{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T04:03:49Z","timestamp":1744344229943,"version":"3.40.4"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2012,10,10]],"date-time":"2012-10-10T00:00:00Z","timestamp":1349827200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2014,3]]},"DOI":"10.1007\/s11554-012-0279-0","type":"journal-article","created":{"date-parts":[[2012,10,9]],"date-time":"2012-10-09T10:52:54Z","timestamp":1349779974000},"page":"217-232","source":"Crossref","is-referenced-by-count":8,"title":["Efficient implementation of data flow graphs on multi-gpu clusters"],"prefix":"10.1007","volume":"9","author":[{"given":"Vincent","family":"Boulos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sylvain","family":"Huet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent","family":"Fristot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luc","family":"Salvo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dominique","family":"Houzet","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,10,10]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Aldinucci, M., Danelutto, M., Kilpatrick, P., Torquati, M.: Targeting heterogeneous architectures via macro data flow. In: International Workshop on High-level Programming for Heterogeneous and Hierarchical Parallel Systems (HLPGPU), HiPEAC, pp. 1\u20136 (2012)","key":"279_CR1","DOI":"10.1142\/S0129626412400063"},{"unstructured":"Aldinucci, M., Danelutto, M., Kilpatrick, P., Torquati, M.: Fastflow: high-level and efficient streaming on multi-core. In: Pllana, S., Xhafa, F. (eds.) Programming Multi-core and Many-core Computing Systems, Parallel and Distributed Computing, Chap 13. Wiley, New York. http:\/\/citeseerx.ist.psu.edu\/viewdoc\/summary?doi=10.1.1.228.2451 (2012)","key":"279_CR2"},{"doi-asserted-by":"crossref","unstructured":"Augonnet, C., Clet-Ortega, J., Thibault, S., Namyst, R.: Data-aware task scheduling on multi-accelerator based platforms. In: 2010 IEEE 16th International Conference on Parallel and Distributed Systems (ICPADS), IEEE, pp. 291\u2013298. doi: 10.1109\/ICPADS.2010.129 (2010)","key":"279_CR3","DOI":"10.1109\/ICPADS.2010.129"},{"doi-asserted-by":"crossref","unstructured":"Ayguad\u00e9, E., Badia, R.M., Igual, F.D., Labarta, J., Mayo, R., Quintana-Ort\u00ed, E.S.: An extension of the starss programming model for platforms with multiple gpus. In: Euro-Par, pp. 851\u2013862 (2009)","key":"279_CR4","DOI":"10.1007\/978-3-642-03869-3_79"},{"doi-asserted-by":"crossref","unstructured":"Binotto, A.P., Pedras, B.M., Gotz, M., Kuijper, A., Pereira, C.E.,Stork, A., Fellner, D.W.: Effective dynamic scheduling on heterogeneous multi\/manycore desktop platforms. In: 2010 22nd International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW), IEEE, pp. 37\u201342. doi: 10.1109\/SBAC-PADW.2010.6","key":"279_CR5","DOI":"10.1109\/SBAC-PADW.2010.6"},{"doi-asserted-by":"crossref","unstructured":"Chen, L., Villa, O., Gao, G.R.: Exploring fine-grained task-based execution on multi-GPU systems. In: 2011 IEEE International Conference on Cluster Computing (CLUSTER), IEEE, pp. 386\u2013394. doi: 10.1109\/CLUSTER.2011.50 (2011)","key":"279_CR6","DOI":"10.1109\/CLUSTER.2011.50"},{"doi-asserted-by":"crossref","unstructured":"Danalis, A., Marin, G., McCurdy, C., Meredith, J.S., Roth, P.C., Spafford, K., Tipparaju, V., Vetter, J.S.: The scalable heterogeneous computing (shoc) benchmark suite. In: Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units (2010)","key":"279_CR7","DOI":"10.1145\/1735688.1735702"},{"doi-asserted-by":"crossref","unstructured":"Diamos, G.F., Yalamanchili, S.: Harmony: an execution model and runtime for heterogeneous many core systems. In: Proceedings of the 17th International Symposium on High Performance Distributed Computing, ACM, New York, HPDC \u201808, pp. 197\u2013200. doi: 10.1145\/1383422.1383447 (2008)","key":"279_CR8","DOI":"10.1145\/1383422.1383447"},{"unstructured":"Dolbeau, R.: Hmpp: a hybrid multi-core parallel. In: First Workshop on General Purpose