{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T03:31:54Z","timestamp":1769657514001,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":74,"publisher":"ACM","funder":[{"name":"Generalitat de catalunya","award":["2021-SGR-01007"],"award-info":[{"award-number":["2021-SGR-01007"]}]},{"name":"MICIU\\\/AEI\\\/10.13039 \\\/50110001103 and FEDER, UE","award":["CEX2021-001148-S\/MCIN\/AEI\/10.13039\/501100011033"],"award-info":[{"award-number":["CEX2021-001148-S\/MCIN\/AEI\/10.13039\/501100011033"]}]},{"name":"MICIU\\\/AEI\\\/10.13039 \\\/50110001103 and FEDER, UE","award":["PID2023-147979NB-C21"],"award-info":[{"award-number":["PID2023-147979NB-C21"]}]},{"name":"European Union - NextGenerationEU","award":["REGAGE22e00058408992"],"award-info":[{"award-number":["REGAGE22e00058408992"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1,28]]},"DOI":"10.1145\/3774934.3786451","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:25:57Z","timestamp":1769613957000},"page":"53-67","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Rethinking Thread Scheduling under Oversubscription: A User-Space Framework for Coordinating Multi-runtime and Multi-process Workloads"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6715-3605","authenticated-orcid":false,"given":"Aleix","family":"Roca","sequence":"first","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3580-9630","authenticated-orcid":false,"given":"Vicen\u00e7","family":"Beltran","sequence":"additional","affiliation":[{"name":"Barcelona Supercomputing Center, Barcelona, Spain"}]}],"member":"320","published-online":{"date-parts":[[2026,1,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03869-3_80"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.71"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Jan Bierbaum Maksym Planeta and Hermann H\u00e4rtig. 2022. Towards Efficient Oversubscription: On the Cost and Benefit of Event-Based Communication in MPI. In 2022 IEEE\/ACM International Workshop on Runtime and Operating Systems for Supercomputers (ROSS). 1\u201310. https:\/\/doi.org\/10.1109\/ROSS56639.2022.00007 10.1109\/ROSS56639.2022.00007","DOI":"10.1109\/ROSS56639.2022.00007"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/209937.209958"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3187"},{"key":"e_1_3_2_1_6_1","unstructured":"Programming Models Group BSC. 2024. Nanos6 Runtime Main Repository. https:\/\/github.com\/bsc-pm\/nanos6 Accessed: 2024-04-22"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00017"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS64566.2025.00015"},{"key":"e_1_3_2_1_9_1","unstructured":"Linux community. [n. d.]. EEVDF Scheduler \u2014 The Linux Kernel documentation. https:\/\/docs.kernel.org\/scheduler\/sched-eevdf.html"},{"key":"e_1_3_2_1_10_1","unstructured":"Linux Community. 2025. CFS Scheduler \u2014 The Linux Kernel documentation. https:\/\/docs.kernel.org\/scheduler\/sched-design-CFS.html"},{"key":"e_1_3_2_1_11_1","unstructured":"Linux Community. 2025. Extensible Scheduler Class \u2014 The Linux Kernel documentation. https:\/\/docs.kernel.org\/scheduler\/sched-ext.html"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Dave Dice and Alex Kogan. 2019. Avoiding Scalability Collapse by Restricting Concurrency. arxiv:1905.10818.","DOI":"10.1007\/978-3-030-29400-7_26"},{"key":"e_1_3_2_1_13_1","unstructured":"Dave Dice and Alex Kogan. 2021. Intra-process Caching and Reuse of Threads. arXiv preprint arXiv:2105.07497."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.7111"},{"key":"e_1_3_2_1_15_1","volume-title":"The Purely Functional Software Deployment Model. Ph. D. Dissertation","author":"Dolstra Eelco","unstructured":"Eelco Dolstra. 2006. The Purely Functional Software Deployment Model. Ph. D. Dissertation. Utrecht University. Utrecht, The Netherlands."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1088149.1088166"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Jorge Ejarque Rosa M. Badia Lo\u00efc Albertin Giovanni Aloisio Enrico Baglione Yolanda Becerra Stefan Boschert Julian R. Berlin Alessandro D\u2019Anca Donatello Elia Fran\u00e7ois Exertier Sandro Fiore Jos\u00e9 Flich Arnau Folch Steven J. Gibbons Nikolay Koldunov Francesc Lordan Stefano Lorito Finn L\u00f8vholt Jorge Mac\u00edas and Manuela Volpe. 2022. Enabling dynamic and intelligent workflows for HPC data analytics and AI convergence. Sept. issn:1872-7115 https:\/\/doi.org\/10.13039\/501100002347 Accepted: 2023-04-18T11:30:03Z Publisher: Elsevier 10.13039\/501100002347","DOI":"10.13039\/501100002347"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Marta Garcia Gasulla. 