{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:53:35Z","timestamp":1768074815202,"version":"3.49.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T00:00:00Z","timestamp":1687478400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T00:00:00Z","timestamp":1687478400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4500303"],"award-info":[{"award-number":["2022YFB4500303"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62072198"],"award-info":[{"award-number":["62072198"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61825202"],"award-info":[{"award-number":["61825202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61929103"],"award-info":[{"award-number":["61929103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. HPC"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1007\/s42514-023-00158-8","type":"journal-article","created":{"date-parts":[[2023,6,23]],"date-time":"2023-06-23T20:07:30Z","timestamp":1687550850000},"page":"192-205","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["FPGA-based acceleration architecture for Apache Spark operators"],"prefix":"10.1007","volume":"6","author":[{"given":"Yuanwei","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4290-1408","authenticated-orcid":false,"given":"Haikun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Liao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,6,23]]},"reference":[{"key":"158_CR1","volume-title":"Parallel Sorting Algorithms","author":"SG Akl","year":"2014","unstructured":"Akl, S.G.: Parallel Sorting Algorithms, vol. 12. Academic Press, Oklahoma (2014)"},{"key":"158_CR2","unstructured":"Alveo U200 and U250 Data Center Accelerator Cards Data Sheet. https:\/\/docs.xilinx.com\/r\/en-US\/ds962-u200-u250\/Summary (2022)"},{"key":"158_CR3","unstructured":"AMD Xilinx Company. https:\/\/docs.xilinx.com\/r\/en-US\/ug1399-vitis-hls\/pragma-HLS-array_reshape (2022)"},{"key":"158_CR4","unstructured":"Apache Spark Company. https:\/\/spark.apache.org\/mllib\/ (2022)"},{"issue":"4","key":"158_CR5","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1145\/358841.358850","volume":"23","author":"JL Bentley","year":"1980","unstructured":"Bentley, J.L.: Multidimensional divide-and-conquer. Commun. ACM 23(4), 214\u2013229 (1980)","journal-title":"Commun. ACM"},{"issue":"2","key":"158_CR6","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/54.500200","volume":"13","author":"S Brown","year":"1996","unstructured":"Brown, S., Rose, J.: Fpga and cpld architectures: A tutorial. IEEE Des. Test Comput. 13(2), 42\u201357 (1996)","journal-title":"IEEE Des. Test Comput."},{"key":"158_CR8","doi-asserted-by":"crossref","unstructured":"Chen, R., Siriyal, S., Prasanna, V.: Energy and memory efficient mapping of bitonic sorting on fpga. In: Proceedings of the 2015 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 240\u2013249 (2015)","DOI":"10.1145\/2684746.2689068"},{"key":"158_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y.-T., Cong, J., Fang, Z., Lei, J., Wei, P.: When spark meets fpgas: a case study for next-generation dna sequencing acceleration. In: Proceeding of the 8th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 16) (2016)","DOI":"10.1109\/FCCM.2016.18"},{"key":"158_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-020-2976-5","volume":"65","author":"B Chen","year":"2022","unstructured":"Chen, B., Fu, H., Luk, W., Yang, G.: A fully-customized dataflow engine for 3d earthquake simulation with a complex topography. Sci. China Inf. Sci. 65, 1\u201316 (2022)","journal-title":"Sci. China Inf. Sci."},{"key":"158_CR10","doi-asserted-by":"crossref","unstructured":"Cilardo, A., Gallo, L.: Interplay of loop unrolling and multidimensional memory partitioning in hls. In: Proceedings of the 2015 Design, Automation Test in Europe Conference Exhibition (DATE), pp. 163\u2013168. IEEE (2015)","DOI":"10.7873\/DATE.2015.0798"},{"key":"158_CR11","doi-asserted-by":"crossref","unstructured":"Dai, G., Huang, T., Chi, Y., Xu, N., Wang, Y., Yang, H.: Foregraph: exploring large-scale graph processing on multi-fpga architecture. In: Proceeding of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 217\u2013226 (2017)","DOI":"10.1145\/3020078.3021739"},{"key":"158_CR12","unstructured":"Francesco Nigro. https:\/\/netty.io (2022)"},{"issue":"2","key":"158_CR13","doi-asserted-by":"publisher","first-page":"4222","DOI":"10.1002\/cpe.4222","volume":"31","author":"E Ghasemi","year":"2019","unstructured":"Ghasemi, E., Chow, P.: Accelerating apache spark with fpgas. Concurr. Comput. Practice Exp. 31(2), 4222 (2019)","journal-title":"Concurr. Comput. Practice Exp."