{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T04:51:09Z","timestamp":1743051069963,"version":"3.40.3"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319527086"},{"type":"electronic","value":"9783319527093"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-52709-3_19","type":"book-chapter","created":{"date-parts":[[2017,1,23]],"date-time":"2017-01-23T07:13:25Z","timestamp":1485155605000},"page":"250-264","source":"Crossref","is-referenced-by-count":2,"title":["Locality-Aware Task-Parallel Execution on GPUs"],"prefix":"10.1007","author":[{"given":"Jad","family":"Hbeika","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milind","family":"Kulkarni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,1,24]]},"reference":[{"issue":"1","key":"19_CR1","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1006\/jpdc.1996.0107","volume":"37","author":"RD Blumofe","year":"1996","unstructured":"Blumofe, R.D., Joerg, C.F., Kuszmaul, B.C., Leiserson, C.E., Randall, K.H., Zhou, Y.: Cilk: an efficient multithreaded runtime system. J. Parallel Distrib. Comput. 37(1), 55\u201369 (1996)","journal-title":"J. Parallel Distrib. Comput."},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Capodieci, N., Burgio, P.: Efficient implementation of genetic algorithms on GP-GPU with scheduled persistent CUDA threads. In: 2015 Seventh International Symposium on Parallel Architectures, Algorithms and Programming (PAAP), pp. 6\u201312. IEEE (2015)","DOI":"10.1109\/PAAP.2015.13"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Chen, G., Shen, X.: Free launch: optimizing GPU dynamic kernel launches through thread reuse. In: Proceedings of the 48th International Symposium on Microarchitecture, pp. 407\u2013419. ACM (2015)","DOI":"10.1145\/2830772.2830818"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Frigo, M., Halpern, P., Leiserson, C.E., Lewin-Berlin, S.: Reducers and other Cilk++ hyperobjects. In: SPAA 2009, pp. 79\u201390 (2009)","DOI":"10.1145\/1583991.1584017"},{"issue":"8","key":"19_CR5","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MC.2012.257","volume":"45","author":"BR Gaster","year":"2012","unstructured":"Gaster, B.R., Howes, L.: Can GPGPU programming be liberated from the data-parallel bottleneck? Computer 45(8), 42\u201352 (2012)","journal-title":"Computer"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Goldfarb, M., Jo, Y., Kulkarni, M.: General transformations for GPU execution of tree traversals. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis (Supercomputing), SC 2013 (2013)","DOI":"10.1145\/2503210.2503223"},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, K., Stuart, J.A., Owens, J.D.: A study of persistent threads style GPU programming for GPGPU workloads. In: Innovative Parallel Computing (InPar) 2012, pp. 1\u201314 (2012)","DOI":"10.1109\/InPar.2012.6339596"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Liu, J., Hegde, N., Kulkarni, M.: Hybrid CPU-GPU scheduling and execution of tree traversals. In: Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2016, pp. 41:1\u201341:2, New York, NY, USA. ACM (2016)","DOI":"10.1145\/3016078.2851174"},{"key":"19_CR9","unstructured":"Munshi, A.: OpenCL parallel computing on the GPU and CPU. In: SIGGRAPH"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Nasre, R., Burtscher, M., Pingali, K.: Data-driven versus topology-driven irregular computations on GPUS. In: IEEE 27th International Symposium on Parallel & Distributed Processing (IPDPS), pp. 463\u2013474. IEEE (2013)","DOI":"10.1109\/IPDPS.2013.28"},{"key":"19_CR11","unstructured":"NVIDIA. CUDA. http:\/\/www.nvidia.com\/object\/cuda_home_new.html"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Orr, M.S., Beckmann, B.M., Reinhardt, S.K., Wood, D.A.: Fine-grain task aggregation and coordination on GPUs. In: ISCA 2014, pp. 181\u2013192 (2014)","DOI":"10.1109\/ISCA.2014.6853209"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Ren, B., Jo, Y., Krishnamoorthy, S., Agrawal, K., Kulkarni, M.: Efficient execution of recursive programs on commodity vector hardware. In: PLDI, pp. 509\u2013520 (2015)","DOI":"10.1145\/2737924.2738004"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Rogers, T.G., O\u2019Connor, M., Aamodt, T.M.: Cache-conscious wavefront scheduling. In: Proceedings of the 45th Annual IEEE\/ACM International Symposium on Microarchitecture, MICRO-45, pp. 72\u201383, Washington, DC, USA. IEEE Computer Society (2012)","DOI":"10.1109\/MICRO.2012.16"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Wu, B., Chen, G., Li, D., Shen, X., Vetter, J.: Enabling and exploiting flexible task assignment on GPU through SM-centric program transformations. In: Proceedings of the 29th ACM on International Conference on Supercomputing, pp. 119\u2013130. ACM (2015)","DOI":"10.1145\/2751205.2751213"}],"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\/978-3-319-52709-3_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,17]],"date-time":"2019-09-17T17:59:19Z","timestamp":1568743159000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-52709-3_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319527086","9783319527093"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-52709-3_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}