{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T15:47:13Z","timestamp":1783784833564,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,5,9]],"date-time":"2017-05-09T00:00:00Z","timestamp":1494288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Alexander von Humboldt Foundation"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,5,9]]},"DOI":"10.1145\/3035918.3064043","type":"proceedings-article","created":{"date-parts":[[2017,5,10]],"date-time":"2017-05-10T18:09:00Z","timestamp":1494439740000},"page":"417-432","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":57,"title":["A Memory Bandwidth-Efficient Hybrid Radix Sort on GPUs"],"prefix":"10.1145","author":[{"given":"Elias","family":"Stehle","sequence":"first","affiliation":[{"name":"Technical University of Munich (TUM), Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans-Arno","family":"Jacobsen","sequence":"additional","affiliation":[{"name":"Technical University of Munich (TUM), Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2017,5,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.14778\/2336664.2336678"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/2851141.2851169"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/2732219.2732227"},{"key":"e_1_3_2_1_4_1","volume-title":"Modern GPU. https:\/\/github.com\/moderngpu\/moderngpu","author":"Baxter S.","year":"2016","unstructured":"S. Baxter . Modern GPU. https:\/\/github.com\/moderngpu\/moderngpu , 2016 . S. Baxter. Modern GPU. https:\/\/github.com\/moderngpu\/moderngpu, 2016."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2593662"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454171"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824077"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824050"},{"key":"e_1_3_2_1_9_1","volume-title":"Global mobile data traffic forecast update","author":"Cisco","year":"2015","unstructured":"Cisco visual networking index : Global mobile data traffic forecast update , 2015 --2020 white paper. Technical report, Cisco , 2016. Cisco visual networking index: Global mobile data traffic forecast update, 2015--2020 white paper. Technical report, Cisco, 2016."},{"key":"e_1_3_2_1_10_1","first-page":"2012","author":"Davidson A.","year":"2012","unstructured":"A. Davidson , D. Tarjan , M. Garland , and J. D. Owens . Efficient parallel merge sort for fixed and variable length keys. InPar 2012 , 2012 . A. Davidson, D. Tarjan, M. Garland, and J. D. Owens. Efficient parallel merge sort for fixed and variable length keys. InPar 2012, 2012.","journal-title":"InPar"},{"key":"e_1_3_2_1_11_1","author":"Dehne F.","year":"2012","unstructured":"F. Dehne and H. Zaboli . Deterministic sample sort for GPUs. Parallel Processing Letters , 2012 . F. Dehne and H. Zaboli. Deterministic sample sort for GPUs. Parallel Processing Letters, 2012.","journal-title":"Deterministic sample sort for GPUs. Parallel Processing Letters"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1142473.1142511"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1132960.1132964"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/191839.191886"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304621"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2009.01542.x"},{"key":"e_1_3_2_1_17_1","volume-title":"Parallel Prefix Sum (Scan) with CUDA","author":"Harris M.","year":"2007","unstructured":"M. Harris , S. Sengupta , and J. D. Owens . Gpu gems 3 . Parallel Prefix Sum (Scan) with CUDA , 2007 . M. Harris, S. Sengupta, and J. D. Owens. Gpu gems 3. Parallel Prefix Sum (Scan) with CUDA, 2007."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1362622.1362684"},{"key":"e_1_3_2_1_19_1","unstructured":"M. Herf. Radix tricks. http:\/\/stereopsis.com\/radix.html 2001.  M. Herf. Radix tricks. http:\/\/stereopsis.com\/radix.html 2001."},{"key":"e_1_3_2_1_20_1","volume-title":"Thrust: A parallel template library. https:\/\/thrust.github.io","author":"Hoberock J.","year":"2016","unstructured":"J. Hoberock and N. Bell . Thrust: A parallel template library. https:\/\/thrust.github.io , 2016 . J. Hoberock and N. Bell. Thrust: A parallel template library. https:\/\/thrust.github.io, 2016."