Designing and building parallel programs: concepts and tools for parallel software engineering","author":"I Foster","year":"1995","unstructured":"Foster, I.: Designing and building parallel programs: concepts and tools for parallel software engineering. Addison-Wesley Longman Publishing Co., Inc., Boston (1995)"},{"key":"349_CR2","volume-title":"The datacenter as a computer: an introduction to the design of warehouse-scale machines","author":"U Hoelzle","year":"2009","unstructured":"Hoelzle, U., Barroso, L.A.: The datacenter as a computer: an introduction to the design of warehouse-scale machines, 1st edn. Morgan and Claypool Publishers, San Rafael (2009)","edition":"1"},{"key":"349_CR3","doi-asserted-by":"crossref","unstructured":"Cirne, W., Paranhos, D., Costa, L., Santos-Neto, E., Brasileiro, F., Sauve, J., Silva, F.A.B., Barros, C., Silveira, C.: Running bag-of-tasks applications on computational grids: the mygrid approach. In: Proceedings of international conference on parallel processing (ICPP 2003), pp. 407\u2013416 (2003)","DOI":"10.1109\/ICPP.2003.1240605"},{"key":"349_CR4","doi-asserted-by":"crossref","unstructured":"Mangharam, R., Saba, A.A.: Anytime algorithms for GPU architectures. In: Proceedings of the 2011 IEEE 32nd real-time systems symposium, RTSS \u201911, pp. 47\u201356. Washington, DC, IEEE Computer Society (2011)","DOI":"10.1109\/RTSS.2011.41"},{"key":"349_CR5","doi-asserted-by":"crossref","unstructured":"Taylor, M.: Bitcoin and the age of bespoke silicon. In: Compilers, architecture and synthesis for embedded systems (CASES), 2013 international conference on, pp. 1\u201310 (2013)","DOI":"10.1109\/CASES.2013.6662520"},{"issue":"1","key":"349_CR6","first-page":"1","volume":"18","author":"AR Brodtkorb","year":"2010","unstructured":"Brodtkorb, A.R., Dyken, C., Hagen, T.R., Hjelmervik, J.M., Storaasli, O.O.: State-of-the-art in heterogeneous computing. Sci. Program. 18(1), 1\u201333 (2010)","journal-title":"Sci. Program."},{"issue":"2","key":"349_CR7","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.micpro.2011.05.006","volume":"36","author":"R Reyes","year":"2012","unstructured":"Reyes, R., de Sande, F.: Optimization strategies in different CUDA architectures using llCoMP. Microprocess. Microsyst. 36(2), 78\u201387 (2012)","journal-title":"Microprocess. Microsyst."},{"key":"349_CR8","doi-asserted-by":"crossref","unstructured":"Liang, T., Li, H., Chiu, J.: Enabling mixed openMP\/MPI programming on hybrid CPU\/GPU computing architecture. In: Proceedings of the 2012 IEEE 26th international parallel and distributed processing symposium workshops & PhD forum (IPDPSW), pp. 2369\u20132377. IEEE, Shanghai (2012)","DOI":"10.1109\/IPDPSW.2012.294"},{"key":"349_CR9","doi-asserted-by":"crossref","unstructured":"Torres, Y., Gonzalez-Escribano, A., Llanos, D.: Using Fermi architecture knowledge to speed up CUDA and OpenCL programs. In: Parallel and distributed processing with applications (ISPA), 2012 IEEE 10th international symposium on, pp. 617\u2013624 (2012)","DOI":"10.1109\/ISPA.2012.92"},{"key":"349_CR10","doi-asserted-by":"crossref","unstructured":"Torres, Y., Gonzalez-Escribano, A., Llanos, D.R.: uBench: exposing the impact of CUDA block geometry in terms of performance. J. Supercomput. 65(3), 1150\u20131163 (2013)","DOI":"10.1007\/s11227-013-0921-z"},{"key":"349_CR11","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.cpc.2010.06.035","volume":"182","author":"C Yang","year":"2011","unstructured":"Yang, C., Huang, C., Lin, C.: Hybrid CUDA, OpenMP, and MPI parallel programming on multicore GPU clusters. Comput. Phys. Commun. 182, 266\u2013269 (2011)","journal-title":"Comput. Phys. Commun."},{"issue":"1","key":"349_CR12","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/TVCG.2011.24","volume":"18","author":"M Howison","year":"2012","unstructured":"Howison, M., Bethel, E., Childs, H.: Hybrid parallelism for volume rendering on large-, multi-, and many-core systems. Vis. Comput. Graph. IEEE Trans. 18(1), 17\u201329 (2012)","journal-title":"Vis. Comput. Graph. IEEE Trans."