Processing on Graphics Processing Units, pp. 1\u20135. http:\/\/www.caps-entreprise.com\/upload\/ckfinder\/userfiles\/files\/caps-hmpp-gpgpu-Boston-Workshop-Oct-2007.pdf (2007)","key":"279_CR9"},{"doi-asserted-by":"crossref","unstructured":"Fan, Z., Qiu, F., Kaufman, A., Yoakum-Stover, S.: GPU cluster for high performance computing. In: Supercomputing, 2004. Proceedings of the ACM\/IEEE SC2004 Conference, IEEE, pp. 47\u2013 47. doi: 10.1109\/SC.2004.26 (2004)","key":"279_CR10","DOI":"10.1109\/SC.2004.26"},{"doi-asserted-by":"crossref","unstructured":"Gautier, T., Besseron, X., Pigeon, L.: KAAPI: a thread scheduling runtime system for data flow computations on cluster of multi-processors. In: 2007 International Workshop on Parallel Symbolic Computation, ACM, Waterloo, pp. 15\u201323. doi: 10.1145\/1278177.1278182 , URL: http:\/\/hal.inria.fr\/hal-00684843 (2007)","key":"279_CR11","DOI":"10.1145\/1278177.1278182"},{"doi-asserted-by":"crossref","unstructured":"Grandpierre, T., Lavarenne, C., Sorel, Y.: Optimized rapid prototyping for real-time embedded heterogeneous multiprocessors. In: Proceedings of the Seventh International Workshop on Hardware\/Software Codesign, ACM, New York, CODES \u201999, pp. 74\u201378. doi: 10.1145\/301177.301489 (1999)","key":"279_CR12","DOI":"10.1145\/301177.301489"},{"key":"279_CR13","volume-title":"Using MPI: Portable Parallel Programming with the Message-Passing Interface","author":"W. Gropp","year":"1999","unstructured":"Gropp, W., Lusk, E., Skjellum, A.: Using MPI: Portable Parallel Programming with the Message-Passing Interface, 2nd edn. MIT Press, Cambridge (1999)","edition":"2"},{"doi-asserted-by":"crossref","unstructured":"Han, T.D., Abdelrahman, T.S.: Hicuda: a high-level directive-based language for gpu programming. In: Proceedings of 2nd Workshop on General Purpose Processing on Graphics Processing Units, ACM, New York, GPGPU-2, pp. 52\u201361. doi: 10.1145\/1513895.1513902 (2009)","key":"279_CR14","DOI":"10.1145\/1513895.1513902"},{"doi-asserted-by":"crossref","unstructured":"Hsu, C.J., Pino, J.L., Bhattacharyya, S.S.: Multithreaded simulation for synchronous dataflow graphs. In: Proceedings of the 45th annual Design Automation Conference, ACM, New York, DAC \u201908, pp. 331\u2013336. doi: 10.1145\/1391469.1391553 (2008)","key":"279_CR15","DOI":"10.1145\/1391469.1391553"},{"key":"279_CR16","doi-asserted-by":"crossref","first-page":"1254","DOI":"10.1109\/34.730558","volume":"20","author":"L. Itti","year":"1998","unstructured":"Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20, 1254\u20131259. doi: 10.1109\/34.730558 (1998)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"unstructured":"Karimi, K., Dickson, N.G., Hamze, F.: A performance comparison of cuda and opencl. CoRR abs\/1005.2581 (2010)","key":"279_CR17"},{"unstructured":"LAVALab (2008) Choosing between pinned and non-pinned memory. Tech. rep., URL: http:\/\/www.cs.virginia.edu\/\u223cmwb7w\/cuda_support\/pinned_tradeoff.html","key":"279_CR18"},{"doi-asserted-by":"crossref","unstructured":"Li, T., Narayana, V.K., El-Ghazawi, T.: A static task scheduling framework for independent tasks accelerated using a shared graphics processing unit. In: 2011 IEEE 17th International Conference on Parallel and Distributed Systems (ICPADS), IEEE, pp. 88\u201395. doi: 10.1109\/ICPADS.2011.13 (2011)","key":"279_CR19","DOI":"10.1109\/ICPADS.2011.13"},{"key":"279_CR20","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1145\/1353535.1346318","volume":"42","author":"M. Linderman","year":"2008","unstructured":"Linderman, M., Collins, J., Wang, H., Meng, T. (2008) Merge: a programming model for heterogeneous multi-core systems. ACM SIGOPS Oper. Syst. Rev. 42, 287\u2013296","journal-title":"ACM SIGOPS Oper. Syst. Rev."},{"key":"279_CR21","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1007\/s11263-009-0215-3","volume":"82","author":"S. Marat","year":"2009","unstructured":"Marat, S., Ho Phuoc, T., Granjon, L., Guyader, N., Pellerin, D., Gu\u00e9rin-Dugu\u00e9, A. (2009) Modelling spatio-temporal saliency to predict gaze direction for short videos. Int. J. Comput. Vis. 82, 231\u2013243. doi: 10.1007\/s11263-009-0215-3","journal-title":"Int. J. Comput. Vis."