{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T23:11:55Z","timestamp":1774998715738,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":62,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,16]]},"DOI":"10.1145\/3712285.3759881","type":"proceedings-article","created":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T16:04:47Z","timestamp":1762963487000},"page":"1043-1059","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["LCI: a Lightweight Communication Interface for Efficient Asynchronous Multithreaded Communication"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6917-5525","authenticated-orcid":false,"given":"Jiakun","family":"Yan","sequence":"first","affiliation":[{"name":"Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, Urbana, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3504-2468","authenticated-orcid":false,"given":"Marc","family":"Snir","sequence":"additional","affiliation":[{"name":"Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign, Urbana, IL, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,11,15]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00008"},{"key":"e_1_3_3_3_3_2","unstructured":"Andrei Alexandrescu and Maged\u00a0M. Michael. 2004. Lock-Free Data Structures with Hazard Pointers. https:\/\/erdani.org\/publications\/cuj-2004-12.pdf"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","unstructured":"Abdelhalim Amer Huiwei Lu Pavan Balaji Milind Chabbi Yanjie Wei Jeff Hammond and Satoshi Matsuoka. 2019-01-08. Lock Contention Management in Multithreaded MPI. ACM Transactions on Parallel Computing 5 3 (2019-01-08) 12:1\u201312:21. 10.1145\/3275443","DOI":"10.1145\/3275443"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2688500.2688522"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00049"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2019.00104"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87475-120"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.71"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3569951.3597559"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-34627-011"},{"key":"e_1_3_3_3_12_2","unstructured":"Dan Bonachea and Jaein Jeong. 2002. GASNet: A portable high-performance communication layer for global address-space languages. CS258 Parallel Computer Architecture Project Spring 31 (2002) 17."},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","unstructured":"George Bosilca Aurelien Bouteiller Anthony Danalis Mathieu Faverge Thomas Herault and Jack\u00a0J. Dongarra. 2013-11. PaRSEC: Exploiting Heterogeneity to Enhance Scalability. Computing in Science & Engineering 15 6 (2013-11) 36\u201345. 10.1109\/MCSE.2013.98","DOI":"10.1109\/MCSE.2013.98"},{"key":"e_1_3_3_3_14_2","unstructured":"ISO C++. [n. d.]. Named Parameter Idiom. https:\/\/isocpp.org\/wiki\/faq\/ctors#named-parameter-idiom"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3330345.3330379"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/2020373.2020375"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Gregor Dai\u00df Patrick Diehl Jiakun Yan John\u00a0K Holmen Rahulkumar Gayatri Christoph Junghans Alexander Straub Jeff\u00a0R Hammond Dominic Marcello Miwako Tsuji et\u00a0al. 2024. Asynchronous-Many-Task Systems: Challenges and Opportunities\u2013Scaling an AMR Astrophysics Code on Exascale machines using Kokkos and HPX. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.15518 (2024).","DOI":"10.1177\/10943420251386503"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/2966884.2966914"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"E.D. Demaine I. Foster C. Kesselman and M. Snir. 2001. Generalized Communicators in the Message Passing Interface. IEEE Transactions on Parallel and Distributed Systems 12 6 (2001) 610\u2013616. 10.1109\/71.932714","DOI":"10.1109\/71.932714"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2488551.2488553"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15646-52"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/1188455.1188483"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00111"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807664"},{"key":"e_1_3_3_3_25_2","volume-title":"Lightweight Threading with MPI Using Persistent Communications Semantics","author":"Grant Ryan","year":"2015","unstructured":"Ryan Grant, Anthony Skjellum, and Purushotham\u00a0V. Bangalore. 2015. Lightweight Threading with MPI Using Persistent Communications Semantics. Technical Report. Sandia National Lab.(SNL-NM), Albuquerque, NM (United States). https:\/\/www.osti.gov\/servlets\/purl\/1328651"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20656-7-17"},{"key":"e_1_3_3_3_27_2","unstructured":"William Gropp Tim Boerner Brett Bode and Greg Bauer. 2023. Delta: Balancing GPU Performance with Advanced System Interfaces. (2023)."},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","unstructured":"Steven Hofmeyr Rob Egan Evangelos Georganas Alex\u00a0C Copeland Robert Riley Alicia Clum Emiley Eloe-Fadrosh Simon Roux Eugene Goltsman Ayd\u0131n Bulu\u00e7 et\u00a0al. 2020. Terabase-scale metagenome coassembly with MetaHipMer. Scientific reports 10 1 (2020) 10689. 10.1038\/s41598-020-67416-5","DOI":"10.1038\/s41598-020-67416-5"},{"key":"e_1_3_3_3_29_2","unstructured":"HPCwire. 2024. Venado: The AI Supercomputer Built to Tackle Science\u2019s Biggest Challenges.https:\/\/www.hpcwire.com\/2024\/09\/16\/venado-the-ai-supercomputer-built-to-tackle-sciences-biggest-challenges\/"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/2597652.2597657"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"Hartmut Kaiser et\u00a0al. 2023. STEllAR-GROUP\/hpx: HPX V1.9.0: The C++ Standard Library for Parallelism and Concurrency. 10.5281\/zenodo.598202","DOI":"10.5281\/zenodo.598202"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","unstructured":"Hartmut Kaiser Patrick Diehl Adrian\u00a0S. Lemoine Bryce\u00a0Adelstein Lelbach Parsa Amini Agust\u00edn Berge John Biddiscombe Steven\u00a0R. Brandt Nikunj Gupta Thomas Heller Kevin Huck Zahra Khatami Alireza Kheirkhahan Auriane Reverdell Shahrzad Shirzad Mikael Simberg Bibek Wagle Weile Wei and Tianyi Zhang. 