{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:52:51Z","timestamp":1775634771458,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584017","type":"print"},{"value":"9789819584024","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-8402-4_17","type":"book-chapter","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:14:53Z","timestamp":1775632493000},"page":"320-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Auto-CLOUDSC: An Auto-generation Framework for\u00a0Vectorization and\u00a0Optimization of\u00a0Cloud Microphysics Parameterization on\u00a0ARM CPUs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3459-7960","authenticated-orcid":false,"given":"Tun","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6365-777X","authenticated-orcid":false,"given":"Jianping","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9227-4919","authenticated-orcid":false,"given":"Yuntian","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4350-1871","authenticated-orcid":false,"given":"Yingjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8353-7000","authenticated-orcid":false,"given":"Fukang","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7437-0245","authenticated-orcid":false,"given":"Jinhui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8412-2472","authenticated-orcid":false,"given":"Juan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8665-5571","authenticated-orcid":false,"given":"Xiaoli","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,9]]},"reference":[{"key":"17_CR1","unstructured":"SVE Optimization Guide. https:\/\/developer.arm.com\/documentation\/102699\/0100\/Optimizing-with-intrinsics"},{"key":"17_CR2","unstructured":"ecmwf-ifs\/dwarf-p-cloudsc (2025). https:\/\/github.com\/ecmwf-ifs\/dwarf-p-cloudsc"},{"key":"17_CR3","unstructured":"ecmwf-ifs\/loki (2025). https:\/\/github.com\/ecmwf-ifs\/loki"},{"key":"17_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2021.100707","volume":"15","author":"A Afanasyev","year":"2021","unstructured":"Afanasyev, A., et al.: Gridtools: a framework for portable weather and climate applications. SoftwareX 15, 100707 (2021)","journal-title":"SoftwareX"},{"issue":"4","key":"17_CR5","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1145\/29873.29875","volume":"9","author":"R Allen","year":"1987","unstructured":"Allen, R., Kennedy, K.: Automatic translation of fortran programs to vector form. ACM Trans. Program. Lang. Syst. (TOPLAS) 9(4), 491\u2013542 (1987)","journal-title":"ACM Trans. Program. Lang. Syst. (TOPLAS)"},{"key":"17_CR6","doi-asserted-by":"publisher","unstructured":"Bauer, P., Dueben, P.D., Hoefler, T., Quintino, T., Schulthess, T.C., Wedi, N.P.: The digital revolution of earth-system science. Nat. Comput. Sci. 1(2), 104\u2013113 (2021). https:\/\/doi.org\/10.1038\/s43588-021-00023-0","DOI":"10.1038\/s43588-021-00023-0"},{"key":"17_CR7","unstructured":"Beazley, D.: David Beazley. http:\/\/www.dabeaz.com"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Ben-Nun, T., de\u00a0Fine\u00a0Licht, J., Ziogas, A.N., Schneider, T., Hoefler, T.: Stateful dataflow multigraphs: a data-centric model for performance portability on heterogeneous architectures. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314 (2019)","DOI":"10.1145\/3295500.3356173"},{"key":"17_CR9","unstructured":"Chandrasekaran, S., Juckeland, G.: OpenACC for Programmers: Concepts and Strategies, 1st edn. Addison-Wesley Professional (2017)"},{"issue":"3","key":"17_CR10","first-page":"51","volume":"6","author":"V Clement","year":"2019","unstructured":"Clement, V., Marti, P., Lapillonne, X., Fuhrer, O., Sawyer, W.: Automatic port to OpenACC\/OpenMP for physical parameterization in climate and weather code using the claw compiler. Supercomput. Front. Innov. 6(3), 51\u201363 (2019)","journal-title":"Supercomput. Front. Innov."},{"issue":"6","key":"17_CR11","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1145\/223428.207162","volume":"30","author":"S Coleman","year":"1995","unstructured":"Coleman, S., McKinley, K.S.: Tile size selection using cache organization and data layout. ACM SIGPLAN Not. 30(6), 279\u2013290 (1995)","journal-title":"ACM SIGPLAN Not."},{"key":"17_CR12","doi-asserted-by":"publisher","unstructured":"Dagum, L., Menon, R.: OpenMP: an industry standard API for shared-memory programming. IEEE Comput. Sci. Eng. 5(1), 46\u201355 (1998). https:\/\/doi.org\/10.1109\/99.660313. https:\/\/ieeexplore.ieee.org\/document\/660313\/citations","DOI":"10.1109\/99.660313"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Dahm, J., et al.: Pace v0.2: a python-based performance-portable atmospheric model. Geosci. Model Dev. 16(9), 2719\u20132736 (2023)","DOI":"10.5194\/gmd-16-2719-2023"},{"key":"17_CR14","unstructured":"ECMWF: IFS Documentation CY48R1 - Part IV: Physical Processes (2023). https:\/\/www.ecmwf.int\/en\/elibrary\/81370-ifs-documentation-cy48r1-part-iv-physical-processes"},{"key":"17_CR15","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s11390-020-0741-6","volume":"36","author":"JB Fang","year":"2021","unstructured":"Fang, J.B., Liao, X.K., Huang, C., Dong, D.Z.: Performance evaluation of memory-centric ARMv8 many-core architectures: a case study with phytium 2000+. J. Comput. Sci. Technol. 36, 33\u201343 (2021)","journal-title":"J. Comput. Sci. Technol."