{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T16:26:18Z","timestamp":1770740778778,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,6,14]],"date-time":"2017-06-14T00:00:00Z","timestamp":1497398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"H2020 Marie SkBodowska-Curie Actions","award":["752321"],"award-info":[{"award-number":["752321"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1247693"],"award-info":[{"award-number":["IIS-1247693"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010661","name":"Horizon 2020","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,6,14]]},"DOI":"10.1145\/3079079.3079105","type":"proceedings-article","created":{"date-parts":[[2017,5,31]],"date-time":"2017-05-31T19:31:40Z","timestamp":1496259100000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":45,"title":["Fast segmented sort on GPUs"],"prefix":"10.1145","author":[{"given":"Kaixi","family":"Hou","sequence":"first","affiliation":[{"name":"Virginia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Copenhagen, Copenhagen, Denmark and Norwegian University of Science and Technology, Trondheim, Norway"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Wang","sequence":"additional","affiliation":[{"name":"Virginia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu-chun","family":"Feng","sequence":"additional","affiliation":[{"name":"Virginia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,6,14]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"L. A. Adamic and B. A. Huberman. 2002. Zipf's Law and the Internet. Glottometrics 3 (2002).  L. A. Adamic and B. A. Huberman. 2002. Zipf's Law and the Internet. Glottometrics 3 (2002)."},{"key":"e_1_3_2_1_2_1","series-title":"Series (2009).","volume-title":"Emerging Architectures: The PLASMA and MAGMA projects. J. of Physics: Conf","author":"Agullo E.","year":"2009","unstructured":"E. Agullo , J. Demmel , J. Dongarra , B. Hadri , J. Kurzak , J. Langou , H. Ltaief , P. Luszczek , and S. Tomov . 2009 . Numerical Linear Algebra on Emerging Architectures: The PLASMA and MAGMA projects. J. of Physics: Conf . Series (2009). E. Agullo, J. Demmel, J. Dongarra, B. Hadri, J. Kurzak, J. Langou, H. Ltaief, P. Luszczek, and S. Tomov. 2009. Numerical Linear Algebra on Emerging Architectures: The PLASMA and MAGMA projects. J. of Physics: Conf. Series (2009)."},{"key":"e_1_3_2_1_3_1","unstructured":"S. Baxter. ModernGPU2.0: A Productivity Library for General-purpose Computing on GPUs. https:\/\/github.com\/moderngpu\/moderngpu.  S. Baxter. ModernGPU2.0: A Productivity Library for General-purpose Computing on GPUs . https:\/\/github.com\/moderngpu\/moderngpu."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"N. Bell S. Dalton and L. N. Olson. 2012. Exposing Fine-Grained Parallelism in Algebraic Multigrid Methods. SIAM J. on Scientific Computing (2012).  N. Bell S. Dalton and L. N. Olson. 2012. Exposing Fine-Grained Parallelism in Algebraic Multigrid Methods. SIAM J. on Scientific Computing (2012).","DOI":"10.1137\/110838844"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926259"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.42122"},{"key":"e_1_3_2_1_7_1","unstructured":"G. E. Blelloch M. A. Heroux and M. Zagha. 1993. Segmented Operations for Sparse Matrix Computation on Vector Multiprocessors. Technical Report.   G. E. Blelloch M. A. Heroux and M. Zagha. 1993. Segmented Operations for Sparse Matrix Computation on Vector Multiprocessors . Technical Report."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1250790.1250877"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/1454159.1454171"},{"key":"e_1_3_2_1_10_1","volume-title":"CUSP: Generic Parallel Algorithms for Sparse Matrix and Graph Computations.","author":"Dalton S.","year":"2014","unstructured":"S. Dalton , N. Bell , L. Olson , and M. Garland . 2014 . CUSP: Generic Parallel Algorithms for Sparse Matrix and Graph Computations. (2014). http:\/\/cusplibrary.github.io\/ V0.5.0. S. Dalton, N. Bell, L. Olson, and M. Garland. 2014. CUSP: Generic Parallel Algorithms for Sparse Matrix and Graph Computations. (2014). http:\/\/cusplibrary.github.io\/ V0.5.0."