2017. Dynamic load balancing for hybrid applications. Universitat Polit\u00e8cnica de Catalunya. https:\/\/doi.org\/10.5821\/dissertation-2117-108227 Accepted: 2017-10-02T00:31:03Z Publication Title: TDX (Tesis Doctorals en Xarxa) 10.5821\/dissertation-2117-108227","DOI":"10.5821\/dissertation-2117-108227"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Bolaji Gbadamosi Luigi Leonardi Tobias Pulls Toke H\u00f8iland-J\u00f8rgensen Simone Ferlin-Reiter Simo Sorce and Anna Brunstr\u00f6m. 2024. The eBPF Runtime in the Linux Kernel. https:\/\/doi.org\/10.48550\/arXiv.2410.00026 arXiv:2410.00026 [cs] 10.48550\/arXiv.2410.00026","DOI":"10.48550\/arXiv.2410.00026"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.15439\/2021F004"},{"key":"e_1_3_2_1_21_1","unstructured":"GNU. [n. d.]. The GNU C Library - GNU Project - Free Software Foundation. https:\/\/www.gnu.org\/software\/libc\/"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"William Gropp Ewing (Rusty) Lusk Rajeev Thakur Pavan Balaji Thomas Gillis Yanfei Guo Rob Latham Ken Raffenetti and Hui Zhou. 2023. MPICH. [Computer Software]. https:\/\/doi.org\/10.11578\/dc.20200514.13 10.11578\/dc.20200514.13","DOI":"10.11578\/dc.20200514.13"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijresmar.2022.05.005"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3431379.3460641"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-020-00361-2"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483542"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470434"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2019.00011"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483548"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731092"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3107775"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-39698-4_15"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2023.3241692"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","unstructured":"Anton Malakhov David Liu Anton Gorshkov and Terry Wilmarth. 2018. Composable Multi-Threading and Multi-Processing for Numeric Libraries. scipy June https:\/\/doi.org\/10.25080\/Majora-4af1f417-003 10.25080\/Majora-4af1f417-003","DOI":"10.25080\/Majora-4af1f417-003"},{"key":"e_1_3_2_1_36_1","unstructured":"man page for shm overview. [n. d.]. shm overview. https:\/\/man7.org\/linux\/man-pages\/man7\/shm_overview.7.html Accessed: 2021-08-07"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/qua.27389"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","unstructured":"Andre Merzky Mikhail Titov Matteo Turilli Ozgur Kilic Tianle Wang and Shantenu Jha. 2025. Scalable Runtime Architecture for Data-driven Hybrid HPC and ML Workflow Applications. https:\/\/doi.org\/10.48550\/arXiv.2503.13343 arXiv:2503.13343 [cs] 10.48550\/arXiv.2503.13343","DOI":"10.48550\/arXiv.2503.13343"},{"key":"e_1_3_2_1_39_1","unstructured":"Antoni Navarro. 2025. bsc-pm\/nodes. https:\/\/github.com\/bsc-pm\/nodes original-date: 2023-04-18T09:43:48Z"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","unstructured":"Poornima Nookala Kyle Chard and Ioan Raicu. 2023. X-Openmp \u2013 Extreme Fine-Grained Tasking Using Lock-Less Work Stealing. https:\/\/doi.org\/10.2139\/ssrn.4639600 10.2139\/ssrn.4639600","DOI":"10.2139\/ssrn.4639600"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34356-9_30"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3656019.3676949"},{"key":"e_1_3_2_1_43_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32 (2019)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2017.69"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.20289"},{"key":"e_1_3_2_1_46_1","unstructured":"Steven J Plimpton Axel Kohlmeyer Aidan P Thompson Stan G Moore and Richard Berger. 2007. LAMMPS: large-scale atomic\/molecular massively parallel simulator. Zenodo."},{"key":"e_1_3_2_1_47_1","first-page":"47","volume-title":"Proceedings of the 13th USENIX conference on Operating Systems Design and Implementation (OSDI\u201918)","author":"Qin Henry","year":"2018","unstructured":"Henry Qin, Qian Li, Jacqueline Speiser, Peter Kraft, and John Ousterhout. 2018. Arachne: core-aware thread management. In Proceedings of the 13th USENIX conference on Operating Systems Design and Implementation (OSDI\u201918). USENIX Association, USA. 145\u2013160. isbn:978-1-931971-47-8"},{"key":"e_1_3_2_1_48_1","unstructured":"Alec Radford Jeff Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners."},{"key":"e_1_3_2_1_49_1","volume-title":"Intel threading building blocks: outfitting C++ for multi-core processor parallelism. \" O\u2019Reilly Media","author":"Reinders James","unstructured":"James Reinders. 