{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T05:42:26Z","timestamp":1725601346047},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642233968"},{"type":"electronic","value":"9783642233975"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[[2011]]},"DOI":"10.1007\/978-3-642-23397-5_43","type":"book-chapter","created":{"date-parts":[[2011,8,18]],"date-time":"2011-08-18T07:40:06Z","timestamp":1313653206000},"page":"438-452","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Automatic OpenCL Device Characterization: Guiding Optimized Kernel Design"],"prefix":"10.1007","author":[{"given":"Peter","family":"Thoman","sequence":"first","affiliation":[]},{"given":"Klaus","family":"Kofler","sequence":"additional","affiliation":[]},{"given":"Heiko","family":"Studt","sequence":"additional","affiliation":[]},{"given":"John","family":"Thomson","sequence":"additional","affiliation":[]},{"given":"Thomas","family":"Fahringer","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"43_CR1","unstructured":"Buck, I., Fatahalian, K., Hanrahan, P.: GPUBench (2004)"},{"key":"43_CR2","unstructured":"Bull, J.M.: Measuring synchronisation and scheduling overheads in openmp. In: Proc. of 1st Europ. Workshop on OpenMP, pp. 99\u2013105 (1999)"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Che, S., Boyer, M., Meng, J., Tarjan, D., Sheaffer, J.W., Lee, S., Skadron, K.: Rodinia: A benchmark suite for heterogeneous computing. In: IEEE Workload Characterization Symposium, pp. 44\u201354 (2009)","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"43_CR4","first-page":"63","volume-title":"GPGPU 2010: Proc.","author":"A. Danalis","year":"2010","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: GPGPU 2010: Proc., pp. 63\u201374. ACM, New York (2010)"},{"key":"43_CR5","first-page":"140","volume-title":"Proceedings of the 10th Annual International Symposium on Computer Architecture","author":"J.A. Fisher","year":"1983","unstructured":"Fisher, J.A.: Very long instruction word architectures and the ELI-512. In: Proceedings of the 10th Annual International Symposium on Computer Architecture, pp. 140\u2013150. ACM, New York (1983)"},{"key":"43_CR6","first-page":"407","volume-title":"MICRO 40","author":"W.L. Fung","year":"2007","unstructured":"Fung, W.L., Sham, I., Yuan, G., Aamodt, T.M.: Dynamic warp formation and scheduling for efficient gpu control flow. In: MICRO 40, pp. 407\u2013420. IEEE Computer Society, Washington, DC, USA (2007)"},{"key":"43_CR7","unstructured":"MPI Intel. Benchmarks: Users Guide and Methodology Description. Intel GmbH, Germany (2004)"},{"key":"43_CR8","unstructured":"McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. IEEE Comp. Soc. Tech. Comm. on Computer Architecture (TCCA) Newsletter, pp. 19\u201325 (December 1995)"},{"issue":"7","key":"43_CR9","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1145\/1095408.1095418","volume":"3","author":"K. Olukotun","year":"2005","unstructured":"Olukotun, K., Hammond, L.: The future of microprocessors. Queue\u00a03(7), 26\u201329 (2005)","journal-title":"Queue"},{"issue":"3","key":"43_CR10","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1145\/1294313.1294315","volume":"35","author":"F.N. Sibai","year":"2007","unstructured":"Sibai, F.N.: Performance analysis and workload characterization of the 3dmark05 benchmark on modern parallel computer platforms. ACM SIGARCH Computer Architecture News\u00a035(3), 44\u201352 (2007)","journal-title":"ACM SIGARCH Computer Architecture News"},{"issue":"6","key":"43_CR11","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1109\/12.286299","volume":"43","author":"J. Torrellas","year":"1994","unstructured":"Torrellas, J., Lam, M.S., Hennessy, J.L.: False sharing and spatial locality in multiprocessor caches. IEEE Transactions on Computers\u00a043(6), 651\u2013663 (1994)","journal-title":"IEEE Transactions on Computers"},{"key":"43_CR12","volume-title":"Multigrid","author":"U. Trottenberg","year":"2001","unstructured":"Trottenberg, U., Oosterlee, C.W., Schueller, A.: Multigrid. Academic Press, London (2001)"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Volkov, V., Demmel, J.W.: Benchmarking gpus to tune dense linear algebra. In: SC 2008, pp. 1\u201311. IEEE Press, Piscataway (2008)","DOI":"10.1109\/SC.2008.5214359"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"Wong, H., Papadopoulou, M., Sadooghi-Alvandi, M., Moshovos, A.: Demystifying gpu microarchitecture through microbenchmarking. In: ISPASS, pp. 235\u2013246 (2010)","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"43_CR15","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1145\/1806596.1806606","volume-title":"Proceedings of the 2010 ACM SIGPLAN conference on Programming language design and implementation, PLDI 2010","author":"Y. Yang","year":"2010","unstructured":"Yang, Y., Xiang, P., Kong, J., Zhou, H.: A gpgpu compiler for memory optimization and parallelism management. In: Proceedings of the 2010 ACM SIGPLAN conference on Programming language design and implementation, PLDI 2010, pp. 86\u201397. ACM, New York (2010)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2011 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-23397-5_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:57:29Z","timestamp":1638320249000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-23397-5_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642233968","9783642233975"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-23397-5_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}