},{"doi-asserted-by":"crossref","unstructured":"Membarth, R., Hannig, F., Teich, J., Korner, M., Eckert, W.: Frameworks for GPU accelerators: a comprehensive evaluation using 2D\/3D image registration. In: 2011 IEEE 9th Symposium on Application Specific Processors (SASP), IEEE, pp. 78\u201381. doi: 10.1109\/SASP.2011.5941083 (2011)","key":"279_CR22","DOI":"10.1109\/SASP.2011.5941083"},{"unstructured":"Ospici, M., Komatitsch, D., Mehaut, J.F., Deutsch, T.: SGPU 2: a runtime system for using of large applications on clusters of hybrid nodes. In: Second Workshop on Hybrid Multi-Core Computing, Held in Conjunction with HiPC 2011, Bangalore (2011)","key":"279_CR23"},{"doi-asserted-by":"crossref","unstructured":"Ou, Y., Chen, H., Lai, L.: A dynamic load balance on GPU cluster for fork-join search. In: 2011 IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS), IEEE, pp. 592\u2013596. doi: 10.1109\/CCIS.2011.6045138 (2011)","key":"279_CR24","DOI":"10.1109\/CCIS.2011.6045138"},{"doi-asserted-by":"crossref","unstructured":"Rahman, A., Houzet, D., Pellerin, D., Marat, S., Guyader, N.: Parallel implementation of a spatio-temporal visual saliency model. J. Real Time Image Process. 6(1), 3\u201314. doi: 10.1007\/s11554-010-0164-7 (2010, d\u00e9partement Images et Signal)","key":"279_CR25","DOI":"10.1007\/s11554-010-0164-7"},{"doi-asserted-by":"crossref","unstructured":"Rahman, A., Houzet, D., Pellerin, D.: Visual saliency model on multi-GPU. In: GPU Computing Gems Emerald Edition, Elsevier, pp. 451\u2013472 (2011)","key":"279_CR26","DOI":"10.1016\/B978-0-12-384988-5.00030-9"},{"doi-asserted-by":"crossref","unstructured":"Sb\u00eerlea, A., Zou, Y., Budiml\u00edc, Z., Cong, J., Sarkar, V.: Mapping a data-flow programming model onto heterogeneous platforms. In: Proceedings of the 13th ACM SIGPLAN\/SIGBED International Conference on Languages, Compilers, Tools and Theory for Embedded Systems, ACM, New York, LCTES \u201912, pp. 61\u201370. doi: 10.1145\/2248418.2248428 (2012)","key":"279_CR27","DOI":"10.1145\/2248418.2248428"},{"key":"279_CR28","volume-title":"Image Analysis and Mathematical Morphology","author":"J. Serra","year":"1983","unstructured":"Serra, J.: Image Analysis and Mathematical Morphology. Academic Press, Orlando (1983)"},{"doi-asserted-by":"crossref","unstructured":"Stefanov, T., Zissulescu, C., Turjan, A., Kienhuis, B., Deprettere, E.: System design using kahn process networks: the compaan\/laura approach. In: Proceedings of the Conference on Design, Automation and Test in Europe, vol. 1, IEEE Computer Society, Washington, DC, DATE \u201904, p. 10,340. http:\/\/www.compaandesign.com\/ (2004)","key":"279_CR29","DOI":"10.1109\/DATE.2004.1268870"},{"doi-asserted-by":"crossref","unstructured":"Wolfe, M.: Implementing the pgi accelerator model. In: Kaeli, D.R., Leeser, M. (eds.) Proceedings of 3rd Workshop on General Purpose Processing on Graphics Processing Units, GPGPU 2010, Pittsburgh, March 14, ACM, ACM International Conference Proceeding Series, vol. 425, pp. 43\u201350. doi: 10.1145\/1735688.1735697 (2010)","key":"279_CR30","DOI":"10.1145\/1735688.1735697"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-012-0279-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11554-012-0279-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-012-0279-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T07:42:44Z","timestamp":1744270964000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11554-012-0279-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,10,10]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2014,3]]}},"alternative-id":["279"],"URL":"https:\/\/doi.org\/10.1007\/s11554-012-0279-0","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"type":"print","value":"1861-8200"},{"type":"electronic","value":"1861-8219"}],"subject":[],"published":{"date-parts":[[2012,10,10]]}}}