{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:40:01Z","timestamp":1759066801238,"version":"3.44.0"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032063427","type":"print"},{"value":"9783032063434","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"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\/978-3-032-06343-4_3","type":"book-chapter","created":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:24:06Z","timestamp":1759065846000},"page":"33-47","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OpenMP Meets I\/O: Portable and\u00a0Runtime-Managed File Tasks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5830-0733","authenticated-orcid":false,"given":"Rodrigo","family":"Ceccato","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2620-0768","authenticated-orcid":false,"given":"Jhonatan","family":"Cl\u00e9to","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6875-1685","authenticated-orcid":false,"given":"Jose M.","family":"Monsalve Diaz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1214-3431","authenticated-orcid":false,"given":"Herv\u00e9","family":"Yviquel","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","unstructured":"Abdulah, S., et al.: Boosting earth system model outputs and saving petabytes in their storage using exascale climate emulators. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2024), pp. 1\u201312 (2024). https:\/\/doi.org\/10.1109\/SC41406.2024.00008","DOI":"10.1109\/SC41406.2024.00008"},{"key":"3_CR2","doi-asserted-by":"publisher","unstructured":"Alverti, C., Karakostas, V., Kunati, N., Goumas, G., Swift, M.: DaxVM: stressing the limits of memory as a file interface. In: 2022 55th IEEE\/ACM International Symposium on Microarchitecture (MICRO), pp. 369\u2013387. IEEE (2022). https:\/\/doi.org\/10.1109\/MICRO56248.2022.00037","DOI":"10.1109\/MICRO56248.2022.00037"},{"key":"3_CR3","doi-asserted-by":"publisher","unstructured":"Antao, S.F., et al.: Offloading support for OpenMP in clang and LLVM. In: 2016 Third Workshop on the LLVM Compiler Infrastructure in HPC (LLVM-HPC), pp. 1\u201311. IEEE (2016). https:\/\/doi.org\/10.1109\/LLVM-HPC.2016.006","DOI":"10.1109\/LLVM-HPC.2016.006"},{"key":"3_CR4","doi-asserted-by":"crossref","unstructured":"Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.A.: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. Concurr. Comput. 23(2), 187\u2013198 (2011). http:\/\/doi.wiley.com\/10.1002\/cpe.1631","DOI":"10.1002\/cpe.1631"},{"key":"3_CR5","unstructured":"Axboe, J.: Efficient I\/O with io_uring (2019). https:\/\/kernel.dk\/io_uring.pdf. Accessed 30 May 2025"},{"key":"3_CR6","doi-asserted-by":"publisher","unstructured":"Bagbaba, A.: A comparative study of MPI-IO libraries for offloading of collective I\/O tasks. In: 2021 International Conference on Engineering and Emerging Technologies (ICEET), pp.\u00a01\u20136. IEEE (2021). https:\/\/doi.org\/10.1109\/ICEET53442.2021.9659767","DOI":"10.1109\/ICEET53442.2021.9659767"},{"key":"3_CR7","doi-asserted-by":"publisher","unstructured":"Bang, J., et al.: An in-depth I\/O pattern analysis in HPC systems. In: 2021 IEEE 28th International Conference on High Performance Computing, Data, and Analytics (HiPC), pp. 400\u2013405 (2021). https:\/\/doi.org\/10.1109\/HiPC53243.2021.00056","DOI":"10.1109\/HiPC53243.2021.00056"},{"key":"3_CR8","doi-asserted-by":"publisher","unstructured":"Bayati, M., Leeser, M., Mi, N.: Exploiting GPU direct access to non-volatile memory to accelerate big data processing. In: 2020 IEEE High Performance Extreme Computing Conference (HPEC), pp.\u00a01\u20136. IEEE (2020). https:\/\/doi.org\/10.1109\/HPEC43674.2020.9286174","DOI":"10.1109\/HPEC43674.2020.9286174"},{"key":"3_CR9","doi-asserted-by":"publisher","unstructured":"Ben-Nun, T., Ates, B., Calotoiu, A., Hoefler, T.: Bridging control-centric and data-centric optimization. In: Proceedings of the 21st ACM\/IEEE International Symposium on Code Generation and Optimization (CGO 2023), pp. 173\u2013185 (2023). https:\/\/doi.org\/10.1145\/3579990.3580018","DOI":"10.1145\/3579990.3580018"},{"key":"3_CR10","doi-asserted-by":"publisher","unstructured":"Bin, H., Gang, X.: Comprehensive analysis of computational and I\/O resource patterns across queues. In: 2024 21st International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), pp.