},{"key":"158_CR14","doi-asserted-by":"crossref","unstructured":"Guo, L., Maidee, P., Zhou, Y., Lavin, C., Wang, J., Chi, Y., Qiao, W., Kaviani, A., Zhang, Z., Cong, J.: Rapidstream: parallel physical implementation of fpga hls designs. In: Proceedings of the 2022 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 1\u201312 (2022)","DOI":"10.1145\/3490422.3502361"},{"issue":"5","key":"158_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-2127-0","volume":"17","author":"J Guo","year":"2023","unstructured":"Guo, J., Zhang, L., Romero Hung, J., Li, C., Zhao, J., Guo, M.: Fpga sharing in the cloud: a comprehensive analysis. Front. Comput. Sci. 17(5), 175106 (2023)","journal-title":"Front. Comput. Sci."},{"key":"158_CR16","unstructured":"He, Z., Korolija, D., Alonso, G.: https:\/\/github.com\/fpgasystems\/Vitis_with_100Gbps_TCP-IP (2022)"},{"key":"158_CR17","doi-asserted-by":"crossref","unstructured":"Hematian, A., Chuprat, S., Manaf, A.A., Parsazadeh, N.: Zero-delay fpga-based odd-even sorting network. In: Proceeding of the 2013 IEEE Symposium on Computers & Informatics (ISCI), pp. 128\u2013131. IEEE (2013)","DOI":"10.1109\/ISCI.2013.6612389"},{"key":"158_CR19","doi-asserted-by":"crossref","unstructured":"Hussain, H.M., Benkrid, K., Seker, H., Erdogan, A.T.: Fpga implementation of k-means algorithm for bioinformatics application: an accelerated approach to clustering microarray data. In: Proceeding of the 2011 NASA\/ESA Conference on Adaptive Hardware and Systems (AHS), pp. 248\u2013255 (2011a)","DOI":"10.1109\/AHS.2011.5963944"},{"key":"158_CR18","doi-asserted-by":"crossref","unstructured":"Hussain, H.M., Benkrid, K., Erdogan, A.T., Seker, H.: Highly parameterized k-means clustering on fpgas: comparative results with gpps and gpus. In: Proceeding of the 2011 international conference on reconfigurable computing and FPGAs, pp. 475\u2013480. IEEE (2011b)","DOI":"10.1109\/ReConFig.2011.49"},{"key":"158_CR20","unstructured":"Karimi, K., Dickson, N.G., Hamze, F.: A performance comparison of cuda and opencl. arXiv preprint arXiv:1005.2581 (2010)"},{"key":"158_CR21","doi-asserted-by":"crossref","unstructured":"Kathail, V.: Xilinx vitis unified software platform. In: Proceedings of the 2020 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays, pp. 173\u2013174 (2020)","DOI":"10.1145\/3373087.3375887"},{"key":"158_CR22","doi-asserted-by":"crossref","unstructured":"Kuon, I., Tessier, R., Rose, J., et al.: Fpga architecture: survey and challenges. Found. Trends\u00ae Electron. Des. Autom. 2(2), 135\u2013253 (2008)","DOI":"10.1561\/1000000005"},{"key":"158_CR23","unstructured":"Li, P., Luo, Y., Zhang, N., Cao, Y.: Heterospark: a heterogeneous cpu\/gpu spark platform for machine learning algorithms. In: Proceeding of the 2015 IEEE International Conference on Networking, Architecture and Storage (NAS), pp. 347\u2013348. IEEE, (2015)"},{"key":"158_CR24","doi-asserted-by":"crossref","unstructured":"Lin, Z., Lo, C., Chow, P.: K-means implementation on fpga for high-dimensional data using triangle inequality. In: Proceeding of the 22nd International Conference on Field Programmable Logic and Applications (FPL), pp. 437\u2013442. IEEE (2012)","DOI":"10.1109\/FPL.2012.6339141"},{"key":"158_CR25","doi-asserted-by":"crossref","unstructured":"Lipu, A.R., Amin, R., Mondal, M.N.I., Al\u00a0Mamun, M.: Exploiting parallelism for faster implementation of bubble sort algorithm using fpga. In: Proceeding of the 2016 2nd International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE), pp. 1\u20134. IEEE (2016)","DOI":"10.1109\/ICECTE.2016.7879576"},{"key":"158_CR26","doi-asserted-by":"crossref","unstructured":"Liu, J., Wickerson, J., Constantinides, G.A.: Loop splitting for efficient pipelining in high-level synthesis. In: Proceedings of the 2016 IEEE 24th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 72\u201379. IEEE (2016)","DOI":"10.1109\/FCCM.2016.27"},{"key":"158_CR27","doi-asserted-by":"crossref","unstructured":"Lu, X., Rahman, M.W.U., Islam, N., Shankar, D., Panda, D.K.: Accelerating spark with rdma for big data processing: early experiences. In: Proceeding of the 2014 IEEE 22nd Annual Symposium on High-Performance Interconnects, pp. 9\u201316. IEEE (2014)","DOI":"10.1109\/HOTI.2014.15"},{"key":"158_CR28","doi-asserted-by":"crossref","unstructured":"Ma, J., Zuo, G., Loughlin, K., Cheng, X., Liu, Y., Eneyew, A.M., Qi, Z., Kasikci, B.: A hypervisor for shared-memory fpga platforms. In: Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 827\u2013844 (2020)","DOI":"10.1145\/3373376.3378482"},{"issue":"7","key":"158_CR29","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1109\/TNS.2019.2904118","volume":"66","author":"W Mansour","year":"2019","unstructured":"Mansour, W., Janvier, N., Fajardo, P.: Fpga implementation of rdma-based data acquisition system over 100-gb ethernet. IEEE Trans. Nuclear Sci. 66(7), 1138\u20131143 (2019)","journal-title":"IEEE Trans. Nuclear Sci."