{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T10:19:49Z","timestamp":1758709189361,"version":"3.37.3"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T00:00:00Z","timestamp":1574640000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T00:00:00Z","timestamp":1574640000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2020,6]]},"DOI":"10.1007\/s10586-019-03011-2","type":"journal-article","created":{"date-parts":[[2019,11,25]],"date-time":"2019-11-25T18:02:37Z","timestamp":1574704957000},"page":"1505-1516","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Comprehensive regression-based model to predict performance of general-purpose graphics processing unit"],"prefix":"10.1007","volume":"23","author":[{"given":"Mohammad Hossein","family":"Shafiabadi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2331-0568","authenticated-orcid":false,"given":"Hossein","family":"Pedram","sequence":"additional","affiliation":[]},{"given":"Midia","family":"Reshadi","sequence":"additional","affiliation":[]},{"given":"Akram","family":"Reza","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,25]]},"reference":[{"key":"3011_CR1","doi-asserted-by":"crossref","unstructured":"Puttaswamy, K., et al.: System level power-performance trade-offs in embedded systems using voltage and frequency scaling of off-chip buses and memory. In: Proceedings of the 15th International Symposium On System Synthesis. ACM (2002)","DOI":"10.1145\/581199.581249"},{"issue":"6","key":"3011_CR2","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1109\/TC.2005.103","volume":"54","author":"BH Meyer","year":"2005","unstructured":"Meyer, B.H., et al.: Power-performance simulation and design strategies for single-chip heterogeneous multiprocessors. IEEE Trans. Comput. 54(6), 684\u2013697 (2005)","journal-title":"IEEE Trans. Comput."},{"key":"3011_CR3","unstructured":"Park, Y.-H., et al.: System-level power-performance trade-offs in bus matrix communication architecture synthesis. In: Hardware\/Software Codesign and System Synthesis, 2006. CODES+ ISSS\u201906. Proceedings of the 4th International Conference. IEEE (2006)"},{"key":"3011_CR4","unstructured":"Top 500.: Available from: https:\/\/www.top500.org\/lists\/2019\/06\/. Accessed June 2019"},{"key":"3011_CR5","unstructured":"Green 500.: Available from: https:\/\/www.top500.org\/green500\/lists\/2019\/06\/. Accessed June 2019"},{"key":"3011_CR6","doi-asserted-by":"crossref","unstructured":"Thompson, M., et al.: A mixed-level co-simulation method for system-level design space exploration. In: Proceedings of the 2006 IEEE\/ACM\/IFIP Workshop on Embedded Systems for Real Time Multimedia. IEEE (2006)","DOI":"10.1109\/ESTMED.2006.321270"},{"key":"3011_CR7","unstructured":"Baghsorkhi, S.S., et al.: Analytical performance prediction for evaluation and tuning of GPGPU applications. In: Workshop on EPHAM2009, in Conjunction with CGO, Citeseer (2009)"},{"key":"3011_CR8","unstructured":"McClanahan, C.: History and Evolution of GPU Architecture. A Survey Paper, p. 9 (2010)"},{"issue":"1","key":"3011_CR9","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/LCA.2014.2299539","volume":"14","author":"J Power","year":"2015","unstructured":"Power, J., et al.: gem5-gpu: a heterogeneous CPU\u2013GPU simulator. IEEE Comput. Archit. Lett. 14(1), 34\u201336 (2015)","journal-title":"IEEE Comput. Archit. Lett."},{"key":"3011_CR10","doi-asserted-by":"crossref","unstructured":"Kothapalli, K., et al.: A performance prediction model for the CUDA GPGPU platform. In: 2009 International Conference on High Performance Computing (HiPC). IEEE (2009)","DOI":"10.1109\/HIPC.2009.5433179"},{"key":"3011_CR11","doi-asserted-by":"crossref","unstructured":"Hong, S., Kim, H.: An integrated GPU power and performance model. In: ACM SIGARCH Computer Architecture News. ACM (2010)","DOI":"10.1145\/1815961.1815998"},{"issue":"2","key":"3011_CR12","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1145\/1839667.1839670","volume":"7","author":"BC Lee","year":"2010","unstructured":"Lee, B.C., Brooks, D.: Applied inference: case studies in microarchitectural design. ACM Trans. Archit. Code Optim. 