{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T11:14:08Z","timestamp":1725966848135},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2011,3,24]],"date-time":"2011-03-24T00:00:00Z","timestamp":1300924800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2012,6]]},"DOI":"10.1007\/s10586-010-0151-6","type":"journal-article","created":{"date-parts":[[2011,3,23]],"date-time":"2011-03-23T19:29:41Z","timestamp":1300908581000},"page":"125-144","source":"Crossref","is-referenced-by-count":17,"title":["Optimizing dataflow applications on heterogeneous environments"],"prefix":"10.1007","volume":"15","author":[{"given":"George","family":"Teodoro","sequence":"first","affiliation":[]},{"given":"Timothy D. R.","family":"Hartley","sequence":"additional","affiliation":[]},{"given":"Umit V.","family":"Catalyurek","sequence":"additional","affiliation":[]},{"given":"Renato","family":"Ferreira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,3,24]]},"reference":[{"key":"151_CR1","volume-title":"IOPADS \u201999: Input\/Output for Parallel and Distributed Systems","author":"R.H. Arpaci-Dusseau","year":"1999","unstructured":"Arpaci-Dusseau, R.H., Anderson, E., Treuhaft, N., Culler, D.E., Hellerstein, J.M., Patterson, D., Yelick, K.: Cluster I\/O with river: making the fast case common. In: IOPADS \u201999: Input\/Output for Parallel and Distributed Systems (1999)"},{"key":"151_CR2","first-page":"863","volume-title":"Euro-Par \u201909: Proceedings of the 15th International Euro-Par Conference on Parallel Processing","author":"C. Augonnet","year":"2009","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.A.: Starpu: A\u00a0unified platform for task scheduling on heterogeneous multicore architectures. In: Euro-Par \u201909: Proceedings of the 15th International Euro-Par Conference on Parallel Processing, pp. 863\u2013874 (2009)"},{"key":"151_CR3","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/369028.369109","volume-title":"Supercomputing \u201996: Proceedings of the 1996 ACM\/IEEE Conference on Supercomputing","author":"F.D. Berman","year":"1996","unstructured":"Berman, F.D., Wolski, R., Figueira, S., Schopf, J., Shao, G.: Application-level scheduling on distributed heterogeneous networks. In: Supercomputing \u201996: Proceedings of the 1996 ACM\/IEEE Conference on Supercomputing, p. 39 (1996)"},{"key":"151_CR4","first-page":"119","volume-title":"IEEE Symposium on Mass Storage Systems","author":"M. Beynon","year":"2000","unstructured":"Beynon, M., Ferreira, R., Kurc, T.M., Sussman, A., Saltz, J.H.: DataCutter: middleware for filtering very large scientific datasets on archival storage systems. In: IEEE Symposium on Mass Storage Systems, pp. 119\u2013134 (2000)"},{"issue":"11","key":"151_CR5","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1016\/S0167-8191(01)00099-0","volume":"27","author":"M.D. Beynon","year":"2001","unstructured":"Beynon, M.D., Kurc, T., Catalyurek, U., Chang, C., Sussman, A., Saltz, J.: Distributed processing of very large datasets with DataCutter. Parallel Comput. 27(11), 1457\u20131478 (2001)","journal-title":"Parallel Comput."},{"issue":"4","key":"151_CR6","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1145\/292523.292524","volume":"16","author":"N.T. Bhatti","year":"1998","unstructured":"Bhatti, N.T., Hiltunen, M.A., Schlichting, R.D., Chiu, W.: Coyote: a system for constructing fine-grain configurable communication services. ACM Trans. Comput. Syst. 16(4), 321\u2013366 (1998)","journal-title":"ACM Trans. Comput. Syst."},{"issue":"3","key":"151_CR7","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1145\/1015706.1015800","volume":"23","author":"I. Buck","year":"2004","unstructured":"Buck, I., Foley, T., Horn, D., Sugerman, J., Fatahalian, K., Houston, M., Hanrahan, P.: Brook for gpus: stream computing on graphics hardware. ACM Trans. Graph. 23(3), 777\u2013786 (2004)","journal-title":"ACM Trans. Graph."},{"issue":"4","key":"151_CR8","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1109\/TITB.2004.823952","volume":"7","author":"U. Catalyurek","year":"2003","unstructured":"Catalyurek, U., Beynon, M.D., Chang, C., Kurc, T., Sussman, A., Saltz, J.: The virtual microscope. IEEE Trans. Inf. Technol. Biomed. 