{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T13:21:09Z","timestamp":1769347269958,"version":"3.49.0"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032076113","type":"print"},{"value":"9783032076120","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"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\/978-3-032-07612-0_11","type":"book-chapter","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T17:57:31Z","timestamp":1763920651000},"page":"135-147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Automatically Parallelizing Batch Inference on\u00a0Deep Neural Networks Using Fiats and\u00a0Fortran 2023 \u201cDo Concurrent\u201d"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2344-868X","authenticated-orcid":false,"given":"Damian","family":"Rouson","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3092-0903","authenticated-orcid":false,"given":"Zhe","family":"Bai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0724-9349","authenticated-orcid":false,"given":"Dan","family":"Bonachea","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6326-8664","authenticated-orcid":false,"given":"Kareem","family":"Ergawy","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4077-3430","authenticated-orcid":false,"given":"Ethan","family":"Gutmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8634-4634","authenticated-orcid":false,"given":"Michael","family":"Klemm","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7974-1853","authenticated-orcid":false,"given":"Katherine","family":"Rasmussen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3205-2169","authenticated-orcid":false,"given":"Brad","family":"Richardson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2592-669X","authenticated-orcid":false,"given":"Sameer","family":"Shende","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2469-5284","authenticated-orcid":false,"given":"David","family":"Torres","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3182-9296","authenticated-orcid":false,"given":"Yunhao","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"11_CR1","doi-asserted-by":"publisher","unstructured":"Austin, B., et\u00a0al.: NERSC-10 Workload Analysis (2020). https:\/\/doi.org\/10.25344\/S4N30W","DOI":"10.25344\/S4N30W"},{"key":"11_CR2","unstructured":"Bai, Z., Wan, H., Hassan, T., Zhang, K., Almgren, A.: Deep learning based aerosol microphysics surrogate model for E3SM. AGU24 (2024)"},{"key":"11_CR3","doi-asserted-by":"publisher","unstructured":"Caplan, R.M., Stulajter, M.M., et\u00a0al.: Portability of Fortran\u2019s \u2018do concurrent\u2019 on GPUs. In: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1904\u20131913 (2024). https:\/\/doi.org\/10.1109\/SCW63240.2024.00240","DOI":"10.1109\/SCW63240.2024.00240"},{"key":"11_CR4","doi-asserted-by":"publisher","unstructured":"Curcic, M.: A parallel Fortran framework for neural networks and deep learning. In: ACM SIGPLAN Fortran Forum, vol. 38, no. 1, pp. 4\u201321. ACM, New York (2019). https:\/\/doi.org\/10.1145\/3323057.3323059","DOI":"10.1145\/3323057.3323059"},{"key":"11_CR5","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1016\/j.jcp.2015.05.020","volume":"297","author":"S Garain","year":"2015","unstructured":"Garain, S., Balsara, D.S., Reid, J.: Comparing Coarray Fortran (CAF) with MPI for several structured mesh PDE applications. J. Comput. Phys. 297, 237\u2013253 (2015). https:\/\/doi.org\/10.1016\/j.jcp.2015.05.020","journal-title":"J. Comput. Phys."