{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T07:07:29Z","timestamp":1767856049079,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2014,8,24]],"date-time":"2014-08-24T00:00:00Z","timestamp":1408838400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003621","name":"Ministry of Science, ICT and Future Planning","doi-asserted-by":"publisher","award":["2013R1A3A2003664"],"award-info":[{"award-number":["2013R1A3A2003664"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2013R1A3A2003664"],"award-info":[{"award-number":["2013R1A3A2003664"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2014,8,24]]},"DOI":"10.1145\/2628071.2628108","type":"proceedings-article","created":{"date-parts":[[2014,8,21]],"date-time":"2014-08-21T12:19:23Z","timestamp":1408623563000},"page":"127-138","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Versatile and scalable parallel histogram construction"],"prefix":"10.1145","author":[{"given":"Wookeun","family":"Jung","sequence":"first","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jongsoo","family":"Park","sequence":"additional","affiliation":[{"name":"Intel Corporation, Santa Clara, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaejin","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2014,8,24]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual. http:\/\/www.intel.com\/content\/dam\/doc\/manual\/64-ia-32-architectures-optimization-manual.pdf.  Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual. http:\/\/www.intel.com\/content\/dam\/doc\/manual\/64-ia-32-architectures-optimization-manual.pdf."},{"key":"e_1_3_2_1_2_1","unstructured":"Adaptive Historgram Template Library. https:\/\/github.com\/pcjung\/AHTL.  Adaptive Historgram Template Library. https:\/\/github.com\/pcjung\/AHTL."},{"key":"e_1_3_2_1_3_1","unstructured":"Intel\u00ae Xeon Phi\u2122 Coprocessor Instruction Set Architecture Reference Manual. http:\/\/software.intel.com\/sites\/default\/files\/forum\/278102\/327364001en.pdf.  Intel\u00ae Xeon Phi\u2122 Coprocessor Instruction Set Architecture Reference Manual. http:\/\/software.intel.com\/sites\/default\/files\/forum\/278102\/327364001en.pdf."},{"key":"e_1_3_2_1_4_1","unstructured":"Wikipedia:Database download. http:\/\/en.wikipedia.org\/wiki\/Wikipedia:Database_download.  Wikipedia:Database download. http:\/\/en.wikipedia.org\/wiki\/Wikipedia:Database_download."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367533"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2005.30"},{"key":"e_1_3_2_1_7_1","volume-title":"Compilers: principles, techniques, & tools","author":"Aho A. V.","year":"2007","unstructured":"A. V. Aho , M. S. Lam , R. Sethi , and J. D. Ullman . Compilers: principles, techniques, & tools , volume 1009 . Pearson\/Addison Wesley , 2007 . A. V. Aho, M. S. Lam, R. Sethi, and J. D. Ullman. Compilers: principles, techniques, & tools, volume 1009. Pearson\/Addison Wesley, 2007."},{"key":"e_1_3_2_1_8_1","volume-title":"Digital Image Processing: Principles and Applications","author":"Baxes G. A.","year":"1994","unstructured":"G. A. Baxes . Digital Image Processing: Principles and Applications . Wiley , 1994 . G. A. Baxes. Digital Image Processing: Principles and Applications. Wiley, 1994."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1009213286"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/InPar.2012.6339589"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/191839.191886"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/2015039.2015535"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454152"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.113"},{"key":"e_1_3_2_1_15_1","volume-title":"R: A language for data analysis and graphics. Journal of computational and graphical statistics, 5(3)","author":"Ihaka R.","year":"1996","unstructured":"R. Ihaka and R. Gentleman . R: A language for data analysis and graphics. Journal of computational and graphical statistics, 5(3) , 1996 . R. Ihaka and R. Gentleman. R: A language for data analysis and graphics. Journal of computational and graphical statistics, 5(3), 1996."},{"key":"e_1_3_2_1_16_1","unstructured":"P. Kankowski. Hash functions: An empirical comparison. http:\/\/\/www.strchr.com\/hash_functions.  P. Kankowski. Hash functions: An empirical comparison. http:\/\/\/www.strchr.com\/hash_functions."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807206"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.14778\/1687553.1687564"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213965"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2008.38"},{"key":"e_1_3_2_1_21_1","volume-title":"Scale-Out Processors. In International Symposium on Computer Architecture (ISCA)","author":"Lofti-Kamran P.","year":"2012","unstructured":"P. Lofti-Kamran , B. Grot , M. Ferdman , S. Volos , O. Kocberber , J. Picorel , A. Adileh , D. Jevdjic , S. Idgunji , E. Ozer , and B. Falsafi . Scale-Out Processors. In International Symposium on Computer Architecture (ISCA) , 2012 . P. Lofti-Kamran, B. Grot, M. Ferdman, S. Volos, O. Kocberber, J. Picorel, A. Adileh, D. Jevdjic, S. Idgunji, E. Ozer, and B. Falsafi. Scale-Out Processors. In International Symposium on Computer Architecture (ISCA), 2012."