{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T18:45:31Z","timestamp":1782499531864,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T00:00:00Z","timestamp":1782604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["OAC-2514054"],"award-info":[{"award-number":["OAC-2514054"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2450093"],"award-info":[{"award-number":["CNS-2450093"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2405142"],"award-info":[{"award-number":["CCF-2405142"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CCF-2412182"],"award-info":[{"award-number":["CCF-2412182"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-NA-0003966"],"award-info":[{"award-number":["DE-NA-0003966"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-NA-0003525"],"award-info":[{"award-number":["DE-NA-0003525"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"DOE U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-NA-0004267"],"award-info":[{"award-number":["DE-NA-0004267"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3815572.3815748","type":"proceedings-article","created":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:44:02Z","timestamp":1782495842000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Kokkos Comm: Performance Portable Communication for Distributed Kokkos Applications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0768-4243","authenticated-orcid":false,"given":"C. Nicole","family":"Avans","sequence":"first","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, New Mexico, USA and Tennessee Technological University, Cookeville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8499-0783","authenticated-orcid":false,"given":"Gabriel","family":"Dos Santos","sequence":"additional","affiliation":[{"name":"CEA, Arpajon, France and Universit\u00e9 Paris-Saclay, Arpajon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7730-9239","authenticated-orcid":false,"given":"C\u00e9dric","family":"Chevalier","sequence":"additional","affiliation":[{"name":"CEA, Arpajon, France and Universit\u00e9 Paris-Saclay, Arpajon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3902-9313","authenticated-orcid":false,"given":"Hugo","family":"Taboada","sequence":"additional","affiliation":[{"name":"CEA, Arpajon, France and Universit\u00e9 Paris-Saclay, Arpajon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1615-2749","authenticated-orcid":false,"given":"Marc","family":"P\u00e9rache","sequence":"additional","affiliation":[{"name":"CEA, Arpajon, France and Universit\u00e9 Paris-Saclay, Arpajon, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5141-9176","authenticated-orcid":false,"given":"Matthew G. F.","family":"Dosanjh","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6247-8980","authenticated-orcid":false,"given":"Stephen L.","family":"Olivier","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6481-970X","authenticated-orcid":false,"given":"Carl","family":"Pearson","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Albuquerque, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8210-8992","authenticated-orcid":false,"given":"Evan D.","family":"Suggs","sequence":"additional","affiliation":[{"name":"Tennessee Technological University, Cookeville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4687-1226","authenticated-orcid":false,"given":"Vivek","family":"Kale","sequence":"additional","affiliation":[{"name":"Sandia National Laboratories, Livermore, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5252-6600","authenticated-orcid":false,"given":"Anthony","family":"Skjellum","sequence":"additional","affiliation":[{"name":"Tennessee Technological University, Cookeville, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Advanced Micro Devices Inc. 2025. HIP Programming Guide. https:\/\/rocm.docs.amd.com\/projects\/HIP\/en\/docs-5.7.1\/user_guide\/programming_manual.html"},{"key":"e_1_3_2_1_2_1","unstructured":"Advanced Micro Devices Inc. (AMD). 2024. ROCm Communication Collectives Library (RCCL). https:\/\/rocm.docs.amd.com\/projects\/rccl\/en\/latest\/index.html Version 2.27.7."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"C. Nicole Avans Alfredo A. Correa Sayan Ghosh Matthias Schimek Joseph Schuchart Anthony Skjellum Evan D. Suggs and Tim Niklas Uhl. 2025. Concepts for Designing Modern C++ Interfaces for MPI. 19 pages. doi:10.1007\/978-3-032-07194-1_10","DOI":"10.1007\/978-3-032-07194-1_10"},{"key":"e_1_3_2_1_4_1","unstructured":"Heiko Bauke. 