{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T07:10:27Z","timestamp":1760080227009,"version":"3.40.3"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030024642"},{"type":"electronic","value":"9783030024659"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-02465-9_52","type":"book-chapter","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T20:06:48Z","timestamp":1548360408000},"page":"724-742","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["A Beginner\u2019s Guide to Estimating and Improving Performance Portability"],"prefix":"10.1007","author":[{"given":"Henk","family":"Dreuning","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roel","family":"Heirman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ana Lucia","family":"Varbanescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,25]]},"reference":[{"issue":"5","key":"52_CR1","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1109\/MC.2016.127","volume":"49","author":"H Bal","year":"2016","unstructured":"Bal, H., et al.: A medium-scale distributed system for computer science research: infrastructure for the long term. Computer 49(5), 54\u201363 (2016)","journal-title":"Computer"},{"key":"52_CR2","unstructured":"Bauer, S.: Accelerator Offloading mit GCC (in German) (2016). \n                      https:\/\/www.heise.de\/developer\/artikel\/Accelerator-Offloading-mit-GCC-3317330.html?seite=3\n                      \n                    . Accessed Apr 2018"},{"key":"52_CR3","doi-asserted-by":"crossref","unstructured":"Che, S., et al.: Rodinia: a benchmark suite for heterogeneous computing. In: IEEE International Symposium on Workload Characterization, IISWC 2009, pp. 44\u201354. IEEE (2009)","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"52_CR4","unstructured":"Fabeiro, J.F.: Tools for improving performance portability in heterogeneous environments. Ph.D. thesis, Department of Computer Engineering, University of A Coru\u00f1a, July 2017"},{"key":"52_CR5","doi-asserted-by":"crossref","unstructured":"Fang, J., Varbanescu, A.L., Sips, H.: A comprehensive performance comparison of CUDA and OpenCL. In: 2011 International Conference on Parallel Processing (ICPP), pp. 216\u2013225. IEEE (2011)","DOI":"10.1109\/ICPP.2011.45"},{"key":"52_CR6","unstructured":"Intel. Intel Math Kernel Library. \n                      https:\/\/software.intel.com\/en-us\/mkl\n                      \n                    . Accessed Apr 2018"},{"issue":"15","key":"52_CR7","doi-asserted-by":"publisher","first-page":"e4117","DOI":"10.1002\/cpe.4117","volume":"29","author":"M Martineau","year":"2017","unstructured":"Martineau, M., McIntosh-Smith, S., Gaudin, W.: Assessing the performance portability of modern parallel programming models using TeaLeaf. Concurrency Comput.: Pract. Exp. 29(15), e4117 (2017)","journal-title":"Concurrency Comput.: Pract. Exp."},{"key":"52_CR8","unstructured":"McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. In: IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter, pp. 19\u201325, December 1995"},{"key":"52_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1007\/978-3-319-07518-1_4","volume-title":"Supercomputing","author":"S McIntosh-Smith","year":"2014","unstructured":"McIntosh-Smith, S., Boulton, M., Curran, D., Price, J.: On the performance portability of structured grid codes on many-core computer architectures. In: Kunkel, J.M., Ludwig, T., Meuer, H.W. (eds.) ISC 2014. LNCS, vol. 8488, pp. 53\u201375. Springer, Cham (2014). \n                      https:\/\/doi.org\/10.1007\/978-3-319-07518-1_4"},{"key":"52_CR10","unstructured":"NVIDIA. cuBLAS. \n                      https:\/\/developer.nvidia.com\/cublas\n                      \n                    . Accessed Apr 2018"},{"key":"52_CR11","unstructured":"NVIDIA. CUDA C Programming Guide (2018). \n                      https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/index.html\n                      \n                    . Accessed Apr 2018"},{"issue":"11","key":"52_CR12","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.1016\/j.jpdc.2012.07.005","volume":"73","author":"SJ Pennycook","year":"2013","unstructured":"Pennycook, S.J., Hammond, S.D., Wright, S.A., Herdman, J.A., Miller, I., Jarvis, S.A.: An investigation of the performance portability of OpenCL. J. Parallel Distrib. Comput. 73(11), 1439\u20131450 (2013)","journal-title":"J. Parallel Distrib. Comput."},{"key":"52_CR13","unstructured":"Pennycook, S.J., Sewall, J.D., Lee, V.W.: A Metric for Performance Portability. arXiv preprint \n                      arXiv:1611.07409\n                      \n                     (2016)"},{"key":"52_CR14","unstructured":"Pennycook, S.J., Sewall, J.D., Lee, V.W.: A metric for performance portability. CoRR, abs\/1611.07409 (2016)"},{"key":"52_CR15","unstructured":"Pennycook, S.J., Sewall, J.D., Lee, V.W.: Implications of a metric for performance portability. Future Gener. Comput. Syst. (2017)"},{"key":"52_CR16","unstructured":"Rul, S., Vandierendonck, H., D\u2019Haene, J., De Bosschere, K.: An experimental study on performance portability of OpenCL kernels. In: 2010 Symposium on Application Accelerators in High Performance Computing (SAAHPC 2010) (2010)"},{"key":"52_CR17","doi-asserted-by":"crossref","unstructured":"Shen, J., Fang, J., Sips, H., Varbanescu, A.L.: Performance gaps between OpenMP and OpenCL for multi-core CPUs. In: Proceedings of the 2012 41st International Conference on Parallel Processing Workshops, ICPPW 2012, Washington, DC, USA, pp. 116\u2013125. IEEE Computer Society (2012)","DOI":"10.1109\/ICPPW.2012.18"},{"key":"52_CR18","unstructured":"Stratton, J.A., Kim, H., Jablin, T.B., Hwu, W.W.: Performance portability in accelerated parallel kernels. Center for Reliable and High-Performance Computing (2013)"},{"key":"52_CR19","unstructured":"UK-MAC. TeaLeaf (2017). \n                      http:\/\/uk-mac.github.io\/TeaLeaf\/"},{"key":"52_CR20","unstructured":"van der Sanden, J.: Evaluating the performance portability of OpenCL. Master\u2019s thesis, Eindhoven University of Technology, The Netherlands (2011)"},{"issue":"4","key":"52_CR21","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1145\/1498765.1498785","volume":"52","author":"S Williams","year":"2009","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: an insightful visual performance model for multicore architectures. Commun. ACM 52(4), 65\u201376 (2009)","journal-title":"Commun. ACM"},{"key":"52_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1007\/978-3-642-38750-0_11","volume-title":"Supercomputing","author":"Y Zhang","year":"2013","unstructured":"Zhang, Y., Sinclair, M., Chien, A.A.: Improving performance portability in OpenCL programs. In: Kunkel, J.M., Ludwig, T., Meuer, H.W. (eds.) ISC 2013. LNCS, vol. 7905, pp. 136\u2013150. Springer, Heidelberg (2013). \n                      https:\/\/doi.org\/10.1007\/978-3-642-38750-0_11"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-02465-9_52","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T05:04:48Z","timestamp":1558328688000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-02465-9_52"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030024642","9783030024659"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-02465-9_52","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"25 January 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Frankfurt","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 June 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 June 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}