},{"key":"e_1_3_2_1_22_1","volume-title":"Efficient Backprojection-based Synthetic Aperture Radar Computation with Many-core Processors. In International Conference for High Performance Computing, Networking, Storage and Analysis (SC)","author":"Park J.","year":"2012","unstructured":"J. Park , P. T. P. Tang , M. Smelyanskiy , D. Kim , and T. Benson . Efficient Backprojection-based Synthetic Aperture Radar Computation with Many-core Processors. In International Conference for High Performance Computing, Networking, Storage and Analysis (SC) , 2012 . J. Park, P. T. P. Tang, M. Smelyanskiy, D. Kim, and T. Benson. Efficient Backprojection-based Synthetic Aperture Radar Computation with Many-core Processors. In International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2012."},{"key":"e_1_3_2_1_23_1","unstructured":"V. Pdlozhnyuk. Histogram calculation in CUDA. http:\/\/docs.nvidia.com\/cuda\/samples\/3_Imaging\/histogram\/doc\/histogram.pdf.  V. Pdlozhnyuk. Histogram calculation in CUDA. http:\/\/docs.nvidia.com\/cuda\/samples\/3_Imaging\/histogram\/doc\/histogram.pdf."},{"key":"e_1_3_2_1_24_1","article-title":"Contributions to the Mathematical Theory of Evolution","volume":"186","author":"Pearson K.","year":"1895","unstructured":"K. Pearson . Contributions to the Mathematical Theory of Evolution . II. Skew Variation in Homogeneous Material. Philosophical Transactions of the Royal Society of London , 186 , 1895 . K. Pearson. Contributions to the Mathematical Theory of Evolution. II. Skew Variation in Homogeneous Material. Philosophical Transactions of the Royal Society of London, 186, 1895.","journal-title":"II. Skew Variation in Homogeneous Material. Philosophical Transactions of the Royal Society of London"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/233269.233342"},{"key":"e_1_3_2_1_26_1","unstructured":"T. Rantalaiho. Generalized Histograms for CUDA-capable GPUs. https:\/\/github.com\/trantalaiho\/Cuda-Histogram.  T. Rantalaiho. Generalized Histograms for CUDA-capable GPUs. https:\/\/github.com\/trantalaiho\/Cuda-Histogram."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/71.752782"},{"key":"e_1_3_2_1_28_1","unstructured":"J. Reinders. Intel Threading Building Blocks: Outfitting C++ for Multi-core Processor Parallelism.   J. Reinders. Intel Threading Building Blocks: Outfitting C++ for Multi-core Processor Parallelism."},{"key":"e_1_3_2_1_29_1","unstructured":"J. Reinders. Transactional Synchronization in Haswell. http:\/\/software.intel.com\/en-us\/blogs\/2012\/02\/07\/transactional-synchronization-in-haswell.  J. Reinders. Transactional Synchronization in Haswell. http:\/\/software.intel.com\/en-us\/blogs\/2012\/02\/07\/transactional-synchronization-in-haswell."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304620"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807207"},{"key":"e_1_3_2_1_32_1","volume-title":"Efficient Histogram Algorithms for NVIDIA CUDA Compatible Devices. In International Conference on Signal Processing and Communication Systems","author":"Shams R.","year":"2007","unstructured":"R. Shams and R. A. Kennedy . Efficient Histogram Algorithms for NVIDIA CUDA Compatible Devices. In International Conference on Signal Processing and Communication Systems , 2007 . R. Shams and R. A. Kennedy. Efficient Histogram Algorithms for NVIDIA CUDA Compatible Devices. In International Conference on Signal Processing and Communication Systems, 2007."},{"key":"e_1_3_2_1_33_1","volume-title":"Using the Intel Integrated Performance Primitives","author":"Taylor S.","year":"2007","unstructured":"S. Taylor . Optimizing Applications for Multi-Core Processors , Using the Intel Integrated Performance Primitives . 2007 . S. Taylor. Optimizing Applications for Multi-Core Processors, Using the Intel Integrated Performance Primitives. 2007."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.5555\/1316689.1316712"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306783"}],"event":{"name":"PACT '14: International Conference on Parallel Architectures and Compilation","location":"Edmonton AB Canada","acronym":"PACT '14","sponsor":["IFIP WG 10.3 IFIP WG 10.3","SIGARCH ACM Special Interest Group on Computer Architecture","IEEE CS TCPP IEEE Computer Society Technical Committee on Parallel Processing","IEEE CS TCAA IEEE CS technical committee on architectural acoustics"]},"container-title":["Proceedings of the 23rd international conference on Parallel architectures and compilation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2628071.2628108","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2628071.2628108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T07:19:38Z","timestamp":1750231178000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2628071.2628108"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,8,24]]},"references-count":35,"alternative-id":["10.1145\/2628071.2628108","10.1145\/2628071"],"URL":"https:\/\/doi.org\/10.1145\/2628071.2628108","relation":{},"subject":[],"published":{"date-parts":[[2014,8,24]]},"assertion":[{"value":"2014-08-24","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}