7(2), 8 (2010)","journal-title":"ACM Trans. Archit. Code Optim."},{"issue":"1","key":"3011_CR13","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1109\/TCAD.2009.2035579","volume":"29","author":"BC Schafer","year":"2010","unstructured":"Schafer, B.C., Wakabayashi, K.: Design space exploration acceleration through operation clustering. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 29(1), 153\u2013157 (2010)","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"3011_CR14","doi-asserted-by":"crossref","unstructured":"Meng, J., et al.: GROPHECY: GPU performance projection from CPU code skeletons. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis. ACM (2011)","DOI":"10.1145\/2063384.2063402"},{"key":"3011_CR15","doi-asserted-by":"crossref","unstructured":"Song, S., et al.: A simplified and accurate model of power-performance efficiency on emergent GPU architectures. In: 2013 IEEE 27th International Symposium on Parallel and Distributed Processing (IPDPS). IEEE (2013)","DOI":"10.1109\/IPDPS.2013.73"},{"key":"3011_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93701-4_23","volume-title":"Automatic Mapping for OpenCL-Programs on CPU\/GPU Heterogeneous Platforms","author":"K Moren","year":"2018","unstructured":"Moren, K., G\u00f6hringer, D.: Automatic Mapping for OpenCL-Programs on CPU\/GPU Heterogeneous Platforms. Springer, Cham (2018)"},{"key":"3011_CR17","unstructured":"Azizi, O., et al.: An integrated framework for joint design space exploration of microarchitecture and circuits. In: Design, Automation and Test in Europe Conference and Exhibition (DATE), 2010. IEEE (2010)"},{"key":"3011_CR18","doi-asserted-by":"crossref","unstructured":"Dubach, C., et al.: A predictive model for dynamic microarchitectural adaptivity control. In: Proceedings of the 2010 43rd Annual IEEE\/ACM International Symposium on Microarchitecture. IEEE Computer Society (2010)","DOI":"10.1109\/MICRO.2010.14"},{"key":"3011_CR19","doi-asserted-by":"crossref","unstructured":"Kerr, A., Diamos, G., Yalamanchili, S.: Modeling GPU\u2013CPU workloads and systems. In: Proceedings of the 3rd Workshop on General-Purpose Computation on Graphics Processing Units. ACM (2010)","DOI":"10.1145\/1735688.1735696"},{"key":"3011_CR20","doi-asserted-by":"crossref","unstructured":"Kerr, A., et al.: Eiger: a framework for the automated synthesis of statistical performance models. In: 2012 19th International Conference on High Performance Computing (HiPC). IEEE (2012)","DOI":"10.1109\/HiPC.2012.6507525"},{"key":"3011_CR21","doi-asserted-by":"crossref","unstructured":"Ubal, R., et al.: Multi2Sim: a simulation framework for CPU\u2013GPU computing. In: 2012 21st International Conference on Parallel Architectures and Compilation Techniques (PACT). IEEE (2012)","DOI":"10.1145\/2370816.2370865"},{"issue":"3","key":"3011_CR22","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1145\/3226228","volume":"15","author":"A Benatia","year":"2018","unstructured":"Benatia, A., et al.: BestSF: a sparse meta-format for optimizing SpMV on GPU. ACM Trans. Archit. Code Optim. 15(3), 29 (2018)","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"3011_CR23","unstructured":"Sun, Y., et al.: MGSim+ MGMark: A Framework for Multi-GPU System Research (2018). arXiv preprint arXiv:1811.02884"},{"key":"3011_CR24","doi-asserted-by":"crossref","unstructured":"Joseph, P., Vaswani, K., Thazhuthaveetil, M.J.: A predictive performance model for superscalar processors. In: Proceedings of the 39th Annual IEEE\/ACM International Symposium on Microarchitecture. IEEE Computer Society (2006)","DOI":"10.1109\/MICRO.2006.6"},{"issue":"4","key":"3011_CR25","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1145\/2873053","volume":"48","author":"L Hu","year":"2016","unstructured":"Hu, L., Che, X., Zheng, S.-Q.: A closer look at GPGPU. ACM Comput. Surv. 48(4), 60 (2016)","journal-title":"ACM Comput. Surv."