7(4), 230\u2013248 (2003)","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"151_CR9","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1145\/165939.165971","volume-title":"ICS \u201993: Proceedings of the 7th International Conference on Supercomputing","author":"T. Fahringer","year":"1993","unstructured":"Fahringer, T., Zima, H.P.: A static parameter based performance prediction tool for parallel programs. In: ICS \u201993: Proceedings of the 7th International Conference on Supercomputing, pp. 207\u2013219 (1993)"},{"key":"151_CR10","doi-asserted-by":"crossref","unstructured":"Fix, E., Hodges, J.: Discriminatory analysis, nonparametric discrimination, consistency properties. Computer science technical report, School of Aviation Medicine, Randolph Field, Texas (1951)","DOI":"10.1037\/e471672008-001"},{"key":"151_CR11","volume-title":"22nd ACM Intl. Conference on Supercomputing","author":"T.D. Hartley","year":"2008","unstructured":"Hartley, T.D., Catalyurek, U.V., Ruiz, A., Ujaldon, M., Igual, F., Mayo, R.: Biomedical image analysis on a cooperative cluster of gpus and multicores. In: 22nd ACM Intl. Conference on Supercomputing (2008)"},{"key":"151_CR12","volume-title":"Parallel Architectures and Compilation Techniques","author":"B. He","year":"2008","unstructured":"He, B., Fang, W., Luo, Q., Govindaraju, N.K., Wang, T.: Mars: A mapreduce framework on graphics processors. In: Parallel Architectures and Compilation Techniques (2008)"},{"key":"151_CR13","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1145\/258734.258843","volume-title":"SIGGRAPH 97 Proc.","author":"H. Hoppe","year":"1997","unstructured":"Hoppe, H.: View-dependent refinement of progressive meshes. In: SIGGRAPH 97 Proc., pp. 189\u2013198 (1997). http:\/\/research.microsoft.com\/hoppe\/"},{"key":"151_CR14","doi-asserted-by":"crossref","unstructured":"Hsu, C.H., Chen, T.L., Li, K.C.: Performance effective pre-scheduling strategy for heterogeneous grid systems in the master slave paradigm. Future Gener. Comput. Syst. (2007)","DOI":"10.1016\/j.future.2006.09.007"},{"key":"151_CR15","volume-title":"4th Heterogeneous Computing Workshop (HCW\u201995)","author":"M. Iverson","year":"1995","unstructured":"Iverson, M., Ozguner, F., Follen, G.: Parallelizing existing applications in a distributed heterogeneous environment. In: 4th Heterogeneous Computing Workshop (HCW\u201995) (1995)"},{"key":"151_CR16","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1145\/582034.582071","volume-title":"Supercomputing \u201901: Proceedings of the 2001 ACM\/IEEE Conference on Supercomputing (CDROM)","author":"D.J. Kerbyson","year":"2001","unstructured":"Kerbyson, D.J., Alme, H.J., Hoisie, A., Petrini, F., Wasserman, H.J., Gittings, M.: Predictive performance and scalability modeling of a large-scale application. In: Supercomputing \u201901: Proceedings of the 2001 ACM\/IEEE Conference on Supercomputing (CDROM), pp. 37\u201337 (2001)"},{"key":"151_CR17","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1145\/1048935.1050160","volume-title":"SC \u201903: Proceedings of the 2003 ACM\/IEEE Conference on Supercomputing","author":"T. Kurc","year":"2003","unstructured":"Kurc, T., Lee, F., Agrawal, G., Catalyurek, U., Ferreira, R., Saltz, J.: Optimizing reduction computations in a distributed environment. In: SC \u201903: Proceedings of the 2003 ACM\/IEEE Conference on Supercomputing, p. 9 (2003)"},{"key":"151_CR18","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1145\/1504176.1504194","volume-title":"PPoPP \u201909: Proceedings of the 14th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","author":"S. Lee","year":"2009","unstructured":"Lee, S., Min, S.J., Eigenmann, R.: OpenMP to GPGPU: a compiler framework for automatic translation and optimization. In: PPoPP \u201909: Proceedings of the 14th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 101\u2013110 (2009)"},{"issue":"3","key":"151_CR19","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1145\/1353536.1346318","volume":"43","author":"M.D. Linderman","year":"2008","unstructured":"Linderman, M.D., Collins, J.D., Wang, H., Meng, T.H.: Merge: a programming model for heterogeneous multi-core systems. ACM SIGPLAN Not. 43(3), 287\u2013296 (2008)","journal-title":"ACM SIGPLAN Not."