{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T04:24:02Z","timestamp":1751862242858},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319143248"},{"type":"electronic","value":"9783319143255"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"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":[[2014]]},"DOI":"10.1007\/978-3-319-14325-5_15","type":"book-chapter","created":{"date-parts":[[2014,12,10]],"date-time":"2014-12-10T08:55:04Z","timestamp":1418201704000},"page":"165-176","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["An Empirical Evaluation of GPGPU Performance Models"],"prefix":"10.1007","author":[{"given":"Souley","family":"Madougou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ana Lucia","family":"Varbanescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cees","family":"de Laat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rob","family":"van Nieuwpoort","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Saule, E., Kaya, K., \u00c7ataly\u00fcrek, \u00dc.V.: Performance evaluation of sparse matrix multiplication kernels on intel xeon phi. CoRR abs\/1302.1078 (2013)","DOI":"10.1007\/978-3-642-55224-3_52"},{"key":"15_CR2","unstructured":"NVIDIA Corporation: Press release: Nvidia tesla gpu computing processor ushers in the era of personal supercomputing (June 2007)"},{"key":"15_CR3","unstructured":"Advanced Micro Devices (AMD) Inc. Press release: Amd delivers enthusiast performance leadership with the introduction of the ati radeon 3870 x2 (January 2008)"},{"issue":"10","key":"15_CR4","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/1562764.1562783","volume":"52","author":"K. Asanovic","year":"2009","unstructured":"Asanovic, K., et al.: A view of the parallel computing landscape. Commun. ACM\u00a052(10), 56\u201367 (2009)","journal-title":"Commun. ACM"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Bakhoda, A., Yuan, G.L., Fung, W.W.L., Wong, H., Aamodt, T.M.: Analyzing cuda workloads using a detailed gpu simulator. In: ISPASS, pp. 163\u2013174. IEEE (2009)","DOI":"10.1109\/ISPASS.2009.4919648"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Mudalige, G.R., Vernon, M.K., Jarvis, S.A.: A plug-and-play model for evaluating wavefront computations on parallel architectures. In: IPDPS, pp. 1\u201314. IEEE (2008)","DOI":"10.1109\/IPDPS.2008.4536243"},{"key":"15_CR7","first-page":"197","volume-title":"Proceedings of HPDC 2008","author":"G.F. Diamos","year":"2008","unstructured":"Diamos, G.F., Yalamanchili, S.: Harmony: An execution model and runtime for heterogeneous many core systems. In: Proceedings of HPDC 2008, pp. 197\u2013200. ACM, New York (2008)"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Linderman, M.D., Collins, J.D., Wang, H., Meng, T.H.: Merge: A programming model for heterogeneous multi-core systems. SIGPLAN Not. 43(3) (March 2008)","DOI":"10.1145\/1353536.1346318"},{"key":"15_CR9","first-page":"1","volume-title":"Proceedings of SC 2002","author":"A. Snavely","year":"2002","unstructured":"Snavely, A., Carrington, L., Wolter, N., Labarta, J., Badia, R., Purkayastha, A.: A framework for performance modeling and prediction. In: Proceedings of SC 2002, pp. 1\u201317. IEEE Computer Society Press, Los Alamitos (2002)"},{"key":"15_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-642-03869-3_16","volume-title":"Euro-Par 2009 Parallel Processing","author":"M.M. Tikir","year":"2009","unstructured":"Tikir, M.M., Laurenzano, M.A., Carrington, L., Snavely, A.: PSINS: An open source event tracer and execution simulator for MPI applications. In: Sips, H., Epema, D., Lin, H.-X. (eds.) Euro-Par 2009. LNCS, vol.\u00a05704, pp. 135\u2013148. Springer, Heidelberg (2009)"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Laurenzano, M., Tikir, M., Carrington, L., Snavely, A.: Pebil: Efficient static binary instrumentation for linux. In: ISPASS 2010, pp. 175\u2013183 (March 2010)","DOI":"10.1109\/ISPASS.2010.5452024"},{"key":"15_CR12","first-page":"202","volume-title":"Proceedings of ICS 2011","author":"L. Carrington","year":"2011","unstructured":"Carrington, L., Tikir, M.M., Olschanowsky, C., Laurenzano, M., Peraza, J., Snavely, A., Poole, S.: An idiom-finding tool for increasing productivity of accelerators. In: Proceedings of ICS 2011, pp. 202\u2013212. ACM, New York (2011)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Kerr, A., Anger, E., Hendry, G., Yalamanchili, S.: Eiger: A framework for the automated synthesis of statistical performance models. In: Proceedings of WPEA 2012 (2012)","DOI":"10.1109\/HiPC.2012.6507525"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Kerr, A., Diamos, G., Yalamanchili, S.: A characterization and analysis of ptx kernels. In: Proceedings of IISWC 2009, Washington, DC, USA, pp. 3\u201312 (2009)","DOI":"10.1109\/IISWC.2009.5306801"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Jia, W., Shaw, K., Martonosi, M.: Stargazer: Automated regression-based gpu design space exploration. In: ISPASS 2012, pp. 2\u201313 (April 2012)","DOI":"10.1109\/ISPASS.2012.6189201"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Baghsorkhi, S.S., Delahaye, M., Patel, S.J., Gropp, W.D., Hwu, W.M.W.: An adaptive performance modeling tool for gpu architectures. SIGPLAN Not. 45(5), 105\u2013114 (2010)","DOI":"10.1145\/1837853.1693470"},{"key":"15_CR17","unstructured":"Hong, S., Kim, H.: An analytical model for a gpu architecture with memory-level and thread-level parallelism awareness. SIGARCH Comput. Archit. News 37(3), 152\u2013163 (2009)"},{"key":"15_CR18","doi-asserted-by":"crossref","unstructured":"Kothapalli, K., Mukherjee, R., Rehman, M., Patidar, S., Narayanan, P.J., Srinathan, K.: A performance prediction model for the cuda gpgpu platform. In: HiPC 2009, pp. 463\u2013472 (December 2009)","DOI":"10.1109\/HIPC.2009.5433179"},{"issue":"8","key":"15_CR19","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/79173.79181","volume":"33","author":"L.G. Valiant","year":"1990","unstructured":"Valiant, L.G.: A bridging model for parallel computation. Commun. ACM\u00a033(8), 103\u2013111 (1990)","journal-title":"Commun. ACM"},{"key":"15_CR20","first-page":"114","volume-title":"Proceedings of STOC 1978","author":"S. Fortune","year":"1978","unstructured":"Fortune, S., Wyllie, J.: Parallelism in random access machines. In: Proceedings of STOC 1978, pp. 114\u2013118. ACM, New York (1978)"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Gibbons, P.B., Matias, Y., Ramachandran, V.: The queue-read queue-write asynchronous pram model. In: Euro-Par 1996. LNCS, vol.\u00a01124, pp. 279\u2013292. Springer, Heidelberg (1996)","DOI":"10.1007\/BFb0024714"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Owens, J.: A quantitative performance analysis model for gpu architectures. In: HPCA 2011, pp. 382\u2013393 (February 2011)","DOI":"10.1109\/HPCA.2011.5749745"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2014: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-14325-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T00:30:09Z","timestamp":1587342609000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-14325-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319143248","9783319143255"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-14325-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}