{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T08:16:04Z","timestamp":1770711364151,"version":"3.49.0"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T00:00:00Z","timestamp":1705622400000},"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":["CCF Trans. HPC"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s42514-023-00175-7","type":"journal-article","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T13:01:48Z","timestamp":1705669308000},"page":"503-518","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["thSORT: an efficient parallel sorting algorithm on multi-core DSPs"],"prefix":"10.1007","volume":"6","author":[{"given":"Mouzhi","family":"Yang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8364-9793","authenticated-orcid":false,"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jianbin","family":"Fang","sequence":"additional","affiliation":[]},{"given":"Weifeng","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Chun","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,1,19]]},"reference":[{"key":"175_CR2","doi-asserted-by":"crossref","unstructured":"Batcher, K.E.: Sorting networks and their applications. In: Proceedings of the April 30\u2013May 2, Spring Joint Computer Conference, AFIPS \u201968 (Spring), pp.\u00a0307\u2013314. Association for Computing Machinery, New York (1968)","DOI":"10.1145\/1468075.1468121"},{"issue":"11","key":"175_CR3","doi-asserted-by":"publisher","first-page":"3100","DOI":"10.1109\/TPDS.2017.2705128","volume":"28","author":"R Chen","year":"2017","unstructured":"Chen, R., Prasanna, V.K.: Computer generation of high throughput and memory efficient sorting designs on FPGA. IEEE Trans. Parallel Distrib. Syst. 28(11), 3100\u20133113 (2017)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"175_CR4","doi-asserted-by":"publisher","first-page":"1313","DOI":"10.14778\/1454159.1454171","volume":"2","author":"J Chhugani","year":"2008","unstructured":"Chhugani, J., Nguyen, A.D., Lee, V.W., Macy, W., Hagog, M., Chen, Y.-K., Baransi, A., Kumar, S., Dubey, P.: Efficient implementation of sorting on multi-core simd cpu architecture. Proc. VLDB Endow. 2, 1313\u20131324 (2008)","journal-title":"Proc. VLDB Endow."},{"issue":"4","key":"175_CR5","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1631\/FITEE.2200359","volume":"24","author":"J Fang","year":"2023","unstructured":"Fang, J., Zhang, P., Huang, C., Tang, T., Lu, K., Wang, R., Wang, Z.: Programming bare-metal accelerators with heterogeneous threading models: a case study of matrix-3000. Front. Inf. Technol. Electron. Eng. 24(4), 509\u2013520 (2023)","journal-title":"Front. Inf. Technol. Electron. Eng."},{"issue":"3","key":"175_CR7","doi-asserted-by":"publisher","first-page":"10-es","DOI":"10.1145\/1132960.1132964","volume":"38","author":"G Graefe","year":"2006","unstructured":"Graefe, G.: Implementing sorting in database systems. ACM Comput. Surv. 38(3), 10-es (2006)","journal-title":"ACM Comput. Surv."},{"key":"175_CR8","doi-asserted-by":"crossref","unstructured":"Green, O., McColl, R., Bader, D.A.: Gpu merge path: a gpu merging algorithm. In: Proceedings of the 26th ACM International Conference on Supercomputing (ICS), pp. 331\u2013340. Association for Computing Machinery, New York (2012)","DOI":"10.1145\/2304576.2304621"},{"issue":"1","key":"175_CR9","first-page":"83","volume":"59","author":"S Gueron","year":"2016","unstructured":"Gueron, S., Krasnov, V.: Fast quicksort implementation using avx instructions. Comput. J. 59(1), 83\u201390 (2016)","journal-title":"Comput. J."},{"key":"175_CR10","doi-asserted-by":"crossref","unstructured":"Guo, C., Chen, H., Li, C., Wu, T.: A memory access reduced sort on multi-core gpu. In: 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp. 586\u2013593. Exeter, UK (2018)","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2018.00108"},{"issue":"5","key":"175_CR12","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1109\/TPDS.2018.2789903","volume":"29","author":"K Hou","year":"2018","unstructured":"Hou, K., Wang, H., Feng, W.-C.: A framework for the automatic vectorization of parallel sort on x86-based processors. IEEE Trans. Parallel Distrib. Syst. 29(5), 958\u2013972 (2018)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"175_CR13","doi-asserted-by":"crossref","unstructured":"Jun, S.-W., Xu, S., Arvind.: Terabyte sort on fpga-accelerated flash storage. In: 2017 IEEE 25th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 17\u201324. Napa, CA, (2017)","DOI":"10.1109\/FCCM.2017.53"},{"issue":"1","key":"175_CR15","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/TC.1979.1675216","volume":"28","author":"S Nassimi","year":"1979","unstructured":"Nassimi, S.: Bitonic sort on a mesh-connected parallel computer. IEEE Trans. Comput. 28(1), 2\u20137 (1979)","journal-title":"IEEE Trans. Comput."},{"issue":"7","key":"175_CR16","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1002\/cpe.1686","volume":"23","author":"H Peters","year":"2011","unstructured":"Peters, H., Schulz-Hildebrandt, O., Luttenberger, N.: Fast in-place, comparison-based sorting with cuda: a study with bitonic sort. Concurr. Comput. Pract. Exp. 23(7), 681\u2013693 (2011)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"175_CR17","doi-asserted-by":"crossref","unstructured":"Satish, N., Harris, M., Garland, M.: Designing efficient sorting algorithms for manycore gpus. In: 2009 IEEE International Symposium on Parallel & Distributed Processing, pp. 1\u201310. Rome, Italy (2009)","DOI":"10.1109\/IPDPS.2009.5161005"},{"key":"175_CR18","doi-asserted-by":"crossref","unstructured":"Stehle, E., Jacobsen, H.-A.: A memory bandwidth-efficient hybrid radix sort on gpus. In: Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD \u201917, pp. 417\u2013432. Association for Computing Machinery, New York (2017)","DOI":"10.1145\/3035918.3064043"},{"key":"175_CR19","doi-asserted-by":"crossref","unstructured":"Yin, Z., Zhang, T., M\u00fcller, A., Liu, H., Wei, Y., Schmidt, B., Liu, W.: Efficient parallel sort on avx-512-based multi-core and many-core architectures. In: 2019 IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp. 168\u2013176. Zhangjiajie, China (2019)","DOI":"10.1109\/HPCC\/SmartCity\/DSS.2019.00038"},{"key":"175_CR20","doi-asserted-by":"crossref","unstructured":"Yin, S., Wang, Q., Hao, R., Zhou, T., Mei, S., Liu, J.: Optimizing irregular-shaped matrix\u2013matrix multiplication on multi-core dsps. In: 2022 IEEE International Conference on Cluster Computing (CLUSTER), pp. 451\u2013461. Heidelberg, Germany (2022)","DOI":"10.1109\/CLUSTER51413.2022.00055"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-023-00175-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-023-00175-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-023-00175-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T07:04:50Z","timestamp":1729494290000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-023-00175-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,19]]},"references-count":16,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["175"],"URL":"https:\/\/doi.org\/10.1007\/s42514-023-00175-7","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,19]]},"assertion":[{"value":"24 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}