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964179.1964185"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_13_1","unstructured":"J. Demouth. 201"},{"key":"e_1_3_2_1_14_1","volume-title":"KLAP: Kernel Launch Aggregation and Promotion for Optimizing Dynamic Parallelism","author":"Hajj I. El","year":"2016","unstructured":"I. El Hajj , J. G\u00f3mez-Luna , C. Li , L.-W. Chang , D. Milojicic , and W.-m. Hwu . 2016 . KLAP: Kernel Launch Aggregation and Promotion for Optimizing Dynamic Parallelism . In IEEE\/ACM Int'l Symp. on Microarchitecture (MICRO) . I. El Hajj, J. G\u00f3mez-Luna, C. Li, L.-W. Chang, D. Milojicic, and W.-m. Hwu. 2016. KLAP: Kernel Launch Aggregation and Promotion for Optimizing Dynamic Parallelism. In IEEE\/ACM Int'l Symp. on Microarchitecture (MICRO)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807609"},{"key":"e_1_3_2_1_16_1","volume-title":"PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs. In USENIX Symp. on Operating Systems Design and Implementation (OSDI).","author":"Gonzalez J. E.","unstructured":"J. E. Gonzalez , Y. Low , H. Gu , D. Bickson , and C. Guestrin . 2012 . PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs. In USENIX Symp. on Operating Systems Design and Implementation (OSDI). J. E. Gonzalez, Y. Low, H. Gu, D. Bickson, and C. Guestrin. 2012. PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs. In USENIX Symp. on Operating Systems Design and Implementation (OSDI)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304621"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342014567546"},{"key":"e_1_3_2_1_19_1","volume-title":"CUDPP: CUDA Data-Parallel Primitives Library.","author":"Harris M.","year":"2016","unstructured":"M. Harris , J. D. Owens , S. Sengupta , S. Tzeng , Y. Zhang , A. Davidson , R. Patel , L. Wang , and S. Ashkiani . 2016 . CUDPP: CUDA Data-Parallel Primitives Library. (2016). http:\/\/cudpp.github.io\/ V2.3. M. Harris, J. D. Owens, S. Sengupta, S. Tzeng, Y. Zhang, A. Davidson, R. Patel, L. Wang, and S. Ashkiani. 2016. CUDPP: CUDA Data-Parallel Primitives Library. (2016). http:\/\/cudpp.github.io\/ V2.3."},{"key":"e_1_3_2_1_20_1","volume-title":"Thrust: A Parallel Algorithms Library. https:\/\/thrust.github.io\/.","author":"Hoberock J.","year":"2015","unstructured":"J. Hoberock and N. Bell . 2015 . Thrust: A Parallel Algorithms Library. https:\/\/thrust.github.io\/. J. Hoberock and N. Bell. 2015. Thrust: A Parallel Algorithms Library. https:\/\/thrust.github.io\/."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPPW.2014.44"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751247"},{"key":"e_1_3_2_1_23_1","volume-title":"AAlign: A SIMD Framework for Pairwise Sequence Alignment on x86-Based Multi-and Many-Core Processors","author":"Hou K.","unstructured":"K. Hou , H. Wang , and W.-c. Feng . 2016. AAlign: A SIMD Framework for Pairwise Sequence Alignment on x86-Based Multi-and Many-Core Processors . In IEEE Int'l Parallel & Distributed Processing Symp. (IPDPS) . K. Hou, H. Wang, and W.-c. Feng. 2016. AAlign: A SIMD Framework for Pairwise Sequence Alignment on x86-Based Multi-and Many-Core Processors. In IEEE Int'l Parallel & Distributed Processing Symp. (IPDPS)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3075564.3075583"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628108"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"N. Leischner V. Osipov and P. Sanders. 2010. GPU Sample Sort. In IEEE Int'l Symp. on Parallel Distributed Processing (IPDPS).  N. Leischner V. Osipov and P. Sanders. 2010. GPU Sample Sort. In IEEE Int'l Symp. on Parallel Distributed Processing (IPDPS) .","DOI":"10.1109\/IPDPS.2010.5470444"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037709"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-43659-3_45"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751209"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2015.06.010"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.parco.2015.04.004"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1137\/0222058"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"D. Merrill and A. Grimshaw. 2011. 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. 