\u00a01\u20137. IEEE (2024). https:\/\/doi.org\/10.1109\/ICCWAMTIP64812.2024.10873682","DOI":"10.1109\/ICCWAMTIP64812.2024.10873682"},{"key":"3_CR11","unstructured":"Board, O.A.R.: OpenMP application programming interface, version 6.0. Technical report, OpenMP Architecture Review Board (2024). https:\/\/www.openmp.org\/wp-content\/uploads\/OpenMP-API-Specification-6-0.pdf. Accessed 14 Nov 2024"},{"key":"3_CR12","doi-asserted-by":"publisher","unstructured":"Carneiro, A.R., Bez, J.L., Osthoff, C., Schnorr, L.M., Navaux, P.O.A.: Uncovering I\/O demands on HPC platforms: peeking under the hood of Santos Dumont. J. Parallel Distrib. Comput. 182(104744), 104744 (2023). https:\/\/doi.org\/10.1016\/j.jpdc.2023.104744","DOI":"10.1016\/j.jpdc.2023.104744"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Ceccato, R., Cl\u00e9to, J., Leite, G., Rigo, S., Diaz, J.M.M., Yviquel, H.: Spinner: enhancing HPC experimentation with a streamlined parameter sweep tool. In: 2024 International Symposium on Computer Architecture and High Performance Computing Workshops (SBAC-PADW), pp. 1\u201311 (2024). https:\/\/ieeexplore.ieee.org\/document\/10764594\/","DOI":"10.1109\/SBAC-PADW64858.2024.00013"},{"key":"3_CR14","doi-asserted-by":"publisher","unstructured":"Chaarawi, M., Gabriel, E.: Automatically selecting the number of aggregators for collective I\/O operations. In: 2011 IEEE International Conference on Cluster Computing, pp. 428\u2013437. IEEE (2011). https:\/\/doi.org\/10.1109\/CLUSTER.2011.79","DOI":"10.1109\/CLUSTER.2011.79"},{"key":"3_CR15","doi-asserted-by":"publisher","unstructured":"Cl\u00e9to, J., Valarini, G., Pereira, M., Araujo, G., Yviquel, H.: Scalable OpenMP remote offloading via asynchronous MPI and coroutine-driven communication. In: Nagel, W.E., Goehringer, D., Diniz, P.C. (eds) Euro-Par 2025. LNCS, vol. 15902, pp. 254\u2013267. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-99872-0_18","DOI":"10.1007\/978-3-031-99872-0_18"},{"key":"3_CR16","doi-asserted-by":"publisher","unstructured":"Dong, B., et al.: Data elevator: low-contention data movement in hierarchical storage system. In: 2016 IEEE 23rd International Conference on High Performance Computing (HiPC), pp. 152\u2013161 (2016). https:\/\/doi.org\/10.1109\/HiPC.2016.026","DOI":"10.1109\/HiPC.2016.026"},{"key":"3_CR17","doi-asserted-by":"publisher","unstructured":"Eisenhauer, G., et al.: HPC I\/O innovations in the exascale era. Int. J. High Perform. Comput. Appl. (2025). https:\/\/doi.org\/10.1177\/10943420251330446","DOI":"10.1177\/10943420251330446"},{"key":"3_CR18","doi-asserted-by":"publisher","unstructured":"Elshazly, H., Ejarque, J., Badia, R.M.: Storage-heterogeneity aware task-based programming models to optimize I\/O intensive applications. IEEE Trans. Parallel Distrib. Syst. 33(12), 3589\u20133599 (2022). https:\/\/doi.org\/10.1109\/TPDS.2022.3161123","DOI":"10.1109\/TPDS.2022.3161123"},{"key":"3_CR19","doi-asserted-by":"publisher","unstructured":"Fox, D., Diaz, J.M., Li, X.: On memory codelets: prefetching, recoding, moving and streaming data (2023). https:\/\/doi.org\/10.48550\/ARXIV.2302.00115","DOI":"10.48550\/ARXIV.2302.00115"},{"key":"3_CR20","doi-asserted-by":"publisher","unstructured":"Godoy, W.F., et al.: ADIOS 2: the adaptable input output system. A framework for high-performance data management. SoftwareX 12 (2020). https:\/\/doi.org\/10.1016\/j.softx.2020.100561","DOI":"10.1016\/j.softx.2020.100561"},{"key":"3_CR21","doi-asserted-by":"publisher","unstructured":"Guo, L., Tang, M., Lee, H., Firoz, J., Tallent, N.R.: Improving I\/O-aware workflow scheduling via data flow characterization and trade-off analysis. In: 2024 IEEE International Conference on Big Data (BigData), pp. 3674\u20133681. IEEE (2024). https:\/\/doi.org\/10.1109\/BigData62323.2024.10825855","DOI":"10.1109\/BigData62323.2024.10825855"},{"key":"3_CR22","unstructured":"Harrington, P., Yoo, W., Sim, A., Wu, K.: Diagnosing parallel I\/O bottlenecks in HPC applications. