{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:05:22Z","timestamp":1766066722946,"version":"3.41.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2017,4,11]],"date-time":"2017-04-11T00:00:00Z","timestamp":1491868800000},"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":["Int J Parallel Prog"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1007\/s10766-017-0502-5","type":"journal-article","created":{"date-parts":[[2017,4,11]],"date-time":"2017-04-11T09:00:58Z","timestamp":1491901258000},"page":"1017-1034","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Survey of GPU Based Sorting Algorithms"],"prefix":"10.1007","volume":"46","author":[{"given":"Dhirendra Pratap","family":"Singh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ishan","family":"Joshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaytrilok","family":"Choudhary","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,4,11]]},"reference":[{"key":"502_CR1","doi-asserted-by":"crossref","unstructured":"Satish, N., Kim, C., Chhugani, J., Nguyen, A.D., Lee, V.W., Kim, D., Dubey, P.: Fast sort on CPUs and GPUs: a case for bandwidth oblivious SIMD sort. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data, pp. 351\u2013362 (2010)","DOI":"10.1145\/1807167.1807207"},{"issue":"2","key":"502_CR2","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1142\/S0129626411000187","volume":"21","author":"D Merrill","year":"2011","unstructured":"Merrill, D., Grimshaw, A.: High performance and scalable radix sorting: a case study of implementing dynamic parallelism for GPU computing. Parallel Proc. Lett. 21(2), 245\u2013272 (2011)","journal-title":"Parallel Proc. Lett."},{"issue":"8","key":"502_CR3","doi-asserted-by":"crossref","first-page":"2368","DOI":"10.1111\/j.1467-8659.2009.01542.x","volume":"28","author":"L Ha","year":"2009","unstructured":"Ha, L., Kruger, L., Silva, C.T.: Fast four-way parallel radix sorting on GPUs. Comput. Graph. Forum 28(8), 2368\u20132378 (2009)","journal-title":"Comput. Graph. Forum"},{"key":"502_CR4","doi-asserted-by":"crossref","unstructured":"Satish, N., Harris, M., Garland, M.: Designing efficient sorting algorithms for manycore GPUs. In: Proceedings of the IEEE International Symposium on Parallel and Distributed Processing (IPDPS), pp. 1\u201310 (2009)","DOI":"10.1109\/IPDPS.2009.5161005"},{"key":"502_CR5","doi-asserted-by":"crossref","unstructured":"Huang, B., Gao, J., Li, X.: An empirically optimized radix sort for GPU. In: Proceedings of the IEEE International Symposium on Parallel and Distributed Processing with Applications, pp. 234\u2013241 (2009)","DOI":"10.1109\/ISPA.2009.89"},{"key":"502_CR6","unstructured":"Harris, M., Owens, J., Sengupta, S., Zhang, Y., Davidson, A.: Cudpp: Cuda Data Parallel Primitives Library (2007). Accessed Aug 2015"},{"key":"502_CR7","unstructured":"Harris, M.: Optimizing Parallel Reduction in CUDA. Technical Report. NVIDIA Developer Technology Website\/projects\/reduction\/doc\/reduction.pdf (2007)"},{"key":"502_CR8","doi-asserted-by":"crossref","unstructured":"Merrill, D.G., Grimshaw, A.S.: Revisiting sorting for GPGPU stream architectures. In: Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques, pp. 545\u2013546 (2010)","DOI":"10.1145\/1854273.1854344"},{"key":"502_CR9","volume-title":"Design Patterns: Elements of Reusable Object-oriented Software","author":"E Gamma","year":"1994","unstructured":"Gamma, E., Johnson, R., Helm, R., Vlissides, J.: Design Patterns: Elements of Reusable Object-oriented Software. Addison-Wesley, Reading (1994)"},{"key":"502_CR10","first-page":"677","volume-title":"GPU Gems 3","author":"SL Grand","year":"2007","unstructured":"Grand, S.L.: Broad-phase collision detection with CUDA. In: Nguyen, H. (ed.) GPU Gems 3, pp. 677\u2013697. Addison Wesley, Reading (2007)"},{"key":"502_CR11","unstructured":"Sengupta, S., Harris, M., Zhang, Y., Owens, J.D.: Scan primitives for GPU computing. In: Proceedings of the 22nd ACM SIGGRAPH\/EUROGRAPHICS Symposium on Graphics Hardware, pp. 97\u2013106 (2007)"},{"key":"502_CR12","doi-asserted-by":"crossref","unstructured":"Govindaraju, N., Gray, J., Kumar, R., Manocha, D.: GPUTeraSort: High performance graphics co-processor sorting for large database management. In: Proceedings of the 2006 ACM SIGMOD International Conference on Management of Data, pp. 325\u2013336 (2006)","DOI":"10.1145\/1142473.1142511"},{"key":"502_CR13","doi-asserted-by":"crossref","unstructured":"Cederman, D., Tsigas, P.: Gpu-quicksort: A practical quicksort algorithm for graphics processors. J. Exp. Algorithmics 14(1.4) (2009)","DOI":"10.1145\/1498698.1564500"},{"key":"502_CR14","unstructured":"Herf, M.: Radix Tricks. http:\/\/stereopsis.com\/radix.html (2001). Accessed Jan 2016"},{"key":"502_CR15","unstructured":"GCC. Standard Template Library. http:\/\/gcc.gnu.org (2008). Accessed Nov 2015"},{"key":"502_CR16","unstructured":"Intel threading building blocks 2.1. http:\/\/www.threadbuildingbuildingblocks.org (2008). Accessed Sept 2015"},{"issue":"10","key":"502_CR17","doi-asserted-by":"crossref","first-page":"1381","DOI":"10.1016\/j.jpdc.2008.05.012","volume":"68","author":"E Sintorn","year":"2008","unstructured":"Sintorn, E., Assarsson, U.: Fast parallel GPU-sorting using a hybrid algorithm. J. Parallel Distrib. Comput. 