},{"key":"3011_CR26","doi-asserted-by":"crossref","unstructured":"Issa, J.: Processor performance modeling using regression method. In: 2016 18th Mediterranean Electrotechnical Conference (MELECON). IEEE (2016)","DOI":"10.1109\/MELCON.2016.7495404"},{"key":"3011_CR27","doi-asserted-by":"crossref","unstructured":"Gianniti, E., Zhang, L., Ardagna, D.: Performance prediction of GPU-based deep learning applications. In: Conference: 2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD) (2018)","DOI":"10.1109\/CAHPC.2018.8645908"},{"key":"3011_CR28","unstructured":"Mukherjee, R., Rehman, M.S., Kothapalli, K., Narayanan, P.J, Srinathan, K.: Fast, Scalable, and Secure encryption on the GPU (2014)"},{"issue":"2","key":"3011_CR29","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1145\/2736287","volume":"12","author":"W Jia","year":"2015","unstructured":"Jia, W., et al.: GPU performance and power tuning using regression trees. ACM Trans. Archit. Code Optim. 12(2), 13 (2015)","journal-title":"ACM Trans. Archit. Code Optim."},{"key":"3011_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-018-2636-7","author":"A Siavashi","year":"2018","unstructured":"Siavashi, A., Momtazpour, M.: GPUCloudSim: an extension of CloudSim for modeling and simulation of GPUs in cloud data centers. J. Supercomput. (2018). https:\/\/doi.org\/10.1007\/s11227-018-2636-7","journal-title":"J. Supercomput."},{"key":"3011_CR31","doi-asserted-by":"crossref","unstructured":"Wu, W., Lee, B.C.: Inferred models for dynamic and sparse hardware\u2013software spaces. In: Proceedings of the 2012 45th Annual IEEE\/ACM International Symposium on Microarchitecture. IEEE Computer Society (2012)","DOI":"10.1109\/MICRO.2012.45"},{"issue":"6","key":"3011_CR32","doi-asserted-by":"publisher","first-page":"2207","DOI":"10.1016\/j.jcp.2010.09.011","volume":"230","author":"B Huang","year":"2011","unstructured":"Huang, B., et al.: Development of a GPU-based high-performance radiative transfer model for the Infrared Atmospheric Sounding Interferometer (IASI). J. Comput. Phys. 230(6), 2207\u20132221 (2011)","journal-title":"J. Comput. Phys."},{"key":"3011_CR33","doi-asserted-by":"crossref","unstructured":"Jia, W., Shaw, K.A., Martonosi, M.: Stargazer: automated regression-based GPU design space exploration. In: 2012 IEEE International Symposium on Performance Analysis of Systems & Software. IEEE (2012)","DOI":"10.1109\/ISPASS.2012.6189201"},{"issue":"124","key":"3011_CR34","first-page":"3","volume":"4","author":"LG Ahmad","year":"2013","unstructured":"Ahmad, L.G., et al.: Using three machine learning techniques for predicting breast cancer recurrence. J. Health Med. Inf. 4(124), 3 (2013)","journal-title":"J. Health Med. Inf."},{"key":"3011_CR35","doi-asserted-by":"crossref","unstructured":"Khalaf, M., et al.: A data science methodology based on machine learning algorithms for flood severity prediction. In: 2018 IEEE Congress on Evolutionary Computation (CEC) (2018)","DOI":"10.1109\/CEC.2018.8477904"},{"key":"3011_CR36","unstructured":"Reference Guide: Southern Islands Series Instruction Set Architecture.: Rev. 1.0, Aug. 2012. http:\/\/developer.amd.com\/wordpress\/media\/2012\/10\/AMD_Southern_Islands_Instruction_Set_Architecture.pdf"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-03011-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-019-03011-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-03011-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,6]],"date-time":"2021-02-06T07:24:44Z","timestamp":1612596284000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-019-03011-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,25]]},"references-count":36,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,6]]}},"alternative-id":["3011"],"URL":"https:\/\/doi.org\/10.1007\/s10586-019-03011-2","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"type":"print","value":"1386-7857"},{"type":"electronic","value":"1573-7543"}],"subject":[],"published":{"date-parts":[[2019,11,25]]},"assertion":[{"value":"5 June 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 November 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}