{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T13:50:57Z","timestamp":1725457857214},"publisher-location":"Berlin, Heidelberg","reference-count":14,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642360350"},{"type":"electronic","value":"9783642360367"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-36036-7_15","type":"book-chapter","created":{"date-parts":[[2013,1,17]],"date-time":"2013-01-17T01:59:30Z","timestamp":1358387970000},"page":"218-236","source":"Crossref","is-referenced-by-count":1,"title":["A Code Merging Optimization Technique for GPU"],"prefix":"10.1007","author":[{"given":"Ryan","family":"Taylor","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"15_CR1","unstructured":"Nvidia OpenCL Programming Guide (May 2010)"},{"key":"15_CR2","unstructured":"AMD OpenCL Programming Guide (June 2010)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Ryoo, S., Rodrigues, C., Baghsorkhi, S., Stone, S., Kirk, D., Hwu, W.: Optimization principles and application performance evaluation of a multithreaded GPU using CUDA. In: Proceedings of the 13th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 73\u201382. ACM (2008)","DOI":"10.1145\/1345206.1345220"},{"key":"15_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-540-89740-8_1","volume-title":"Languages and Compilers for Parallel Computing","author":"S.-Z. Ueng","year":"2008","unstructured":"Ueng, S.-Z., Lathara, M., Baghsorkhi, S.S., Hwu, W.-M.W.: CUDA-Lite: Reducing GPU Programming Complexity. In: Amaral, J.N. (ed.) LCPC 2008. LNCS, vol.\u00a05335, pp. 1\u201315. Springer, Heidelberg (2008)"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, E., Jiang, Y., Guo, Z., Shen, X.: Streamlining GPU applications on the fly. In: Proceedings of the 24th ACM International Conference on Supercomputing, pp. 115\u2013126. ACM (2010)","DOI":"10.1145\/1810085.1810104"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., Villa, O., Krishnamoorthy, S., Ga, G.: Dynamic load balancing on single- and multi-GPU systems. In: 2010 IEEE International Symposium on Parallel and Distributed Processing, pp. 1\u201312. IEEE (2010)","DOI":"10.1109\/IPDPS.2010.5470413"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Carrillo, S., Siegel, J., Li, X.: A control-structure splitting optimization for GPGPU. In: Proceedings of the 6th ACM Conference on Computing Frontiers, pp. 147\u2013150. ACM (2009)","DOI":"10.1145\/1531743.1531766"},{"key":"15_CR8","unstructured":"Hily, S., Seznec, A.: Contention on 2nd Level Cache May Limit the Effectiveness of Simultaneous Multithreading. Technical Report PI-1086 (1997)"},{"key":"15_CR9","unstructured":"Leng, T., Ali, R., Hsieh, J., Mashayekhi, V., Rooholamini, R.: A Study of Hyper-threading in High-performance Computing Clusters. In: Dell Power Solutions HPC Cluster Environment, pp. 33\u201336 (2002)"},{"issue":"12","key":"15_CR10","doi-asserted-by":"publisher","first-page":"1318","DOI":"10.1109\/71.970566","volume":"12","author":"M. Kandemir","year":"2001","unstructured":"Kandemir, M.: Compiler-Directed Collective-I\/O. IEEE Trans. Parallel Distrib. Syst.\u00a012(12), 1318\u20131331 (2001)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"15_CR11","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1109\/LPE.2005.195543","volume-title":"ISLPED 2005: Proceedings of the 2005 International Symposium on Low Power Electronics and Design","author":"J. Hom","year":"2005","unstructured":"Hom, J., Kremer, U.: Inter-program Optimizations for Conserving Disk Energy. In: ISLPED 2005: Proceedings of the 2005 International Symposium on Low Power Electronics and Design, pp. 335\u2013338. ACM Press, New York (2005)"},{"key":"15_CR12","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1145\/1128022.1128043","volume-title":"CF 2006: Proceedings of the 3rd Conference on Computing Frontiers","author":"O. Ozturk","year":"2006","unstructured":"Ozturk, O., Chen, G., Kandemir, M.: Multi-compilation: Capturing Interactions Among Concurrently-executing Applications. In: CF 2006: Proceedings of the 3rd Conference on Computing Frontiers, pp. 157\u2013170. ACM Press, New York (2006)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Yang, Y., Xiang, P., Kong, J., Zhou, H.: A GPGPU compiler for memory optimization and parallelism management. In: Proceedings of the 2010 ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 86\u201397. ACM (2010)","DOI":"10.1145\/1806596.1806606"},{"issue":"10","key":"15_CR14","doi-asserted-by":"publisher","first-page":"1389","DOI":"10.1016\/j.jpdc.2008.05.011","volume":"68","author":"S. Ryoo","year":"2008","unstructured":"Ryoo, S., Rodrigues, C.I., Stone, S.S., Stratton, J.A., Ueng, S.Z., Baghsorkhi, S.S., Hwu, W.W.: Program optimization carving for GPU computing. Journal of Parallel and Distributed Computing\u00a068(10), 1389\u20131401 (2008)","journal-title":"Journal of Parallel and Distributed Computing"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-36036-7_15.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T13:34:33Z","timestamp":1620135273000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-36036-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642360350","9783642360367"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-36036-7_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}