{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T03:41:48Z","timestamp":1752982908607,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031226762"},{"type":"electronic","value":"9783031226779"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-22677-9_36","type":"book-chapter","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T09:04:32Z","timestamp":1673341472000},"page":"676-690","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimizing Yinyang K-Means Algorithm on\u00a0ARMv8 Many-Core CPUs"],"prefix":"10.1007","author":[{"given":"Tianyang","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Qinglin","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shangfei","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Ruochen","family":"Hao","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,1,11]]},"reference":[{"key":"36_CR1","unstructured":"Arthur, D., Vassilvitskii, S.: k-means++: the advantages of careful seeding. Technical report, Stanford (2006)"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Bhimani, J., Leeser, M., Mi, N.: Accelerating k-means clustering with parallel implementations and GPU computing. In: 2015 IEEE High Performance Extreme Computing Conference (HPEC), pp. 1\u20136. IEEE (2015)","DOI":"10.1109\/HPEC.2015.7322467"},{"key":"36_CR3","doi-asserted-by":"publisher","first-page":"41071","DOI":"10.1109\/ACCESS.2020.2976900","volume":"8","author":"LA Dias","year":"2020","unstructured":"Dias, L.A., Ferreira, J.C., Fernandes, M.A.: Parallel implementation of k-means algorithm on FPGA. IEEE Access 8, 41071\u201341084 (2020)","journal-title":"IEEE Access"},{"key":"36_CR4","unstructured":"Ding, Y., Zhao, Y., Shen, X., Musuvathi, M., Mytkowicz, T.: Yinyang k-means: a drop-in replacement of the classic k-means with consistent speedup. In: International Conference on Machine Learning, pp. 579\u2013587. PMLR (2015)"},{"key":"36_CR5","unstructured":"Drake, J., Hamerly, G.: Accelerated k-means with adaptive distance bounds. In: 5th NIPS Workshop on Optimization for Machine Learning, vol. 8 (2012)"},{"key":"36_CR6","unstructured":"Dua, D., Graff, C.: UCI machine learning repository (2017). http:\/\/archive.ics.uci.edu\/ml"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Hamerly, G.: Making k-means even faster. In: Proceedings of the 2010 SIAM International Conference on Data Mining, pp. 130\u2013140. SIAM (2010)","DOI":"10.1137\/1.9781611972801.12"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Huang, X., Wang, Q., Lu, S., Hao, R., Mei, S., Liu, J.: Evaluating FFT-based algorithms for strided convolutions on ARMv8 architectures. Perform. Eval. 152, 102248 (2021). https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0166531621000651","DOI":"10.1016\/j.peva.2021.102248"},{"key":"36_CR9","doi-asserted-by":"crossref","unstructured":"Huang, X., Wang, Q., Lu, S., Hao, R., Mei, S., Liu, J.: NUMA-aware FFT-based convolution on ARMv8 many-core CPUs. In: 2021 IEEE International Conference on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA\/BDCloud\/SocialCom\/SustainCom), pp. 1019\u20131026. IEEE (2021)","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00142"},{"key":"36_CR10","doi-asserted-by":"crossref","unstructured":"Jin, C., Wang, Q., Zhao, Y., Dou, Y.: Parallelization of fast Monte Carlo dose calculation for radiotherapy treatment planning on the ARMv8 architecture. In: 2021 11th International Conference on Information Science and Technology (ICIST), pp. 261\u2013265 (2021)","DOI":"10.1109\/ICIST52614.2021.9440606"},{"key":"36_CR11","unstructured":"Kaggle: Kaggle datasets. https:\/\/www.kaggle.com\/datasets. Accessed 18 Apr 2022"},{"issue":"7","key":"36_CR12","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1109\/TPAMI.2002.1017616","volume":"24","author":"T Kanungo","year":"2002","unstructured":"Kanungo, T., Mount, D.M., Netanyahu, N.S., Piatko, C.D., Silverman, R., Wu, A.Y.: An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 881\u2013892 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"36_CR13","doi-asserted-by":"publisher","first-page":"1602","DOI":"10.1016\/j.procs.2011.04.173","volume":"4","author":"J Kumar","year":"2011","unstructured":"Kumar, J., Mills, R.T., Hoffman, F.M., Hargrove, W.W.: Parallel k-means clustering for quantitative ecoregion delineation using large data sets. Procedia Comput. Sci. 4, 1602\u20131611 (2011)","journal-title":"Procedia Comput. Sci."},{"key":"36_CR14","doi-asserted-by":"publisher","first-page":"42280","DOI":"10.1109\/ACCESS.2019.2907885","volume":"7","author":"W Kwedlo","year":"2019","unstructured":"Kwedlo, W., Czochanski, P.J.: A hybrid MPI\/OpenMP parallelization of $$ k $$-means algorithms accelerated using the triangle inequality. IEEE Access 7, 42280\u201342297 (2019)","journal-title":"IEEE Access"},{"key":"36_CR15","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: AutoFFT: a template-based FFT codes auto-generation framework for arm and x86 CPUs. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2019. Association for Computing Machinery, New York, NY, USA (2019). https:\/\/doi.org\/10.1145\/3295500.3356138","DOI":"10.1145\/3295500.3356138"},{"issue":"2","key":"36_CR16","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd, S.: Least squares quantization in PCM. IEEE Trans. Inf. Theory 28(2), 129\u2013137 (1982)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Matsuoka, S.: Fugaku and A64FX: the first exascale supercomputer and its innovative arm CPU. In: 2021 Symposium on VLSI Circuits, pp. 1\u20133 (2021)","DOI":"10.23919\/VLSICircuits52068.2021.9492415"},{"key":"36_CR18","unstructured":"Newling, J., Fleuret, F.: Fast k-means with accurate bounds. In: International Conference on Machine Learning, pp. 936\u2013944. PMLR (2016)"},{"key":"36_CR19","doi-asserted-by":"crossref","unstructured":"Pelleg, D., Moore, A.: Accelerating exact k-means algorithms with geometric reasoning. In: Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 277\u2013281 (1999)","DOI":"10.1145\/312129.312248"},{"key":"36_CR20","unstructured":"Rajovic, N., et al.: The mont-blanc prototype: an alternative approach for high-performance computing systems (2016)"},{"key":"36_CR21","unstructured":"Taylor: Scalar yinyang kmeans. https:\/\/github.com\/ctaylor389\/k_means_yinyang_gpu. Accessed 18 Apr 2022"},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"Taylor, C., Gowanlock, M.: Accelerating the Yinyang k-means algorithm using the GPU. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE), pp. 1835\u20131840. IEEE (2021)","DOI":"10.1109\/ICDE51399.2021.00163"},{"key":"36_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1007\/978-3-030-57675-2_16","volume-title":"Euro-Par 2020: Parallel Processing","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Li, D., Huang, X., Shen, S., Mei, S., Liu, J.: Optimizing FFT-based convolution on ARMv8 multi-core CPUs. In: Malawski, M., Rzadca, K. (eds.) Euro-Par 2020. LNCS, vol. 12247, pp. 248\u2013262. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-57675-2_16"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Q., Mei, S., Liu, J., Gong, C.: Parallel convolution algorithm using implicit matrix multiplication on multi-core CPUs. In: 2019 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137. IEEE (2019)","DOI":"10.1109\/IJCNN.2019.8852012"},{"key":"36_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/978-3-642-45293-2_21","volume-title":"Advanced Parallel Processing Technologies","author":"F Wu","year":"2013","unstructured":"Wu, F., Wu, Q., Tan, Y., Wei, L., Shao, L., Gao, L.: A vectorized K-means algorithm for Intel many integrated core architecture. In: Wu, C., Cohen, A. (eds.) APPT 2013. LNCS, vol. 8299, pp. 277\u2013294. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-45293-2_21"},{"key":"36_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-030-18645-6_6","volume-title":"Supercomputing Frontiers","author":"X You","year":"2019","unstructured":"You, X., Yang, H., Luan, Z., Liu, Y., Qian, D.: Performance evaluation and analysis of linear algebra kernels in the prototype Tianhe-3 cluster. In: Abramson, D., de Supinski, B.R. (eds.) SCFA 2019. LNCS, vol. 11416, pp. 86\u2013105. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-18645-6_6"},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"Zechner, M., Granitzer, M.: Accelerating k-means on the graphics processor via CUDA. In: 2009 First International Conference on Intensive Applications and Services, pp. 7\u201315. IEEE (2009)","DOI":"10.1109\/INTENSIVE.2009.19"},{"key":"36_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"674","DOI":"10.1007\/978-3-642-10665-1_71","volume-title":"Cloud Computing","author":"W Zhao","year":"2009","unstructured":"Zhao, W., Ma, H., He, Q.: Parallel K-means clustering based on MapReduce. In: Jaatun, M.G., Zhao, G., Rong, C. (eds.) CloudCom 2009. LNCS, vol. 5931, pp. 674\u2013679. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-10665-1_71"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22677-9_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T09:12:44Z","timestamp":1673341964000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22677-9_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031226762","9783031226779"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22677-9_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"11 January 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Copenhagen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Denmark","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"91","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"33","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"10","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"36% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}