2020. HPX - The C++ Standard Library for Parallelism and Concurrency. Journal of Open Source Software 5 53 (2020) 2352. 10.21105\/joss.02352","DOI":"10.21105\/joss.02352"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPPS.1996.508060"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/2592798.2592820"},{"key":"e_1_3_3_3_35_2","unstructured":"LLNL. [n. d.]. Lawrence Livermore National Laboratory\u2019s El Capitan verified as world\u2019s fastest supercomputer.https:\/\/www.llnl.gov\/article\/52061\/lawrence-livermore-national-laboratorys-el-capitan-verified-worlds-fastest-supercomputer"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/PAW-ATM49560.2019.00010"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","unstructured":"Dominic\u00a0C Marcello Sagiv Shiber Orsola De\u00a0Marco Juhan Frank Geoffrey\u00a0C Clayton Patrick\u00a0M Motl Patrick Diehl and Hartmut Kaiser. 2021. octo-tiger: a new 3D hydrodynamic code for stellar mergers that uses hpx parallelization. Monthly Notices of the Royal Astronomical Society 504 4 (04 2021) 5345\u20135382. 10.1093\/mnras\/stab937 arXiv:https:\/\/academic.oup.com\/mnras\/article-pdf\/504\/4\/5345\/37975469\/stab937.pdf","DOI":"10.1093\/mnras\/stab937"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605642"},{"key":"e_1_3_3_3_39_2","first-page":"561","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18)","author":"Moritz Philipp","year":"2018","unstructured":"Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael\u00a0I. Jordan, and Ion Stoica. 2018. Ray: A Distributed Framework for Emerging AI Applications. In 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 18). USENIX Association, Carlsbad, CA, 561\u2013577. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/moritz"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442527"},{"key":"e_1_3_3_3_41_2","unstructured":"NVIDIA. 2019. Getting Started with CUDA Graphs. https:\/\/developer.nvidia.com\/blog\/cuda-graphs\/"},{"key":"e_1_3_3_3_42_2","unstructured":"NVIDIA. 2025. RDMA Aware Networks Programming User Manual. https:\/\/docs.nvidia.com\/networking\/display\/rdmaawareprogrammingv17"},{"key":"e_1_3_3_3_43_2","unstructured":"OFI Working\u00a0Group (OFIWG). 2024. Libfabric Programmer\u2019s Manual."},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2019.8891015"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","unstructured":"Joseph Schuchart Philipp Samfass Christoph Niethammer Jos\u00e9 Gracia and George Bosilca. 2021-09-01. Callback-Based Completion Notification Using MPI Continuations. Parallel Comput. 106 (2021-09-01) 102793. 10.1016\/j.parco.2021.102793","DOI":"10.1016\/j.parco.2021.102793"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2015.13"},{"key":"e_1_3_3_3_47_2","volume-title":"MPI\u2013the Complete Reference: the MPI core","author":"Snir Marc","year":"1998","unstructured":"Marc Snir. 1998. MPI\u2013the Complete Reference: the MPI core. Vol.\u00a01. MIT press."},{"key":"e_1_3_3_3_48_2","unstructured":"Marc Snir Hoang-Vu Dang Omri Mor and Jiakun Yan. 2023. LCI: A Lightweight Communication Interface v1.7. https:\/\/github.com\/uiuc-hpc\/LC\/blob\/icpp23\/doc\/LCI.pdf"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.45"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581784.3607103"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-61763-8_11"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3437359.3465588"},{"key":"e_1_3_3_3_53_2","unstructured":"Philippe Swartvagher. 2022. On the Interactions between HPC Task-based Runtime Systems and Communication Libraries. Ph.\u00a0D. Dissertation. Universit\u00e9 de Bordeaux."},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624598"},{"key":"e_1_3_3_3_55_2","unstructured":"Jiakun Yan Hartmut Kaiser and Marc Snir. 2025. Understanding the Communication Needs of Asynchronous Many-Task Systems\u2013A Case Study of HPX+ LCI. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.12774 (2025)."},{"key":"e_1_3_3_3_56_2","unstructured":"Jiakun Yan and Marc Snir. 2025. Contemplating a Lightweight Communication Interface for Asynchronous Many-Task Systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.15400 (2025)."},{"key":"e_1_3_3_3_57_2","series-title":"(EuroMPI\/USA \u201925)","volume-title":"Recent Advances in the Message Passing Interface","author":"Yan Jiakun","year":"2025","unstructured":"Jiakun Yan, Marc Snir, and Yanfei Guo. 2025. Examining MPI and its Extensions for Asynchronous Multithreaded Communication. In Recent Advances in the Message Passing Interface (Charlotte, NC, USA) (EuroMPI\/USA \u201925). Springer Nature Switzerland."},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41404.2022.00082"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2018.8645059"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392773"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","unstructured":"Rohit Zambre Damodar Sahasrabudhe Hui Zhou Martin Berzins Aparna Chandramowlishwaran and Pavan Balaji. 2021. Logically Parallel Communication for Fast MPI+Threads Applications. IEEE Transactions on Parallel and Distributed Systems 32 12 (2021) 3038\u20133052. 10.1109\/TPDS.2021.3075157","DOI":"10.1109\/TPDS.2021.3075157"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3555819.3555820"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC59590.2023.10507290"}],"event":{"name":"SC '25: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis MO USA","acronym":"SC '25","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712285.3759881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T18:46:20Z","timestamp":1773254780000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712285.3759881"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,15]]},"references-count":62,"alternative-id":["10.1145\/3712285.3759881","10.1145\/3712285"],"URL":"https:\/\/doi.org\/10.1145\/3712285.3759881","relation":{},"subject":[],"published":{"date-parts":[[2025,11,15]]},"assertion":[{"value":"2025-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}