2015. MPL - A message passing library. https:\/\/github.com\/rabauke\/mpl"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/P3HPC49587.2019.00012"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3731599.3767394"},{"key":"e_1_3_2_1_7_1","unstructured":"Amanda Bienz Derek Schafer and Anthony Skjellum. 2023. MPI Advance : Open-Source Message Passing Optimizations. arXiv:2309.07337 [cs.DC] https:\/\/arxiv.org\/abs\/2309.07337"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3416315.3416321"},{"key":"e_1_3_2_1_9_1","volume-title":"Bangalore","author":"Bridges Patrick G.","year":"2024","unstructured":"Patrick G. Bridges, Anthony Skjellum, Evan D. Suggs, Derek Schafer, and Purushotham V. Bangalore. 2024. Understanding GPU Triggering APIs for MPI+X Communication. arXiv:2406.05594 [cs.DC] https:\/\/arxiv.org\/abs\/2406.05594"},{"key":"e_1_3_2_1_10_1","unstructured":"Alexandra Carpen-Amarie Sascha Hunold and Jesper Larsson Tr\u00e4ff. 2016. MPI Derived Datatypes: Performance Expectations and Status Quo. arXiv:1607.00178 [cs.DC] https:\/\/arxiv.org\/abs\/1607.00178"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3624062.3624153"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTI.2015.15"},{"key":"e_1_3_2_1_13_1","volume-title":"Lee Howes, Kirk Shoop, Michael Garland, Eric Niebler, and Bryce Adelstein Lelbach.","author":"Dominiak Micha\u0142","year":"2024","unstructured":"Micha\u0142 Dominiak, Georgy Evtushenko, Lewis Baker, Lucian Radu Teodorescu, Lee Howes, Kirk Shoop, Michael Garland, Eric Niebler, and Bryce Adelstein Lelbach. 2024. P2300R10: stdr.execution. https:\/\/www.open-std.org\/jtc1\/sc22\/wg21\/docs\/papers\/2024\/p2300r10.html"},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings, 11th European PVM\/MPI Users' Group Meeting","author":"Gabriel Edgar","unstructured":"Edgar Gabriel, GrahamE. Fagg, George Bosilca, Thara Angskun, Jack J. Dongarra, Jeffrey M. Squyres, Vishal Sahay, Prabhanjan Kambadur, Brian Barrett, Andrew Lumsdaine, Ralph H. Castain, David J. Daniel, Richard L. Graham, and Timothy S. Woodall. 2004. Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation. In Proceedings, 11th European PVM\/MPI Users' Group Meeting. Budapest, Hungary, 97\u2013104."},{"key":"e_1_3_2_1_15_1","volume-title":"Finepoints: Partitioned Multithreaded MPI Communication","author":"Grant Ryan E.","year":"2019","unstructured":"Ryan E. Grant, Matthew G. F. Dosanjh, Michael J. Levenhagen, Ron Brightwell, and Anthony Skjellum. 2019. Finepoints: Partitioned Multithreaded MPI Communication. In High Performance Computing, Mich\u00e8le Weiland, Guido Juckeland, Carsten Trinitis, and Ponnuswamy Sadayappan (Eds.). Springer International Publishing, Cham, 330\u2013350."},{"key":"e_1_3_2_1_16_1","volume-title":"Using MPI-2: Advanced Features of the Message Passing Interface","author":"Gropp William","unstructured":"William Gropp, Rajeev Thakur, and Ewing Lusk. 1999. Using MPI-2: Advanced Features of the Message Passing Interface (2nd ed.). MIT Press, Cambridge, MA, USA.","edition":"2"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3225058.3225114"},{"key":"e_1_3_2_1_18_1","unstructured":"Intel Corp. 2024. Intel MPI Library Developer Reference for Linux: GPU Buffers Support. https:\/\/www.intel.com\/content\/www\/us\/en\/docs\/mpi-library\/developer-reference-linux\/2021-12\/gpu-buffers-support.html#GUID-43A895E2-0FAC-4166-944C-67D5DE15A31C"},{"key":"e_1_3_2_1_19_1","unstructured":"Sandia National Laboratories. 2024. Kokkos Tools. https:\/\/github.com\/kokkos\/kokkos-tools Accessed: 2024-08-29."},{"key":"e_1_3_2_1_20_1","unstructured":"Lawrence Livermore National Laboratory. 2025. LLNL\/RAJA. https:\/\/github.com\/LLNL\/RAJA"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356176"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/Cluster48925.2021.00028"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid59990.2024.00013"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"A. Matthes R. Widera E. Zenker B. Worpitz A. Huebl and M. Bussmann. 