{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T09:23:48Z","timestamp":1725701028837},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642328190"},{"type":"electronic","value":"9783642328206"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"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":[[2012]]},"DOI":"10.1007\/978-3-642-32820-6_90","type":"book-chapter","created":{"date-parts":[[2012,8,23]],"date-time":"2012-08-23T12:26:25Z","timestamp":1345724785000},"page":"920-932","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["GPURoofline: A Model for Guiding Performance Optimizations on GPUs"],"prefix":"10.1007","author":[{"given":"Haipeng","family":"Jia","sequence":"first","affiliation":[]},{"given":"Yunquan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Guoping","family":"Long","sequence":"additional","affiliation":[]},{"given":"Jianliang","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Shengen","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"90_CR1","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Owens, J.D.: A quantitative performance analysis model for GPU architectures. In: High Performance Computer Architecture, pp. 382\u2013393 (February 2011)","DOI":"10.1109\/HPCA.2011.5749745"},{"key":"90_CR2","doi-asserted-by":"crossref","unstructured":"Baghsorkhi, S., Delahaye, M., Patel, S.J., Gropp, W.D., Hwu, W.-M.W.: An Adaptive Performance Modeling Tool for GPU Architectures. In: Principles and Practice of Parallel Programming, pp. 105\u2013114 (January 2010)","DOI":"10.1145\/1837853.1693470"},{"key":"90_CR3","unstructured":"Daga, M., Scogland, T.R.W., Feng, W-C.: Architecture-Aware Optimization on a 1600-core Graphics Processor. Technical Report TR-11-08, Computer Science, Virginia Tech."},{"key":"90_CR4","doi-asserted-by":"crossref","unstructured":"Kothapalli, K., Mukherjee, R., Rehman, M.S., Patidar, S., Narayanan, P.J., Srinathan, K.: A performance prediction model for the CUDA GPGPU platform. In: International Conference on High Performance Computing, pp. 463\u2013472 (2009)","DOI":"10.1109\/HIPC.2009.5433179"},{"key":"90_CR5","doi-asserted-by":"crossref","unstructured":"Ryoo, S., Rodrigues, C.I., Stone, S.S., Baghsorkhi, S.S., Ueng, S., Stratton, J.A.: Program Optimization Space Pruning for a Multithreaded GPU. In: International Symposium on Code Generation and Optimization, pp. 195\u2013204 (April 2008)","DOI":"10.1145\/1356058.1356084"},{"key":"90_CR6","doi-asserted-by":"crossref","unstructured":"Hong, S., Kim, H.: An analytical model for a gpu architecture with memory-level and thread-level parallelism awareness. In: International Conference on Computer Architecture, pp. 152\u2013163 (2009)","DOI":"10.1145\/1555815.1555775"},{"key":"90_CR7","doi-asserted-by":"crossref","unstructured":"Jang, B., Do, S., Pien, H.: Architecture-Aware Optimization Targeting Multithreaded Stream Computing. In: Second Workshop on General-Purpose on Graphics Processing Units (2009)","DOI":"10.1145\/1513895.1513903"},{"key":"90_CR8","doi-asserted-by":"crossref","unstructured":"Meng, J., Morozov, V.A., Kumaran, K., Vishwanath, V., Uram, T.D.: GROPHECY: GPU Performance Projection from CPU Code Skeletons. In: Conference on High Performance Computing (2011)","DOI":"10.1145\/2063384.2063402"},{"key":"90_CR9","doi-asserted-by":"crossref","unstructured":"Bauer, M., Cook, H., Khailany, B.: CudaDMA: optimizing GPU memory bandwidth via warp specialization. In: Conference on High Performance Computing(Supercomputing) (2011)","DOI":"10.1145\/2063384.2063400"},{"key":"90_CR10","doi-asserted-by":"crossref","unstructured":"Govindaraju, N.K., Larsen, S., Gray, J., Manocha, D.: A Memory Model for Scientific Algorithms on Graphics Processors. In: ACM\/IEEE Conference on Supercomputing (November 2006)","DOI":"10.1109\/SC.2006.2"},{"key":"90_CR11","doi-asserted-by":"crossref","unstructured":"Williams, S., Waterman, A., Patterson, D.: Roofline: An Insightful Visual Performance Model for Multicore Architectures. Communications of the ACM, 65\u201376 (2009)","DOI":"10.1145\/1498765.1498785"},{"key":"90_CR12","volume-title":"Quantitative System Performance: Computer System Analysis using Queueing Network Models","author":"E.D. Lazowska","year":"1984","unstructured":"Lazowska, E.D., Zahorjan, J., Scott Graham, G., Sevcik, K.C.: Quantitative System Performance: Computer System Analysis using Queueing Network Models. Prentice-Hall. Inc., Upper Saddle River (1984)"},{"key":"90_CR13","doi-asserted-by":"crossref","unstructured":"Fatahalian, K., Sugerman, J., Hanrahan, P.: Understanding the Efficiency of GPU Algorithms for Matrix-matrix Multiplication. In: Conference on Graphics Hardware, pp. 133\u2013137 (August 2004)","DOI":"10.1145\/1058129.1058148"},{"key":"90_CR14","doi-asserted-by":"crossref","unstructured":"Taylor, R., Li, X.: A Micro-benchmark Suite for AMD GPUs. In: International Conference on Parallel Processing Workshops, pp. 387\u2013396 (2010)","DOI":"10.1109\/ICPPW.2010.59"},{"key":"90_CR15","doi-asserted-by":"crossref","unstructured":"Liu, W., Muller-Wittig, W., Schmidt, B.: Performance Predictions for General-Purpose Computation on GPUs. In: International Conference on Parallel Processing, pp. 50\u201357 (September 2007)","DOI":"10.1109\/ICPP.2007.67"},{"key":"90_CR16","unstructured":"Viola, P., Jones, M.: Robust Real-time object Detection. In: Second International Workshop on Statistical and Computation, pp (July 2011)"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2012 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-32820-6_90","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,20]],"date-time":"2020-04-20T00:57:33Z","timestamp":1587344253000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-32820-6_90"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642328190","9783642328206"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-32820-6_90","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}