},{"key":"349_CR13","first-page":"258272","volume-title":"Parallel computing technologies","author":"M Steuwer","year":"2013","unstructured":"Steuwer, M., Gorlatch, S.: SkelCL: enhancing OpenCL for high-level programming of multi-GPU systems. In: LNCS, ser, Malyshkin, V. (eds.) Parallel computing technologies, p. 258272. Springer, Berlin (2013)"},{"key":"349_CR14","doi-asserted-by":"crossref","unstructured":"Hugo, A.-E., Guermouche, A., Wacrenier, P.-A., Namyst, R.: Composing multiple starPU applications over heterogeneous machines: a supervised approach. In: Proceedings of IEEE 27th IPDPSW\u201913, pp. 1050\u20131059. Washington, USA: IEEE, (2013)","DOI":"10.1109\/IPDPSW.2013.217"},{"key":"349_CR15","doi-asserted-by":"crossref","unstructured":"Dastgeer, U., Enmyren, J., Kessler, C. W.: Auto-tuning SkePU: a multi-backend skeleton programming framework for multi-GPU systems. In: Proceedings of the 4th IWMSE, pp. 25\u201332. New York, NY, USA: ACM, (2011)","DOI":"10.1145\/1984693.1984697"},{"key":"349_CR16","doi-asserted-by":"crossref","unstructured":"Reyes, R., L\u00f3pez-Rodr\u00edguez, I., Fumero, J.J., de Sande, F.: accULL: an OpenACC implementation with CUDA and OpenCL support. In: Proceedings of the 18th conference on parallel processing, ser. EuroPar\u201912, pp. 871\u2013882. Springer, Berlin (2012)","DOI":"10.1007\/978-3-642-32820-6_86"},{"key":"349_CR17","doi-asserted-by":"crossref","unstructured":"Farooqui, N., Kerr, A., Diamos, G.F., Yalamanchili, S., Schwan, K.:A framework for dynamically instrumenting GPU compute applications within GPU Ocelot. In: Proceedings of 4th workshop on GPGPU: CA, USA, 5 Mar 2011. ACM, p. 9 (2011)","DOI":"10.1145\/1964179.1964192"},{"issue":"4","key":"349_CR18","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1145\/2499368.2451160","volume":"48","author":"S Pai","year":"2013","unstructured":"Pai, S., Thazhuthaveetil, M.J., Govindarajan, R.: Improving GPGPU concurrency with elastic kernels. SIGPLAN Not. 48(4), 407\u2013418 (2013)","journal-title":"SIGPLAN Not."},{"key":"349_CR19","unstructured":"NVIDIA.: NVIDIA CUDA programming guide 6.0, (2014)"},{"key":"349_CR20","unstructured":"Kirk, D. B., Hwu, W.W.: Programming massively parallel processors: a hands-on approach, 1st edn. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2010)"},{"key":"349_CR21","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/BF01386390","volume":"1","author":"EW Dijkstra","year":"1959","unstructured":"Dijkstra, E.W.: A note on two problems in connexion with graphs. Numerische Mathematik 1, 269\u2013271 (1959)","journal-title":"Numerische Mathematik"},{"key":"349_CR22","doi-asserted-by":"crossref","unstructured":"Crauser, A., Mehlhorn, K., Meyer, U., Sanders, P.: A parallelization of Dijkstra\u2019s shortest path algorithm. In: LNCS, ser, Brim, L., Gruska, J., Zlatu\u0161ka, J. (eds.) Mathematical foundations of computer science 1998, pp. 722\u2013731. Springer, Berlin (1998)","DOI":"10.1007\/BFb0055823"},{"key":"349_CR23","doi-asserted-by":"crossref","unstructured":"Ortega-Arranz, H., Torres, Y., Llanos, D.R., Gonzalez-Escribano, A.: A new GPU-based approach to the shortest path problem. In: High performance computing and simulation (HPCS). international conference on 2013, pp. 505\u2013512 (2013)","DOI":"10.1109\/HPCSim.2013.6641461"},{"key":"349_CR24","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1007\/978-3-642-01970-8_91","volume-title":"Computational Science: ICCS 2009","author":"P Mart\u00edn","year":"2009","unstructured":"Mart\u00edn, P., Torres, R., Gavilanes, A.: CUDA solutions for the SSSP problem. In: LNCS, ser, Allen, G., Nabrzyski, J., Seidel, E., van Albada, G., Dongarra, J., Sloot, P. (eds.) Computational Science: ICCS 2009, pp. 904\u2013913. Springer, Berlin (2009)"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-015-0349-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-015-0349-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-015-0349-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T02:46:14Z","timestamp":1747709174000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-015-0349-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2,27]]},"references-count":24,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2015,10]]}},"alternative-id":["349"],"URL":"https:\/\/doi.org\/10.1007\/s10766-015-0349-6","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2015,2,27]]}}}