},{"key":"151_CR20","volume-title":"Proceedings of ACM Sigmetrics","author":"S. Low","year":"2001","unstructured":"Low, S., Peterson, L., Wang, L.: Understanding tcp vegas: a duality model. In: Proceedings of ACM Sigmetrics (2001)"},{"key":"151_CR21","volume-title":"42nd International Symposium on Microarchitecture (MICRO)","author":"C.K. Luk","year":"2009","unstructured":"Luk, C.K., Hong, S., Kim, H.: Qilin: Exploiting parallelism on heterogeneous multiprocessors with adaptive mapping. In: 42nd International Symposium on Microarchitecture (MICRO) (2009)"},{"issue":"4","key":"151_CR22","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/S1361-8415(99)80030-9","volume":"3","author":"F. Maes","year":"1999","unstructured":"Maes, F., Vandermeulen, D., Suetens, P.: Comparative evaluation of multiresolution optimization strategies for multimodality image registration by maximization of mutual information. Med. Image Anal. 3(4), 373\u2013386 (1999)","journal-title":"Med. Image Anal."},{"key":"151_CR23","unstructured":"NVIDIA: NVIDIA CUDA SDK (2007). http:\/\/nvidia.com\/cuda"},{"key":"151_CR24","doi-asserted-by":"crossref","unstructured":"O\u2019Malley, S.W., Peterson, L.L.: A dynamic network architecture. ACM Trans. Comput. Syst. 10(2) (1992)","DOI":"10.1145\/128899.128901"},{"key":"151_CR25","first-page":"259","volume-title":"IEEE International Computer Conference","author":"N. Patkar","year":"1995","unstructured":"Patkar, N., Katsuno, A., Li, S., Maruyama, T., Savkar, S., Simone, M., Shen, G., Swami, R., Tovey, D.: Microarchitecture of hal\u2019s cpu. In: IEEE International Computer Conference, p. 259 (1995)"},{"key":"151_CR26","volume-title":"Workshop on Automatic Tuning for Petascale Systems","author":"J. Ramanujam","year":"2008","unstructured":"Ramanujam, J.: Toward automatic parallelization and auto-tuning of affine kernels for gpus. In: Workshop on Automatic Tuning for Petascale Systems (2008)"},{"key":"151_CR27","doi-asserted-by":"crossref","unstructured":"Rocha, B.M., Campos, F.O., Plank, G., dos Santos, R.W., Liebmann4, M., Haase, G.: Simulations of the electrical activity in the heart with graphic processing units. Accepted for publication in Eighth International Conference on Parallel Processing and Applied Mathematics (2009)","DOI":"10.1007\/978-3-642-14390-8_46"},{"key":"151_CR28","volume-title":"Multiresolution Image Processing and Analysis","year":"1984","unstructured":"Rosenfeld, A. (ed.): Multiresolution Image Processing and Analysis. Springer, Berlin (1984)"},{"key":"151_CR29","volume-title":"Proc. of IEEE Int. Conf. on Bioinformatics and Biomedicine","author":"A. Ruiz","year":"2007","unstructured":"Ruiz, A., Sertel, O., Ujaldon, M., Catalyurek, U., Saltz, J., Gurcan, M.: Pathological image analysis using the gpu: Stroma classification for neuroblastoma. In: Proc. of IEEE Int. Conf. on Bioinformatics and Biomedicine (2007)"},{"key":"151_CR30","volume-title":"International Parallel and Distributed Processing Symposium (IPDPS)","author":"J.C. Sancho","year":"2008","unstructured":"Sancho, J.C., Kerbyson, D.J.: Analysis of double buffering on two different multicore architectures: quad-core opteron and the Cell-BE. In: International Parallel and Distributed Processing Symposium (IPDPS) (2008)"},{"key":"151_CR31","doi-asserted-by":"crossref","unstructured":"Sertel, O., Kong, J., Shimada, H., Catalyurek, U.V., Saltz, J.H., Gurcan, M.N.: Computer-aided prognosis of neuroblastoma on whole-slide images: classification of stromal development. Pattern Recognit. 42(6) (2009)","DOI":"10.1016\/j.patcog.2008.08.027"},{"key":"151_CR32","doi-asserted-by":"crossref","unstructured":"Shimada, H., Ambros, I.M., Dehner, L.P., Ichi Hata, J., Joshi, V.V., Roald, B.: Terminology and morphologic criteria of neuroblastic tumors: recommendation by the international neuroblastoma pathology committee. Cancer 86(2) (1999)","DOI":"10.1002\/(SICI)1097-0142(19990715)86:2<349::AID-CNCR20>3.0.CO;2-Y"},{"key":"151_CR33","volume-title":"SC \u201909: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","author":"F. Song","year":"2009","unstructured":"Song, F., YarKhan, A., Dongarra, J.: Dynamic task scheduling for linear algebra algorithms on distributed-memory multicore systems. In: SC \u201909: Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis (2009)"},{"key":"151_CR34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IPDPS.2009.5161039","volume-title":"IPDPS \u201909: Proceedings of the 2009 IEEE International Symposium on Parallel and Distributed Processing","author":"N. Sundaram","year":"2009","unstructured":"Sundaram, N., Raghunathan, A., Chakradhar, S.T.: A framework for efficient and scalable execution of domain-specific templates on gpus. In: IPDPS \u201909: Proceedings of the 2009 IEEE International Symposium on Parallel and Distributed Processing, pp.