68(10), 1381\u20131388 (2008)","journal-title":"J. Parallel Distrib. Comput."},{"key":"502_CR18","doi-asserted-by":"crossref","unstructured":"Ye, X., Fan, D., Lin, W., Yuan, N., Ienne, P.: High performance comparison-based sorting algorithm on many-core GPUs. In: Proceedings of the IEEE International Symposium on Parallel and Distributed Processing (IPDPS), pp. 1\u201310 (2010)","DOI":"10.1109\/IPDPS.2010.5470445"},{"issue":"8","key":"502_CR19","doi-asserted-by":"crossref","first-page":"983","DOI":"10.1002\/(SICI)1097-024X(199708)27:8<983::AID-SPE117>3.0.CO;2-#","volume":"27","author":"DR Musser","year":"1997","unstructured":"Musser, D.R.: Introspective sorting and selection algorithms. Softw. Pract. Exp. 27(8), 983\u2013993 (1997)","journal-title":"Softw. Pract. Exp."},{"key":"502_CR20","unstructured":"Baraglia, R., Capannini, G., Nardini, F.M., Silvestri, F.: Sorting using bitonic network with CUDA. In: Proceedings of the 7th Workshop on Large-Scale Distributed Systems for Information Retrieval (LSDS-IR), Boston, USA (2009)"},{"issue":"8","key":"502_CR21","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1109\/71.532111","volume":"7","author":"AC Dusseau","year":"1996","unstructured":"Dusseau, A.C., Culler, D.E., Schauser, K.E., Martin, R.P.: Fast parallel sorting under LogP: experience with the CM-5. IEEE Trans. Parallel Distrib. Syst. 7(8), 791\u2013804 (1996)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"502_CR22","doi-asserted-by":"crossref","unstructured":"Blelloch, G.E., Leiserson, C.E., Maggs, B.M., Plaxton, C.G., Smith, S.J., Zagha, M.: A comparison of sorting algorithms for the connection machine CM-2. In: Proceedings of the Third Annual ACM Symposium on Parallel Algorithms and Architectures, pp. 3\u201316 (1991)","DOI":"10.1145\/113379.113380"},{"key":"502_CR23","doi-asserted-by":"crossref","unstructured":"Leischner, N., Osipov, V., Sanders, P.: GPU sample sort. In: Proceedings of the IEEE International Symposium on Parallel and Distributed Processing (IPDPS), pp. 1\u201310 (2010)","DOI":"10.1109\/IPDPS.2010.5470444"},{"key":"502_CR24","doi-asserted-by":"crossref","unstructured":"Dehne, F., Zaboli, H.: Deterministic sample sort for GPUs. Parallel Process. Lett. 22(3), CoRR. arXiv:1002.4464 (2012)","DOI":"10.1142\/S0129626412500089"},{"key":"502_CR25","doi-asserted-by":"crossref","unstructured":"Chen, S., Qin, J., Xie, Y., Zhao, J., Heng, P.A.: A fast and flexible sorting algorithm with cuda. In: Proceedings of the International Conference on Algorithms and Architectures for Parallel Processing, pp. 281\u2013290 (2009)","DOI":"10.1007\/978-3-642-03095-6_28"},{"key":"502_CR26","volume-title":"Vector Models for Data-Parallel Computing","author":"GE Blelloch","year":"1990","unstructured":"Blelloch, G.E.: Vector Models for Data-Parallel Computing. MIT Press, Cambridge (1990)"},{"key":"502_CR27","unstructured":"Cuda toolkit documentation 6.5. http:\/\/docs.nvidia.com\/cuda\/cuda-samples\/index.html . Accessed July 2015"},{"issue":"1","key":"502_CR28","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1002\/cpe.3611","volume":"28","author":"E Manca","year":"2016","unstructured":"Manca, E., Manconi, A., Orro, A., Armano, G., Milanesi, L.: CUDA-quicksort: an improved GPU-based implementation of quicksort. Concurr. Comput.: Pract. Exp. 28(1), 21\u201343 (2016)","journal-title":"Concurr. Comput.: Pract. Exp."},{"key":"502_CR29","first-page":"851","volume-title":"GPU Gems 3","author":"M Harris","year":"2007","unstructured":"Harris, M., Sengupta, S., Owens, J.D.: Parallel prefix sum (scan) with CUDA. In: Nguyen, H. (ed.) GPU Gems 3, pp. 851\u2013876. Addison Wesley, Reading (2007)"},{"key":"502_CR30","unstructured":"Govindaraju, N.K., Raghuvanshi, N., Henson, M., Manocha, D.: A Cache-efficient Sorting Algorithm for Database and Data Mining Computations Using Graphics Processors. University of North Carolina (2005)"},{"key":"502_CR31","doi-asserted-by":"crossref","unstructured":"Batcher, K.E.: Sorting networks and their applications. In: Proceedings of the 1968 Spring Joint Computer Conference, pp. 307\u2013314 (1968)","DOI":"10.1145\/1468075.1468121"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-017-0502-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-017-0502-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-017-0502-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:49:17Z","timestamp":1750196957000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-017-0502-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,11]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["502"],"URL":"https:\/\/doi.org\/10.1007\/s10766-017-0502-5","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2017,4,11]]}}}