},{"key":"11_CR6","doi-asserted-by":"publisher","unstructured":"Hammond, J.R., Deakin, T., Cownie, J., McIntosh-Smith, S.: Benchmarking Fortran do concurrent on CPUs and GPUs using BabelStream. In: 2022 IEEE\/ACM International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS), pp. 82\u201399. IEEE (2022). https:\/\/doi.org\/10.1109\/PMBS56514.2022.00013","DOI":"10.1109\/PMBS56514.2022.00013"},{"key":"11_CR7","unstructured":"Institute of Computing for Climate Science at the University of Cambridge: Fortran-TF-Lib. https:\/\/github.com\/Cambridge-ICCS\/fortran-tf-lib"},{"key":"11_CR8","unstructured":"Institute of Computing for Climate Science at the University of Cambridge: FTorch. https:\/\/github.com\/Cambridge-ICCS\/FTorch"},{"key":"11_CR9","unstructured":"Lawrence Berkeley National Laboratory: Fiats: Functional inference and training for surrogates. https:\/\/go.lbl.gov\/fiats"},{"key":"11_CR10","unstructured":"Lawrence Berkeley National Laboratory (LBNL), Computer Languages and Systems Software (CLaSS) Group: Fortran at LBNL. https:\/\/fortran.lbl.gov\/"},{"key":"11_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2025.113788","volume":"252","author":"S Maqbool","year":"2025","unstructured":"Maqbool, S., Lee, B.J.: High performance additive manufacturing phase field simulation: Fortran do concurrent vs OpenMP. Comput. Mater. Sci. 252, 113788 (2025). https:\/\/doi.org\/10.1016\/j.commatsci.2025.113788","journal-title":"Comput. Mater. Sci."},{"key":"11_CR12","unstructured":"National Energy Research Scientific Computing (NERSC): Perlmutter Architecture. https:\/\/docs.nersc.gov\/systems\/perlmutter\/architecture\/"},{"key":"11_CR13","unstructured":"neural-fortran. https:\/\/github.com\/modern-fortran\/neural-fortran"},{"key":"11_CR14","unstructured":"Nvidia Corporation: TorchFort. https:\/\/github.com\/NVIDIA\/TorchFort"},{"key":"11_CR15","doi-asserted-by":"publisher","unstructured":"Paszke, A., Gross, S., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019). https:\/\/doi.org\/10.48550\/arxiv.1912.01703","DOI":"10.48550\/arxiv.1912.01703"},{"key":"11_CR16","doi-asserted-by":"publisher","unstructured":"Preissl, R., Wichmann, N., Long, B., Shalf, J., Ethier, S., Koniges, A.: Multithreaded global address space communication techniques for gyrokinetic fusion applications on ultra-scale platforms. In: Proceedings of 2011 International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201311 (2011). https:\/\/doi.org\/10.1145\/2063384.2063404","DOI":"10.1145\/2063384.2063404"},{"key":"11_CR17","doi-asserted-by":"publisher","unstructured":"Rouson, D., Bonachea, D.: Caffeine: Coarray Fortran framework of efficient interfaces to network environments. In: 2022 IEEE\/ACM Eighth Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC), pp. 34\u201342. IEEE (2022). https:\/\/doi.org\/10.25344\/S4459B","DOI":"10.25344\/S4459B"},{"key":"11_CR18","doi-asserted-by":"publisher","unstructured":"Rouson, D., Gutmann, E.D., Fanfarillo, A., Friesen, B.: Performance portability of an intermediate-complexity atmospheric research model in coarray Fortran. In: Proceedings of the Second Annual PGAS Applications Workshop, pp.\u00a01\u20134 (2017). https:\/\/doi.org\/10.1145\/3144779.3169104","DOI":"10.1145\/3144779.3169104"},{"key":"11_CR19","doi-asserted-by":"publisher","unstructured":"Stulajter, M.M., Caplan, R.M., Linker, J.A.: Can Fortran\u2019s \u2018do concurrent\u2019 replace directives for accelerated computing? In: International Workshop on Accelerator Programming Using Directives, pp. 3\u201321. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-97759-7_1","DOI":"10.1007\/978-3-030-97759-7_1"},{"issue":"99","key":"11_CR20","doi-asserted-by":"publisher","first-page":"6492","DOI":"10.21105\/joss.06492","volume":"9","author":"NT Taylor","year":"2024","unstructured":"Taylor, N.T.: Athena: a Fortran package for neural networks. J. Open Source Softw. 9(99), 6492 (2024). https:\/\/doi.org\/10.21105\/joss.06492","journal-title":"J. Open Source Softw."}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-07612-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T18:02:36Z","timestamp":1763920956000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-07612-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"ISBN":["9783032076113","9783032076120"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-07612-0_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]},"assertion":[{"value":"24 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","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":"10 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"40","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}