{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:44:32Z","timestamp":1773193472671,"version":"3.50.1"},"publisher-location":"Cham","reference-count":10,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319321486","type":"print"},{"value":"9783319321493","type":"electronic"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"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":[[2016]]},"DOI":"10.1007\/978-3-319-32149-3_53","type":"book-chapter","created":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T02:24:42Z","timestamp":1459477482000},"page":"570-579","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Benchmarking the Cost of Thread Divergence in CUDA"],"prefix":"10.1007","author":[{"given":"Piotr","family":"Bialas","sequence":"first","affiliation":[]},{"given":"Adam","family":"Strzelecki","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,4,2]]},"reference":[{"key":"53_CR1","unstructured":"Aamodt, T.M., et al.: GPGPU-Sim (2012). http:\/\/www.gpgpu-sim.org"},{"key":"53_CR2","unstructured":"Bia\u0142as, P., Kowal, J., Strzelecki, A., et al.: GPU accelerated image reconstruction in a two-strip J-PET tomograph (2015). arxiv:1502.07478"},{"key":"53_CR3","unstructured":"Collange, S., Daumas, M., Defour, D., Parello, D.: Comparaison d\u2019algorithmes de branchements pour le simulateur de processeur graphique Barra. In: 13\u2018eme Symposium sur les Architectures Nouvelles de Machines, pp. 1\u201312 (2009)"},{"key":"53_CR4","doi-asserted-by":"crossref","unstructured":"Collange, S., Daumas, M., Defour, D., Parello, D.: Barra: A parallel functional simulator for GPGPU. In: 2010 IEEE International Symposium on Modeling, Analysis & Simulation of Computer and Telecommunication Systems (MASCOTS), pp. 351\u2013360. IEEE (2010)","DOI":"10.1109\/MASCOTS.2010.43"},{"key":"53_CR5","unstructured":"Coon, B.W., Lindholm, J.E.: System and method for managing divergent threads in a SIMD architecture, April 2008. https:\/\/www.google.com\/patents\/US7353369"},{"key":"53_CR6","unstructured":"Coon, B.W., Nickolls, J.R., Nyland, L., Mills, P.C., Lindholm, J.E.: Indirect function call instructions in a synchronous parallel thread processor, November 2012. https:\/\/www.google.com\/patents\/US8312254"},{"key":"53_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1007\/978-3-642-28869-2_16","volume-title":"Programming Languages and Systems","author":"A Habermaier","year":"2012","unstructured":"Habermaier, A., Knapp, A.: On the correctness of the SIMT execution model of GPUs. In: Seidl, H. (ed.) Programming Languages and Systems. LNCS, vol. 7211, pp. 316\u2013335. Springer, Heidelberg (2012)"},{"issue":"2","key":"53_CR8","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., Montrym, J.: NVIDIA Tesla: a unified graphics and computing architecture. IEEE Micro 28(2), 39\u201355 (2008)","journal-title":"IEEE Micro"},{"key":"53_CR9","volume-title":"The CUDA Handbook: A Comprehensive Guide to GPU Programming","author":"N Wilt","year":"2013","unstructured":"Wilt, N.: The CUDA Handbook: A Comprehensive Guide to GPU Programming. Pearson Education, Upper Saddle River (2013)"},{"key":"53_CR10","doi-asserted-by":"crossref","unstructured":"Wong, H., Papadopoulou, M.M., Sadooghi-Alvandi, M., Moshovos, A.: DemystifyingGPU microarchitecture through microbenchmarking. In: 2010 IEEE International Symposium on Performance Analysis of Systems & Software (ISPASS), pp. 235\u2013246. IEEE (2010)","DOI":"10.1109\/ISPASS.2010.5452013"}],"container-title":["Lecture Notes in Computer Science","Parallel Processing and Applied Mathematics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-32149-3_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,15]],"date-time":"2020-12-15T01:20:02Z","timestamp":1607995202000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-32149-3_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319321486","9783319321493"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-32149-3_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016]]},"assertion":[{"value":"2 April 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}