{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T06:31:31Z","timestamp":1776925891983,"version":"3.51.2"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319099668","type":"print"},{"value":"9783319099675","type":"electronic"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-09967-5_5","type":"book-chapter","created":{"date-parts":[[2014,9,30]],"date-time":"2014-09-30T15:10:04Z","timestamp":1412089804000},"page":"87-101","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["OpenCL Task Partitioning in the Presence of GPU Contention"],"prefix":"10.1007","author":[{"given":"Dominik","family":"Grewe","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael F. P.","family":"O\u2019Boyle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,10,1]]},"reference":[{"key":"5_CR1","unstructured":"AMD. Accelerated parallel processing (APP) SDK (2013)"},{"key":"5_CR2","volume-title":"Pattern Recognition and Machine Learning (Information Science and Statistics)","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, New York (2006)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Boser, B.E., Guyon, I., Vapnik, V.: A training algorithm for optimal margin classifiers. In: Proceedings of the 5th Annual ACM Conference on Computational Learning Theory, pp. 144\u2013152 (1992)","DOI":"10.1145\/130385.130401"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Cooper, K.D., Schielke, P.J., Subramanian, D.: Optimizing for reduced code space using genetic algorithms. In: LCTES \u201999, pp. 1\u20139 (1999)","DOI":"10.1145\/315253.314414"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Eyerman, S., Eeckhout, L.: Probabilistic job symbiosis modeling for SMT processor scheduling. In: ASPLOS \u201910, pp. 91\u2013102","DOI":"10.1145\/1735971.1736033"},{"key":"5_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1007\/978-3-642-19861-8_16","volume-title":"Compiler Construction","author":"D Grewe","year":"2011","unstructured":"Grewe, D., O\u2019Boyle, M.F.P.: A static task partitioning approach for heterogeneous systems using OpenCL. In: Knoop, J. (ed.) CC 2011. LNCS, vol. 6601, pp. 286\u2013305. Springer, Heidelberg (2011)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Grewe, D., Wang, Z., O\u2019Boyle, M.F.P.: A workload-aware mapping approach for data-parallel programs. In: HiPEAC \u201911 (2011)","DOI":"10.1145\/1944862.1944881"},{"key":"5_CR8","unstructured":"Han, T.D., Abdelrahman, T.S.: hiCUDA: a high-level\u00a0 directive-based language for GPU programming. In: GPGPU \u201909"},{"key":"5_CR9","unstructured":"Hormati, A., Samadi, M., Woh, M., Mudge, T., Mahlke, S.:\u00a0 Sponge: portable stream programming on graphics engines. In: ASPLOS \u201911"},{"key":"5_CR10","unstructured":"Intel. Intel SDK for OpenCL applications 2013 \u2014 intel developer zone (2013)"},{"key":"5_CR11","unstructured":"Kim, J., Kim, H., Lee, J.H. Lee, J.: Achieving a single\u00a0 compute device image in OpenCL for multiple GPUs. In: PPoPP \u201911"},{"key":"5_CR12","unstructured":"LLVM. Clang: a C language family frontend for LLVM. http:\/\/clang.llvm.org\/"},{"key":"5_CR13","unstructured":"Long, S., O\u2019Boyle, M.F.P.: Adaptive java optimisation using instance-based learning. In: ICS \u201904"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Luk, C.-K., Hong, S., Kim, H.: Qilin: exploiting parallelism on heterogeneous multiprocessors with adaptive mapping. In: MICRO 42 (2009)","DOI":"10.1145\/1669112.1669121"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Raman, A., Zaks, A., Lee, J.W., August, D.I.: Parcae: a system for\u00a0 exible parallel execution. In: PLDI \u201912, pp. 133\u2013144","DOI":"10.1145\/2345156.2254082"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Ravi, V.T. Ma, W., Chiu, D., Agrawal, G.: Compiler and runtime support for enabling generalized reduction computations on heterogeneous parallel configurations. In: SC, pp. 137\u2013146 (2010)","DOI":"10.1145\/1810085.1810106"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Snavely, A., Tullsen, D.M.: Symbiotic jobscheduling for a simultaneous multithreaded processor. In: ASPLOS-IX, pp. 234\u2013244 (2000)","DOI":"10.1145\/378995.379244"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Wang, Z., O\u2019Boyle, M.F.P.: Using machine learning to partition streaming programs. ACM Trans. Archit. Code Optim. 10(3) (2013)","DOI":"10.1145\/2512436"},{"key":"5_CR19","unstructured":"Wang, Z., O\u2019Boyle, M.F.P., Emani, M.K.: Smart, adaptive mapping of parallelism in the presence of external workload. In: CGO \u201913 (2013)"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Z., O\u2019Boyle, M.F.P.: Mapping parallelism to multi-cores: a machine learning based approach. In: PPoPP \u201909 (2008)","DOI":"10.1145\/1504176.1504189"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Z., O\u2019Boyle, M.F.P.: Partitioning streaming parallelism for multi-cores: a machine learning based approach. In: PACT \u201910 (2010)","DOI":"10.1145\/1854273.1854313"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-09967-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T11:00:41Z","timestamp":1676890841000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-09967-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319099668","9783319099675"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-09967-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"1 October 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}