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/1299042.1299047"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809988"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687564"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213965"},{"key":"e_1_3_2_1_25_1","first-page":"733","volume":"2","author":"Kipfer P.","year":"2005","unstructured":"P. Kipfer and R. Westermann . Improved gpu sorting. GPU gems , 2 : 733 -- 746 , 2005 . P. Kipfer and R. Westermann. Improved gpu sorting. GPU gems, 2:733--746, 2005.","journal-title":"Improved gpu sorting. GPU gems"},{"key":"e_1_3_2_1_26_1","volume-title":"ADMS@ VLDB","author":"Krueger J.","year":"2011","unstructured":"J. Krueger , M. Grund , I. Jaeckel , A. Zeier , and H. Plattner . Applicability of gpu computing for efficient merge in in-memory databases . In ADMS@ VLDB , 2011 . J. Krueger, M. Grund, I. Jaeckel, A. Zeier, and H. Plattner. Applicability of gpu computing for efficient merge in in-memory databases. In ADMS@ VLDB, 2011."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470444"},{"key":"e_1_3_2_1_28_1","author":"Merrill D.","year":"2011","unstructured":"D. Merrill and A. Grimshaw . High performance and scalable radix sorting: A case study of implementing dynamic parallelism for gpu computing. Parallel Processing Letters , 2011 . D. Merrill and A. Grimshaw. High performance and scalable radix sorting: A case study of implementing dynamic parallelism for gpu computing. Parallel Processing Letters, 2011.","journal-title":"Parallel Processing Letters"},{"key":"e_1_3_2_1_29_1","volume-title":"https:\/\/github.com\/NVlabs\/cub","author":"D. Merrill and NVIDIA Corporation","year":"2016","unstructured":"D. Merrill and NVIDIA Corporation . CUB. https:\/\/github.com\/NVlabs\/cub , 2016 . D. Merrill and NVIDIA Corporation. CUB. https:\/\/github.com\/NVlabs\/cub, 2016."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113336"},{"key":"e_1_3_2_1_31_1","volume-title":"NVIDIA","author":"Whitepaper NVIDIA","year":"2014","unstructured":"NVIDIA GeForce GTX 980. Whitepaper . Technical report , NVIDIA , 2014 . NVIDIA GeForce GTX 980. Whitepaper. Technical report, NVIDIA, 2014."},{"key":"e_1_3_2_1_32_1","volume-title":"NVIDIA","author":"Whitepaper NVIDIA","year":"2016","unstructured":"NVIDIA Tesla P100. Whitepaper . Technical report , NVIDIA , 2016 . NVIDIA Tesla P100. Whitepaper. Technical report, NVIDIA, 2016."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2610522"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161005"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807207"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882918"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.05.012"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2458523.2458524"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.5555\/147877.147896"},{"key":"e_1_3_2_1_40_1","first-page":"2011","author":"Wassenberg J.","year":"2011","unstructured":"J. Wassenberg and P. Sanders . Engineering a Multi-core Radix Sort. Euro-Par 2011 . 2011 . J. Wassenberg and P. Sanders. Engineering a Multi-core Radix Sort. Euro-Par 2011. 2011.","journal-title":"Engineering a Multi-core Radix Sort. Euro-Par"},{"key":"e_1_3_2_1_41_1","volume-title":"IPDPS","author":"Ye X.","year":"2010","unstructured":"X. Ye , D. Fan , W. Lin , N. Yuan , and P. Ienne . High performance comparison-based sorting algorithm on many-core gpus . IPDPS , 2010 . X. Ye, D. Fan, W. Lin, N. Yuan, and P. Ienne. High performance comparison-based sorting algorithm on many-core gpus. IPDPS, 2010."}],"event":{"name":"SIGMOD\/PODS'17: International Conference on Management of Data","location":"Chicago Illinois USA","acronym":"SIGMOD\/PODS'17","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 2017 ACM International Conference on Management of Data"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3035918.3064043","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3035918.3064043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:36:41Z","timestamp":1750217801000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3035918.3064043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5,9]]},"references-count":41,"alternative-id":["10.1145\/3035918.3064043","10.1145\/3035918"],"URL":"https:\/\/doi.org\/10.1145\/3035918.3064043","relation":{},"subject":[],"published":{"date-parts":[[2017,5,9]]},"assertion":[{"value":"2017-05-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}