},{"issue":"6","key":"17_CR16","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1007\/s11390-021-1251-x","volume":"38","author":"WR Gao","year":"2023","unstructured":"Gao, W.R., Fang, J.B., Huang, C., Xu, C.F., Wang, Z.: wrBench: comparing cache architectures and coherency protocols on ARMv8 many-core systems. J. Comput. Sci. Technol. 38(6), 1323\u20131338 (2023)","journal-title":"J. Comput. Sci. Technol."},{"key":"17_CR17","unstructured":"Hague, J.: IFS Vectorisation Improvements Using Cray Supercomputer (2014)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Hampton, M., Asanovic, K.: Compiling for vector-thread architectures. In: Proceedings of the 6th Annual IEEE\/ACM International Symposium on Code Generation and Optimization, pp. 205\u2013215 (2008)","DOI":"10.1145\/1356058.1356085"},{"issue":"7825","key":"17_CR19","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","volume":"585","author":"CR Harris","year":"2020","unstructured":"Harris, C.R., et al.: Array programming with numpy. Nature 585(7825), 357\u2013362 (2020)","journal-title":"Nature"},{"key":"17_CR20","unstructured":"Kennedy, K., Allen, J.R.: Optimizing compilers for modern architectures: a dependence-based approach. Morgan Kaufmann Publishers Inc. (2001)"},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Lapillonne, X., Osterried, K., Fuhrer, O.: Using openacc to port large legacy climate and weather modeling code to GPUs. In: Parallel Programming with OpenACC, pp. 267\u2013290. Elsevier (2017)","DOI":"10.1016\/B978-0-12-410397-9.00013-5"},{"key":"17_CR22","unstructured":"Martin, S.: DaCe on GPU for Climate and Weather Models Using CLOUDSC as a Case Study. Master\u2019s thesis, ETH Zurich (2023)"},{"issue":"4","key":"17_CR23","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1145\/233561.233564","volume":"18","author":"KS McKinley","year":"1996","unstructured":"McKinley, K.S., Carr, S., Tseng, C.W.: Improving data locality with loop transformations. ACM Trans. Program. Lang. Syst. (TOPLAS) 18(4), 424\u2013453 (1996)","journal-title":"ACM Trans. Program. Lang. Syst. (TOPLAS)"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"M\u00e9ndez, M., Tinetti, F.G., Overbey, J.L.: Climate models: challenges for fortran development tools. In: 2014 Second International Workshop on Software Engineering for High Performance Computing in Computational Science and Engineering, pp. 6\u201312. IEEE (2014)","DOI":"10.1109\/SE-HPCCSE.2014.7"},{"issue":"10","key":"17_CR25","doi-asserted-by":"publisher","first-page":"4425","DOI":"10.5194\/gmd-12-4425-2019","volume":"12","author":"A M\u00fcller","year":"2019","unstructured":"M\u00fcller, A., et al.: The escape project: energy-efficient scalable algorithms for weather prediction at exascale. Geosci. Model Dev. 12(10), 4425\u20134441 (2019)","journal-title":"Geosci. Model Dev."},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Sato, M., et al.: Co-design for a64fx manycore processor and \u201cfugaku\u201d. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201315. IEEE (2020)","DOI":"10.1109\/SC41405.2020.00051"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Sch\u00e4r, C., et al.: Kilometer-scale climate models: prospects and challenges. B. Am. Meteorol. Soc. 101, e567\u2013e587 (2020)","DOI":"10.1175\/BAMS-D-18-0167.1"},{"issue":"1","key":"17_CR28","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MCSE.2018.2888788","volume":"21","author":"TC Schulthess","year":"2018","unstructured":"Schulthess, T.C., Bauer, P., Wedi, N., Fuhrer, O., Hoefler, T., Sch\u00e4r, C.: Reflecting on the goal and baseline for exascale computing: a roadmap based on weather and climate simulations. Comput. Sci. Eng. 21(1), 30\u201341 (2018)","journal-title":"Comput. Sci. Eng."},{"issue":"5","key":"17_CR29","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1145\/301631.301668","volume":"34","author":"Y Song","year":"1999","unstructured":"Song, Y., Li, Z.: New tiling techniques to improve cache temporal locality. ACM SIGPLAN Not. 34(5), 215\u2013228 (1999)","journal-title":"ACM SIGPLAN Not."},{"key":"17_CR30","first-page":"1","volume":"2024","author":"S Ubbiali","year":"2024","unstructured":"Ubbiali, S., et al.: Exploring a high-level programming model for the NWP domain using ECMWF microphysics schemes. Geosci. Model Dev. Discuss. 2024, 1\u201330 (2024)","journal-title":"Geosci. Model Dev. Discuss."},{"issue":"04","key":"17_CR31","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1109\/71.97902","volume":"2","author":"ME Wolf","year":"1991","unstructured":"Wolf, M.E., Lam, M.S.: A loop transformation theory and an algorithm to maximize parallelism. IEEE Trans. Parallel Distrib. Syst. 2(04), 452\u2013471 (1991)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"5","key":"17_CR32","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/MM.2021.3085578","volume":"41","author":"J Xia","year":"2021","unstructured":"Xia, J., Cheng, C., Zhou, X., Hu, Y., Chun, P.: Kunpeng 920: the first 7-nm chiplet-based 64-core arm soc for cloud services. IEEE Micro 41(5), 67\u201375 (2021)","journal-title":"IEEE Micro"}],"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\/978-981-95-8402-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T07:14:59Z","timestamp":1775632499000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8402-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584017","9789819584024"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8402-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"9 April 2026","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":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}