{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T05:48:13Z","timestamp":1751348893505,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":7,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T00:00:00Z","timestamp":1708387200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,3,2]]},"DOI":"10.1145\/3627535.3638478","type":"proceedings-article","created":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T14:22:41Z","timestamp":1708438961000},"page":"472-474","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["POSTER: RadiK: Scalable Radix Top-K Selection on GPUs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5041-1284","authenticated-orcid":false,"given":"Yifei","family":"Li","sequence":"first","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5450-5124","authenticated-orcid":false,"given":"Bole","family":"Zhou","sequence":"additional","affiliation":[{"name":"Independent, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3341-2943","authenticated-orcid":false,"given":"Jiejing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0996-2260","authenticated-orcid":false,"given":"Xuechao","family":"Wei","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9618-5523","authenticated-orcid":false,"given":"Yinghan","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7358-819X","authenticated-orcid":false,"given":"Yingda","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Seattle, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,2,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Andy Adinets. 2014. CUDA Pro Tip: Optimized Filtering with Warp-Aggregated Atomics. NVIDIA. https:\/\/developer.nvidia.com\/blog\/cuda-pro-tip-optimized-filtering-warp-aggregated-atomics\/"},{"issue":"2","key":"e_1_3_2_1_2_1","article-title":"Fast k-Selection Algorithms for Graphics Processing Units","volume":"4","author":"Alabi Tolu","year":"2012","unstructured":"Tolu Alabi, Jeffrey D. Blanchard, Bradley Gordon, and Russel Steinbach. 2012. Fast k-Selection Algorithms for Graphics Processing Units. ACM J. Exp. Algorithmics 17, Article 4.2 (10 2012), 29 pages.","journal-title":"ACM J. Exp. Algorithmics 17, Article"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"3508","author":"Kool Wouter","year":"2019","unstructured":"Wouter Kool, Herke van Hoof, and Max Welling. 2019. Stochastic Beams and Where To Find Them: The Gumbel-Top-k Trick for Sampling Sequences Without Replacement. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, Long Beach, California, USA, 3499--3508."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183735"},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"35136","author":"Vilnis Luke","year":"2023","unstructured":"Luke Vilnis, Yury Zemlyanskiy, Patrick Murray, Alexandre Tachard Passos, and Sumit Sanghai. 2023. Arithmetic Sampling: Parallel Diverse Decoding for Large Language Models. In Proceedings of the 40th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, Honolulu, Hawaii, USA, 35120--35136."},{"key":"e_1_3_2_1_7_1","unstructured":"Christina Zhang and Yong Wang. 2020. Accelerating Top-K Computation on GPU. NVIDIA. https:\/\/live.nvidia.cn\/gtc-od\/attachments\/CNS20315.pdf"}],"event":{"name":"PPoPP '24: 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGPLAN ACM Special Interest Group on Programming Languages"],"location":"Edinburgh United Kingdom","acronym":"PPoPP '24"},"container-title":["Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627535.3638478","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627535.3638478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:49:26Z","timestamp":1750182566000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627535.3638478"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,20]]},"references-count":7,"alternative-id":["10.1145\/3627535.3638478","10.1145\/3627535"],"URL":"https:\/\/doi.org\/10.1145\/3627535.3638478","relation":{},"subject":[],"published":{"date-parts":[[2024,2,20]]},"assertion":[{"value":"2024-02-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}