\u00a01\u201312. (2009)"},{"key":"151_CR35","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1109\/CCGRID.2007.20","volume-title":"IEEE International Symposium on Cluster Computing and the Grid","author":"T. Tavares","year":"2007","unstructured":"Tavares, T., Teodoro, G., Kurc, T., Ferreira, R., Guedes, D., Meira, W.J., Catalyurek, U., Hastings, S., Oster, S., Langella, S., Saltz, J.: An efficient and reliable scientific workflow system. In: IEEE International Symposium on Cluster Computing and the Grid, pp.\u00a0445\u2013452 (2007)"},{"key":"151_CR36","volume-title":"The 37th International Conference on Parallel Processing (ICPP)","author":"G. Teodoro","year":"2008","unstructured":"Teodoro, G., Fireman, D., Guedes, D. Jr., Ferreira, R.: Achieving multi-level parallelism in filter-labeled stream programming model. In: The 37th International Conference on Parallel Processing (ICPP) (2008)"},{"key":"151_CR37","volume-title":"Proc. of the 19th ACM International Symposium on High Performance Distributed Computing (HPDC)","author":"G. Teodoro","year":"2010","unstructured":"Teodoro, G., Hartley, T.D.R., Catalyurek, U., Ferreira, R.: Run-time optimizations for replicated dataflows on heterogeneous environments. In: Proc. of the 19th ACM International Symposium on High Performance Distributed Computing (HPDC) (2010)"},{"key":"151_CR38","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/SBAC-PAD.2009.14","volume-title":"21st International Symposium on Computer Architecture and High Performance Computing","author":"G. Teodoro","year":"2009","unstructured":"Teodoro, G., Sachetto, R., Fireman, D., Guedes, D., Ferreira, R.: Exploiting computational resources in distributed heterogeneous platforms. In: 21st International Symposium on Computer Architecture and High Performance Computing, pp. 83\u201390 (2009)"},{"key":"151_CR39","volume-title":"IEEE Cluster","author":"G. Teodoro","year":"2009","unstructured":"Teodoro, G., Sachetto, R., Sertel, O., Gurcan, M. Jr., Catalyurek, U., Ferreira, R.: Coordinating the use of GPU and CPU for improving performance of compute intensive applications. In: IEEE Cluster (2009)"},{"key":"151_CR40","volume-title":"International Symposium on Computer Architecture and High Performance Computing","author":"G. Teodoro","year":"2006","unstructured":"Teodoro, G., Tavares, T., Ferreira, R., Kurc, T., Meira, W., Guedes, D., Pan, T., Saltz, J.: Run-time support for efficient execution of scientific workflows on distributed environmments. In: International Symposium on Computer Architecture and High Performance Computing, Ouro Preto, Brazil (2006)"},{"key":"151_CR41","doi-asserted-by":"crossref","unstructured":"Vrsalovic, D.F., Siewiorek, D.P., Segall, Z.Z., Gehringer, E.F.: Performance prediction and calibration for a class of multiprocessors. IEEE Trans. Comput. 37(11) (1988)","DOI":"10.1109\/12.8701"},{"issue":"5","key":"151_CR42","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1145\/502059.502057","volume":"35","author":"M. Welsh","year":"2001","unstructured":"Welsh, M., Culler, D., Brewer, E.: Seda: an architecture for well-conditioned, scalable internet services. SIGOPS Oper. Syst. Rev. 35(5), 230\u2013243 (2001)","journal-title":"SIGOPS Oper. Syst. Rev."},{"key":"151_CR43","volume-title":"SC \u201904: Proceedings of the 204 ACM\/IEEE Conference on Supercomputing","author":"B. Woods","year":"2004","unstructured":"Woods, B., Clymer, B., Saltz, J., Kurc, T.: A parallel implementation of 4-dimensional haralick texture analysis for disk-resident image datasets. In: SC \u201904: Proceedings of the 204 ACM\/IEEE Conference on Supercomputing (2004)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-010-0151-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-010-0151-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-010-0151-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T11:04:36Z","timestamp":1712315076000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-010-0151-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,3,24]]},"references-count":43,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2012,6]]}},"alternative-id":["151"],"URL":"https:\/\/doi.org\/10.1007\/s10586-010-0151-6","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,3,24]]}}}