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2017) (2017). https:\/\/sdm.lbl.gov\/oapapers\/sc17-harrington-poster.pdf"},{"key":"3_CR23","unstructured":"Ivanov, A., Dryden, N., Ben-Nun, T., Li, S., Hoefler, T.: Data movement is all you need: A case study on optimizing transformers. In: Proceedings of Machine Learning and Systems, vol. 3, pp. 711\u2013732 (2021)"},{"issue":"9","key":"3_CR24","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1016\/j.parco.2011.02.002","volume":"37","author":"H Jin","year":"2011","unstructured":"Jin, H., Jespersen, D., Mehrotra, P., Biswas, R., Huang, L., Chapman, B.: High performance computing using MPI and OpenMP on multi-core parallel systems. Parallel Comput. 37(9), 562\u2013575 (2011). https:\/\/doi.org\/10.1016\/j.parco.2011.02.002","journal-title":"Parallel Comput."},{"issue":"11","key":"3_CR25","doi-asserted-by":"publisher","first-page":"2682","DOI":"10.1109\/TPDS.2020.3000458","volume":"31","author":"Q Kang","year":"2020","unstructured":"Kang, Q., et al.: Improving MPI collective I\/O for high volume non-contiguous requests with intra-node aggregation. IEEE Trans. Parallel Distrib. Syst. 31(11), 2682\u20132695 (2020). https:\/\/doi.org\/10.1109\/TPDS.2020.3000458","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"3_CR26","doi-asserted-by":"publisher","unstructured":"Klinkenberg, J., Kraus, J., Terboven, C., M\u00fcller, M.S.: Towards locality-aware host-to-device offloading in OpenMP. In: Espinosa, A., Klemm, M., de\u00a0Supinski, B.R., Cytowski, M., Klinkenberg, J. (eds.) IWOMP 2024. LNCS, vol. 15195, pp. 3\u201315. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72567-8_1","DOI":"10.1007\/978-3-031-72567-8_1"},{"issue":"3","key":"3_CR27","doi-asserted-by":"publisher","first-page":"e0173038","DOI":"10.1371\/journal.pone.0173038","volume":"12","author":"T Liu","year":"2017","unstructured":"Liu, T., Liu, Y., Qian, C., Qian, D.: IOPA: I\/O-aware parallelism adaption for parallel programs. PLoS ONE 12(3), e0173038 (2017). https:\/\/doi.org\/10.1371\/journal.pone.0173038","journal-title":"PLoS ONE"},{"key":"3_CR28","doi-asserted-by":"publisher","first-page":"66917","DOI":"10.1109\/ACCESS.2020.2985928","volume":"8","author":"W Liu","year":"2020","unstructured":"Liu, W., Wu, L., Xu, X.: Topology aware algorithm for two-phase I\/O in clusters with tapered hierarchical networks. IEEE Access 8, 66917\u201366930 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2985928","journal-title":"IEEE Access"},{"key":"3_CR29","unstructured":"Maknee: An intro to deepseek\u2019s distributed file system (2025). https:\/\/maknee.github.io\/blog\/2025\/3FS-Performance-Journal-1\/. Accessed 15 May 2025"},{"key":"3_CR30","doi-asserted-by":"publisher","unstructured":"Maurya, A., Underwood, R., Rafique, M., Cappello, F., Nicolae, B.: DataStates-LLM: lazy asynchronous checkpointing for large language models. In: The 33rd International Symposium on High-Performance Parallel and Distributed Computing (HPDC 2024), Pisa, Italy, vol. 1, no. 1 (2024). https:\/\/doi.org\/10.1145\/3625549.3658685","DOI":"10.1145\/3625549.3658685"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Mehta, K., Gabriel, E.: Multi-threaded parallel I\/O for OpenMP applications. Int. J. Parallel Program. 43(2), 286\u2013309 (2015). https:\/\/www.researchgate.net\/publication\/271658580","DOI":"10.1007\/s10766-014-0306-9"},{"key":"3_CR32","doi-asserted-by":"publisher","unstructured":"Nicolae, B., Moody, A., Gonsiorowski, E., Mohror, K., Cappello, F.: VeloC: towards high performance adaptive asynchronous checkpointing at large scale. In: Proceedings of the IEEE International Parallel and Distributed Processing Symposium (IPDPS 2019), pp. 911\u2013920 (2019). https:\/\/doi.org\/10.1109\/IPDPS.2019.00099","DOI":"10.1109\/IPDPS.2019.00099"},{"key":"3_CR33","doi-asserted-by":"publisher","unstructured":"Oral, S., et al.: End-to-end I\/O portfolio for the summit supercomputing ecosystem. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. ACM, New York (2019). https:\/\/doi.org\/10.1145\/3295500.3356157","DOI":"10.1145\/3295500.3356157"},{"key":"3_CR34","doi-asserted-by":"publisher","unstructured":"Patel, A., Doerfert, J.: Remote OpenMP offloading. In: Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP 2022), PPoPP 2022, pp. 441\u2013442. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3503221.3508416","DOI":"10.1145\/3503221.3508416"},{"key":"3_CR35","doi-asserted-by":"publisher","unstructured":"Ravi, J., Byna, S., Koziol, Q.: GPU direct I\/O with HDF5. In: 2020 IEEE\/ACM Fifth International Parallel Data Systems Workshop (PDSW), pp. 28\u201333. IEEE (2020). https:\/\/doi.org\/10.1109\/PDSW51947.2020.00010","DOI":"10.1109\/PDSW51947.2020.00010"},{"key":"3_CR36","doi-asserted-by":"publisher","unstructured":"Ren, Z., Doekemeijer, K., De\u00a0Matteis, T., Pinto, C., Stoica, R., Trivedi, A.: An I\/O characterizing study of offloading LLM models and KV caches to NVMe SSD. In: Proceedings of the 5th Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems, vol.\u00a01, pp. 23\u201333. ACM, New York (2025). https:\/\/doi.org\/10.1145\/3719330.3721230","DOI":"10.1145\/3719330.3721230"},{"key":"3_CR37","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1007\/978-3-030-28596-8_19","volume-title":"OpenMP: Conquering the Full Hardware Spectrum","author":"A Roca Nonell","year":"2019","unstructured":"Roca Nonell, A., Beltran Querol, V., Mateo Bellido, S.: Introducing the task-aware storage I\/O (TASIO) library. In: Fan, X., de Supinski, B.R., Sinnen, O., Giacaman, N. (eds.) IWOMP 2019. LNCS, vol. 11718, pp. 274\u2013288. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-28596-8_19"},{"key":"3_CR38","doi-asserted-by":"publisher","unstructured":"Shan, H., Antypas, K., Shalf, J.: Characterizing and predicting the I\/O performance of HPC applications using a parameterized synthetic benchmark. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis (SC 2008), vol.\u00a0978, pp. 1\u201312 (2008). https:\/\/doi.org\/10.1145\/1413370.1413413","DOI":"10.1145\/1413370.1413413"},{"key":"3_CR39","doi-asserted-by":"publisher","unstructured":"Tessier, F., Vishwanath, V., Jeannot, E.: TAPIOCA: an I\/O library for optimized topology-aware data aggregation on large-scale supercomputers. In: Proceedings of the IEEE International Conference on Cluster Computing (CLUSTER 2017). IEEE (2017). https:\/\/doi.org\/10.1109\/CLUSTER.2017.80","DOI":"10.1109\/CLUSTER.2017.80"},{"key":"3_CR40","doi-asserted-by":"publisher","unstructured":"Thakur, R., Gropp, W., Lusk, E.: Data sieving and collective I\/O in ROMIO. In: Proceedings of the Seventh Symposium on the Frontiers of Massively Parallel Computation (Frontiers 1999), pp. 182\u2013189. IEEE (1999). https:\/\/doi.org\/10.1109\/FMPC.1999.750599","DOI":"10.1109\/FMPC.1999.750599"},{"key":"3_CR41","doi-asserted-by":"publisher","unstructured":"Wang, Y., Davis, K., Xu, Y., Jiang, S.: IHarmonizer: improving the disk efficiency of I\/O-intensive multithreaded codes. In: 2012 IEEE 26th International Parallel and Distributed Processing Symposium, pp. 921\u2013932. IEEE (2012). https:\/\/doi.org\/10.1109\/IPDPS.2012.87","DOI":"10.1109\/IPDPS.2012.87"},{"key":"3_CR42","doi-asserted-by":"publisher","unstructured":"Yviquel, H., et al.: The OpenMP cluster programming model. In: Workshop Proceedings of the 51st International Conference on Parallel Processing, No. Article 17 in ICPP Workshops 2022, pp. 1\u201311. Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3547276.3548444","DOI":"10.1145\/3547276.3548444"}],"container-title":["Lecture Notes in Computer Science","OpenMP: Balancing Productivity and Performance Portability"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06343-4_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T13:24:08Z","timestamp":1759065848000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06343-4_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"ISBN":["9783032063427","9783032063434"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06343-4_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"assertion":[{"value":"29 September 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":"IWOMP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on OpenMP","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Charlotte, NC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"29 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iwomp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iwomp.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}