{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T12:10:35Z","timestamp":1725797435463},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783662444900"},{"type":"electronic","value":"9783662444917"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-662-44491-7_8","type":"book-chapter","created":{"date-parts":[[2014,7,20]],"date-time":"2014-07-20T21:13:00Z","timestamp":1405890780000},"page":"98-112","source":"Crossref","is-referenced-by-count":2,"title":["A Throughput-Aware Analytical Performance Model for GPU Applications"],"prefix":"10.1007","author":[{"given":"Zhidan","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenrui","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"5","key":"8_CR1","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1109\/MM.2011.89","volume":"31","author":"S.W. Keckler","year":"2011","unstructured":"Keckler, S.W., Dally, W.J., Khailany, B., et al.: GPUs and the future of parallel computing. IEEE Micro\u00a031(5), 7\u201317 (2011)","journal-title":"IEEE Micro"},{"key":"8_CR2","unstructured":"Advanced Micro Devices, Inc. AMD Brook+"},{"key":"8_CR3","unstructured":"NVIDIA Corporation. CUDA Programming Guide, Version 4.0"},{"issue":"3","key":"8_CR4","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/MCSE.2010.69","volume":"12","author":"J.E. Stone","year":"2010","unstructured":"Stone, J.E., Gohara, D., Shi, G.: OpenCL: A parallel programming standard for heterogeneous computing systems. Computing in Science & Engineering\u00a012(3), 66 (2010)","journal-title":"Computing in Science & Engineering"},{"issue":"5","key":"8_CR5","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1109\/JPROC.2008.917757","volume":"96","author":"J.D. Owens","year":"2008","unstructured":"Owens, J.D., Houston, M., Luebke, D., et al.: GPU computing. Proceedings of the IEEE\u00a096(5), 879\u2013899 (2008)","journal-title":"Proceedings of the IEEE"},{"issue":"2","key":"8_CR6","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1109\/MM.2008.31","volume":"28","author":"E. Lindholm","year":"2008","unstructured":"Lindholm, E., Nickolls, J., Oberman, S., et al.: NVIDIA Tesla: A unified graphics and computing architecture. IEEE Micro\u00a028(2), 39\u201355 (2008)","journal-title":"IEEE Micro"},{"issue":"4","key":"8_CR7","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. Communications of the ACM\u00a052(4), 65\u201376 (2009)","journal-title":"Communications of the ACM"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Owens, J.D.: A quantitative performance analysis model for GPU architectures. In: 2011 IEEE 17th International Symposium on High Performance Computer Architecture (HPCA), pp. 382\u2013393. IEEE (2011)","DOI":"10.1109\/HPCA.2011.5749745"},{"issue":"3","key":"8_CR9","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1145\/1555815.1555775","volume":"37","author":"S. Hong","year":"2009","unstructured":"Hong, S., Kim, H.: An analytical model for a GPU architecture with memory-level and thread-level parallelism awareness. ACM SIGARCH Computer Architecture News\u00a037(3), 152\u2013163 (2009)","journal-title":"ACM SIGARCH Computer Architecture News"},{"issue":"5","key":"8_CR10","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/1837853.1693470","volume":"45","author":"S.S. Baghsorkhi","year":"2010","unstructured":"Baghsorkhi, S.S., Delahaye, M., Patel, S.J., et al.: An adaptive performance modeling tool for GPU architectures. ACM Sigplan Notices\u00a045(5), 105\u2013114 (2010)","journal-title":"ACM Sigplan Notices"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Meng, J., Morozov, V.A., Kumaran, K., et al.: GROPHECY: GPU performance projection from CPU code skeletons. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, p. 14. ACM (2011)","DOI":"10.1145\/2063384.2063402"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Cui, Z., et al.: An accurate GPU performance model for effective control flow divergence optimization. In: 2012 IEEE 26th International Parallel & Distributed Processing Symposium (IPDPS). IEEE (2012)","DOI":"10.1109\/IPDPS.2012.18"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Che, S., Boyer, M., Meng, J., 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"}],"container-title":["Communications in Computer and Information Science","Advanced Computer Architecture"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-44491-7_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,27]],"date-time":"2019-05-27T07:29:44Z","timestamp":1558942184000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-662-44491-7_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783662444900","9783662444917"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-44491-7_8","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2014]]}}}