2017. Tuning and optimization for a variety of many-core architectures without changing a single line of implementation code using the Alpaka library. arXiv:1706.10086 https:\/\/arxiv.org\/abs\/1706.10086","DOI":"10.1007\/978-3-319-67630-2_36"},{"key":"e_1_3_2_1_25_1","unstructured":"Message Passing Interface Forum.2025. MPI: A Message-Passing Interface Standard Version 5.0. https:\/\/www.mpi-forum.org\/docs\/mpi-5.0\/mpi50-report.pdf"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/SBAC-PAD55451.2022.00038"},{"key":"e_1_3_2_1_27_1","volume-title":"Larry Kaplan, and Mark Pagel.","author":"Namashivayam Naveen","year":"2023","unstructured":"Naveen Namashivayam, Krishna Kandalla, James B White III, Larry Kaplan, and Mark Pagel. 2023. Exploring Fully Offloaded GPU Stream-Aware Message Passing. arXiv:2306.15773 [cs.DC] https:\/\/arxiv.org\/abs\/2306.15773"},{"key":"e_1_3_2_1_28_1","unstructured":"NVIDIA Corporation. 2024. NVIDIA Collective Communications Library (NCCL). https:\/\/developer.nvidia.com\/nccl Version 2.22.3."},{"key":"e_1_3_2_1_29_1","unstructured":"NVIDIA Corporation. 2025. CUDA C++ Programming Guide. NVIDIA. https:\/\/docs.nvidia.com\/cuda\/cuda-c-programming-guide\/"},{"key":"e_1_3_2_1_30_1","unstructured":"Ohio State University. [n.d.]. MVAPICH: Benchmarks. https:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/."},{"key":"e_1_3_2_1_31_1","unstructured":"OpenFabrics Interfaces Working Group. 2024. libfabric: High-Performance Fabric Interface. https:\/\/ofiwg.github.io\/libfabric Version 1.22.0."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 31st European MPI Users' Group Meeting (EuroMPI\/Australia '24)","author":"Santos Gabriel Dos","year":"2024","unstructured":"Gabriel Dos Santos, C. Nicole Avans, C\u00e9dric Chevalier, Hugo Taboada, Carl W. Pearson, Jan Ciesko, Stephen L. Olivier, and Marc P\u00e9rache. 2024. KokkosComm: Communication Layer for Distributed Kokkos Applications. In Proceedings of the 31st European MPI Users' Group Meeting (EuroMPI\/Australia '24). https:\/\/events.asc.ac.at\/event\/123\/attachments\/86\/344\/EuroMPI%202024%20Short%20Paper%20-%20KokkosComm_%20Communication%20Layer%20for%20Distributed%20Kokkos%20Applications.pdf"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER59342.2025.11186498"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ExaMPI54564.2021.00008"},{"key":"e_1_3_2_1_35_1","volume-title":"ExaMPI: A Modern Design and Implementation to Accelerate Message Passing Interface Innovation","author":"Skjellum Anthony","unstructured":"Anthony Skjellum, Martin R\u00fcfenacht, Nawrin Sultana, Derek Schafer, Ignacio Laguna, and Kathryn Mohror. 2020. ExaMPI: A Modern Design and Implementation to Accelerate Message Passing Interface Innovation. In High Performance Computing, Juan Luis Crespo-Mari\u00f1o and Esteban Meneses-Rojas (Eds.). Springer International Publishing, Cham, 153\u2013169."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3615318.3615321"},{"key":"e_1_3_2_1_37_1","unstructured":"The Teuchos Project Team. 2020. The Teuchos Project Website. https:\/\/trilinos.github.io\/teuchos.html"},{"key":"e_1_3_2_1_38_1","unstructured":"The Trilinos Project Team. 2020. The Trilinos Project Website. https:\/\/trilinos.github.io"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3097283"},{"key":"e_1_3_2_1_40_1","unstructured":"UCX Consortium. 2024. Unified Communication X (UCX). https:\/\/openucx.org\/documentation\/ Version 1.17.0."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC41406.2024.00050"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236367.3236378"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3555819.3555820"}],"event":{"name":"PASC '26: Platform for Advanced Scientific Computing Conference","location":"Bern Switzerland","acronym":"PASC '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the Platform for Advanced Scientific Computing Conference"],"original-title":[],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T17:45:42Z","timestamp":1782495942000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3815572.3815748"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,28]]},"references-count":43,"alternative-id":["10.1145\/3815572.3815748","10.1145\/3815572"],"URL":"https:\/\/doi.org\/10.1145\/3815572.3815748","relation":{},"subject":[],"published":{"date-parts":[[2026,6,28]]},"assertion":[{"value":"2026-06-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}