{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T12:30:34Z","timestamp":1725798634047},"publisher-location":"Cham","reference-count":10,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319098722"},{"type":"electronic","value":"9783319098739"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"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":[[2014]]},"DOI":"10.1007\/978-3-319-09873-9_66","type":"book-chapter","created":{"date-parts":[[2014,8,11]],"date-time":"2014-08-11T02:04:21Z","timestamp":1407722661000},"page":"788-799","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Concurrent Kernel Execution on Xeon Phi within Parallel Heterogeneous Workloads"],"prefix":"10.1007","author":[{"given":"Florian","family":"Wende","sequence":"first","affiliation":[]},{"given":"Thomas","family":"Steinke","sequence":"additional","affiliation":[]},{"given":"Frank","family":"Cordes","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"66_CR1","volume-title":"GPU Computing Gems Jade Edition","author":"W.M.W. Hwu","year":"2011","unstructured":"Hwu, W.M.W.: GPU Computing Gems Jade Edition, 1st edn. Morgan Kaufmann Publishers Inc., San Francisco (2011)","edition":"1"},{"key":"66_CR2","unstructured":"Intel Corporation: Intel Xeon Phi Product Family Performance, rev. 1.0. (December 2012), \n                    \n                      http:\/\/www.intel.com\/performance"},{"key":"66_CR3","doi-asserted-by":"crossref","unstructured":"Newburn, C.J., Dmitriev, S., Narayanaswamy, R., Wiegert, J., Murty, R., Chinchilla, F., Deodhar, R., McGuire, R.: Offload Compiler Runtime for the Intel Xeon Phi Coprocessor. In: IPDPS Workshops, pp. 1213\u20131225. IEEE Computer Society (2013)","DOI":"10.1109\/IPDPSW.2013.251"},{"key":"66_CR4","unstructured":"Johnson, J., Krieder, S.J., Grimmer, B., Wozniak, J.M., Wilde, M., Raicu, I.: Understanding the Costs of Many-Task Computing Workloads on Intel Xeon Phi Coprocessors. In: 2nd Greater Chicago Area System Research Workshop (GCASR). Northwestern University, Evanston (2013)"},{"key":"66_CR5","first-page":"1085","volume-title":"IEEE International Parallel & Distributed Processing Symposium","author":"S.J. Pennycook","year":"2013","unstructured":"Pennycook, S.J., Hughes, C.J., Smelyanskiy, M., Jarvis, S.A.: Exploring SIMD for Molecular Dynamics Using Intel Xeon Processors and Intel Xeon Phi Coprocessors. In: IEEE International Parallel & Distributed Processing Symposium, pp. 1085\u20131097. IEEE Computer Society, Los Alamitos (2013)"},{"key":"66_CR6","first-page":"23","volume-title":"Proceedings of the 2nd International Workshop on Performance Modeling, Benchmarking and Simulation of HPC Systems, PMBS 2011","author":"L. Wang","year":"2011","unstructured":"Wang, L., Huang, M., El-Ghazawi, T.: Towards Efficient GPU Sharing on Multicore Processors. In: Proceedings of the 2nd International Workshop on Performance Modeling, Benchmarking and Simulation of HPC Systems, PMBS 2011, pp. 23\u201324. ACM, New York (2011)"},{"key":"66_CR7","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1109\/SAAHPC.2012.12","volume-title":"Proceedings of the 2012 Symposium on Application Accelerators in High Performance Computing, SAAHPC 2012","author":"F. Wende","year":"2012","unstructured":"Wende, F., Cordes, F., Steinke, T.: On Improving the Performance of Multi-threaded CUDA Applications with Concurrent Kernel Execution by Kernel Reordering. In: Proceedings of the 2012 Symposium on Application Accelerators in High Performance Computing, SAAHPC 2012, pp. 74\u201383. IEEE Computer Society, Washington, DC (2012)"},{"key":"66_CR8","unstructured":"Wende, F., Cordes, F., Steinke, T.: Multi-threaded Kernel Offloading to GPGPU using Hyper-Q on Kepler Architecture. Technical Report 14-19, ZIB, Takustr. 7, 14195 Berlin (June 2014)"},{"key":"66_CR9","volume-title":"Intel Xeon Phi Coprocessor High Performance Programming","author":"J. Jeffers","year":"2013","unstructured":"Jeffers, J., Reinders, J.: Intel Xeon Phi Coprocessor High Performance Programming, 1st edn. Morgan Kaufmann Publishers Inc., San Francisco (2013)","edition":"1"},{"key":"66_CR10","unstructured":"OpenMP Architecture Review Board: OpenMP Application Program Interface, Version 4.0. 4.0 edn. (July 2013), \n                    \n                      http:\/\/www.openmp.org"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2014 Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-09873-9_66","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,19]],"date-time":"2020-04-19T20:19:05Z","timestamp":1587327545000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-09873-9_66"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319098722","9783319098739"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-09873-9_66","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}