2011. High Performance and Scalable Radix Sorting: A Case Study of Implementing Dynamic Parallelism for GPU Computing. Parallel Processing Letters (2011).","DOI":"10.1142\/S0129626411000187"},{"key":"e_1_3_2_1_34_1","unstructured":"NCBI. Genbank. ftp:\/\/ftp.ncbi.nlm.nih.gov\/genbank  NCBI. Genbank . ftp:\/\/ftp.ncbi.nlm.nih.gov\/genbank"},{"key":"e_1_3_2_1_35_1","unstructured":"NVIDIA. 2016. cuSPARSE library. (2016). https:\/\/developer.nvidia.com\/cuSPARSE  NVIDIA. 2016. cuSPARSE library. (2016). https:\/\/developer.nvidia.com\/cuSPARSE"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018743.3018763"},{"key":"e_1_3_2_1_37_1","unstructured":"NVIDIA Research. 2016. CUB 1.6.4. http:\/\/nvlabs.github.io\/cub\/.  NVIDIA Research. 2016. CUB 1.6.4 . http:\/\/nvlabs.github.io\/cub\/."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161005"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2312005.2312018"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.05.012"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/1798596.1798597"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926291"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"J. Wang and S. Yalamanchili. 2014. Characterization and analysis of dynamic parallelism in unstructured GPU applications. In IEEE Int'l Symp. on Workload Characterization (IISWC).  J. Wang and S. Yalamanchili. 2014. Characterization and analysis of dynamic parallelism in unstructured GPU applications. In IEEE Int'l Symp. on Workload Characterization (IISWC) .","DOI":"10.1109\/IISWC.2014.6983039"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"L. Wang S. Baxter and J. D. Owens. 2015. Fast Parallel Suffix Array on the GPU. In Parallel Processing: Int'l European Conf. on Parallel and Distributed Computing (Euro-Par). Springer Berlin Heidelberg.  L. Wang S. Baxter and J. D. Owens. 2015. Fast Parallel Suffix Array on the GPU. In Parallel Processing: Int'l European Conf. on Parallel and Distributed Computing (Euro-Par) . Springer Berlin Heidelberg.","DOI":"10.1007\/978-3-662-48096-0_44"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2544137.2544166"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"H. Wu D. Li and M. Becchi. 2016. Compiler-Assisted Workload Consolidation for Efficient Dynamic Parallelism on GPU. In IEEE Int'l Parallel & Distributed Processing Symp. (IPDPS).  H. Wu D. Li and M. Becchi. 2016. Compiler-Assisted Workload Consolidation for Efficient Dynamic Parallelism on GPU. In IEEE Int'l Parallel & Distributed Processing Symp. (IPDPS) .","DOI":"10.1109\/IPDPS.2016.98"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442539"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/2555243.2555254"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536206.2536210"},{"key":"e_1_3_2_1_50_1","volume-title":"cuBLASTP: Fine-Grained Parallelization of Protein Sequence Search on CPU+GPU","author":"Zhang J.","year":"2016","unstructured":"J. Zhang , H. Wang , and W.-c. Feng . 2016. cuBLASTP: Fine-Grained Parallelization of Protein Sequence Search on CPU+GPU . IEEE\/ACM Trans. on Computational Biology and Bioinformatics (TCBB) ( 2016 ). J. Zhang, H. Wang, and W.-c. Feng. 2016. cuBLASTP: Fine-Grained Parallelization of Protein Sequence Search on CPU+GPU. IEEE\/ACM Trans. on Computational Biology and Bioinformatics (TCBB) (2016)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.14778\/2809974.2809984"}],"event":{"name":"ICS '17: 2017 International Conference on Supercomputing","location":"Chicago Illinois","acronym":"ICS '17","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3079079.3079105","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3079079.3079105","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3079079.3079105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T03:03:25Z","timestamp":1750215805000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3079079.3079105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,6,14]]},"references-count":51,"alternative-id":["10.1145\/3079079.3079105","10.1145\/3079079"],"URL":"https:\/\/doi.org\/10.1145\/3079079.3079105","relation":{},"subject":[],"published":{"date-parts":[[2017,6,14]]},"assertion":[{"value":"2017-06-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}