2007. Intel threading building blocks: outfitting C++ for multi-core processor parallelism. \" O\u2019Reilly Media, Inc.\"."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28596-8_19"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER49012.2020.00042"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2766062"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.110"},{"key":"e_1_3_2_1_54_1","unstructured":"Ion Stoica and Hussein Abdel-Wahab. 1995. Earliest eligible virtual deadline first: A flexible and accurate mechanism for proportional share resource allocation. Old Dominion Univ. Norfolk VA Tech. Rep. TR-95-22."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-7804-5_31"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3064176.3064180"},{"key":"e_1_3_2_1_57_1","volume-title":"Axel Kohlmeyer, Stan G Moore, Trung Dac Nguyen, et al.","author":"Thompson Aidan P","year":"2022","unstructured":"Aidan P Thompson, H Metin Aktulga, Richard Berger, Dan S Bolintineanu, W Michael Brown, Paul S Crozier, Pieter J In\u2019t Veld, Axel Kohlmeyer, Stan G Moore, Trung Dac Nguyen, et al. 2022. LAMMPS-a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales. Computer physics communications, 271 (2022), 108171."},{"key":"e_1_3_2_1_58_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971.","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","unstructured":"Ioannis Vardas Sascha Hunold Philippe Swartvagher and Jesper Larsson Tr\u00e4ff. 2024. Exploring Mapping Strategies for\u00a0Co-allocated HPC Applications. In Euro-Par 2023: Parallel Processing Workshops Demetris Zeinalipour Dora Blanco Heras George Pallis Herodotos Herodotou Demetris Trihinas Daniel Balouek Patrick Diehl Terry Cojean Karl F\u00fcrlinger Maja Hanne Kirkeby Matteo Nardelli and Pierangelo Di Sanzo (Eds.). Springer Nature Switzerland Cham. 271\u2013276. isbn:978-3-031-48803-0 https:\/\/doi.org\/10.1007\/978-3-031-48803-0_31 10.1007\/978-3-031-48803-0_31","DOI":"10.1007\/978-3-031-48803-0_31"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-97196-9_8"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","unstructured":"Han Wang Linfeng Zhang Jiequn Han and Weinan E. 2018. DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics. Comput. Phys. Comm. 228 (2018) jul 178\u2013184. https:\/\/doi.org\/10.1016\/j.cpc.2018.03.016 10.1016\/j.cpc.2018.03.016","DOI":"10.1016\/j.cpc.2018.03.016"},{"key":"e_1_3_2_1_63_1","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online. 38\u201345","author":"Wolf Thomas","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, R\u00e9mi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander M. Rush. 2020. Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. Association for Computational Linguistics, Online. 38\u201345. https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2018.8547644"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-45550-1_14"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3284219"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3686081.3686118"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2021.02.010"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1063\/5.0155600"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jctc.5c00340"},{"key":"e_1_3_2_1_71_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML\u201923","volume":"40718","author":"Zeng Zhanpeng","year":"2023","unstructured":"Zhanpeng Zeng, Michael Davies, Pranav Pulijala, Karthikeyan Sankaralingam, and Vikas Singh. 2023. LookupFFN: making transformers compute-lite for CPU inference. In Proceedings of the 40th International Conference on Machine Learning (ICML\u201923, Vol. 202). JMLR.org, Honolulu, Hawaii, USA. 40707\u201340718."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.23919\/ICS.2025.3568404"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/NAS63802.2024.10781349"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00035"}],"event":{"name":"PPoPP '26: 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Sydney NSW Australia","acronym":"PPoPP '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 31st ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774934.3786451","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T15:26:14Z","timestamp":1769613974000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774934.3786451"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,28]]},"references-count":74,"alternative-id":["10.1145\/3774934.3786451","10.1145\/3774934"],"URL":"https:\/\/doi.org\/10.1145\/3774934.3786451","relation":{},"subject":[],"published":{"date-parts":[[2026,1,28]]},"assertion":[{"value":"2026-01-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}