},{"key":"158_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00778-011-0232-z","volume":"21","author":"R Mueller","year":"2012","unstructured":"Mueller, R., Teubner, J., Alonso, G.: Sorting networks on fpgas. VLDB J. 21, 1\u201323 (2012)","journal-title":"VLDB J."},{"key":"158_CR31","doi-asserted-by":"crossref","unstructured":"Recio, R., Metzler, B., Culley, P., Hilland, J., Garcia, D.: A remote direct memory access protocol specification. Technical report (2007)","DOI":"10.17487\/rfc5040"},{"key":"158_CR32","doi-asserted-by":"crossref","unstructured":"Ruiz, M., Sidler, D., Sutter, G., Alonso, G., L\u00f3pez-Buedo, S.: Limago: an fpga-based open-source 100 gbe tcp\/ip stack. In: Proceeding of the 2019 29th International Conference on Field Programmable Logic and Applications (FPL), pp. 286\u2013292. IEEE (2019)","DOI":"10.1109\/FPL.2019.00053"},{"issue":"4","key":"158_CR33","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1109\/TCAD.2016.2597232","volume":"36","author":"A Sengupta","year":"2016","unstructured":"Sengupta, A., Bhadauria, S., Mohanty, S.P.: Tl-hls: methodology for low cost hardware trojan security aware scheduling with optimal loop unrolling factor during high level synthesis. IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. 36(4), 655\u2013668 (2016)","journal-title":"IEEE Trans. Comput. Aided Des. Integr. Circuits Syst."},{"key":"158_CR34","unstructured":"Sidler, D., He, Z.: Mario Daniel Ruiz Noguera and Xilinx company. https:\/\/github.com\/hcxxstl\/Vitis_RoCE (2022)"},{"key":"158_CR35","doi-asserted-by":"crossref","unstructured":"Winterstein, F., Bayliss, S., Constantinides, G.A.: High-level synthesis of dynamic data structures: a case study using vivado hls. In: Proceeding of the 2013 International conference on field-programmable technology (FPT), pp. 362\u2013365. IEEE (2013)","DOI":"10.1109\/FPT.2013.6718388"},{"key":"158_CR36","unstructured":"Xilinx Runtime Library (XRT). https:\/\/www.xilinx.com\/products\/design-tools\/vitis\/xrt.html (2022)"},{"key":"158_CR38","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: cluster computing with working sets. In: Proceeding of the 2nd USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 10) (2010)"},{"key":"158_CR37","unstructured":"Zaharia, M., Chowdhury, M., Das, T., Dave, A., Ma, J., McCauly, M., Franklin, M.J., Shenker, S., Stoica, I.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Proceeding of the 9th USENIX Symposium on Networked Systems Design and Implementation (NSDI 12), pp. 15\u201328 (2012)"},{"issue":"11","key":"158_CR39","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/2934664","volume":"59","author":"M Zaharia","year":"2016","unstructured":"Zaharia, M., Xin, R.S., Wendell, P., Das, T., Armbrust, M., Dave, A., Meng, X., Rosen, J., Venkataraman, S., Franklin, M.J., et al.: Apache spark: a unified engine for big data processing. Commun. ACM 59(11), 56\u201365 (2016)","journal-title":"Commun. ACM"},{"issue":"3","key":"158_CR40","doi-asserted-by":"publisher","first-page":"905","DOI":"10.1109\/TPDS.2016.2586074","volume":"28","author":"F Zhang","year":"2016","unstructured":"Zhang, F., Zhai, J., He, B., Zhang, S., Chen, W.: Understanding co-running behaviors on integrated cpu\/gpu architectures. IEEE Trans. Parallel Distrib. Syst. 28(3), 905\u2013918 (2016)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"158_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, S., Chelmis, C., Prasanna, V.K.: Optimizing memory performance for fpga implementation of pagerank. In: Proceeding of the 2015 International Conference on ReConFigurable Computing and FPGAs (ReConFig), pp. 1\u20136. IEEE (2015)","DOI":"10.1109\/ReConFig.2015.7393332"}],"container-title":["CCF Transactions on High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-023-00158-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42514-023-00158-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42514-023-00158-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T09:04:01Z","timestamp":1715677441000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42514-023-00158-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,23]]},"references-count":41,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["158"],"URL":"https:\/\/doi.org\/10.1007\/s42514-023-00158-8","relation":{},"ISSN":["2524-4922","2524-4930"],"issn-type":[{"value":"2524-4922","type":"print"},{"value":"2524-4930","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,23]]},"assertion":[{"value":"21 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}